Hugging Face's logo

lemingshen
/
GPIoT_Code_Generation

Safetensors
Model card Files Community
lemingshen commited on
Commit
6f11f76
·
1 Parent(s): 83ab3b0

new model

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. README.md +6 -0
  2. adapter_config.json +29 -0
  3. adapter_model.safetensors +3 -0
  4. checkpoint-1000/README.md +202 -0
  5. checkpoint-1000/adapter_config.json +29 -0
  6. checkpoint-1000/adapter_model.safetensors +3 -0
  7. checkpoint-1000/optimizer.pt +3 -0
  8. checkpoint-1000/rng_state.pth +3 -0
  9. checkpoint-1000/scheduler.pt +3 -0
  10. checkpoint-1000/special_tokens_map.json +24 -0
  11. checkpoint-1000/tokenizer.json +0 -0
  12. checkpoint-1000/tokenizer.model +3 -0
  13. checkpoint-1000/tokenizer_config.json +43 -0
  14. checkpoint-1000/trainer_state.json +313 -0
  15. checkpoint-1000/training_args.bin +3 -0
  16. checkpoint-10000/README.md +202 -0
  17. checkpoint-10000/adapter_config.json +29 -0
  18. checkpoint-10000/adapter_model.safetensors +3 -0
  19. checkpoint-10000/optimizer.pt +3 -0
  20. checkpoint-10000/rng_state.pth +3 -0
  21. checkpoint-10000/scheduler.pt +3 -0
  22. checkpoint-10000/special_tokens_map.json +24 -0
  23. checkpoint-10000/tokenizer.json +0 -0
  24. checkpoint-10000/tokenizer.model +3 -0
  25. checkpoint-10000/tokenizer_config.json +43 -0
  26. checkpoint-10000/trainer_state.json +2833 -0
  27. checkpoint-10000/training_args.bin +3 -0
  28. checkpoint-10200/README.md +202 -0
  29. checkpoint-10200/adapter_config.json +29 -0
  30. checkpoint-10200/adapter_model.safetensors +3 -0
  31. checkpoint-10200/optimizer.pt +3 -0
  32. checkpoint-10200/rng_state.pth +3 -0
  33. checkpoint-10200/scheduler.pt +3 -0
  34. checkpoint-10200/special_tokens_map.json +24 -0
  35. checkpoint-10200/tokenizer.json +0 -0
  36. checkpoint-10200/tokenizer.model +3 -0
  37. checkpoint-10200/tokenizer_config.json +43 -0
  38. checkpoint-10200/trainer_state.json +2889 -0
  39. checkpoint-10200/training_args.bin +3 -0
  40. checkpoint-10400/README.md +202 -0
  41. checkpoint-10400/adapter_config.json +29 -0
  42. checkpoint-10400/adapter_model.safetensors +3 -0
  43. checkpoint-10400/optimizer.pt +3 -0
  44. checkpoint-10400/rng_state.pth +3 -0
  45. checkpoint-10400/scheduler.pt +3 -0
  46. checkpoint-10400/special_tokens_map.json +24 -0
  47. checkpoint-10400/tokenizer.json +0 -0
  48. checkpoint-10400/tokenizer.model +3 -0
  49. checkpoint-10400/tokenizer_config.json +43 -0
  50. checkpoint-10400/trainer_state.json +2945 -0
README.md CHANGED
@@ -1,3 +1,9 @@
1
  ---
2
  license: mit
3
  ---
 
 
 
 
 
 
 
1
  ---
2
  license: mit
3
  ---
4
+
5
+ # GPIoT: Tailoring Small Language Models for IoT Program Synthesis and Development
6
+ - Foundation model: Llama-2-13b-chat-hf
7
+ - LoRA fine tuned with INT8 quantization
8
+
9
+ ### Feel free to choose any checkpoint
adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Llama-2-13b-chat-hf",
5
+ "bias": "lora_only",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.001,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 64,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "v_proj",
24
+ "q_proj"
25
+ ],
26
+ "task_type": "CAUSAL_LM",
27
+ "use_dora": false,
28
+ "use_rslora": false
29
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3494d6950ca9dc47e47f86f730f4acb8a6d91ca1af99effc22af2d0e8589103b
3
+ size 209736952
checkpoint-1000/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Llama-2-13b-chat-hf
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.12.0
checkpoint-1000/adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Llama-2-13b-chat-hf",
5
+ "bias": "lora_only",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.001,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 64,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "v_proj",
24
+ "q_proj"
25
+ ],
26
+ "task_type": "CAUSAL_LM",
27
+ "use_dora": false,
28
+ "use_rslora": false
29
+ }
checkpoint-1000/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56758d6ac3dd95bd2d82f4f0d0830e56b859d87aa193307dcfaec60736634a48
3
+ size 209736952
checkpoint-1000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee8dbf9c8cd9b2103fdefc7c2b1aded9edbb981943bdfe768ad6513d50af65fe
3
+ size 419529285
checkpoint-1000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efbef5f2e99e032e7a90490381f3317a6e67e04dd91b4746e33558937294eb87
3
+ size 14575
checkpoint-1000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:182d8c7b52a37e75073fb833cdb6cf257619727d9ad268099f8c9eba2d88f121
3
+ size 627
checkpoint-1000/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
checkpoint-1000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1000/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
checkpoint-1000/tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "bos_token": "<s>",
32
+ "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": false,
36
+ "model_max_length": 1000000000000000019884624838656,
37
+ "pad_token": "</s>",
38
+ "padding_side": "right",
39
+ "sp_model_kwargs": {},
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
+ }
checkpoint-1000/trainer_state.json ADDED
@@ -0,0 +1,313 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.22586109542631283,
5
+ "eval_steps": 500,
6
+ "global_step": 1000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.00564652738565782,
13
+ "grad_norm": 0.0635828971862793,
14
+ "learning_rate": 1.2531328320802006e-05,
15
+ "loss": 1.3836,
16
+ "step": 25
17
+ },
18
+ {
19
+ "epoch": 0.01129305477131564,
20
+ "grad_norm": 0.2005225569009781,
21
+ "learning_rate": 2.506265664160401e-05,
22
+ "loss": 1.6497,
23
+ "step": 50
24
+ },
25
+ {
26
+ "epoch": 0.01693958215697346,
27
+ "grad_norm": 0.07235410064458847,
28
+ "learning_rate": 3.759398496240601e-05,
29
+ "loss": 1.1768,
30
+ "step": 75
31
+ },
32
+ {
33
+ "epoch": 0.02258610954263128,
34
+ "grad_norm": 0.17648495733737946,
35
+ "learning_rate": 5.012531328320802e-05,
36
+ "loss": 1.2146,
37
+ "step": 100
38
+ },
39
+ {
40
+ "epoch": 0.028232636928289104,
41
+ "grad_norm": 0.06953724473714828,
42
+ "learning_rate": 6.265664160401002e-05,
43
+ "loss": 0.8725,
44
+ "step": 125
45
+ },
46
+ {
47
+ "epoch": 0.03387916431394692,
48
+ "grad_norm": 0.12059248238801956,
49
+ "learning_rate": 7.518796992481203e-05,
50
+ "loss": 0.7548,
51
+ "step": 150
52
+ },
53
+ {
54
+ "epoch": 0.039525691699604744,
55
+ "grad_norm": 0.0689113661646843,
56
+ "learning_rate": 8.771929824561403e-05,
57
+ "loss": 0.7917,
58
+ "step": 175
59
+ },
60
+ {
61
+ "epoch": 0.04517221908526256,
62
+ "grad_norm": 0.16621273756027222,
63
+ "learning_rate": 0.00010025062656641604,
64
+ "loss": 0.6985,
65
+ "step": 200
66
+ },
67
+ {
68
+ "epoch": 0.050818746470920384,
69
+ "grad_norm": 0.07838872820138931,
70
+ "learning_rate": 0.00011278195488721806,
71
+ "loss": 0.7874,
72
+ "step": 225
73
+ },
74
+ {
75
+ "epoch": 0.05646527385657821,
76
+ "grad_norm": 0.11714337766170502,
77
+ "learning_rate": 0.00012531328320802005,
78
+ "loss": 0.689,
79
+ "step": 250
80
+ },
81
+ {
82
+ "epoch": 0.062111801242236024,
83
+ "grad_norm": 0.07283364981412888,
84
+ "learning_rate": 0.00013784461152882208,
85
+ "loss": 0.7719,
86
+ "step": 275
87
+ },
88
+ {
89
+ "epoch": 0.06775832862789384,
90
+ "grad_norm": 0.1499466449022293,
91
+ "learning_rate": 0.00015037593984962405,
92
+ "loss": 0.655,
93
+ "step": 300
94
+ },
95
+ {
96
+ "epoch": 0.07340485601355166,
97
+ "grad_norm": 0.08195521682500839,
98
+ "learning_rate": 0.00016290726817042608,
99
+ "loss": 0.7508,
100
+ "step": 325
101
+ },
102
+ {
103
+ "epoch": 0.07905138339920949,
104
+ "grad_norm": 0.1490202099084854,
105
+ "learning_rate": 0.00017543859649122806,
106
+ "loss": 0.6372,
107
+ "step": 350
108
+ },
109
+ {
110
+ "epoch": 0.08469791078486731,
111
+ "grad_norm": 0.1617508977651596,
112
+ "learning_rate": 0.00018796992481203009,
113
+ "loss": 0.7396,
114
+ "step": 375
115
+ },
116
+ {
117
+ "epoch": 0.09034443817052512,
118
+ "grad_norm": 0.180181622505188,
119
+ "learning_rate": 0.00019999999702625888,
120
+ "loss": 0.6318,
121
+ "step": 400
122
+ },
123
+ {
124
+ "epoch": 0.09599096555618294,
125
+ "grad_norm": 0.08272858709096909,
126
+ "learning_rate": 0.00019999798975772924,
127
+ "loss": 0.724,
128
+ "step": 425
129
+ },
130
+ {
131
+ "epoch": 0.10163749294184077,
132
+ "grad_norm": 0.120403952896595,
133
+ "learning_rate": 0.00019999226539902187,
134
+ "loss": 0.6271,
135
+ "step": 450
136
+ },
137
+ {
138
+ "epoch": 0.10728402032749859,
139
+ "grad_norm": 0.07971920073032379,
140
+ "learning_rate": 0.00019998282416292055,
141
+ "loss": 0.7256,
142
+ "step": 475
143
+ },
144
+ {
145
+ "epoch": 0.11293054771315642,
146
+ "grad_norm": 0.1328658014535904,
147
+ "learning_rate": 0.00019996966640037166,
148
+ "loss": 0.6231,
149
+ "step": 500
150
+ },
151
+ {
152
+ "epoch": 0.11857707509881422,
153
+ "grad_norm": 0.07475866377353668,
154
+ "learning_rate": 0.00019995279260047092,
155
+ "loss": 0.7251,
156
+ "step": 525
157
+ },
158
+ {
159
+ "epoch": 0.12422360248447205,
160
+ "grad_norm": 0.1371573656797409,
161
+ "learning_rate": 0.00019993220339044524,
162
+ "loss": 0.5907,
163
+ "step": 550
164
+ },
165
+ {
166
+ "epoch": 0.12987012987012986,
167
+ "grad_norm": 0.07268711924552917,
168
+ "learning_rate": 0.00019990789953562961,
169
+ "loss": 0.7304,
170
+ "step": 575
171
+ },
172
+ {
173
+ "epoch": 0.13551665725578768,
174
+ "grad_norm": 0.14224526286125183,
175
+ "learning_rate": 0.0001998798819394383,
176
+ "loss": 0.5931,
177
+ "step": 600
178
+ },
179
+ {
180
+ "epoch": 0.1411631846414455,
181
+ "grad_norm": 0.0803467407822609,
182
+ "learning_rate": 0.00019984815164333163,
183
+ "loss": 0.7076,
184
+ "step": 625
185
+ },
186
+ {
187
+ "epoch": 0.14680971202710333,
188
+ "grad_norm": 0.12445727735757828,
189
+ "learning_rate": 0.00019981270982677698,
190
+ "loss": 0.5566,
191
+ "step": 650
192
+ },
193
+ {
194
+ "epoch": 0.15245623941276115,
195
+ "grad_norm": 0.07665792107582092,
196
+ "learning_rate": 0.00019977355780720514,
197
+ "loss": 0.6985,
198
+ "step": 675
199
+ },
200
+ {
201
+ "epoch": 0.15810276679841898,
202
+ "grad_norm": 0.13053999841213226,
203
+ "learning_rate": 0.00019973069703996125,
204
+ "loss": 0.5901,
205
+ "step": 700
206
+ },
207
+ {
208
+ "epoch": 0.1637492941840768,
209
+ "grad_norm": 0.07512692362070084,
210
+ "learning_rate": 0.00019968412911825067,
211
+ "loss": 0.7184,
212
+ "step": 725
213
+ },
214
+ {
215
+ "epoch": 0.16939582156973462,
216
+ "grad_norm": 0.12033283710479736,
217
+ "learning_rate": 0.00019963385577307987,
218
+ "loss": 0.6013,
219
+ "step": 750
220
+ },
221
+ {
222
+ "epoch": 0.17504234895539245,
223
+ "grad_norm": 0.0809774249792099,
224
+ "learning_rate": 0.000199579878873192,
225
+ "loss": 0.7054,
226
+ "step": 775
227
+ },
228
+ {
229
+ "epoch": 0.18068887634105024,
230
+ "grad_norm": 0.12490582466125488,
231
+ "learning_rate": 0.0001995222004249974,
232
+ "loss": 0.5714,
233
+ "step": 800
234
+ },
235
+ {
236
+ "epoch": 0.18633540372670807,
237
+ "grad_norm": 0.08289226144552231,
238
+ "learning_rate": 0.00019946082257249912,
239
+ "loss": 0.7304,
240
+ "step": 825
241
+ },
242
+ {
243
+ "epoch": 0.1919819311123659,
244
+ "grad_norm": 0.14385385811328888,
245
+ "learning_rate": 0.00019939574759721316,
246
+ "loss": 0.5639,
247
+ "step": 850
248
+ },
249
+ {
250
+ "epoch": 0.1976284584980237,
251
+ "grad_norm": 0.07623141258955002,
252
+ "learning_rate": 0.00019932697791808366,
253
+ "loss": 0.7126,
254
+ "step": 875
255
+ },
256
+ {
257
+ "epoch": 0.20327498588368154,
258
+ "grad_norm": 0.11150185018777847,
259
+ "learning_rate": 0.000199254516091393,
260
+ "loss": 0.5903,
261
+ "step": 900
262
+ },
263
+ {
264
+ "epoch": 0.20892151326933936,
265
+ "grad_norm": 0.07193930447101593,
266
+ "learning_rate": 0.00019917836481066675,
267
+ "loss": 0.6952,
268
+ "step": 925
269
+ },
270
+ {
271
+ "epoch": 0.21456804065499718,
272
+ "grad_norm": 0.11242598295211792,
273
+ "learning_rate": 0.00019909852690657359,
274
+ "loss": 0.5853,
275
+ "step": 950
276
+ },
277
+ {
278
+ "epoch": 0.220214568040655,
279
+ "grad_norm": 0.07508910447359085,
280
+ "learning_rate": 0.0001990150053468201,
281
+ "loss": 0.6969,
282
+ "step": 975
283
+ },
284
+ {
285
+ "epoch": 0.22586109542631283,
286
+ "grad_norm": 0.11998436599969864,
287
+ "learning_rate": 0.00019892780323604035,
288
+ "loss": 0.5791,
289
+ "step": 1000
290
+ }
291
+ ],
292
+ "logging_steps": 25,
293
+ "max_steps": 13281,
294
+ "num_input_tokens_seen": 0,
295
+ "num_train_epochs": 3,
296
+ "save_steps": 200,
297
+ "stateful_callbacks": {
298
+ "TrainerControl": {
299
+ "args": {
300
+ "should_epoch_stop": false,
301
+ "should_evaluate": false,
302
+ "should_log": false,
303
+ "should_save": true,
304
+ "should_training_stop": false
305
+ },
306
+ "attributes": {}
307
+ }
308
+ },
309
+ "total_flos": 5.919624163446989e+17,
310
+ "train_batch_size": 2,
311
+ "trial_name": null,
312
+ "trial_params": null
313
+ }
checkpoint-1000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fc98f22665d02224015b9535b80e5c69ad66eca110b77e2e7ae87eceaba5b8a
3
+ size 5051
checkpoint-10000/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Llama-2-13b-chat-hf
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.12.0
checkpoint-10000/adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Llama-2-13b-chat-hf",
5
+ "bias": "lora_only",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.001,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 64,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "v_proj",
24
+ "q_proj"
25
+ ],
26
+ "task_type": "CAUSAL_LM",
27
+ "use_dora": false,
28
+ "use_rslora": false
29
+ }
checkpoint-10000/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f6ce1869411995bc9aec16498cea6df86ec4f8d31101e4a11cd98a47a2a9933
3
+ size 209736952
checkpoint-10000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:019ba2f34d4efce65d3c6cebe30da07054c17a6c52482cc6aa549811f95dd341
3
+ size 419529285
checkpoint-10000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2a46b49787b4e01dcc90e481046376a4be0a77ab6ad4dc91788f7e1272b5953
3
+ size 14575
checkpoint-10000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1759e50592cff2ba9e598e352b2a56c9f82224b73c65d99a1c68039533368516
3
+ size 627
checkpoint-10000/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
checkpoint-10000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-10000/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
checkpoint-10000/tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "bos_token": "<s>",
32
+ "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": false,
36
+ "model_max_length": 1000000000000000019884624838656,
37
+ "pad_token": "</s>",
38
+ "padding_side": "right",
39
+ "sp_model_kwargs": {},
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
+ }
checkpoint-10000/trainer_state.json ADDED
@@ -0,0 +1,2833 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.258610954263128,
5
+ "eval_steps": 500,
6
+ "global_step": 10000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.00564652738565782,
13
+ "grad_norm": 0.0635828971862793,
14
+ "learning_rate": 1.2531328320802006e-05,
15
+ "loss": 1.3836,
16
+ "step": 25
17
+ },
18
+ {
19
+ "epoch": 0.01129305477131564,
20
+ "grad_norm": 0.2005225569009781,
21
+ "learning_rate": 2.506265664160401e-05,
22
+ "loss": 1.6497,
23
+ "step": 50
24
+ },
25
+ {
26
+ "epoch": 0.01693958215697346,
27
+ "grad_norm": 0.07235410064458847,
28
+ "learning_rate": 3.759398496240601e-05,
29
+ "loss": 1.1768,
30
+ "step": 75
31
+ },
32
+ {
33
+ "epoch": 0.02258610954263128,
34
+ "grad_norm": 0.17648495733737946,
35
+ "learning_rate": 5.012531328320802e-05,
36
+ "loss": 1.2146,
37
+ "step": 100
38
+ },
39
+ {
40
+ "epoch": 0.028232636928289104,
41
+ "grad_norm": 0.06953724473714828,
42
+ "learning_rate": 6.265664160401002e-05,
43
+ "loss": 0.8725,
44
+ "step": 125
45
+ },
46
+ {
47
+ "epoch": 0.03387916431394692,
48
+ "grad_norm": 0.12059248238801956,
49
+ "learning_rate": 7.518796992481203e-05,
50
+ "loss": 0.7548,
51
+ "step": 150
52
+ },
53
+ {
54
+ "epoch": 0.039525691699604744,
55
+ "grad_norm": 0.0689113661646843,
56
+ "learning_rate": 8.771929824561403e-05,
57
+ "loss": 0.7917,
58
+ "step": 175
59
+ },
60
+ {
61
+ "epoch": 0.04517221908526256,
62
+ "grad_norm": 0.16621273756027222,
63
+ "learning_rate": 0.00010025062656641604,
64
+ "loss": 0.6985,
65
+ "step": 200
66
+ },
67
+ {
68
+ "epoch": 0.050818746470920384,
69
+ "grad_norm": 0.07838872820138931,
70
+ "learning_rate": 0.00011278195488721806,
71
+ "loss": 0.7874,
72
+ "step": 225
73
+ },
74
+ {
75
+ "epoch": 0.05646527385657821,
76
+ "grad_norm": 0.11714337766170502,
77
+ "learning_rate": 0.00012531328320802005,
78
+ "loss": 0.689,
79
+ "step": 250
80
+ },
81
+ {
82
+ "epoch": 0.062111801242236024,
83
+ "grad_norm": 0.07283364981412888,
84
+ "learning_rate": 0.00013784461152882208,
85
+ "loss": 0.7719,
86
+ "step": 275
87
+ },
88
+ {
89
+ "epoch": 0.06775832862789384,
90
+ "grad_norm": 0.1499466449022293,
91
+ "learning_rate": 0.00015037593984962405,
92
+ "loss": 0.655,
93
+ "step": 300
94
+ },
95
+ {
96
+ "epoch": 0.07340485601355166,
97
+ "grad_norm": 0.08195521682500839,
98
+ "learning_rate": 0.00016290726817042608,
99
+ "loss": 0.7508,
100
+ "step": 325
101
+ },
102
+ {
103
+ "epoch": 0.07905138339920949,
104
+ "grad_norm": 0.1490202099084854,
105
+ "learning_rate": 0.00017543859649122806,
106
+ "loss": 0.6372,
107
+ "step": 350
108
+ },
109
+ {
110
+ "epoch": 0.08469791078486731,
111
+ "grad_norm": 0.1617508977651596,
112
+ "learning_rate": 0.00018796992481203009,
113
+ "loss": 0.7396,
114
+ "step": 375
115
+ },
116
+ {
117
+ "epoch": 0.09034443817052512,
118
+ "grad_norm": 0.180181622505188,
119
+ "learning_rate": 0.00019999999702625888,
120
+ "loss": 0.6318,
121
+ "step": 400
122
+ },
123
+ {
124
+ "epoch": 0.09599096555618294,
125
+ "grad_norm": 0.08272858709096909,
126
+ "learning_rate": 0.00019999798975772924,
127
+ "loss": 0.724,
128
+ "step": 425
129
+ },
130
+ {
131
+ "epoch": 0.10163749294184077,
132
+ "grad_norm": 0.120403952896595,
133
+ "learning_rate": 0.00019999226539902187,
134
+ "loss": 0.6271,
135
+ "step": 450
136
+ },
137
+ {
138
+ "epoch": 0.10728402032749859,
139
+ "grad_norm": 0.07971920073032379,
140
+ "learning_rate": 0.00019998282416292055,
141
+ "loss": 0.7256,
142
+ "step": 475
143
+ },
144
+ {
145
+ "epoch": 0.11293054771315642,
146
+ "grad_norm": 0.1328658014535904,
147
+ "learning_rate": 0.00019996966640037166,
148
+ "loss": 0.6231,
149
+ "step": 500
150
+ },
151
+ {
152
+ "epoch": 0.11857707509881422,
153
+ "grad_norm": 0.07475866377353668,
154
+ "learning_rate": 0.00019995279260047092,
155
+ "loss": 0.7251,
156
+ "step": 525
157
+ },
158
+ {
159
+ "epoch": 0.12422360248447205,
160
+ "grad_norm": 0.1371573656797409,
161
+ "learning_rate": 0.00019993220339044524,
162
+ "loss": 0.5907,
163
+ "step": 550
164
+ },
165
+ {
166
+ "epoch": 0.12987012987012986,
167
+ "grad_norm": 0.07268711924552917,
168
+ "learning_rate": 0.00019990789953562961,
169
+ "loss": 0.7304,
170
+ "step": 575
171
+ },
172
+ {
173
+ "epoch": 0.13551665725578768,
174
+ "grad_norm": 0.14224526286125183,
175
+ "learning_rate": 0.0001998798819394383,
176
+ "loss": 0.5931,
177
+ "step": 600
178
+ },
179
+ {
180
+ "epoch": 0.1411631846414455,
181
+ "grad_norm": 0.0803467407822609,
182
+ "learning_rate": 0.00019984815164333163,
183
+ "loss": 0.7076,
184
+ "step": 625
185
+ },
186
+ {
187
+ "epoch": 0.14680971202710333,
188
+ "grad_norm": 0.12445727735757828,
189
+ "learning_rate": 0.00019981270982677698,
190
+ "loss": 0.5566,
191
+ "step": 650
192
+ },
193
+ {
194
+ "epoch": 0.15245623941276115,
195
+ "grad_norm": 0.07665792107582092,
196
+ "learning_rate": 0.00019977355780720514,
197
+ "loss": 0.6985,
198
+ "step": 675
199
+ },
200
+ {
201
+ "epoch": 0.15810276679841898,
202
+ "grad_norm": 0.13053999841213226,
203
+ "learning_rate": 0.00019973069703996125,
204
+ "loss": 0.5901,
205
+ "step": 700
206
+ },
207
+ {
208
+ "epoch": 0.1637492941840768,
209
+ "grad_norm": 0.07512692362070084,
210
+ "learning_rate": 0.00019968412911825067,
211
+ "loss": 0.7184,
212
+ "step": 725
213
+ },
214
+ {
215
+ "epoch": 0.16939582156973462,
216
+ "grad_norm": 0.12033283710479736,
217
+ "learning_rate": 0.00019963385577307987,
218
+ "loss": 0.6013,
219
+ "step": 750
220
+ },
221
+ {
222
+ "epoch": 0.17504234895539245,
223
+ "grad_norm": 0.0809774249792099,
224
+ "learning_rate": 0.000199579878873192,
225
+ "loss": 0.7054,
226
+ "step": 775
227
+ },
228
+ {
229
+ "epoch": 0.18068887634105024,
230
+ "grad_norm": 0.12490582466125488,
231
+ "learning_rate": 0.0001995222004249974,
232
+ "loss": 0.5714,
233
+ "step": 800
234
+ },
235
+ {
236
+ "epoch": 0.18633540372670807,
237
+ "grad_norm": 0.08289226144552231,
238
+ "learning_rate": 0.00019946082257249912,
239
+ "loss": 0.7304,
240
+ "step": 825
241
+ },
242
+ {
243
+ "epoch": 0.1919819311123659,
244
+ "grad_norm": 0.14385385811328888,
245
+ "learning_rate": 0.00019939574759721316,
246
+ "loss": 0.5639,
247
+ "step": 850
248
+ },
249
+ {
250
+ "epoch": 0.1976284584980237,
251
+ "grad_norm": 0.07623141258955002,
252
+ "learning_rate": 0.00019932697791808366,
253
+ "loss": 0.7126,
254
+ "step": 875
255
+ },
256
+ {
257
+ "epoch": 0.20327498588368154,
258
+ "grad_norm": 0.11150185018777847,
259
+ "learning_rate": 0.000199254516091393,
260
+ "loss": 0.5903,
261
+ "step": 900
262
+ },
263
+ {
264
+ "epoch": 0.20892151326933936,
265
+ "grad_norm": 0.07193930447101593,
266
+ "learning_rate": 0.00019917836481066675,
267
+ "loss": 0.6952,
268
+ "step": 925
269
+ },
270
+ {
271
+ "epoch": 0.21456804065499718,
272
+ "grad_norm": 0.11242598295211792,
273
+ "learning_rate": 0.00019909852690657359,
274
+ "loss": 0.5853,
275
+ "step": 950
276
+ },
277
+ {
278
+ "epoch": 0.220214568040655,
279
+ "grad_norm": 0.07508910447359085,
280
+ "learning_rate": 0.0001990150053468201,
281
+ "loss": 0.6969,
282
+ "step": 975
283
+ },
284
+ {
285
+ "epoch": 0.22586109542631283,
286
+ "grad_norm": 0.11998436599969864,
287
+ "learning_rate": 0.00019892780323604035,
288
+ "loss": 0.5791,
289
+ "step": 1000
290
+ },
291
+ {
292
+ "epoch": 0.23150762281197063,
293
+ "grad_norm": 0.07748444378376007,
294
+ "learning_rate": 0.0001988369238156806,
295
+ "loss": 0.7038,
296
+ "step": 1025
297
+ },
298
+ {
299
+ "epoch": 0.23715415019762845,
300
+ "grad_norm": 0.19617140293121338,
301
+ "learning_rate": 0.0001987423704638788,
302
+ "loss": 0.5792,
303
+ "step": 1050
304
+ },
305
+ {
306
+ "epoch": 0.24280067758328627,
307
+ "grad_norm": 0.08167731016874313,
308
+ "learning_rate": 0.00019864414669533892,
309
+ "loss": 0.6989,
310
+ "step": 1075
311
+ },
312
+ {
313
+ "epoch": 0.2484472049689441,
314
+ "grad_norm": 0.11911099404096603,
315
+ "learning_rate": 0.00019854225616120044,
316
+ "loss": 0.5985,
317
+ "step": 1100
318
+ },
319
+ {
320
+ "epoch": 0.2540937323546019,
321
+ "grad_norm": 0.0718325674533844,
322
+ "learning_rate": 0.0001984367026489025,
323
+ "loss": 0.6853,
324
+ "step": 1125
325
+ },
326
+ {
327
+ "epoch": 0.2597402597402597,
328
+ "grad_norm": 0.12495870143175125,
329
+ "learning_rate": 0.0001983274900820432,
330
+ "loss": 0.5738,
331
+ "step": 1150
332
+ },
333
+ {
334
+ "epoch": 0.26538678712591757,
335
+ "grad_norm": 0.08245467394590378,
336
+ "learning_rate": 0.0001982146225202338,
337
+ "loss": 0.6766,
338
+ "step": 1175
339
+ },
340
+ {
341
+ "epoch": 0.27103331451157536,
342
+ "grad_norm": 0.11854438483715057,
343
+ "learning_rate": 0.00019809810415894767,
344
+ "loss": 0.5828,
345
+ "step": 1200
346
+ },
347
+ {
348
+ "epoch": 0.2766798418972332,
349
+ "grad_norm": 0.07968372851610184,
350
+ "learning_rate": 0.0001979779393293644,
351
+ "loss": 0.6901,
352
+ "step": 1225
353
+ },
354
+ {
355
+ "epoch": 0.282326369282891,
356
+ "grad_norm": 0.13610929250717163,
357
+ "learning_rate": 0.00019785413249820893,
358
+ "loss": 0.554,
359
+ "step": 1250
360
+ },
361
+ {
362
+ "epoch": 0.28797289666854886,
363
+ "grad_norm": 0.08099998533725739,
364
+ "learning_rate": 0.00019772668826758527,
365
+ "loss": 0.6615,
366
+ "step": 1275
367
+ },
368
+ {
369
+ "epoch": 0.29361942405420666,
370
+ "grad_norm": 0.10878365486860275,
371
+ "learning_rate": 0.0001975956113748057,
372
+ "loss": 0.547,
373
+ "step": 1300
374
+ },
375
+ {
376
+ "epoch": 0.2992659514398645,
377
+ "grad_norm": 0.0784253254532814,
378
+ "learning_rate": 0.0001974609066922144,
379
+ "loss": 0.6589,
380
+ "step": 1325
381
+ },
382
+ {
383
+ "epoch": 0.3049124788255223,
384
+ "grad_norm": 0.10678227245807648,
385
+ "learning_rate": 0.00019732257922700655,
386
+ "loss": 0.5443,
387
+ "step": 1350
388
+ },
389
+ {
390
+ "epoch": 0.3105590062111801,
391
+ "grad_norm": 0.07781955599784851,
392
+ "learning_rate": 0.00019718063412104222,
393
+ "loss": 0.6798,
394
+ "step": 1375
395
+ },
396
+ {
397
+ "epoch": 0.31620553359683795,
398
+ "grad_norm": 0.12910470366477966,
399
+ "learning_rate": 0.00019703507665065498,
400
+ "loss": 0.54,
401
+ "step": 1400
402
+ },
403
+ {
404
+ "epoch": 0.32185206098249575,
405
+ "grad_norm": 0.08442296832799911,
406
+ "learning_rate": 0.00019688591222645607,
407
+ "loss": 0.6998,
408
+ "step": 1425
409
+ },
410
+ {
411
+ "epoch": 0.3274985883681536,
412
+ "grad_norm": 0.10945732891559601,
413
+ "learning_rate": 0.00019673314639313315,
414
+ "loss": 0.5576,
415
+ "step": 1450
416
+ },
417
+ {
418
+ "epoch": 0.3331451157538114,
419
+ "grad_norm": 0.07373673468828201,
420
+ "learning_rate": 0.00019657678482924406,
421
+ "loss": 0.709,
422
+ "step": 1475
423
+ },
424
+ {
425
+ "epoch": 0.33879164313946925,
426
+ "grad_norm": 0.10061786323785782,
427
+ "learning_rate": 0.00019641683334700608,
428
+ "loss": 0.5329,
429
+ "step": 1500
430
+ },
431
+ {
432
+ "epoch": 0.34443817052512704,
433
+ "grad_norm": 0.08854890614748001,
434
+ "learning_rate": 0.00019625329789207949,
435
+ "loss": 0.6753,
436
+ "step": 1525
437
+ },
438
+ {
439
+ "epoch": 0.3500846979107849,
440
+ "grad_norm": 0.11869047582149506,
441
+ "learning_rate": 0.00019608618454334685,
442
+ "loss": 0.54,
443
+ "step": 1550
444
+ },
445
+ {
446
+ "epoch": 0.3557312252964427,
447
+ "grad_norm": 0.0819987803697586,
448
+ "learning_rate": 0.00019591549951268692,
449
+ "loss": 0.683,
450
+ "step": 1575
451
+ },
452
+ {
453
+ "epoch": 0.3613777526821005,
454
+ "grad_norm": 0.10941476374864578,
455
+ "learning_rate": 0.00019574124914474374,
456
+ "loss": 0.5713,
457
+ "step": 1600
458
+ },
459
+ {
460
+ "epoch": 0.36702428006775834,
461
+ "grad_norm": 0.0801759734749794,
462
+ "learning_rate": 0.00019556343991669083,
463
+ "loss": 0.6494,
464
+ "step": 1625
465
+ },
466
+ {
467
+ "epoch": 0.37267080745341613,
468
+ "grad_norm": 0.11291850358247757,
469
+ "learning_rate": 0.0001953820784379904,
470
+ "loss": 0.5428,
471
+ "step": 1650
472
+ },
473
+ {
474
+ "epoch": 0.378317334839074,
475
+ "grad_norm": 0.0784342810511589,
476
+ "learning_rate": 0.00019519717145014765,
477
+ "loss": 0.6789,
478
+ "step": 1675
479
+ },
480
+ {
481
+ "epoch": 0.3839638622247318,
482
+ "grad_norm": 0.11995444446802139,
483
+ "learning_rate": 0.00019500872582646034,
484
+ "loss": 0.5409,
485
+ "step": 1700
486
+ },
487
+ {
488
+ "epoch": 0.38961038961038963,
489
+ "grad_norm": 0.10059577226638794,
490
+ "learning_rate": 0.00019481674857176293,
491
+ "loss": 0.6887,
492
+ "step": 1725
493
+ },
494
+ {
495
+ "epoch": 0.3952569169960474,
496
+ "grad_norm": 0.11123017966747284,
497
+ "learning_rate": 0.0001946212468221666,
498
+ "loss": 0.5482,
499
+ "step": 1750
500
+ },
501
+ {
502
+ "epoch": 0.4009034443817053,
503
+ "grad_norm": 0.0788169875741005,
504
+ "learning_rate": 0.00019442222784479382,
505
+ "loss": 0.6577,
506
+ "step": 1775
507
+ },
508
+ {
509
+ "epoch": 0.40654997176736307,
510
+ "grad_norm": 0.09987206757068634,
511
+ "learning_rate": 0.0001942196990375081,
512
+ "loss": 0.5353,
513
+ "step": 1800
514
+ },
515
+ {
516
+ "epoch": 0.41219649915302087,
517
+ "grad_norm": 0.081305131316185,
518
+ "learning_rate": 0.00019401366792863914,
519
+ "loss": 0.6757,
520
+ "step": 1825
521
+ },
522
+ {
523
+ "epoch": 0.4178430265386787,
524
+ "grad_norm": 0.11595868319272995,
525
+ "learning_rate": 0.00019380414217670309,
526
+ "loss": 0.5306,
527
+ "step": 1850
528
+ },
529
+ {
530
+ "epoch": 0.4234895539243365,
531
+ "grad_norm": 0.08652087301015854,
532
+ "learning_rate": 0.00019359112957011764,
533
+ "loss": 0.6634,
534
+ "step": 1875
535
+ },
536
+ {
537
+ "epoch": 0.42913608130999437,
538
+ "grad_norm": 0.1181817501783371,
539
+ "learning_rate": 0.00019337463802691264,
540
+ "loss": 0.5465,
541
+ "step": 1900
542
+ },
543
+ {
544
+ "epoch": 0.43478260869565216,
545
+ "grad_norm": 0.08145532757043839,
546
+ "learning_rate": 0.00019315467559443574,
547
+ "loss": 0.6639,
548
+ "step": 1925
549
+ },
550
+ {
551
+ "epoch": 0.44042913608131,
552
+ "grad_norm": 0.10263626277446747,
553
+ "learning_rate": 0.0001929312504490533,
554
+ "loss": 0.5418,
555
+ "step": 1950
556
+ },
557
+ {
558
+ "epoch": 0.4460756634669678,
559
+ "grad_norm": 0.07672405242919922,
560
+ "learning_rate": 0.00019270437089584635,
561
+ "loss": 0.6547,
562
+ "step": 1975
563
+ },
564
+ {
565
+ "epoch": 0.45172219085262566,
566
+ "grad_norm": 0.0984482392668724,
567
+ "learning_rate": 0.00019247404536830204,
568
+ "loss": 0.5321,
569
+ "step": 2000
570
+ },
571
+ {
572
+ "epoch": 0.45736871823828346,
573
+ "grad_norm": 0.08558057248592377,
574
+ "learning_rate": 0.00019224028242800006,
575
+ "loss": 0.6657,
576
+ "step": 2025
577
+ },
578
+ {
579
+ "epoch": 0.46301524562394125,
580
+ "grad_norm": 0.10624836385250092,
581
+ "learning_rate": 0.00019200309076429438,
582
+ "loss": 0.5542,
583
+ "step": 2050
584
+ },
585
+ {
586
+ "epoch": 0.4686617730095991,
587
+ "grad_norm": 0.08049538731575012,
588
+ "learning_rate": 0.00019176247919399023,
589
+ "loss": 0.6389,
590
+ "step": 2075
591
+ },
592
+ {
593
+ "epoch": 0.4743083003952569,
594
+ "grad_norm": 0.11163744330406189,
595
+ "learning_rate": 0.00019151845666101646,
596
+ "loss": 0.5382,
597
+ "step": 2100
598
+ },
599
+ {
600
+ "epoch": 0.47995482778091475,
601
+ "grad_norm": 0.07694784551858902,
602
+ "learning_rate": 0.00019127103223609307,
603
+ "loss": 0.6345,
604
+ "step": 2125
605
+ },
606
+ {
607
+ "epoch": 0.48560135516657255,
608
+ "grad_norm": 0.11501342058181763,
609
+ "learning_rate": 0.0001910202151163939,
610
+ "loss": 0.5303,
611
+ "step": 2150
612
+ },
613
+ {
614
+ "epoch": 0.4912478825522304,
615
+ "grad_norm": 0.08532056957483292,
616
+ "learning_rate": 0.00019076601462520492,
617
+ "loss": 0.666,
618
+ "step": 2175
619
+ },
620
+ {
621
+ "epoch": 0.4968944099378882,
622
+ "grad_norm": 0.09018545597791672,
623
+ "learning_rate": 0.00019050844021157752,
624
+ "loss": 0.5363,
625
+ "step": 2200
626
+ },
627
+ {
628
+ "epoch": 0.502540937323546,
629
+ "grad_norm": 0.08757849037647247,
630
+ "learning_rate": 0.00019024750144997746,
631
+ "loss": 0.6684,
632
+ "step": 2225
633
+ },
634
+ {
635
+ "epoch": 0.5081874647092038,
636
+ "grad_norm": 0.09418553113937378,
637
+ "learning_rate": 0.00018998320803992872,
638
+ "loss": 0.565,
639
+ "step": 2250
640
+ },
641
+ {
642
+ "epoch": 0.5138339920948617,
643
+ "grad_norm": 0.10246949642896652,
644
+ "learning_rate": 0.00018971556980565329,
645
+ "loss": 0.6524,
646
+ "step": 2275
647
+ },
648
+ {
649
+ "epoch": 0.5194805194805194,
650
+ "grad_norm": 0.12446881830692291,
651
+ "learning_rate": 0.00018944459669570555,
652
+ "loss": 0.5447,
653
+ "step": 2300
654
+ },
655
+ {
656
+ "epoch": 0.5251270468661773,
657
+ "grad_norm": 0.08439560234546661,
658
+ "learning_rate": 0.00018917029878260294,
659
+ "loss": 0.673,
660
+ "step": 2325
661
+ },
662
+ {
663
+ "epoch": 0.5307735742518351,
664
+ "grad_norm": 0.1195409968495369,
665
+ "learning_rate": 0.00018889268626245116,
666
+ "loss": 0.51,
667
+ "step": 2350
668
+ },
669
+ {
670
+ "epoch": 0.536420101637493,
671
+ "grad_norm": 0.09150119870901108,
672
+ "learning_rate": 0.0001886117694545654,
673
+ "loss": 0.6631,
674
+ "step": 2375
675
+ },
676
+ {
677
+ "epoch": 0.5420666290231507,
678
+ "grad_norm": 0.10301247239112854,
679
+ "learning_rate": 0.0001883275588010866,
680
+ "loss": 0.5257,
681
+ "step": 2400
682
+ },
683
+ {
684
+ "epoch": 0.5477131564088086,
685
+ "grad_norm": 0.08086048811674118,
686
+ "learning_rate": 0.00018804006486659346,
687
+ "loss": 0.6305,
688
+ "step": 2425
689
+ },
690
+ {
691
+ "epoch": 0.5533596837944664,
692
+ "grad_norm": 0.10540500283241272,
693
+ "learning_rate": 0.0001877492983377096,
694
+ "loss": 0.5607,
695
+ "step": 2450
696
+ },
697
+ {
698
+ "epoch": 0.5590062111801242,
699
+ "grad_norm": 0.0777876153588295,
700
+ "learning_rate": 0.00018745527002270634,
701
+ "loss": 0.6413,
702
+ "step": 2475
703
+ },
704
+ {
705
+ "epoch": 0.564652738565782,
706
+ "grad_norm": 0.10727331042289734,
707
+ "learning_rate": 0.00018715799085110112,
708
+ "loss": 0.5206,
709
+ "step": 2500
710
+ },
711
+ {
712
+ "epoch": 0.5702992659514399,
713
+ "grad_norm": 0.09144891798496246,
714
+ "learning_rate": 0.0001868574718732508,
715
+ "loss": 0.6655,
716
+ "step": 2525
717
+ },
718
+ {
719
+ "epoch": 0.5759457933370977,
720
+ "grad_norm": 0.08949702978134155,
721
+ "learning_rate": 0.00018655372425994152,
722
+ "loss": 0.5358,
723
+ "step": 2550
724
+ },
725
+ {
726
+ "epoch": 0.5815923207227555,
727
+ "grad_norm": 0.08744482696056366,
728
+ "learning_rate": 0.0001862467593019728,
729
+ "loss": 0.6396,
730
+ "step": 2575
731
+ },
732
+ {
733
+ "epoch": 0.5872388481084133,
734
+ "grad_norm": 0.10931294411420822,
735
+ "learning_rate": 0.0001859365884097384,
736
+ "loss": 0.5132,
737
+ "step": 2600
738
+ },
739
+ {
740
+ "epoch": 0.5928853754940712,
741
+ "grad_norm": 0.07518015056848526,
742
+ "learning_rate": 0.00018562322311280186,
743
+ "loss": 0.6378,
744
+ "step": 2625
745
+ },
746
+ {
747
+ "epoch": 0.598531902879729,
748
+ "grad_norm": 0.09787683933973312,
749
+ "learning_rate": 0.000185306675059468,
750
+ "loss": 0.5272,
751
+ "step": 2650
752
+ },
753
+ {
754
+ "epoch": 0.6041784302653868,
755
+ "grad_norm": 0.08679146319627762,
756
+ "learning_rate": 0.00018498695601634993,
757
+ "loss": 0.6486,
758
+ "step": 2675
759
+ },
760
+ {
761
+ "epoch": 0.6098249576510446,
762
+ "grad_norm": 0.10611116141080856,
763
+ "learning_rate": 0.00018466407786793174,
764
+ "loss": 0.5237,
765
+ "step": 2700
766
+ },
767
+ {
768
+ "epoch": 0.6154714850367025,
769
+ "grad_norm": 0.0772860199213028,
770
+ "learning_rate": 0.00018433805261612663,
771
+ "loss": 0.6526,
772
+ "step": 2725
773
+ },
774
+ {
775
+ "epoch": 0.6211180124223602,
776
+ "grad_norm": 0.1005689725279808,
777
+ "learning_rate": 0.00018400889237983086,
778
+ "loss": 0.5297,
779
+ "step": 2750
780
+ },
781
+ {
782
+ "epoch": 0.626764539808018,
783
+ "grad_norm": 0.08322805911302567,
784
+ "learning_rate": 0.00018367660939447316,
785
+ "loss": 0.6448,
786
+ "step": 2775
787
+ },
788
+ {
789
+ "epoch": 0.6324110671936759,
790
+ "grad_norm": 0.10492440313100815,
791
+ "learning_rate": 0.00018334121601156002,
792
+ "loss": 0.493,
793
+ "step": 2800
794
+ },
795
+ {
796
+ "epoch": 0.6380575945793338,
797
+ "grad_norm": 0.08439356088638306,
798
+ "learning_rate": 0.00018300272469821662,
799
+ "loss": 0.6421,
800
+ "step": 2825
801
+ },
802
+ {
803
+ "epoch": 0.6437041219649915,
804
+ "grad_norm": 0.11175478994846344,
805
+ "learning_rate": 0.00018266114803672318,
806
+ "loss": 0.5293,
807
+ "step": 2850
808
+ },
809
+ {
810
+ "epoch": 0.6493506493506493,
811
+ "grad_norm": 0.07700271904468536,
812
+ "learning_rate": 0.00018231649872404754,
813
+ "loss": 0.6506,
814
+ "step": 2875
815
+ },
816
+ {
817
+ "epoch": 0.6549971767363072,
818
+ "grad_norm": 0.08704936504364014,
819
+ "learning_rate": 0.00018196878957137295,
820
+ "loss": 0.5091,
821
+ "step": 2900
822
+ },
823
+ {
824
+ "epoch": 0.6606437041219649,
825
+ "grad_norm": 0.0863596498966217,
826
+ "learning_rate": 0.00018161803350362198,
827
+ "loss": 0.6531,
828
+ "step": 2925
829
+ },
830
+ {
831
+ "epoch": 0.6662902315076228,
832
+ "grad_norm": 0.11374282091856003,
833
+ "learning_rate": 0.00018126424355897612,
834
+ "loss": 0.5389,
835
+ "step": 2950
836
+ },
837
+ {
838
+ "epoch": 0.6719367588932806,
839
+ "grad_norm": 0.08936896920204163,
840
+ "learning_rate": 0.000180907432888391,
841
+ "loss": 0.6267,
842
+ "step": 2975
843
+ },
844
+ {
845
+ "epoch": 0.6775832862789385,
846
+ "grad_norm": 0.08924362808465958,
847
+ "learning_rate": 0.0001805476147551076,
848
+ "loss": 0.4882,
849
+ "step": 3000
850
+ },
851
+ {
852
+ "epoch": 0.6832298136645962,
853
+ "grad_norm": 0.08161070942878723,
854
+ "learning_rate": 0.0001801848025341593,
855
+ "loss": 0.6502,
856
+ "step": 3025
857
+ },
858
+ {
859
+ "epoch": 0.6888763410502541,
860
+ "grad_norm": 0.11261451989412308,
861
+ "learning_rate": 0.00017981900971187465,
862
+ "loss": 0.5241,
863
+ "step": 3050
864
+ },
865
+ {
866
+ "epoch": 0.6945228684359119,
867
+ "grad_norm": 0.0859522670507431,
868
+ "learning_rate": 0.00017945024988537603,
869
+ "loss": 0.6413,
870
+ "step": 3075
871
+ },
872
+ {
873
+ "epoch": 0.7001693958215698,
874
+ "grad_norm": 0.11650535464286804,
875
+ "learning_rate": 0.0001790785367620743,
876
+ "loss": 0.519,
877
+ "step": 3100
878
+ },
879
+ {
880
+ "epoch": 0.7058159232072275,
881
+ "grad_norm": 0.09202492237091064,
882
+ "learning_rate": 0.00017870388415915922,
883
+ "loss": 0.6212,
884
+ "step": 3125
885
+ },
886
+ {
887
+ "epoch": 0.7114624505928854,
888
+ "grad_norm": 0.1048663780093193,
889
+ "learning_rate": 0.00017832630600308585,
890
+ "loss": 0.5266,
891
+ "step": 3150
892
+ },
893
+ {
894
+ "epoch": 0.7171089779785432,
895
+ "grad_norm": 0.08784987032413483,
896
+ "learning_rate": 0.00017794581632905683,
897
+ "loss": 0.6214,
898
+ "step": 3175
899
+ },
900
+ {
901
+ "epoch": 0.722755505364201,
902
+ "grad_norm": 0.10895237326622009,
903
+ "learning_rate": 0.00017756242928050085,
904
+ "loss": 0.5059,
905
+ "step": 3200
906
+ },
907
+ {
908
+ "epoch": 0.7284020327498588,
909
+ "grad_norm": 0.09365130960941315,
910
+ "learning_rate": 0.0001771761591085467,
911
+ "loss": 0.6529,
912
+ "step": 3225
913
+ },
914
+ {
915
+ "epoch": 0.7340485601355167,
916
+ "grad_norm": 0.1045169085264206,
917
+ "learning_rate": 0.0001767870201714936,
918
+ "loss": 0.5229,
919
+ "step": 3250
920
+ },
921
+ {
922
+ "epoch": 0.7396950875211745,
923
+ "grad_norm": 0.08621610701084137,
924
+ "learning_rate": 0.0001763950269342776,
925
+ "loss": 0.6489,
926
+ "step": 3275
927
+ },
928
+ {
929
+ "epoch": 0.7453416149068323,
930
+ "grad_norm": 0.1039639338850975,
931
+ "learning_rate": 0.00017600019396793367,
932
+ "loss": 0.5116,
933
+ "step": 3300
934
+ },
935
+ {
936
+ "epoch": 0.7509881422924901,
937
+ "grad_norm": 0.09034851938486099,
938
+ "learning_rate": 0.00017560253594905425,
939
+ "loss": 0.6587,
940
+ "step": 3325
941
+ },
942
+ {
943
+ "epoch": 0.756634669678148,
944
+ "grad_norm": 0.10783170908689499,
945
+ "learning_rate": 0.00017520206765924372,
946
+ "loss": 0.5019,
947
+ "step": 3350
948
+ },
949
+ {
950
+ "epoch": 0.7622811970638057,
951
+ "grad_norm": 0.08911153674125671,
952
+ "learning_rate": 0.00017479880398456871,
953
+ "loss": 0.6242,
954
+ "step": 3375
955
+ },
956
+ {
957
+ "epoch": 0.7679277244494636,
958
+ "grad_norm": 0.10053360462188721,
959
+ "learning_rate": 0.00017439275991500507,
960
+ "loss": 0.4996,
961
+ "step": 3400
962
+ },
963
+ {
964
+ "epoch": 0.7735742518351214,
965
+ "grad_norm": 0.09367632865905762,
966
+ "learning_rate": 0.0001739839505438804,
967
+ "loss": 0.6347,
968
+ "step": 3425
969
+ },
970
+ {
971
+ "epoch": 0.7792207792207793,
972
+ "grad_norm": 0.09187789261341095,
973
+ "learning_rate": 0.00017357239106731317,
974
+ "loss": 0.4857,
975
+ "step": 3450
976
+ },
977
+ {
978
+ "epoch": 0.784867306606437,
979
+ "grad_norm": 0.08425033092498779,
980
+ "learning_rate": 0.00017315809678364777,
981
+ "loss": 0.6305,
982
+ "step": 3475
983
+ },
984
+ {
985
+ "epoch": 0.7905138339920948,
986
+ "grad_norm": 0.10775783658027649,
987
+ "learning_rate": 0.00017274108309288594,
988
+ "loss": 0.5013,
989
+ "step": 3500
990
+ },
991
+ {
992
+ "epoch": 0.7961603613777527,
993
+ "grad_norm": 0.082928866147995,
994
+ "learning_rate": 0.00017232136549611416,
995
+ "loss": 0.6217,
996
+ "step": 3525
997
+ },
998
+ {
999
+ "epoch": 0.8018068887634106,
1000
+ "grad_norm": 0.09590538591146469,
1001
+ "learning_rate": 0.00017189895959492772,
1002
+ "loss": 0.4871,
1003
+ "step": 3550
1004
+ },
1005
+ {
1006
+ "epoch": 0.8074534161490683,
1007
+ "grad_norm": 0.08597232401371002,
1008
+ "learning_rate": 0.00017147388109085048,
1009
+ "loss": 0.6298,
1010
+ "step": 3575
1011
+ },
1012
+ {
1013
+ "epoch": 0.8130999435347261,
1014
+ "grad_norm": 0.10229629278182983,
1015
+ "learning_rate": 0.00017104614578475135,
1016
+ "loss": 0.5191,
1017
+ "step": 3600
1018
+ },
1019
+ {
1020
+ "epoch": 0.818746470920384,
1021
+ "grad_norm": 0.09689701348543167,
1022
+ "learning_rate": 0.0001706157695762571,
1023
+ "loss": 0.6087,
1024
+ "step": 3625
1025
+ },
1026
+ {
1027
+ "epoch": 0.8243929983060417,
1028
+ "grad_norm": 0.1155649945139885,
1029
+ "learning_rate": 0.000170182768463161,
1030
+ "loss": 0.5237,
1031
+ "step": 3650
1032
+ },
1033
+ {
1034
+ "epoch": 0.8300395256916996,
1035
+ "grad_norm": 0.08635739237070084,
1036
+ "learning_rate": 0.00016974715854082848,
1037
+ "loss": 0.6337,
1038
+ "step": 3675
1039
+ },
1040
+ {
1041
+ "epoch": 0.8356860530773574,
1042
+ "grad_norm": 0.08977790176868439,
1043
+ "learning_rate": 0.00016930895600159867,
1044
+ "loss": 0.4942,
1045
+ "step": 3700
1046
+ },
1047
+ {
1048
+ "epoch": 0.8413325804630153,
1049
+ "grad_norm": 0.08372893184423447,
1050
+ "learning_rate": 0.00016886817713418264,
1051
+ "loss": 0.6224,
1052
+ "step": 3725
1053
+ },
1054
+ {
1055
+ "epoch": 0.846979107848673,
1056
+ "grad_norm": 0.09409157931804657,
1057
+ "learning_rate": 0.00016842483832305765,
1058
+ "loss": 0.4948,
1059
+ "step": 3750
1060
+ },
1061
+ {
1062
+ "epoch": 0.8526256352343309,
1063
+ "grad_norm": 0.0824190303683281,
1064
+ "learning_rate": 0.00016797895604785842,
1065
+ "loss": 0.6188,
1066
+ "step": 3775
1067
+ },
1068
+ {
1069
+ "epoch": 0.8582721626199887,
1070
+ "grad_norm": 0.11509312689304352,
1071
+ "learning_rate": 0.0001675305468827644,
1072
+ "loss": 0.513,
1073
+ "step": 3800
1074
+ },
1075
+ {
1076
+ "epoch": 0.8639186900056465,
1077
+ "grad_norm": 0.08958346396684647,
1078
+ "learning_rate": 0.0001670796274958837,
1079
+ "loss": 0.6206,
1080
+ "step": 3825
1081
+ },
1082
+ {
1083
+ "epoch": 0.8695652173913043,
1084
+ "grad_norm": 0.0959952101111412,
1085
+ "learning_rate": 0.00016662621464863338,
1086
+ "loss": 0.4885,
1087
+ "step": 3850
1088
+ },
1089
+ {
1090
+ "epoch": 0.8752117447769622,
1091
+ "grad_norm": 0.11436719447374344,
1092
+ "learning_rate": 0.00016617032519511686,
1093
+ "loss": 0.635,
1094
+ "step": 3875
1095
+ },
1096
+ {
1097
+ "epoch": 0.88085827216262,
1098
+ "grad_norm": 0.11012863367795944,
1099
+ "learning_rate": 0.00016571197608149674,
1100
+ "loss": 0.4982,
1101
+ "step": 3900
1102
+ },
1103
+ {
1104
+ "epoch": 0.8865047995482778,
1105
+ "grad_norm": 0.08522720634937286,
1106
+ "learning_rate": 0.00016525118434536546,
1107
+ "loss": 0.6105,
1108
+ "step": 3925
1109
+ },
1110
+ {
1111
+ "epoch": 0.8921513269339356,
1112
+ "grad_norm": 0.11074435710906982,
1113
+ "learning_rate": 0.00016478796711511171,
1114
+ "loss": 0.5007,
1115
+ "step": 3950
1116
+ },
1117
+ {
1118
+ "epoch": 0.8977978543195935,
1119
+ "grad_norm": 0.08319137990474701,
1120
+ "learning_rate": 0.00016432234160928378,
1121
+ "loss": 0.6008,
1122
+ "step": 3975
1123
+ },
1124
+ {
1125
+ "epoch": 0.9034443817052513,
1126
+ "grad_norm": 0.11340347677469254,
1127
+ "learning_rate": 0.00016385432513594953,
1128
+ "loss": 0.502,
1129
+ "step": 4000
1130
+ },
1131
+ {
1132
+ "epoch": 0.9090909090909091,
1133
+ "grad_norm": 0.08557943999767303,
1134
+ "learning_rate": 0.0001633839350920531,
1135
+ "loss": 0.598,
1136
+ "step": 4025
1137
+ },
1138
+ {
1139
+ "epoch": 0.9147374364765669,
1140
+ "grad_norm": 0.09813399612903595,
1141
+ "learning_rate": 0.00016291118896276803,
1142
+ "loss": 0.5139,
1143
+ "step": 4050
1144
+ },
1145
+ {
1146
+ "epoch": 0.9203839638622248,
1147
+ "grad_norm": 0.07974950224161148,
1148
+ "learning_rate": 0.00016243610432084755,
1149
+ "loss": 0.6227,
1150
+ "step": 4075
1151
+ },
1152
+ {
1153
+ "epoch": 0.9260304912478825,
1154
+ "grad_norm": 0.09820155799388885,
1155
+ "learning_rate": 0.0001619586988259712,
1156
+ "loss": 0.5044,
1157
+ "step": 4100
1158
+ },
1159
+ {
1160
+ "epoch": 0.9316770186335404,
1161
+ "grad_norm": 0.0881289690732956,
1162
+ "learning_rate": 0.00016147899022408852,
1163
+ "loss": 0.6192,
1164
+ "step": 4125
1165
+ },
1166
+ {
1167
+ "epoch": 0.9373235460191982,
1168
+ "grad_norm": 0.11012347787618637,
1169
+ "learning_rate": 0.00016099699634675925,
1170
+ "loss": 0.508,
1171
+ "step": 4150
1172
+ },
1173
+ {
1174
+ "epoch": 0.9429700734048561,
1175
+ "grad_norm": 0.0851251408457756,
1176
+ "learning_rate": 0.00016051273511049065,
1177
+ "loss": 0.5897,
1178
+ "step": 4175
1179
+ },
1180
+ {
1181
+ "epoch": 0.9486166007905138,
1182
+ "grad_norm": 0.10288140922784805,
1183
+ "learning_rate": 0.0001600262245160714,
1184
+ "loss": 0.4803,
1185
+ "step": 4200
1186
+ },
1187
+ {
1188
+ "epoch": 0.9542631281761716,
1189
+ "grad_norm": 0.08995950222015381,
1190
+ "learning_rate": 0.0001595374826479026,
1191
+ "loss": 0.6203,
1192
+ "step": 4225
1193
+ },
1194
+ {
1195
+ "epoch": 0.9599096555618295,
1196
+ "grad_norm": 0.10717281699180603,
1197
+ "learning_rate": 0.00015904652767332537,
1198
+ "loss": 0.5068,
1199
+ "step": 4250
1200
+ },
1201
+ {
1202
+ "epoch": 0.9655561829474872,
1203
+ "grad_norm": 0.08305976539850235,
1204
+ "learning_rate": 0.00015855337784194577,
1205
+ "loss": 0.5919,
1206
+ "step": 4275
1207
+ },
1208
+ {
1209
+ "epoch": 0.9712027103331451,
1210
+ "grad_norm": 0.09328145533800125,
1211
+ "learning_rate": 0.00015805805148495623,
1212
+ "loss": 0.4948,
1213
+ "step": 4300
1214
+ },
1215
+ {
1216
+ "epoch": 0.9768492377188029,
1217
+ "grad_norm": 0.09493458271026611,
1218
+ "learning_rate": 0.00015756056701445422,
1219
+ "loss": 0.6024,
1220
+ "step": 4325
1221
+ },
1222
+ {
1223
+ "epoch": 0.9824957651044608,
1224
+ "grad_norm": 0.1051265150308609,
1225
+ "learning_rate": 0.0001570609429227579,
1226
+ "loss": 0.4991,
1227
+ "step": 4350
1228
+ },
1229
+ {
1230
+ "epoch": 0.9881422924901185,
1231
+ "grad_norm": 0.09176123887300491,
1232
+ "learning_rate": 0.00015655919778171862,
1233
+ "loss": 0.6006,
1234
+ "step": 4375
1235
+ },
1236
+ {
1237
+ "epoch": 0.9937888198757764,
1238
+ "grad_norm": 0.0787501335144043,
1239
+ "learning_rate": 0.00015605535024203069,
1240
+ "loss": 0.5013,
1241
+ "step": 4400
1242
+ },
1243
+ {
1244
+ "epoch": 0.9994353472614342,
1245
+ "grad_norm": 0.10489033907651901,
1246
+ "learning_rate": 0.00015554941903253797,
1247
+ "loss": 0.5548,
1248
+ "step": 4425
1249
+ },
1250
+ {
1251
+ "epoch": 1.005081874647092,
1252
+ "grad_norm": 0.08116624504327774,
1253
+ "learning_rate": 0.00015504142295953783,
1254
+ "loss": 0.5719,
1255
+ "step": 4450
1256
+ },
1257
+ {
1258
+ "epoch": 1.0107284020327498,
1259
+ "grad_norm": 0.09656750410795212,
1260
+ "learning_rate": 0.000154531380906082,
1261
+ "loss": 0.4752,
1262
+ "step": 4475
1263
+ },
1264
+ {
1265
+ "epoch": 1.0163749294184077,
1266
+ "grad_norm": 0.09433398395776749,
1267
+ "learning_rate": 0.0001540193118312747,
1268
+ "loss": 0.5796,
1269
+ "step": 4500
1270
+ },
1271
+ {
1272
+ "epoch": 1.0220214568040655,
1273
+ "grad_norm": 0.10783005505800247,
1274
+ "learning_rate": 0.0001535052347695678,
1275
+ "loss": 0.5077,
1276
+ "step": 4525
1277
+ },
1278
+ {
1279
+ "epoch": 1.0276679841897234,
1280
+ "grad_norm": 0.08784560114145279,
1281
+ "learning_rate": 0.00015298916883005342,
1282
+ "loss": 0.5571,
1283
+ "step": 4550
1284
+ },
1285
+ {
1286
+ "epoch": 1.0333145115753812,
1287
+ "grad_norm": 0.11868823319673538,
1288
+ "learning_rate": 0.00015247113319575358,
1289
+ "loss": 0.5223,
1290
+ "step": 4575
1291
+ },
1292
+ {
1293
+ "epoch": 1.0389610389610389,
1294
+ "grad_norm": 0.08813630044460297,
1295
+ "learning_rate": 0.000151951147122907,
1296
+ "loss": 0.561,
1297
+ "step": 4600
1298
+ },
1299
+ {
1300
+ "epoch": 1.0446075663466967,
1301
+ "grad_norm": 0.09996681660413742,
1302
+ "learning_rate": 0.0001514292299402535,
1303
+ "loss": 0.5138,
1304
+ "step": 4625
1305
+ },
1306
+ {
1307
+ "epoch": 1.0502540937323546,
1308
+ "grad_norm": 0.07442251592874527,
1309
+ "learning_rate": 0.00015090540104831539,
1310
+ "loss": 0.5698,
1311
+ "step": 4650
1312
+ },
1313
+ {
1314
+ "epoch": 1.0559006211180124,
1315
+ "grad_norm": 0.09993384033441544,
1316
+ "learning_rate": 0.00015037967991867642,
1317
+ "loss": 0.5093,
1318
+ "step": 4675
1319
+ },
1320
+ {
1321
+ "epoch": 1.0615471485036703,
1322
+ "grad_norm": 0.0890798568725586,
1323
+ "learning_rate": 0.0001498520860932579,
1324
+ "loss": 0.5481,
1325
+ "step": 4700
1326
+ },
1327
+ {
1328
+ "epoch": 1.0671936758893281,
1329
+ "grad_norm": 0.1006857305765152,
1330
+ "learning_rate": 0.00014932263918359228,
1331
+ "loss": 0.5045,
1332
+ "step": 4725
1333
+ },
1334
+ {
1335
+ "epoch": 1.072840203274986,
1336
+ "grad_norm": 0.08858868479728699,
1337
+ "learning_rate": 0.00014879135887009435,
1338
+ "loss": 0.5772,
1339
+ "step": 4750
1340
+ },
1341
+ {
1342
+ "epoch": 1.0784867306606438,
1343
+ "grad_norm": 0.11783988773822784,
1344
+ "learning_rate": 0.00014825826490132938,
1345
+ "loss": 0.4937,
1346
+ "step": 4775
1347
+ },
1348
+ {
1349
+ "epoch": 1.0841332580463015,
1350
+ "grad_norm": 0.0875164121389389,
1351
+ "learning_rate": 0.00014772337709327923,
1352
+ "loss": 0.5554,
1353
+ "step": 4800
1354
+ },
1355
+ {
1356
+ "epoch": 1.0897797854319593,
1357
+ "grad_norm": 0.112996406853199,
1358
+ "learning_rate": 0.00014718671532860592,
1359
+ "loss": 0.5126,
1360
+ "step": 4825
1361
+ },
1362
+ {
1363
+ "epoch": 1.0954263128176172,
1364
+ "grad_norm": 0.08834437280893326,
1365
+ "learning_rate": 0.000146648299555912,
1366
+ "loss": 0.5885,
1367
+ "step": 4850
1368
+ },
1369
+ {
1370
+ "epoch": 1.101072840203275,
1371
+ "grad_norm": 0.11341985315084457,
1372
+ "learning_rate": 0.00014610814978899983,
1373
+ "loss": 0.4871,
1374
+ "step": 4875
1375
+ },
1376
+ {
1377
+ "epoch": 1.1067193675889329,
1378
+ "grad_norm": 0.09301973134279251,
1379
+ "learning_rate": 0.00014556628610612677,
1380
+ "loss": 0.5839,
1381
+ "step": 4900
1382
+ },
1383
+ {
1384
+ "epoch": 1.1123658949745907,
1385
+ "grad_norm": 0.11545081436634064,
1386
+ "learning_rate": 0.00014502272864925955,
1387
+ "loss": 0.4868,
1388
+ "step": 4925
1389
+ },
1390
+ {
1391
+ "epoch": 1.1180124223602483,
1392
+ "grad_norm": 0.08969846367835999,
1393
+ "learning_rate": 0.00014447749762332515,
1394
+ "loss": 0.5472,
1395
+ "step": 4950
1396
+ },
1397
+ {
1398
+ "epoch": 1.1236589497459062,
1399
+ "grad_norm": 0.12094131112098694,
1400
+ "learning_rate": 0.00014393061329545992,
1401
+ "loss": 0.5234,
1402
+ "step": 4975
1403
+ },
1404
+ {
1405
+ "epoch": 1.129305477131564,
1406
+ "grad_norm": 0.0875294953584671,
1407
+ "learning_rate": 0.0001433820959942561,
1408
+ "loss": 0.5852,
1409
+ "step": 5000
1410
+ },
1411
+ {
1412
+ "epoch": 1.134952004517222,
1413
+ "grad_norm": 0.12163736671209335,
1414
+ "learning_rate": 0.00014283196610900638,
1415
+ "loss": 0.4951,
1416
+ "step": 5025
1417
+ },
1418
+ {
1419
+ "epoch": 1.1405985319028797,
1420
+ "grad_norm": 0.08404785394668579,
1421
+ "learning_rate": 0.00014230234328167044,
1422
+ "loss": 0.5629,
1423
+ "step": 5050
1424
+ },
1425
+ {
1426
+ "epoch": 1.1462450592885376,
1427
+ "grad_norm": 0.11473394185304642,
1428
+ "learning_rate": 0.0001417491121057749,
1429
+ "loss": 0.5062,
1430
+ "step": 5075
1431
+ },
1432
+ {
1433
+ "epoch": 1.1518915866741954,
1434
+ "grad_norm": 0.09582609683275223,
1435
+ "learning_rate": 0.0001411943290465374,
1436
+ "loss": 0.5705,
1437
+ "step": 5100
1438
+ },
1439
+ {
1440
+ "epoch": 1.1575381140598533,
1441
+ "grad_norm": 0.11270004510879517,
1442
+ "learning_rate": 0.00014063801472615902,
1443
+ "loss": 0.4918,
1444
+ "step": 5125
1445
+ },
1446
+ {
1447
+ "epoch": 1.163184641445511,
1448
+ "grad_norm": 0.2396761178970337,
1449
+ "learning_rate": 0.00014008018982376044,
1450
+ "loss": 0.5965,
1451
+ "step": 5150
1452
+ },
1453
+ {
1454
+ "epoch": 1.1688311688311688,
1455
+ "grad_norm": 0.1252664476633072,
1456
+ "learning_rate": 0.00013952087507461321,
1457
+ "loss": 0.4814,
1458
+ "step": 5175
1459
+ },
1460
+ {
1461
+ "epoch": 1.1744776962168266,
1462
+ "grad_norm": 0.10077520459890366,
1463
+ "learning_rate": 0.0001389600912693688,
1464
+ "loss": 0.5723,
1465
+ "step": 5200
1466
+ },
1467
+ {
1468
+ "epoch": 1.1801242236024845,
1469
+ "grad_norm": 0.10539643466472626,
1470
+ "learning_rate": 0.00013839785925328605,
1471
+ "loss": 0.4476,
1472
+ "step": 5225
1473
+ },
1474
+ {
1475
+ "epoch": 1.1857707509881423,
1476
+ "grad_norm": 0.0933731198310852,
1477
+ "learning_rate": 0.0001378341999254561,
1478
+ "loss": 0.5683,
1479
+ "step": 5250
1480
+ },
1481
+ {
1482
+ "epoch": 1.1914172783738002,
1483
+ "grad_norm": 0.12707217037677765,
1484
+ "learning_rate": 0.00013726913423802562,
1485
+ "loss": 0.5142,
1486
+ "step": 5275
1487
+ },
1488
+ {
1489
+ "epoch": 1.1970638057594578,
1490
+ "grad_norm": 0.08691050857305527,
1491
+ "learning_rate": 0.0001367026831954181,
1492
+ "loss": 0.5628,
1493
+ "step": 5300
1494
+ },
1495
+ {
1496
+ "epoch": 1.2027103331451157,
1497
+ "grad_norm": 0.10984601825475693,
1498
+ "learning_rate": 0.0001361348678535528,
1499
+ "loss": 0.4924,
1500
+ "step": 5325
1501
+ },
1502
+ {
1503
+ "epoch": 1.2083568605307735,
1504
+ "grad_norm": 0.10582837462425232,
1505
+ "learning_rate": 0.00013556570931906232,
1506
+ "loss": 0.5564,
1507
+ "step": 5350
1508
+ },
1509
+ {
1510
+ "epoch": 1.2140033879164314,
1511
+ "grad_norm": 0.1085626408457756,
1512
+ "learning_rate": 0.000134995228748508,
1513
+ "loss": 0.492,
1514
+ "step": 5375
1515
+ },
1516
+ {
1517
+ "epoch": 1.2196499153020892,
1518
+ "grad_norm": 0.11668406426906586,
1519
+ "learning_rate": 0.00013442344734759332,
1520
+ "loss": 0.5651,
1521
+ "step": 5400
1522
+ },
1523
+ {
1524
+ "epoch": 1.225296442687747,
1525
+ "grad_norm": 0.10734312981367111,
1526
+ "learning_rate": 0.00013385038637037585,
1527
+ "loss": 0.4848,
1528
+ "step": 5425
1529
+ },
1530
+ {
1531
+ "epoch": 1.230942970073405,
1532
+ "grad_norm": 0.10206615924835205,
1533
+ "learning_rate": 0.00013327606711847713,
1534
+ "loss": 0.5739,
1535
+ "step": 5450
1536
+ },
1537
+ {
1538
+ "epoch": 1.2365894974590628,
1539
+ "grad_norm": 0.11335214227437973,
1540
+ "learning_rate": 0.00013270051094029075,
1541
+ "loss": 0.4757,
1542
+ "step": 5475
1543
+ },
1544
+ {
1545
+ "epoch": 1.2422360248447206,
1546
+ "grad_norm": 0.10749132186174393,
1547
+ "learning_rate": 0.00013212373923018905,
1548
+ "loss": 0.5769,
1549
+ "step": 5500
1550
+ },
1551
+ {
1552
+ "epoch": 1.2478825522303783,
1553
+ "grad_norm": 0.13299238681793213,
1554
+ "learning_rate": 0.0001315457734277275,
1555
+ "loss": 0.4758,
1556
+ "step": 5525
1557
+ },
1558
+ {
1559
+ "epoch": 1.253529079616036,
1560
+ "grad_norm": 0.09394491463899612,
1561
+ "learning_rate": 0.00013096663501684813,
1562
+ "loss": 0.5465,
1563
+ "step": 5550
1564
+ },
1565
+ {
1566
+ "epoch": 1.259175607001694,
1567
+ "grad_norm": 0.11942502111196518,
1568
+ "learning_rate": 0.00013038634552508063,
1569
+ "loss": 0.478,
1570
+ "step": 5575
1571
+ },
1572
+ {
1573
+ "epoch": 1.2648221343873518,
1574
+ "grad_norm": 0.09682100266218185,
1575
+ "learning_rate": 0.00012980492652274234,
1576
+ "loss": 0.5667,
1577
+ "step": 5600
1578
+ },
1579
+ {
1580
+ "epoch": 1.2704686617730097,
1581
+ "grad_norm": 0.1254328489303589,
1582
+ "learning_rate": 0.00012922239962213637,
1583
+ "loss": 0.5116,
1584
+ "step": 5625
1585
+ },
1586
+ {
1587
+ "epoch": 1.2761151891586673,
1588
+ "grad_norm": 0.09513936936855316,
1589
+ "learning_rate": 0.00012863878647674816,
1590
+ "loss": 0.5433,
1591
+ "step": 5650
1592
+ },
1593
+ {
1594
+ "epoch": 1.2817617165443251,
1595
+ "grad_norm": 0.10922129452228546,
1596
+ "learning_rate": 0.00012805410878044074,
1597
+ "loss": 0.4867,
1598
+ "step": 5675
1599
+ },
1600
+ {
1601
+ "epoch": 1.287408243929983,
1602
+ "grad_norm": 0.09911426901817322,
1603
+ "learning_rate": 0.00012746838826664826,
1604
+ "loss": 0.5785,
1605
+ "step": 5700
1606
+ },
1607
+ {
1608
+ "epoch": 1.2930547713156408,
1609
+ "grad_norm": 0.11289256066083908,
1610
+ "learning_rate": 0.00012688164670756802,
1611
+ "loss": 0.4761,
1612
+ "step": 5725
1613
+ },
1614
+ {
1615
+ "epoch": 1.2987012987012987,
1616
+ "grad_norm": 0.08862913399934769,
1617
+ "learning_rate": 0.00012629390591335134,
1618
+ "loss": 0.5743,
1619
+ "step": 5750
1620
+ },
1621
+ {
1622
+ "epoch": 1.3043478260869565,
1623
+ "grad_norm": 0.13005360960960388,
1624
+ "learning_rate": 0.00012570518773129277,
1625
+ "loss": 0.49,
1626
+ "step": 5775
1627
+ },
1628
+ {
1629
+ "epoch": 1.3099943534726144,
1630
+ "grad_norm": 0.08972469717264175,
1631
+ "learning_rate": 0.0001251155140450179,
1632
+ "loss": 0.5443,
1633
+ "step": 5800
1634
+ },
1635
+ {
1636
+ "epoch": 1.3156408808582722,
1637
+ "grad_norm": 0.11599931865930557,
1638
+ "learning_rate": 0.00012452490677367003,
1639
+ "loss": 0.5138,
1640
+ "step": 5825
1641
+ },
1642
+ {
1643
+ "epoch": 1.32128740824393,
1644
+ "grad_norm": 0.096194326877594,
1645
+ "learning_rate": 0.0001239333878710954,
1646
+ "loss": 0.5524,
1647
+ "step": 5850
1648
+ },
1649
+ {
1650
+ "epoch": 1.3269339356295877,
1651
+ "grad_norm": 0.11309222131967545,
1652
+ "learning_rate": 0.00012334097932502702,
1653
+ "loss": 0.485,
1654
+ "step": 5875
1655
+ },
1656
+ {
1657
+ "epoch": 1.3325804630152456,
1658
+ "grad_norm": 0.09447719901800156,
1659
+ "learning_rate": 0.00012274770315626743,
1660
+ "loss": 0.5748,
1661
+ "step": 5900
1662
+ },
1663
+ {
1664
+ "epoch": 1.3382269904009034,
1665
+ "grad_norm": 0.11994371563196182,
1666
+ "learning_rate": 0.00012215358141787016,
1667
+ "loss": 0.4826,
1668
+ "step": 5925
1669
+ },
1670
+ {
1671
+ "epoch": 1.3438735177865613,
1672
+ "grad_norm": 0.10158982127904892,
1673
+ "learning_rate": 0.00012155863619431993,
1674
+ "loss": 0.5593,
1675
+ "step": 5950
1676
+ },
1677
+ {
1678
+ "epoch": 1.3495200451722191,
1679
+ "grad_norm": 0.1210799366235733,
1680
+ "learning_rate": 0.00012096288960071178,
1681
+ "loss": 0.4977,
1682
+ "step": 5975
1683
+ },
1684
+ {
1685
+ "epoch": 1.355166572557877,
1686
+ "grad_norm": 0.0946585088968277,
1687
+ "learning_rate": 0.00012036636378192902,
1688
+ "loss": 0.5617,
1689
+ "step": 6000
1690
+ },
1691
+ {
1692
+ "epoch": 1.3608130999435346,
1693
+ "grad_norm": 0.10858285427093506,
1694
+ "learning_rate": 0.00011976908091181998,
1695
+ "loss": 0.468,
1696
+ "step": 6025
1697
+ },
1698
+ {
1699
+ "epoch": 1.3664596273291925,
1700
+ "grad_norm": 0.08753529191017151,
1701
+ "learning_rate": 0.00011917106319237386,
1702
+ "loss": 0.5854,
1703
+ "step": 6050
1704
+ },
1705
+ {
1706
+ "epoch": 1.3721061547148503,
1707
+ "grad_norm": 0.1213916763663292,
1708
+ "learning_rate": 0.00011857233285289546,
1709
+ "loss": 0.4915,
1710
+ "step": 6075
1711
+ },
1712
+ {
1713
+ "epoch": 1.3777526821005082,
1714
+ "grad_norm": 0.09568001329898834,
1715
+ "learning_rate": 0.00011797291214917881,
1716
+ "loss": 0.5699,
1717
+ "step": 6100
1718
+ },
1719
+ {
1720
+ "epoch": 1.383399209486166,
1721
+ "grad_norm": 0.10872907191514969,
1722
+ "learning_rate": 0.00011737282336267992,
1723
+ "loss": 0.4744,
1724
+ "step": 6125
1725
+ },
1726
+ {
1727
+ "epoch": 1.3890457368718239,
1728
+ "grad_norm": 0.1102764755487442,
1729
+ "learning_rate": 0.00011677208879968858,
1730
+ "loss": 0.5315,
1731
+ "step": 6150
1732
+ },
1733
+ {
1734
+ "epoch": 1.3946922642574817,
1735
+ "grad_norm": 0.1172797903418541,
1736
+ "learning_rate": 0.00011617073079049905,
1737
+ "loss": 0.493,
1738
+ "step": 6175
1739
+ },
1740
+ {
1741
+ "epoch": 1.4003387916431396,
1742
+ "grad_norm": 0.09269782900810242,
1743
+ "learning_rate": 0.0001155687716885802,
1744
+ "loss": 0.5383,
1745
+ "step": 6200
1746
+ },
1747
+ {
1748
+ "epoch": 1.4059853190287974,
1749
+ "grad_norm": 0.11610530316829681,
1750
+ "learning_rate": 0.00011496623386974454,
1751
+ "loss": 0.4748,
1752
+ "step": 6225
1753
+ },
1754
+ {
1755
+ "epoch": 1.411631846414455,
1756
+ "grad_norm": 0.10046471655368805,
1757
+ "learning_rate": 0.00011436313973131634,
1758
+ "loss": 0.5397,
1759
+ "step": 6250
1760
+ },
1761
+ {
1762
+ "epoch": 1.417278373800113,
1763
+ "grad_norm": 0.1363869458436966,
1764
+ "learning_rate": 0.00011375951169129926,
1765
+ "loss": 0.4944,
1766
+ "step": 6275
1767
+ },
1768
+ {
1769
+ "epoch": 1.4229249011857708,
1770
+ "grad_norm": 0.09395238012075424,
1771
+ "learning_rate": 0.00011315537218754295,
1772
+ "loss": 0.5614,
1773
+ "step": 6300
1774
+ },
1775
+ {
1776
+ "epoch": 1.4285714285714286,
1777
+ "grad_norm": 0.11986027657985687,
1778
+ "learning_rate": 0.00011255074367690897,
1779
+ "loss": 0.4914,
1780
+ "step": 6325
1781
+ },
1782
+ {
1783
+ "epoch": 1.4342179559570865,
1784
+ "grad_norm": 0.0886669009923935,
1785
+ "learning_rate": 0.0001119456486344361,
1786
+ "loss": 0.5615,
1787
+ "step": 6350
1788
+ },
1789
+ {
1790
+ "epoch": 1.439864483342744,
1791
+ "grad_norm": 0.12676212191581726,
1792
+ "learning_rate": 0.00011134010955250491,
1793
+ "loss": 0.4836,
1794
+ "step": 6375
1795
+ },
1796
+ {
1797
+ "epoch": 1.445511010728402,
1798
+ "grad_norm": 0.09607352316379547,
1799
+ "learning_rate": 0.00011073414894000161,
1800
+ "loss": 0.5505,
1801
+ "step": 6400
1802
+ },
1803
+ {
1804
+ "epoch": 1.4511575381140598,
1805
+ "grad_norm": 0.12430471181869507,
1806
+ "learning_rate": 0.00011012778932148142,
1807
+ "loss": 0.4949,
1808
+ "step": 6425
1809
+ },
1810
+ {
1811
+ "epoch": 1.4568040654997176,
1812
+ "grad_norm": 0.10339995473623276,
1813
+ "learning_rate": 0.00010952105323633126,
1814
+ "loss": 0.5583,
1815
+ "step": 6450
1816
+ },
1817
+ {
1818
+ "epoch": 1.4624505928853755,
1819
+ "grad_norm": 0.11074826866388321,
1820
+ "learning_rate": 0.00010891396323793189,
1821
+ "loss": 0.4973,
1822
+ "step": 6475
1823
+ },
1824
+ {
1825
+ "epoch": 1.4680971202710333,
1826
+ "grad_norm": 0.09366384148597717,
1827
+ "learning_rate": 0.00010830654189281968,
1828
+ "loss": 0.5329,
1829
+ "step": 6500
1830
+ },
1831
+ {
1832
+ "epoch": 1.4737436476566912,
1833
+ "grad_norm": 0.12167912721633911,
1834
+ "learning_rate": 0.00010769881177984771,
1835
+ "loss": 0.4901,
1836
+ "step": 6525
1837
+ },
1838
+ {
1839
+ "epoch": 1.479390175042349,
1840
+ "grad_norm": 0.09269159287214279,
1841
+ "learning_rate": 0.0001070907954893464,
1842
+ "loss": 0.5685,
1843
+ "step": 6550
1844
+ },
1845
+ {
1846
+ "epoch": 1.485036702428007,
1847
+ "grad_norm": 0.11428316682577133,
1848
+ "learning_rate": 0.00010648251562228386,
1849
+ "loss": 0.5,
1850
+ "step": 6575
1851
+ },
1852
+ {
1853
+ "epoch": 1.4906832298136645,
1854
+ "grad_norm": 0.10255276411771774,
1855
+ "learning_rate": 0.00010587399478942592,
1856
+ "loss": 0.5492,
1857
+ "step": 6600
1858
+ },
1859
+ {
1860
+ "epoch": 1.4963297571993224,
1861
+ "grad_norm": 0.10394936800003052,
1862
+ "learning_rate": 0.0001052652556104953,
1863
+ "loss": 0.4788,
1864
+ "step": 6625
1865
+ },
1866
+ {
1867
+ "epoch": 1.5019762845849802,
1868
+ "grad_norm": 0.0881161019206047,
1869
+ "learning_rate": 0.00010465632071333113,
1870
+ "loss": 0.5606,
1871
+ "step": 6650
1872
+ },
1873
+ {
1874
+ "epoch": 1.507622811970638,
1875
+ "grad_norm": 0.1109280213713646,
1876
+ "learning_rate": 0.00010404721273304769,
1877
+ "loss": 0.5183,
1878
+ "step": 6675
1879
+ },
1880
+ {
1881
+ "epoch": 1.513269339356296,
1882
+ "grad_norm": 0.10558915883302689,
1883
+ "learning_rate": 0.00010343795431119304,
1884
+ "loss": 0.5563,
1885
+ "step": 6700
1886
+ },
1887
+ {
1888
+ "epoch": 1.5189158667419536,
1889
+ "grad_norm": 0.13079263269901276,
1890
+ "learning_rate": 0.00010282856809490739,
1891
+ "loss": 0.4977,
1892
+ "step": 6725
1893
+ },
1894
+ {
1895
+ "epoch": 1.5245623941276114,
1896
+ "grad_norm": 0.09773046523332596,
1897
+ "learning_rate": 0.00010221907673608133,
1898
+ "loss": 0.5698,
1899
+ "step": 6750
1900
+ },
1901
+ {
1902
+ "epoch": 1.5302089215132693,
1903
+ "grad_norm": 0.11996293067932129,
1904
+ "learning_rate": 0.00010160950289051365,
1905
+ "loss": 0.4764,
1906
+ "step": 6775
1907
+ },
1908
+ {
1909
+ "epoch": 1.5358554488989271,
1910
+ "grad_norm": 0.12360116094350815,
1911
+ "learning_rate": 0.00010099986921706946,
1912
+ "loss": 0.5274,
1913
+ "step": 6800
1914
+ },
1915
+ {
1916
+ "epoch": 1.541501976284585,
1917
+ "grad_norm": 0.1305209845304489,
1918
+ "learning_rate": 0.00010039019837683767,
1919
+ "loss": 0.4531,
1920
+ "step": 6825
1921
+ },
1922
+ {
1923
+ "epoch": 1.5471485036702428,
1924
+ "grad_norm": 0.10246080160140991,
1925
+ "learning_rate": 9.978051303228875e-05,
1926
+ "loss": 0.5593,
1927
+ "step": 6850
1928
+ },
1929
+ {
1930
+ "epoch": 1.5527950310559007,
1931
+ "grad_norm": 0.13810117542743683,
1932
+ "learning_rate": 9.917083584643235e-05,
1933
+ "loss": 0.4838,
1934
+ "step": 6875
1935
+ },
1936
+ {
1937
+ "epoch": 1.5584415584415585,
1938
+ "grad_norm": 0.10199406743049622,
1939
+ "learning_rate": 9.856118948197488e-05,
1940
+ "loss": 0.5405,
1941
+ "step": 6900
1942
+ },
1943
+ {
1944
+ "epoch": 1.5640880858272164,
1945
+ "grad_norm": 0.11060495674610138,
1946
+ "learning_rate": 9.795159660047697e-05,
1947
+ "loss": 0.4974,
1948
+ "step": 6925
1949
+ },
1950
+ {
1951
+ "epoch": 1.5697346132128742,
1952
+ "grad_norm": 0.10460948944091797,
1953
+ "learning_rate": 9.734207986151126e-05,
1954
+ "loss": 0.5568,
1955
+ "step": 6950
1956
+ },
1957
+ {
1958
+ "epoch": 1.5753811405985318,
1959
+ "grad_norm": 0.11652641743421555,
1960
+ "learning_rate": 9.673266192182008e-05,
1961
+ "loss": 0.4683,
1962
+ "step": 6975
1963
+ },
1964
+ {
1965
+ "epoch": 1.5810276679841897,
1966
+ "grad_norm": 0.09894441068172455,
1967
+ "learning_rate": 9.612336543447314e-05,
1968
+ "loss": 0.5598,
1969
+ "step": 7000
1970
+ },
1971
+ {
1972
+ "epoch": 1.5866741953698476,
1973
+ "grad_norm": 0.10987823456525803,
1974
+ "learning_rate": 9.551421304802565e-05,
1975
+ "loss": 0.4582,
1976
+ "step": 7025
1977
+ },
1978
+ {
1979
+ "epoch": 1.5923207227555054,
1980
+ "grad_norm": 0.09542589634656906,
1981
+ "learning_rate": 9.490522740567633e-05,
1982
+ "loss": 0.5482,
1983
+ "step": 7050
1984
+ },
1985
+ {
1986
+ "epoch": 1.597967250141163,
1987
+ "grad_norm": 0.12428826838731766,
1988
+ "learning_rate": 9.42964311444257e-05,
1989
+ "loss": 0.4999,
1990
+ "step": 7075
1991
+ },
1992
+ {
1993
+ "epoch": 1.6036137775268209,
1994
+ "grad_norm": 0.10819413512945175,
1995
+ "learning_rate": 9.368784689423467e-05,
1996
+ "loss": 0.5652,
1997
+ "step": 7100
1998
+ },
1999
+ {
2000
+ "epoch": 1.6092603049124787,
2001
+ "grad_norm": 0.13115598261356354,
2002
+ "learning_rate": 9.307949727718346e-05,
2003
+ "loss": 0.4771,
2004
+ "step": 7125
2005
+ },
2006
+ {
2007
+ "epoch": 1.6149068322981366,
2008
+ "grad_norm": 0.1047302857041359,
2009
+ "learning_rate": 9.24714049066305e-05,
2010
+ "loss": 0.5376,
2011
+ "step": 7150
2012
+ },
2013
+ {
2014
+ "epoch": 1.6205533596837944,
2015
+ "grad_norm": 0.13034017384052277,
2016
+ "learning_rate": 9.186359238637197e-05,
2017
+ "loss": 0.4863,
2018
+ "step": 7175
2019
+ },
2020
+ {
2021
+ "epoch": 1.6261998870694523,
2022
+ "grad_norm": 0.10137925297021866,
2023
+ "learning_rate": 9.12560823098015e-05,
2024
+ "loss": 0.5442,
2025
+ "step": 7200
2026
+ },
2027
+ {
2028
+ "epoch": 1.6318464144551101,
2029
+ "grad_norm": 0.12191277742385864,
2030
+ "learning_rate": 9.064889725907043e-05,
2031
+ "loss": 0.4717,
2032
+ "step": 7225
2033
+ },
2034
+ {
2035
+ "epoch": 1.637492941840768,
2036
+ "grad_norm": 0.10191314667463303,
2037
+ "learning_rate": 9.004205980424842e-05,
2038
+ "loss": 0.5457,
2039
+ "step": 7250
2040
+ },
2041
+ {
2042
+ "epoch": 1.6431394692264258,
2043
+ "grad_norm": 0.11787448078393936,
2044
+ "learning_rate": 8.943559250248426e-05,
2045
+ "loss": 0.4858,
2046
+ "step": 7275
2047
+ },
2048
+ {
2049
+ "epoch": 1.6487859966120837,
2050
+ "grad_norm": 0.1057475134730339,
2051
+ "learning_rate": 8.88295178971677e-05,
2052
+ "loss": 0.5735,
2053
+ "step": 7300
2054
+ },
2055
+ {
2056
+ "epoch": 1.6544325239977415,
2057
+ "grad_norm": 0.12938141822814941,
2058
+ "learning_rate": 8.822385851709125e-05,
2059
+ "loss": 0.4829,
2060
+ "step": 7325
2061
+ },
2062
+ {
2063
+ "epoch": 1.6600790513833992,
2064
+ "grad_norm": 0.10724066197872162,
2065
+ "learning_rate": 8.761863687561275e-05,
2066
+ "loss": 0.5408,
2067
+ "step": 7350
2068
+ },
2069
+ {
2070
+ "epoch": 1.665725578769057,
2071
+ "grad_norm": 0.11694779992103577,
2072
+ "learning_rate": 8.701387546981868e-05,
2073
+ "loss": 0.4961,
2074
+ "step": 7375
2075
+ },
2076
+ {
2077
+ "epoch": 1.6713721061547149,
2078
+ "grad_norm": 0.10590225458145142,
2079
+ "learning_rate": 8.640959677968778e-05,
2080
+ "loss": 0.5466,
2081
+ "step": 7400
2082
+ },
2083
+ {
2084
+ "epoch": 1.6770186335403725,
2085
+ "grad_norm": 0.11699523031711578,
2086
+ "learning_rate": 8.580582326725535e-05,
2087
+ "loss": 0.4709,
2088
+ "step": 7425
2089
+ },
2090
+ {
2091
+ "epoch": 1.6826651609260304,
2092
+ "grad_norm": 0.1064140573143959,
2093
+ "learning_rate": 8.520257737577854e-05,
2094
+ "loss": 0.5349,
2095
+ "step": 7450
2096
+ },
2097
+ {
2098
+ "epoch": 1.6883116883116882,
2099
+ "grad_norm": 0.12415055185556412,
2100
+ "learning_rate": 8.459988152890188e-05,
2101
+ "loss": 0.4655,
2102
+ "step": 7475
2103
+ },
2104
+ {
2105
+ "epoch": 1.693958215697346,
2106
+ "grad_norm": 0.11068243533372879,
2107
+ "learning_rate": 8.39977581298239e-05,
2108
+ "loss": 0.5459,
2109
+ "step": 7500
2110
+ },
2111
+ {
2112
+ "epoch": 1.699604743083004,
2113
+ "grad_norm": 0.12139423191547394,
2114
+ "learning_rate": 8.339622956046417e-05,
2115
+ "loss": 0.4657,
2116
+ "step": 7525
2117
+ },
2118
+ {
2119
+ "epoch": 1.7052512704686618,
2120
+ "grad_norm": 0.10302968323230743,
2121
+ "learning_rate": 8.27953181806316e-05,
2122
+ "loss": 0.5571,
2123
+ "step": 7550
2124
+ },
2125
+ {
2126
+ "epoch": 1.7108977978543196,
2127
+ "grad_norm": 0.12433881312608719,
2128
+ "learning_rate": 8.21950463271931e-05,
2129
+ "loss": 0.4887,
2130
+ "step": 7575
2131
+ },
2132
+ {
2133
+ "epoch": 1.7165443252399775,
2134
+ "grad_norm": 0.09217355400323868,
2135
+ "learning_rate": 8.159543631324327e-05,
2136
+ "loss": 0.5281,
2137
+ "step": 7600
2138
+ },
2139
+ {
2140
+ "epoch": 1.7221908526256353,
2141
+ "grad_norm": 0.11367136240005493,
2142
+ "learning_rate": 8.099651042727515e-05,
2143
+ "loss": 0.4849,
2144
+ "step": 7625
2145
+ },
2146
+ {
2147
+ "epoch": 1.7278373800112932,
2148
+ "grad_norm": 0.10472942888736725,
2149
+ "learning_rate": 8.039829093235156e-05,
2150
+ "loss": 0.5748,
2151
+ "step": 7650
2152
+ },
2153
+ {
2154
+ "epoch": 1.733483907396951,
2155
+ "grad_norm": 0.13037872314453125,
2156
+ "learning_rate": 7.980080006527751e-05,
2157
+ "loss": 0.4781,
2158
+ "step": 7675
2159
+ },
2160
+ {
2161
+ "epoch": 1.7391304347826086,
2162
+ "grad_norm": 0.1035398542881012,
2163
+ "learning_rate": 7.920406003577394e-05,
2164
+ "loss": 0.5419,
2165
+ "step": 7700
2166
+ },
2167
+ {
2168
+ "epoch": 1.7447769621682665,
2169
+ "grad_norm": 0.12669602036476135,
2170
+ "learning_rate": 7.86080930256517e-05,
2171
+ "loss": 0.4865,
2172
+ "step": 7725
2173
+ },
2174
+ {
2175
+ "epoch": 1.7504234895539243,
2176
+ "grad_norm": 0.09713231027126312,
2177
+ "learning_rate": 7.801292118798732e-05,
2178
+ "loss": 0.564,
2179
+ "step": 7750
2180
+ },
2181
+ {
2182
+ "epoch": 1.7560700169395822,
2183
+ "grad_norm": 0.12088830769062042,
2184
+ "learning_rate": 7.74185666462995e-05,
2185
+ "loss": 0.4641,
2186
+ "step": 7775
2187
+ },
2188
+ {
2189
+ "epoch": 1.7617165443252398,
2190
+ "grad_norm": 0.11002447456121445,
2191
+ "learning_rate": 7.68250514937266e-05,
2192
+ "loss": 0.5407,
2193
+ "step": 7800
2194
+ },
2195
+ {
2196
+ "epoch": 1.7673630717108977,
2197
+ "grad_norm": 0.12338761240243912,
2198
+ "learning_rate": 7.623239779220557e-05,
2199
+ "loss": 0.4558,
2200
+ "step": 7825
2201
+ },
2202
+ {
2203
+ "epoch": 1.7730095990965555,
2204
+ "grad_norm": 0.10458722710609436,
2205
+ "learning_rate": 7.564062757165183e-05,
2206
+ "loss": 0.55,
2207
+ "step": 7850
2208
+ },
2209
+ {
2210
+ "epoch": 1.7786561264822134,
2211
+ "grad_norm": 0.1287498027086258,
2212
+ "learning_rate": 7.504976282914027e-05,
2213
+ "loss": 0.4745,
2214
+ "step": 7875
2215
+ },
2216
+ {
2217
+ "epoch": 1.7843026538678712,
2218
+ "grad_norm": 0.10165251046419144,
2219
+ "learning_rate": 7.445982552808774e-05,
2220
+ "loss": 0.567,
2221
+ "step": 7900
2222
+ },
2223
+ {
2224
+ "epoch": 1.789949181253529,
2225
+ "grad_norm": 0.12862220406532288,
2226
+ "learning_rate": 7.387083759743655e-05,
2227
+ "loss": 0.4777,
2228
+ "step": 7925
2229
+ },
2230
+ {
2231
+ "epoch": 1.795595708639187,
2232
+ "grad_norm": 0.1015312671661377,
2233
+ "learning_rate": 7.328282093083929e-05,
2234
+ "loss": 0.5648,
2235
+ "step": 7950
2236
+ },
2237
+ {
2238
+ "epoch": 1.8012422360248448,
2239
+ "grad_norm": 0.1260487586259842,
2240
+ "learning_rate": 7.269579738584513e-05,
2241
+ "loss": 0.4895,
2242
+ "step": 7975
2243
+ },
2244
+ {
2245
+ "epoch": 1.8068887634105026,
2246
+ "grad_norm": 0.10070119798183441,
2247
+ "learning_rate": 7.210978878308729e-05,
2248
+ "loss": 0.581,
2249
+ "step": 8000
2250
+ },
2251
+ {
2252
+ "epoch": 1.8125352907961605,
2253
+ "grad_norm": 0.12946705520153046,
2254
+ "learning_rate": 7.152481690547182e-05,
2255
+ "loss": 0.475,
2256
+ "step": 8025
2257
+ },
2258
+ {
2259
+ "epoch": 1.8181818181818183,
2260
+ "grad_norm": 0.09579546749591827,
2261
+ "learning_rate": 7.094090349736803e-05,
2262
+ "loss": 0.5516,
2263
+ "step": 8050
2264
+ },
2265
+ {
2266
+ "epoch": 1.823828345567476,
2267
+ "grad_norm": 0.12078605592250824,
2268
+ "learning_rate": 7.035807026380026e-05,
2269
+ "loss": 0.4882,
2270
+ "step": 8075
2271
+ },
2272
+ {
2273
+ "epoch": 1.8294748729531338,
2274
+ "grad_norm": 0.10442069917917252,
2275
+ "learning_rate": 6.977633886964081e-05,
2276
+ "loss": 0.5322,
2277
+ "step": 8100
2278
+ },
2279
+ {
2280
+ "epoch": 1.8351214003387917,
2281
+ "grad_norm": 0.13175725936889648,
2282
+ "learning_rate": 6.919573093880494e-05,
2283
+ "loss": 0.4578,
2284
+ "step": 8125
2285
+ },
2286
+ {
2287
+ "epoch": 1.8407679277244493,
2288
+ "grad_norm": 0.10551594197750092,
2289
+ "learning_rate": 6.861626805344689e-05,
2290
+ "loss": 0.547,
2291
+ "step": 8150
2292
+ },
2293
+ {
2294
+ "epoch": 1.8464144551101072,
2295
+ "grad_norm": 0.11718405783176422,
2296
+ "learning_rate": 6.803797175315761e-05,
2297
+ "loss": 0.4872,
2298
+ "step": 8175
2299
+ },
2300
+ {
2301
+ "epoch": 1.852060982495765,
2302
+ "grad_norm": 0.12317229807376862,
2303
+ "learning_rate": 6.74608635341642e-05,
2304
+ "loss": 0.5724,
2305
+ "step": 8200
2306
+ },
2307
+ {
2308
+ "epoch": 1.8577075098814229,
2309
+ "grad_norm": 0.13172867894172668,
2310
+ "learning_rate": 6.688496484853084e-05,
2311
+ "loss": 0.4506,
2312
+ "step": 8225
2313
+ },
2314
+ {
2315
+ "epoch": 1.8633540372670807,
2316
+ "grad_norm": 0.09928746521472931,
2317
+ "learning_rate": 6.631029710336133e-05,
2318
+ "loss": 0.5094,
2319
+ "step": 8250
2320
+ },
2321
+ {
2322
+ "epoch": 1.8690005646527386,
2323
+ "grad_norm": 0.12048971652984619,
2324
+ "learning_rate": 6.573688166000345e-05,
2325
+ "loss": 0.4608,
2326
+ "step": 8275
2327
+ },
2328
+ {
2329
+ "epoch": 1.8746470920383964,
2330
+ "grad_norm": 0.1059262603521347,
2331
+ "learning_rate": 6.516473983325473e-05,
2332
+ "loss": 0.5475,
2333
+ "step": 8300
2334
+ },
2335
+ {
2336
+ "epoch": 1.8802936194240543,
2337
+ "grad_norm": 0.1448829621076584,
2338
+ "learning_rate": 6.459389289057038e-05,
2339
+ "loss": 0.4695,
2340
+ "step": 8325
2341
+ },
2342
+ {
2343
+ "epoch": 1.8859401468097121,
2344
+ "grad_norm": 0.0976184606552124,
2345
+ "learning_rate": 6.40243620512726e-05,
2346
+ "loss": 0.549,
2347
+ "step": 8350
2348
+ },
2349
+ {
2350
+ "epoch": 1.89158667419537,
2351
+ "grad_norm": 0.14233841001987457,
2352
+ "learning_rate": 6.345616848576184e-05,
2353
+ "loss": 0.4716,
2354
+ "step": 8375
2355
+ },
2356
+ {
2357
+ "epoch": 1.8972332015810278,
2358
+ "grad_norm": 0.10030635446310043,
2359
+ "learning_rate": 6.288933331472988e-05,
2360
+ "loss": 0.561,
2361
+ "step": 8400
2362
+ },
2363
+ {
2364
+ "epoch": 1.9028797289666854,
2365
+ "grad_norm": 0.12384554743766785,
2366
+ "learning_rate": 6.232387760837474e-05,
2367
+ "loss": 0.4872,
2368
+ "step": 8425
2369
+ },
2370
+ {
2371
+ "epoch": 1.9085262563523433,
2372
+ "grad_norm": 0.10905805230140686,
2373
+ "learning_rate": 6.175982238561755e-05,
2374
+ "loss": 0.5347,
2375
+ "step": 8450
2376
+ },
2377
+ {
2378
+ "epoch": 1.9141727837380011,
2379
+ "grad_norm": 0.13816171884536743,
2380
+ "learning_rate": 6.119718861332098e-05,
2381
+ "loss": 0.477,
2382
+ "step": 8475
2383
+ },
2384
+ {
2385
+ "epoch": 1.919819311123659,
2386
+ "grad_norm": 0.11039167642593384,
2387
+ "learning_rate": 6.0635997205510175e-05,
2388
+ "loss": 0.5706,
2389
+ "step": 8500
2390
+ },
2391
+ {
2392
+ "epoch": 1.9254658385093166,
2393
+ "grad_norm": 0.1241937056183815,
2394
+ "learning_rate": 6.007626902259521e-05,
2395
+ "loss": 0.4787,
2396
+ "step": 8525
2397
+ },
2398
+ {
2399
+ "epoch": 1.9311123658949745,
2400
+ "grad_norm": 0.1162077784538269,
2401
+ "learning_rate": 5.951802487059559e-05,
2402
+ "loss": 0.5515,
2403
+ "step": 8550
2404
+ },
2405
+ {
2406
+ "epoch": 1.9367588932806323,
2407
+ "grad_norm": 0.12294231355190277,
2408
+ "learning_rate": 5.8961285500367034e-05,
2409
+ "loss": 0.4699,
2410
+ "step": 8575
2411
+ },
2412
+ {
2413
+ "epoch": 1.9424054206662902,
2414
+ "grad_norm": 0.10771624743938446,
2415
+ "learning_rate": 5.8406071606830026e-05,
2416
+ "loss": 0.5373,
2417
+ "step": 8600
2418
+ },
2419
+ {
2420
+ "epoch": 1.948051948051948,
2421
+ "grad_norm": 0.11943277716636658,
2422
+ "learning_rate": 5.7852403828200495e-05,
2423
+ "loss": 0.4648,
2424
+ "step": 8625
2425
+ },
2426
+ {
2427
+ "epoch": 1.9536984754376059,
2428
+ "grad_norm": 0.11853492259979248,
2429
+ "learning_rate": 5.730030274522282e-05,
2430
+ "loss": 0.5501,
2431
+ "step": 8650
2432
+ },
2433
+ {
2434
+ "epoch": 1.9593450028232637,
2435
+ "grad_norm": 0.12967811524868011,
2436
+ "learning_rate": 5.674978888040463e-05,
2437
+ "loss": 0.4808,
2438
+ "step": 8675
2439
+ },
2440
+ {
2441
+ "epoch": 1.9649915302089216,
2442
+ "grad_norm": 0.112027108669281,
2443
+ "learning_rate": 5.6200882697254154e-05,
2444
+ "loss": 0.5311,
2445
+ "step": 8700
2446
+ },
2447
+ {
2448
+ "epoch": 1.9706380575945794,
2449
+ "grad_norm": 0.1347729116678238,
2450
+ "learning_rate": 5.565360459951936e-05,
2451
+ "loss": 0.4679,
2452
+ "step": 8725
2453
+ },
2454
+ {
2455
+ "epoch": 1.9762845849802373,
2456
+ "grad_norm": 0.11015453189611435,
2457
+ "learning_rate": 5.510797493042954e-05,
2458
+ "loss": 0.5595,
2459
+ "step": 8750
2460
+ },
2461
+ {
2462
+ "epoch": 1.981931112365895,
2463
+ "grad_norm": 0.13183894753456116,
2464
+ "learning_rate": 5.456401397193936e-05,
2465
+ "loss": 0.4656,
2466
+ "step": 8775
2467
+ },
2468
+ {
2469
+ "epoch": 1.9875776397515528,
2470
+ "grad_norm": 0.10906127840280533,
2471
+ "learning_rate": 5.402174194397458e-05,
2472
+ "loss": 0.537,
2473
+ "step": 8800
2474
+ },
2475
+ {
2476
+ "epoch": 1.9932241671372106,
2477
+ "grad_norm": 0.1271781325340271,
2478
+ "learning_rate": 5.348117900368066e-05,
2479
+ "loss": 0.4639,
2480
+ "step": 8825
2481
+ },
2482
+ {
2483
+ "epoch": 1.9988706945228685,
2484
+ "grad_norm": 0.12033294886350632,
2485
+ "learning_rate": 5.2942345244673564e-05,
2486
+ "loss": 0.5076,
2487
+ "step": 8850
2488
+ },
2489
+ {
2490
+ "epoch": 2.004517221908526,
2491
+ "grad_norm": 0.11611133068799973,
2492
+ "learning_rate": 5.240526069629265e-05,
2493
+ "loss": 0.5368,
2494
+ "step": 8875
2495
+ },
2496
+ {
2497
+ "epoch": 2.010163749294184,
2498
+ "grad_norm": 0.16251997649669647,
2499
+ "learning_rate": 5.1869945322856196e-05,
2500
+ "loss": 0.4708,
2501
+ "step": 8900
2502
+ },
2503
+ {
2504
+ "epoch": 2.015810276679842,
2505
+ "grad_norm": 0.10342962294816971,
2506
+ "learning_rate": 5.1336419022919435e-05,
2507
+ "loss": 0.5186,
2508
+ "step": 8925
2509
+ },
2510
+ {
2511
+ "epoch": 2.0214568040654997,
2512
+ "grad_norm": 0.12473160028457642,
2513
+ "learning_rate": 5.080470162853472e-05,
2514
+ "loss": 0.4405,
2515
+ "step": 8950
2516
+ },
2517
+ {
2518
+ "epoch": 2.0271033314511575,
2519
+ "grad_norm": 0.10961506515741348,
2520
+ "learning_rate": 5.0274812904514346e-05,
2521
+ "loss": 0.4963,
2522
+ "step": 8975
2523
+ },
2524
+ {
2525
+ "epoch": 2.0327498588368154,
2526
+ "grad_norm": 0.13045734167099,
2527
+ "learning_rate": 4.974677254769608e-05,
2528
+ "loss": 0.4648,
2529
+ "step": 9000
2530
+ },
2531
+ {
2532
+ "epoch": 2.038396386222473,
2533
+ "grad_norm": 0.10588447749614716,
2534
+ "learning_rate": 4.922060018621066e-05,
2535
+ "loss": 0.514,
2536
+ "step": 9025
2537
+ },
2538
+ {
2539
+ "epoch": 2.044042913608131,
2540
+ "grad_norm": 0.1310020089149475,
2541
+ "learning_rate": 4.869631537875243e-05,
2542
+ "loss": 0.4581,
2543
+ "step": 9050
2544
+ },
2545
+ {
2546
+ "epoch": 2.049689440993789,
2547
+ "grad_norm": 0.11264315247535706,
2548
+ "learning_rate": 4.8173937613852296e-05,
2549
+ "loss": 0.514,
2550
+ "step": 9075
2551
+ },
2552
+ {
2553
+ "epoch": 2.0553359683794468,
2554
+ "grad_norm": 0.11348750442266464,
2555
+ "learning_rate": 4.765348630915315e-05,
2556
+ "loss": 0.4509,
2557
+ "step": 9100
2558
+ },
2559
+ {
2560
+ "epoch": 2.0609824957651046,
2561
+ "grad_norm": 0.1084527000784874,
2562
+ "learning_rate": 4.713498081068819e-05,
2563
+ "loss": 0.4836,
2564
+ "step": 9125
2565
+ },
2566
+ {
2567
+ "epoch": 2.0666290231507625,
2568
+ "grad_norm": 0.12957565486431122,
2569
+ "learning_rate": 4.6618440392161886e-05,
2570
+ "loss": 0.4467,
2571
+ "step": 9150
2572
+ },
2573
+ {
2574
+ "epoch": 2.0722755505364203,
2575
+ "grad_norm": 0.10537248849868774,
2576
+ "learning_rate": 4.610388425423336e-05,
2577
+ "loss": 0.52,
2578
+ "step": 9175
2579
+ },
2580
+ {
2581
+ "epoch": 2.0779220779220777,
2582
+ "grad_norm": 0.13615071773529053,
2583
+ "learning_rate": 4.559133152380272e-05,
2584
+ "loss": 0.4567,
2585
+ "step": 9200
2586
+ },
2587
+ {
2588
+ "epoch": 2.0835686053077356,
2589
+ "grad_norm": 0.11438791453838348,
2590
+ "learning_rate": 4.508080125330022e-05,
2591
+ "loss": 0.5111,
2592
+ "step": 9225
2593
+ },
2594
+ {
2595
+ "epoch": 2.0892151326933934,
2596
+ "grad_norm": 0.1288277804851532,
2597
+ "learning_rate": 4.457231241997788e-05,
2598
+ "loss": 0.4584,
2599
+ "step": 9250
2600
+ },
2601
+ {
2602
+ "epoch": 2.0948616600790513,
2603
+ "grad_norm": 0.10171278566122055,
2604
+ "learning_rate": 4.40658839252041e-05,
2605
+ "loss": 0.5065,
2606
+ "step": 9275
2607
+ },
2608
+ {
2609
+ "epoch": 2.100508187464709,
2610
+ "grad_norm": 0.1178368479013443,
2611
+ "learning_rate": 4.356153459376121e-05,
2612
+ "loss": 0.4426,
2613
+ "step": 9300
2614
+ },
2615
+ {
2616
+ "epoch": 2.106154714850367,
2617
+ "grad_norm": 0.12345319241285324,
2618
+ "learning_rate": 4.305928317314549e-05,
2619
+ "loss": 0.5134,
2620
+ "step": 9325
2621
+ },
2622
+ {
2623
+ "epoch": 2.111801242236025,
2624
+ "grad_norm": 0.1341843158006668,
2625
+ "learning_rate": 4.255914833287046e-05,
2626
+ "loss": 0.4526,
2627
+ "step": 9350
2628
+ },
2629
+ {
2630
+ "epoch": 2.1174477696216827,
2631
+ "grad_norm": 0.12422988563776016,
2632
+ "learning_rate": 4.206114866377291e-05,
2633
+ "loss": 0.5025,
2634
+ "step": 9375
2635
+ },
2636
+ {
2637
+ "epoch": 2.1230942970073405,
2638
+ "grad_norm": 0.1362808346748352,
2639
+ "learning_rate": 4.156530267732173e-05,
2640
+ "loss": 0.4701,
2641
+ "step": 9400
2642
+ },
2643
+ {
2644
+ "epoch": 2.1287408243929984,
2645
+ "grad_norm": 0.11891162395477295,
2646
+ "learning_rate": 4.107162880492984e-05,
2647
+ "loss": 0.5091,
2648
+ "step": 9425
2649
+ },
2650
+ {
2651
+ "epoch": 2.1343873517786562,
2652
+ "grad_norm": 0.13123708963394165,
2653
+ "learning_rate": 4.058014539726922e-05,
2654
+ "loss": 0.4593,
2655
+ "step": 9450
2656
+ },
2657
+ {
2658
+ "epoch": 2.140033879164314,
2659
+ "grad_norm": 0.11908406764268875,
2660
+ "learning_rate": 4.0090870723588606e-05,
2661
+ "loss": 0.5076,
2662
+ "step": 9475
2663
+ },
2664
+ {
2665
+ "epoch": 2.145680406549972,
2666
+ "grad_norm": 0.1421327143907547,
2667
+ "learning_rate": 3.960382297103442e-05,
2668
+ "loss": 0.4467,
2669
+ "step": 9500
2670
+ },
2671
+ {
2672
+ "epoch": 2.15132693393563,
2673
+ "grad_norm": 0.1141195222735405,
2674
+ "learning_rate": 3.911902024397473e-05,
2675
+ "loss": 0.5044,
2676
+ "step": 9525
2677
+ },
2678
+ {
2679
+ "epoch": 2.1569734613212876,
2680
+ "grad_norm": 0.11890695989131927,
2681
+ "learning_rate": 3.8636480563326425e-05,
2682
+ "loss": 0.4562,
2683
+ "step": 9550
2684
+ },
2685
+ {
2686
+ "epoch": 2.162619988706945,
2687
+ "grad_norm": 0.12307918071746826,
2688
+ "learning_rate": 3.8156221865885126e-05,
2689
+ "loss": 0.5154,
2690
+ "step": 9575
2691
+ },
2692
+ {
2693
+ "epoch": 2.168266516092603,
2694
+ "grad_norm": 0.12713749706745148,
2695
+ "learning_rate": 3.767826200365853e-05,
2696
+ "loss": 0.4578,
2697
+ "step": 9600
2698
+ },
2699
+ {
2700
+ "epoch": 2.1739130434782608,
2701
+ "grad_norm": 0.12245321273803711,
2702
+ "learning_rate": 3.7202618743202935e-05,
2703
+ "loss": 0.5022,
2704
+ "step": 9625
2705
+ },
2706
+ {
2707
+ "epoch": 2.1795595708639186,
2708
+ "grad_norm": 0.1354779750108719,
2709
+ "learning_rate": 3.6729309764962616e-05,
2710
+ "loss": 0.4534,
2711
+ "step": 9650
2712
+ },
2713
+ {
2714
+ "epoch": 2.1852060982495765,
2715
+ "grad_norm": 0.10722421109676361,
2716
+ "learning_rate": 3.625835266261287e-05,
2717
+ "loss": 0.5021,
2718
+ "step": 9675
2719
+ },
2720
+ {
2721
+ "epoch": 2.1908526256352343,
2722
+ "grad_norm": 0.1329207420349121,
2723
+ "learning_rate": 3.578976494240577e-05,
2724
+ "loss": 0.4639,
2725
+ "step": 9700
2726
+ },
2727
+ {
2728
+ "epoch": 2.196499153020892,
2729
+ "grad_norm": 0.11663591116666794,
2730
+ "learning_rate": 3.532356402251954e-05,
2731
+ "loss": 0.4882,
2732
+ "step": 9725
2733
+ },
2734
+ {
2735
+ "epoch": 2.20214568040655,
2736
+ "grad_norm": 0.13668714463710785,
2737
+ "learning_rate": 3.485976723241121e-05,
2738
+ "loss": 0.465,
2739
+ "step": 9750
2740
+ },
2741
+ {
2742
+ "epoch": 2.207792207792208,
2743
+ "grad_norm": 0.11890459805727005,
2744
+ "learning_rate": 3.439839181217227e-05,
2745
+ "loss": 0.505,
2746
+ "step": 9775
2747
+ },
2748
+ {
2749
+ "epoch": 2.2134387351778657,
2750
+ "grad_norm": 0.1332354098558426,
2751
+ "learning_rate": 3.3939454911887844e-05,
2752
+ "loss": 0.4497,
2753
+ "step": 9800
2754
+ },
2755
+ {
2756
+ "epoch": 2.2190852625635236,
2757
+ "grad_norm": 0.11797164380550385,
2758
+ "learning_rate": 3.34829735909994e-05,
2759
+ "loss": 0.536,
2760
+ "step": 9825
2761
+ },
2762
+ {
2763
+ "epoch": 2.2247317899491814,
2764
+ "grad_norm": 0.13317126035690308,
2765
+ "learning_rate": 3.302896481767034e-05,
2766
+ "loss": 0.4645,
2767
+ "step": 9850
2768
+ },
2769
+ {
2770
+ "epoch": 2.2303783173348393,
2771
+ "grad_norm": 0.11745914816856384,
2772
+ "learning_rate": 3.25774454681554e-05,
2773
+ "loss": 0.4991,
2774
+ "step": 9875
2775
+ },
2776
+ {
2777
+ "epoch": 2.2360248447204967,
2778
+ "grad_norm": 0.13392220437526703,
2779
+ "learning_rate": 3.212843232617343e-05,
2780
+ "loss": 0.4385,
2781
+ "step": 9900
2782
+ },
2783
+ {
2784
+ "epoch": 2.2416713721061545,
2785
+ "grad_norm": 0.11925249546766281,
2786
+ "learning_rate": 3.168194208228331e-05,
2787
+ "loss": 0.4801,
2788
+ "step": 9925
2789
+ },
2790
+ {
2791
+ "epoch": 2.2473178994918124,
2792
+ "grad_norm": 0.1346205770969391,
2793
+ "learning_rate": 3.123799133326366e-05,
2794
+ "loss": 0.4562,
2795
+ "step": 9950
2796
+ },
2797
+ {
2798
+ "epoch": 2.2529644268774702,
2799
+ "grad_norm": 0.1318216472864151,
2800
+ "learning_rate": 3.0796596581495963e-05,
2801
+ "loss": 0.499,
2802
+ "step": 9975
2803
+ },
2804
+ {
2805
+ "epoch": 2.258610954263128,
2806
+ "grad_norm": 0.1402980238199234,
2807
+ "learning_rate": 3.0357774234350945e-05,
2808
+ "loss": 0.4386,
2809
+ "step": 10000
2810
+ }
2811
+ ],
2812
+ "logging_steps": 25,
2813
+ "max_steps": 13281,
2814
+ "num_input_tokens_seen": 0,
2815
+ "num_train_epochs": 3,
2816
+ "save_steps": 200,
2817
+ "stateful_callbacks": {
2818
+ "TrainerControl": {
2819
+ "args": {
2820
+ "should_epoch_stop": false,
2821
+ "should_evaluate": false,
2822
+ "should_log": false,
2823
+ "should_save": true,
2824
+ "should_training_stop": false
2825
+ },
2826
+ "attributes": {}
2827
+ }
2828
+ },
2829
+ "total_flos": 5.882541565636669e+18,
2830
+ "train_batch_size": 2,
2831
+ "trial_name": null,
2832
+ "trial_params": null
2833
+ }
checkpoint-10000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fc98f22665d02224015b9535b80e5c69ad66eca110b77e2e7ae87eceaba5b8a
3
+ size 5051
checkpoint-10200/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Llama-2-13b-chat-hf
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.12.0
checkpoint-10200/adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Llama-2-13b-chat-hf",
5
+ "bias": "lora_only",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.001,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 64,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "v_proj",
24
+ "q_proj"
25
+ ],
26
+ "task_type": "CAUSAL_LM",
27
+ "use_dora": false,
28
+ "use_rslora": false
29
+ }
checkpoint-10200/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4c03586c59bf46b3f3555d5bb078462a47123c5c7a94c2a71edf04787d5ca1a
3
+ size 209736952
checkpoint-10200/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc1ce7577bb0035bbe7457f7466e89d2171e298904e6016c98bd123c2afe0210
3
+ size 419529285
checkpoint-10200/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:499d4b17c2eac28a9d366d4b1d6c1c5c26740280343d33b1eca2f1e77e7ccd7d
3
+ size 14575
checkpoint-10200/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:913bfcacd94757b6a64c911998029288de8620fb6a939c609b02a98e5c530d9b
3
+ size 627
checkpoint-10200/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
checkpoint-10200/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-10200/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
checkpoint-10200/tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "bos_token": "<s>",
32
+ "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": false,
36
+ "model_max_length": 1000000000000000019884624838656,
37
+ "pad_token": "</s>",
38
+ "padding_side": "right",
39
+ "sp_model_kwargs": {},
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
+ }
checkpoint-10200/trainer_state.json ADDED
@@ -0,0 +1,2889 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.303783173348391,
5
+ "eval_steps": 500,
6
+ "global_step": 10200,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.00564652738565782,
13
+ "grad_norm": 0.0635828971862793,
14
+ "learning_rate": 1.2531328320802006e-05,
15
+ "loss": 1.3836,
16
+ "step": 25
17
+ },
18
+ {
19
+ "epoch": 0.01129305477131564,
20
+ "grad_norm": 0.2005225569009781,
21
+ "learning_rate": 2.506265664160401e-05,
22
+ "loss": 1.6497,
23
+ "step": 50
24
+ },
25
+ {
26
+ "epoch": 0.01693958215697346,
27
+ "grad_norm": 0.07235410064458847,
28
+ "learning_rate": 3.759398496240601e-05,
29
+ "loss": 1.1768,
30
+ "step": 75
31
+ },
32
+ {
33
+ "epoch": 0.02258610954263128,
34
+ "grad_norm": 0.17648495733737946,
35
+ "learning_rate": 5.012531328320802e-05,
36
+ "loss": 1.2146,
37
+ "step": 100
38
+ },
39
+ {
40
+ "epoch": 0.028232636928289104,
41
+ "grad_norm": 0.06953724473714828,
42
+ "learning_rate": 6.265664160401002e-05,
43
+ "loss": 0.8725,
44
+ "step": 125
45
+ },
46
+ {
47
+ "epoch": 0.03387916431394692,
48
+ "grad_norm": 0.12059248238801956,
49
+ "learning_rate": 7.518796992481203e-05,
50
+ "loss": 0.7548,
51
+ "step": 150
52
+ },
53
+ {
54
+ "epoch": 0.039525691699604744,
55
+ "grad_norm": 0.0689113661646843,
56
+ "learning_rate": 8.771929824561403e-05,
57
+ "loss": 0.7917,
58
+ "step": 175
59
+ },
60
+ {
61
+ "epoch": 0.04517221908526256,
62
+ "grad_norm": 0.16621273756027222,
63
+ "learning_rate": 0.00010025062656641604,
64
+ "loss": 0.6985,
65
+ "step": 200
66
+ },
67
+ {
68
+ "epoch": 0.050818746470920384,
69
+ "grad_norm": 0.07838872820138931,
70
+ "learning_rate": 0.00011278195488721806,
71
+ "loss": 0.7874,
72
+ "step": 225
73
+ },
74
+ {
75
+ "epoch": 0.05646527385657821,
76
+ "grad_norm": 0.11714337766170502,
77
+ "learning_rate": 0.00012531328320802005,
78
+ "loss": 0.689,
79
+ "step": 250
80
+ },
81
+ {
82
+ "epoch": 0.062111801242236024,
83
+ "grad_norm": 0.07283364981412888,
84
+ "learning_rate": 0.00013784461152882208,
85
+ "loss": 0.7719,
86
+ "step": 275
87
+ },
88
+ {
89
+ "epoch": 0.06775832862789384,
90
+ "grad_norm": 0.1499466449022293,
91
+ "learning_rate": 0.00015037593984962405,
92
+ "loss": 0.655,
93
+ "step": 300
94
+ },
95
+ {
96
+ "epoch": 0.07340485601355166,
97
+ "grad_norm": 0.08195521682500839,
98
+ "learning_rate": 0.00016290726817042608,
99
+ "loss": 0.7508,
100
+ "step": 325
101
+ },
102
+ {
103
+ "epoch": 0.07905138339920949,
104
+ "grad_norm": 0.1490202099084854,
105
+ "learning_rate": 0.00017543859649122806,
106
+ "loss": 0.6372,
107
+ "step": 350
108
+ },
109
+ {
110
+ "epoch": 0.08469791078486731,
111
+ "grad_norm": 0.1617508977651596,
112
+ "learning_rate": 0.00018796992481203009,
113
+ "loss": 0.7396,
114
+ "step": 375
115
+ },
116
+ {
117
+ "epoch": 0.09034443817052512,
118
+ "grad_norm": 0.180181622505188,
119
+ "learning_rate": 0.00019999999702625888,
120
+ "loss": 0.6318,
121
+ "step": 400
122
+ },
123
+ {
124
+ "epoch": 0.09599096555618294,
125
+ "grad_norm": 0.08272858709096909,
126
+ "learning_rate": 0.00019999798975772924,
127
+ "loss": 0.724,
128
+ "step": 425
129
+ },
130
+ {
131
+ "epoch": 0.10163749294184077,
132
+ "grad_norm": 0.120403952896595,
133
+ "learning_rate": 0.00019999226539902187,
134
+ "loss": 0.6271,
135
+ "step": 450
136
+ },
137
+ {
138
+ "epoch": 0.10728402032749859,
139
+ "grad_norm": 0.07971920073032379,
140
+ "learning_rate": 0.00019998282416292055,
141
+ "loss": 0.7256,
142
+ "step": 475
143
+ },
144
+ {
145
+ "epoch": 0.11293054771315642,
146
+ "grad_norm": 0.1328658014535904,
147
+ "learning_rate": 0.00019996966640037166,
148
+ "loss": 0.6231,
149
+ "step": 500
150
+ },
151
+ {
152
+ "epoch": 0.11857707509881422,
153
+ "grad_norm": 0.07475866377353668,
154
+ "learning_rate": 0.00019995279260047092,
155
+ "loss": 0.7251,
156
+ "step": 525
157
+ },
158
+ {
159
+ "epoch": 0.12422360248447205,
160
+ "grad_norm": 0.1371573656797409,
161
+ "learning_rate": 0.00019993220339044524,
162
+ "loss": 0.5907,
163
+ "step": 550
164
+ },
165
+ {
166
+ "epoch": 0.12987012987012986,
167
+ "grad_norm": 0.07268711924552917,
168
+ "learning_rate": 0.00019990789953562961,
169
+ "loss": 0.7304,
170
+ "step": 575
171
+ },
172
+ {
173
+ "epoch": 0.13551665725578768,
174
+ "grad_norm": 0.14224526286125183,
175
+ "learning_rate": 0.0001998798819394383,
176
+ "loss": 0.5931,
177
+ "step": 600
178
+ },
179
+ {
180
+ "epoch": 0.1411631846414455,
181
+ "grad_norm": 0.0803467407822609,
182
+ "learning_rate": 0.00019984815164333163,
183
+ "loss": 0.7076,
184
+ "step": 625
185
+ },
186
+ {
187
+ "epoch": 0.14680971202710333,
188
+ "grad_norm": 0.12445727735757828,
189
+ "learning_rate": 0.00019981270982677698,
190
+ "loss": 0.5566,
191
+ "step": 650
192
+ },
193
+ {
194
+ "epoch": 0.15245623941276115,
195
+ "grad_norm": 0.07665792107582092,
196
+ "learning_rate": 0.00019977355780720514,
197
+ "loss": 0.6985,
198
+ "step": 675
199
+ },
200
+ {
201
+ "epoch": 0.15810276679841898,
202
+ "grad_norm": 0.13053999841213226,
203
+ "learning_rate": 0.00019973069703996125,
204
+ "loss": 0.5901,
205
+ "step": 700
206
+ },
207
+ {
208
+ "epoch": 0.1637492941840768,
209
+ "grad_norm": 0.07512692362070084,
210
+ "learning_rate": 0.00019968412911825067,
211
+ "loss": 0.7184,
212
+ "step": 725
213
+ },
214
+ {
215
+ "epoch": 0.16939582156973462,
216
+ "grad_norm": 0.12033283710479736,
217
+ "learning_rate": 0.00019963385577307987,
218
+ "loss": 0.6013,
219
+ "step": 750
220
+ },
221
+ {
222
+ "epoch": 0.17504234895539245,
223
+ "grad_norm": 0.0809774249792099,
224
+ "learning_rate": 0.000199579878873192,
225
+ "loss": 0.7054,
226
+ "step": 775
227
+ },
228
+ {
229
+ "epoch": 0.18068887634105024,
230
+ "grad_norm": 0.12490582466125488,
231
+ "learning_rate": 0.0001995222004249974,
232
+ "loss": 0.5714,
233
+ "step": 800
234
+ },
235
+ {
236
+ "epoch": 0.18633540372670807,
237
+ "grad_norm": 0.08289226144552231,
238
+ "learning_rate": 0.00019946082257249912,
239
+ "loss": 0.7304,
240
+ "step": 825
241
+ },
242
+ {
243
+ "epoch": 0.1919819311123659,
244
+ "grad_norm": 0.14385385811328888,
245
+ "learning_rate": 0.00019939574759721316,
246
+ "loss": 0.5639,
247
+ "step": 850
248
+ },
249
+ {
250
+ "epoch": 0.1976284584980237,
251
+ "grad_norm": 0.07623141258955002,
252
+ "learning_rate": 0.00019932697791808366,
253
+ "loss": 0.7126,
254
+ "step": 875
255
+ },
256
+ {
257
+ "epoch": 0.20327498588368154,
258
+ "grad_norm": 0.11150185018777847,
259
+ "learning_rate": 0.000199254516091393,
260
+ "loss": 0.5903,
261
+ "step": 900
262
+ },
263
+ {
264
+ "epoch": 0.20892151326933936,
265
+ "grad_norm": 0.07193930447101593,
266
+ "learning_rate": 0.00019917836481066675,
267
+ "loss": 0.6952,
268
+ "step": 925
269
+ },
270
+ {
271
+ "epoch": 0.21456804065499718,
272
+ "grad_norm": 0.11242598295211792,
273
+ "learning_rate": 0.00019909852690657359,
274
+ "loss": 0.5853,
275
+ "step": 950
276
+ },
277
+ {
278
+ "epoch": 0.220214568040655,
279
+ "grad_norm": 0.07508910447359085,
280
+ "learning_rate": 0.0001990150053468201,
281
+ "loss": 0.6969,
282
+ "step": 975
283
+ },
284
+ {
285
+ "epoch": 0.22586109542631283,
286
+ "grad_norm": 0.11998436599969864,
287
+ "learning_rate": 0.00019892780323604035,
288
+ "loss": 0.5791,
289
+ "step": 1000
290
+ },
291
+ {
292
+ "epoch": 0.23150762281197063,
293
+ "grad_norm": 0.07748444378376007,
294
+ "learning_rate": 0.0001988369238156806,
295
+ "loss": 0.7038,
296
+ "step": 1025
297
+ },
298
+ {
299
+ "epoch": 0.23715415019762845,
300
+ "grad_norm": 0.19617140293121338,
301
+ "learning_rate": 0.0001987423704638788,
302
+ "loss": 0.5792,
303
+ "step": 1050
304
+ },
305
+ {
306
+ "epoch": 0.24280067758328627,
307
+ "grad_norm": 0.08167731016874313,
308
+ "learning_rate": 0.00019864414669533892,
309
+ "loss": 0.6989,
310
+ "step": 1075
311
+ },
312
+ {
313
+ "epoch": 0.2484472049689441,
314
+ "grad_norm": 0.11911099404096603,
315
+ "learning_rate": 0.00019854225616120044,
316
+ "loss": 0.5985,
317
+ "step": 1100
318
+ },
319
+ {
320
+ "epoch": 0.2540937323546019,
321
+ "grad_norm": 0.0718325674533844,
322
+ "learning_rate": 0.0001984367026489025,
323
+ "loss": 0.6853,
324
+ "step": 1125
325
+ },
326
+ {
327
+ "epoch": 0.2597402597402597,
328
+ "grad_norm": 0.12495870143175125,
329
+ "learning_rate": 0.0001983274900820432,
330
+ "loss": 0.5738,
331
+ "step": 1150
332
+ },
333
+ {
334
+ "epoch": 0.26538678712591757,
335
+ "grad_norm": 0.08245467394590378,
336
+ "learning_rate": 0.0001982146225202338,
337
+ "loss": 0.6766,
338
+ "step": 1175
339
+ },
340
+ {
341
+ "epoch": 0.27103331451157536,
342
+ "grad_norm": 0.11854438483715057,
343
+ "learning_rate": 0.00019809810415894767,
344
+ "loss": 0.5828,
345
+ "step": 1200
346
+ },
347
+ {
348
+ "epoch": 0.2766798418972332,
349
+ "grad_norm": 0.07968372851610184,
350
+ "learning_rate": 0.0001979779393293644,
351
+ "loss": 0.6901,
352
+ "step": 1225
353
+ },
354
+ {
355
+ "epoch": 0.282326369282891,
356
+ "grad_norm": 0.13610929250717163,
357
+ "learning_rate": 0.00019785413249820893,
358
+ "loss": 0.554,
359
+ "step": 1250
360
+ },
361
+ {
362
+ "epoch": 0.28797289666854886,
363
+ "grad_norm": 0.08099998533725739,
364
+ "learning_rate": 0.00019772668826758527,
365
+ "loss": 0.6615,
366
+ "step": 1275
367
+ },
368
+ {
369
+ "epoch": 0.29361942405420666,
370
+ "grad_norm": 0.10878365486860275,
371
+ "learning_rate": 0.0001975956113748057,
372
+ "loss": 0.547,
373
+ "step": 1300
374
+ },
375
+ {
376
+ "epoch": 0.2992659514398645,
377
+ "grad_norm": 0.0784253254532814,
378
+ "learning_rate": 0.0001974609066922144,
379
+ "loss": 0.6589,
380
+ "step": 1325
381
+ },
382
+ {
383
+ "epoch": 0.3049124788255223,
384
+ "grad_norm": 0.10678227245807648,
385
+ "learning_rate": 0.00019732257922700655,
386
+ "loss": 0.5443,
387
+ "step": 1350
388
+ },
389
+ {
390
+ "epoch": 0.3105590062111801,
391
+ "grad_norm": 0.07781955599784851,
392
+ "learning_rate": 0.00019718063412104222,
393
+ "loss": 0.6798,
394
+ "step": 1375
395
+ },
396
+ {
397
+ "epoch": 0.31620553359683795,
398
+ "grad_norm": 0.12910470366477966,
399
+ "learning_rate": 0.00019703507665065498,
400
+ "loss": 0.54,
401
+ "step": 1400
402
+ },
403
+ {
404
+ "epoch": 0.32185206098249575,
405
+ "grad_norm": 0.08442296832799911,
406
+ "learning_rate": 0.00019688591222645607,
407
+ "loss": 0.6998,
408
+ "step": 1425
409
+ },
410
+ {
411
+ "epoch": 0.3274985883681536,
412
+ "grad_norm": 0.10945732891559601,
413
+ "learning_rate": 0.00019673314639313315,
414
+ "loss": 0.5576,
415
+ "step": 1450
416
+ },
417
+ {
418
+ "epoch": 0.3331451157538114,
419
+ "grad_norm": 0.07373673468828201,
420
+ "learning_rate": 0.00019657678482924406,
421
+ "loss": 0.709,
422
+ "step": 1475
423
+ },
424
+ {
425
+ "epoch": 0.33879164313946925,
426
+ "grad_norm": 0.10061786323785782,
427
+ "learning_rate": 0.00019641683334700608,
428
+ "loss": 0.5329,
429
+ "step": 1500
430
+ },
431
+ {
432
+ "epoch": 0.34443817052512704,
433
+ "grad_norm": 0.08854890614748001,
434
+ "learning_rate": 0.00019625329789207949,
435
+ "loss": 0.6753,
436
+ "step": 1525
437
+ },
438
+ {
439
+ "epoch": 0.3500846979107849,
440
+ "grad_norm": 0.11869047582149506,
441
+ "learning_rate": 0.00019608618454334685,
442
+ "loss": 0.54,
443
+ "step": 1550
444
+ },
445
+ {
446
+ "epoch": 0.3557312252964427,
447
+ "grad_norm": 0.0819987803697586,
448
+ "learning_rate": 0.00019591549951268692,
449
+ "loss": 0.683,
450
+ "step": 1575
451
+ },
452
+ {
453
+ "epoch": 0.3613777526821005,
454
+ "grad_norm": 0.10941476374864578,
455
+ "learning_rate": 0.00019574124914474374,
456
+ "loss": 0.5713,
457
+ "step": 1600
458
+ },
459
+ {
460
+ "epoch": 0.36702428006775834,
461
+ "grad_norm": 0.0801759734749794,
462
+ "learning_rate": 0.00019556343991669083,
463
+ "loss": 0.6494,
464
+ "step": 1625
465
+ },
466
+ {
467
+ "epoch": 0.37267080745341613,
468
+ "grad_norm": 0.11291850358247757,
469
+ "learning_rate": 0.0001953820784379904,
470
+ "loss": 0.5428,
471
+ "step": 1650
472
+ },
473
+ {
474
+ "epoch": 0.378317334839074,
475
+ "grad_norm": 0.0784342810511589,
476
+ "learning_rate": 0.00019519717145014765,
477
+ "loss": 0.6789,
478
+ "step": 1675
479
+ },
480
+ {
481
+ "epoch": 0.3839638622247318,
482
+ "grad_norm": 0.11995444446802139,
483
+ "learning_rate": 0.00019500872582646034,
484
+ "loss": 0.5409,
485
+ "step": 1700
486
+ },
487
+ {
488
+ "epoch": 0.38961038961038963,
489
+ "grad_norm": 0.10059577226638794,
490
+ "learning_rate": 0.00019481674857176293,
491
+ "loss": 0.6887,
492
+ "step": 1725
493
+ },
494
+ {
495
+ "epoch": 0.3952569169960474,
496
+ "grad_norm": 0.11123017966747284,
497
+ "learning_rate": 0.0001946212468221666,
498
+ "loss": 0.5482,
499
+ "step": 1750
500
+ },
501
+ {
502
+ "epoch": 0.4009034443817053,
503
+ "grad_norm": 0.0788169875741005,
504
+ "learning_rate": 0.00019442222784479382,
505
+ "loss": 0.6577,
506
+ "step": 1775
507
+ },
508
+ {
509
+ "epoch": 0.40654997176736307,
510
+ "grad_norm": 0.09987206757068634,
511
+ "learning_rate": 0.0001942196990375081,
512
+ "loss": 0.5353,
513
+ "step": 1800
514
+ },
515
+ {
516
+ "epoch": 0.41219649915302087,
517
+ "grad_norm": 0.081305131316185,
518
+ "learning_rate": 0.00019401366792863914,
519
+ "loss": 0.6757,
520
+ "step": 1825
521
+ },
522
+ {
523
+ "epoch": 0.4178430265386787,
524
+ "grad_norm": 0.11595868319272995,
525
+ "learning_rate": 0.00019380414217670309,
526
+ "loss": 0.5306,
527
+ "step": 1850
528
+ },
529
+ {
530
+ "epoch": 0.4234895539243365,
531
+ "grad_norm": 0.08652087301015854,
532
+ "learning_rate": 0.00019359112957011764,
533
+ "loss": 0.6634,
534
+ "step": 1875
535
+ },
536
+ {
537
+ "epoch": 0.42913608130999437,
538
+ "grad_norm": 0.1181817501783371,
539
+ "learning_rate": 0.00019337463802691264,
540
+ "loss": 0.5465,
541
+ "step": 1900
542
+ },
543
+ {
544
+ "epoch": 0.43478260869565216,
545
+ "grad_norm": 0.08145532757043839,
546
+ "learning_rate": 0.00019315467559443574,
547
+ "loss": 0.6639,
548
+ "step": 1925
549
+ },
550
+ {
551
+ "epoch": 0.44042913608131,
552
+ "grad_norm": 0.10263626277446747,
553
+ "learning_rate": 0.0001929312504490533,
554
+ "loss": 0.5418,
555
+ "step": 1950
556
+ },
557
+ {
558
+ "epoch": 0.4460756634669678,
559
+ "grad_norm": 0.07672405242919922,
560
+ "learning_rate": 0.00019270437089584635,
561
+ "loss": 0.6547,
562
+ "step": 1975
563
+ },
564
+ {
565
+ "epoch": 0.45172219085262566,
566
+ "grad_norm": 0.0984482392668724,
567
+ "learning_rate": 0.00019247404536830204,
568
+ "loss": 0.5321,
569
+ "step": 2000
570
+ },
571
+ {
572
+ "epoch": 0.45736871823828346,
573
+ "grad_norm": 0.08558057248592377,
574
+ "learning_rate": 0.00019224028242800006,
575
+ "loss": 0.6657,
576
+ "step": 2025
577
+ },
578
+ {
579
+ "epoch": 0.46301524562394125,
580
+ "grad_norm": 0.10624836385250092,
581
+ "learning_rate": 0.00019200309076429438,
582
+ "loss": 0.5542,
583
+ "step": 2050
584
+ },
585
+ {
586
+ "epoch": 0.4686617730095991,
587
+ "grad_norm": 0.08049538731575012,
588
+ "learning_rate": 0.00019176247919399023,
589
+ "loss": 0.6389,
590
+ "step": 2075
591
+ },
592
+ {
593
+ "epoch": 0.4743083003952569,
594
+ "grad_norm": 0.11163744330406189,
595
+ "learning_rate": 0.00019151845666101646,
596
+ "loss": 0.5382,
597
+ "step": 2100
598
+ },
599
+ {
600
+ "epoch": 0.47995482778091475,
601
+ "grad_norm": 0.07694784551858902,
602
+ "learning_rate": 0.00019127103223609307,
603
+ "loss": 0.6345,
604
+ "step": 2125
605
+ },
606
+ {
607
+ "epoch": 0.48560135516657255,
608
+ "grad_norm": 0.11501342058181763,
609
+ "learning_rate": 0.0001910202151163939,
610
+ "loss": 0.5303,
611
+ "step": 2150
612
+ },
613
+ {
614
+ "epoch": 0.4912478825522304,
615
+ "grad_norm": 0.08532056957483292,
616
+ "learning_rate": 0.00019076601462520492,
617
+ "loss": 0.666,
618
+ "step": 2175
619
+ },
620
+ {
621
+ "epoch": 0.4968944099378882,
622
+ "grad_norm": 0.09018545597791672,
623
+ "learning_rate": 0.00019050844021157752,
624
+ "loss": 0.5363,
625
+ "step": 2200
626
+ },
627
+ {
628
+ "epoch": 0.502540937323546,
629
+ "grad_norm": 0.08757849037647247,
630
+ "learning_rate": 0.00019024750144997746,
631
+ "loss": 0.6684,
632
+ "step": 2225
633
+ },
634
+ {
635
+ "epoch": 0.5081874647092038,
636
+ "grad_norm": 0.09418553113937378,
637
+ "learning_rate": 0.00018998320803992872,
638
+ "loss": 0.565,
639
+ "step": 2250
640
+ },
641
+ {
642
+ "epoch": 0.5138339920948617,
643
+ "grad_norm": 0.10246949642896652,
644
+ "learning_rate": 0.00018971556980565329,
645
+ "loss": 0.6524,
646
+ "step": 2275
647
+ },
648
+ {
649
+ "epoch": 0.5194805194805194,
650
+ "grad_norm": 0.12446881830692291,
651
+ "learning_rate": 0.00018944459669570555,
652
+ "loss": 0.5447,
653
+ "step": 2300
654
+ },
655
+ {
656
+ "epoch": 0.5251270468661773,
657
+ "grad_norm": 0.08439560234546661,
658
+ "learning_rate": 0.00018917029878260294,
659
+ "loss": 0.673,
660
+ "step": 2325
661
+ },
662
+ {
663
+ "epoch": 0.5307735742518351,
664
+ "grad_norm": 0.1195409968495369,
665
+ "learning_rate": 0.00018889268626245116,
666
+ "loss": 0.51,
667
+ "step": 2350
668
+ },
669
+ {
670
+ "epoch": 0.536420101637493,
671
+ "grad_norm": 0.09150119870901108,
672
+ "learning_rate": 0.0001886117694545654,
673
+ "loss": 0.6631,
674
+ "step": 2375
675
+ },
676
+ {
677
+ "epoch": 0.5420666290231507,
678
+ "grad_norm": 0.10301247239112854,
679
+ "learning_rate": 0.0001883275588010866,
680
+ "loss": 0.5257,
681
+ "step": 2400
682
+ },
683
+ {
684
+ "epoch": 0.5477131564088086,
685
+ "grad_norm": 0.08086048811674118,
686
+ "learning_rate": 0.00018804006486659346,
687
+ "loss": 0.6305,
688
+ "step": 2425
689
+ },
690
+ {
691
+ "epoch": 0.5533596837944664,
692
+ "grad_norm": 0.10540500283241272,
693
+ "learning_rate": 0.0001877492983377096,
694
+ "loss": 0.5607,
695
+ "step": 2450
696
+ },
697
+ {
698
+ "epoch": 0.5590062111801242,
699
+ "grad_norm": 0.0777876153588295,
700
+ "learning_rate": 0.00018745527002270634,
701
+ "loss": 0.6413,
702
+ "step": 2475
703
+ },
704
+ {
705
+ "epoch": 0.564652738565782,
706
+ "grad_norm": 0.10727331042289734,
707
+ "learning_rate": 0.00018715799085110112,
708
+ "loss": 0.5206,
709
+ "step": 2500
710
+ },
711
+ {
712
+ "epoch": 0.5702992659514399,
713
+ "grad_norm": 0.09144891798496246,
714
+ "learning_rate": 0.0001868574718732508,
715
+ "loss": 0.6655,
716
+ "step": 2525
717
+ },
718
+ {
719
+ "epoch": 0.5759457933370977,
720
+ "grad_norm": 0.08949702978134155,
721
+ "learning_rate": 0.00018655372425994152,
722
+ "loss": 0.5358,
723
+ "step": 2550
724
+ },
725
+ {
726
+ "epoch": 0.5815923207227555,
727
+ "grad_norm": 0.08744482696056366,
728
+ "learning_rate": 0.0001862467593019728,
729
+ "loss": 0.6396,
730
+ "step": 2575
731
+ },
732
+ {
733
+ "epoch": 0.5872388481084133,
734
+ "grad_norm": 0.10931294411420822,
735
+ "learning_rate": 0.0001859365884097384,
736
+ "loss": 0.5132,
737
+ "step": 2600
738
+ },
739
+ {
740
+ "epoch": 0.5928853754940712,
741
+ "grad_norm": 0.07518015056848526,
742
+ "learning_rate": 0.00018562322311280186,
743
+ "loss": 0.6378,
744
+ "step": 2625
745
+ },
746
+ {
747
+ "epoch": 0.598531902879729,
748
+ "grad_norm": 0.09787683933973312,
749
+ "learning_rate": 0.000185306675059468,
750
+ "loss": 0.5272,
751
+ "step": 2650
752
+ },
753
+ {
754
+ "epoch": 0.6041784302653868,
755
+ "grad_norm": 0.08679146319627762,
756
+ "learning_rate": 0.00018498695601634993,
757
+ "loss": 0.6486,
758
+ "step": 2675
759
+ },
760
+ {
761
+ "epoch": 0.6098249576510446,
762
+ "grad_norm": 0.10611116141080856,
763
+ "learning_rate": 0.00018466407786793174,
764
+ "loss": 0.5237,
765
+ "step": 2700
766
+ },
767
+ {
768
+ "epoch": 0.6154714850367025,
769
+ "grad_norm": 0.0772860199213028,
770
+ "learning_rate": 0.00018433805261612663,
771
+ "loss": 0.6526,
772
+ "step": 2725
773
+ },
774
+ {
775
+ "epoch": 0.6211180124223602,
776
+ "grad_norm": 0.1005689725279808,
777
+ "learning_rate": 0.00018400889237983086,
778
+ "loss": 0.5297,
779
+ "step": 2750
780
+ },
781
+ {
782
+ "epoch": 0.626764539808018,
783
+ "grad_norm": 0.08322805911302567,
784
+ "learning_rate": 0.00018367660939447316,
785
+ "loss": 0.6448,
786
+ "step": 2775
787
+ },
788
+ {
789
+ "epoch": 0.6324110671936759,
790
+ "grad_norm": 0.10492440313100815,
791
+ "learning_rate": 0.00018334121601156002,
792
+ "loss": 0.493,
793
+ "step": 2800
794
+ },
795
+ {
796
+ "epoch": 0.6380575945793338,
797
+ "grad_norm": 0.08439356088638306,
798
+ "learning_rate": 0.00018300272469821662,
799
+ "loss": 0.6421,
800
+ "step": 2825
801
+ },
802
+ {
803
+ "epoch": 0.6437041219649915,
804
+ "grad_norm": 0.11175478994846344,
805
+ "learning_rate": 0.00018266114803672318,
806
+ "loss": 0.5293,
807
+ "step": 2850
808
+ },
809
+ {
810
+ "epoch": 0.6493506493506493,
811
+ "grad_norm": 0.07700271904468536,
812
+ "learning_rate": 0.00018231649872404754,
813
+ "loss": 0.6506,
814
+ "step": 2875
815
+ },
816
+ {
817
+ "epoch": 0.6549971767363072,
818
+ "grad_norm": 0.08704936504364014,
819
+ "learning_rate": 0.00018196878957137295,
820
+ "loss": 0.5091,
821
+ "step": 2900
822
+ },
823
+ {
824
+ "epoch": 0.6606437041219649,
825
+ "grad_norm": 0.0863596498966217,
826
+ "learning_rate": 0.00018161803350362198,
827
+ "loss": 0.6531,
828
+ "step": 2925
829
+ },
830
+ {
831
+ "epoch": 0.6662902315076228,
832
+ "grad_norm": 0.11374282091856003,
833
+ "learning_rate": 0.00018126424355897612,
834
+ "loss": 0.5389,
835
+ "step": 2950
836
+ },
837
+ {
838
+ "epoch": 0.6719367588932806,
839
+ "grad_norm": 0.08936896920204163,
840
+ "learning_rate": 0.000180907432888391,
841
+ "loss": 0.6267,
842
+ "step": 2975
843
+ },
844
+ {
845
+ "epoch": 0.6775832862789385,
846
+ "grad_norm": 0.08924362808465958,
847
+ "learning_rate": 0.0001805476147551076,
848
+ "loss": 0.4882,
849
+ "step": 3000
850
+ },
851
+ {
852
+ "epoch": 0.6832298136645962,
853
+ "grad_norm": 0.08161070942878723,
854
+ "learning_rate": 0.0001801848025341593,
855
+ "loss": 0.6502,
856
+ "step": 3025
857
+ },
858
+ {
859
+ "epoch": 0.6888763410502541,
860
+ "grad_norm": 0.11261451989412308,
861
+ "learning_rate": 0.00017981900971187465,
862
+ "loss": 0.5241,
863
+ "step": 3050
864
+ },
865
+ {
866
+ "epoch": 0.6945228684359119,
867
+ "grad_norm": 0.0859522670507431,
868
+ "learning_rate": 0.00017945024988537603,
869
+ "loss": 0.6413,
870
+ "step": 3075
871
+ },
872
+ {
873
+ "epoch": 0.7001693958215698,
874
+ "grad_norm": 0.11650535464286804,
875
+ "learning_rate": 0.0001790785367620743,
876
+ "loss": 0.519,
877
+ "step": 3100
878
+ },
879
+ {
880
+ "epoch": 0.7058159232072275,
881
+ "grad_norm": 0.09202492237091064,
882
+ "learning_rate": 0.00017870388415915922,
883
+ "loss": 0.6212,
884
+ "step": 3125
885
+ },
886
+ {
887
+ "epoch": 0.7114624505928854,
888
+ "grad_norm": 0.1048663780093193,
889
+ "learning_rate": 0.00017832630600308585,
890
+ "loss": 0.5266,
891
+ "step": 3150
892
+ },
893
+ {
894
+ "epoch": 0.7171089779785432,
895
+ "grad_norm": 0.08784987032413483,
896
+ "learning_rate": 0.00017794581632905683,
897
+ "loss": 0.6214,
898
+ "step": 3175
899
+ },
900
+ {
901
+ "epoch": 0.722755505364201,
902
+ "grad_norm": 0.10895237326622009,
903
+ "learning_rate": 0.00017756242928050085,
904
+ "loss": 0.5059,
905
+ "step": 3200
906
+ },
907
+ {
908
+ "epoch": 0.7284020327498588,
909
+ "grad_norm": 0.09365130960941315,
910
+ "learning_rate": 0.0001771761591085467,
911
+ "loss": 0.6529,
912
+ "step": 3225
913
+ },
914
+ {
915
+ "epoch": 0.7340485601355167,
916
+ "grad_norm": 0.1045169085264206,
917
+ "learning_rate": 0.0001767870201714936,
918
+ "loss": 0.5229,
919
+ "step": 3250
920
+ },
921
+ {
922
+ "epoch": 0.7396950875211745,
923
+ "grad_norm": 0.08621610701084137,
924
+ "learning_rate": 0.0001763950269342776,
925
+ "loss": 0.6489,
926
+ "step": 3275
927
+ },
928
+ {
929
+ "epoch": 0.7453416149068323,
930
+ "grad_norm": 0.1039639338850975,
931
+ "learning_rate": 0.00017600019396793367,
932
+ "loss": 0.5116,
933
+ "step": 3300
934
+ },
935
+ {
936
+ "epoch": 0.7509881422924901,
937
+ "grad_norm": 0.09034851938486099,
938
+ "learning_rate": 0.00017560253594905425,
939
+ "loss": 0.6587,
940
+ "step": 3325
941
+ },
942
+ {
943
+ "epoch": 0.756634669678148,
944
+ "grad_norm": 0.10783170908689499,
945
+ "learning_rate": 0.00017520206765924372,
946
+ "loss": 0.5019,
947
+ "step": 3350
948
+ },
949
+ {
950
+ "epoch": 0.7622811970638057,
951
+ "grad_norm": 0.08911153674125671,
952
+ "learning_rate": 0.00017479880398456871,
953
+ "loss": 0.6242,
954
+ "step": 3375
955
+ },
956
+ {
957
+ "epoch": 0.7679277244494636,
958
+ "grad_norm": 0.10053360462188721,
959
+ "learning_rate": 0.00017439275991500507,
960
+ "loss": 0.4996,
961
+ "step": 3400
962
+ },
963
+ {
964
+ "epoch": 0.7735742518351214,
965
+ "grad_norm": 0.09367632865905762,
966
+ "learning_rate": 0.0001739839505438804,
967
+ "loss": 0.6347,
968
+ "step": 3425
969
+ },
970
+ {
971
+ "epoch": 0.7792207792207793,
972
+ "grad_norm": 0.09187789261341095,
973
+ "learning_rate": 0.00017357239106731317,
974
+ "loss": 0.4857,
975
+ "step": 3450
976
+ },
977
+ {
978
+ "epoch": 0.784867306606437,
979
+ "grad_norm": 0.08425033092498779,
980
+ "learning_rate": 0.00017315809678364777,
981
+ "loss": 0.6305,
982
+ "step": 3475
983
+ },
984
+ {
985
+ "epoch": 0.7905138339920948,
986
+ "grad_norm": 0.10775783658027649,
987
+ "learning_rate": 0.00017274108309288594,
988
+ "loss": 0.5013,
989
+ "step": 3500
990
+ },
991
+ {
992
+ "epoch": 0.7961603613777527,
993
+ "grad_norm": 0.082928866147995,
994
+ "learning_rate": 0.00017232136549611416,
995
+ "loss": 0.6217,
996
+ "step": 3525
997
+ },
998
+ {
999
+ "epoch": 0.8018068887634106,
1000
+ "grad_norm": 0.09590538591146469,
1001
+ "learning_rate": 0.00017189895959492772,
1002
+ "loss": 0.4871,
1003
+ "step": 3550
1004
+ },
1005
+ {
1006
+ "epoch": 0.8074534161490683,
1007
+ "grad_norm": 0.08597232401371002,
1008
+ "learning_rate": 0.00017147388109085048,
1009
+ "loss": 0.6298,
1010
+ "step": 3575
1011
+ },
1012
+ {
1013
+ "epoch": 0.8130999435347261,
1014
+ "grad_norm": 0.10229629278182983,
1015
+ "learning_rate": 0.00017104614578475135,
1016
+ "loss": 0.5191,
1017
+ "step": 3600
1018
+ },
1019
+ {
1020
+ "epoch": 0.818746470920384,
1021
+ "grad_norm": 0.09689701348543167,
1022
+ "learning_rate": 0.0001706157695762571,
1023
+ "loss": 0.6087,
1024
+ "step": 3625
1025
+ },
1026
+ {
1027
+ "epoch": 0.8243929983060417,
1028
+ "grad_norm": 0.1155649945139885,
1029
+ "learning_rate": 0.000170182768463161,
1030
+ "loss": 0.5237,
1031
+ "step": 3650
1032
+ },
1033
+ {
1034
+ "epoch": 0.8300395256916996,
1035
+ "grad_norm": 0.08635739237070084,
1036
+ "learning_rate": 0.00016974715854082848,
1037
+ "loss": 0.6337,
1038
+ "step": 3675
1039
+ },
1040
+ {
1041
+ "epoch": 0.8356860530773574,
1042
+ "grad_norm": 0.08977790176868439,
1043
+ "learning_rate": 0.00016930895600159867,
1044
+ "loss": 0.4942,
1045
+ "step": 3700
1046
+ },
1047
+ {
1048
+ "epoch": 0.8413325804630153,
1049
+ "grad_norm": 0.08372893184423447,
1050
+ "learning_rate": 0.00016886817713418264,
1051
+ "loss": 0.6224,
1052
+ "step": 3725
1053
+ },
1054
+ {
1055
+ "epoch": 0.846979107848673,
1056
+ "grad_norm": 0.09409157931804657,
1057
+ "learning_rate": 0.00016842483832305765,
1058
+ "loss": 0.4948,
1059
+ "step": 3750
1060
+ },
1061
+ {
1062
+ "epoch": 0.8526256352343309,
1063
+ "grad_norm": 0.0824190303683281,
1064
+ "learning_rate": 0.00016797895604785842,
1065
+ "loss": 0.6188,
1066
+ "step": 3775
1067
+ },
1068
+ {
1069
+ "epoch": 0.8582721626199887,
1070
+ "grad_norm": 0.11509312689304352,
1071
+ "learning_rate": 0.0001675305468827644,
1072
+ "loss": 0.513,
1073
+ "step": 3800
1074
+ },
1075
+ {
1076
+ "epoch": 0.8639186900056465,
1077
+ "grad_norm": 0.08958346396684647,
1078
+ "learning_rate": 0.0001670796274958837,
1079
+ "loss": 0.6206,
1080
+ "step": 3825
1081
+ },
1082
+ {
1083
+ "epoch": 0.8695652173913043,
1084
+ "grad_norm": 0.0959952101111412,
1085
+ "learning_rate": 0.00016662621464863338,
1086
+ "loss": 0.4885,
1087
+ "step": 3850
1088
+ },
1089
+ {
1090
+ "epoch": 0.8752117447769622,
1091
+ "grad_norm": 0.11436719447374344,
1092
+ "learning_rate": 0.00016617032519511686,
1093
+ "loss": 0.635,
1094
+ "step": 3875
1095
+ },
1096
+ {
1097
+ "epoch": 0.88085827216262,
1098
+ "grad_norm": 0.11012863367795944,
1099
+ "learning_rate": 0.00016571197608149674,
1100
+ "loss": 0.4982,
1101
+ "step": 3900
1102
+ },
1103
+ {
1104
+ "epoch": 0.8865047995482778,
1105
+ "grad_norm": 0.08522720634937286,
1106
+ "learning_rate": 0.00016525118434536546,
1107
+ "loss": 0.6105,
1108
+ "step": 3925
1109
+ },
1110
+ {
1111
+ "epoch": 0.8921513269339356,
1112
+ "grad_norm": 0.11074435710906982,
1113
+ "learning_rate": 0.00016478796711511171,
1114
+ "loss": 0.5007,
1115
+ "step": 3950
1116
+ },
1117
+ {
1118
+ "epoch": 0.8977978543195935,
1119
+ "grad_norm": 0.08319137990474701,
1120
+ "learning_rate": 0.00016432234160928378,
1121
+ "loss": 0.6008,
1122
+ "step": 3975
1123
+ },
1124
+ {
1125
+ "epoch": 0.9034443817052513,
1126
+ "grad_norm": 0.11340347677469254,
1127
+ "learning_rate": 0.00016385432513594953,
1128
+ "loss": 0.502,
1129
+ "step": 4000
1130
+ },
1131
+ {
1132
+ "epoch": 0.9090909090909091,
1133
+ "grad_norm": 0.08557943999767303,
1134
+ "learning_rate": 0.0001633839350920531,
1135
+ "loss": 0.598,
1136
+ "step": 4025
1137
+ },
1138
+ {
1139
+ "epoch": 0.9147374364765669,
1140
+ "grad_norm": 0.09813399612903595,
1141
+ "learning_rate": 0.00016291118896276803,
1142
+ "loss": 0.5139,
1143
+ "step": 4050
1144
+ },
1145
+ {
1146
+ "epoch": 0.9203839638622248,
1147
+ "grad_norm": 0.07974950224161148,
1148
+ "learning_rate": 0.00016243610432084755,
1149
+ "loss": 0.6227,
1150
+ "step": 4075
1151
+ },
1152
+ {
1153
+ "epoch": 0.9260304912478825,
1154
+ "grad_norm": 0.09820155799388885,
1155
+ "learning_rate": 0.0001619586988259712,
1156
+ "loss": 0.5044,
1157
+ "step": 4100
1158
+ },
1159
+ {
1160
+ "epoch": 0.9316770186335404,
1161
+ "grad_norm": 0.0881289690732956,
1162
+ "learning_rate": 0.00016147899022408852,
1163
+ "loss": 0.6192,
1164
+ "step": 4125
1165
+ },
1166
+ {
1167
+ "epoch": 0.9373235460191982,
1168
+ "grad_norm": 0.11012347787618637,
1169
+ "learning_rate": 0.00016099699634675925,
1170
+ "loss": 0.508,
1171
+ "step": 4150
1172
+ },
1173
+ {
1174
+ "epoch": 0.9429700734048561,
1175
+ "grad_norm": 0.0851251408457756,
1176
+ "learning_rate": 0.00016051273511049065,
1177
+ "loss": 0.5897,
1178
+ "step": 4175
1179
+ },
1180
+ {
1181
+ "epoch": 0.9486166007905138,
1182
+ "grad_norm": 0.10288140922784805,
1183
+ "learning_rate": 0.0001600262245160714,
1184
+ "loss": 0.4803,
1185
+ "step": 4200
1186
+ },
1187
+ {
1188
+ "epoch": 0.9542631281761716,
1189
+ "grad_norm": 0.08995950222015381,
1190
+ "learning_rate": 0.0001595374826479026,
1191
+ "loss": 0.6203,
1192
+ "step": 4225
1193
+ },
1194
+ {
1195
+ "epoch": 0.9599096555618295,
1196
+ "grad_norm": 0.10717281699180603,
1197
+ "learning_rate": 0.00015904652767332537,
1198
+ "loss": 0.5068,
1199
+ "step": 4250
1200
+ },
1201
+ {
1202
+ "epoch": 0.9655561829474872,
1203
+ "grad_norm": 0.08305976539850235,
1204
+ "learning_rate": 0.00015855337784194577,
1205
+ "loss": 0.5919,
1206
+ "step": 4275
1207
+ },
1208
+ {
1209
+ "epoch": 0.9712027103331451,
1210
+ "grad_norm": 0.09328145533800125,
1211
+ "learning_rate": 0.00015805805148495623,
1212
+ "loss": 0.4948,
1213
+ "step": 4300
1214
+ },
1215
+ {
1216
+ "epoch": 0.9768492377188029,
1217
+ "grad_norm": 0.09493458271026611,
1218
+ "learning_rate": 0.00015756056701445422,
1219
+ "loss": 0.6024,
1220
+ "step": 4325
1221
+ },
1222
+ {
1223
+ "epoch": 0.9824957651044608,
1224
+ "grad_norm": 0.1051265150308609,
1225
+ "learning_rate": 0.0001570609429227579,
1226
+ "loss": 0.4991,
1227
+ "step": 4350
1228
+ },
1229
+ {
1230
+ "epoch": 0.9881422924901185,
1231
+ "grad_norm": 0.09176123887300491,
1232
+ "learning_rate": 0.00015655919778171862,
1233
+ "loss": 0.6006,
1234
+ "step": 4375
1235
+ },
1236
+ {
1237
+ "epoch": 0.9937888198757764,
1238
+ "grad_norm": 0.0787501335144043,
1239
+ "learning_rate": 0.00015605535024203069,
1240
+ "loss": 0.5013,
1241
+ "step": 4400
1242
+ },
1243
+ {
1244
+ "epoch": 0.9994353472614342,
1245
+ "grad_norm": 0.10489033907651901,
1246
+ "learning_rate": 0.00015554941903253797,
1247
+ "loss": 0.5548,
1248
+ "step": 4425
1249
+ },
1250
+ {
1251
+ "epoch": 1.005081874647092,
1252
+ "grad_norm": 0.08116624504327774,
1253
+ "learning_rate": 0.00015504142295953783,
1254
+ "loss": 0.5719,
1255
+ "step": 4450
1256
+ },
1257
+ {
1258
+ "epoch": 1.0107284020327498,
1259
+ "grad_norm": 0.09656750410795212,
1260
+ "learning_rate": 0.000154531380906082,
1261
+ "loss": 0.4752,
1262
+ "step": 4475
1263
+ },
1264
+ {
1265
+ "epoch": 1.0163749294184077,
1266
+ "grad_norm": 0.09433398395776749,
1267
+ "learning_rate": 0.0001540193118312747,
1268
+ "loss": 0.5796,
1269
+ "step": 4500
1270
+ },
1271
+ {
1272
+ "epoch": 1.0220214568040655,
1273
+ "grad_norm": 0.10783005505800247,
1274
+ "learning_rate": 0.0001535052347695678,
1275
+ "loss": 0.5077,
1276
+ "step": 4525
1277
+ },
1278
+ {
1279
+ "epoch": 1.0276679841897234,
1280
+ "grad_norm": 0.08784560114145279,
1281
+ "learning_rate": 0.00015298916883005342,
1282
+ "loss": 0.5571,
1283
+ "step": 4550
1284
+ },
1285
+ {
1286
+ "epoch": 1.0333145115753812,
1287
+ "grad_norm": 0.11868823319673538,
1288
+ "learning_rate": 0.00015247113319575358,
1289
+ "loss": 0.5223,
1290
+ "step": 4575
1291
+ },
1292
+ {
1293
+ "epoch": 1.0389610389610389,
1294
+ "grad_norm": 0.08813630044460297,
1295
+ "learning_rate": 0.000151951147122907,
1296
+ "loss": 0.561,
1297
+ "step": 4600
1298
+ },
1299
+ {
1300
+ "epoch": 1.0446075663466967,
1301
+ "grad_norm": 0.09996681660413742,
1302
+ "learning_rate": 0.0001514292299402535,
1303
+ "loss": 0.5138,
1304
+ "step": 4625
1305
+ },
1306
+ {
1307
+ "epoch": 1.0502540937323546,
1308
+ "grad_norm": 0.07442251592874527,
1309
+ "learning_rate": 0.00015090540104831539,
1310
+ "loss": 0.5698,
1311
+ "step": 4650
1312
+ },
1313
+ {
1314
+ "epoch": 1.0559006211180124,
1315
+ "grad_norm": 0.09993384033441544,
1316
+ "learning_rate": 0.00015037967991867642,
1317
+ "loss": 0.5093,
1318
+ "step": 4675
1319
+ },
1320
+ {
1321
+ "epoch": 1.0615471485036703,
1322
+ "grad_norm": 0.0890798568725586,
1323
+ "learning_rate": 0.0001498520860932579,
1324
+ "loss": 0.5481,
1325
+ "step": 4700
1326
+ },
1327
+ {
1328
+ "epoch": 1.0671936758893281,
1329
+ "grad_norm": 0.1006857305765152,
1330
+ "learning_rate": 0.00014932263918359228,
1331
+ "loss": 0.5045,
1332
+ "step": 4725
1333
+ },
1334
+ {
1335
+ "epoch": 1.072840203274986,
1336
+ "grad_norm": 0.08858868479728699,
1337
+ "learning_rate": 0.00014879135887009435,
1338
+ "loss": 0.5772,
1339
+ "step": 4750
1340
+ },
1341
+ {
1342
+ "epoch": 1.0784867306606438,
1343
+ "grad_norm": 0.11783988773822784,
1344
+ "learning_rate": 0.00014825826490132938,
1345
+ "loss": 0.4937,
1346
+ "step": 4775
1347
+ },
1348
+ {
1349
+ "epoch": 1.0841332580463015,
1350
+ "grad_norm": 0.0875164121389389,
1351
+ "learning_rate": 0.00014772337709327923,
1352
+ "loss": 0.5554,
1353
+ "step": 4800
1354
+ },
1355
+ {
1356
+ "epoch": 1.0897797854319593,
1357
+ "grad_norm": 0.112996406853199,
1358
+ "learning_rate": 0.00014718671532860592,
1359
+ "loss": 0.5126,
1360
+ "step": 4825
1361
+ },
1362
+ {
1363
+ "epoch": 1.0954263128176172,
1364
+ "grad_norm": 0.08834437280893326,
1365
+ "learning_rate": 0.000146648299555912,
1366
+ "loss": 0.5885,
1367
+ "step": 4850
1368
+ },
1369
+ {
1370
+ "epoch": 1.101072840203275,
1371
+ "grad_norm": 0.11341985315084457,
1372
+ "learning_rate": 0.00014610814978899983,
1373
+ "loss": 0.4871,
1374
+ "step": 4875
1375
+ },
1376
+ {
1377
+ "epoch": 1.1067193675889329,
1378
+ "grad_norm": 0.09301973134279251,
1379
+ "learning_rate": 0.00014556628610612677,
1380
+ "loss": 0.5839,
1381
+ "step": 4900
1382
+ },
1383
+ {
1384
+ "epoch": 1.1123658949745907,
1385
+ "grad_norm": 0.11545081436634064,
1386
+ "learning_rate": 0.00014502272864925955,
1387
+ "loss": 0.4868,
1388
+ "step": 4925
1389
+ },
1390
+ {
1391
+ "epoch": 1.1180124223602483,
1392
+ "grad_norm": 0.08969846367835999,
1393
+ "learning_rate": 0.00014447749762332515,
1394
+ "loss": 0.5472,
1395
+ "step": 4950
1396
+ },
1397
+ {
1398
+ "epoch": 1.1236589497459062,
1399
+ "grad_norm": 0.12094131112098694,
1400
+ "learning_rate": 0.00014393061329545992,
1401
+ "loss": 0.5234,
1402
+ "step": 4975
1403
+ },
1404
+ {
1405
+ "epoch": 1.129305477131564,
1406
+ "grad_norm": 0.0875294953584671,
1407
+ "learning_rate": 0.0001433820959942561,
1408
+ "loss": 0.5852,
1409
+ "step": 5000
1410
+ },
1411
+ {
1412
+ "epoch": 1.134952004517222,
1413
+ "grad_norm": 0.12163736671209335,
1414
+ "learning_rate": 0.00014283196610900638,
1415
+ "loss": 0.4951,
1416
+ "step": 5025
1417
+ },
1418
+ {
1419
+ "epoch": 1.1405985319028797,
1420
+ "grad_norm": 0.08404785394668579,
1421
+ "learning_rate": 0.00014230234328167044,
1422
+ "loss": 0.5629,
1423
+ "step": 5050
1424
+ },
1425
+ {
1426
+ "epoch": 1.1462450592885376,
1427
+ "grad_norm": 0.11473394185304642,
1428
+ "learning_rate": 0.0001417491121057749,
1429
+ "loss": 0.5062,
1430
+ "step": 5075
1431
+ },
1432
+ {
1433
+ "epoch": 1.1518915866741954,
1434
+ "grad_norm": 0.09582609683275223,
1435
+ "learning_rate": 0.0001411943290465374,
1436
+ "loss": 0.5705,
1437
+ "step": 5100
1438
+ },
1439
+ {
1440
+ "epoch": 1.1575381140598533,
1441
+ "grad_norm": 0.11270004510879517,
1442
+ "learning_rate": 0.00014063801472615902,
1443
+ "loss": 0.4918,
1444
+ "step": 5125
1445
+ },
1446
+ {
1447
+ "epoch": 1.163184641445511,
1448
+ "grad_norm": 0.2396761178970337,
1449
+ "learning_rate": 0.00014008018982376044,
1450
+ "loss": 0.5965,
1451
+ "step": 5150
1452
+ },
1453
+ {
1454
+ "epoch": 1.1688311688311688,
1455
+ "grad_norm": 0.1252664476633072,
1456
+ "learning_rate": 0.00013952087507461321,
1457
+ "loss": 0.4814,
1458
+ "step": 5175
1459
+ },
1460
+ {
1461
+ "epoch": 1.1744776962168266,
1462
+ "grad_norm": 0.10077520459890366,
1463
+ "learning_rate": 0.0001389600912693688,
1464
+ "loss": 0.5723,
1465
+ "step": 5200
1466
+ },
1467
+ {
1468
+ "epoch": 1.1801242236024845,
1469
+ "grad_norm": 0.10539643466472626,
1470
+ "learning_rate": 0.00013839785925328605,
1471
+ "loss": 0.4476,
1472
+ "step": 5225
1473
+ },
1474
+ {
1475
+ "epoch": 1.1857707509881423,
1476
+ "grad_norm": 0.0933731198310852,
1477
+ "learning_rate": 0.0001378341999254561,
1478
+ "loss": 0.5683,
1479
+ "step": 5250
1480
+ },
1481
+ {
1482
+ "epoch": 1.1914172783738002,
1483
+ "grad_norm": 0.12707217037677765,
1484
+ "learning_rate": 0.00013726913423802562,
1485
+ "loss": 0.5142,
1486
+ "step": 5275
1487
+ },
1488
+ {
1489
+ "epoch": 1.1970638057594578,
1490
+ "grad_norm": 0.08691050857305527,
1491
+ "learning_rate": 0.0001367026831954181,
1492
+ "loss": 0.5628,
1493
+ "step": 5300
1494
+ },
1495
+ {
1496
+ "epoch": 1.2027103331451157,
1497
+ "grad_norm": 0.10984601825475693,
1498
+ "learning_rate": 0.0001361348678535528,
1499
+ "loss": 0.4924,
1500
+ "step": 5325
1501
+ },
1502
+ {
1503
+ "epoch": 1.2083568605307735,
1504
+ "grad_norm": 0.10582837462425232,
1505
+ "learning_rate": 0.00013556570931906232,
1506
+ "loss": 0.5564,
1507
+ "step": 5350
1508
+ },
1509
+ {
1510
+ "epoch": 1.2140033879164314,
1511
+ "grad_norm": 0.1085626408457756,
1512
+ "learning_rate": 0.000134995228748508,
1513
+ "loss": 0.492,
1514
+ "step": 5375
1515
+ },
1516
+ {
1517
+ "epoch": 1.2196499153020892,
1518
+ "grad_norm": 0.11668406426906586,
1519
+ "learning_rate": 0.00013442344734759332,
1520
+ "loss": 0.5651,
1521
+ "step": 5400
1522
+ },
1523
+ {
1524
+ "epoch": 1.225296442687747,
1525
+ "grad_norm": 0.10734312981367111,
1526
+ "learning_rate": 0.00013385038637037585,
1527
+ "loss": 0.4848,
1528
+ "step": 5425
1529
+ },
1530
+ {
1531
+ "epoch": 1.230942970073405,
1532
+ "grad_norm": 0.10206615924835205,
1533
+ "learning_rate": 0.00013327606711847713,
1534
+ "loss": 0.5739,
1535
+ "step": 5450
1536
+ },
1537
+ {
1538
+ "epoch": 1.2365894974590628,
1539
+ "grad_norm": 0.11335214227437973,
1540
+ "learning_rate": 0.00013270051094029075,
1541
+ "loss": 0.4757,
1542
+ "step": 5475
1543
+ },
1544
+ {
1545
+ "epoch": 1.2422360248447206,
1546
+ "grad_norm": 0.10749132186174393,
1547
+ "learning_rate": 0.00013212373923018905,
1548
+ "loss": 0.5769,
1549
+ "step": 5500
1550
+ },
1551
+ {
1552
+ "epoch": 1.2478825522303783,
1553
+ "grad_norm": 0.13299238681793213,
1554
+ "learning_rate": 0.0001315457734277275,
1555
+ "loss": 0.4758,
1556
+ "step": 5525
1557
+ },
1558
+ {
1559
+ "epoch": 1.253529079616036,
1560
+ "grad_norm": 0.09394491463899612,
1561
+ "learning_rate": 0.00013096663501684813,
1562
+ "loss": 0.5465,
1563
+ "step": 5550
1564
+ },
1565
+ {
1566
+ "epoch": 1.259175607001694,
1567
+ "grad_norm": 0.11942502111196518,
1568
+ "learning_rate": 0.00013038634552508063,
1569
+ "loss": 0.478,
1570
+ "step": 5575
1571
+ },
1572
+ {
1573
+ "epoch": 1.2648221343873518,
1574
+ "grad_norm": 0.09682100266218185,
1575
+ "learning_rate": 0.00012980492652274234,
1576
+ "loss": 0.5667,
1577
+ "step": 5600
1578
+ },
1579
+ {
1580
+ "epoch": 1.2704686617730097,
1581
+ "grad_norm": 0.1254328489303589,
1582
+ "learning_rate": 0.00012922239962213637,
1583
+ "loss": 0.5116,
1584
+ "step": 5625
1585
+ },
1586
+ {
1587
+ "epoch": 1.2761151891586673,
1588
+ "grad_norm": 0.09513936936855316,
1589
+ "learning_rate": 0.00012863878647674816,
1590
+ "loss": 0.5433,
1591
+ "step": 5650
1592
+ },
1593
+ {
1594
+ "epoch": 1.2817617165443251,
1595
+ "grad_norm": 0.10922129452228546,
1596
+ "learning_rate": 0.00012805410878044074,
1597
+ "loss": 0.4867,
1598
+ "step": 5675
1599
+ },
1600
+ {
1601
+ "epoch": 1.287408243929983,
1602
+ "grad_norm": 0.09911426901817322,
1603
+ "learning_rate": 0.00012746838826664826,
1604
+ "loss": 0.5785,
1605
+ "step": 5700
1606
+ },
1607
+ {
1608
+ "epoch": 1.2930547713156408,
1609
+ "grad_norm": 0.11289256066083908,
1610
+ "learning_rate": 0.00012688164670756802,
1611
+ "loss": 0.4761,
1612
+ "step": 5725
1613
+ },
1614
+ {
1615
+ "epoch": 1.2987012987012987,
1616
+ "grad_norm": 0.08862913399934769,
1617
+ "learning_rate": 0.00012629390591335134,
1618
+ "loss": 0.5743,
1619
+ "step": 5750
1620
+ },
1621
+ {
1622
+ "epoch": 1.3043478260869565,
1623
+ "grad_norm": 0.13005360960960388,
1624
+ "learning_rate": 0.00012570518773129277,
1625
+ "loss": 0.49,
1626
+ "step": 5775
1627
+ },
1628
+ {
1629
+ "epoch": 1.3099943534726144,
1630
+ "grad_norm": 0.08972469717264175,
1631
+ "learning_rate": 0.0001251155140450179,
1632
+ "loss": 0.5443,
1633
+ "step": 5800
1634
+ },
1635
+ {
1636
+ "epoch": 1.3156408808582722,
1637
+ "grad_norm": 0.11599931865930557,
1638
+ "learning_rate": 0.00012452490677367003,
1639
+ "loss": 0.5138,
1640
+ "step": 5825
1641
+ },
1642
+ {
1643
+ "epoch": 1.32128740824393,
1644
+ "grad_norm": 0.096194326877594,
1645
+ "learning_rate": 0.0001239333878710954,
1646
+ "loss": 0.5524,
1647
+ "step": 5850
1648
+ },
1649
+ {
1650
+ "epoch": 1.3269339356295877,
1651
+ "grad_norm": 0.11309222131967545,
1652
+ "learning_rate": 0.00012334097932502702,
1653
+ "loss": 0.485,
1654
+ "step": 5875
1655
+ },
1656
+ {
1657
+ "epoch": 1.3325804630152456,
1658
+ "grad_norm": 0.09447719901800156,
1659
+ "learning_rate": 0.00012274770315626743,
1660
+ "loss": 0.5748,
1661
+ "step": 5900
1662
+ },
1663
+ {
1664
+ "epoch": 1.3382269904009034,
1665
+ "grad_norm": 0.11994371563196182,
1666
+ "learning_rate": 0.00012215358141787016,
1667
+ "loss": 0.4826,
1668
+ "step": 5925
1669
+ },
1670
+ {
1671
+ "epoch": 1.3438735177865613,
1672
+ "grad_norm": 0.10158982127904892,
1673
+ "learning_rate": 0.00012155863619431993,
1674
+ "loss": 0.5593,
1675
+ "step": 5950
1676
+ },
1677
+ {
1678
+ "epoch": 1.3495200451722191,
1679
+ "grad_norm": 0.1210799366235733,
1680
+ "learning_rate": 0.00012096288960071178,
1681
+ "loss": 0.4977,
1682
+ "step": 5975
1683
+ },
1684
+ {
1685
+ "epoch": 1.355166572557877,
1686
+ "grad_norm": 0.0946585088968277,
1687
+ "learning_rate": 0.00012036636378192902,
1688
+ "loss": 0.5617,
1689
+ "step": 6000
1690
+ },
1691
+ {
1692
+ "epoch": 1.3608130999435346,
1693
+ "grad_norm": 0.10858285427093506,
1694
+ "learning_rate": 0.00011976908091181998,
1695
+ "loss": 0.468,
1696
+ "step": 6025
1697
+ },
1698
+ {
1699
+ "epoch": 1.3664596273291925,
1700
+ "grad_norm": 0.08753529191017151,
1701
+ "learning_rate": 0.00011917106319237386,
1702
+ "loss": 0.5854,
1703
+ "step": 6050
1704
+ },
1705
+ {
1706
+ "epoch": 1.3721061547148503,
1707
+ "grad_norm": 0.1213916763663292,
1708
+ "learning_rate": 0.00011857233285289546,
1709
+ "loss": 0.4915,
1710
+ "step": 6075
1711
+ },
1712
+ {
1713
+ "epoch": 1.3777526821005082,
1714
+ "grad_norm": 0.09568001329898834,
1715
+ "learning_rate": 0.00011797291214917881,
1716
+ "loss": 0.5699,
1717
+ "step": 6100
1718
+ },
1719
+ {
1720
+ "epoch": 1.383399209486166,
1721
+ "grad_norm": 0.10872907191514969,
1722
+ "learning_rate": 0.00011737282336267992,
1723
+ "loss": 0.4744,
1724
+ "step": 6125
1725
+ },
1726
+ {
1727
+ "epoch": 1.3890457368718239,
1728
+ "grad_norm": 0.1102764755487442,
1729
+ "learning_rate": 0.00011677208879968858,
1730
+ "loss": 0.5315,
1731
+ "step": 6150
1732
+ },
1733
+ {
1734
+ "epoch": 1.3946922642574817,
1735
+ "grad_norm": 0.1172797903418541,
1736
+ "learning_rate": 0.00011617073079049905,
1737
+ "loss": 0.493,
1738
+ "step": 6175
1739
+ },
1740
+ {
1741
+ "epoch": 1.4003387916431396,
1742
+ "grad_norm": 0.09269782900810242,
1743
+ "learning_rate": 0.0001155687716885802,
1744
+ "loss": 0.5383,
1745
+ "step": 6200
1746
+ },
1747
+ {
1748
+ "epoch": 1.4059853190287974,
1749
+ "grad_norm": 0.11610530316829681,
1750
+ "learning_rate": 0.00011496623386974454,
1751
+ "loss": 0.4748,
1752
+ "step": 6225
1753
+ },
1754
+ {
1755
+ "epoch": 1.411631846414455,
1756
+ "grad_norm": 0.10046471655368805,
1757
+ "learning_rate": 0.00011436313973131634,
1758
+ "loss": 0.5397,
1759
+ "step": 6250
1760
+ },
1761
+ {
1762
+ "epoch": 1.417278373800113,
1763
+ "grad_norm": 0.1363869458436966,
1764
+ "learning_rate": 0.00011375951169129926,
1765
+ "loss": 0.4944,
1766
+ "step": 6275
1767
+ },
1768
+ {
1769
+ "epoch": 1.4229249011857708,
1770
+ "grad_norm": 0.09395238012075424,
1771
+ "learning_rate": 0.00011315537218754295,
1772
+ "loss": 0.5614,
1773
+ "step": 6300
1774
+ },
1775
+ {
1776
+ "epoch": 1.4285714285714286,
1777
+ "grad_norm": 0.11986027657985687,
1778
+ "learning_rate": 0.00011255074367690897,
1779
+ "loss": 0.4914,
1780
+ "step": 6325
1781
+ },
1782
+ {
1783
+ "epoch": 1.4342179559570865,
1784
+ "grad_norm": 0.0886669009923935,
1785
+ "learning_rate": 0.0001119456486344361,
1786
+ "loss": 0.5615,
1787
+ "step": 6350
1788
+ },
1789
+ {
1790
+ "epoch": 1.439864483342744,
1791
+ "grad_norm": 0.12676212191581726,
1792
+ "learning_rate": 0.00011134010955250491,
1793
+ "loss": 0.4836,
1794
+ "step": 6375
1795
+ },
1796
+ {
1797
+ "epoch": 1.445511010728402,
1798
+ "grad_norm": 0.09607352316379547,
1799
+ "learning_rate": 0.00011073414894000161,
1800
+ "loss": 0.5505,
1801
+ "step": 6400
1802
+ },
1803
+ {
1804
+ "epoch": 1.4511575381140598,
1805
+ "grad_norm": 0.12430471181869507,
1806
+ "learning_rate": 0.00011012778932148142,
1807
+ "loss": 0.4949,
1808
+ "step": 6425
1809
+ },
1810
+ {
1811
+ "epoch": 1.4568040654997176,
1812
+ "grad_norm": 0.10339995473623276,
1813
+ "learning_rate": 0.00010952105323633126,
1814
+ "loss": 0.5583,
1815
+ "step": 6450
1816
+ },
1817
+ {
1818
+ "epoch": 1.4624505928853755,
1819
+ "grad_norm": 0.11074826866388321,
1820
+ "learning_rate": 0.00010891396323793189,
1821
+ "loss": 0.4973,
1822
+ "step": 6475
1823
+ },
1824
+ {
1825
+ "epoch": 1.4680971202710333,
1826
+ "grad_norm": 0.09366384148597717,
1827
+ "learning_rate": 0.00010830654189281968,
1828
+ "loss": 0.5329,
1829
+ "step": 6500
1830
+ },
1831
+ {
1832
+ "epoch": 1.4737436476566912,
1833
+ "grad_norm": 0.12167912721633911,
1834
+ "learning_rate": 0.00010769881177984771,
1835
+ "loss": 0.4901,
1836
+ "step": 6525
1837
+ },
1838
+ {
1839
+ "epoch": 1.479390175042349,
1840
+ "grad_norm": 0.09269159287214279,
1841
+ "learning_rate": 0.0001070907954893464,
1842
+ "loss": 0.5685,
1843
+ "step": 6550
1844
+ },
1845
+ {
1846
+ "epoch": 1.485036702428007,
1847
+ "grad_norm": 0.11428316682577133,
1848
+ "learning_rate": 0.00010648251562228386,
1849
+ "loss": 0.5,
1850
+ "step": 6575
1851
+ },
1852
+ {
1853
+ "epoch": 1.4906832298136645,
1854
+ "grad_norm": 0.10255276411771774,
1855
+ "learning_rate": 0.00010587399478942592,
1856
+ "loss": 0.5492,
1857
+ "step": 6600
1858
+ },
1859
+ {
1860
+ "epoch": 1.4963297571993224,
1861
+ "grad_norm": 0.10394936800003052,
1862
+ "learning_rate": 0.0001052652556104953,
1863
+ "loss": 0.4788,
1864
+ "step": 6625
1865
+ },
1866
+ {
1867
+ "epoch": 1.5019762845849802,
1868
+ "grad_norm": 0.0881161019206047,
1869
+ "learning_rate": 0.00010465632071333113,
1870
+ "loss": 0.5606,
1871
+ "step": 6650
1872
+ },
1873
+ {
1874
+ "epoch": 1.507622811970638,
1875
+ "grad_norm": 0.1109280213713646,
1876
+ "learning_rate": 0.00010404721273304769,
1877
+ "loss": 0.5183,
1878
+ "step": 6675
1879
+ },
1880
+ {
1881
+ "epoch": 1.513269339356296,
1882
+ "grad_norm": 0.10558915883302689,
1883
+ "learning_rate": 0.00010343795431119304,
1884
+ "loss": 0.5563,
1885
+ "step": 6700
1886
+ },
1887
+ {
1888
+ "epoch": 1.5189158667419536,
1889
+ "grad_norm": 0.13079263269901276,
1890
+ "learning_rate": 0.00010282856809490739,
1891
+ "loss": 0.4977,
1892
+ "step": 6725
1893
+ },
1894
+ {
1895
+ "epoch": 1.5245623941276114,
1896
+ "grad_norm": 0.09773046523332596,
1897
+ "learning_rate": 0.00010221907673608133,
1898
+ "loss": 0.5698,
1899
+ "step": 6750
1900
+ },
1901
+ {
1902
+ "epoch": 1.5302089215132693,
1903
+ "grad_norm": 0.11996293067932129,
1904
+ "learning_rate": 0.00010160950289051365,
1905
+ "loss": 0.4764,
1906
+ "step": 6775
1907
+ },
1908
+ {
1909
+ "epoch": 1.5358554488989271,
1910
+ "grad_norm": 0.12360116094350815,
1911
+ "learning_rate": 0.00010099986921706946,
1912
+ "loss": 0.5274,
1913
+ "step": 6800
1914
+ },
1915
+ {
1916
+ "epoch": 1.541501976284585,
1917
+ "grad_norm": 0.1305209845304489,
1918
+ "learning_rate": 0.00010039019837683767,
1919
+ "loss": 0.4531,
1920
+ "step": 6825
1921
+ },
1922
+ {
1923
+ "epoch": 1.5471485036702428,
1924
+ "grad_norm": 0.10246080160140991,
1925
+ "learning_rate": 9.978051303228875e-05,
1926
+ "loss": 0.5593,
1927
+ "step": 6850
1928
+ },
1929
+ {
1930
+ "epoch": 1.5527950310559007,
1931
+ "grad_norm": 0.13810117542743683,
1932
+ "learning_rate": 9.917083584643235e-05,
1933
+ "loss": 0.4838,
1934
+ "step": 6875
1935
+ },
1936
+ {
1937
+ "epoch": 1.5584415584415585,
1938
+ "grad_norm": 0.10199406743049622,
1939
+ "learning_rate": 9.856118948197488e-05,
1940
+ "loss": 0.5405,
1941
+ "step": 6900
1942
+ },
1943
+ {
1944
+ "epoch": 1.5640880858272164,
1945
+ "grad_norm": 0.11060495674610138,
1946
+ "learning_rate": 9.795159660047697e-05,
1947
+ "loss": 0.4974,
1948
+ "step": 6925
1949
+ },
1950
+ {
1951
+ "epoch": 1.5697346132128742,
1952
+ "grad_norm": 0.10460948944091797,
1953
+ "learning_rate": 9.734207986151126e-05,
1954
+ "loss": 0.5568,
1955
+ "step": 6950
1956
+ },
1957
+ {
1958
+ "epoch": 1.5753811405985318,
1959
+ "grad_norm": 0.11652641743421555,
1960
+ "learning_rate": 9.673266192182008e-05,
1961
+ "loss": 0.4683,
1962
+ "step": 6975
1963
+ },
1964
+ {
1965
+ "epoch": 1.5810276679841897,
1966
+ "grad_norm": 0.09894441068172455,
1967
+ "learning_rate": 9.612336543447314e-05,
1968
+ "loss": 0.5598,
1969
+ "step": 7000
1970
+ },
1971
+ {
1972
+ "epoch": 1.5866741953698476,
1973
+ "grad_norm": 0.10987823456525803,
1974
+ "learning_rate": 9.551421304802565e-05,
1975
+ "loss": 0.4582,
1976
+ "step": 7025
1977
+ },
1978
+ {
1979
+ "epoch": 1.5923207227555054,
1980
+ "grad_norm": 0.09542589634656906,
1981
+ "learning_rate": 9.490522740567633e-05,
1982
+ "loss": 0.5482,
1983
+ "step": 7050
1984
+ },
1985
+ {
1986
+ "epoch": 1.597967250141163,
1987
+ "grad_norm": 0.12428826838731766,
1988
+ "learning_rate": 9.42964311444257e-05,
1989
+ "loss": 0.4999,
1990
+ "step": 7075
1991
+ },
1992
+ {
1993
+ "epoch": 1.6036137775268209,
1994
+ "grad_norm": 0.10819413512945175,
1995
+ "learning_rate": 9.368784689423467e-05,
1996
+ "loss": 0.5652,
1997
+ "step": 7100
1998
+ },
1999
+ {
2000
+ "epoch": 1.6092603049124787,
2001
+ "grad_norm": 0.13115598261356354,
2002
+ "learning_rate": 9.307949727718346e-05,
2003
+ "loss": 0.4771,
2004
+ "step": 7125
2005
+ },
2006
+ {
2007
+ "epoch": 1.6149068322981366,
2008
+ "grad_norm": 0.1047302857041359,
2009
+ "learning_rate": 9.24714049066305e-05,
2010
+ "loss": 0.5376,
2011
+ "step": 7150
2012
+ },
2013
+ {
2014
+ "epoch": 1.6205533596837944,
2015
+ "grad_norm": 0.13034017384052277,
2016
+ "learning_rate": 9.186359238637197e-05,
2017
+ "loss": 0.4863,
2018
+ "step": 7175
2019
+ },
2020
+ {
2021
+ "epoch": 1.6261998870694523,
2022
+ "grad_norm": 0.10137925297021866,
2023
+ "learning_rate": 9.12560823098015e-05,
2024
+ "loss": 0.5442,
2025
+ "step": 7200
2026
+ },
2027
+ {
2028
+ "epoch": 1.6318464144551101,
2029
+ "grad_norm": 0.12191277742385864,
2030
+ "learning_rate": 9.064889725907043e-05,
2031
+ "loss": 0.4717,
2032
+ "step": 7225
2033
+ },
2034
+ {
2035
+ "epoch": 1.637492941840768,
2036
+ "grad_norm": 0.10191314667463303,
2037
+ "learning_rate": 9.004205980424842e-05,
2038
+ "loss": 0.5457,
2039
+ "step": 7250
2040
+ },
2041
+ {
2042
+ "epoch": 1.6431394692264258,
2043
+ "grad_norm": 0.11787448078393936,
2044
+ "learning_rate": 8.943559250248426e-05,
2045
+ "loss": 0.4858,
2046
+ "step": 7275
2047
+ },
2048
+ {
2049
+ "epoch": 1.6487859966120837,
2050
+ "grad_norm": 0.1057475134730339,
2051
+ "learning_rate": 8.88295178971677e-05,
2052
+ "loss": 0.5735,
2053
+ "step": 7300
2054
+ },
2055
+ {
2056
+ "epoch": 1.6544325239977415,
2057
+ "grad_norm": 0.12938141822814941,
2058
+ "learning_rate": 8.822385851709125e-05,
2059
+ "loss": 0.4829,
2060
+ "step": 7325
2061
+ },
2062
+ {
2063
+ "epoch": 1.6600790513833992,
2064
+ "grad_norm": 0.10724066197872162,
2065
+ "learning_rate": 8.761863687561275e-05,
2066
+ "loss": 0.5408,
2067
+ "step": 7350
2068
+ },
2069
+ {
2070
+ "epoch": 1.665725578769057,
2071
+ "grad_norm": 0.11694779992103577,
2072
+ "learning_rate": 8.701387546981868e-05,
2073
+ "loss": 0.4961,
2074
+ "step": 7375
2075
+ },
2076
+ {
2077
+ "epoch": 1.6713721061547149,
2078
+ "grad_norm": 0.10590225458145142,
2079
+ "learning_rate": 8.640959677968778e-05,
2080
+ "loss": 0.5466,
2081
+ "step": 7400
2082
+ },
2083
+ {
2084
+ "epoch": 1.6770186335403725,
2085
+ "grad_norm": 0.11699523031711578,
2086
+ "learning_rate": 8.580582326725535e-05,
2087
+ "loss": 0.4709,
2088
+ "step": 7425
2089
+ },
2090
+ {
2091
+ "epoch": 1.6826651609260304,
2092
+ "grad_norm": 0.1064140573143959,
2093
+ "learning_rate": 8.520257737577854e-05,
2094
+ "loss": 0.5349,
2095
+ "step": 7450
2096
+ },
2097
+ {
2098
+ "epoch": 1.6883116883116882,
2099
+ "grad_norm": 0.12415055185556412,
2100
+ "learning_rate": 8.459988152890188e-05,
2101
+ "loss": 0.4655,
2102
+ "step": 7475
2103
+ },
2104
+ {
2105
+ "epoch": 1.693958215697346,
2106
+ "grad_norm": 0.11068243533372879,
2107
+ "learning_rate": 8.39977581298239e-05,
2108
+ "loss": 0.5459,
2109
+ "step": 7500
2110
+ },
2111
+ {
2112
+ "epoch": 1.699604743083004,
2113
+ "grad_norm": 0.12139423191547394,
2114
+ "learning_rate": 8.339622956046417e-05,
2115
+ "loss": 0.4657,
2116
+ "step": 7525
2117
+ },
2118
+ {
2119
+ "epoch": 1.7052512704686618,
2120
+ "grad_norm": 0.10302968323230743,
2121
+ "learning_rate": 8.27953181806316e-05,
2122
+ "loss": 0.5571,
2123
+ "step": 7550
2124
+ },
2125
+ {
2126
+ "epoch": 1.7108977978543196,
2127
+ "grad_norm": 0.12433881312608719,
2128
+ "learning_rate": 8.21950463271931e-05,
2129
+ "loss": 0.4887,
2130
+ "step": 7575
2131
+ },
2132
+ {
2133
+ "epoch": 1.7165443252399775,
2134
+ "grad_norm": 0.09217355400323868,
2135
+ "learning_rate": 8.159543631324327e-05,
2136
+ "loss": 0.5281,
2137
+ "step": 7600
2138
+ },
2139
+ {
2140
+ "epoch": 1.7221908526256353,
2141
+ "grad_norm": 0.11367136240005493,
2142
+ "learning_rate": 8.099651042727515e-05,
2143
+ "loss": 0.4849,
2144
+ "step": 7625
2145
+ },
2146
+ {
2147
+ "epoch": 1.7278373800112932,
2148
+ "grad_norm": 0.10472942888736725,
2149
+ "learning_rate": 8.039829093235156e-05,
2150
+ "loss": 0.5748,
2151
+ "step": 7650
2152
+ },
2153
+ {
2154
+ "epoch": 1.733483907396951,
2155
+ "grad_norm": 0.13037872314453125,
2156
+ "learning_rate": 7.980080006527751e-05,
2157
+ "loss": 0.4781,
2158
+ "step": 7675
2159
+ },
2160
+ {
2161
+ "epoch": 1.7391304347826086,
2162
+ "grad_norm": 0.1035398542881012,
2163
+ "learning_rate": 7.920406003577394e-05,
2164
+ "loss": 0.5419,
2165
+ "step": 7700
2166
+ },
2167
+ {
2168
+ "epoch": 1.7447769621682665,
2169
+ "grad_norm": 0.12669602036476135,
2170
+ "learning_rate": 7.86080930256517e-05,
2171
+ "loss": 0.4865,
2172
+ "step": 7725
2173
+ },
2174
+ {
2175
+ "epoch": 1.7504234895539243,
2176
+ "grad_norm": 0.09713231027126312,
2177
+ "learning_rate": 7.801292118798732e-05,
2178
+ "loss": 0.564,
2179
+ "step": 7750
2180
+ },
2181
+ {
2182
+ "epoch": 1.7560700169395822,
2183
+ "grad_norm": 0.12088830769062042,
2184
+ "learning_rate": 7.74185666462995e-05,
2185
+ "loss": 0.4641,
2186
+ "step": 7775
2187
+ },
2188
+ {
2189
+ "epoch": 1.7617165443252398,
2190
+ "grad_norm": 0.11002447456121445,
2191
+ "learning_rate": 7.68250514937266e-05,
2192
+ "loss": 0.5407,
2193
+ "step": 7800
2194
+ },
2195
+ {
2196
+ "epoch": 1.7673630717108977,
2197
+ "grad_norm": 0.12338761240243912,
2198
+ "learning_rate": 7.623239779220557e-05,
2199
+ "loss": 0.4558,
2200
+ "step": 7825
2201
+ },
2202
+ {
2203
+ "epoch": 1.7730095990965555,
2204
+ "grad_norm": 0.10458722710609436,
2205
+ "learning_rate": 7.564062757165183e-05,
2206
+ "loss": 0.55,
2207
+ "step": 7850
2208
+ },
2209
+ {
2210
+ "epoch": 1.7786561264822134,
2211
+ "grad_norm": 0.1287498027086258,
2212
+ "learning_rate": 7.504976282914027e-05,
2213
+ "loss": 0.4745,
2214
+ "step": 7875
2215
+ },
2216
+ {
2217
+ "epoch": 1.7843026538678712,
2218
+ "grad_norm": 0.10165251046419144,
2219
+ "learning_rate": 7.445982552808774e-05,
2220
+ "loss": 0.567,
2221
+ "step": 7900
2222
+ },
2223
+ {
2224
+ "epoch": 1.789949181253529,
2225
+ "grad_norm": 0.12862220406532288,
2226
+ "learning_rate": 7.387083759743655e-05,
2227
+ "loss": 0.4777,
2228
+ "step": 7925
2229
+ },
2230
+ {
2231
+ "epoch": 1.795595708639187,
2232
+ "grad_norm": 0.1015312671661377,
2233
+ "learning_rate": 7.328282093083929e-05,
2234
+ "loss": 0.5648,
2235
+ "step": 7950
2236
+ },
2237
+ {
2238
+ "epoch": 1.8012422360248448,
2239
+ "grad_norm": 0.1260487586259842,
2240
+ "learning_rate": 7.269579738584513e-05,
2241
+ "loss": 0.4895,
2242
+ "step": 7975
2243
+ },
2244
+ {
2245
+ "epoch": 1.8068887634105026,
2246
+ "grad_norm": 0.10070119798183441,
2247
+ "learning_rate": 7.210978878308729e-05,
2248
+ "loss": 0.581,
2249
+ "step": 8000
2250
+ },
2251
+ {
2252
+ "epoch": 1.8125352907961605,
2253
+ "grad_norm": 0.12946705520153046,
2254
+ "learning_rate": 7.152481690547182e-05,
2255
+ "loss": 0.475,
2256
+ "step": 8025
2257
+ },
2258
+ {
2259
+ "epoch": 1.8181818181818183,
2260
+ "grad_norm": 0.09579546749591827,
2261
+ "learning_rate": 7.094090349736803e-05,
2262
+ "loss": 0.5516,
2263
+ "step": 8050
2264
+ },
2265
+ {
2266
+ "epoch": 1.823828345567476,
2267
+ "grad_norm": 0.12078605592250824,
2268
+ "learning_rate": 7.035807026380026e-05,
2269
+ "loss": 0.4882,
2270
+ "step": 8075
2271
+ },
2272
+ {
2273
+ "epoch": 1.8294748729531338,
2274
+ "grad_norm": 0.10442069917917252,
2275
+ "learning_rate": 6.977633886964081e-05,
2276
+ "loss": 0.5322,
2277
+ "step": 8100
2278
+ },
2279
+ {
2280
+ "epoch": 1.8351214003387917,
2281
+ "grad_norm": 0.13175725936889648,
2282
+ "learning_rate": 6.919573093880494e-05,
2283
+ "loss": 0.4578,
2284
+ "step": 8125
2285
+ },
2286
+ {
2287
+ "epoch": 1.8407679277244493,
2288
+ "grad_norm": 0.10551594197750092,
2289
+ "learning_rate": 6.861626805344689e-05,
2290
+ "loss": 0.547,
2291
+ "step": 8150
2292
+ },
2293
+ {
2294
+ "epoch": 1.8464144551101072,
2295
+ "grad_norm": 0.11718405783176422,
2296
+ "learning_rate": 6.803797175315761e-05,
2297
+ "loss": 0.4872,
2298
+ "step": 8175
2299
+ },
2300
+ {
2301
+ "epoch": 1.852060982495765,
2302
+ "grad_norm": 0.12317229807376862,
2303
+ "learning_rate": 6.74608635341642e-05,
2304
+ "loss": 0.5724,
2305
+ "step": 8200
2306
+ },
2307
+ {
2308
+ "epoch": 1.8577075098814229,
2309
+ "grad_norm": 0.13172867894172668,
2310
+ "learning_rate": 6.688496484853084e-05,
2311
+ "loss": 0.4506,
2312
+ "step": 8225
2313
+ },
2314
+ {
2315
+ "epoch": 1.8633540372670807,
2316
+ "grad_norm": 0.09928746521472931,
2317
+ "learning_rate": 6.631029710336133e-05,
2318
+ "loss": 0.5094,
2319
+ "step": 8250
2320
+ },
2321
+ {
2322
+ "epoch": 1.8690005646527386,
2323
+ "grad_norm": 0.12048971652984619,
2324
+ "learning_rate": 6.573688166000345e-05,
2325
+ "loss": 0.4608,
2326
+ "step": 8275
2327
+ },
2328
+ {
2329
+ "epoch": 1.8746470920383964,
2330
+ "grad_norm": 0.1059262603521347,
2331
+ "learning_rate": 6.516473983325473e-05,
2332
+ "loss": 0.5475,
2333
+ "step": 8300
2334
+ },
2335
+ {
2336
+ "epoch": 1.8802936194240543,
2337
+ "grad_norm": 0.1448829621076584,
2338
+ "learning_rate": 6.459389289057038e-05,
2339
+ "loss": 0.4695,
2340
+ "step": 8325
2341
+ },
2342
+ {
2343
+ "epoch": 1.8859401468097121,
2344
+ "grad_norm": 0.0976184606552124,
2345
+ "learning_rate": 6.40243620512726e-05,
2346
+ "loss": 0.549,
2347
+ "step": 8350
2348
+ },
2349
+ {
2350
+ "epoch": 1.89158667419537,
2351
+ "grad_norm": 0.14233841001987457,
2352
+ "learning_rate": 6.345616848576184e-05,
2353
+ "loss": 0.4716,
2354
+ "step": 8375
2355
+ },
2356
+ {
2357
+ "epoch": 1.8972332015810278,
2358
+ "grad_norm": 0.10030635446310043,
2359
+ "learning_rate": 6.288933331472988e-05,
2360
+ "loss": 0.561,
2361
+ "step": 8400
2362
+ },
2363
+ {
2364
+ "epoch": 1.9028797289666854,
2365
+ "grad_norm": 0.12384554743766785,
2366
+ "learning_rate": 6.232387760837474e-05,
2367
+ "loss": 0.4872,
2368
+ "step": 8425
2369
+ },
2370
+ {
2371
+ "epoch": 1.9085262563523433,
2372
+ "grad_norm": 0.10905805230140686,
2373
+ "learning_rate": 6.175982238561755e-05,
2374
+ "loss": 0.5347,
2375
+ "step": 8450
2376
+ },
2377
+ {
2378
+ "epoch": 1.9141727837380011,
2379
+ "grad_norm": 0.13816171884536743,
2380
+ "learning_rate": 6.119718861332098e-05,
2381
+ "loss": 0.477,
2382
+ "step": 8475
2383
+ },
2384
+ {
2385
+ "epoch": 1.919819311123659,
2386
+ "grad_norm": 0.11039167642593384,
2387
+ "learning_rate": 6.0635997205510175e-05,
2388
+ "loss": 0.5706,
2389
+ "step": 8500
2390
+ },
2391
+ {
2392
+ "epoch": 1.9254658385093166,
2393
+ "grad_norm": 0.1241937056183815,
2394
+ "learning_rate": 6.007626902259521e-05,
2395
+ "loss": 0.4787,
2396
+ "step": 8525
2397
+ },
2398
+ {
2399
+ "epoch": 1.9311123658949745,
2400
+ "grad_norm": 0.1162077784538269,
2401
+ "learning_rate": 5.951802487059559e-05,
2402
+ "loss": 0.5515,
2403
+ "step": 8550
2404
+ },
2405
+ {
2406
+ "epoch": 1.9367588932806323,
2407
+ "grad_norm": 0.12294231355190277,
2408
+ "learning_rate": 5.8961285500367034e-05,
2409
+ "loss": 0.4699,
2410
+ "step": 8575
2411
+ },
2412
+ {
2413
+ "epoch": 1.9424054206662902,
2414
+ "grad_norm": 0.10771624743938446,
2415
+ "learning_rate": 5.8406071606830026e-05,
2416
+ "loss": 0.5373,
2417
+ "step": 8600
2418
+ },
2419
+ {
2420
+ "epoch": 1.948051948051948,
2421
+ "grad_norm": 0.11943277716636658,
2422
+ "learning_rate": 5.7852403828200495e-05,
2423
+ "loss": 0.4648,
2424
+ "step": 8625
2425
+ },
2426
+ {
2427
+ "epoch": 1.9536984754376059,
2428
+ "grad_norm": 0.11853492259979248,
2429
+ "learning_rate": 5.730030274522282e-05,
2430
+ "loss": 0.5501,
2431
+ "step": 8650
2432
+ },
2433
+ {
2434
+ "epoch": 1.9593450028232637,
2435
+ "grad_norm": 0.12967811524868011,
2436
+ "learning_rate": 5.674978888040463e-05,
2437
+ "loss": 0.4808,
2438
+ "step": 8675
2439
+ },
2440
+ {
2441
+ "epoch": 1.9649915302089216,
2442
+ "grad_norm": 0.112027108669281,
2443
+ "learning_rate": 5.6200882697254154e-05,
2444
+ "loss": 0.5311,
2445
+ "step": 8700
2446
+ },
2447
+ {
2448
+ "epoch": 1.9706380575945794,
2449
+ "grad_norm": 0.1347729116678238,
2450
+ "learning_rate": 5.565360459951936e-05,
2451
+ "loss": 0.4679,
2452
+ "step": 8725
2453
+ },
2454
+ {
2455
+ "epoch": 1.9762845849802373,
2456
+ "grad_norm": 0.11015453189611435,
2457
+ "learning_rate": 5.510797493042954e-05,
2458
+ "loss": 0.5595,
2459
+ "step": 8750
2460
+ },
2461
+ {
2462
+ "epoch": 1.981931112365895,
2463
+ "grad_norm": 0.13183894753456116,
2464
+ "learning_rate": 5.456401397193936e-05,
2465
+ "loss": 0.4656,
2466
+ "step": 8775
2467
+ },
2468
+ {
2469
+ "epoch": 1.9875776397515528,
2470
+ "grad_norm": 0.10906127840280533,
2471
+ "learning_rate": 5.402174194397458e-05,
2472
+ "loss": 0.537,
2473
+ "step": 8800
2474
+ },
2475
+ {
2476
+ "epoch": 1.9932241671372106,
2477
+ "grad_norm": 0.1271781325340271,
2478
+ "learning_rate": 5.348117900368066e-05,
2479
+ "loss": 0.4639,
2480
+ "step": 8825
2481
+ },
2482
+ {
2483
+ "epoch": 1.9988706945228685,
2484
+ "grad_norm": 0.12033294886350632,
2485
+ "learning_rate": 5.2942345244673564e-05,
2486
+ "loss": 0.5076,
2487
+ "step": 8850
2488
+ },
2489
+ {
2490
+ "epoch": 2.004517221908526,
2491
+ "grad_norm": 0.11611133068799973,
2492
+ "learning_rate": 5.240526069629265e-05,
2493
+ "loss": 0.5368,
2494
+ "step": 8875
2495
+ },
2496
+ {
2497
+ "epoch": 2.010163749294184,
2498
+ "grad_norm": 0.16251997649669647,
2499
+ "learning_rate": 5.1869945322856196e-05,
2500
+ "loss": 0.4708,
2501
+ "step": 8900
2502
+ },
2503
+ {
2504
+ "epoch": 2.015810276679842,
2505
+ "grad_norm": 0.10342962294816971,
2506
+ "learning_rate": 5.1336419022919435e-05,
2507
+ "loss": 0.5186,
2508
+ "step": 8925
2509
+ },
2510
+ {
2511
+ "epoch": 2.0214568040654997,
2512
+ "grad_norm": 0.12473160028457642,
2513
+ "learning_rate": 5.080470162853472e-05,
2514
+ "loss": 0.4405,
2515
+ "step": 8950
2516
+ },
2517
+ {
2518
+ "epoch": 2.0271033314511575,
2519
+ "grad_norm": 0.10961506515741348,
2520
+ "learning_rate": 5.0274812904514346e-05,
2521
+ "loss": 0.4963,
2522
+ "step": 8975
2523
+ },
2524
+ {
2525
+ "epoch": 2.0327498588368154,
2526
+ "grad_norm": 0.13045734167099,
2527
+ "learning_rate": 4.974677254769608e-05,
2528
+ "loss": 0.4648,
2529
+ "step": 9000
2530
+ },
2531
+ {
2532
+ "epoch": 2.038396386222473,
2533
+ "grad_norm": 0.10588447749614716,
2534
+ "learning_rate": 4.922060018621066e-05,
2535
+ "loss": 0.514,
2536
+ "step": 9025
2537
+ },
2538
+ {
2539
+ "epoch": 2.044042913608131,
2540
+ "grad_norm": 0.1310020089149475,
2541
+ "learning_rate": 4.869631537875243e-05,
2542
+ "loss": 0.4581,
2543
+ "step": 9050
2544
+ },
2545
+ {
2546
+ "epoch": 2.049689440993789,
2547
+ "grad_norm": 0.11264315247535706,
2548
+ "learning_rate": 4.8173937613852296e-05,
2549
+ "loss": 0.514,
2550
+ "step": 9075
2551
+ },
2552
+ {
2553
+ "epoch": 2.0553359683794468,
2554
+ "grad_norm": 0.11348750442266464,
2555
+ "learning_rate": 4.765348630915315e-05,
2556
+ "loss": 0.4509,
2557
+ "step": 9100
2558
+ },
2559
+ {
2560
+ "epoch": 2.0609824957651046,
2561
+ "grad_norm": 0.1084527000784874,
2562
+ "learning_rate": 4.713498081068819e-05,
2563
+ "loss": 0.4836,
2564
+ "step": 9125
2565
+ },
2566
+ {
2567
+ "epoch": 2.0666290231507625,
2568
+ "grad_norm": 0.12957565486431122,
2569
+ "learning_rate": 4.6618440392161886e-05,
2570
+ "loss": 0.4467,
2571
+ "step": 9150
2572
+ },
2573
+ {
2574
+ "epoch": 2.0722755505364203,
2575
+ "grad_norm": 0.10537248849868774,
2576
+ "learning_rate": 4.610388425423336e-05,
2577
+ "loss": 0.52,
2578
+ "step": 9175
2579
+ },
2580
+ {
2581
+ "epoch": 2.0779220779220777,
2582
+ "grad_norm": 0.13615071773529053,
2583
+ "learning_rate": 4.559133152380272e-05,
2584
+ "loss": 0.4567,
2585
+ "step": 9200
2586
+ },
2587
+ {
2588
+ "epoch": 2.0835686053077356,
2589
+ "grad_norm": 0.11438791453838348,
2590
+ "learning_rate": 4.508080125330022e-05,
2591
+ "loss": 0.5111,
2592
+ "step": 9225
2593
+ },
2594
+ {
2595
+ "epoch": 2.0892151326933934,
2596
+ "grad_norm": 0.1288277804851532,
2597
+ "learning_rate": 4.457231241997788e-05,
2598
+ "loss": 0.4584,
2599
+ "step": 9250
2600
+ },
2601
+ {
2602
+ "epoch": 2.0948616600790513,
2603
+ "grad_norm": 0.10171278566122055,
2604
+ "learning_rate": 4.40658839252041e-05,
2605
+ "loss": 0.5065,
2606
+ "step": 9275
2607
+ },
2608
+ {
2609
+ "epoch": 2.100508187464709,
2610
+ "grad_norm": 0.1178368479013443,
2611
+ "learning_rate": 4.356153459376121e-05,
2612
+ "loss": 0.4426,
2613
+ "step": 9300
2614
+ },
2615
+ {
2616
+ "epoch": 2.106154714850367,
2617
+ "grad_norm": 0.12345319241285324,
2618
+ "learning_rate": 4.305928317314549e-05,
2619
+ "loss": 0.5134,
2620
+ "step": 9325
2621
+ },
2622
+ {
2623
+ "epoch": 2.111801242236025,
2624
+ "grad_norm": 0.1341843158006668,
2625
+ "learning_rate": 4.255914833287046e-05,
2626
+ "loss": 0.4526,
2627
+ "step": 9350
2628
+ },
2629
+ {
2630
+ "epoch": 2.1174477696216827,
2631
+ "grad_norm": 0.12422988563776016,
2632
+ "learning_rate": 4.206114866377291e-05,
2633
+ "loss": 0.5025,
2634
+ "step": 9375
2635
+ },
2636
+ {
2637
+ "epoch": 2.1230942970073405,
2638
+ "grad_norm": 0.1362808346748352,
2639
+ "learning_rate": 4.156530267732173e-05,
2640
+ "loss": 0.4701,
2641
+ "step": 9400
2642
+ },
2643
+ {
2644
+ "epoch": 2.1287408243929984,
2645
+ "grad_norm": 0.11891162395477295,
2646
+ "learning_rate": 4.107162880492984e-05,
2647
+ "loss": 0.5091,
2648
+ "step": 9425
2649
+ },
2650
+ {
2651
+ "epoch": 2.1343873517786562,
2652
+ "grad_norm": 0.13123708963394165,
2653
+ "learning_rate": 4.058014539726922e-05,
2654
+ "loss": 0.4593,
2655
+ "step": 9450
2656
+ },
2657
+ {
2658
+ "epoch": 2.140033879164314,
2659
+ "grad_norm": 0.11908406764268875,
2660
+ "learning_rate": 4.0090870723588606e-05,
2661
+ "loss": 0.5076,
2662
+ "step": 9475
2663
+ },
2664
+ {
2665
+ "epoch": 2.145680406549972,
2666
+ "grad_norm": 0.1421327143907547,
2667
+ "learning_rate": 3.960382297103442e-05,
2668
+ "loss": 0.4467,
2669
+ "step": 9500
2670
+ },
2671
+ {
2672
+ "epoch": 2.15132693393563,
2673
+ "grad_norm": 0.1141195222735405,
2674
+ "learning_rate": 3.911902024397473e-05,
2675
+ "loss": 0.5044,
2676
+ "step": 9525
2677
+ },
2678
+ {
2679
+ "epoch": 2.1569734613212876,
2680
+ "grad_norm": 0.11890695989131927,
2681
+ "learning_rate": 3.8636480563326425e-05,
2682
+ "loss": 0.4562,
2683
+ "step": 9550
2684
+ },
2685
+ {
2686
+ "epoch": 2.162619988706945,
2687
+ "grad_norm": 0.12307918071746826,
2688
+ "learning_rate": 3.8156221865885126e-05,
2689
+ "loss": 0.5154,
2690
+ "step": 9575
2691
+ },
2692
+ {
2693
+ "epoch": 2.168266516092603,
2694
+ "grad_norm": 0.12713749706745148,
2695
+ "learning_rate": 3.767826200365853e-05,
2696
+ "loss": 0.4578,
2697
+ "step": 9600
2698
+ },
2699
+ {
2700
+ "epoch": 2.1739130434782608,
2701
+ "grad_norm": 0.12245321273803711,
2702
+ "learning_rate": 3.7202618743202935e-05,
2703
+ "loss": 0.5022,
2704
+ "step": 9625
2705
+ },
2706
+ {
2707
+ "epoch": 2.1795595708639186,
2708
+ "grad_norm": 0.1354779750108719,
2709
+ "learning_rate": 3.6729309764962616e-05,
2710
+ "loss": 0.4534,
2711
+ "step": 9650
2712
+ },
2713
+ {
2714
+ "epoch": 2.1852060982495765,
2715
+ "grad_norm": 0.10722421109676361,
2716
+ "learning_rate": 3.625835266261287e-05,
2717
+ "loss": 0.5021,
2718
+ "step": 9675
2719
+ },
2720
+ {
2721
+ "epoch": 2.1908526256352343,
2722
+ "grad_norm": 0.1329207420349121,
2723
+ "learning_rate": 3.578976494240577e-05,
2724
+ "loss": 0.4639,
2725
+ "step": 9700
2726
+ },
2727
+ {
2728
+ "epoch": 2.196499153020892,
2729
+ "grad_norm": 0.11663591116666794,
2730
+ "learning_rate": 3.532356402251954e-05,
2731
+ "loss": 0.4882,
2732
+ "step": 9725
2733
+ },
2734
+ {
2735
+ "epoch": 2.20214568040655,
2736
+ "grad_norm": 0.13668714463710785,
2737
+ "learning_rate": 3.485976723241121e-05,
2738
+ "loss": 0.465,
2739
+ "step": 9750
2740
+ },
2741
+ {
2742
+ "epoch": 2.207792207792208,
2743
+ "grad_norm": 0.11890459805727005,
2744
+ "learning_rate": 3.439839181217227e-05,
2745
+ "loss": 0.505,
2746
+ "step": 9775
2747
+ },
2748
+ {
2749
+ "epoch": 2.2134387351778657,
2750
+ "grad_norm": 0.1332354098558426,
2751
+ "learning_rate": 3.3939454911887844e-05,
2752
+ "loss": 0.4497,
2753
+ "step": 9800
2754
+ },
2755
+ {
2756
+ "epoch": 2.2190852625635236,
2757
+ "grad_norm": 0.11797164380550385,
2758
+ "learning_rate": 3.34829735909994e-05,
2759
+ "loss": 0.536,
2760
+ "step": 9825
2761
+ },
2762
+ {
2763
+ "epoch": 2.2247317899491814,
2764
+ "grad_norm": 0.13317126035690308,
2765
+ "learning_rate": 3.302896481767034e-05,
2766
+ "loss": 0.4645,
2767
+ "step": 9850
2768
+ },
2769
+ {
2770
+ "epoch": 2.2303783173348393,
2771
+ "grad_norm": 0.11745914816856384,
2772
+ "learning_rate": 3.25774454681554e-05,
2773
+ "loss": 0.4991,
2774
+ "step": 9875
2775
+ },
2776
+ {
2777
+ "epoch": 2.2360248447204967,
2778
+ "grad_norm": 0.13392220437526703,
2779
+ "learning_rate": 3.212843232617343e-05,
2780
+ "loss": 0.4385,
2781
+ "step": 9900
2782
+ },
2783
+ {
2784
+ "epoch": 2.2416713721061545,
2785
+ "grad_norm": 0.11925249546766281,
2786
+ "learning_rate": 3.168194208228331e-05,
2787
+ "loss": 0.4801,
2788
+ "step": 9925
2789
+ },
2790
+ {
2791
+ "epoch": 2.2473178994918124,
2792
+ "grad_norm": 0.1346205770969391,
2793
+ "learning_rate": 3.123799133326366e-05,
2794
+ "loss": 0.4562,
2795
+ "step": 9950
2796
+ },
2797
+ {
2798
+ "epoch": 2.2529644268774702,
2799
+ "grad_norm": 0.1318216472864151,
2800
+ "learning_rate": 3.0796596581495963e-05,
2801
+ "loss": 0.499,
2802
+ "step": 9975
2803
+ },
2804
+ {
2805
+ "epoch": 2.258610954263128,
2806
+ "grad_norm": 0.1402980238199234,
2807
+ "learning_rate": 3.0357774234350945e-05,
2808
+ "loss": 0.4386,
2809
+ "step": 10000
2810
+ },
2811
+ {
2812
+ "epoch": 2.264257481648786,
2813
+ "grad_norm": 0.12823522090911865,
2814
+ "learning_rate": 2.9921540603578935e-05,
2815
+ "loss": 0.5133,
2816
+ "step": 10025
2817
+ },
2818
+ {
2819
+ "epoch": 2.269904009034444,
2820
+ "grad_norm": 0.14426416158676147,
2821
+ "learning_rate": 2.948791190470328e-05,
2822
+ "loss": 0.4595,
2823
+ "step": 10050
2824
+ },
2825
+ {
2826
+ "epoch": 2.2755505364201016,
2827
+ "grad_norm": 0.1231706440448761,
2828
+ "learning_rate": 2.905690425641785e-05,
2829
+ "loss": 0.5228,
2830
+ "step": 10075
2831
+ },
2832
+ {
2833
+ "epoch": 2.2811970638057595,
2834
+ "grad_norm": 0.13321641087532043,
2835
+ "learning_rate": 2.8628533679987634e-05,
2836
+ "loss": 0.4573,
2837
+ "step": 10100
2838
+ },
2839
+ {
2840
+ "epoch": 2.2868435911914173,
2841
+ "grad_norm": 0.11738098412752151,
2842
+ "learning_rate": 2.8219793665574002e-05,
2843
+ "loss": 0.4917,
2844
+ "step": 10125
2845
+ },
2846
+ {
2847
+ "epoch": 2.292490118577075,
2848
+ "grad_norm": 0.13331496715545654,
2849
+ "learning_rate": 2.779663784858103e-05,
2850
+ "loss": 0.4596,
2851
+ "step": 10150
2852
+ },
2853
+ {
2854
+ "epoch": 2.298136645962733,
2855
+ "grad_norm": 0.12486054003238678,
2856
+ "learning_rate": 2.73761659496239e-05,
2857
+ "loss": 0.494,
2858
+ "step": 10175
2859
+ },
2860
+ {
2861
+ "epoch": 2.303783173348391,
2862
+ "grad_norm": 0.14081965386867523,
2863
+ "learning_rate": 2.6958393598336407e-05,
2864
+ "loss": 0.467,
2865
+ "step": 10200
2866
+ }
2867
+ ],
2868
+ "logging_steps": 25,
2869
+ "max_steps": 13281,
2870
+ "num_input_tokens_seen": 0,
2871
+ "num_train_epochs": 3,
2872
+ "save_steps": 200,
2873
+ "stateful_callbacks": {
2874
+ "TrainerControl": {
2875
+ "args": {
2876
+ "should_epoch_stop": false,
2877
+ "should_evaluate": false,
2878
+ "should_log": false,
2879
+ "should_save": true,
2880
+ "should_training_stop": false
2881
+ },
2882
+ "attributes": {}
2883
+ }
2884
+ },
2885
+ "total_flos": 6.00010010120362e+18,
2886
+ "train_batch_size": 2,
2887
+ "trial_name": null,
2888
+ "trial_params": null
2889
+ }
checkpoint-10200/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fc98f22665d02224015b9535b80e5c69ad66eca110b77e2e7ae87eceaba5b8a
3
+ size 5051
checkpoint-10400/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Llama-2-13b-chat-hf
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.12.0
checkpoint-10400/adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Llama-2-13b-chat-hf",
5
+ "bias": "lora_only",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.001,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 64,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "v_proj",
24
+ "q_proj"
25
+ ],
26
+ "task_type": "CAUSAL_LM",
27
+ "use_dora": false,
28
+ "use_rslora": false
29
+ }
checkpoint-10400/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47915cf7732f79f3fb2d87592f42470a63deb87a909ee2a230553513b03d0b3f
3
+ size 209736952
checkpoint-10400/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56c1b86b054b7ff53d3e9f428e82b40f8594db5ec717e86ed46a869f416e3512
3
+ size 419529285
checkpoint-10400/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1c6d9b5cb8db96fe7fcc93b7a209d9711bcdacafe964a6b02e01ade1ce69ded
3
+ size 14575
checkpoint-10400/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8b354828f68a250de528f551e1882fe187785af83a3f058c4442b923b29667b
3
+ size 627
checkpoint-10400/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
checkpoint-10400/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-10400/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
checkpoint-10400/tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "bos_token": "<s>",
32
+ "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": false,
36
+ "model_max_length": 1000000000000000019884624838656,
37
+ "pad_token": "</s>",
38
+ "padding_side": "right",
39
+ "sp_model_kwargs": {},
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
+ }
checkpoint-10400/trainer_state.json ADDED
@@ -0,0 +1,2945 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.3489553924336533,
5
+ "eval_steps": 500,
6
+ "global_step": 10400,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.00564652738565782,
13
+ "grad_norm": 0.0635828971862793,
14
+ "learning_rate": 1.2531328320802006e-05,
15
+ "loss": 1.3836,
16
+ "step": 25
17
+ },
18
+ {
19
+ "epoch": 0.01129305477131564,
20
+ "grad_norm": 0.2005225569009781,
21
+ "learning_rate": 2.506265664160401e-05,
22
+ "loss": 1.6497,
23
+ "step": 50
24
+ },
25
+ {
26
+ "epoch": 0.01693958215697346,
27
+ "grad_norm": 0.07235410064458847,
28
+ "learning_rate": 3.759398496240601e-05,
29
+ "loss": 1.1768,
30
+ "step": 75
31
+ },
32
+ {
33
+ "epoch": 0.02258610954263128,
34
+ "grad_norm": 0.17648495733737946,
35
+ "learning_rate": 5.012531328320802e-05,
36
+ "loss": 1.2146,
37
+ "step": 100
38
+ },
39
+ {
40
+ "epoch": 0.028232636928289104,
41
+ "grad_norm": 0.06953724473714828,
42
+ "learning_rate": 6.265664160401002e-05,
43
+ "loss": 0.8725,
44
+ "step": 125
45
+ },
46
+ {
47
+ "epoch": 0.03387916431394692,
48
+ "grad_norm": 0.12059248238801956,
49
+ "learning_rate": 7.518796992481203e-05,
50
+ "loss": 0.7548,
51
+ "step": 150
52
+ },
53
+ {
54
+ "epoch": 0.039525691699604744,
55
+ "grad_norm": 0.0689113661646843,
56
+ "learning_rate": 8.771929824561403e-05,
57
+ "loss": 0.7917,
58
+ "step": 175
59
+ },
60
+ {
61
+ "epoch": 0.04517221908526256,
62
+ "grad_norm": 0.16621273756027222,
63
+ "learning_rate": 0.00010025062656641604,
64
+ "loss": 0.6985,
65
+ "step": 200
66
+ },
67
+ {
68
+ "epoch": 0.050818746470920384,
69
+ "grad_norm": 0.07838872820138931,
70
+ "learning_rate": 0.00011278195488721806,
71
+ "loss": 0.7874,
72
+ "step": 225
73
+ },
74
+ {
75
+ "epoch": 0.05646527385657821,
76
+ "grad_norm": 0.11714337766170502,
77
+ "learning_rate": 0.00012531328320802005,
78
+ "loss": 0.689,
79
+ "step": 250
80
+ },
81
+ {
82
+ "epoch": 0.062111801242236024,
83
+ "grad_norm": 0.07283364981412888,
84
+ "learning_rate": 0.00013784461152882208,
85
+ "loss": 0.7719,
86
+ "step": 275
87
+ },
88
+ {
89
+ "epoch": 0.06775832862789384,
90
+ "grad_norm": 0.1499466449022293,
91
+ "learning_rate": 0.00015037593984962405,
92
+ "loss": 0.655,
93
+ "step": 300
94
+ },
95
+ {
96
+ "epoch": 0.07340485601355166,
97
+ "grad_norm": 0.08195521682500839,
98
+ "learning_rate": 0.00016290726817042608,
99
+ "loss": 0.7508,
100
+ "step": 325
101
+ },
102
+ {
103
+ "epoch": 0.07905138339920949,
104
+ "grad_norm": 0.1490202099084854,
105
+ "learning_rate": 0.00017543859649122806,
106
+ "loss": 0.6372,
107
+ "step": 350
108
+ },
109
+ {
110
+ "epoch": 0.08469791078486731,
111
+ "grad_norm": 0.1617508977651596,
112
+ "learning_rate": 0.00018796992481203009,
113
+ "loss": 0.7396,
114
+ "step": 375
115
+ },
116
+ {
117
+ "epoch": 0.09034443817052512,
118
+ "grad_norm": 0.180181622505188,
119
+ "learning_rate": 0.00019999999702625888,
120
+ "loss": 0.6318,
121
+ "step": 400
122
+ },
123
+ {
124
+ "epoch": 0.09599096555618294,
125
+ "grad_norm": 0.08272858709096909,
126
+ "learning_rate": 0.00019999798975772924,
127
+ "loss": 0.724,
128
+ "step": 425
129
+ },
130
+ {
131
+ "epoch": 0.10163749294184077,
132
+ "grad_norm": 0.120403952896595,
133
+ "learning_rate": 0.00019999226539902187,
134
+ "loss": 0.6271,
135
+ "step": 450
136
+ },
137
+ {
138
+ "epoch": 0.10728402032749859,
139
+ "grad_norm": 0.07971920073032379,
140
+ "learning_rate": 0.00019998282416292055,
141
+ "loss": 0.7256,
142
+ "step": 475
143
+ },
144
+ {
145
+ "epoch": 0.11293054771315642,
146
+ "grad_norm": 0.1328658014535904,
147
+ "learning_rate": 0.00019996966640037166,
148
+ "loss": 0.6231,
149
+ "step": 500
150
+ },
151
+ {
152
+ "epoch": 0.11857707509881422,
153
+ "grad_norm": 0.07475866377353668,
154
+ "learning_rate": 0.00019995279260047092,
155
+ "loss": 0.7251,
156
+ "step": 525
157
+ },
158
+ {
159
+ "epoch": 0.12422360248447205,
160
+ "grad_norm": 0.1371573656797409,
161
+ "learning_rate": 0.00019993220339044524,
162
+ "loss": 0.5907,
163
+ "step": 550
164
+ },
165
+ {
166
+ "epoch": 0.12987012987012986,
167
+ "grad_norm": 0.07268711924552917,
168
+ "learning_rate": 0.00019990789953562961,
169
+ "loss": 0.7304,
170
+ "step": 575
171
+ },
172
+ {
173
+ "epoch": 0.13551665725578768,
174
+ "grad_norm": 0.14224526286125183,
175
+ "learning_rate": 0.0001998798819394383,
176
+ "loss": 0.5931,
177
+ "step": 600
178
+ },
179
+ {
180
+ "epoch": 0.1411631846414455,
181
+ "grad_norm": 0.0803467407822609,
182
+ "learning_rate": 0.00019984815164333163,
183
+ "loss": 0.7076,
184
+ "step": 625
185
+ },
186
+ {
187
+ "epoch": 0.14680971202710333,
188
+ "grad_norm": 0.12445727735757828,
189
+ "learning_rate": 0.00019981270982677698,
190
+ "loss": 0.5566,
191
+ "step": 650
192
+ },
193
+ {
194
+ "epoch": 0.15245623941276115,
195
+ "grad_norm": 0.07665792107582092,
196
+ "learning_rate": 0.00019977355780720514,
197
+ "loss": 0.6985,
198
+ "step": 675
199
+ },
200
+ {
201
+ "epoch": 0.15810276679841898,
202
+ "grad_norm": 0.13053999841213226,
203
+ "learning_rate": 0.00019973069703996125,
204
+ "loss": 0.5901,
205
+ "step": 700
206
+ },
207
+ {
208
+ "epoch": 0.1637492941840768,
209
+ "grad_norm": 0.07512692362070084,
210
+ "learning_rate": 0.00019968412911825067,
211
+ "loss": 0.7184,
212
+ "step": 725
213
+ },
214
+ {
215
+ "epoch": 0.16939582156973462,
216
+ "grad_norm": 0.12033283710479736,
217
+ "learning_rate": 0.00019963385577307987,
218
+ "loss": 0.6013,
219
+ "step": 750
220
+ },
221
+ {
222
+ "epoch": 0.17504234895539245,
223
+ "grad_norm": 0.0809774249792099,
224
+ "learning_rate": 0.000199579878873192,
225
+ "loss": 0.7054,
226
+ "step": 775
227
+ },
228
+ {
229
+ "epoch": 0.18068887634105024,
230
+ "grad_norm": 0.12490582466125488,
231
+ "learning_rate": 0.0001995222004249974,
232
+ "loss": 0.5714,
233
+ "step": 800
234
+ },
235
+ {
236
+ "epoch": 0.18633540372670807,
237
+ "grad_norm": 0.08289226144552231,
238
+ "learning_rate": 0.00019946082257249912,
239
+ "loss": 0.7304,
240
+ "step": 825
241
+ },
242
+ {
243
+ "epoch": 0.1919819311123659,
244
+ "grad_norm": 0.14385385811328888,
245
+ "learning_rate": 0.00019939574759721316,
246
+ "loss": 0.5639,
247
+ "step": 850
248
+ },
249
+ {
250
+ "epoch": 0.1976284584980237,
251
+ "grad_norm": 0.07623141258955002,
252
+ "learning_rate": 0.00019932697791808366,
253
+ "loss": 0.7126,
254
+ "step": 875
255
+ },
256
+ {
257
+ "epoch": 0.20327498588368154,
258
+ "grad_norm": 0.11150185018777847,
259
+ "learning_rate": 0.000199254516091393,
260
+ "loss": 0.5903,
261
+ "step": 900
262
+ },
263
+ {
264
+ "epoch": 0.20892151326933936,
265
+ "grad_norm": 0.07193930447101593,
266
+ "learning_rate": 0.00019917836481066675,
267
+ "loss": 0.6952,
268
+ "step": 925
269
+ },
270
+ {
271
+ "epoch": 0.21456804065499718,
272
+ "grad_norm": 0.11242598295211792,
273
+ "learning_rate": 0.00019909852690657359,
274
+ "loss": 0.5853,
275
+ "step": 950
276
+ },
277
+ {
278
+ "epoch": 0.220214568040655,
279
+ "grad_norm": 0.07508910447359085,
280
+ "learning_rate": 0.0001990150053468201,
281
+ "loss": 0.6969,
282
+ "step": 975
283
+ },
284
+ {
285
+ "epoch": 0.22586109542631283,
286
+ "grad_norm": 0.11998436599969864,
287
+ "learning_rate": 0.00019892780323604035,
288
+ "loss": 0.5791,
289
+ "step": 1000
290
+ },
291
+ {
292
+ "epoch": 0.23150762281197063,
293
+ "grad_norm": 0.07748444378376007,
294
+ "learning_rate": 0.0001988369238156806,
295
+ "loss": 0.7038,
296
+ "step": 1025
297
+ },
298
+ {
299
+ "epoch": 0.23715415019762845,
300
+ "grad_norm": 0.19617140293121338,
301
+ "learning_rate": 0.0001987423704638788,
302
+ "loss": 0.5792,
303
+ "step": 1050
304
+ },
305
+ {
306
+ "epoch": 0.24280067758328627,
307
+ "grad_norm": 0.08167731016874313,
308
+ "learning_rate": 0.00019864414669533892,
309
+ "loss": 0.6989,
310
+ "step": 1075
311
+ },
312
+ {
313
+ "epoch": 0.2484472049689441,
314
+ "grad_norm": 0.11911099404096603,
315
+ "learning_rate": 0.00019854225616120044,
316
+ "loss": 0.5985,
317
+ "step": 1100
318
+ },
319
+ {
320
+ "epoch": 0.2540937323546019,
321
+ "grad_norm": 0.0718325674533844,
322
+ "learning_rate": 0.0001984367026489025,
323
+ "loss": 0.6853,
324
+ "step": 1125
325
+ },
326
+ {
327
+ "epoch": 0.2597402597402597,
328
+ "grad_norm": 0.12495870143175125,
329
+ "learning_rate": 0.0001983274900820432,
330
+ "loss": 0.5738,
331
+ "step": 1150
332
+ },
333
+ {
334
+ "epoch": 0.26538678712591757,
335
+ "grad_norm": 0.08245467394590378,
336
+ "learning_rate": 0.0001982146225202338,
337
+ "loss": 0.6766,
338
+ "step": 1175
339
+ },
340
+ {
341
+ "epoch": 0.27103331451157536,
342
+ "grad_norm": 0.11854438483715057,
343
+ "learning_rate": 0.00019809810415894767,
344
+ "loss": 0.5828,
345
+ "step": 1200
346
+ },
347
+ {
348
+ "epoch": 0.2766798418972332,
349
+ "grad_norm": 0.07968372851610184,
350
+ "learning_rate": 0.0001979779393293644,
351
+ "loss": 0.6901,
352
+ "step": 1225
353
+ },
354
+ {
355
+ "epoch": 0.282326369282891,
356
+ "grad_norm": 0.13610929250717163,
357
+ "learning_rate": 0.00019785413249820893,
358
+ "loss": 0.554,
359
+ "step": 1250
360
+ },
361
+ {
362
+ "epoch": 0.28797289666854886,
363
+ "grad_norm": 0.08099998533725739,
364
+ "learning_rate": 0.00019772668826758527,
365
+ "loss": 0.6615,
366
+ "step": 1275
367
+ },
368
+ {
369
+ "epoch": 0.29361942405420666,
370
+ "grad_norm": 0.10878365486860275,
371
+ "learning_rate": 0.0001975956113748057,
372
+ "loss": 0.547,
373
+ "step": 1300
374
+ },
375
+ {
376
+ "epoch": 0.2992659514398645,
377
+ "grad_norm": 0.0784253254532814,
378
+ "learning_rate": 0.0001974609066922144,
379
+ "loss": 0.6589,
380
+ "step": 1325
381
+ },
382
+ {
383
+ "epoch": 0.3049124788255223,
384
+ "grad_norm": 0.10678227245807648,
385
+ "learning_rate": 0.00019732257922700655,
386
+ "loss": 0.5443,
387
+ "step": 1350
388
+ },
389
+ {
390
+ "epoch": 0.3105590062111801,
391
+ "grad_norm": 0.07781955599784851,
392
+ "learning_rate": 0.00019718063412104222,
393
+ "loss": 0.6798,
394
+ "step": 1375
395
+ },
396
+ {
397
+ "epoch": 0.31620553359683795,
398
+ "grad_norm": 0.12910470366477966,
399
+ "learning_rate": 0.00019703507665065498,
400
+ "loss": 0.54,
401
+ "step": 1400
402
+ },
403
+ {
404
+ "epoch": 0.32185206098249575,
405
+ "grad_norm": 0.08442296832799911,
406
+ "learning_rate": 0.00019688591222645607,
407
+ "loss": 0.6998,
408
+ "step": 1425
409
+ },
410
+ {
411
+ "epoch": 0.3274985883681536,
412
+ "grad_norm": 0.10945732891559601,
413
+ "learning_rate": 0.00019673314639313315,
414
+ "loss": 0.5576,
415
+ "step": 1450
416
+ },
417
+ {
418
+ "epoch": 0.3331451157538114,
419
+ "grad_norm": 0.07373673468828201,
420
+ "learning_rate": 0.00019657678482924406,
421
+ "loss": 0.709,
422
+ "step": 1475
423
+ },
424
+ {
425
+ "epoch": 0.33879164313946925,
426
+ "grad_norm": 0.10061786323785782,
427
+ "learning_rate": 0.00019641683334700608,
428
+ "loss": 0.5329,
429
+ "step": 1500
430
+ },
431
+ {
432
+ "epoch": 0.34443817052512704,
433
+ "grad_norm": 0.08854890614748001,
434
+ "learning_rate": 0.00019625329789207949,
435
+ "loss": 0.6753,
436
+ "step": 1525
437
+ },
438
+ {
439
+ "epoch": 0.3500846979107849,
440
+ "grad_norm": 0.11869047582149506,
441
+ "learning_rate": 0.00019608618454334685,
442
+ "loss": 0.54,
443
+ "step": 1550
444
+ },
445
+ {
446
+ "epoch": 0.3557312252964427,
447
+ "grad_norm": 0.0819987803697586,
448
+ "learning_rate": 0.00019591549951268692,
449
+ "loss": 0.683,
450
+ "step": 1575
451
+ },
452
+ {
453
+ "epoch": 0.3613777526821005,
454
+ "grad_norm": 0.10941476374864578,
455
+ "learning_rate": 0.00019574124914474374,
456
+ "loss": 0.5713,
457
+ "step": 1600
458
+ },
459
+ {
460
+ "epoch": 0.36702428006775834,
461
+ "grad_norm": 0.0801759734749794,
462
+ "learning_rate": 0.00019556343991669083,
463
+ "loss": 0.6494,
464
+ "step": 1625
465
+ },
466
+ {
467
+ "epoch": 0.37267080745341613,
468
+ "grad_norm": 0.11291850358247757,
469
+ "learning_rate": 0.0001953820784379904,
470
+ "loss": 0.5428,
471
+ "step": 1650
472
+ },
473
+ {
474
+ "epoch": 0.378317334839074,
475
+ "grad_norm": 0.0784342810511589,
476
+ "learning_rate": 0.00019519717145014765,
477
+ "loss": 0.6789,
478
+ "step": 1675
479
+ },
480
+ {
481
+ "epoch": 0.3839638622247318,
482
+ "grad_norm": 0.11995444446802139,
483
+ "learning_rate": 0.00019500872582646034,
484
+ "loss": 0.5409,
485
+ "step": 1700
486
+ },
487
+ {
488
+ "epoch": 0.38961038961038963,
489
+ "grad_norm": 0.10059577226638794,
490
+ "learning_rate": 0.00019481674857176293,
491
+ "loss": 0.6887,
492
+ "step": 1725
493
+ },
494
+ {
495
+ "epoch": 0.3952569169960474,
496
+ "grad_norm": 0.11123017966747284,
497
+ "learning_rate": 0.0001946212468221666,
498
+ "loss": 0.5482,
499
+ "step": 1750
500
+ },
501
+ {
502
+ "epoch": 0.4009034443817053,
503
+ "grad_norm": 0.0788169875741005,
504
+ "learning_rate": 0.00019442222784479382,
505
+ "loss": 0.6577,
506
+ "step": 1775
507
+ },
508
+ {
509
+ "epoch": 0.40654997176736307,
510
+ "grad_norm": 0.09987206757068634,
511
+ "learning_rate": 0.0001942196990375081,
512
+ "loss": 0.5353,
513
+ "step": 1800
514
+ },
515
+ {
516
+ "epoch": 0.41219649915302087,
517
+ "grad_norm": 0.081305131316185,
518
+ "learning_rate": 0.00019401366792863914,
519
+ "loss": 0.6757,
520
+ "step": 1825
521
+ },
522
+ {
523
+ "epoch": 0.4178430265386787,
524
+ "grad_norm": 0.11595868319272995,
525
+ "learning_rate": 0.00019380414217670309,
526
+ "loss": 0.5306,
527
+ "step": 1850
528
+ },
529
+ {
530
+ "epoch": 0.4234895539243365,
531
+ "grad_norm": 0.08652087301015854,
532
+ "learning_rate": 0.00019359112957011764,
533
+ "loss": 0.6634,
534
+ "step": 1875
535
+ },
536
+ {
537
+ "epoch": 0.42913608130999437,
538
+ "grad_norm": 0.1181817501783371,
539
+ "learning_rate": 0.00019337463802691264,
540
+ "loss": 0.5465,
541
+ "step": 1900
542
+ },
543
+ {
544
+ "epoch": 0.43478260869565216,
545
+ "grad_norm": 0.08145532757043839,
546
+ "learning_rate": 0.00019315467559443574,
547
+ "loss": 0.6639,
548
+ "step": 1925
549
+ },
550
+ {
551
+ "epoch": 0.44042913608131,
552
+ "grad_norm": 0.10263626277446747,
553
+ "learning_rate": 0.0001929312504490533,
554
+ "loss": 0.5418,
555
+ "step": 1950
556
+ },
557
+ {
558
+ "epoch": 0.4460756634669678,
559
+ "grad_norm": 0.07672405242919922,
560
+ "learning_rate": 0.00019270437089584635,
561
+ "loss": 0.6547,
562
+ "step": 1975
563
+ },
564
+ {
565
+ "epoch": 0.45172219085262566,
566
+ "grad_norm": 0.0984482392668724,
567
+ "learning_rate": 0.00019247404536830204,
568
+ "loss": 0.5321,
569
+ "step": 2000
570
+ },
571
+ {
572
+ "epoch": 0.45736871823828346,
573
+ "grad_norm": 0.08558057248592377,
574
+ "learning_rate": 0.00019224028242800006,
575
+ "loss": 0.6657,
576
+ "step": 2025
577
+ },
578
+ {
579
+ "epoch": 0.46301524562394125,
580
+ "grad_norm": 0.10624836385250092,
581
+ "learning_rate": 0.00019200309076429438,
582
+ "loss": 0.5542,
583
+ "step": 2050
584
+ },
585
+ {
586
+ "epoch": 0.4686617730095991,
587
+ "grad_norm": 0.08049538731575012,
588
+ "learning_rate": 0.00019176247919399023,
589
+ "loss": 0.6389,
590
+ "step": 2075
591
+ },
592
+ {
593
+ "epoch": 0.4743083003952569,
594
+ "grad_norm": 0.11163744330406189,
595
+ "learning_rate": 0.00019151845666101646,
596
+ "loss": 0.5382,
597
+ "step": 2100
598
+ },
599
+ {
600
+ "epoch": 0.47995482778091475,
601
+ "grad_norm": 0.07694784551858902,
602
+ "learning_rate": 0.00019127103223609307,
603
+ "loss": 0.6345,
604
+ "step": 2125
605
+ },
606
+ {
607
+ "epoch": 0.48560135516657255,
608
+ "grad_norm": 0.11501342058181763,
609
+ "learning_rate": 0.0001910202151163939,
610
+ "loss": 0.5303,
611
+ "step": 2150
612
+ },
613
+ {
614
+ "epoch": 0.4912478825522304,
615
+ "grad_norm": 0.08532056957483292,
616
+ "learning_rate": 0.00019076601462520492,
617
+ "loss": 0.666,
618
+ "step": 2175
619
+ },
620
+ {
621
+ "epoch": 0.4968944099378882,
622
+ "grad_norm": 0.09018545597791672,
623
+ "learning_rate": 0.00019050844021157752,
624
+ "loss": 0.5363,
625
+ "step": 2200
626
+ },
627
+ {
628
+ "epoch": 0.502540937323546,
629
+ "grad_norm": 0.08757849037647247,
630
+ "learning_rate": 0.00019024750144997746,
631
+ "loss": 0.6684,
632
+ "step": 2225
633
+ },
634
+ {
635
+ "epoch": 0.5081874647092038,
636
+ "grad_norm": 0.09418553113937378,
637
+ "learning_rate": 0.00018998320803992872,
638
+ "loss": 0.565,
639
+ "step": 2250
640
+ },
641
+ {
642
+ "epoch": 0.5138339920948617,
643
+ "grad_norm": 0.10246949642896652,
644
+ "learning_rate": 0.00018971556980565329,
645
+ "loss": 0.6524,
646
+ "step": 2275
647
+ },
648
+ {
649
+ "epoch": 0.5194805194805194,
650
+ "grad_norm": 0.12446881830692291,
651
+ "learning_rate": 0.00018944459669570555,
652
+ "loss": 0.5447,
653
+ "step": 2300
654
+ },
655
+ {
656
+ "epoch": 0.5251270468661773,
657
+ "grad_norm": 0.08439560234546661,
658
+ "learning_rate": 0.00018917029878260294,
659
+ "loss": 0.673,
660
+ "step": 2325
661
+ },
662
+ {
663
+ "epoch": 0.5307735742518351,
664
+ "grad_norm": 0.1195409968495369,
665
+ "learning_rate": 0.00018889268626245116,
666
+ "loss": 0.51,
667
+ "step": 2350
668
+ },
669
+ {
670
+ "epoch": 0.536420101637493,
671
+ "grad_norm": 0.09150119870901108,
672
+ "learning_rate": 0.0001886117694545654,
673
+ "loss": 0.6631,
674
+ "step": 2375
675
+ },
676
+ {
677
+ "epoch": 0.5420666290231507,
678
+ "grad_norm": 0.10301247239112854,
679
+ "learning_rate": 0.0001883275588010866,
680
+ "loss": 0.5257,
681
+ "step": 2400
682
+ },
683
+ {
684
+ "epoch": 0.5477131564088086,
685
+ "grad_norm": 0.08086048811674118,
686
+ "learning_rate": 0.00018804006486659346,
687
+ "loss": 0.6305,
688
+ "step": 2425
689
+ },
690
+ {
691
+ "epoch": 0.5533596837944664,
692
+ "grad_norm": 0.10540500283241272,
693
+ "learning_rate": 0.0001877492983377096,
694
+ "loss": 0.5607,
695
+ "step": 2450
696
+ },
697
+ {
698
+ "epoch": 0.5590062111801242,
699
+ "grad_norm": 0.0777876153588295,
700
+ "learning_rate": 0.00018745527002270634,
701
+ "loss": 0.6413,
702
+ "step": 2475
703
+ },
704
+ {
705
+ "epoch": 0.564652738565782,
706
+ "grad_norm": 0.10727331042289734,
707
+ "learning_rate": 0.00018715799085110112,
708
+ "loss": 0.5206,
709
+ "step": 2500
710
+ },
711
+ {
712
+ "epoch": 0.5702992659514399,
713
+ "grad_norm": 0.09144891798496246,
714
+ "learning_rate": 0.0001868574718732508,
715
+ "loss": 0.6655,
716
+ "step": 2525
717
+ },
718
+ {
719
+ "epoch": 0.5759457933370977,
720
+ "grad_norm": 0.08949702978134155,
721
+ "learning_rate": 0.00018655372425994152,
722
+ "loss": 0.5358,
723
+ "step": 2550
724
+ },
725
+ {
726
+ "epoch": 0.5815923207227555,
727
+ "grad_norm": 0.08744482696056366,
728
+ "learning_rate": 0.0001862467593019728,
729
+ "loss": 0.6396,
730
+ "step": 2575
731
+ },
732
+ {
733
+ "epoch": 0.5872388481084133,
734
+ "grad_norm": 0.10931294411420822,
735
+ "learning_rate": 0.0001859365884097384,
736
+ "loss": 0.5132,
737
+ "step": 2600
738
+ },
739
+ {
740
+ "epoch": 0.5928853754940712,
741
+ "grad_norm": 0.07518015056848526,
742
+ "learning_rate": 0.00018562322311280186,
743
+ "loss": 0.6378,
744
+ "step": 2625
745
+ },
746
+ {
747
+ "epoch": 0.598531902879729,
748
+ "grad_norm": 0.09787683933973312,
749
+ "learning_rate": 0.000185306675059468,
750
+ "loss": 0.5272,
751
+ "step": 2650
752
+ },
753
+ {
754
+ "epoch": 0.6041784302653868,
755
+ "grad_norm": 0.08679146319627762,
756
+ "learning_rate": 0.00018498695601634993,
757
+ "loss": 0.6486,
758
+ "step": 2675
759
+ },
760
+ {
761
+ "epoch": 0.6098249576510446,
762
+ "grad_norm": 0.10611116141080856,
763
+ "learning_rate": 0.00018466407786793174,
764
+ "loss": 0.5237,
765
+ "step": 2700
766
+ },
767
+ {
768
+ "epoch": 0.6154714850367025,
769
+ "grad_norm": 0.0772860199213028,
770
+ "learning_rate": 0.00018433805261612663,
771
+ "loss": 0.6526,
772
+ "step": 2725
773
+ },
774
+ {
775
+ "epoch": 0.6211180124223602,
776
+ "grad_norm": 0.1005689725279808,
777
+ "learning_rate": 0.00018400889237983086,
778
+ "loss": 0.5297,
779
+ "step": 2750
780
+ },
781
+ {
782
+ "epoch": 0.626764539808018,
783
+ "grad_norm": 0.08322805911302567,
784
+ "learning_rate": 0.00018367660939447316,
785
+ "loss": 0.6448,
786
+ "step": 2775
787
+ },
788
+ {
789
+ "epoch": 0.6324110671936759,
790
+ "grad_norm": 0.10492440313100815,
791
+ "learning_rate": 0.00018334121601156002,
792
+ "loss": 0.493,
793
+ "step": 2800
794
+ },
795
+ {
796
+ "epoch": 0.6380575945793338,
797
+ "grad_norm": 0.08439356088638306,
798
+ "learning_rate": 0.00018300272469821662,
799
+ "loss": 0.6421,
800
+ "step": 2825
801
+ },
802
+ {
803
+ "epoch": 0.6437041219649915,
804
+ "grad_norm": 0.11175478994846344,
805
+ "learning_rate": 0.00018266114803672318,
806
+ "loss": 0.5293,
807
+ "step": 2850
808
+ },
809
+ {
810
+ "epoch": 0.6493506493506493,
811
+ "grad_norm": 0.07700271904468536,
812
+ "learning_rate": 0.00018231649872404754,
813
+ "loss": 0.6506,
814
+ "step": 2875
815
+ },
816
+ {
817
+ "epoch": 0.6549971767363072,
818
+ "grad_norm": 0.08704936504364014,
819
+ "learning_rate": 0.00018196878957137295,
820
+ "loss": 0.5091,
821
+ "step": 2900
822
+ },
823
+ {
824
+ "epoch": 0.6606437041219649,
825
+ "grad_norm": 0.0863596498966217,
826
+ "learning_rate": 0.00018161803350362198,
827
+ "loss": 0.6531,
828
+ "step": 2925
829
+ },
830
+ {
831
+ "epoch": 0.6662902315076228,
832
+ "grad_norm": 0.11374282091856003,
833
+ "learning_rate": 0.00018126424355897612,
834
+ "loss": 0.5389,
835
+ "step": 2950
836
+ },
837
+ {
838
+ "epoch": 0.6719367588932806,
839
+ "grad_norm": 0.08936896920204163,
840
+ "learning_rate": 0.000180907432888391,
841
+ "loss": 0.6267,
842
+ "step": 2975
843
+ },
844
+ {
845
+ "epoch": 0.6775832862789385,
846
+ "grad_norm": 0.08924362808465958,
847
+ "learning_rate": 0.0001805476147551076,
848
+ "loss": 0.4882,
849
+ "step": 3000
850
+ },
851
+ {
852
+ "epoch": 0.6832298136645962,
853
+ "grad_norm": 0.08161070942878723,
854
+ "learning_rate": 0.0001801848025341593,
855
+ "loss": 0.6502,
856
+ "step": 3025
857
+ },
858
+ {
859
+ "epoch": 0.6888763410502541,
860
+ "grad_norm": 0.11261451989412308,
861
+ "learning_rate": 0.00017981900971187465,
862
+ "loss": 0.5241,
863
+ "step": 3050
864
+ },
865
+ {
866
+ "epoch": 0.6945228684359119,
867
+ "grad_norm": 0.0859522670507431,
868
+ "learning_rate": 0.00017945024988537603,
869
+ "loss": 0.6413,
870
+ "step": 3075
871
+ },
872
+ {
873
+ "epoch": 0.7001693958215698,
874
+ "grad_norm": 0.11650535464286804,
875
+ "learning_rate": 0.0001790785367620743,
876
+ "loss": 0.519,
877
+ "step": 3100
878
+ },
879
+ {
880
+ "epoch": 0.7058159232072275,
881
+ "grad_norm": 0.09202492237091064,
882
+ "learning_rate": 0.00017870388415915922,
883
+ "loss": 0.6212,
884
+ "step": 3125
885
+ },
886
+ {
887
+ "epoch": 0.7114624505928854,
888
+ "grad_norm": 0.1048663780093193,
889
+ "learning_rate": 0.00017832630600308585,
890
+ "loss": 0.5266,
891
+ "step": 3150
892
+ },
893
+ {
894
+ "epoch": 0.7171089779785432,
895
+ "grad_norm": 0.08784987032413483,
896
+ "learning_rate": 0.00017794581632905683,
897
+ "loss": 0.6214,
898
+ "step": 3175
899
+ },
900
+ {
901
+ "epoch": 0.722755505364201,
902
+ "grad_norm": 0.10895237326622009,
903
+ "learning_rate": 0.00017756242928050085,
904
+ "loss": 0.5059,
905
+ "step": 3200
906
+ },
907
+ {
908
+ "epoch": 0.7284020327498588,
909
+ "grad_norm": 0.09365130960941315,
910
+ "learning_rate": 0.0001771761591085467,
911
+ "loss": 0.6529,
912
+ "step": 3225
913
+ },
914
+ {
915
+ "epoch": 0.7340485601355167,
916
+ "grad_norm": 0.1045169085264206,
917
+ "learning_rate": 0.0001767870201714936,
918
+ "loss": 0.5229,
919
+ "step": 3250
920
+ },
921
+ {
922
+ "epoch": 0.7396950875211745,
923
+ "grad_norm": 0.08621610701084137,
924
+ "learning_rate": 0.0001763950269342776,
925
+ "loss": 0.6489,
926
+ "step": 3275
927
+ },
928
+ {
929
+ "epoch": 0.7453416149068323,
930
+ "grad_norm": 0.1039639338850975,
931
+ "learning_rate": 0.00017600019396793367,
932
+ "loss": 0.5116,
933
+ "step": 3300
934
+ },
935
+ {
936
+ "epoch": 0.7509881422924901,
937
+ "grad_norm": 0.09034851938486099,
938
+ "learning_rate": 0.00017560253594905425,
939
+ "loss": 0.6587,
940
+ "step": 3325
941
+ },
942
+ {
943
+ "epoch": 0.756634669678148,
944
+ "grad_norm": 0.10783170908689499,
945
+ "learning_rate": 0.00017520206765924372,
946
+ "loss": 0.5019,
947
+ "step": 3350
948
+ },
949
+ {
950
+ "epoch": 0.7622811970638057,
951
+ "grad_norm": 0.08911153674125671,
952
+ "learning_rate": 0.00017479880398456871,
953
+ "loss": 0.6242,
954
+ "step": 3375
955
+ },
956
+ {
957
+ "epoch": 0.7679277244494636,
958
+ "grad_norm": 0.10053360462188721,
959
+ "learning_rate": 0.00017439275991500507,
960
+ "loss": 0.4996,
961
+ "step": 3400
962
+ },
963
+ {
964
+ "epoch": 0.7735742518351214,
965
+ "grad_norm": 0.09367632865905762,
966
+ "learning_rate": 0.0001739839505438804,
967
+ "loss": 0.6347,
968
+ "step": 3425
969
+ },
970
+ {
971
+ "epoch": 0.7792207792207793,
972
+ "grad_norm": 0.09187789261341095,
973
+ "learning_rate": 0.00017357239106731317,
974
+ "loss": 0.4857,
975
+ "step": 3450
976
+ },
977
+ {
978
+ "epoch": 0.784867306606437,
979
+ "grad_norm": 0.08425033092498779,
980
+ "learning_rate": 0.00017315809678364777,
981
+ "loss": 0.6305,
982
+ "step": 3475
983
+ },
984
+ {
985
+ "epoch": 0.7905138339920948,
986
+ "grad_norm": 0.10775783658027649,
987
+ "learning_rate": 0.00017274108309288594,
988
+ "loss": 0.5013,
989
+ "step": 3500
990
+ },
991
+ {
992
+ "epoch": 0.7961603613777527,
993
+ "grad_norm": 0.082928866147995,
994
+ "learning_rate": 0.00017232136549611416,
995
+ "loss": 0.6217,
996
+ "step": 3525
997
+ },
998
+ {
999
+ "epoch": 0.8018068887634106,
1000
+ "grad_norm": 0.09590538591146469,
1001
+ "learning_rate": 0.00017189895959492772,
1002
+ "loss": 0.4871,
1003
+ "step": 3550
1004
+ },
1005
+ {
1006
+ "epoch": 0.8074534161490683,
1007
+ "grad_norm": 0.08597232401371002,
1008
+ "learning_rate": 0.00017147388109085048,
1009
+ "loss": 0.6298,
1010
+ "step": 3575
1011
+ },
1012
+ {
1013
+ "epoch": 0.8130999435347261,
1014
+ "grad_norm": 0.10229629278182983,
1015
+ "learning_rate": 0.00017104614578475135,
1016
+ "loss": 0.5191,
1017
+ "step": 3600
1018
+ },
1019
+ {
1020
+ "epoch": 0.818746470920384,
1021
+ "grad_norm": 0.09689701348543167,
1022
+ "learning_rate": 0.0001706157695762571,
1023
+ "loss": 0.6087,
1024
+ "step": 3625
1025
+ },
1026
+ {
1027
+ "epoch": 0.8243929983060417,
1028
+ "grad_norm": 0.1155649945139885,
1029
+ "learning_rate": 0.000170182768463161,
1030
+ "loss": 0.5237,
1031
+ "step": 3650
1032
+ },
1033
+ {
1034
+ "epoch": 0.8300395256916996,
1035
+ "grad_norm": 0.08635739237070084,
1036
+ "learning_rate": 0.00016974715854082848,
1037
+ "loss": 0.6337,
1038
+ "step": 3675
1039
+ },
1040
+ {
1041
+ "epoch": 0.8356860530773574,
1042
+ "grad_norm": 0.08977790176868439,
1043
+ "learning_rate": 0.00016930895600159867,
1044
+ "loss": 0.4942,
1045
+ "step": 3700
1046
+ },
1047
+ {
1048
+ "epoch": 0.8413325804630153,
1049
+ "grad_norm": 0.08372893184423447,
1050
+ "learning_rate": 0.00016886817713418264,
1051
+ "loss": 0.6224,
1052
+ "step": 3725
1053
+ },
1054
+ {
1055
+ "epoch": 0.846979107848673,
1056
+ "grad_norm": 0.09409157931804657,
1057
+ "learning_rate": 0.00016842483832305765,
1058
+ "loss": 0.4948,
1059
+ "step": 3750
1060
+ },
1061
+ {
1062
+ "epoch": 0.8526256352343309,
1063
+ "grad_norm": 0.0824190303683281,
1064
+ "learning_rate": 0.00016797895604785842,
1065
+ "loss": 0.6188,
1066
+ "step": 3775
1067
+ },
1068
+ {
1069
+ "epoch": 0.8582721626199887,
1070
+ "grad_norm": 0.11509312689304352,
1071
+ "learning_rate": 0.0001675305468827644,
1072
+ "loss": 0.513,
1073
+ "step": 3800
1074
+ },
1075
+ {
1076
+ "epoch": 0.8639186900056465,
1077
+ "grad_norm": 0.08958346396684647,
1078
+ "learning_rate": 0.0001670796274958837,
1079
+ "loss": 0.6206,
1080
+ "step": 3825
1081
+ },
1082
+ {
1083
+ "epoch": 0.8695652173913043,
1084
+ "grad_norm": 0.0959952101111412,
1085
+ "learning_rate": 0.00016662621464863338,
1086
+ "loss": 0.4885,
1087
+ "step": 3850
1088
+ },
1089
+ {
1090
+ "epoch": 0.8752117447769622,
1091
+ "grad_norm": 0.11436719447374344,
1092
+ "learning_rate": 0.00016617032519511686,
1093
+ "loss": 0.635,
1094
+ "step": 3875
1095
+ },
1096
+ {
1097
+ "epoch": 0.88085827216262,
1098
+ "grad_norm": 0.11012863367795944,
1099
+ "learning_rate": 0.00016571197608149674,
1100
+ "loss": 0.4982,
1101
+ "step": 3900
1102
+ },
1103
+ {
1104
+ "epoch": 0.8865047995482778,
1105
+ "grad_norm": 0.08522720634937286,
1106
+ "learning_rate": 0.00016525118434536546,
1107
+ "loss": 0.6105,
1108
+ "step": 3925
1109
+ },
1110
+ {
1111
+ "epoch": 0.8921513269339356,
1112
+ "grad_norm": 0.11074435710906982,
1113
+ "learning_rate": 0.00016478796711511171,
1114
+ "loss": 0.5007,
1115
+ "step": 3950
1116
+ },
1117
+ {
1118
+ "epoch": 0.8977978543195935,
1119
+ "grad_norm": 0.08319137990474701,
1120
+ "learning_rate": 0.00016432234160928378,
1121
+ "loss": 0.6008,
1122
+ "step": 3975
1123
+ },
1124
+ {
1125
+ "epoch": 0.9034443817052513,
1126
+ "grad_norm": 0.11340347677469254,
1127
+ "learning_rate": 0.00016385432513594953,
1128
+ "loss": 0.502,
1129
+ "step": 4000
1130
+ },
1131
+ {
1132
+ "epoch": 0.9090909090909091,
1133
+ "grad_norm": 0.08557943999767303,
1134
+ "learning_rate": 0.0001633839350920531,
1135
+ "loss": 0.598,
1136
+ "step": 4025
1137
+ },
1138
+ {
1139
+ "epoch": 0.9147374364765669,
1140
+ "grad_norm": 0.09813399612903595,
1141
+ "learning_rate": 0.00016291118896276803,
1142
+ "loss": 0.5139,
1143
+ "step": 4050
1144
+ },
1145
+ {
1146
+ "epoch": 0.9203839638622248,
1147
+ "grad_norm": 0.07974950224161148,
1148
+ "learning_rate": 0.00016243610432084755,
1149
+ "loss": 0.6227,
1150
+ "step": 4075
1151
+ },
1152
+ {
1153
+ "epoch": 0.9260304912478825,
1154
+ "grad_norm": 0.09820155799388885,
1155
+ "learning_rate": 0.0001619586988259712,
1156
+ "loss": 0.5044,
1157
+ "step": 4100
1158
+ },
1159
+ {
1160
+ "epoch": 0.9316770186335404,
1161
+ "grad_norm": 0.0881289690732956,
1162
+ "learning_rate": 0.00016147899022408852,
1163
+ "loss": 0.6192,
1164
+ "step": 4125
1165
+ },
1166
+ {
1167
+ "epoch": 0.9373235460191982,
1168
+ "grad_norm": 0.11012347787618637,
1169
+ "learning_rate": 0.00016099699634675925,
1170
+ "loss": 0.508,
1171
+ "step": 4150
1172
+ },
1173
+ {
1174
+ "epoch": 0.9429700734048561,
1175
+ "grad_norm": 0.0851251408457756,
1176
+ "learning_rate": 0.00016051273511049065,
1177
+ "loss": 0.5897,
1178
+ "step": 4175
1179
+ },
1180
+ {
1181
+ "epoch": 0.9486166007905138,
1182
+ "grad_norm": 0.10288140922784805,
1183
+ "learning_rate": 0.0001600262245160714,
1184
+ "loss": 0.4803,
1185
+ "step": 4200
1186
+ },
1187
+ {
1188
+ "epoch": 0.9542631281761716,
1189
+ "grad_norm": 0.08995950222015381,
1190
+ "learning_rate": 0.0001595374826479026,
1191
+ "loss": 0.6203,
1192
+ "step": 4225
1193
+ },
1194
+ {
1195
+ "epoch": 0.9599096555618295,
1196
+ "grad_norm": 0.10717281699180603,
1197
+ "learning_rate": 0.00015904652767332537,
1198
+ "loss": 0.5068,
1199
+ "step": 4250
1200
+ },
1201
+ {
1202
+ "epoch": 0.9655561829474872,
1203
+ "grad_norm": 0.08305976539850235,
1204
+ "learning_rate": 0.00015855337784194577,
1205
+ "loss": 0.5919,
1206
+ "step": 4275
1207
+ },
1208
+ {
1209
+ "epoch": 0.9712027103331451,
1210
+ "grad_norm": 0.09328145533800125,
1211
+ "learning_rate": 0.00015805805148495623,
1212
+ "loss": 0.4948,
1213
+ "step": 4300
1214
+ },
1215
+ {
1216
+ "epoch": 0.9768492377188029,
1217
+ "grad_norm": 0.09493458271026611,
1218
+ "learning_rate": 0.00015756056701445422,
1219
+ "loss": 0.6024,
1220
+ "step": 4325
1221
+ },
1222
+ {
1223
+ "epoch": 0.9824957651044608,
1224
+ "grad_norm": 0.1051265150308609,
1225
+ "learning_rate": 0.0001570609429227579,
1226
+ "loss": 0.4991,
1227
+ "step": 4350
1228
+ },
1229
+ {
1230
+ "epoch": 0.9881422924901185,
1231
+ "grad_norm": 0.09176123887300491,
1232
+ "learning_rate": 0.00015655919778171862,
1233
+ "loss": 0.6006,
1234
+ "step": 4375
1235
+ },
1236
+ {
1237
+ "epoch": 0.9937888198757764,
1238
+ "grad_norm": 0.0787501335144043,
1239
+ "learning_rate": 0.00015605535024203069,
1240
+ "loss": 0.5013,
1241
+ "step": 4400
1242
+ },
1243
+ {
1244
+ "epoch": 0.9994353472614342,
1245
+ "grad_norm": 0.10489033907651901,
1246
+ "learning_rate": 0.00015554941903253797,
1247
+ "loss": 0.5548,
1248
+ "step": 4425
1249
+ },
1250
+ {
1251
+ "epoch": 1.005081874647092,
1252
+ "grad_norm": 0.08116624504327774,
1253
+ "learning_rate": 0.00015504142295953783,
1254
+ "loss": 0.5719,
1255
+ "step": 4450
1256
+ },
1257
+ {
1258
+ "epoch": 1.0107284020327498,
1259
+ "grad_norm": 0.09656750410795212,
1260
+ "learning_rate": 0.000154531380906082,
1261
+ "loss": 0.4752,
1262
+ "step": 4475
1263
+ },
1264
+ {
1265
+ "epoch": 1.0163749294184077,
1266
+ "grad_norm": 0.09433398395776749,
1267
+ "learning_rate": 0.0001540193118312747,
1268
+ "loss": 0.5796,
1269
+ "step": 4500
1270
+ },
1271
+ {
1272
+ "epoch": 1.0220214568040655,
1273
+ "grad_norm": 0.10783005505800247,
1274
+ "learning_rate": 0.0001535052347695678,
1275
+ "loss": 0.5077,
1276
+ "step": 4525
1277
+ },
1278
+ {
1279
+ "epoch": 1.0276679841897234,
1280
+ "grad_norm": 0.08784560114145279,
1281
+ "learning_rate": 0.00015298916883005342,
1282
+ "loss": 0.5571,
1283
+ "step": 4550
1284
+ },
1285
+ {
1286
+ "epoch": 1.0333145115753812,
1287
+ "grad_norm": 0.11868823319673538,
1288
+ "learning_rate": 0.00015247113319575358,
1289
+ "loss": 0.5223,
1290
+ "step": 4575
1291
+ },
1292
+ {
1293
+ "epoch": 1.0389610389610389,
1294
+ "grad_norm": 0.08813630044460297,
1295
+ "learning_rate": 0.000151951147122907,
1296
+ "loss": 0.561,
1297
+ "step": 4600
1298
+ },
1299
+ {
1300
+ "epoch": 1.0446075663466967,
1301
+ "grad_norm": 0.09996681660413742,
1302
+ "learning_rate": 0.0001514292299402535,
1303
+ "loss": 0.5138,
1304
+ "step": 4625
1305
+ },
1306
+ {
1307
+ "epoch": 1.0502540937323546,
1308
+ "grad_norm": 0.07442251592874527,
1309
+ "learning_rate": 0.00015090540104831539,
1310
+ "loss": 0.5698,
1311
+ "step": 4650
1312
+ },
1313
+ {
1314
+ "epoch": 1.0559006211180124,
1315
+ "grad_norm": 0.09993384033441544,
1316
+ "learning_rate": 0.00015037967991867642,
1317
+ "loss": 0.5093,
1318
+ "step": 4675
1319
+ },
1320
+ {
1321
+ "epoch": 1.0615471485036703,
1322
+ "grad_norm": 0.0890798568725586,
1323
+ "learning_rate": 0.0001498520860932579,
1324
+ "loss": 0.5481,
1325
+ "step": 4700
1326
+ },
1327
+ {
1328
+ "epoch": 1.0671936758893281,
1329
+ "grad_norm": 0.1006857305765152,
1330
+ "learning_rate": 0.00014932263918359228,
1331
+ "loss": 0.5045,
1332
+ "step": 4725
1333
+ },
1334
+ {
1335
+ "epoch": 1.072840203274986,
1336
+ "grad_norm": 0.08858868479728699,
1337
+ "learning_rate": 0.00014879135887009435,
1338
+ "loss": 0.5772,
1339
+ "step": 4750
1340
+ },
1341
+ {
1342
+ "epoch": 1.0784867306606438,
1343
+ "grad_norm": 0.11783988773822784,
1344
+ "learning_rate": 0.00014825826490132938,
1345
+ "loss": 0.4937,
1346
+ "step": 4775
1347
+ },
1348
+ {
1349
+ "epoch": 1.0841332580463015,
1350
+ "grad_norm": 0.0875164121389389,
1351
+ "learning_rate": 0.00014772337709327923,
1352
+ "loss": 0.5554,
1353
+ "step": 4800
1354
+ },
1355
+ {
1356
+ "epoch": 1.0897797854319593,
1357
+ "grad_norm": 0.112996406853199,
1358
+ "learning_rate": 0.00014718671532860592,
1359
+ "loss": 0.5126,
1360
+ "step": 4825
1361
+ },
1362
+ {
1363
+ "epoch": 1.0954263128176172,
1364
+ "grad_norm": 0.08834437280893326,
1365
+ "learning_rate": 0.000146648299555912,
1366
+ "loss": 0.5885,
1367
+ "step": 4850
1368
+ },
1369
+ {
1370
+ "epoch": 1.101072840203275,
1371
+ "grad_norm": 0.11341985315084457,
1372
+ "learning_rate": 0.00014610814978899983,
1373
+ "loss": 0.4871,
1374
+ "step": 4875
1375
+ },
1376
+ {
1377
+ "epoch": 1.1067193675889329,
1378
+ "grad_norm": 0.09301973134279251,
1379
+ "learning_rate": 0.00014556628610612677,
1380
+ "loss": 0.5839,
1381
+ "step": 4900
1382
+ },
1383
+ {
1384
+ "epoch": 1.1123658949745907,
1385
+ "grad_norm": 0.11545081436634064,
1386
+ "learning_rate": 0.00014502272864925955,
1387
+ "loss": 0.4868,
1388
+ "step": 4925
1389
+ },
1390
+ {
1391
+ "epoch": 1.1180124223602483,
1392
+ "grad_norm": 0.08969846367835999,
1393
+ "learning_rate": 0.00014447749762332515,
1394
+ "loss": 0.5472,
1395
+ "step": 4950
1396
+ },
1397
+ {
1398
+ "epoch": 1.1236589497459062,
1399
+ "grad_norm": 0.12094131112098694,
1400
+ "learning_rate": 0.00014393061329545992,
1401
+ "loss": 0.5234,
1402
+ "step": 4975
1403
+ },
1404
+ {
1405
+ "epoch": 1.129305477131564,
1406
+ "grad_norm": 0.0875294953584671,
1407
+ "learning_rate": 0.0001433820959942561,
1408
+ "loss": 0.5852,
1409
+ "step": 5000
1410
+ },
1411
+ {
1412
+ "epoch": 1.134952004517222,
1413
+ "grad_norm": 0.12163736671209335,
1414
+ "learning_rate": 0.00014283196610900638,
1415
+ "loss": 0.4951,
1416
+ "step": 5025
1417
+ },
1418
+ {
1419
+ "epoch": 1.1405985319028797,
1420
+ "grad_norm": 0.08404785394668579,
1421
+ "learning_rate": 0.00014230234328167044,
1422
+ "loss": 0.5629,
1423
+ "step": 5050
1424
+ },
1425
+ {
1426
+ "epoch": 1.1462450592885376,
1427
+ "grad_norm": 0.11473394185304642,
1428
+ "learning_rate": 0.0001417491121057749,
1429
+ "loss": 0.5062,
1430
+ "step": 5075
1431
+ },
1432
+ {
1433
+ "epoch": 1.1518915866741954,
1434
+ "grad_norm": 0.09582609683275223,
1435
+ "learning_rate": 0.0001411943290465374,
1436
+ "loss": 0.5705,
1437
+ "step": 5100
1438
+ },
1439
+ {
1440
+ "epoch": 1.1575381140598533,
1441
+ "grad_norm": 0.11270004510879517,
1442
+ "learning_rate": 0.00014063801472615902,
1443
+ "loss": 0.4918,
1444
+ "step": 5125
1445
+ },
1446
+ {
1447
+ "epoch": 1.163184641445511,
1448
+ "grad_norm": 0.2396761178970337,
1449
+ "learning_rate": 0.00014008018982376044,
1450
+ "loss": 0.5965,
1451
+ "step": 5150
1452
+ },
1453
+ {
1454
+ "epoch": 1.1688311688311688,
1455
+ "grad_norm": 0.1252664476633072,
1456
+ "learning_rate": 0.00013952087507461321,
1457
+ "loss": 0.4814,
1458
+ "step": 5175
1459
+ },
1460
+ {
1461
+ "epoch": 1.1744776962168266,
1462
+ "grad_norm": 0.10077520459890366,
1463
+ "learning_rate": 0.0001389600912693688,
1464
+ "loss": 0.5723,
1465
+ "step": 5200
1466
+ },
1467
+ {
1468
+ "epoch": 1.1801242236024845,
1469
+ "grad_norm": 0.10539643466472626,
1470
+ "learning_rate": 0.00013839785925328605,
1471
+ "loss": 0.4476,
1472
+ "step": 5225
1473
+ },
1474
+ {
1475
+ "epoch": 1.1857707509881423,
1476
+ "grad_norm": 0.0933731198310852,
1477
+ "learning_rate": 0.0001378341999254561,
1478
+ "loss": 0.5683,
1479
+ "step": 5250
1480
+ },
1481
+ {
1482
+ "epoch": 1.1914172783738002,
1483
+ "grad_norm": 0.12707217037677765,
1484
+ "learning_rate": 0.00013726913423802562,
1485
+ "loss": 0.5142,
1486
+ "step": 5275
1487
+ },
1488
+ {
1489
+ "epoch": 1.1970638057594578,
1490
+ "grad_norm": 0.08691050857305527,
1491
+ "learning_rate": 0.0001367026831954181,
1492
+ "loss": 0.5628,
1493
+ "step": 5300
1494
+ },
1495
+ {
1496
+ "epoch": 1.2027103331451157,
1497
+ "grad_norm": 0.10984601825475693,
1498
+ "learning_rate": 0.0001361348678535528,
1499
+ "loss": 0.4924,
1500
+ "step": 5325
1501
+ },
1502
+ {
1503
+ "epoch": 1.2083568605307735,
1504
+ "grad_norm": 0.10582837462425232,
1505
+ "learning_rate": 0.00013556570931906232,
1506
+ "loss": 0.5564,
1507
+ "step": 5350
1508
+ },
1509
+ {
1510
+ "epoch": 1.2140033879164314,
1511
+ "grad_norm": 0.1085626408457756,
1512
+ "learning_rate": 0.000134995228748508,
1513
+ "loss": 0.492,
1514
+ "step": 5375
1515
+ },
1516
+ {
1517
+ "epoch": 1.2196499153020892,
1518
+ "grad_norm": 0.11668406426906586,
1519
+ "learning_rate": 0.00013442344734759332,
1520
+ "loss": 0.5651,
1521
+ "step": 5400
1522
+ },
1523
+ {
1524
+ "epoch": 1.225296442687747,
1525
+ "grad_norm": 0.10734312981367111,
1526
+ "learning_rate": 0.00013385038637037585,
1527
+ "loss": 0.4848,
1528
+ "step": 5425
1529
+ },
1530
+ {
1531
+ "epoch": 1.230942970073405,
1532
+ "grad_norm": 0.10206615924835205,
1533
+ "learning_rate": 0.00013327606711847713,
1534
+ "loss": 0.5739,
1535
+ "step": 5450
1536
+ },
1537
+ {
1538
+ "epoch": 1.2365894974590628,
1539
+ "grad_norm": 0.11335214227437973,
1540
+ "learning_rate": 0.00013270051094029075,
1541
+ "loss": 0.4757,
1542
+ "step": 5475
1543
+ },
1544
+ {
1545
+ "epoch": 1.2422360248447206,
1546
+ "grad_norm": 0.10749132186174393,
1547
+ "learning_rate": 0.00013212373923018905,
1548
+ "loss": 0.5769,
1549
+ "step": 5500
1550
+ },
1551
+ {
1552
+ "epoch": 1.2478825522303783,
1553
+ "grad_norm": 0.13299238681793213,
1554
+ "learning_rate": 0.0001315457734277275,
1555
+ "loss": 0.4758,
1556
+ "step": 5525
1557
+ },
1558
+ {
1559
+ "epoch": 1.253529079616036,
1560
+ "grad_norm": 0.09394491463899612,
1561
+ "learning_rate": 0.00013096663501684813,
1562
+ "loss": 0.5465,
1563
+ "step": 5550
1564
+ },
1565
+ {
1566
+ "epoch": 1.259175607001694,
1567
+ "grad_norm": 0.11942502111196518,
1568
+ "learning_rate": 0.00013038634552508063,
1569
+ "loss": 0.478,
1570
+ "step": 5575
1571
+ },
1572
+ {
1573
+ "epoch": 1.2648221343873518,
1574
+ "grad_norm": 0.09682100266218185,
1575
+ "learning_rate": 0.00012980492652274234,
1576
+ "loss": 0.5667,
1577
+ "step": 5600
1578
+ },
1579
+ {
1580
+ "epoch": 1.2704686617730097,
1581
+ "grad_norm": 0.1254328489303589,
1582
+ "learning_rate": 0.00012922239962213637,
1583
+ "loss": 0.5116,
1584
+ "step": 5625
1585
+ },
1586
+ {
1587
+ "epoch": 1.2761151891586673,
1588
+ "grad_norm": 0.09513936936855316,
1589
+ "learning_rate": 0.00012863878647674816,
1590
+ "loss": 0.5433,
1591
+ "step": 5650
1592
+ },
1593
+ {
1594
+ "epoch": 1.2817617165443251,
1595
+ "grad_norm": 0.10922129452228546,
1596
+ "learning_rate": 0.00012805410878044074,
1597
+ "loss": 0.4867,
1598
+ "step": 5675
1599
+ },
1600
+ {
1601
+ "epoch": 1.287408243929983,
1602
+ "grad_norm": 0.09911426901817322,
1603
+ "learning_rate": 0.00012746838826664826,
1604
+ "loss": 0.5785,
1605
+ "step": 5700
1606
+ },
1607
+ {
1608
+ "epoch": 1.2930547713156408,
1609
+ "grad_norm": 0.11289256066083908,
1610
+ "learning_rate": 0.00012688164670756802,
1611
+ "loss": 0.4761,
1612
+ "step": 5725
1613
+ },
1614
+ {
1615
+ "epoch": 1.2987012987012987,
1616
+ "grad_norm": 0.08862913399934769,
1617
+ "learning_rate": 0.00012629390591335134,
1618
+ "loss": 0.5743,
1619
+ "step": 5750
1620
+ },
1621
+ {
1622
+ "epoch": 1.3043478260869565,
1623
+ "grad_norm": 0.13005360960960388,
1624
+ "learning_rate": 0.00012570518773129277,
1625
+ "loss": 0.49,
1626
+ "step": 5775
1627
+ },
1628
+ {
1629
+ "epoch": 1.3099943534726144,
1630
+ "grad_norm": 0.08972469717264175,
1631
+ "learning_rate": 0.0001251155140450179,
1632
+ "loss": 0.5443,
1633
+ "step": 5800
1634
+ },
1635
+ {
1636
+ "epoch": 1.3156408808582722,
1637
+ "grad_norm": 0.11599931865930557,
1638
+ "learning_rate": 0.00012452490677367003,
1639
+ "loss": 0.5138,
1640
+ "step": 5825
1641
+ },
1642
+ {
1643
+ "epoch": 1.32128740824393,
1644
+ "grad_norm": 0.096194326877594,
1645
+ "learning_rate": 0.0001239333878710954,
1646
+ "loss": 0.5524,
1647
+ "step": 5850
1648
+ },
1649
+ {
1650
+ "epoch": 1.3269339356295877,
1651
+ "grad_norm": 0.11309222131967545,
1652
+ "learning_rate": 0.00012334097932502702,
1653
+ "loss": 0.485,
1654
+ "step": 5875
1655
+ },
1656
+ {
1657
+ "epoch": 1.3325804630152456,
1658
+ "grad_norm": 0.09447719901800156,
1659
+ "learning_rate": 0.00012274770315626743,
1660
+ "loss": 0.5748,
1661
+ "step": 5900
1662
+ },
1663
+ {
1664
+ "epoch": 1.3382269904009034,
1665
+ "grad_norm": 0.11994371563196182,
1666
+ "learning_rate": 0.00012215358141787016,
1667
+ "loss": 0.4826,
1668
+ "step": 5925
1669
+ },
1670
+ {
1671
+ "epoch": 1.3438735177865613,
1672
+ "grad_norm": 0.10158982127904892,
1673
+ "learning_rate": 0.00012155863619431993,
1674
+ "loss": 0.5593,
1675
+ "step": 5950
1676
+ },
1677
+ {
1678
+ "epoch": 1.3495200451722191,
1679
+ "grad_norm": 0.1210799366235733,
1680
+ "learning_rate": 0.00012096288960071178,
1681
+ "loss": 0.4977,
1682
+ "step": 5975
1683
+ },
1684
+ {
1685
+ "epoch": 1.355166572557877,
1686
+ "grad_norm": 0.0946585088968277,
1687
+ "learning_rate": 0.00012036636378192902,
1688
+ "loss": 0.5617,
1689
+ "step": 6000
1690
+ },
1691
+ {
1692
+ "epoch": 1.3608130999435346,
1693
+ "grad_norm": 0.10858285427093506,
1694
+ "learning_rate": 0.00011976908091181998,
1695
+ "loss": 0.468,
1696
+ "step": 6025
1697
+ },
1698
+ {
1699
+ "epoch": 1.3664596273291925,
1700
+ "grad_norm": 0.08753529191017151,
1701
+ "learning_rate": 0.00011917106319237386,
1702
+ "loss": 0.5854,
1703
+ "step": 6050
1704
+ },
1705
+ {
1706
+ "epoch": 1.3721061547148503,
1707
+ "grad_norm": 0.1213916763663292,
1708
+ "learning_rate": 0.00011857233285289546,
1709
+ "loss": 0.4915,
1710
+ "step": 6075
1711
+ },
1712
+ {
1713
+ "epoch": 1.3777526821005082,
1714
+ "grad_norm": 0.09568001329898834,
1715
+ "learning_rate": 0.00011797291214917881,
1716
+ "loss": 0.5699,
1717
+ "step": 6100
1718
+ },
1719
+ {
1720
+ "epoch": 1.383399209486166,
1721
+ "grad_norm": 0.10872907191514969,
1722
+ "learning_rate": 0.00011737282336267992,
1723
+ "loss": 0.4744,
1724
+ "step": 6125
1725
+ },
1726
+ {
1727
+ "epoch": 1.3890457368718239,
1728
+ "grad_norm": 0.1102764755487442,
1729
+ "learning_rate": 0.00011677208879968858,
1730
+ "loss": 0.5315,
1731
+ "step": 6150
1732
+ },
1733
+ {
1734
+ "epoch": 1.3946922642574817,
1735
+ "grad_norm": 0.1172797903418541,
1736
+ "learning_rate": 0.00011617073079049905,
1737
+ "loss": 0.493,
1738
+ "step": 6175
1739
+ },
1740
+ {
1741
+ "epoch": 1.4003387916431396,
1742
+ "grad_norm": 0.09269782900810242,
1743
+ "learning_rate": 0.0001155687716885802,
1744
+ "loss": 0.5383,
1745
+ "step": 6200
1746
+ },
1747
+ {
1748
+ "epoch": 1.4059853190287974,
1749
+ "grad_norm": 0.11610530316829681,
1750
+ "learning_rate": 0.00011496623386974454,
1751
+ "loss": 0.4748,
1752
+ "step": 6225
1753
+ },
1754
+ {
1755
+ "epoch": 1.411631846414455,
1756
+ "grad_norm": 0.10046471655368805,
1757
+ "learning_rate": 0.00011436313973131634,
1758
+ "loss": 0.5397,
1759
+ "step": 6250
1760
+ },
1761
+ {
1762
+ "epoch": 1.417278373800113,
1763
+ "grad_norm": 0.1363869458436966,
1764
+ "learning_rate": 0.00011375951169129926,
1765
+ "loss": 0.4944,
1766
+ "step": 6275
1767
+ },
1768
+ {
1769
+ "epoch": 1.4229249011857708,
1770
+ "grad_norm": 0.09395238012075424,
1771
+ "learning_rate": 0.00011315537218754295,
1772
+ "loss": 0.5614,
1773
+ "step": 6300
1774
+ },
1775
+ {
1776
+ "epoch": 1.4285714285714286,
1777
+ "grad_norm": 0.11986027657985687,
1778
+ "learning_rate": 0.00011255074367690897,
1779
+ "loss": 0.4914,
1780
+ "step": 6325
1781
+ },
1782
+ {
1783
+ "epoch": 1.4342179559570865,
1784
+ "grad_norm": 0.0886669009923935,
1785
+ "learning_rate": 0.0001119456486344361,
1786
+ "loss": 0.5615,
1787
+ "step": 6350
1788
+ },
1789
+ {
1790
+ "epoch": 1.439864483342744,
1791
+ "grad_norm": 0.12676212191581726,
1792
+ "learning_rate": 0.00011134010955250491,
1793
+ "loss": 0.4836,
1794
+ "step": 6375
1795
+ },
1796
+ {
1797
+ "epoch": 1.445511010728402,
1798
+ "grad_norm": 0.09607352316379547,
1799
+ "learning_rate": 0.00011073414894000161,
1800
+ "loss": 0.5505,
1801
+ "step": 6400
1802
+ },
1803
+ {
1804
+ "epoch": 1.4511575381140598,
1805
+ "grad_norm": 0.12430471181869507,
1806
+ "learning_rate": 0.00011012778932148142,
1807
+ "loss": 0.4949,
1808
+ "step": 6425
1809
+ },
1810
+ {
1811
+ "epoch": 1.4568040654997176,
1812
+ "grad_norm": 0.10339995473623276,
1813
+ "learning_rate": 0.00010952105323633126,
1814
+ "loss": 0.5583,
1815
+ "step": 6450
1816
+ },
1817
+ {
1818
+ "epoch": 1.4624505928853755,
1819
+ "grad_norm": 0.11074826866388321,
1820
+ "learning_rate": 0.00010891396323793189,
1821
+ "loss": 0.4973,
1822
+ "step": 6475
1823
+ },
1824
+ {
1825
+ "epoch": 1.4680971202710333,
1826
+ "grad_norm": 0.09366384148597717,
1827
+ "learning_rate": 0.00010830654189281968,
1828
+ "loss": 0.5329,
1829
+ "step": 6500
1830
+ },
1831
+ {
1832
+ "epoch": 1.4737436476566912,
1833
+ "grad_norm": 0.12167912721633911,
1834
+ "learning_rate": 0.00010769881177984771,
1835
+ "loss": 0.4901,
1836
+ "step": 6525
1837
+ },
1838
+ {
1839
+ "epoch": 1.479390175042349,
1840
+ "grad_norm": 0.09269159287214279,
1841
+ "learning_rate": 0.0001070907954893464,
1842
+ "loss": 0.5685,
1843
+ "step": 6550
1844
+ },
1845
+ {
1846
+ "epoch": 1.485036702428007,
1847
+ "grad_norm": 0.11428316682577133,
1848
+ "learning_rate": 0.00010648251562228386,
1849
+ "loss": 0.5,
1850
+ "step": 6575
1851
+ },
1852
+ {
1853
+ "epoch": 1.4906832298136645,
1854
+ "grad_norm": 0.10255276411771774,
1855
+ "learning_rate": 0.00010587399478942592,
1856
+ "loss": 0.5492,
1857
+ "step": 6600
1858
+ },
1859
+ {
1860
+ "epoch": 1.4963297571993224,
1861
+ "grad_norm": 0.10394936800003052,
1862
+ "learning_rate": 0.0001052652556104953,
1863
+ "loss": 0.4788,
1864
+ "step": 6625
1865
+ },
1866
+ {
1867
+ "epoch": 1.5019762845849802,
1868
+ "grad_norm": 0.0881161019206047,
1869
+ "learning_rate": 0.00010465632071333113,
1870
+ "loss": 0.5606,
1871
+ "step": 6650
1872
+ },
1873
+ {
1874
+ "epoch": 1.507622811970638,
1875
+ "grad_norm": 0.1109280213713646,
1876
+ "learning_rate": 0.00010404721273304769,
1877
+ "loss": 0.5183,
1878
+ "step": 6675
1879
+ },
1880
+ {
1881
+ "epoch": 1.513269339356296,
1882
+ "grad_norm": 0.10558915883302689,
1883
+ "learning_rate": 0.00010343795431119304,
1884
+ "loss": 0.5563,
1885
+ "step": 6700
1886
+ },
1887
+ {
1888
+ "epoch": 1.5189158667419536,
1889
+ "grad_norm": 0.13079263269901276,
1890
+ "learning_rate": 0.00010282856809490739,
1891
+ "loss": 0.4977,
1892
+ "step": 6725
1893
+ },
1894
+ {
1895
+ "epoch": 1.5245623941276114,
1896
+ "grad_norm": 0.09773046523332596,
1897
+ "learning_rate": 0.00010221907673608133,
1898
+ "loss": 0.5698,
1899
+ "step": 6750
1900
+ },
1901
+ {
1902
+ "epoch": 1.5302089215132693,
1903
+ "grad_norm": 0.11996293067932129,
1904
+ "learning_rate": 0.00010160950289051365,
1905
+ "loss": 0.4764,
1906
+ "step": 6775
1907
+ },
1908
+ {
1909
+ "epoch": 1.5358554488989271,
1910
+ "grad_norm": 0.12360116094350815,
1911
+ "learning_rate": 0.00010099986921706946,
1912
+ "loss": 0.5274,
1913
+ "step": 6800
1914
+ },
1915
+ {
1916
+ "epoch": 1.541501976284585,
1917
+ "grad_norm": 0.1305209845304489,
1918
+ "learning_rate": 0.00010039019837683767,
1919
+ "loss": 0.4531,
1920
+ "step": 6825
1921
+ },
1922
+ {
1923
+ "epoch": 1.5471485036702428,
1924
+ "grad_norm": 0.10246080160140991,
1925
+ "learning_rate": 9.978051303228875e-05,
1926
+ "loss": 0.5593,
1927
+ "step": 6850
1928
+ },
1929
+ {
1930
+ "epoch": 1.5527950310559007,
1931
+ "grad_norm": 0.13810117542743683,
1932
+ "learning_rate": 9.917083584643235e-05,
1933
+ "loss": 0.4838,
1934
+ "step": 6875
1935
+ },
1936
+ {
1937
+ "epoch": 1.5584415584415585,
1938
+ "grad_norm": 0.10199406743049622,
1939
+ "learning_rate": 9.856118948197488e-05,
1940
+ "loss": 0.5405,
1941
+ "step": 6900
1942
+ },
1943
+ {
1944
+ "epoch": 1.5640880858272164,
1945
+ "grad_norm": 0.11060495674610138,
1946
+ "learning_rate": 9.795159660047697e-05,
1947
+ "loss": 0.4974,
1948
+ "step": 6925
1949
+ },
1950
+ {
1951
+ "epoch": 1.5697346132128742,
1952
+ "grad_norm": 0.10460948944091797,
1953
+ "learning_rate": 9.734207986151126e-05,
1954
+ "loss": 0.5568,
1955
+ "step": 6950
1956
+ },
1957
+ {
1958
+ "epoch": 1.5753811405985318,
1959
+ "grad_norm": 0.11652641743421555,
1960
+ "learning_rate": 9.673266192182008e-05,
1961
+ "loss": 0.4683,
1962
+ "step": 6975
1963
+ },
1964
+ {
1965
+ "epoch": 1.5810276679841897,
1966
+ "grad_norm": 0.09894441068172455,
1967
+ "learning_rate": 9.612336543447314e-05,
1968
+ "loss": 0.5598,
1969
+ "step": 7000
1970
+ },
1971
+ {
1972
+ "epoch": 1.5866741953698476,
1973
+ "grad_norm": 0.10987823456525803,
1974
+ "learning_rate": 9.551421304802565e-05,
1975
+ "loss": 0.4582,
1976
+ "step": 7025
1977
+ },
1978
+ {
1979
+ "epoch": 1.5923207227555054,
1980
+ "grad_norm": 0.09542589634656906,
1981
+ "learning_rate": 9.490522740567633e-05,
1982
+ "loss": 0.5482,
1983
+ "step": 7050
1984
+ },
1985
+ {
1986
+ "epoch": 1.597967250141163,
1987
+ "grad_norm": 0.12428826838731766,
1988
+ "learning_rate": 9.42964311444257e-05,
1989
+ "loss": 0.4999,
1990
+ "step": 7075
1991
+ },
1992
+ {
1993
+ "epoch": 1.6036137775268209,
1994
+ "grad_norm": 0.10819413512945175,
1995
+ "learning_rate": 9.368784689423467e-05,
1996
+ "loss": 0.5652,
1997
+ "step": 7100
1998
+ },
1999
+ {
2000
+ "epoch": 1.6092603049124787,
2001
+ "grad_norm": 0.13115598261356354,
2002
+ "learning_rate": 9.307949727718346e-05,
2003
+ "loss": 0.4771,
2004
+ "step": 7125
2005
+ },
2006
+ {
2007
+ "epoch": 1.6149068322981366,
2008
+ "grad_norm": 0.1047302857041359,
2009
+ "learning_rate": 9.24714049066305e-05,
2010
+ "loss": 0.5376,
2011
+ "step": 7150
2012
+ },
2013
+ {
2014
+ "epoch": 1.6205533596837944,
2015
+ "grad_norm": 0.13034017384052277,
2016
+ "learning_rate": 9.186359238637197e-05,
2017
+ "loss": 0.4863,
2018
+ "step": 7175
2019
+ },
2020
+ {
2021
+ "epoch": 1.6261998870694523,
2022
+ "grad_norm": 0.10137925297021866,
2023
+ "learning_rate": 9.12560823098015e-05,
2024
+ "loss": 0.5442,
2025
+ "step": 7200
2026
+ },
2027
+ {
2028
+ "epoch": 1.6318464144551101,
2029
+ "grad_norm": 0.12191277742385864,
2030
+ "learning_rate": 9.064889725907043e-05,
2031
+ "loss": 0.4717,
2032
+ "step": 7225
2033
+ },
2034
+ {
2035
+ "epoch": 1.637492941840768,
2036
+ "grad_norm": 0.10191314667463303,
2037
+ "learning_rate": 9.004205980424842e-05,
2038
+ "loss": 0.5457,
2039
+ "step": 7250
2040
+ },
2041
+ {
2042
+ "epoch": 1.6431394692264258,
2043
+ "grad_norm": 0.11787448078393936,
2044
+ "learning_rate": 8.943559250248426e-05,
2045
+ "loss": 0.4858,
2046
+ "step": 7275
2047
+ },
2048
+ {
2049
+ "epoch": 1.6487859966120837,
2050
+ "grad_norm": 0.1057475134730339,
2051
+ "learning_rate": 8.88295178971677e-05,
2052
+ "loss": 0.5735,
2053
+ "step": 7300
2054
+ },
2055
+ {
2056
+ "epoch": 1.6544325239977415,
2057
+ "grad_norm": 0.12938141822814941,
2058
+ "learning_rate": 8.822385851709125e-05,
2059
+ "loss": 0.4829,
2060
+ "step": 7325
2061
+ },
2062
+ {
2063
+ "epoch": 1.6600790513833992,
2064
+ "grad_norm": 0.10724066197872162,
2065
+ "learning_rate": 8.761863687561275e-05,
2066
+ "loss": 0.5408,
2067
+ "step": 7350
2068
+ },
2069
+ {
2070
+ "epoch": 1.665725578769057,
2071
+ "grad_norm": 0.11694779992103577,
2072
+ "learning_rate": 8.701387546981868e-05,
2073
+ "loss": 0.4961,
2074
+ "step": 7375
2075
+ },
2076
+ {
2077
+ "epoch": 1.6713721061547149,
2078
+ "grad_norm": 0.10590225458145142,
2079
+ "learning_rate": 8.640959677968778e-05,
2080
+ "loss": 0.5466,
2081
+ "step": 7400
2082
+ },
2083
+ {
2084
+ "epoch": 1.6770186335403725,
2085
+ "grad_norm": 0.11699523031711578,
2086
+ "learning_rate": 8.580582326725535e-05,
2087
+ "loss": 0.4709,
2088
+ "step": 7425
2089
+ },
2090
+ {
2091
+ "epoch": 1.6826651609260304,
2092
+ "grad_norm": 0.1064140573143959,
2093
+ "learning_rate": 8.520257737577854e-05,
2094
+ "loss": 0.5349,
2095
+ "step": 7450
2096
+ },
2097
+ {
2098
+ "epoch": 1.6883116883116882,
2099
+ "grad_norm": 0.12415055185556412,
2100
+ "learning_rate": 8.459988152890188e-05,
2101
+ "loss": 0.4655,
2102
+ "step": 7475
2103
+ },
2104
+ {
2105
+ "epoch": 1.693958215697346,
2106
+ "grad_norm": 0.11068243533372879,
2107
+ "learning_rate": 8.39977581298239e-05,
2108
+ "loss": 0.5459,
2109
+ "step": 7500
2110
+ },
2111
+ {
2112
+ "epoch": 1.699604743083004,
2113
+ "grad_norm": 0.12139423191547394,
2114
+ "learning_rate": 8.339622956046417e-05,
2115
+ "loss": 0.4657,
2116
+ "step": 7525
2117
+ },
2118
+ {
2119
+ "epoch": 1.7052512704686618,
2120
+ "grad_norm": 0.10302968323230743,
2121
+ "learning_rate": 8.27953181806316e-05,
2122
+ "loss": 0.5571,
2123
+ "step": 7550
2124
+ },
2125
+ {
2126
+ "epoch": 1.7108977978543196,
2127
+ "grad_norm": 0.12433881312608719,
2128
+ "learning_rate": 8.21950463271931e-05,
2129
+ "loss": 0.4887,
2130
+ "step": 7575
2131
+ },
2132
+ {
2133
+ "epoch": 1.7165443252399775,
2134
+ "grad_norm": 0.09217355400323868,
2135
+ "learning_rate": 8.159543631324327e-05,
2136
+ "loss": 0.5281,
2137
+ "step": 7600
2138
+ },
2139
+ {
2140
+ "epoch": 1.7221908526256353,
2141
+ "grad_norm": 0.11367136240005493,
2142
+ "learning_rate": 8.099651042727515e-05,
2143
+ "loss": 0.4849,
2144
+ "step": 7625
2145
+ },
2146
+ {
2147
+ "epoch": 1.7278373800112932,
2148
+ "grad_norm": 0.10472942888736725,
2149
+ "learning_rate": 8.039829093235156e-05,
2150
+ "loss": 0.5748,
2151
+ "step": 7650
2152
+ },
2153
+ {
2154
+ "epoch": 1.733483907396951,
2155
+ "grad_norm": 0.13037872314453125,
2156
+ "learning_rate": 7.980080006527751e-05,
2157
+ "loss": 0.4781,
2158
+ "step": 7675
2159
+ },
2160
+ {
2161
+ "epoch": 1.7391304347826086,
2162
+ "grad_norm": 0.1035398542881012,
2163
+ "learning_rate": 7.920406003577394e-05,
2164
+ "loss": 0.5419,
2165
+ "step": 7700
2166
+ },
2167
+ {
2168
+ "epoch": 1.7447769621682665,
2169
+ "grad_norm": 0.12669602036476135,
2170
+ "learning_rate": 7.86080930256517e-05,
2171
+ "loss": 0.4865,
2172
+ "step": 7725
2173
+ },
2174
+ {
2175
+ "epoch": 1.7504234895539243,
2176
+ "grad_norm": 0.09713231027126312,
2177
+ "learning_rate": 7.801292118798732e-05,
2178
+ "loss": 0.564,
2179
+ "step": 7750
2180
+ },
2181
+ {
2182
+ "epoch": 1.7560700169395822,
2183
+ "grad_norm": 0.12088830769062042,
2184
+ "learning_rate": 7.74185666462995e-05,
2185
+ "loss": 0.4641,
2186
+ "step": 7775
2187
+ },
2188
+ {
2189
+ "epoch": 1.7617165443252398,
2190
+ "grad_norm": 0.11002447456121445,
2191
+ "learning_rate": 7.68250514937266e-05,
2192
+ "loss": 0.5407,
2193
+ "step": 7800
2194
+ },
2195
+ {
2196
+ "epoch": 1.7673630717108977,
2197
+ "grad_norm": 0.12338761240243912,
2198
+ "learning_rate": 7.623239779220557e-05,
2199
+ "loss": 0.4558,
2200
+ "step": 7825
2201
+ },
2202
+ {
2203
+ "epoch": 1.7730095990965555,
2204
+ "grad_norm": 0.10458722710609436,
2205
+ "learning_rate": 7.564062757165183e-05,
2206
+ "loss": 0.55,
2207
+ "step": 7850
2208
+ },
2209
+ {
2210
+ "epoch": 1.7786561264822134,
2211
+ "grad_norm": 0.1287498027086258,
2212
+ "learning_rate": 7.504976282914027e-05,
2213
+ "loss": 0.4745,
2214
+ "step": 7875
2215
+ },
2216
+ {
2217
+ "epoch": 1.7843026538678712,
2218
+ "grad_norm": 0.10165251046419144,
2219
+ "learning_rate": 7.445982552808774e-05,
2220
+ "loss": 0.567,
2221
+ "step": 7900
2222
+ },
2223
+ {
2224
+ "epoch": 1.789949181253529,
2225
+ "grad_norm": 0.12862220406532288,
2226
+ "learning_rate": 7.387083759743655e-05,
2227
+ "loss": 0.4777,
2228
+ "step": 7925
2229
+ },
2230
+ {
2231
+ "epoch": 1.795595708639187,
2232
+ "grad_norm": 0.1015312671661377,
2233
+ "learning_rate": 7.328282093083929e-05,
2234
+ "loss": 0.5648,
2235
+ "step": 7950
2236
+ },
2237
+ {
2238
+ "epoch": 1.8012422360248448,
2239
+ "grad_norm": 0.1260487586259842,
2240
+ "learning_rate": 7.269579738584513e-05,
2241
+ "loss": 0.4895,
2242
+ "step": 7975
2243
+ },
2244
+ {
2245
+ "epoch": 1.8068887634105026,
2246
+ "grad_norm": 0.10070119798183441,
2247
+ "learning_rate": 7.210978878308729e-05,
2248
+ "loss": 0.581,
2249
+ "step": 8000
2250
+ },
2251
+ {
2252
+ "epoch": 1.8125352907961605,
2253
+ "grad_norm": 0.12946705520153046,
2254
+ "learning_rate": 7.152481690547182e-05,
2255
+ "loss": 0.475,
2256
+ "step": 8025
2257
+ },
2258
+ {
2259
+ "epoch": 1.8181818181818183,
2260
+ "grad_norm": 0.09579546749591827,
2261
+ "learning_rate": 7.094090349736803e-05,
2262
+ "loss": 0.5516,
2263
+ "step": 8050
2264
+ },
2265
+ {
2266
+ "epoch": 1.823828345567476,
2267
+ "grad_norm": 0.12078605592250824,
2268
+ "learning_rate": 7.035807026380026e-05,
2269
+ "loss": 0.4882,
2270
+ "step": 8075
2271
+ },
2272
+ {
2273
+ "epoch": 1.8294748729531338,
2274
+ "grad_norm": 0.10442069917917252,
2275
+ "learning_rate": 6.977633886964081e-05,
2276
+ "loss": 0.5322,
2277
+ "step": 8100
2278
+ },
2279
+ {
2280
+ "epoch": 1.8351214003387917,
2281
+ "grad_norm": 0.13175725936889648,
2282
+ "learning_rate": 6.919573093880494e-05,
2283
+ "loss": 0.4578,
2284
+ "step": 8125
2285
+ },
2286
+ {
2287
+ "epoch": 1.8407679277244493,
2288
+ "grad_norm": 0.10551594197750092,
2289
+ "learning_rate": 6.861626805344689e-05,
2290
+ "loss": 0.547,
2291
+ "step": 8150
2292
+ },
2293
+ {
2294
+ "epoch": 1.8464144551101072,
2295
+ "grad_norm": 0.11718405783176422,
2296
+ "learning_rate": 6.803797175315761e-05,
2297
+ "loss": 0.4872,
2298
+ "step": 8175
2299
+ },
2300
+ {
2301
+ "epoch": 1.852060982495765,
2302
+ "grad_norm": 0.12317229807376862,
2303
+ "learning_rate": 6.74608635341642e-05,
2304
+ "loss": 0.5724,
2305
+ "step": 8200
2306
+ },
2307
+ {
2308
+ "epoch": 1.8577075098814229,
2309
+ "grad_norm": 0.13172867894172668,
2310
+ "learning_rate": 6.688496484853084e-05,
2311
+ "loss": 0.4506,
2312
+ "step": 8225
2313
+ },
2314
+ {
2315
+ "epoch": 1.8633540372670807,
2316
+ "grad_norm": 0.09928746521472931,
2317
+ "learning_rate": 6.631029710336133e-05,
2318
+ "loss": 0.5094,
2319
+ "step": 8250
2320
+ },
2321
+ {
2322
+ "epoch": 1.8690005646527386,
2323
+ "grad_norm": 0.12048971652984619,
2324
+ "learning_rate": 6.573688166000345e-05,
2325
+ "loss": 0.4608,
2326
+ "step": 8275
2327
+ },
2328
+ {
2329
+ "epoch": 1.8746470920383964,
2330
+ "grad_norm": 0.1059262603521347,
2331
+ "learning_rate": 6.516473983325473e-05,
2332
+ "loss": 0.5475,
2333
+ "step": 8300
2334
+ },
2335
+ {
2336
+ "epoch": 1.8802936194240543,
2337
+ "grad_norm": 0.1448829621076584,
2338
+ "learning_rate": 6.459389289057038e-05,
2339
+ "loss": 0.4695,
2340
+ "step": 8325
2341
+ },
2342
+ {
2343
+ "epoch": 1.8859401468097121,
2344
+ "grad_norm": 0.0976184606552124,
2345
+ "learning_rate": 6.40243620512726e-05,
2346
+ "loss": 0.549,
2347
+ "step": 8350
2348
+ },
2349
+ {
2350
+ "epoch": 1.89158667419537,
2351
+ "grad_norm": 0.14233841001987457,
2352
+ "learning_rate": 6.345616848576184e-05,
2353
+ "loss": 0.4716,
2354
+ "step": 8375
2355
+ },
2356
+ {
2357
+ "epoch": 1.8972332015810278,
2358
+ "grad_norm": 0.10030635446310043,
2359
+ "learning_rate": 6.288933331472988e-05,
2360
+ "loss": 0.561,
2361
+ "step": 8400
2362
+ },
2363
+ {
2364
+ "epoch": 1.9028797289666854,
2365
+ "grad_norm": 0.12384554743766785,
2366
+ "learning_rate": 6.232387760837474e-05,
2367
+ "loss": 0.4872,
2368
+ "step": 8425
2369
+ },
2370
+ {
2371
+ "epoch": 1.9085262563523433,
2372
+ "grad_norm": 0.10905805230140686,
2373
+ "learning_rate": 6.175982238561755e-05,
2374
+ "loss": 0.5347,
2375
+ "step": 8450
2376
+ },
2377
+ {
2378
+ "epoch": 1.9141727837380011,
2379
+ "grad_norm": 0.13816171884536743,
2380
+ "learning_rate": 6.119718861332098e-05,
2381
+ "loss": 0.477,
2382
+ "step": 8475
2383
+ },
2384
+ {
2385
+ "epoch": 1.919819311123659,
2386
+ "grad_norm": 0.11039167642593384,
2387
+ "learning_rate": 6.0635997205510175e-05,
2388
+ "loss": 0.5706,
2389
+ "step": 8500
2390
+ },
2391
+ {
2392
+ "epoch": 1.9254658385093166,
2393
+ "grad_norm": 0.1241937056183815,
2394
+ "learning_rate": 6.007626902259521e-05,
2395
+ "loss": 0.4787,
2396
+ "step": 8525
2397
+ },
2398
+ {
2399
+ "epoch": 1.9311123658949745,
2400
+ "grad_norm": 0.1162077784538269,
2401
+ "learning_rate": 5.951802487059559e-05,
2402
+ "loss": 0.5515,
2403
+ "step": 8550
2404
+ },
2405
+ {
2406
+ "epoch": 1.9367588932806323,
2407
+ "grad_norm": 0.12294231355190277,
2408
+ "learning_rate": 5.8961285500367034e-05,
2409
+ "loss": 0.4699,
2410
+ "step": 8575
2411
+ },
2412
+ {
2413
+ "epoch": 1.9424054206662902,
2414
+ "grad_norm": 0.10771624743938446,
2415
+ "learning_rate": 5.8406071606830026e-05,
2416
+ "loss": 0.5373,
2417
+ "step": 8600
2418
+ },
2419
+ {
2420
+ "epoch": 1.948051948051948,
2421
+ "grad_norm": 0.11943277716636658,
2422
+ "learning_rate": 5.7852403828200495e-05,
2423
+ "loss": 0.4648,
2424
+ "step": 8625
2425
+ },
2426
+ {
2427
+ "epoch": 1.9536984754376059,
2428
+ "grad_norm": 0.11853492259979248,
2429
+ "learning_rate": 5.730030274522282e-05,
2430
+ "loss": 0.5501,
2431
+ "step": 8650
2432
+ },
2433
+ {
2434
+ "epoch": 1.9593450028232637,
2435
+ "grad_norm": 0.12967811524868011,
2436
+ "learning_rate": 5.674978888040463e-05,
2437
+ "loss": 0.4808,
2438
+ "step": 8675
2439
+ },
2440
+ {
2441
+ "epoch": 1.9649915302089216,
2442
+ "grad_norm": 0.112027108669281,
2443
+ "learning_rate": 5.6200882697254154e-05,
2444
+ "loss": 0.5311,
2445
+ "step": 8700
2446
+ },
2447
+ {
2448
+ "epoch": 1.9706380575945794,
2449
+ "grad_norm": 0.1347729116678238,
2450
+ "learning_rate": 5.565360459951936e-05,
2451
+ "loss": 0.4679,
2452
+ "step": 8725
2453
+ },
2454
+ {
2455
+ "epoch": 1.9762845849802373,
2456
+ "grad_norm": 0.11015453189611435,
2457
+ "learning_rate": 5.510797493042954e-05,
2458
+ "loss": 0.5595,
2459
+ "step": 8750
2460
+ },
2461
+ {
2462
+ "epoch": 1.981931112365895,
2463
+ "grad_norm": 0.13183894753456116,
2464
+ "learning_rate": 5.456401397193936e-05,
2465
+ "loss": 0.4656,
2466
+ "step": 8775
2467
+ },
2468
+ {
2469
+ "epoch": 1.9875776397515528,
2470
+ "grad_norm": 0.10906127840280533,
2471
+ "learning_rate": 5.402174194397458e-05,
2472
+ "loss": 0.537,
2473
+ "step": 8800
2474
+ },
2475
+ {
2476
+ "epoch": 1.9932241671372106,
2477
+ "grad_norm": 0.1271781325340271,
2478
+ "learning_rate": 5.348117900368066e-05,
2479
+ "loss": 0.4639,
2480
+ "step": 8825
2481
+ },
2482
+ {
2483
+ "epoch": 1.9988706945228685,
2484
+ "grad_norm": 0.12033294886350632,
2485
+ "learning_rate": 5.2942345244673564e-05,
2486
+ "loss": 0.5076,
2487
+ "step": 8850
2488
+ },
2489
+ {
2490
+ "epoch": 2.004517221908526,
2491
+ "grad_norm": 0.11611133068799973,
2492
+ "learning_rate": 5.240526069629265e-05,
2493
+ "loss": 0.5368,
2494
+ "step": 8875
2495
+ },
2496
+ {
2497
+ "epoch": 2.010163749294184,
2498
+ "grad_norm": 0.16251997649669647,
2499
+ "learning_rate": 5.1869945322856196e-05,
2500
+ "loss": 0.4708,
2501
+ "step": 8900
2502
+ },
2503
+ {
2504
+ "epoch": 2.015810276679842,
2505
+ "grad_norm": 0.10342962294816971,
2506
+ "learning_rate": 5.1336419022919435e-05,
2507
+ "loss": 0.5186,
2508
+ "step": 8925
2509
+ },
2510
+ {
2511
+ "epoch": 2.0214568040654997,
2512
+ "grad_norm": 0.12473160028457642,
2513
+ "learning_rate": 5.080470162853472e-05,
2514
+ "loss": 0.4405,
2515
+ "step": 8950
2516
+ },
2517
+ {
2518
+ "epoch": 2.0271033314511575,
2519
+ "grad_norm": 0.10961506515741348,
2520
+ "learning_rate": 5.0274812904514346e-05,
2521
+ "loss": 0.4963,
2522
+ "step": 8975
2523
+ },
2524
+ {
2525
+ "epoch": 2.0327498588368154,
2526
+ "grad_norm": 0.13045734167099,
2527
+ "learning_rate": 4.974677254769608e-05,
2528
+ "loss": 0.4648,
2529
+ "step": 9000
2530
+ },
2531
+ {
2532
+ "epoch": 2.038396386222473,
2533
+ "grad_norm": 0.10588447749614716,
2534
+ "learning_rate": 4.922060018621066e-05,
2535
+ "loss": 0.514,
2536
+ "step": 9025
2537
+ },
2538
+ {
2539
+ "epoch": 2.044042913608131,
2540
+ "grad_norm": 0.1310020089149475,
2541
+ "learning_rate": 4.869631537875243e-05,
2542
+ "loss": 0.4581,
2543
+ "step": 9050
2544
+ },
2545
+ {
2546
+ "epoch": 2.049689440993789,
2547
+ "grad_norm": 0.11264315247535706,
2548
+ "learning_rate": 4.8173937613852296e-05,
2549
+ "loss": 0.514,
2550
+ "step": 9075
2551
+ },
2552
+ {
2553
+ "epoch": 2.0553359683794468,
2554
+ "grad_norm": 0.11348750442266464,
2555
+ "learning_rate": 4.765348630915315e-05,
2556
+ "loss": 0.4509,
2557
+ "step": 9100
2558
+ },
2559
+ {
2560
+ "epoch": 2.0609824957651046,
2561
+ "grad_norm": 0.1084527000784874,
2562
+ "learning_rate": 4.713498081068819e-05,
2563
+ "loss": 0.4836,
2564
+ "step": 9125
2565
+ },
2566
+ {
2567
+ "epoch": 2.0666290231507625,
2568
+ "grad_norm": 0.12957565486431122,
2569
+ "learning_rate": 4.6618440392161886e-05,
2570
+ "loss": 0.4467,
2571
+ "step": 9150
2572
+ },
2573
+ {
2574
+ "epoch": 2.0722755505364203,
2575
+ "grad_norm": 0.10537248849868774,
2576
+ "learning_rate": 4.610388425423336e-05,
2577
+ "loss": 0.52,
2578
+ "step": 9175
2579
+ },
2580
+ {
2581
+ "epoch": 2.0779220779220777,
2582
+ "grad_norm": 0.13615071773529053,
2583
+ "learning_rate": 4.559133152380272e-05,
2584
+ "loss": 0.4567,
2585
+ "step": 9200
2586
+ },
2587
+ {
2588
+ "epoch": 2.0835686053077356,
2589
+ "grad_norm": 0.11438791453838348,
2590
+ "learning_rate": 4.508080125330022e-05,
2591
+ "loss": 0.5111,
2592
+ "step": 9225
2593
+ },
2594
+ {
2595
+ "epoch": 2.0892151326933934,
2596
+ "grad_norm": 0.1288277804851532,
2597
+ "learning_rate": 4.457231241997788e-05,
2598
+ "loss": 0.4584,
2599
+ "step": 9250
2600
+ },
2601
+ {
2602
+ "epoch": 2.0948616600790513,
2603
+ "grad_norm": 0.10171278566122055,
2604
+ "learning_rate": 4.40658839252041e-05,
2605
+ "loss": 0.5065,
2606
+ "step": 9275
2607
+ },
2608
+ {
2609
+ "epoch": 2.100508187464709,
2610
+ "grad_norm": 0.1178368479013443,
2611
+ "learning_rate": 4.356153459376121e-05,
2612
+ "loss": 0.4426,
2613
+ "step": 9300
2614
+ },
2615
+ {
2616
+ "epoch": 2.106154714850367,
2617
+ "grad_norm": 0.12345319241285324,
2618
+ "learning_rate": 4.305928317314549e-05,
2619
+ "loss": 0.5134,
2620
+ "step": 9325
2621
+ },
2622
+ {
2623
+ "epoch": 2.111801242236025,
2624
+ "grad_norm": 0.1341843158006668,
2625
+ "learning_rate": 4.255914833287046e-05,
2626
+ "loss": 0.4526,
2627
+ "step": 9350
2628
+ },
2629
+ {
2630
+ "epoch": 2.1174477696216827,
2631
+ "grad_norm": 0.12422988563776016,
2632
+ "learning_rate": 4.206114866377291e-05,
2633
+ "loss": 0.5025,
2634
+ "step": 9375
2635
+ },
2636
+ {
2637
+ "epoch": 2.1230942970073405,
2638
+ "grad_norm": 0.1362808346748352,
2639
+ "learning_rate": 4.156530267732173e-05,
2640
+ "loss": 0.4701,
2641
+ "step": 9400
2642
+ },
2643
+ {
2644
+ "epoch": 2.1287408243929984,
2645
+ "grad_norm": 0.11891162395477295,
2646
+ "learning_rate": 4.107162880492984e-05,
2647
+ "loss": 0.5091,
2648
+ "step": 9425
2649
+ },
2650
+ {
2651
+ "epoch": 2.1343873517786562,
2652
+ "grad_norm": 0.13123708963394165,
2653
+ "learning_rate": 4.058014539726922e-05,
2654
+ "loss": 0.4593,
2655
+ "step": 9450
2656
+ },
2657
+ {
2658
+ "epoch": 2.140033879164314,
2659
+ "grad_norm": 0.11908406764268875,
2660
+ "learning_rate": 4.0090870723588606e-05,
2661
+ "loss": 0.5076,
2662
+ "step": 9475
2663
+ },
2664
+ {
2665
+ "epoch": 2.145680406549972,
2666
+ "grad_norm": 0.1421327143907547,
2667
+ "learning_rate": 3.960382297103442e-05,
2668
+ "loss": 0.4467,
2669
+ "step": 9500
2670
+ },
2671
+ {
2672
+ "epoch": 2.15132693393563,
2673
+ "grad_norm": 0.1141195222735405,
2674
+ "learning_rate": 3.911902024397473e-05,
2675
+ "loss": 0.5044,
2676
+ "step": 9525
2677
+ },
2678
+ {
2679
+ "epoch": 2.1569734613212876,
2680
+ "grad_norm": 0.11890695989131927,
2681
+ "learning_rate": 3.8636480563326425e-05,
2682
+ "loss": 0.4562,
2683
+ "step": 9550
2684
+ },
2685
+ {
2686
+ "epoch": 2.162619988706945,
2687
+ "grad_norm": 0.12307918071746826,
2688
+ "learning_rate": 3.8156221865885126e-05,
2689
+ "loss": 0.5154,
2690
+ "step": 9575
2691
+ },
2692
+ {
2693
+ "epoch": 2.168266516092603,
2694
+ "grad_norm": 0.12713749706745148,
2695
+ "learning_rate": 3.767826200365853e-05,
2696
+ "loss": 0.4578,
2697
+ "step": 9600
2698
+ },
2699
+ {
2700
+ "epoch": 2.1739130434782608,
2701
+ "grad_norm": 0.12245321273803711,
2702
+ "learning_rate": 3.7202618743202935e-05,
2703
+ "loss": 0.5022,
2704
+ "step": 9625
2705
+ },
2706
+ {
2707
+ "epoch": 2.1795595708639186,
2708
+ "grad_norm": 0.1354779750108719,
2709
+ "learning_rate": 3.6729309764962616e-05,
2710
+ "loss": 0.4534,
2711
+ "step": 9650
2712
+ },
2713
+ {
2714
+ "epoch": 2.1852060982495765,
2715
+ "grad_norm": 0.10722421109676361,
2716
+ "learning_rate": 3.625835266261287e-05,
2717
+ "loss": 0.5021,
2718
+ "step": 9675
2719
+ },
2720
+ {
2721
+ "epoch": 2.1908526256352343,
2722
+ "grad_norm": 0.1329207420349121,
2723
+ "learning_rate": 3.578976494240577e-05,
2724
+ "loss": 0.4639,
2725
+ "step": 9700
2726
+ },
2727
+ {
2728
+ "epoch": 2.196499153020892,
2729
+ "grad_norm": 0.11663591116666794,
2730
+ "learning_rate": 3.532356402251954e-05,
2731
+ "loss": 0.4882,
2732
+ "step": 9725
2733
+ },
2734
+ {
2735
+ "epoch": 2.20214568040655,
2736
+ "grad_norm": 0.13668714463710785,
2737
+ "learning_rate": 3.485976723241121e-05,
2738
+ "loss": 0.465,
2739
+ "step": 9750
2740
+ },
2741
+ {
2742
+ "epoch": 2.207792207792208,
2743
+ "grad_norm": 0.11890459805727005,
2744
+ "learning_rate": 3.439839181217227e-05,
2745
+ "loss": 0.505,
2746
+ "step": 9775
2747
+ },
2748
+ {
2749
+ "epoch": 2.2134387351778657,
2750
+ "grad_norm": 0.1332354098558426,
2751
+ "learning_rate": 3.3939454911887844e-05,
2752
+ "loss": 0.4497,
2753
+ "step": 9800
2754
+ },
2755
+ {
2756
+ "epoch": 2.2190852625635236,
2757
+ "grad_norm": 0.11797164380550385,
2758
+ "learning_rate": 3.34829735909994e-05,
2759
+ "loss": 0.536,
2760
+ "step": 9825
2761
+ },
2762
+ {
2763
+ "epoch": 2.2247317899491814,
2764
+ "grad_norm": 0.13317126035690308,
2765
+ "learning_rate": 3.302896481767034e-05,
2766
+ "loss": 0.4645,
2767
+ "step": 9850
2768
+ },
2769
+ {
2770
+ "epoch": 2.2303783173348393,
2771
+ "grad_norm": 0.11745914816856384,
2772
+ "learning_rate": 3.25774454681554e-05,
2773
+ "loss": 0.4991,
2774
+ "step": 9875
2775
+ },
2776
+ {
2777
+ "epoch": 2.2360248447204967,
2778
+ "grad_norm": 0.13392220437526703,
2779
+ "learning_rate": 3.212843232617343e-05,
2780
+ "loss": 0.4385,
2781
+ "step": 9900
2782
+ },
2783
+ {
2784
+ "epoch": 2.2416713721061545,
2785
+ "grad_norm": 0.11925249546766281,
2786
+ "learning_rate": 3.168194208228331e-05,
2787
+ "loss": 0.4801,
2788
+ "step": 9925
2789
+ },
2790
+ {
2791
+ "epoch": 2.2473178994918124,
2792
+ "grad_norm": 0.1346205770969391,
2793
+ "learning_rate": 3.123799133326366e-05,
2794
+ "loss": 0.4562,
2795
+ "step": 9950
2796
+ },
2797
+ {
2798
+ "epoch": 2.2529644268774702,
2799
+ "grad_norm": 0.1318216472864151,
2800
+ "learning_rate": 3.0796596581495963e-05,
2801
+ "loss": 0.499,
2802
+ "step": 9975
2803
+ },
2804
+ {
2805
+ "epoch": 2.258610954263128,
2806
+ "grad_norm": 0.1402980238199234,
2807
+ "learning_rate": 3.0357774234350945e-05,
2808
+ "loss": 0.4386,
2809
+ "step": 10000
2810
+ },
2811
+ {
2812
+ "epoch": 2.264257481648786,
2813
+ "grad_norm": 0.12823522090911865,
2814
+ "learning_rate": 2.9921540603578935e-05,
2815
+ "loss": 0.5133,
2816
+ "step": 10025
2817
+ },
2818
+ {
2819
+ "epoch": 2.269904009034444,
2820
+ "grad_norm": 0.14426416158676147,
2821
+ "learning_rate": 2.948791190470328e-05,
2822
+ "loss": 0.4595,
2823
+ "step": 10050
2824
+ },
2825
+ {
2826
+ "epoch": 2.2755505364201016,
2827
+ "grad_norm": 0.1231706440448761,
2828
+ "learning_rate": 2.905690425641785e-05,
2829
+ "loss": 0.5228,
2830
+ "step": 10075
2831
+ },
2832
+ {
2833
+ "epoch": 2.2811970638057595,
2834
+ "grad_norm": 0.13321641087532043,
2835
+ "learning_rate": 2.8628533679987634e-05,
2836
+ "loss": 0.4573,
2837
+ "step": 10100
2838
+ },
2839
+ {
2840
+ "epoch": 2.2868435911914173,
2841
+ "grad_norm": 0.11738098412752151,
2842
+ "learning_rate": 2.8219793665574002e-05,
2843
+ "loss": 0.4917,
2844
+ "step": 10125
2845
+ },
2846
+ {
2847
+ "epoch": 2.292490118577075,
2848
+ "grad_norm": 0.13331496715545654,
2849
+ "learning_rate": 2.779663784858103e-05,
2850
+ "loss": 0.4596,
2851
+ "step": 10150
2852
+ },
2853
+ {
2854
+ "epoch": 2.298136645962733,
2855
+ "grad_norm": 0.12486054003238678,
2856
+ "learning_rate": 2.73761659496239e-05,
2857
+ "loss": 0.494,
2858
+ "step": 10175
2859
+ },
2860
+ {
2861
+ "epoch": 2.303783173348391,
2862
+ "grad_norm": 0.14081965386867523,
2863
+ "learning_rate": 2.6958393598336407e-05,
2864
+ "loss": 0.467,
2865
+ "step": 10200
2866
+ },
2867
+ {
2868
+ "epoch": 2.3094297007340487,
2869
+ "grad_norm": 0.1274556964635849,
2870
+ "learning_rate": 2.654333632400574e-05,
2871
+ "loss": 0.5183,
2872
+ "step": 10225
2873
+ },
2874
+ {
2875
+ "epoch": 2.3150762281197066,
2876
+ "grad_norm": 0.14484131336212158,
2877
+ "learning_rate": 2.6131009554995288e-05,
2878
+ "loss": 0.4589,
2879
+ "step": 10250
2880
+ },
2881
+ {
2882
+ "epoch": 2.320722755505364,
2883
+ "grad_norm": 0.11335089802742004,
2884
+ "learning_rate": 2.572142861817095e-05,
2885
+ "loss": 0.4942,
2886
+ "step": 10275
2887
+ },
2888
+ {
2889
+ "epoch": 2.326369282891022,
2890
+ "grad_norm": 0.1360946148633957,
2891
+ "learning_rate": 2.5314608738331537e-05,
2892
+ "loss": 0.4664,
2893
+ "step": 10300
2894
+ },
2895
+ {
2896
+ "epoch": 2.3320158102766797,
2897
+ "grad_norm": 0.15792761743068695,
2898
+ "learning_rate": 2.4910565037642885e-05,
2899
+ "loss": 0.5171,
2900
+ "step": 10325
2901
+ },
2902
+ {
2903
+ "epoch": 2.3376623376623376,
2904
+ "grad_norm": 0.14088444411754608,
2905
+ "learning_rate": 2.45093125350756e-05,
2906
+ "loss": 0.4478,
2907
+ "step": 10350
2908
+ },
2909
+ {
2910
+ "epoch": 2.3433088650479954,
2911
+ "grad_norm": 0.12279202044010162,
2912
+ "learning_rate": 2.4110866145846846e-05,
2913
+ "loss": 0.5165,
2914
+ "step": 10375
2915
+ },
2916
+ {
2917
+ "epoch": 2.3489553924336533,
2918
+ "grad_norm": 0.13455908000469208,
2919
+ "learning_rate": 2.3715240680866004e-05,
2920
+ "loss": 0.4524,
2921
+ "step": 10400
2922
+ }
2923
+ ],
2924
+ "logging_steps": 25,
2925
+ "max_steps": 13281,
2926
+ "num_input_tokens_seen": 0,
2927
+ "num_train_epochs": 3,
2928
+ "save_steps": 200,
2929
+ "stateful_callbacks": {
2930
+ "TrainerControl": {
2931
+ "args": {
2932
+ "should_epoch_stop": false,
2933
+ "should_evaluate": false,
2934
+ "should_log": false,
2935
+ "should_save": true,
2936
+ "should_training_stop": false
2937
+ },
2938
+ "attributes": {}
2939
+ }
2940
+ },
2941
+ "total_flos": 6.117139722901709e+18,
2942
+ "train_batch_size": 2,
2943
+ "trial_name": null,
2944
+ "trial_params": null
2945
+ }