Jamesb1974 commited on
Commit
f21ecc5
1 Parent(s): 3ddba5d

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - autotrain
4
+ - text-generation-inference
5
+ - text-generation
6
+ - peft
7
+ library_name: transformers
8
+ widget:
9
+ - messages:
10
+ - role: user
11
+ content: What is your favorite condiment?
12
+ license: other
13
+ ---
14
+
15
+ # Model Trained Using AutoTrain
16
+
17
+ This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain).
18
+
19
+ # Usage
20
+
21
+ ```python
22
+
23
+ from transformers import AutoModelForCausalLM, AutoTokenizer
24
+
25
+ model_path = "PATH_TO_THIS_REPO"
26
+
27
+ tokenizer = AutoTokenizer.from_pretrained(model_path)
28
+ model = AutoModelForCausalLM.from_pretrained(
29
+ model_path,
30
+ device_map="auto",
31
+ torch_dtype='auto'
32
+ ).eval()
33
+
34
+ # Prompt content: "hi"
35
+ messages = [
36
+ {"role": "user", "content": "hi"}
37
+ ]
38
+
39
+ input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
40
+ output_ids = model.generate(input_ids.to('cuda'))
41
+ response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
42
+
43
+ # Model response: "Hello! How can I assist you today?"
44
+ print(response)
45
+ ```
adapter_config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "openai-community/gpt2",
5
+ "bias": "none",
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": 32,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 16,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "c_proj",
24
+ "c_attn",
25
+ "c_fc"
26
+ ],
27
+ "task_type": "CAUSAL_LM",
28
+ "use_dora": false,
29
+ "use_rslora": false
30
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6efbcdd293ac58d989af284231807d14dd3113b3800940ec786dbe25caa3cf1f
3
+ size 9449344
checkpoint-3174/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: openai-community/gpt2
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 0.10.0
checkpoint-3174/adapter_config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "openai-community/gpt2",
5
+ "bias": "none",
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": 32,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 16,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "c_proj",
24
+ "c_attn",
25
+ "c_fc"
26
+ ],
27
+ "task_type": "CAUSAL_LM",
28
+ "use_dora": false,
29
+ "use_rslora": false
30
+ }
checkpoint-3174/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6efbcdd293ac58d989af284231807d14dd3113b3800940ec786dbe25caa3cf1f
3
+ size 9449344
checkpoint-3174/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-3174/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57c9f6de877aa9570e634a5ef35886af08db5516c3d6f12f15b56619bbfe0fc2
3
+ size 18955258
checkpoint-3174/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:049c26b844b79121ddd8379f7f69194e63f6fbf6aa007eeac0c66f17eebb8893
3
+ size 888
checkpoint-3174/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e015086b6e106c3d7d2dd6bc6a1c03f745b78bdfae3151c1c631d89aed345ece
3
+ size 14244
checkpoint-3174/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab386026c67f080b79b0ac8b6317068f3c6060e4e11305c8dc69cd961d2305fd
3
+ size 1064
checkpoint-3174/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
checkpoint-3174/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-3174/tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ }
12
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
15
+ "clean_up_tokenization_spaces": true,
16
+ "eos_token": "<|endoftext|>",
17
+ "model_max_length": 1024,
18
+ "pad_token": "<|endoftext|>",
19
+ "tokenizer_class": "GPT2Tokenizer",
20
+ "unk_token": "<|endoftext|>"
21
+ }
checkpoint-3174/trainer_state.json ADDED
@@ -0,0 +1,903 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.994334277620396,
5
+ "eval_steps": 500,
6
+ "global_step": 3174,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.05,
13
+ "grad_norm": 1.3795244693756104,
14
+ "learning_rate": 2.358490566037736e-06,
15
+ "loss": 2.6953,
16
+ "step": 25
17
+ },
18
+ {
19
+ "epoch": 0.09,
20
+ "grad_norm": 1.2704118490219116,
21
+ "learning_rate": 4.716981132075472e-06,
22
+ "loss": 2.7089,
23
+ "step": 50
24
+ },
25
+ {
26
+ "epoch": 0.14,
27
+ "grad_norm": 1.1683423519134521,
28
+ "learning_rate": 7.0754716981132075e-06,
29
+ "loss": 2.6511,
30
+ "step": 75
31
+ },
32
+ {
33
+ "epoch": 0.19,
34
+ "grad_norm": 1.2082363367080688,
35
+ "learning_rate": 9.433962264150944e-06,
36
+ "loss": 2.5193,
37
+ "step": 100
38
+ },
39
+ {
40
+ "epoch": 0.24,
41
+ "grad_norm": 1.1215194463729858,
42
+ "learning_rate": 1.179245283018868e-05,
43
+ "loss": 2.306,
44
+ "step": 125
45
+ },
46
+ {
47
+ "epoch": 0.28,
48
+ "grad_norm": 0.6498327255249023,
49
+ "learning_rate": 1.4150943396226415e-05,
50
+ "loss": 2.1279,
51
+ "step": 150
52
+ },
53
+ {
54
+ "epoch": 0.33,
55
+ "grad_norm": 0.5128926038742065,
56
+ "learning_rate": 1.650943396226415e-05,
57
+ "loss": 1.979,
58
+ "step": 175
59
+ },
60
+ {
61
+ "epoch": 0.38,
62
+ "grad_norm": 0.4196425676345825,
63
+ "learning_rate": 1.8867924528301888e-05,
64
+ "loss": 1.857,
65
+ "step": 200
66
+ },
67
+ {
68
+ "epoch": 0.42,
69
+ "grad_norm": 0.39977598190307617,
70
+ "learning_rate": 2.122641509433962e-05,
71
+ "loss": 1.7905,
72
+ "step": 225
73
+ },
74
+ {
75
+ "epoch": 0.47,
76
+ "grad_norm": 0.3468642830848694,
77
+ "learning_rate": 2.358490566037736e-05,
78
+ "loss": 1.7396,
79
+ "step": 250
80
+ },
81
+ {
82
+ "epoch": 0.52,
83
+ "grad_norm": 0.3703348934650421,
84
+ "learning_rate": 2.5943396226415097e-05,
85
+ "loss": 1.6826,
86
+ "step": 275
87
+ },
88
+ {
89
+ "epoch": 0.57,
90
+ "grad_norm": 0.3471335470676422,
91
+ "learning_rate": 2.830188679245283e-05,
92
+ "loss": 1.6333,
93
+ "step": 300
94
+ },
95
+ {
96
+ "epoch": 0.61,
97
+ "grad_norm": 0.30928292870521545,
98
+ "learning_rate": 2.9926470588235295e-05,
99
+ "loss": 1.5934,
100
+ "step": 325
101
+ },
102
+ {
103
+ "epoch": 0.66,
104
+ "grad_norm": 0.33998557925224304,
105
+ "learning_rate": 2.966386554621849e-05,
106
+ "loss": 1.5503,
107
+ "step": 350
108
+ },
109
+ {
110
+ "epoch": 0.71,
111
+ "grad_norm": 0.3642776906490326,
112
+ "learning_rate": 2.940126050420168e-05,
113
+ "loss": 1.5243,
114
+ "step": 375
115
+ },
116
+ {
117
+ "epoch": 0.76,
118
+ "grad_norm": 0.31012433767318726,
119
+ "learning_rate": 2.9138655462184876e-05,
120
+ "loss": 1.4618,
121
+ "step": 400
122
+ },
123
+ {
124
+ "epoch": 0.8,
125
+ "grad_norm": 0.4258916974067688,
126
+ "learning_rate": 2.8876050420168067e-05,
127
+ "loss": 1.4161,
128
+ "step": 425
129
+ },
130
+ {
131
+ "epoch": 0.85,
132
+ "grad_norm": 0.3025980591773987,
133
+ "learning_rate": 2.8613445378151262e-05,
134
+ "loss": 1.419,
135
+ "step": 450
136
+ },
137
+ {
138
+ "epoch": 0.9,
139
+ "grad_norm": 0.3354116678237915,
140
+ "learning_rate": 2.8350840336134453e-05,
141
+ "loss": 1.3576,
142
+ "step": 475
143
+ },
144
+ {
145
+ "epoch": 0.94,
146
+ "grad_norm": 0.3400489091873169,
147
+ "learning_rate": 2.8088235294117648e-05,
148
+ "loss": 1.3323,
149
+ "step": 500
150
+ },
151
+ {
152
+ "epoch": 0.99,
153
+ "grad_norm": 0.315164715051651,
154
+ "learning_rate": 2.7825630252100843e-05,
155
+ "loss": 1.344,
156
+ "step": 525
157
+ },
158
+ {
159
+ "epoch": 1.04,
160
+ "grad_norm": 0.3593141734600067,
161
+ "learning_rate": 2.7563025210084034e-05,
162
+ "loss": 1.3023,
163
+ "step": 550
164
+ },
165
+ {
166
+ "epoch": 1.09,
167
+ "grad_norm": 0.4317137598991394,
168
+ "learning_rate": 2.730042016806723e-05,
169
+ "loss": 1.3028,
170
+ "step": 575
171
+ },
172
+ {
173
+ "epoch": 1.13,
174
+ "grad_norm": 0.3506380617618561,
175
+ "learning_rate": 2.703781512605042e-05,
176
+ "loss": 1.3026,
177
+ "step": 600
178
+ },
179
+ {
180
+ "epoch": 1.18,
181
+ "grad_norm": 0.33726122975349426,
182
+ "learning_rate": 2.6775210084033615e-05,
183
+ "loss": 1.319,
184
+ "step": 625
185
+ },
186
+ {
187
+ "epoch": 1.23,
188
+ "grad_norm": 0.37094271183013916,
189
+ "learning_rate": 2.6512605042016806e-05,
190
+ "loss": 1.2583,
191
+ "step": 650
192
+ },
193
+ {
194
+ "epoch": 1.27,
195
+ "grad_norm": 0.41374334692955017,
196
+ "learning_rate": 2.625e-05,
197
+ "loss": 1.2486,
198
+ "step": 675
199
+ },
200
+ {
201
+ "epoch": 1.32,
202
+ "grad_norm": 0.46000728011131287,
203
+ "learning_rate": 2.5987394957983196e-05,
204
+ "loss": 1.2463,
205
+ "step": 700
206
+ },
207
+ {
208
+ "epoch": 1.37,
209
+ "grad_norm": 0.3955087661743164,
210
+ "learning_rate": 2.5724789915966387e-05,
211
+ "loss": 1.2397,
212
+ "step": 725
213
+ },
214
+ {
215
+ "epoch": 1.42,
216
+ "grad_norm": 0.4096736013889313,
217
+ "learning_rate": 2.546218487394958e-05,
218
+ "loss": 1.229,
219
+ "step": 750
220
+ },
221
+ {
222
+ "epoch": 1.46,
223
+ "grad_norm": 0.3845139741897583,
224
+ "learning_rate": 2.5199579831932773e-05,
225
+ "loss": 1.2314,
226
+ "step": 775
227
+ },
228
+ {
229
+ "epoch": 1.51,
230
+ "grad_norm": 0.4077882170677185,
231
+ "learning_rate": 2.4936974789915968e-05,
232
+ "loss": 1.2219,
233
+ "step": 800
234
+ },
235
+ {
236
+ "epoch": 1.56,
237
+ "grad_norm": 0.36021721363067627,
238
+ "learning_rate": 2.467436974789916e-05,
239
+ "loss": 1.234,
240
+ "step": 825
241
+ },
242
+ {
243
+ "epoch": 1.61,
244
+ "grad_norm": 0.36913222074508667,
245
+ "learning_rate": 2.4411764705882354e-05,
246
+ "loss": 1.1998,
247
+ "step": 850
248
+ },
249
+ {
250
+ "epoch": 1.65,
251
+ "grad_norm": 0.35471582412719727,
252
+ "learning_rate": 2.414915966386555e-05,
253
+ "loss": 1.1988,
254
+ "step": 875
255
+ },
256
+ {
257
+ "epoch": 1.7,
258
+ "grad_norm": 0.3558790683746338,
259
+ "learning_rate": 2.3886554621848737e-05,
260
+ "loss": 1.2106,
261
+ "step": 900
262
+ },
263
+ {
264
+ "epoch": 1.75,
265
+ "grad_norm": 0.36467084288597107,
266
+ "learning_rate": 2.362394957983193e-05,
267
+ "loss": 1.1717,
268
+ "step": 925
269
+ },
270
+ {
271
+ "epoch": 1.79,
272
+ "grad_norm": 0.381874680519104,
273
+ "learning_rate": 2.3361344537815126e-05,
274
+ "loss": 1.1896,
275
+ "step": 950
276
+ },
277
+ {
278
+ "epoch": 1.84,
279
+ "grad_norm": 0.3758748769760132,
280
+ "learning_rate": 2.309873949579832e-05,
281
+ "loss": 1.1712,
282
+ "step": 975
283
+ },
284
+ {
285
+ "epoch": 1.89,
286
+ "grad_norm": 0.35793235898017883,
287
+ "learning_rate": 2.2836134453781513e-05,
288
+ "loss": 1.1389,
289
+ "step": 1000
290
+ },
291
+ {
292
+ "epoch": 1.94,
293
+ "grad_norm": 0.44111478328704834,
294
+ "learning_rate": 2.2573529411764707e-05,
295
+ "loss": 1.1726,
296
+ "step": 1025
297
+ },
298
+ {
299
+ "epoch": 1.98,
300
+ "grad_norm": 0.3741939663887024,
301
+ "learning_rate": 2.2310924369747902e-05,
302
+ "loss": 1.1607,
303
+ "step": 1050
304
+ },
305
+ {
306
+ "epoch": 2.03,
307
+ "grad_norm": 0.3894720673561096,
308
+ "learning_rate": 2.2048319327731093e-05,
309
+ "loss": 1.2186,
310
+ "step": 1075
311
+ },
312
+ {
313
+ "epoch": 2.08,
314
+ "grad_norm": 0.3636987805366516,
315
+ "learning_rate": 2.1785714285714285e-05,
316
+ "loss": 1.1376,
317
+ "step": 1100
318
+ },
319
+ {
320
+ "epoch": 2.12,
321
+ "grad_norm": 0.42893752455711365,
322
+ "learning_rate": 2.152310924369748e-05,
323
+ "loss": 1.158,
324
+ "step": 1125
325
+ },
326
+ {
327
+ "epoch": 2.17,
328
+ "grad_norm": 0.3795158863067627,
329
+ "learning_rate": 2.1260504201680674e-05,
330
+ "loss": 1.1574,
331
+ "step": 1150
332
+ },
333
+ {
334
+ "epoch": 2.22,
335
+ "grad_norm": 0.36902275681495667,
336
+ "learning_rate": 2.0997899159663866e-05,
337
+ "loss": 1.1523,
338
+ "step": 1175
339
+ },
340
+ {
341
+ "epoch": 2.27,
342
+ "grad_norm": 0.431219220161438,
343
+ "learning_rate": 2.073529411764706e-05,
344
+ "loss": 1.1433,
345
+ "step": 1200
346
+ },
347
+ {
348
+ "epoch": 2.31,
349
+ "grad_norm": 0.4199659824371338,
350
+ "learning_rate": 2.0472689075630252e-05,
351
+ "loss": 1.1481,
352
+ "step": 1225
353
+ },
354
+ {
355
+ "epoch": 2.36,
356
+ "grad_norm": 0.6324878334999084,
357
+ "learning_rate": 2.0210084033613447e-05,
358
+ "loss": 1.1526,
359
+ "step": 1250
360
+ },
361
+ {
362
+ "epoch": 2.41,
363
+ "grad_norm": 0.523536205291748,
364
+ "learning_rate": 1.9947478991596638e-05,
365
+ "loss": 1.1216,
366
+ "step": 1275
367
+ },
368
+ {
369
+ "epoch": 2.46,
370
+ "grad_norm": 0.5140235424041748,
371
+ "learning_rate": 1.9684873949579833e-05,
372
+ "loss": 1.1539,
373
+ "step": 1300
374
+ },
375
+ {
376
+ "epoch": 2.5,
377
+ "grad_norm": 0.3695720136165619,
378
+ "learning_rate": 1.9422268907563027e-05,
379
+ "loss": 1.1666,
380
+ "step": 1325
381
+ },
382
+ {
383
+ "epoch": 2.55,
384
+ "grad_norm": 0.4080689251422882,
385
+ "learning_rate": 1.915966386554622e-05,
386
+ "loss": 1.1037,
387
+ "step": 1350
388
+ },
389
+ {
390
+ "epoch": 2.6,
391
+ "grad_norm": 0.35790908336639404,
392
+ "learning_rate": 1.889705882352941e-05,
393
+ "loss": 1.136,
394
+ "step": 1375
395
+ },
396
+ {
397
+ "epoch": 2.64,
398
+ "grad_norm": 0.42846861481666565,
399
+ "learning_rate": 1.8634453781512605e-05,
400
+ "loss": 1.1325,
401
+ "step": 1400
402
+ },
403
+ {
404
+ "epoch": 2.69,
405
+ "grad_norm": 0.37662366032600403,
406
+ "learning_rate": 1.83718487394958e-05,
407
+ "loss": 1.1439,
408
+ "step": 1425
409
+ },
410
+ {
411
+ "epoch": 2.74,
412
+ "grad_norm": 0.4963545501232147,
413
+ "learning_rate": 1.810924369747899e-05,
414
+ "loss": 1.1701,
415
+ "step": 1450
416
+ },
417
+ {
418
+ "epoch": 2.79,
419
+ "grad_norm": 0.4511197507381439,
420
+ "learning_rate": 1.7846638655462186e-05,
421
+ "loss": 1.1338,
422
+ "step": 1475
423
+ },
424
+ {
425
+ "epoch": 2.83,
426
+ "grad_norm": 0.44771987199783325,
427
+ "learning_rate": 1.758403361344538e-05,
428
+ "loss": 1.1021,
429
+ "step": 1500
430
+ },
431
+ {
432
+ "epoch": 2.88,
433
+ "grad_norm": 0.4158724248409271,
434
+ "learning_rate": 1.7321428571428572e-05,
435
+ "loss": 1.094,
436
+ "step": 1525
437
+ },
438
+ {
439
+ "epoch": 2.93,
440
+ "grad_norm": 0.43490564823150635,
441
+ "learning_rate": 1.7058823529411763e-05,
442
+ "loss": 1.1154,
443
+ "step": 1550
444
+ },
445
+ {
446
+ "epoch": 2.97,
447
+ "grad_norm": 0.4746383726596832,
448
+ "learning_rate": 1.6796218487394958e-05,
449
+ "loss": 1.1311,
450
+ "step": 1575
451
+ },
452
+ {
453
+ "epoch": 3.02,
454
+ "grad_norm": 0.4157463312149048,
455
+ "learning_rate": 1.6533613445378153e-05,
456
+ "loss": 1.1202,
457
+ "step": 1600
458
+ },
459
+ {
460
+ "epoch": 3.07,
461
+ "grad_norm": 0.38272300362586975,
462
+ "learning_rate": 1.6271008403361344e-05,
463
+ "loss": 1.1173,
464
+ "step": 1625
465
+ },
466
+ {
467
+ "epoch": 3.12,
468
+ "grad_norm": 0.5032052397727966,
469
+ "learning_rate": 1.600840336134454e-05,
470
+ "loss": 1.1313,
471
+ "step": 1650
472
+ },
473
+ {
474
+ "epoch": 3.16,
475
+ "grad_norm": 0.3842039704322815,
476
+ "learning_rate": 1.5745798319327734e-05,
477
+ "loss": 1.0984,
478
+ "step": 1675
479
+ },
480
+ {
481
+ "epoch": 3.21,
482
+ "grad_norm": 0.43160513043403625,
483
+ "learning_rate": 1.5483193277310925e-05,
484
+ "loss": 1.1108,
485
+ "step": 1700
486
+ },
487
+ {
488
+ "epoch": 3.26,
489
+ "grad_norm": 0.420173704624176,
490
+ "learning_rate": 1.5220588235294118e-05,
491
+ "loss": 1.144,
492
+ "step": 1725
493
+ },
494
+ {
495
+ "epoch": 3.31,
496
+ "grad_norm": 0.43490853905677795,
497
+ "learning_rate": 1.4957983193277311e-05,
498
+ "loss": 1.0752,
499
+ "step": 1750
500
+ },
501
+ {
502
+ "epoch": 3.35,
503
+ "grad_norm": 0.45708540081977844,
504
+ "learning_rate": 1.4695378151260504e-05,
505
+ "loss": 1.1447,
506
+ "step": 1775
507
+ },
508
+ {
509
+ "epoch": 3.4,
510
+ "grad_norm": 0.417322039604187,
511
+ "learning_rate": 1.4432773109243699e-05,
512
+ "loss": 1.102,
513
+ "step": 1800
514
+ },
515
+ {
516
+ "epoch": 3.45,
517
+ "grad_norm": 0.4371644854545593,
518
+ "learning_rate": 1.417016806722689e-05,
519
+ "loss": 1.1473,
520
+ "step": 1825
521
+ },
522
+ {
523
+ "epoch": 3.49,
524
+ "grad_norm": 0.4273310899734497,
525
+ "learning_rate": 1.3907563025210085e-05,
526
+ "loss": 1.0967,
527
+ "step": 1850
528
+ },
529
+ {
530
+ "epoch": 3.54,
531
+ "grad_norm": 0.5089781880378723,
532
+ "learning_rate": 1.3644957983193278e-05,
533
+ "loss": 1.1297,
534
+ "step": 1875
535
+ },
536
+ {
537
+ "epoch": 3.59,
538
+ "grad_norm": 0.48617228865623474,
539
+ "learning_rate": 1.3382352941176471e-05,
540
+ "loss": 1.0955,
541
+ "step": 1900
542
+ },
543
+ {
544
+ "epoch": 3.64,
545
+ "grad_norm": 0.4370473623275757,
546
+ "learning_rate": 1.3119747899159664e-05,
547
+ "loss": 1.0791,
548
+ "step": 1925
549
+ },
550
+ {
551
+ "epoch": 3.68,
552
+ "grad_norm": 0.4495941400527954,
553
+ "learning_rate": 1.2857142857142857e-05,
554
+ "loss": 1.0648,
555
+ "step": 1950
556
+ },
557
+ {
558
+ "epoch": 3.73,
559
+ "grad_norm": 0.4138700067996979,
560
+ "learning_rate": 1.259453781512605e-05,
561
+ "loss": 1.0948,
562
+ "step": 1975
563
+ },
564
+ {
565
+ "epoch": 3.78,
566
+ "grad_norm": 0.4161551296710968,
567
+ "learning_rate": 1.2331932773109243e-05,
568
+ "loss": 1.0947,
569
+ "step": 2000
570
+ },
571
+ {
572
+ "epoch": 3.82,
573
+ "grad_norm": 0.3938988745212555,
574
+ "learning_rate": 1.2069327731092438e-05,
575
+ "loss": 1.0863,
576
+ "step": 2025
577
+ },
578
+ {
579
+ "epoch": 3.87,
580
+ "grad_norm": 0.44733569025993347,
581
+ "learning_rate": 1.180672268907563e-05,
582
+ "loss": 1.1015,
583
+ "step": 2050
584
+ },
585
+ {
586
+ "epoch": 3.92,
587
+ "grad_norm": 0.4151917099952698,
588
+ "learning_rate": 1.1544117647058824e-05,
589
+ "loss": 1.0817,
590
+ "step": 2075
591
+ },
592
+ {
593
+ "epoch": 3.97,
594
+ "grad_norm": 0.45207536220550537,
595
+ "learning_rate": 1.1281512605042017e-05,
596
+ "loss": 1.0935,
597
+ "step": 2100
598
+ },
599
+ {
600
+ "epoch": 4.01,
601
+ "grad_norm": 0.43334582448005676,
602
+ "learning_rate": 1.1018907563025212e-05,
603
+ "loss": 1.0843,
604
+ "step": 2125
605
+ },
606
+ {
607
+ "epoch": 4.06,
608
+ "grad_norm": 0.44301116466522217,
609
+ "learning_rate": 1.0756302521008403e-05,
610
+ "loss": 1.0617,
611
+ "step": 2150
612
+ },
613
+ {
614
+ "epoch": 4.11,
615
+ "grad_norm": 0.42584851384162903,
616
+ "learning_rate": 1.0493697478991596e-05,
617
+ "loss": 1.102,
618
+ "step": 2175
619
+ },
620
+ {
621
+ "epoch": 4.15,
622
+ "grad_norm": 0.46070751547813416,
623
+ "learning_rate": 1.0231092436974791e-05,
624
+ "loss": 1.0943,
625
+ "step": 2200
626
+ },
627
+ {
628
+ "epoch": 4.2,
629
+ "grad_norm": 0.43757393956184387,
630
+ "learning_rate": 9.968487394957983e-06,
631
+ "loss": 1.082,
632
+ "step": 2225
633
+ },
634
+ {
635
+ "epoch": 4.25,
636
+ "grad_norm": 0.43552663922309875,
637
+ "learning_rate": 9.705882352941177e-06,
638
+ "loss": 1.1033,
639
+ "step": 2250
640
+ },
641
+ {
642
+ "epoch": 4.3,
643
+ "grad_norm": 0.44868725538253784,
644
+ "learning_rate": 9.44327731092437e-06,
645
+ "loss": 1.0912,
646
+ "step": 2275
647
+ },
648
+ {
649
+ "epoch": 4.34,
650
+ "grad_norm": 0.43542513251304626,
651
+ "learning_rate": 9.180672268907563e-06,
652
+ "loss": 1.1113,
653
+ "step": 2300
654
+ },
655
+ {
656
+ "epoch": 4.39,
657
+ "grad_norm": 0.47481635212898254,
658
+ "learning_rate": 8.918067226890756e-06,
659
+ "loss": 1.0455,
660
+ "step": 2325
661
+ },
662
+ {
663
+ "epoch": 4.44,
664
+ "grad_norm": 0.46137455105781555,
665
+ "learning_rate": 8.65546218487395e-06,
666
+ "loss": 1.0898,
667
+ "step": 2350
668
+ },
669
+ {
670
+ "epoch": 4.49,
671
+ "grad_norm": 0.4473894536495209,
672
+ "learning_rate": 8.392857142857143e-06,
673
+ "loss": 1.0836,
674
+ "step": 2375
675
+ },
676
+ {
677
+ "epoch": 4.53,
678
+ "grad_norm": 0.39784467220306396,
679
+ "learning_rate": 8.130252100840336e-06,
680
+ "loss": 1.0629,
681
+ "step": 2400
682
+ },
683
+ {
684
+ "epoch": 4.58,
685
+ "grad_norm": 0.48481184244155884,
686
+ "learning_rate": 7.86764705882353e-06,
687
+ "loss": 1.1173,
688
+ "step": 2425
689
+ },
690
+ {
691
+ "epoch": 4.63,
692
+ "grad_norm": 0.485196590423584,
693
+ "learning_rate": 7.605042016806723e-06,
694
+ "loss": 1.0673,
695
+ "step": 2450
696
+ },
697
+ {
698
+ "epoch": 4.67,
699
+ "grad_norm": 0.5114961266517639,
700
+ "learning_rate": 7.342436974789916e-06,
701
+ "loss": 1.0877,
702
+ "step": 2475
703
+ },
704
+ {
705
+ "epoch": 4.72,
706
+ "grad_norm": 0.4506637752056122,
707
+ "learning_rate": 7.07983193277311e-06,
708
+ "loss": 1.0995,
709
+ "step": 2500
710
+ },
711
+ {
712
+ "epoch": 4.77,
713
+ "grad_norm": 0.45109784603118896,
714
+ "learning_rate": 6.817226890756303e-06,
715
+ "loss": 1.0819,
716
+ "step": 2525
717
+ },
718
+ {
719
+ "epoch": 4.82,
720
+ "grad_norm": 0.4272564947605133,
721
+ "learning_rate": 6.554621848739496e-06,
722
+ "loss": 1.1109,
723
+ "step": 2550
724
+ },
725
+ {
726
+ "epoch": 4.86,
727
+ "grad_norm": 0.4301404058933258,
728
+ "learning_rate": 6.29201680672269e-06,
729
+ "loss": 1.0738,
730
+ "step": 2575
731
+ },
732
+ {
733
+ "epoch": 4.91,
734
+ "grad_norm": 0.49940961599349976,
735
+ "learning_rate": 6.029411764705883e-06,
736
+ "loss": 1.0865,
737
+ "step": 2600
738
+ },
739
+ {
740
+ "epoch": 4.96,
741
+ "grad_norm": 0.41319113969802856,
742
+ "learning_rate": 5.7773109243697485e-06,
743
+ "loss": 1.0535,
744
+ "step": 2625
745
+ },
746
+ {
747
+ "epoch": 5.0,
748
+ "grad_norm": 0.4326096773147583,
749
+ "learning_rate": 5.5147058823529415e-06,
750
+ "loss": 1.0745,
751
+ "step": 2650
752
+ },
753
+ {
754
+ "epoch": 5.05,
755
+ "grad_norm": 0.4360290765762329,
756
+ "learning_rate": 5.252100840336135e-06,
757
+ "loss": 1.0745,
758
+ "step": 2675
759
+ },
760
+ {
761
+ "epoch": 5.1,
762
+ "grad_norm": 0.42354682087898254,
763
+ "learning_rate": 4.989495798319328e-06,
764
+ "loss": 1.0685,
765
+ "step": 2700
766
+ },
767
+ {
768
+ "epoch": 5.15,
769
+ "grad_norm": 0.49250248074531555,
770
+ "learning_rate": 4.726890756302521e-06,
771
+ "loss": 1.0841,
772
+ "step": 2725
773
+ },
774
+ {
775
+ "epoch": 5.19,
776
+ "grad_norm": 0.4505230784416199,
777
+ "learning_rate": 4.464285714285715e-06,
778
+ "loss": 1.0935,
779
+ "step": 2750
780
+ },
781
+ {
782
+ "epoch": 5.24,
783
+ "grad_norm": 0.41872066259384155,
784
+ "learning_rate": 4.201680672268908e-06,
785
+ "loss": 1.0827,
786
+ "step": 2775
787
+ },
788
+ {
789
+ "epoch": 5.29,
790
+ "grad_norm": 0.45635831356048584,
791
+ "learning_rate": 3.939075630252101e-06,
792
+ "loss": 1.0973,
793
+ "step": 2800
794
+ },
795
+ {
796
+ "epoch": 5.34,
797
+ "grad_norm": 0.49893826246261597,
798
+ "learning_rate": 3.6764705882352942e-06,
799
+ "loss": 1.0859,
800
+ "step": 2825
801
+ },
802
+ {
803
+ "epoch": 5.38,
804
+ "grad_norm": 0.5377572774887085,
805
+ "learning_rate": 3.4138655462184873e-06,
806
+ "loss": 1.088,
807
+ "step": 2850
808
+ },
809
+ {
810
+ "epoch": 5.43,
811
+ "grad_norm": 0.45102909207344055,
812
+ "learning_rate": 3.1512605042016808e-06,
813
+ "loss": 1.0875,
814
+ "step": 2875
815
+ },
816
+ {
817
+ "epoch": 5.48,
818
+ "grad_norm": 0.3922051191329956,
819
+ "learning_rate": 2.8886554621848742e-06,
820
+ "loss": 1.0708,
821
+ "step": 2900
822
+ },
823
+ {
824
+ "epoch": 5.52,
825
+ "grad_norm": 0.4416084289550781,
826
+ "learning_rate": 2.6260504201680673e-06,
827
+ "loss": 1.0816,
828
+ "step": 2925
829
+ },
830
+ {
831
+ "epoch": 5.57,
832
+ "grad_norm": 0.5171985626220703,
833
+ "learning_rate": 2.3634453781512604e-06,
834
+ "loss": 1.0859,
835
+ "step": 2950
836
+ },
837
+ {
838
+ "epoch": 5.62,
839
+ "grad_norm": 0.4239521920681,
840
+ "learning_rate": 2.100840336134454e-06,
841
+ "loss": 1.0387,
842
+ "step": 2975
843
+ },
844
+ {
845
+ "epoch": 5.67,
846
+ "grad_norm": 0.5627429485321045,
847
+ "learning_rate": 1.8382352941176471e-06,
848
+ "loss": 1.0818,
849
+ "step": 3000
850
+ },
851
+ {
852
+ "epoch": 5.71,
853
+ "grad_norm": 0.4605351686477661,
854
+ "learning_rate": 1.5756302521008404e-06,
855
+ "loss": 1.0637,
856
+ "step": 3025
857
+ },
858
+ {
859
+ "epoch": 5.76,
860
+ "grad_norm": 0.40121838450431824,
861
+ "learning_rate": 1.3130252100840336e-06,
862
+ "loss": 1.039,
863
+ "step": 3050
864
+ },
865
+ {
866
+ "epoch": 5.81,
867
+ "grad_norm": 0.45940887928009033,
868
+ "learning_rate": 1.050420168067227e-06,
869
+ "loss": 1.0434,
870
+ "step": 3075
871
+ },
872
+ {
873
+ "epoch": 5.85,
874
+ "grad_norm": 0.4496408998966217,
875
+ "learning_rate": 7.878151260504202e-07,
876
+ "loss": 1.1024,
877
+ "step": 3100
878
+ },
879
+ {
880
+ "epoch": 5.9,
881
+ "grad_norm": 0.4458378553390503,
882
+ "learning_rate": 5.252100840336135e-07,
883
+ "loss": 1.0948,
884
+ "step": 3125
885
+ },
886
+ {
887
+ "epoch": 5.95,
888
+ "grad_norm": 0.49208617210388184,
889
+ "learning_rate": 2.6260504201680673e-07,
890
+ "loss": 1.0673,
891
+ "step": 3150
892
+ }
893
+ ],
894
+ "logging_steps": 25,
895
+ "max_steps": 3174,
896
+ "num_input_tokens_seen": 0,
897
+ "num_train_epochs": 6,
898
+ "save_steps": 500,
899
+ "total_flos": 1.3634839262527488e+16,
900
+ "train_batch_size": 2,
901
+ "trial_name": null,
902
+ "trial_params": null
903
+ }
checkpoint-3174/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:942ab171a1e5a3d05366be3399099d57efe1f4b2e056c134bd4f3f0d9ced48bf
3
+ size 4984
checkpoint-3174/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Mar26_22-16-25_r-jamesb1974-46gb-14tslmif-c1936-q6t3c/events.out.tfevents.1711491386.r-jamesb1974-46gb-14tslmif-c1936-q6t3c.101.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0dffbda1456417ef3a9443efa139d625563629a9147bd7e116a67fba623e603a
3
- size 31989
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8c6c0b1e86cc92b934e23bc1875192860988ed1238d9c7ac957e52db5497709
3
+ size 32343
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ }
12
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
15
+ "clean_up_tokenization_spaces": true,
16
+ "eos_token": "<|endoftext|>",
17
+ "model_max_length": 1024,
18
+ "pad_token": "<|endoftext|>",
19
+ "tokenizer_class": "GPT2Tokenizer",
20
+ "unk_token": "<|endoftext|>"
21
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:942ab171a1e5a3d05366be3399099d57efe1f4b2e056c134bd4f3f0d9ced48bf
3
+ size 4984
training_params.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model": "openai-community/gpt2",
3
+ "project_name": "autotrain-gpt2-large-ep6-generic",
4
+ "data_path": "autotrain-gpt2-large-ep6-generic/autotrain-data",
5
+ "train_split": "train",
6
+ "valid_split": null,
7
+ "add_eos_token": true,
8
+ "block_size": 1024,
9
+ "model_max_length": 2048,
10
+ "padding": "right",
11
+ "trainer": "default",
12
+ "use_flash_attention_2": false,
13
+ "log": "tensorboard",
14
+ "disable_gradient_checkpointing": false,
15
+ "logging_steps": -1,
16
+ "evaluation_strategy": "epoch",
17
+ "save_total_limit": 1,
18
+ "save_strategy": "epoch",
19
+ "auto_find_batch_size": false,
20
+ "mixed_precision": "fp16",
21
+ "lr": 3e-05,
22
+ "epochs": 6,
23
+ "batch_size": 2,
24
+ "warmup_ratio": 0.1,
25
+ "gradient_accumulation": 4,
26
+ "optimizer": "adamw_torch",
27
+ "scheduler": "linear",
28
+ "weight_decay": 0.0,
29
+ "max_grad_norm": 1.0,
30
+ "seed": 42,
31
+ "chat_template": "none",
32
+ "quantization": "int4",
33
+ "target_modules": "all-linear",
34
+ "merge_adapter": false,
35
+ "peft": true,
36
+ "lora_r": 16,
37
+ "lora_alpha": 32,
38
+ "lora_dropout": 0.05,
39
+ "model_ref": null,
40
+ "dpo_beta": 0.1,
41
+ "prompt_text_column": "autotrain_prompt",
42
+ "text_column": "autotrain_text",
43
+ "rejected_text_column": "autotrain_rejected_text",
44
+ "push_to_hub": true,
45
+ "repo_id": "Jamesb1974/autotrain-gpt2-large-ep6-generic",
46
+ "username": "Jamesb1974"
47
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff