tktung commited on
Commit
91fecd8
·
verified ·
1 Parent(s): 345e69d

Upload folder using huggingface_hub

Browse files
Files changed (23) hide show
  1. .gitattributes +1 -0
  2. output_model/irish_llama31_lora_data_v3/checkpoint-3500/README.md +202 -0
  3. output_model/irish_llama31_lora_data_v3/checkpoint-3500/adapter_config.json +34 -0
  4. output_model/irish_llama31_lora_data_v3/checkpoint-3500/adapter_model.bin +3 -0
  5. output_model/irish_llama31_lora_data_v3/checkpoint-3500/latest +1 -0
  6. output_model/irish_llama31_lora_data_v3/checkpoint-3500/pt_peft_model/README.md +202 -0
  7. output_model/irish_llama31_lora_data_v3/checkpoint-3500/pt_peft_model/adapter_config.json +34 -0
  8. output_model/irish_llama31_lora_data_v3/checkpoint-3500/pt_peft_model/adapter_model.bin +3 -0
  9. output_model/irish_llama31_lora_data_v3/checkpoint-3500/rng_state_0.pth +3 -0
  10. output_model/irish_llama31_lora_data_v3/checkpoint-3500/rng_state_1.pth +3 -0
  11. output_model/irish_llama31_lora_data_v3/checkpoint-3500/rng_state_2.pth +3 -0
  12. output_model/irish_llama31_lora_data_v3/checkpoint-3500/rng_state_3.pth +3 -0
  13. output_model/irish_llama31_lora_data_v3/checkpoint-3500/rng_state_4.pth +3 -0
  14. output_model/irish_llama31_lora_data_v3/checkpoint-3500/rng_state_5.pth +3 -0
  15. output_model/irish_llama31_lora_data_v3/checkpoint-3500/rng_state_6.pth +3 -0
  16. output_model/irish_llama31_lora_data_v3/checkpoint-3500/rng_state_7.pth +3 -0
  17. output_model/irish_llama31_lora_data_v3/checkpoint-3500/scheduler.pt +3 -0
  18. output_model/irish_llama31_lora_data_v3/checkpoint-3500/special_tokens_map.json +16 -0
  19. output_model/irish_llama31_lora_data_v3/checkpoint-3500/tokenizer.json +3 -0
  20. output_model/irish_llama31_lora_data_v3/checkpoint-3500/tokenizer_config.json +2085 -0
  21. output_model/irish_llama31_lora_data_v3/checkpoint-3500/trainer_state.json +2490 -0
  22. output_model/irish_llama31_lora_data_v3/checkpoint-3500/training_args.bin +3 -0
  23. output_model/irish_llama31_lora_data_v3/checkpoint-3500/zero_to_fp32.py +592 -0
.gitattributes CHANGED
@@ -95,3 +95,4 @@ output_model/irish_llama31_lora/checkpoint-2/tokenizer.json filter=lfs diff=lfs
95
  output_model/irish_llama31_lora/checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
96
  output_model/irish_llama31_lora_data_v3/checkpoint-3800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
97
  output_model/irish_llama31_lora_data_v3/checkpoint-2300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
95
  output_model/irish_llama31_lora/checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
96
  output_model/irish_llama31_lora_data_v3/checkpoint-3800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
97
  output_model/irish_llama31_lora_data_v3/checkpoint-2300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
98
+ output_model/irish_llama31_lora_data_v3/checkpoint-3500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
output_model/irish_llama31_lora_data_v3/checkpoint-3500/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Meta-Llama-3.1-70B
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 0.7.1
output_model/irish_llama31_lora_data_v3/checkpoint-3500/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Meta-Llama-3.1-70B",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 32.0,
13
+ "lora_dropout": 0.05,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": [
17
+ "embed_tokens",
18
+ "lm_head"
19
+ ],
20
+ "peft_type": "LORA",
21
+ "r": 16,
22
+ "rank_pattern": {},
23
+ "revision": null,
24
+ "target_modules": [
25
+ "k_proj",
26
+ "gate_proj",
27
+ "up_proj",
28
+ "q_proj",
29
+ "v_proj",
30
+ "down_proj",
31
+ "o_proj"
32
+ ],
33
+ "task_type": "CAUSAL_LM"
34
+ }
output_model/irish_llama31_lora_data_v3/checkpoint-3500/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4f5433275f33fcd4d0b2440c72db6191b95acc3ad5ce2a7efec2518dd448b22
3
+ size 9693045296
output_model/irish_llama31_lora_data_v3/checkpoint-3500/latest ADDED
@@ -0,0 +1 @@
 
 
1
+ global_step3500
output_model/irish_llama31_lora_data_v3/checkpoint-3500/pt_peft_model/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Meta-Llama-3.1-70B
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 0.7.1
output_model/irish_llama31_lora_data_v3/checkpoint-3500/pt_peft_model/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Meta-Llama-3.1-70B",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 32.0,
13
+ "lora_dropout": 0.05,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": [
17
+ "embed_tokens",
18
+ "lm_head"
19
+ ],
20
+ "peft_type": "LORA",
21
+ "r": 16,
22
+ "rank_pattern": {},
23
+ "revision": null,
24
+ "target_modules": [
25
+ "v_proj",
26
+ "k_proj",
27
+ "gate_proj",
28
+ "down_proj",
29
+ "up_proj",
30
+ "q_proj",
31
+ "o_proj"
32
+ ],
33
+ "task_type": "CAUSAL_LM"
34
+ }
output_model/irish_llama31_lora_data_v3/checkpoint-3500/pt_peft_model/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48933e39a9395f2e0621e24469adfe8446243f0d04dcac737874ea2f64e001d2
3
+ size 5578892
output_model/irish_llama31_lora_data_v3/checkpoint-3500/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18ff579fa96c45bd168892d69376e4171d20f8ec324ba396377e694751a99d2b
3
+ size 15984
output_model/irish_llama31_lora_data_v3/checkpoint-3500/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5608b1920aef05ecb06e8ba93e58ac1e4a2ee95bb1b32597d002743b0bf5c8a4
3
+ size 15984
output_model/irish_llama31_lora_data_v3/checkpoint-3500/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7b2b8989c92c46c2e24652988b3aa583bdb65ffd92ae24defb80f8c81f41327
3
+ size 15984
output_model/irish_llama31_lora_data_v3/checkpoint-3500/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3f98d726b5d77a24a9f96c1a367f792fe8073b1963f1a3624bc1ad34ddf9b76
3
+ size 15984
output_model/irish_llama31_lora_data_v3/checkpoint-3500/rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47898862e3d7c09d7fc84727e295d69649a56cac0acd7e87ad3da79694fd91c7
3
+ size 15984
output_model/irish_llama31_lora_data_v3/checkpoint-3500/rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa1b7bd28aa3dbf3b7736009ddb4a1b7de5f72a387d759d9d07fd149819a2d9f
3
+ size 15984
output_model/irish_llama31_lora_data_v3/checkpoint-3500/rng_state_6.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:911bea78654c5c51df576fe1aeee853285d404a559c27ef5ab0805f8d5842c7a
3
+ size 15984
output_model/irish_llama31_lora_data_v3/checkpoint-3500/rng_state_7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8084c71d3158618156860d767d196797da6f9e442f9315d13646fa3c06b7d683
3
+ size 15984
output_model/irish_llama31_lora_data_v3/checkpoint-3500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c892636d4dd4c4c87918ef6f998a68f2a0cf5a89d2efaf8921a29f311fbf3d6
3
+ size 1064
output_model/irish_llama31_lora_data_v3/checkpoint-3500/special_tokens_map.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|end_of_text|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ }
16
+ }
output_model/irish_llama31_lora_data_v3/checkpoint-3500/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b0cea782aa577bc7b5c6bab9e1299e377daf2dd787f18568a82b024edbbcbc9
3
+ size 17745270
output_model/irish_llama31_lora_data_v3/checkpoint-3500/tokenizer_config.json ADDED
@@ -0,0 +1,2085 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "134999": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "135000": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "135001": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "135002": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "135003": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "135004": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "135005": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "135006": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "135007": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "135008": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "135009": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "135010": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "135011": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "135012": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "135013": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "135014": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "135015": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "135016": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "135017": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "135018": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "135019": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "135020": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "135021": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "135022": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "135023": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "135024": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "135025": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "135026": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "135027": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "135028": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "135029": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "135030": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "135031": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "135032": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "135033": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "135034": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "135035": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "135036": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "135037": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "135038": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "135039": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "135040": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "135041": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "135042": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "135043": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "135044": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "135045": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "135046": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "135047": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "135048": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "135049": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "135050": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "135051": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "135052": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "135053": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "135054": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "135055": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "135056": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "135057": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "135058": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "135059": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "135060": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "135061": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "135062": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "135063": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "135064": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "135065": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "135066": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "135067": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "135068": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "135069": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "135070": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "135071": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "135072": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "135073": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "135074": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "135075": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "135076": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "135077": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "135078": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "135079": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "135080": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "135081": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "135082": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "135083": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "135084": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "135085": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "135086": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "135087": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "135088": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "135089": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "135090": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "135091": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "135092": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "135093": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "135094": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "135095": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "135096": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "135097": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "135098": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "135099": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "135100": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "135101": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "135102": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "135103": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "135104": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "135105": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "135106": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "135107": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "135108": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "135109": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "135110": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "135111": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "135112": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "135113": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "135114": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "135115": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "135116": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "135117": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "135118": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "135119": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "135120": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "135121": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "135122": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "135123": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "135124": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "135125": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "135126": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "135127": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "135128": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "135129": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "135130": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "135131": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "135132": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "135133": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "135134": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "135135": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "135136": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "135137": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "135138": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "135139": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "135140": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "135141": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "135142": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "135143": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "135144": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "135145": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "135146": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "135147": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "135148": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "135149": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "135150": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "135151": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "135152": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "135153": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "135154": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "135155": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "135156": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "135157": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "135158": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "135159": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "135160": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "135161": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "135162": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "135163": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "135164": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "135165": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "135166": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "135167": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "135168": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "135169": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "135170": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "135171": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "135172": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "135173": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "135174": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "135175": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "135176": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "135177": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "135178": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "135179": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "135180": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "135181": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "135182": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "135183": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "135184": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "135185": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "135186": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "135187": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "135188": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "135189": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "135190": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "135191": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "135192": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "135193": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "135194": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "135195": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "135196": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "135197": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "135198": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "135199": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "135200": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "135201": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "135202": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "135203": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "135204": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "135205": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "135206": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "135207": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "135208": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "135209": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "135210": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "135211": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "135212": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "135213": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "135214": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "135215": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "135216": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "135217": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "135218": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "135219": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "135220": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "135221": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "135222": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "135223": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "135224": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "135225": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "135226": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "135227": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "135228": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "135229": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "135230": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "135231": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "135232": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "135233": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "135234": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "135235": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "135236": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "135237": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "135238": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "135239": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "135240": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "135241": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "135242": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "135243": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "135244": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "135245": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "135246": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "135247": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "135248": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "135249": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "135250": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "135251": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "135252": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "135253": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "135254": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ },
2051
+ "135255": {
2052
+ "content": "<|reserved_special_token_248|>",
2053
+ "lstrip": false,
2054
+ "normalized": false,
2055
+ "rstrip": false,
2056
+ "single_word": false,
2057
+ "special": true
2058
+ },
2059
+ "135256": {
2060
+ "content": "<|reserved_special_token_249|>",
2061
+ "lstrip": false,
2062
+ "normalized": false,
2063
+ "rstrip": false,
2064
+ "single_word": false,
2065
+ "special": true
2066
+ },
2067
+ "135257": {
2068
+ "content": "<|reserved_special_token_250|>",
2069
+ "lstrip": false,
2070
+ "normalized": false,
2071
+ "rstrip": false,
2072
+ "single_word": false,
2073
+ "special": true
2074
+ }
2075
+ },
2076
+ "bos_token": "<|begin_of_text|>",
2077
+ "clean_up_tokenization_spaces": true,
2078
+ "eos_token": "<|end_of_text|>",
2079
+ "model_input_names": [
2080
+ "input_ids",
2081
+ "attention_mask"
2082
+ ],
2083
+ "model_max_length": 1000000000000000019884624838656,
2084
+ "tokenizer_class": "PreTrainedTokenizerFast"
2085
+ }
output_model/irish_llama31_lora_data_v3/checkpoint-3500/trainer_state.json ADDED
@@ -0,0 +1,2490 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.6344755970924196,
5
+ "eval_steps": 500,
6
+ "global_step": 3500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0010384215991692627,
13
+ "grad_norm": 6771.571161850106,
14
+ "learning_rate": 1.0362694300518136e-06,
15
+ "loss": 5.4426,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.010384215991692628,
20
+ "grad_norm": 134.95297213288782,
21
+ "learning_rate": 1.0362694300518135e-05,
22
+ "loss": 6.8521,
23
+ "step": 10
24
+ },
25
+ {
26
+ "epoch": 0.020768431983385256,
27
+ "grad_norm": 3.058694616142935,
28
+ "learning_rate": 2.072538860103627e-05,
29
+ "loss": 7.2002,
30
+ "step": 20
31
+ },
32
+ {
33
+ "epoch": 0.03115264797507788,
34
+ "grad_norm": 12.52029724158249,
35
+ "learning_rate": 3.108808290155441e-05,
36
+ "loss": 6.1425,
37
+ "step": 30
38
+ },
39
+ {
40
+ "epoch": 0.04153686396677051,
41
+ "grad_norm": 3.3322667958765497,
42
+ "learning_rate": 4.145077720207254e-05,
43
+ "loss": 5.3216,
44
+ "step": 40
45
+ },
46
+ {
47
+ "epoch": 0.05192107995846314,
48
+ "grad_norm": 2.6283588718132282,
49
+ "learning_rate": 5.1813471502590674e-05,
50
+ "loss": 4.8108,
51
+ "step": 50
52
+ },
53
+ {
54
+ "epoch": 0.06230529595015576,
55
+ "grad_norm": 0.8013888775211938,
56
+ "learning_rate": 6.217616580310881e-05,
57
+ "loss": 4.3835,
58
+ "step": 60
59
+ },
60
+ {
61
+ "epoch": 0.07268951194184839,
62
+ "grad_norm": 1.0574118008818925,
63
+ "learning_rate": 7.253886010362695e-05,
64
+ "loss": 3.8619,
65
+ "step": 70
66
+ },
67
+ {
68
+ "epoch": 0.08307372793354102,
69
+ "grad_norm": 2.0171663763357093,
70
+ "learning_rate": 8.290155440414508e-05,
71
+ "loss": 3.3499,
72
+ "step": 80
73
+ },
74
+ {
75
+ "epoch": 0.09345794392523364,
76
+ "grad_norm": 0.6990198459836748,
77
+ "learning_rate": 9.326424870466322e-05,
78
+ "loss": 2.9807,
79
+ "step": 90
80
+ },
81
+ {
82
+ "epoch": 0.10384215991692627,
83
+ "grad_norm": 0.7067077697602618,
84
+ "learning_rate": 0.00010362694300518135,
85
+ "loss": 2.7515,
86
+ "step": 100
87
+ },
88
+ {
89
+ "epoch": 0.1142263759086189,
90
+ "grad_norm": 0.4987064556722102,
91
+ "learning_rate": 0.00011398963730569949,
92
+ "loss": 2.634,
93
+ "step": 110
94
+ },
95
+ {
96
+ "epoch": 0.12461059190031153,
97
+ "grad_norm": 0.13698892464952092,
98
+ "learning_rate": 0.00012435233160621763,
99
+ "loss": 2.5434,
100
+ "step": 120
101
+ },
102
+ {
103
+ "epoch": 0.13499480789200416,
104
+ "grad_norm": 0.16969591221761152,
105
+ "learning_rate": 0.00013471502590673575,
106
+ "loss": 2.4856,
107
+ "step": 130
108
+ },
109
+ {
110
+ "epoch": 0.14537902388369678,
111
+ "grad_norm": 0.13686098465733426,
112
+ "learning_rate": 0.0001450777202072539,
113
+ "loss": 2.4712,
114
+ "step": 140
115
+ },
116
+ {
117
+ "epoch": 0.1557632398753894,
118
+ "grad_norm": 0.30527427609768404,
119
+ "learning_rate": 0.00015544041450777204,
120
+ "loss": 2.4517,
121
+ "step": 150
122
+ },
123
+ {
124
+ "epoch": 0.16614745586708204,
125
+ "grad_norm": 0.2886820686822109,
126
+ "learning_rate": 0.00016580310880829016,
127
+ "loss": 2.4709,
128
+ "step": 160
129
+ },
130
+ {
131
+ "epoch": 0.17653167185877466,
132
+ "grad_norm": 0.3511496450922119,
133
+ "learning_rate": 0.00017616580310880832,
134
+ "loss": 2.4179,
135
+ "step": 170
136
+ },
137
+ {
138
+ "epoch": 0.18691588785046728,
139
+ "grad_norm": 0.4779532261123508,
140
+ "learning_rate": 0.00018652849740932644,
141
+ "loss": 2.4067,
142
+ "step": 180
143
+ },
144
+ {
145
+ "epoch": 0.19730010384215993,
146
+ "grad_norm": 0.37119087152961927,
147
+ "learning_rate": 0.00019689119170984457,
148
+ "loss": 2.37,
149
+ "step": 190
150
+ },
151
+ {
152
+ "epoch": 0.20768431983385255,
153
+ "grad_norm": 0.17615185452571058,
154
+ "learning_rate": 0.0001999981939086881,
155
+ "loss": 2.3294,
156
+ "step": 200
157
+ },
158
+ {
159
+ "epoch": 0.21806853582554517,
160
+ "grad_norm": 0.29896379021683067,
161
+ "learning_rate": 0.00019998934790421263,
162
+ "loss": 2.3401,
163
+ "step": 210
164
+ },
165
+ {
166
+ "epoch": 0.2284527518172378,
167
+ "grad_norm": 0.2611590278836532,
168
+ "learning_rate": 0.00019997313090680896,
169
+ "loss": 2.3323,
170
+ "step": 220
171
+ },
172
+ {
173
+ "epoch": 0.23883696780893043,
174
+ "grad_norm": 0.1988949200713875,
175
+ "learning_rate": 0.00019994954411195817,
176
+ "loss": 2.3081,
177
+ "step": 230
178
+ },
179
+ {
180
+ "epoch": 0.24922118380062305,
181
+ "grad_norm": 0.07009483129761722,
182
+ "learning_rate": 0.00019991858925842647,
183
+ "loss": 2.2845,
184
+ "step": 240
185
+ },
186
+ {
187
+ "epoch": 0.25960539979231567,
188
+ "grad_norm": 0.587558081982074,
189
+ "learning_rate": 0.00019988026862813695,
190
+ "loss": 2.2872,
191
+ "step": 250
192
+ },
193
+ {
194
+ "epoch": 0.2699896157840083,
195
+ "grad_norm": 0.1768197009244115,
196
+ "learning_rate": 0.00019983458504600155,
197
+ "loss": 2.271,
198
+ "step": 260
199
+ },
200
+ {
201
+ "epoch": 0.2803738317757009,
202
+ "grad_norm": 0.09112598907067371,
203
+ "learning_rate": 0.00019978154187971255,
204
+ "loss": 2.2764,
205
+ "step": 270
206
+ },
207
+ {
208
+ "epoch": 0.29075804776739356,
209
+ "grad_norm": 0.08201166327834156,
210
+ "learning_rate": 0.0001997211430394945,
211
+ "loss": 2.2597,
212
+ "step": 280
213
+ },
214
+ {
215
+ "epoch": 0.3011422637590862,
216
+ "grad_norm": 0.3272782822467744,
217
+ "learning_rate": 0.00019965339297781597,
218
+ "loss": 2.2468,
219
+ "step": 290
220
+ },
221
+ {
222
+ "epoch": 0.3115264797507788,
223
+ "grad_norm": 0.25259363834162013,
224
+ "learning_rate": 0.00019957829668906124,
225
+ "loss": 2.236,
226
+ "step": 300
227
+ },
228
+ {
229
+ "epoch": 0.32191069574247144,
230
+ "grad_norm": 0.0820417936678913,
231
+ "learning_rate": 0.00019949585970916201,
232
+ "loss": 2.2183,
233
+ "step": 310
234
+ },
235
+ {
236
+ "epoch": 0.3322949117341641,
237
+ "grad_norm": 0.06159098829842787,
238
+ "learning_rate": 0.0001994060881151897,
239
+ "loss": 2.2406,
240
+ "step": 320
241
+ },
242
+ {
243
+ "epoch": 0.3426791277258567,
244
+ "grad_norm": 0.22462601807341828,
245
+ "learning_rate": 0.00019930898852490704,
246
+ "loss": 2.2222,
247
+ "step": 330
248
+ },
249
+ {
250
+ "epoch": 0.3530633437175493,
251
+ "grad_norm": 0.15419608457833653,
252
+ "learning_rate": 0.00019920456809628047,
253
+ "loss": 2.2197,
254
+ "step": 340
255
+ },
256
+ {
257
+ "epoch": 0.363447559709242,
258
+ "grad_norm": 0.3007251018284251,
259
+ "learning_rate": 0.00019909283452695226,
260
+ "loss": 2.2022,
261
+ "step": 350
262
+ },
263
+ {
264
+ "epoch": 0.37383177570093457,
265
+ "grad_norm": 0.24216948719103942,
266
+ "learning_rate": 0.0001989737960536734,
267
+ "loss": 2.2318,
268
+ "step": 360
269
+ },
270
+ {
271
+ "epoch": 0.3842159916926272,
272
+ "grad_norm": 0.17790782764873742,
273
+ "learning_rate": 0.00019884746145169602,
274
+ "loss": 2.2222,
275
+ "step": 370
276
+ },
277
+ {
278
+ "epoch": 0.39460020768431986,
279
+ "grad_norm": 0.08320316719895847,
280
+ "learning_rate": 0.00019871384003412678,
281
+ "loss": 2.1953,
282
+ "step": 380
283
+ },
284
+ {
285
+ "epoch": 0.40498442367601245,
286
+ "grad_norm": 0.06166544865553665,
287
+ "learning_rate": 0.00019857294165124016,
288
+ "loss": 2.187,
289
+ "step": 390
290
+ },
291
+ {
292
+ "epoch": 0.4153686396677051,
293
+ "grad_norm": 0.08481193224685966,
294
+ "learning_rate": 0.0001984247766897524,
295
+ "loss": 2.1625,
296
+ "step": 400
297
+ },
298
+ {
299
+ "epoch": 0.4257528556593977,
300
+ "grad_norm": 0.3884869427874005,
301
+ "learning_rate": 0.0001982693560720558,
302
+ "loss": 2.179,
303
+ "step": 410
304
+ },
305
+ {
306
+ "epoch": 0.43613707165109034,
307
+ "grad_norm": 0.052170618747599616,
308
+ "learning_rate": 0.00019810669125541354,
309
+ "loss": 2.1784,
310
+ "step": 420
311
+ },
312
+ {
313
+ "epoch": 0.446521287642783,
314
+ "grad_norm": 0.05280080117280797,
315
+ "learning_rate": 0.00019793679423111508,
316
+ "loss": 2.1707,
317
+ "step": 430
318
+ },
319
+ {
320
+ "epoch": 0.4569055036344756,
321
+ "grad_norm": 0.05305676460778228,
322
+ "learning_rate": 0.00019775967752359218,
323
+ "loss": 2.156,
324
+ "step": 440
325
+ },
326
+ {
327
+ "epoch": 0.4672897196261682,
328
+ "grad_norm": 0.05341937300389739,
329
+ "learning_rate": 0.0001975753541894956,
330
+ "loss": 2.1583,
331
+ "step": 450
332
+ },
333
+ {
334
+ "epoch": 0.47767393561786087,
335
+ "grad_norm": 0.05004903746770481,
336
+ "learning_rate": 0.00019738383781673272,
337
+ "loss": 2.1503,
338
+ "step": 460
339
+ },
340
+ {
341
+ "epoch": 0.48805815160955346,
342
+ "grad_norm": 0.07162193094476302,
343
+ "learning_rate": 0.00019718514252346566,
344
+ "loss": 2.1648,
345
+ "step": 470
346
+ },
347
+ {
348
+ "epoch": 0.4984423676012461,
349
+ "grad_norm": 0.05394389394777499,
350
+ "learning_rate": 0.00019697928295707068,
351
+ "loss": 2.1321,
352
+ "step": 480
353
+ },
354
+ {
355
+ "epoch": 0.5088265835929388,
356
+ "grad_norm": 0.08936854303317211,
357
+ "learning_rate": 0.00019676627429305842,
358
+ "loss": 2.1405,
359
+ "step": 490
360
+ },
361
+ {
362
+ "epoch": 0.5192107995846313,
363
+ "grad_norm": 0.07230430933700419,
364
+ "learning_rate": 0.00019654613223395507,
365
+ "loss": 2.1324,
366
+ "step": 500
367
+ },
368
+ {
369
+ "epoch": 0.5295950155763239,
370
+ "grad_norm": 0.05681386302660038,
371
+ "learning_rate": 0.0001963188730081449,
372
+ "loss": 2.131,
373
+ "step": 510
374
+ },
375
+ {
376
+ "epoch": 0.5399792315680166,
377
+ "grad_norm": 0.07934642497981438,
378
+ "learning_rate": 0.0001960845133686739,
379
+ "loss": 2.1362,
380
+ "step": 520
381
+ },
382
+ {
383
+ "epoch": 0.5503634475597092,
384
+ "grad_norm": 0.1367984267080894,
385
+ "learning_rate": 0.0001958430705920149,
386
+ "loss": 2.1297,
387
+ "step": 530
388
+ },
389
+ {
390
+ "epoch": 0.5607476635514018,
391
+ "grad_norm": 0.10004829492236059,
392
+ "learning_rate": 0.00019559456247679374,
393
+ "loss": 2.1152,
394
+ "step": 540
395
+ },
396
+ {
397
+ "epoch": 0.5711318795430945,
398
+ "grad_norm": 0.09395290807999984,
399
+ "learning_rate": 0.00019533900734247742,
400
+ "loss": 2.12,
401
+ "step": 550
402
+ },
403
+ {
404
+ "epoch": 0.5815160955347871,
405
+ "grad_norm": 0.07904364973698164,
406
+ "learning_rate": 0.00019507642402802363,
407
+ "loss": 2.1194,
408
+ "step": 560
409
+ },
410
+ {
411
+ "epoch": 0.5919003115264797,
412
+ "grad_norm": 0.06473337281519655,
413
+ "learning_rate": 0.00019480683189049183,
414
+ "loss": 2.1278,
415
+ "step": 570
416
+ },
417
+ {
418
+ "epoch": 0.6022845275181724,
419
+ "grad_norm": 0.06164133227719758,
420
+ "learning_rate": 0.00019453025080361634,
421
+ "loss": 2.1153,
422
+ "step": 580
423
+ },
424
+ {
425
+ "epoch": 0.612668743509865,
426
+ "grad_norm": 0.05375772302542781,
427
+ "learning_rate": 0.00019424670115634137,
428
+ "loss": 2.114,
429
+ "step": 590
430
+ },
431
+ {
432
+ "epoch": 0.6230529595015576,
433
+ "grad_norm": 0.10764963107530885,
434
+ "learning_rate": 0.00019395620385131797,
435
+ "loss": 2.1111,
436
+ "step": 600
437
+ },
438
+ {
439
+ "epoch": 0.6334371754932503,
440
+ "grad_norm": 0.24686654172966374,
441
+ "learning_rate": 0.00019365878030336306,
442
+ "loss": 2.1064,
443
+ "step": 610
444
+ },
445
+ {
446
+ "epoch": 0.6438213914849429,
447
+ "grad_norm": 0.0633309050294984,
448
+ "learning_rate": 0.00019335445243788083,
449
+ "loss": 2.1058,
450
+ "step": 620
451
+ },
452
+ {
453
+ "epoch": 0.6542056074766355,
454
+ "grad_norm": 0.09426362680144383,
455
+ "learning_rate": 0.00019304324268924647,
456
+ "loss": 2.1071,
457
+ "step": 630
458
+ },
459
+ {
460
+ "epoch": 0.6645898234683282,
461
+ "grad_norm": 0.052870741886339216,
462
+ "learning_rate": 0.00019272517399915233,
463
+ "loss": 2.105,
464
+ "step": 640
465
+ },
466
+ {
467
+ "epoch": 0.6749740394600208,
468
+ "grad_norm": 0.14316500758422496,
469
+ "learning_rate": 0.00019240026981491665,
470
+ "loss": 2.0969,
471
+ "step": 650
472
+ },
473
+ {
474
+ "epoch": 0.6853582554517134,
475
+ "grad_norm": 0.2964095809138048,
476
+ "learning_rate": 0.00019206855408775522,
477
+ "loss": 2.0961,
478
+ "step": 660
479
+ },
480
+ {
481
+ "epoch": 0.6957424714434061,
482
+ "grad_norm": 0.07846897219554658,
483
+ "learning_rate": 0.00019173005127101563,
484
+ "loss": 2.1082,
485
+ "step": 670
486
+ },
487
+ {
488
+ "epoch": 0.7061266874350987,
489
+ "grad_norm": 0.10216962018480472,
490
+ "learning_rate": 0.0001913847863183746,
491
+ "loss": 2.1099,
492
+ "step": 680
493
+ },
494
+ {
495
+ "epoch": 0.7165109034267912,
496
+ "grad_norm": 0.12374153163020074,
497
+ "learning_rate": 0.0001910327846819986,
498
+ "loss": 2.0939,
499
+ "step": 690
500
+ },
501
+ {
502
+ "epoch": 0.726895119418484,
503
+ "grad_norm": 0.18394864053200513,
504
+ "learning_rate": 0.00019067407231066743,
505
+ "loss": 2.0941,
506
+ "step": 700
507
+ },
508
+ {
509
+ "epoch": 0.7372793354101765,
510
+ "grad_norm": 0.06892520851876649,
511
+ "learning_rate": 0.00019030867564786142,
512
+ "loss": 2.0981,
513
+ "step": 710
514
+ },
515
+ {
516
+ "epoch": 0.7476635514018691,
517
+ "grad_norm": 0.05213422027835434,
518
+ "learning_rate": 0.000189936621629812,
519
+ "loss": 2.0787,
520
+ "step": 720
521
+ },
522
+ {
523
+ "epoch": 0.7580477673935618,
524
+ "grad_norm": 0.05301235146862068,
525
+ "learning_rate": 0.0001895579376835161,
526
+ "loss": 2.0855,
527
+ "step": 730
528
+ },
529
+ {
530
+ "epoch": 0.7684319833852544,
531
+ "grad_norm": 0.05645359334954648,
532
+ "learning_rate": 0.00018917265172471422,
533
+ "loss": 2.0765,
534
+ "step": 740
535
+ },
536
+ {
537
+ "epoch": 0.778816199376947,
538
+ "grad_norm": 0.06749830507097539,
539
+ "learning_rate": 0.00018878079215583257,
540
+ "loss": 2.0776,
541
+ "step": 750
542
+ },
543
+ {
544
+ "epoch": 0.7892004153686397,
545
+ "grad_norm": 0.050248851221657065,
546
+ "learning_rate": 0.00018838238786388935,
547
+ "loss": 2.083,
548
+ "step": 760
549
+ },
550
+ {
551
+ "epoch": 0.7995846313603323,
552
+ "grad_norm": 0.10481035510821658,
553
+ "learning_rate": 0.0001879774682183652,
554
+ "loss": 2.088,
555
+ "step": 770
556
+ },
557
+ {
558
+ "epoch": 0.8099688473520249,
559
+ "grad_norm": 0.11988320084276193,
560
+ "learning_rate": 0.00018756606306903826,
561
+ "loss": 2.0922,
562
+ "step": 780
563
+ },
564
+ {
565
+ "epoch": 0.8203530633437176,
566
+ "grad_norm": 0.07484519561394828,
567
+ "learning_rate": 0.00018714820274378342,
568
+ "loss": 2.0714,
569
+ "step": 790
570
+ },
571
+ {
572
+ "epoch": 0.8307372793354102,
573
+ "grad_norm": 0.18409258460597286,
574
+ "learning_rate": 0.00018672391804633702,
575
+ "loss": 2.0776,
576
+ "step": 800
577
+ },
578
+ {
579
+ "epoch": 0.8411214953271028,
580
+ "grad_norm": 0.055573940520536255,
581
+ "learning_rate": 0.0001862932402540258,
582
+ "loss": 2.0797,
583
+ "step": 810
584
+ },
585
+ {
586
+ "epoch": 0.8515057113187954,
587
+ "grad_norm": 0.09962682477657142,
588
+ "learning_rate": 0.00018585620111546126,
589
+ "loss": 2.0744,
590
+ "step": 820
591
+ },
592
+ {
593
+ "epoch": 0.8618899273104881,
594
+ "grad_norm": 0.053139827741639216,
595
+ "learning_rate": 0.00018541283284819919,
596
+ "loss": 2.072,
597
+ "step": 830
598
+ },
599
+ {
600
+ "epoch": 0.8722741433021807,
601
+ "grad_norm": 0.05840277743400175,
602
+ "learning_rate": 0.00018496316813636484,
603
+ "loss": 2.0732,
604
+ "step": 840
605
+ },
606
+ {
607
+ "epoch": 0.8826583592938733,
608
+ "grad_norm": 0.581822044101678,
609
+ "learning_rate": 0.00018450724012824326,
610
+ "loss": 2.0707,
611
+ "step": 850
612
+ },
613
+ {
614
+ "epoch": 0.893042575285566,
615
+ "grad_norm": 0.05987679677422036,
616
+ "learning_rate": 0.00018404508243383586,
617
+ "loss": 2.0632,
618
+ "step": 860
619
+ },
620
+ {
621
+ "epoch": 0.9034267912772586,
622
+ "grad_norm": 0.1044690605667318,
623
+ "learning_rate": 0.00018357672912238271,
624
+ "loss": 2.072,
625
+ "step": 870
626
+ },
627
+ {
628
+ "epoch": 0.9138110072689511,
629
+ "grad_norm": 0.11892437852447918,
630
+ "learning_rate": 0.00018310221471985104,
631
+ "loss": 2.0742,
632
+ "step": 880
633
+ },
634
+ {
635
+ "epoch": 0.9241952232606438,
636
+ "grad_norm": 0.07466042691817742,
637
+ "learning_rate": 0.00018262157420638995,
638
+ "loss": 2.0513,
639
+ "step": 890
640
+ },
641
+ {
642
+ "epoch": 0.9345794392523364,
643
+ "grad_norm": 0.06930392829368234,
644
+ "learning_rate": 0.000182134843013752,
645
+ "loss": 2.0661,
646
+ "step": 900
647
+ },
648
+ {
649
+ "epoch": 0.944963655244029,
650
+ "grad_norm": 0.12083347867951476,
651
+ "learning_rate": 0.000181642057022681,
652
+ "loss": 2.0488,
653
+ "step": 910
654
+ },
655
+ {
656
+ "epoch": 0.9553478712357217,
657
+ "grad_norm": 0.06969499634828284,
658
+ "learning_rate": 0.00018114325256026706,
659
+ "loss": 2.0553,
660
+ "step": 920
661
+ },
662
+ {
663
+ "epoch": 0.9657320872274143,
664
+ "grad_norm": 0.10575009279466846,
665
+ "learning_rate": 0.00018063846639726873,
666
+ "loss": 2.0479,
667
+ "step": 930
668
+ },
669
+ {
670
+ "epoch": 0.9761163032191069,
671
+ "grad_norm": 0.08447424385475227,
672
+ "learning_rate": 0.00018012773574540222,
673
+ "loss": 2.0556,
674
+ "step": 940
675
+ },
676
+ {
677
+ "epoch": 0.9865005192107996,
678
+ "grad_norm": 0.0732017373601837,
679
+ "learning_rate": 0.00017961109825459826,
680
+ "loss": 2.0433,
681
+ "step": 950
682
+ },
683
+ {
684
+ "epoch": 0.9968847352024922,
685
+ "grad_norm": 0.051944546511144864,
686
+ "learning_rate": 0.00017908859201022664,
687
+ "loss": 2.0529,
688
+ "step": 960
689
+ },
690
+ {
691
+ "epoch": 1.0072689511941848,
692
+ "grad_norm": 0.07890230560830609,
693
+ "learning_rate": 0.00017856025553028869,
694
+ "loss": 2.0094,
695
+ "step": 970
696
+ },
697
+ {
698
+ "epoch": 1.0176531671858775,
699
+ "grad_norm": 0.07917635819389922,
700
+ "learning_rate": 0.00017802612776257766,
701
+ "loss": 2.0014,
702
+ "step": 980
703
+ },
704
+ {
705
+ "epoch": 1.02803738317757,
706
+ "grad_norm": 0.06549191362732582,
707
+ "learning_rate": 0.00017748624808180784,
708
+ "loss": 1.9939,
709
+ "step": 990
710
+ },
711
+ {
712
+ "epoch": 1.0384215991692627,
713
+ "grad_norm": 0.04970222339349025,
714
+ "learning_rate": 0.0001769406562867117,
715
+ "loss": 1.9901,
716
+ "step": 1000
717
+ },
718
+ {
719
+ "epoch": 1.0488058151609554,
720
+ "grad_norm": 0.06812235750532956,
721
+ "learning_rate": 0.0001763893925971061,
722
+ "loss": 1.9881,
723
+ "step": 1010
724
+ },
725
+ {
726
+ "epoch": 1.0591900311526479,
727
+ "grad_norm": 0.1204567699128316,
728
+ "learning_rate": 0.0001758324976509275,
729
+ "loss": 2.0001,
730
+ "step": 1020
731
+ },
732
+ {
733
+ "epoch": 1.0695742471443406,
734
+ "grad_norm": 0.08131968313793256,
735
+ "learning_rate": 0.0001752700125012359,
736
+ "loss": 2.0107,
737
+ "step": 1030
738
+ },
739
+ {
740
+ "epoch": 1.0799584631360333,
741
+ "grad_norm": 0.06731565902451081,
742
+ "learning_rate": 0.00017470197861318886,
743
+ "loss": 1.9986,
744
+ "step": 1040
745
+ },
746
+ {
747
+ "epoch": 1.0903426791277258,
748
+ "grad_norm": 0.0964919492706108,
749
+ "learning_rate": 0.0001741284378609846,
750
+ "loss": 1.9999,
751
+ "step": 1050
752
+ },
753
+ {
754
+ "epoch": 1.1007268951194185,
755
+ "grad_norm": 0.056870419817597724,
756
+ "learning_rate": 0.00017354943252477508,
757
+ "loss": 2.0042,
758
+ "step": 1060
759
+ },
760
+ {
761
+ "epoch": 1.1111111111111112,
762
+ "grad_norm": 0.06472268594817922,
763
+ "learning_rate": 0.00017296500528754936,
764
+ "loss": 1.9871,
765
+ "step": 1070
766
+ },
767
+ {
768
+ "epoch": 1.1214953271028036,
769
+ "grad_norm": 0.07542864095494253,
770
+ "learning_rate": 0.00017237519923198695,
771
+ "loss": 1.9915,
772
+ "step": 1080
773
+ },
774
+ {
775
+ "epoch": 1.1318795430944963,
776
+ "grad_norm": 0.04812576351783156,
777
+ "learning_rate": 0.00017178005783728196,
778
+ "loss": 1.9805,
779
+ "step": 1090
780
+ },
781
+ {
782
+ "epoch": 1.142263759086189,
783
+ "grad_norm": 0.12142040432834711,
784
+ "learning_rate": 0.00017117962497593782,
785
+ "loss": 1.9882,
786
+ "step": 1100
787
+ },
788
+ {
789
+ "epoch": 1.1526479750778815,
790
+ "grad_norm": 0.04906623480637564,
791
+ "learning_rate": 0.00017057394491053324,
792
+ "loss": 1.9866,
793
+ "step": 1110
794
+ },
795
+ {
796
+ "epoch": 1.1630321910695742,
797
+ "grad_norm": 0.27533084139310077,
798
+ "learning_rate": 0.00016996306229045898,
799
+ "loss": 1.9941,
800
+ "step": 1120
801
+ },
802
+ {
803
+ "epoch": 1.173416407061267,
804
+ "grad_norm": 0.06234200258542851,
805
+ "learning_rate": 0.00016934702214862682,
806
+ "loss": 2.0031,
807
+ "step": 1130
808
+ },
809
+ {
810
+ "epoch": 1.1838006230529594,
811
+ "grad_norm": 0.036960896106862894,
812
+ "learning_rate": 0.00016872586989814944,
813
+ "loss": 1.9945,
814
+ "step": 1140
815
+ },
816
+ {
817
+ "epoch": 1.1941848390446521,
818
+ "grad_norm": 0.07454553301824038,
819
+ "learning_rate": 0.00016809965132899297,
820
+ "loss": 1.9913,
821
+ "step": 1150
822
+ },
823
+ {
824
+ "epoch": 1.2045690550363448,
825
+ "grad_norm": 0.07379717367270512,
826
+ "learning_rate": 0.0001674684126046011,
827
+ "loss": 1.9871,
828
+ "step": 1160
829
+ },
830
+ {
831
+ "epoch": 1.2149532710280373,
832
+ "grad_norm": 0.05170562425237877,
833
+ "learning_rate": 0.0001668322002584925,
834
+ "loss": 1.9781,
835
+ "step": 1170
836
+ },
837
+ {
838
+ "epoch": 1.22533748701973,
839
+ "grad_norm": 0.04384184285858784,
840
+ "learning_rate": 0.00016619106119082993,
841
+ "loss": 1.98,
842
+ "step": 1180
843
+ },
844
+ {
845
+ "epoch": 1.2357217030114227,
846
+ "grad_norm": 0.06140783401016278,
847
+ "learning_rate": 0.00016554504266496337,
848
+ "loss": 1.9868,
849
+ "step": 1190
850
+ },
851
+ {
852
+ "epoch": 1.2461059190031152,
853
+ "grad_norm": 0.08234898872196791,
854
+ "learning_rate": 0.00016489419230394548,
855
+ "loss": 1.9881,
856
+ "step": 1200
857
+ },
858
+ {
859
+ "epoch": 1.2564901349948079,
860
+ "grad_norm": 0.07064443953162482,
861
+ "learning_rate": 0.00016423855808702116,
862
+ "loss": 1.9824,
863
+ "step": 1210
864
+ },
865
+ {
866
+ "epoch": 1.2668743509865006,
867
+ "grad_norm": 0.06404791599092167,
868
+ "learning_rate": 0.00016357818834609046,
869
+ "loss": 1.9837,
870
+ "step": 1220
871
+ },
872
+ {
873
+ "epoch": 1.277258566978193,
874
+ "grad_norm": 0.04958974513719812,
875
+ "learning_rate": 0.00016291313176214594,
876
+ "loss": 1.9958,
877
+ "step": 1230
878
+ },
879
+ {
880
+ "epoch": 1.2876427829698858,
881
+ "grad_norm": 0.06000642526639929,
882
+ "learning_rate": 0.00016224343736168364,
883
+ "loss": 1.9826,
884
+ "step": 1240
885
+ },
886
+ {
887
+ "epoch": 1.2980269989615785,
888
+ "grad_norm": 0.0691162645669215,
889
+ "learning_rate": 0.0001615691545130893,
890
+ "loss": 1.9859,
891
+ "step": 1250
892
+ },
893
+ {
894
+ "epoch": 1.308411214953271,
895
+ "grad_norm": 0.08208145864348057,
896
+ "learning_rate": 0.00016089033292299873,
897
+ "loss": 1.9733,
898
+ "step": 1260
899
+ },
900
+ {
901
+ "epoch": 1.3187954309449637,
902
+ "grad_norm": 0.06063246637692115,
903
+ "learning_rate": 0.0001602070226326338,
904
+ "loss": 1.9877,
905
+ "step": 1270
906
+ },
907
+ {
908
+ "epoch": 1.3291796469366564,
909
+ "grad_norm": 0.05081448247031672,
910
+ "learning_rate": 0.00015951927401411338,
911
+ "loss": 1.9754,
912
+ "step": 1280
913
+ },
914
+ {
915
+ "epoch": 1.3395638629283488,
916
+ "grad_norm": 0.09886293194104055,
917
+ "learning_rate": 0.00015882713776674002,
918
+ "loss": 1.9876,
919
+ "step": 1290
920
+ },
921
+ {
922
+ "epoch": 1.3499480789200415,
923
+ "grad_norm": 0.04546233737433733,
924
+ "learning_rate": 0.00015813066491326264,
925
+ "loss": 1.9809,
926
+ "step": 1300
927
+ },
928
+ {
929
+ "epoch": 1.3603322949117342,
930
+ "grad_norm": 0.062362532759014794,
931
+ "learning_rate": 0.00015742990679611495,
932
+ "loss": 1.9941,
933
+ "step": 1310
934
+ },
935
+ {
936
+ "epoch": 1.3707165109034267,
937
+ "grad_norm": 0.07940499364650176,
938
+ "learning_rate": 0.00015672491507363098,
939
+ "loss": 1.9744,
940
+ "step": 1320
941
+ },
942
+ {
943
+ "epoch": 1.3811007268951194,
944
+ "grad_norm": 0.05526952881354372,
945
+ "learning_rate": 0.00015601574171623662,
946
+ "loss": 1.9848,
947
+ "step": 1330
948
+ },
949
+ {
950
+ "epoch": 1.3914849428868121,
951
+ "grad_norm": 0.06363654150905072,
952
+ "learning_rate": 0.00015530243900261875,
953
+ "loss": 1.9925,
954
+ "step": 1340
955
+ },
956
+ {
957
+ "epoch": 1.4018691588785046,
958
+ "grad_norm": 0.04851079344686748,
959
+ "learning_rate": 0.00015458505951587107,
960
+ "loss": 1.9735,
961
+ "step": 1350
962
+ },
963
+ {
964
+ "epoch": 1.4122533748701973,
965
+ "grad_norm": 0.03877506751064831,
966
+ "learning_rate": 0.00015386365613961808,
967
+ "loss": 1.9823,
968
+ "step": 1360
969
+ },
970
+ {
971
+ "epoch": 1.42263759086189,
972
+ "grad_norm": 0.057357211666960554,
973
+ "learning_rate": 0.00015313828205411643,
974
+ "loss": 1.979,
975
+ "step": 1370
976
+ },
977
+ {
978
+ "epoch": 1.4330218068535825,
979
+ "grad_norm": 0.33394378281583326,
980
+ "learning_rate": 0.00015240899073233459,
981
+ "loss": 1.9739,
982
+ "step": 1380
983
+ },
984
+ {
985
+ "epoch": 1.4434060228452752,
986
+ "grad_norm": 0.076600081601143,
987
+ "learning_rate": 0.00015167583593601118,
988
+ "loss": 1.975,
989
+ "step": 1390
990
+ },
991
+ {
992
+ "epoch": 1.4537902388369677,
993
+ "grad_norm": 0.06205212035398695,
994
+ "learning_rate": 0.0001509388717116914,
995
+ "loss": 1.9832,
996
+ "step": 1400
997
+ },
998
+ {
999
+ "epoch": 1.4641744548286604,
1000
+ "grad_norm": 0.07576423778510906,
1001
+ "learning_rate": 0.00015019815238674316,
1002
+ "loss": 1.9648,
1003
+ "step": 1410
1004
+ },
1005
+ {
1006
+ "epoch": 1.474558670820353,
1007
+ "grad_norm": 0.054255366239335946,
1008
+ "learning_rate": 0.00014945373256535193,
1009
+ "loss": 1.9748,
1010
+ "step": 1420
1011
+ },
1012
+ {
1013
+ "epoch": 1.4849428868120458,
1014
+ "grad_norm": 0.049400147544495954,
1015
+ "learning_rate": 0.00014870566712449574,
1016
+ "loss": 1.9696,
1017
+ "step": 1430
1018
+ },
1019
+ {
1020
+ "epoch": 1.4953271028037383,
1021
+ "grad_norm": 0.07084996389646055,
1022
+ "learning_rate": 0.00014795401120989946,
1023
+ "loss": 1.9846,
1024
+ "step": 1440
1025
+ },
1026
+ {
1027
+ "epoch": 1.505711318795431,
1028
+ "grad_norm": 0.07725519025462456,
1029
+ "learning_rate": 0.0001471988202319698,
1030
+ "loss": 1.9807,
1031
+ "step": 1450
1032
+ },
1033
+ {
1034
+ "epoch": 1.5160955347871234,
1035
+ "grad_norm": 0.09599754724343246,
1036
+ "learning_rate": 0.00014644014986171043,
1037
+ "loss": 1.9741,
1038
+ "step": 1460
1039
+ },
1040
+ {
1041
+ "epoch": 1.5264797507788161,
1042
+ "grad_norm": 0.10926696005297051,
1043
+ "learning_rate": 0.00014567805602661818,
1044
+ "loss": 1.9722,
1045
+ "step": 1470
1046
+ },
1047
+ {
1048
+ "epoch": 1.5368639667705088,
1049
+ "grad_norm": 0.0575723615133672,
1050
+ "learning_rate": 0.00014491259490656005,
1051
+ "loss": 1.982,
1052
+ "step": 1480
1053
+ },
1054
+ {
1055
+ "epoch": 1.5472481827622016,
1056
+ "grad_norm": 0.07279352095271414,
1057
+ "learning_rate": 0.00014414382292963183,
1058
+ "loss": 1.9764,
1059
+ "step": 1490
1060
+ },
1061
+ {
1062
+ "epoch": 1.557632398753894,
1063
+ "grad_norm": 0.040859676675886324,
1064
+ "learning_rate": 0.00014337179676799833,
1065
+ "loss": 1.9709,
1066
+ "step": 1500
1067
+ },
1068
+ {
1069
+ "epoch": 1.5680166147455867,
1070
+ "grad_norm": 0.12336166925694625,
1071
+ "learning_rate": 0.00014259657333371578,
1072
+ "loss": 1.9506,
1073
+ "step": 1510
1074
+ },
1075
+ {
1076
+ "epoch": 1.5784008307372792,
1077
+ "grad_norm": 0.0683838357758422,
1078
+ "learning_rate": 0.00014181820977453597,
1079
+ "loss": 1.9615,
1080
+ "step": 1520
1081
+ },
1082
+ {
1083
+ "epoch": 1.588785046728972,
1084
+ "grad_norm": 0.06707290549423066,
1085
+ "learning_rate": 0.00014103676346969397,
1086
+ "loss": 1.9743,
1087
+ "step": 1530
1088
+ },
1089
+ {
1090
+ "epoch": 1.5991692627206646,
1091
+ "grad_norm": 0.049517403695693,
1092
+ "learning_rate": 0.00014025229202567794,
1093
+ "loss": 1.9828,
1094
+ "step": 1540
1095
+ },
1096
+ {
1097
+ "epoch": 1.6095534787123573,
1098
+ "grad_norm": 0.04316844783056632,
1099
+ "learning_rate": 0.0001394648532719826,
1100
+ "loss": 1.9683,
1101
+ "step": 1550
1102
+ },
1103
+ {
1104
+ "epoch": 1.6199376947040498,
1105
+ "grad_norm": 0.0513619702195281,
1106
+ "learning_rate": 0.0001386745052568461,
1107
+ "loss": 1.9694,
1108
+ "step": 1560
1109
+ },
1110
+ {
1111
+ "epoch": 1.6303219106957425,
1112
+ "grad_norm": 0.05590615830992317,
1113
+ "learning_rate": 0.00013788130624297108,
1114
+ "loss": 1.9578,
1115
+ "step": 1570
1116
+ },
1117
+ {
1118
+ "epoch": 1.640706126687435,
1119
+ "grad_norm": 0.04960199558386229,
1120
+ "learning_rate": 0.00013708531470322917,
1121
+ "loss": 1.9619,
1122
+ "step": 1580
1123
+ },
1124
+ {
1125
+ "epoch": 1.6510903426791277,
1126
+ "grad_norm": 0.0540186757487458,
1127
+ "learning_rate": 0.00013628658931635112,
1128
+ "loss": 1.9603,
1129
+ "step": 1590
1130
+ },
1131
+ {
1132
+ "epoch": 1.6614745586708204,
1133
+ "grad_norm": 0.04468195014616628,
1134
+ "learning_rate": 0.0001354851889626006,
1135
+ "loss": 1.9606,
1136
+ "step": 1600
1137
+ },
1138
+ {
1139
+ "epoch": 1.671858774662513,
1140
+ "grad_norm": 0.04940602450150429,
1141
+ "learning_rate": 0.0001346811727194341,
1142
+ "loss": 1.9769,
1143
+ "step": 1610
1144
+ },
1145
+ {
1146
+ "epoch": 1.6822429906542056,
1147
+ "grad_norm": 0.054784881791703995,
1148
+ "learning_rate": 0.00013387459985714548,
1149
+ "loss": 1.9597,
1150
+ "step": 1620
1151
+ },
1152
+ {
1153
+ "epoch": 1.6926272066458983,
1154
+ "grad_norm": 0.0436280187041277,
1155
+ "learning_rate": 0.00013306552983449702,
1156
+ "loss": 1.9499,
1157
+ "step": 1630
1158
+ },
1159
+ {
1160
+ "epoch": 1.7030114226375908,
1161
+ "grad_norm": 0.052954976174433656,
1162
+ "learning_rate": 0.00013225402229433613,
1163
+ "loss": 1.9656,
1164
+ "step": 1640
1165
+ },
1166
+ {
1167
+ "epoch": 1.7133956386292835,
1168
+ "grad_norm": 0.04038061588172427,
1169
+ "learning_rate": 0.0001314401370591985,
1170
+ "loss": 1.9572,
1171
+ "step": 1650
1172
+ },
1173
+ {
1174
+ "epoch": 1.7237798546209762,
1175
+ "grad_norm": 0.19087870552648079,
1176
+ "learning_rate": 0.0001306239341268983,
1177
+ "loss": 1.9759,
1178
+ "step": 1660
1179
+ },
1180
+ {
1181
+ "epoch": 1.7341640706126689,
1182
+ "grad_norm": 0.0557585132432444,
1183
+ "learning_rate": 0.00012980547366610513,
1184
+ "loss": 1.9632,
1185
+ "step": 1670
1186
+ },
1187
+ {
1188
+ "epoch": 1.7445482866043613,
1189
+ "grad_norm": 0.04761529270545494,
1190
+ "learning_rate": 0.00012898481601190872,
1191
+ "loss": 1.9636,
1192
+ "step": 1680
1193
+ },
1194
+ {
1195
+ "epoch": 1.754932502596054,
1196
+ "grad_norm": 0.04760364370759641,
1197
+ "learning_rate": 0.00012816202166137088,
1198
+ "loss": 1.9456,
1199
+ "step": 1690
1200
+ },
1201
+ {
1202
+ "epoch": 1.7653167185877465,
1203
+ "grad_norm": 0.0455373551494814,
1204
+ "learning_rate": 0.00012733715126906598,
1205
+ "loss": 1.9634,
1206
+ "step": 1700
1207
+ },
1208
+ {
1209
+ "epoch": 1.7757009345794392,
1210
+ "grad_norm": 0.0457119348381667,
1211
+ "learning_rate": 0.0001265102656426096,
1212
+ "loss": 1.9568,
1213
+ "step": 1710
1214
+ },
1215
+ {
1216
+ "epoch": 1.786085150571132,
1217
+ "grad_norm": 0.037460420379211885,
1218
+ "learning_rate": 0.0001256814257381759,
1219
+ "loss": 1.9594,
1220
+ "step": 1720
1221
+ },
1222
+ {
1223
+ "epoch": 1.7964693665628246,
1224
+ "grad_norm": 0.05644971226502932,
1225
+ "learning_rate": 0.00012485069265600406,
1226
+ "loss": 1.9706,
1227
+ "step": 1730
1228
+ },
1229
+ {
1230
+ "epoch": 1.8068535825545171,
1231
+ "grad_norm": 0.048531751014330375,
1232
+ "learning_rate": 0.00012401812763589417,
1233
+ "loss": 1.965,
1234
+ "step": 1740
1235
+ },
1236
+ {
1237
+ "epoch": 1.8172377985462098,
1238
+ "grad_norm": 0.0897133700097393,
1239
+ "learning_rate": 0.00012318379205269268,
1240
+ "loss": 1.9544,
1241
+ "step": 1750
1242
+ },
1243
+ {
1244
+ "epoch": 1.8276220145379023,
1245
+ "grad_norm": 0.05634059035295753,
1246
+ "learning_rate": 0.00012234774741176803,
1247
+ "loss": 1.9478,
1248
+ "step": 1760
1249
+ },
1250
+ {
1251
+ "epoch": 1.838006230529595,
1252
+ "grad_norm": 0.04447498594371484,
1253
+ "learning_rate": 0.0001215100553444766,
1254
+ "loss": 1.9651,
1255
+ "step": 1770
1256
+ },
1257
+ {
1258
+ "epoch": 1.8483904465212877,
1259
+ "grad_norm": 0.04049850207427813,
1260
+ "learning_rate": 0.0001206707776036194,
1261
+ "loss": 1.9561,
1262
+ "step": 1780
1263
+ },
1264
+ {
1265
+ "epoch": 1.8587746625129804,
1266
+ "grad_norm": 0.049905900865747664,
1267
+ "learning_rate": 0.00011982997605888982,
1268
+ "loss": 1.9525,
1269
+ "step": 1790
1270
+ },
1271
+ {
1272
+ "epoch": 1.8691588785046729,
1273
+ "grad_norm": 0.046428029588076354,
1274
+ "learning_rate": 0.00011898771269231259,
1275
+ "loss": 1.9549,
1276
+ "step": 1800
1277
+ },
1278
+ {
1279
+ "epoch": 1.8795430944963654,
1280
+ "grad_norm": 0.05518629809387894,
1281
+ "learning_rate": 0.0001181440495936748,
1282
+ "loss": 1.9551,
1283
+ "step": 1810
1284
+ },
1285
+ {
1286
+ "epoch": 1.889927310488058,
1287
+ "grad_norm": 0.05516268355276683,
1288
+ "learning_rate": 0.0001172990489559486,
1289
+ "loss": 1.9503,
1290
+ "step": 1820
1291
+ },
1292
+ {
1293
+ "epoch": 1.9003115264797508,
1294
+ "grad_norm": 0.04050717081556759,
1295
+ "learning_rate": 0.00011645277307070665,
1296
+ "loss": 1.944,
1297
+ "step": 1830
1298
+ },
1299
+ {
1300
+ "epoch": 1.9106957424714435,
1301
+ "grad_norm": 0.04085466329001451,
1302
+ "learning_rate": 0.00011560528432352995,
1303
+ "loss": 1.9412,
1304
+ "step": 1840
1305
+ },
1306
+ {
1307
+ "epoch": 1.9210799584631362,
1308
+ "grad_norm": 0.04035870672075856,
1309
+ "learning_rate": 0.00011475664518940906,
1310
+ "loss": 1.9454,
1311
+ "step": 1850
1312
+ },
1313
+ {
1314
+ "epoch": 1.9314641744548287,
1315
+ "grad_norm": 0.04525049145261087,
1316
+ "learning_rate": 0.00011390691822813834,
1317
+ "loss": 1.9488,
1318
+ "step": 1860
1319
+ },
1320
+ {
1321
+ "epoch": 1.9418483904465211,
1322
+ "grad_norm": 0.07583001954124924,
1323
+ "learning_rate": 0.00011305616607970466,
1324
+ "loss": 1.9581,
1325
+ "step": 1870
1326
+ },
1327
+ {
1328
+ "epoch": 1.9522326064382138,
1329
+ "grad_norm": 0.04571807710480933,
1330
+ "learning_rate": 0.00011220445145966909,
1331
+ "loss": 1.9491,
1332
+ "step": 1880
1333
+ },
1334
+ {
1335
+ "epoch": 1.9626168224299065,
1336
+ "grad_norm": 0.03677710521162795,
1337
+ "learning_rate": 0.00011135183715454425,
1338
+ "loss": 1.9405,
1339
+ "step": 1890
1340
+ },
1341
+ {
1342
+ "epoch": 1.9730010384215992,
1343
+ "grad_norm": 0.03152877913624589,
1344
+ "learning_rate": 0.0001104983860171653,
1345
+ "loss": 1.9588,
1346
+ "step": 1900
1347
+ },
1348
+ {
1349
+ "epoch": 1.983385254413292,
1350
+ "grad_norm": 0.04719661115480296,
1351
+ "learning_rate": 0.00010964416096205703,
1352
+ "loss": 1.9476,
1353
+ "step": 1910
1354
+ },
1355
+ {
1356
+ "epoch": 1.9937694704049844,
1357
+ "grad_norm": 0.03771695185458553,
1358
+ "learning_rate": 0.00010878922496079557,
1359
+ "loss": 1.9573,
1360
+ "step": 1920
1361
+ },
1362
+ {
1363
+ "epoch": 2.004153686396677,
1364
+ "grad_norm": 0.10051051339687664,
1365
+ "learning_rate": 0.00010793364103736654,
1366
+ "loss": 1.9209,
1367
+ "step": 1930
1368
+ },
1369
+ {
1370
+ "epoch": 2.0145379023883696,
1371
+ "grad_norm": 0.053046758269573425,
1372
+ "learning_rate": 0.00010707747226351885,
1373
+ "loss": 1.8992,
1374
+ "step": 1940
1375
+ },
1376
+ {
1377
+ "epoch": 2.0249221183800623,
1378
+ "grad_norm": 0.04951461768457373,
1379
+ "learning_rate": 0.00010622078175411539,
1380
+ "loss": 1.8827,
1381
+ "step": 1950
1382
+ },
1383
+ {
1384
+ "epoch": 2.035306334371755,
1385
+ "grad_norm": 0.048922742722624736,
1386
+ "learning_rate": 0.00010536363266248006,
1387
+ "loss": 1.8931,
1388
+ "step": 1960
1389
+ },
1390
+ {
1391
+ "epoch": 2.0456905503634477,
1392
+ "grad_norm": 0.035328186325718505,
1393
+ "learning_rate": 0.0001045060881757427,
1394
+ "loss": 1.889,
1395
+ "step": 1970
1396
+ },
1397
+ {
1398
+ "epoch": 2.05607476635514,
1399
+ "grad_norm": 0.040216878273991646,
1400
+ "learning_rate": 0.0001036482115101805,
1401
+ "loss": 1.8882,
1402
+ "step": 1980
1403
+ },
1404
+ {
1405
+ "epoch": 2.0664589823468327,
1406
+ "grad_norm": 0.0412638566285706,
1407
+ "learning_rate": 0.00010279006590655838,
1408
+ "loss": 1.8845,
1409
+ "step": 1990
1410
+ },
1411
+ {
1412
+ "epoch": 2.0768431983385254,
1413
+ "grad_norm": 0.054540957226290813,
1414
+ "learning_rate": 0.00010193171462546663,
1415
+ "loss": 1.8803,
1416
+ "step": 2000
1417
+ },
1418
+ {
1419
+ "epoch": 2.087227414330218,
1420
+ "grad_norm": 0.039021677799949306,
1421
+ "learning_rate": 0.00010107322094265763,
1422
+ "loss": 1.8807,
1423
+ "step": 2010
1424
+ },
1425
+ {
1426
+ "epoch": 2.097611630321911,
1427
+ "grad_norm": 0.7994152420449053,
1428
+ "learning_rate": 0.00010021464814438147,
1429
+ "loss": 1.902,
1430
+ "step": 2020
1431
+ },
1432
+ {
1433
+ "epoch": 2.1079958463136035,
1434
+ "grad_norm": 0.17887365510689546,
1435
+ "learning_rate": 9.93560595227202e-05,
1436
+ "loss": 1.8845,
1437
+ "step": 2030
1438
+ },
1439
+ {
1440
+ "epoch": 2.1183800623052957,
1441
+ "grad_norm": 0.03460922099094267,
1442
+ "learning_rate": 9.849751837092247e-05,
1443
+ "loss": 1.8897,
1444
+ "step": 2040
1445
+ },
1446
+ {
1447
+ "epoch": 2.1287642782969884,
1448
+ "grad_norm": 0.03500662028709463,
1449
+ "learning_rate": 9.763908797873766e-05,
1450
+ "loss": 1.897,
1451
+ "step": 2050
1452
+ },
1453
+ {
1454
+ "epoch": 2.139148494288681,
1455
+ "grad_norm": 0.23891276176664628,
1456
+ "learning_rate": 9.678083162774996e-05,
1457
+ "loss": 1.8933,
1458
+ "step": 2060
1459
+ },
1460
+ {
1461
+ "epoch": 2.149532710280374,
1462
+ "grad_norm": 0.03511645627931291,
1463
+ "learning_rate": 9.592281258671383e-05,
1464
+ "loss": 1.8905,
1465
+ "step": 2070
1466
+ },
1467
+ {
1468
+ "epoch": 2.1599169262720666,
1469
+ "grad_norm": 0.029028519789360867,
1470
+ "learning_rate": 9.506509410688967e-05,
1471
+ "loss": 1.8924,
1472
+ "step": 2080
1473
+ },
1474
+ {
1475
+ "epoch": 2.1703011422637593,
1476
+ "grad_norm": 0.039617884777983815,
1477
+ "learning_rate": 9.42077394173812e-05,
1478
+ "loss": 1.8992,
1479
+ "step": 2090
1480
+ },
1481
+ {
1482
+ "epoch": 2.1806853582554515,
1483
+ "grad_norm": 0.04334116340629134,
1484
+ "learning_rate": 9.335081172047432e-05,
1485
+ "loss": 1.8867,
1486
+ "step": 2100
1487
+ },
1488
+ {
1489
+ "epoch": 2.191069574247144,
1490
+ "grad_norm": 0.0449949789226227,
1491
+ "learning_rate": 9.249437418697795e-05,
1492
+ "loss": 1.8822,
1493
+ "step": 2110
1494
+ },
1495
+ {
1496
+ "epoch": 2.201453790238837,
1497
+ "grad_norm": 0.03589882350253351,
1498
+ "learning_rate": 9.163848995156735e-05,
1499
+ "loss": 1.8894,
1500
+ "step": 2120
1501
+ },
1502
+ {
1503
+ "epoch": 2.2118380062305296,
1504
+ "grad_norm": 0.04660350436587833,
1505
+ "learning_rate": 9.078322210812977e-05,
1506
+ "loss": 1.8855,
1507
+ "step": 2130
1508
+ },
1509
+ {
1510
+ "epoch": 2.2222222222222223,
1511
+ "grad_norm": 0.03337838047499648,
1512
+ "learning_rate": 8.992863370511345e-05,
1513
+ "loss": 1.887,
1514
+ "step": 2140
1515
+ },
1516
+ {
1517
+ "epoch": 2.232606438213915,
1518
+ "grad_norm": 0.035796992309033424,
1519
+ "learning_rate": 8.907478774087978e-05,
1520
+ "loss": 1.8939,
1521
+ "step": 2150
1522
+ },
1523
+ {
1524
+ "epoch": 2.2429906542056073,
1525
+ "grad_norm": 0.05087780255678321,
1526
+ "learning_rate": 8.822174715905921e-05,
1527
+ "loss": 1.8964,
1528
+ "step": 2160
1529
+ },
1530
+ {
1531
+ "epoch": 2.2533748701973,
1532
+ "grad_norm": 0.11438552126019742,
1533
+ "learning_rate": 8.736957484391121e-05,
1534
+ "loss": 1.8905,
1535
+ "step": 2170
1536
+ },
1537
+ {
1538
+ "epoch": 2.2637590861889927,
1539
+ "grad_norm": 0.04049650564404653,
1540
+ "learning_rate": 8.651833361568858e-05,
1541
+ "loss": 1.9003,
1542
+ "step": 2180
1543
+ },
1544
+ {
1545
+ "epoch": 2.2741433021806854,
1546
+ "grad_norm": 0.03717207474262037,
1547
+ "learning_rate": 8.566808622600635e-05,
1548
+ "loss": 1.8907,
1549
+ "step": 2190
1550
+ },
1551
+ {
1552
+ "epoch": 2.284527518172378,
1553
+ "grad_norm": 0.03364482887335288,
1554
+ "learning_rate": 8.481889535321606e-05,
1555
+ "loss": 1.8916,
1556
+ "step": 2200
1557
+ },
1558
+ {
1559
+ "epoch": 2.294911734164071,
1560
+ "grad_norm": 0.03469965219006881,
1561
+ "learning_rate": 8.397082359778517e-05,
1562
+ "loss": 1.8863,
1563
+ "step": 2210
1564
+ },
1565
+ {
1566
+ "epoch": 2.305295950155763,
1567
+ "grad_norm": 0.07167874265458626,
1568
+ "learning_rate": 8.312393347768227e-05,
1569
+ "loss": 1.8939,
1570
+ "step": 2220
1571
+ },
1572
+ {
1573
+ "epoch": 2.3156801661474558,
1574
+ "grad_norm": 0.039264910030250226,
1575
+ "learning_rate": 8.22782874237684e-05,
1576
+ "loss": 1.8842,
1577
+ "step": 2230
1578
+ },
1579
+ {
1580
+ "epoch": 2.3260643821391485,
1581
+ "grad_norm": 0.043840673162470714,
1582
+ "learning_rate": 8.14339477751948e-05,
1583
+ "loss": 1.893,
1584
+ "step": 2240
1585
+ },
1586
+ {
1587
+ "epoch": 2.336448598130841,
1588
+ "grad_norm": 0.08409638753030813,
1589
+ "learning_rate": 8.059097677480747e-05,
1590
+ "loss": 1.8813,
1591
+ "step": 2250
1592
+ },
1593
+ {
1594
+ "epoch": 2.346832814122534,
1595
+ "grad_norm": 0.058647669381385874,
1596
+ "learning_rate": 7.974943656455866e-05,
1597
+ "loss": 1.8889,
1598
+ "step": 2260
1599
+ },
1600
+ {
1601
+ "epoch": 2.3572170301142266,
1602
+ "grad_norm": 0.03781952356296934,
1603
+ "learning_rate": 7.890938918092589e-05,
1604
+ "loss": 1.8943,
1605
+ "step": 2270
1606
+ },
1607
+ {
1608
+ "epoch": 2.367601246105919,
1609
+ "grad_norm": 0.034418604501786784,
1610
+ "learning_rate": 7.80708965503389e-05,
1611
+ "loss": 1.8881,
1612
+ "step": 2280
1613
+ },
1614
+ {
1615
+ "epoch": 2.3779854620976115,
1616
+ "grad_norm": 0.037318431359647554,
1617
+ "learning_rate": 7.72340204846144e-05,
1618
+ "loss": 1.8863,
1619
+ "step": 2290
1620
+ },
1621
+ {
1622
+ "epoch": 2.3883696780893042,
1623
+ "grad_norm": 0.2131547601678803,
1624
+ "learning_rate": 7.639882267639968e-05,
1625
+ "loss": 1.8905,
1626
+ "step": 2300
1627
+ },
1628
+ {
1629
+ "epoch": 2.398753894080997,
1630
+ "grad_norm": 0.03310764658637136,
1631
+ "learning_rate": 7.556536469462438e-05,
1632
+ "loss": 1.8839,
1633
+ "step": 2310
1634
+ },
1635
+ {
1636
+ "epoch": 2.4091381100726896,
1637
+ "grad_norm": 0.03197638258078385,
1638
+ "learning_rate": 7.473370797996218e-05,
1639
+ "loss": 1.8915,
1640
+ "step": 2320
1641
+ },
1642
+ {
1643
+ "epoch": 2.4195223260643823,
1644
+ "grad_norm": 0.03246304055917123,
1645
+ "learning_rate": 7.390391384030127e-05,
1646
+ "loss": 1.8817,
1647
+ "step": 2330
1648
+ },
1649
+ {
1650
+ "epoch": 2.4299065420560746,
1651
+ "grad_norm": 0.03798793293663323,
1652
+ "learning_rate": 7.307604344622492e-05,
1653
+ "loss": 1.8972,
1654
+ "step": 2340
1655
+ },
1656
+ {
1657
+ "epoch": 2.4402907580477673,
1658
+ "grad_norm": 0.03658165397388397,
1659
+ "learning_rate": 7.225015782650227e-05,
1660
+ "loss": 1.8916,
1661
+ "step": 2350
1662
+ },
1663
+ {
1664
+ "epoch": 2.45067497403946,
1665
+ "grad_norm": 0.05025404979760921,
1666
+ "learning_rate": 7.142631786358906e-05,
1667
+ "loss": 1.8968,
1668
+ "step": 2360
1669
+ },
1670
+ {
1671
+ "epoch": 2.4610591900311527,
1672
+ "grad_norm": 0.0334975984641327,
1673
+ "learning_rate": 7.060458428914001e-05,
1674
+ "loss": 1.8904,
1675
+ "step": 2370
1676
+ },
1677
+ {
1678
+ "epoch": 2.4714434060228454,
1679
+ "grad_norm": 0.04647438899735641,
1680
+ "learning_rate": 6.978501767953138e-05,
1681
+ "loss": 1.8854,
1682
+ "step": 2380
1683
+ },
1684
+ {
1685
+ "epoch": 2.4818276220145377,
1686
+ "grad_norm": 0.08974715928533734,
1687
+ "learning_rate": 6.896767845139567e-05,
1688
+ "loss": 1.8872,
1689
+ "step": 2390
1690
+ },
1691
+ {
1692
+ "epoch": 2.4922118380062304,
1693
+ "grad_norm": 0.05117661139357449,
1694
+ "learning_rate": 6.81526268571677e-05,
1695
+ "loss": 1.8913,
1696
+ "step": 2400
1697
+ },
1698
+ {
1699
+ "epoch": 2.502596053997923,
1700
+ "grad_norm": 0.032791100418119334,
1701
+ "learning_rate": 6.733992298064302e-05,
1702
+ "loss": 1.8879,
1703
+ "step": 2410
1704
+ },
1705
+ {
1706
+ "epoch": 2.5129802699896158,
1707
+ "grad_norm": 0.029623444681847317,
1708
+ "learning_rate": 6.65296267325487e-05,
1709
+ "loss": 1.8782,
1710
+ "step": 2420
1711
+ },
1712
+ {
1713
+ "epoch": 2.5233644859813085,
1714
+ "grad_norm": 0.03694773121265341,
1715
+ "learning_rate": 6.572179784612669e-05,
1716
+ "loss": 1.8843,
1717
+ "step": 2430
1718
+ },
1719
+ {
1720
+ "epoch": 2.533748701973001,
1721
+ "grad_norm": 0.03318007980734069,
1722
+ "learning_rate": 6.491649587273055e-05,
1723
+ "loss": 1.879,
1724
+ "step": 2440
1725
+ },
1726
+ {
1727
+ "epoch": 2.544132917964694,
1728
+ "grad_norm": 0.03776736168188557,
1729
+ "learning_rate": 6.41137801774354e-05,
1730
+ "loss": 1.8894,
1731
+ "step": 2450
1732
+ },
1733
+ {
1734
+ "epoch": 2.554517133956386,
1735
+ "grad_norm": 0.03154442159359809,
1736
+ "learning_rate": 6.33137099346617e-05,
1737
+ "loss": 1.8853,
1738
+ "step": 2460
1739
+ },
1740
+ {
1741
+ "epoch": 2.564901349948079,
1742
+ "grad_norm": 0.03867615437671989,
1743
+ "learning_rate": 6.251634412381305e-05,
1744
+ "loss": 1.8868,
1745
+ "step": 2470
1746
+ },
1747
+ {
1748
+ "epoch": 2.5752855659397715,
1749
+ "grad_norm": 0.027466663771499894,
1750
+ "learning_rate": 6.17217415249282e-05,
1751
+ "loss": 1.8763,
1752
+ "step": 2480
1753
+ },
1754
+ {
1755
+ "epoch": 2.5856697819314642,
1756
+ "grad_norm": 0.036700022200396934,
1757
+ "learning_rate": 6.0929960714348175e-05,
1758
+ "loss": 1.8862,
1759
+ "step": 2490
1760
+ },
1761
+ {
1762
+ "epoch": 2.596053997923157,
1763
+ "grad_norm": 0.04531269998341858,
1764
+ "learning_rate": 6.014106006039799e-05,
1765
+ "loss": 1.8939,
1766
+ "step": 2500
1767
+ },
1768
+ {
1769
+ "epoch": 2.606438213914849,
1770
+ "grad_norm": 0.03582993228713201,
1771
+ "learning_rate": 5.9355097719083906e-05,
1772
+ "loss": 1.8844,
1773
+ "step": 2510
1774
+ },
1775
+ {
1776
+ "epoch": 2.616822429906542,
1777
+ "grad_norm": 0.0281171458258059,
1778
+ "learning_rate": 5.857213162980624e-05,
1779
+ "loss": 1.8782,
1780
+ "step": 2520
1781
+ },
1782
+ {
1783
+ "epoch": 2.6272066458982346,
1784
+ "grad_norm": 0.029490846996600113,
1785
+ "learning_rate": 5.779221951108831e-05,
1786
+ "loss": 1.8971,
1787
+ "step": 2530
1788
+ },
1789
+ {
1790
+ "epoch": 2.6375908618899273,
1791
+ "grad_norm": 0.03608030454019105,
1792
+ "learning_rate": 5.7015418856321455e-05,
1793
+ "loss": 1.8791,
1794
+ "step": 2540
1795
+ },
1796
+ {
1797
+ "epoch": 2.64797507788162,
1798
+ "grad_norm": 0.03541306400353621,
1799
+ "learning_rate": 5.6241786929526905e-05,
1800
+ "loss": 1.875,
1801
+ "step": 2550
1802
+ },
1803
+ {
1804
+ "epoch": 2.6583592938733127,
1805
+ "grad_norm": 0.04468135089516037,
1806
+ "learning_rate": 5.547138076113415e-05,
1807
+ "loss": 1.878,
1808
+ "step": 2560
1809
+ },
1810
+ {
1811
+ "epoch": 2.6687435098650054,
1812
+ "grad_norm": 0.23796063882100216,
1813
+ "learning_rate": 5.470425714377696e-05,
1814
+ "loss": 1.8895,
1815
+ "step": 2570
1816
+ },
1817
+ {
1818
+ "epoch": 2.6791277258566977,
1819
+ "grad_norm": 0.036731035188722984,
1820
+ "learning_rate": 5.394047262810677e-05,
1821
+ "loss": 1.8841,
1822
+ "step": 2580
1823
+ },
1824
+ {
1825
+ "epoch": 2.6895119418483904,
1826
+ "grad_norm": 0.036413088394694086,
1827
+ "learning_rate": 5.318008351862389e-05,
1828
+ "loss": 1.8887,
1829
+ "step": 2590
1830
+ },
1831
+ {
1832
+ "epoch": 2.699896157840083,
1833
+ "grad_norm": 0.02878250541056217,
1834
+ "learning_rate": 5.24231458695267e-05,
1835
+ "loss": 1.8827,
1836
+ "step": 2600
1837
+ },
1838
+ {
1839
+ "epoch": 2.710280373831776,
1840
+ "grad_norm": 0.028719921150055488,
1841
+ "learning_rate": 5.1669715480579605e-05,
1842
+ "loss": 1.8877,
1843
+ "step": 2610
1844
+ },
1845
+ {
1846
+ "epoch": 2.7206645898234685,
1847
+ "grad_norm": 0.03189115204754057,
1848
+ "learning_rate": 5.091984789299966e-05,
1849
+ "loss": 1.8797,
1850
+ "step": 2620
1851
+ },
1852
+ {
1853
+ "epoch": 2.7310488058151607,
1854
+ "grad_norm": 0.03396106864883253,
1855
+ "learning_rate": 5.017359838536196e-05,
1856
+ "loss": 1.8835,
1857
+ "step": 2630
1858
+ },
1859
+ {
1860
+ "epoch": 2.7414330218068534,
1861
+ "grad_norm": 0.028895138001411413,
1862
+ "learning_rate": 4.943102196952496e-05,
1863
+ "loss": 1.882,
1864
+ "step": 2640
1865
+ },
1866
+ {
1867
+ "epoch": 2.751817237798546,
1868
+ "grad_norm": 0.03115500319946936,
1869
+ "learning_rate": 4.8692173386574725e-05,
1870
+ "loss": 1.8777,
1871
+ "step": 2650
1872
+ },
1873
+ {
1874
+ "epoch": 2.762201453790239,
1875
+ "grad_norm": 0.03109695539054872,
1876
+ "learning_rate": 4.795710710278994e-05,
1877
+ "loss": 1.8779,
1878
+ "step": 2660
1879
+ },
1880
+ {
1881
+ "epoch": 2.7725856697819315,
1882
+ "grad_norm": 0.02872076628599255,
1883
+ "learning_rate": 4.722587730562644e-05,
1884
+ "loss": 1.8789,
1885
+ "step": 2670
1886
+ },
1887
+ {
1888
+ "epoch": 2.7829698857736243,
1889
+ "grad_norm": 0.029544139531373234,
1890
+ "learning_rate": 4.6498537899722886e-05,
1891
+ "loss": 1.8845,
1892
+ "step": 2680
1893
+ },
1894
+ {
1895
+ "epoch": 2.793354101765317,
1896
+ "grad_norm": 0.031185958105230793,
1897
+ "learning_rate": 4.577514250292686e-05,
1898
+ "loss": 1.8839,
1899
+ "step": 2690
1900
+ },
1901
+ {
1902
+ "epoch": 2.803738317757009,
1903
+ "grad_norm": 0.032808530871134264,
1904
+ "learning_rate": 4.5055744442342306e-05,
1905
+ "loss": 1.8762,
1906
+ "step": 2700
1907
+ },
1908
+ {
1909
+ "epoch": 2.814122533748702,
1910
+ "grad_norm": 0.03336722828713624,
1911
+ "learning_rate": 4.434039675039849e-05,
1912
+ "loss": 1.8865,
1913
+ "step": 2710
1914
+ },
1915
+ {
1916
+ "epoch": 2.8245067497403946,
1917
+ "grad_norm": 0.03152635316825106,
1918
+ "learning_rate": 4.362915216094052e-05,
1919
+ "loss": 1.8948,
1920
+ "step": 2720
1921
+ },
1922
+ {
1923
+ "epoch": 2.8348909657320873,
1924
+ "grad_norm": 0.0397529790570945,
1925
+ "learning_rate": 4.292206310534178e-05,
1926
+ "loss": 1.8873,
1927
+ "step": 2730
1928
+ },
1929
+ {
1930
+ "epoch": 2.84527518172378,
1931
+ "grad_norm": 0.028759030768262736,
1932
+ "learning_rate": 4.221918170863891e-05,
1933
+ "loss": 1.865,
1934
+ "step": 2740
1935
+ },
1936
+ {
1937
+ "epoch": 2.8556593977154723,
1938
+ "grad_norm": 0.02644421553872256,
1939
+ "learning_rate": 4.1520559785689417e-05,
1940
+ "loss": 1.8855,
1941
+ "step": 2750
1942
+ },
1943
+ {
1944
+ "epoch": 2.866043613707165,
1945
+ "grad_norm": 0.028563082694737164,
1946
+ "learning_rate": 4.0826248837351676e-05,
1947
+ "loss": 1.8787,
1948
+ "step": 2760
1949
+ },
1950
+ {
1951
+ "epoch": 2.8764278296988577,
1952
+ "grad_norm": 0.029444868094979,
1953
+ "learning_rate": 4.0136300046688724e-05,
1954
+ "loss": 1.8732,
1955
+ "step": 2770
1956
+ },
1957
+ {
1958
+ "epoch": 2.8868120456905504,
1959
+ "grad_norm": 0.03241472330555303,
1960
+ "learning_rate": 3.945076427519487e-05,
1961
+ "loss": 1.889,
1962
+ "step": 2780
1963
+ },
1964
+ {
1965
+ "epoch": 2.897196261682243,
1966
+ "grad_norm": 0.03149461745854848,
1967
+ "learning_rate": 3.876969205904661e-05,
1968
+ "loss": 1.8801,
1969
+ "step": 2790
1970
+ },
1971
+ {
1972
+ "epoch": 2.9075804776739353,
1973
+ "grad_norm": 0.028978522468481756,
1974
+ "learning_rate": 3.809313360537685e-05,
1975
+ "loss": 1.8772,
1976
+ "step": 2800
1977
+ },
1978
+ {
1979
+ "epoch": 2.9179646936656285,
1980
+ "grad_norm": 0.0302145465899097,
1981
+ "learning_rate": 3.7421138788574105e-05,
1982
+ "loss": 1.8841,
1983
+ "step": 2810
1984
+ },
1985
+ {
1986
+ "epoch": 2.9283489096573208,
1987
+ "grad_norm": 0.02837293766893793,
1988
+ "learning_rate": 3.67537571466056e-05,
1989
+ "loss": 1.8738,
1990
+ "step": 2820
1991
+ },
1992
+ {
1993
+ "epoch": 2.9387331256490135,
1994
+ "grad_norm": 0.026790965166424704,
1995
+ "learning_rate": 3.609103787736554e-05,
1996
+ "loss": 1.8877,
1997
+ "step": 2830
1998
+ },
1999
+ {
2000
+ "epoch": 2.949117341640706,
2001
+ "grad_norm": 0.06056919378725827,
2002
+ "learning_rate": 3.5433029835048424e-05,
2003
+ "loss": 1.8778,
2004
+ "step": 2840
2005
+ },
2006
+ {
2007
+ "epoch": 2.959501557632399,
2008
+ "grad_norm": 0.03289459614837355,
2009
+ "learning_rate": 3.477978152654755e-05,
2010
+ "loss": 1.8755,
2011
+ "step": 2850
2012
+ },
2013
+ {
2014
+ "epoch": 2.9698857736240916,
2015
+ "grad_norm": 0.02826028146463465,
2016
+ "learning_rate": 3.413134110787914e-05,
2017
+ "loss": 1.8839,
2018
+ "step": 2860
2019
+ },
2020
+ {
2021
+ "epoch": 2.980269989615784,
2022
+ "grad_norm": 0.029206905700744863,
2023
+ "learning_rate": 3.348775638063243e-05,
2024
+ "loss": 1.8755,
2025
+ "step": 2870
2026
+ },
2027
+ {
2028
+ "epoch": 2.9906542056074765,
2029
+ "grad_norm": 0.023384168914128062,
2030
+ "learning_rate": 3.2849074788445934e-05,
2031
+ "loss": 1.8753,
2032
+ "step": 2880
2033
+ },
2034
+ {
2035
+ "epoch": 3.0010384215991692,
2036
+ "grad_norm": 0.03341943042039971,
2037
+ "learning_rate": 3.2215343413509905e-05,
2038
+ "loss": 1.8686,
2039
+ "step": 2890
2040
+ },
2041
+ {
2042
+ "epoch": 3.011422637590862,
2043
+ "grad_norm": 0.026364353919536725,
2044
+ "learning_rate": 3.158660897309552e-05,
2045
+ "loss": 1.8259,
2046
+ "step": 2900
2047
+ },
2048
+ {
2049
+ "epoch": 3.0218068535825546,
2050
+ "grad_norm": 0.02694200207629535,
2051
+ "learning_rate": 3.0962917816111015e-05,
2052
+ "loss": 1.831,
2053
+ "step": 2910
2054
+ },
2055
+ {
2056
+ "epoch": 3.0321910695742473,
2057
+ "grad_norm": 0.027264395799842606,
2058
+ "learning_rate": 3.034431591968505e-05,
2059
+ "loss": 1.8316,
2060
+ "step": 2920
2061
+ },
2062
+ {
2063
+ "epoch": 3.0425752855659396,
2064
+ "grad_norm": 0.02705865742740763,
2065
+ "learning_rate": 2.9730848885777174e-05,
2066
+ "loss": 1.8411,
2067
+ "step": 2930
2068
+ },
2069
+ {
2070
+ "epoch": 3.0529595015576323,
2071
+ "grad_norm": 0.027823888273444175,
2072
+ "learning_rate": 2.9122561937816385e-05,
2073
+ "loss": 1.8301,
2074
+ "step": 2940
2075
+ },
2076
+ {
2077
+ "epoch": 3.063343717549325,
2078
+ "grad_norm": 0.024461142921072543,
2079
+ "learning_rate": 2.8519499917367122e-05,
2080
+ "loss": 1.8308,
2081
+ "step": 2950
2082
+ },
2083
+ {
2084
+ "epoch": 3.0737279335410177,
2085
+ "grad_norm": 0.023706784124181608,
2086
+ "learning_rate": 2.7921707280823772e-05,
2087
+ "loss": 1.8315,
2088
+ "step": 2960
2089
+ },
2090
+ {
2091
+ "epoch": 3.0841121495327104,
2092
+ "grad_norm": 0.027231205141808358,
2093
+ "learning_rate": 2.7329228096133485e-05,
2094
+ "loss": 1.8281,
2095
+ "step": 2970
2096
+ },
2097
+ {
2098
+ "epoch": 3.094496365524403,
2099
+ "grad_norm": 0.03248321320895205,
2100
+ "learning_rate": 2.6742106039547554e-05,
2101
+ "loss": 1.8392,
2102
+ "step": 2980
2103
+ },
2104
+ {
2105
+ "epoch": 3.1048805815160954,
2106
+ "grad_norm": 0.02502731562284351,
2107
+ "learning_rate": 2.6160384392401583e-05,
2108
+ "loss": 1.8311,
2109
+ "step": 2990
2110
+ },
2111
+ {
2112
+ "epoch": 3.115264797507788,
2113
+ "grad_norm": 0.03720497378470297,
2114
+ "learning_rate": 2.558410603792496e-05,
2115
+ "loss": 1.8339,
2116
+ "step": 3000
2117
+ },
2118
+ {
2119
+ "epoch": 3.1256490134994808,
2120
+ "grad_norm": 0.026801563478718465,
2121
+ "learning_rate": 2.5013313458079703e-05,
2122
+ "loss": 1.8274,
2123
+ "step": 3010
2124
+ },
2125
+ {
2126
+ "epoch": 3.1360332294911735,
2127
+ "grad_norm": 0.025965034465224246,
2128
+ "learning_rate": 2.4448048730428706e-05,
2129
+ "loss": 1.8429,
2130
+ "step": 3020
2131
+ },
2132
+ {
2133
+ "epoch": 3.146417445482866,
2134
+ "grad_norm": 0.032573263708424026,
2135
+ "learning_rate": 2.3888353525033692e-05,
2136
+ "loss": 1.8346,
2137
+ "step": 3030
2138
+ },
2139
+ {
2140
+ "epoch": 3.156801661474559,
2141
+ "grad_norm": 0.026037586657472158,
2142
+ "learning_rate": 2.333426910138372e-05,
2143
+ "loss": 1.8448,
2144
+ "step": 3040
2145
+ },
2146
+ {
2147
+ "epoch": 3.167185877466251,
2148
+ "grad_norm": 0.024761889596049712,
2149
+ "learning_rate": 2.2785836305353446e-05,
2150
+ "loss": 1.8438,
2151
+ "step": 3050
2152
+ },
2153
+ {
2154
+ "epoch": 3.177570093457944,
2155
+ "grad_norm": 0.03200575290596344,
2156
+ "learning_rate": 2.2243095566191994e-05,
2157
+ "loss": 1.835,
2158
+ "step": 3060
2159
+ },
2160
+ {
2161
+ "epoch": 3.1879543094496365,
2162
+ "grad_norm": 0.03982323095987121,
2163
+ "learning_rate": 2.1706086893542775e-05,
2164
+ "loss": 1.8368,
2165
+ "step": 3070
2166
+ },
2167
+ {
2168
+ "epoch": 3.1983385254413292,
2169
+ "grad_norm": 0.027090117149582347,
2170
+ "learning_rate": 2.1174849874493884e-05,
2171
+ "loss": 1.8342,
2172
+ "step": 3080
2173
+ },
2174
+ {
2175
+ "epoch": 3.208722741433022,
2176
+ "grad_norm": 0.055829957488488326,
2177
+ "learning_rate": 2.064942367066002e-05,
2178
+ "loss": 1.8327,
2179
+ "step": 3090
2180
+ },
2181
+ {
2182
+ "epoch": 3.2191069574247146,
2183
+ "grad_norm": 0.024167312375239496,
2184
+ "learning_rate": 2.0129847015295335e-05,
2185
+ "loss": 1.8382,
2186
+ "step": 3100
2187
+ },
2188
+ {
2189
+ "epoch": 3.229491173416407,
2190
+ "grad_norm": 0.029543263767544348,
2191
+ "learning_rate": 1.9616158210438396e-05,
2192
+ "loss": 1.8395,
2193
+ "step": 3110
2194
+ },
2195
+ {
2196
+ "epoch": 3.2398753894080996,
2197
+ "grad_norm": 0.02532592655026882,
2198
+ "learning_rate": 1.9108395124088387e-05,
2199
+ "loss": 1.8387,
2200
+ "step": 3120
2201
+ },
2202
+ {
2203
+ "epoch": 3.2502596053997923,
2204
+ "grad_norm": 0.028105616678480865,
2205
+ "learning_rate": 1.860659518741367e-05,
2206
+ "loss": 1.833,
2207
+ "step": 3130
2208
+ },
2209
+ {
2210
+ "epoch": 3.260643821391485,
2211
+ "grad_norm": 0.02514532350434615,
2212
+ "learning_rate": 1.8110795391992495e-05,
2213
+ "loss": 1.8336,
2214
+ "step": 3140
2215
+ },
2216
+ {
2217
+ "epoch": 3.2710280373831777,
2218
+ "grad_norm": 0.10788982510529156,
2219
+ "learning_rate": 1.7621032287086016e-05,
2220
+ "loss": 1.8429,
2221
+ "step": 3150
2222
+ },
2223
+ {
2224
+ "epoch": 3.28141225337487,
2225
+ "grad_norm": 0.02716445574648588,
2226
+ "learning_rate": 1.713734197694389e-05,
2227
+ "loss": 1.8384,
2228
+ "step": 3160
2229
+ },
2230
+ {
2231
+ "epoch": 3.2917964693665627,
2232
+ "grad_norm": 0.026705801667825362,
2233
+ "learning_rate": 1.665976011814281e-05,
2234
+ "loss": 1.838,
2235
+ "step": 3170
2236
+ },
2237
+ {
2238
+ "epoch": 3.3021806853582554,
2239
+ "grad_norm": 0.024543903316036432,
2240
+ "learning_rate": 1.618832191695808e-05,
2241
+ "loss": 1.8332,
2242
+ "step": 3180
2243
+ },
2244
+ {
2245
+ "epoch": 3.312564901349948,
2246
+ "grad_norm": 0.027601030056442148,
2247
+ "learning_rate": 1.5723062126768118e-05,
2248
+ "loss": 1.8288,
2249
+ "step": 3190
2250
+ },
2251
+ {
2252
+ "epoch": 3.322949117341641,
2253
+ "grad_norm": 0.02804326118827403,
2254
+ "learning_rate": 1.5264015045492553e-05,
2255
+ "loss": 1.8421,
2256
+ "step": 3200
2257
+ },
2258
+ {
2259
+ "epoch": 3.3333333333333335,
2260
+ "grad_norm": 0.05395823033648557,
2261
+ "learning_rate": 1.4811214513063999e-05,
2262
+ "loss": 1.8401,
2263
+ "step": 3210
2264
+ },
2265
+ {
2266
+ "epoch": 3.343717549325026,
2267
+ "grad_norm": 0.023756760976785002,
2268
+ "learning_rate": 1.436469390893329e-05,
2269
+ "loss": 1.8209,
2270
+ "step": 3220
2271
+ },
2272
+ {
2273
+ "epoch": 3.3541017653167184,
2274
+ "grad_norm": 0.027557577932954304,
2275
+ "learning_rate": 1.3924486149608873e-05,
2276
+ "loss": 1.8361,
2277
+ "step": 3230
2278
+ },
2279
+ {
2280
+ "epoch": 3.364485981308411,
2281
+ "grad_norm": 0.025018509889372927,
2282
+ "learning_rate": 1.3490623686230241e-05,
2283
+ "loss": 1.8306,
2284
+ "step": 3240
2285
+ },
2286
+ {
2287
+ "epoch": 3.374870197300104,
2288
+ "grad_norm": 0.024771549070247176,
2289
+ "learning_rate": 1.3063138502175854e-05,
2290
+ "loss": 1.8391,
2291
+ "step": 3250
2292
+ },
2293
+ {
2294
+ "epoch": 3.3852544132917965,
2295
+ "grad_norm": 0.028735012305241347,
2296
+ "learning_rate": 1.2642062110705166e-05,
2297
+ "loss": 1.8387,
2298
+ "step": 3260
2299
+ },
2300
+ {
2301
+ "epoch": 3.3956386292834893,
2302
+ "grad_norm": 0.043099806337619166,
2303
+ "learning_rate": 1.2227425552635729e-05,
2304
+ "loss": 1.8371,
2305
+ "step": 3270
2306
+ },
2307
+ {
2308
+ "epoch": 3.4060228452751815,
2309
+ "grad_norm": 0.027606725592885465,
2310
+ "learning_rate": 1.1819259394054882e-05,
2311
+ "loss": 1.8309,
2312
+ "step": 3280
2313
+ },
2314
+ {
2315
+ "epoch": 3.416407061266874,
2316
+ "grad_norm": 0.023337257862491845,
2317
+ "learning_rate": 1.1417593724066389e-05,
2318
+ "loss": 1.8309,
2319
+ "step": 3290
2320
+ },
2321
+ {
2322
+ "epoch": 3.426791277258567,
2323
+ "grad_norm": 0.06343732868486207,
2324
+ "learning_rate": 1.1022458152572445e-05,
2325
+ "loss": 1.8285,
2326
+ "step": 3300
2327
+ },
2328
+ {
2329
+ "epoch": 3.4371754932502596,
2330
+ "grad_norm": 0.02604204838194835,
2331
+ "learning_rate": 1.0633881808090917e-05,
2332
+ "loss": 1.8286,
2333
+ "step": 3310
2334
+ },
2335
+ {
2336
+ "epoch": 3.4475597092419523,
2337
+ "grad_norm": 0.023864704629613265,
2338
+ "learning_rate": 1.0251893335607954e-05,
2339
+ "loss": 1.8324,
2340
+ "step": 3320
2341
+ },
2342
+ {
2343
+ "epoch": 3.457943925233645,
2344
+ "grad_norm": 0.02468893642826398,
2345
+ "learning_rate": 9.87652089446638e-06,
2346
+ "loss": 1.8307,
2347
+ "step": 3330
2348
+ },
2349
+ {
2350
+ "epoch": 3.4683281412253377,
2351
+ "grad_norm": 0.02343400044938008,
2352
+ "learning_rate": 9.507792156289919e-06,
2353
+ "loss": 1.8343,
2354
+ "step": 3340
2355
+ },
2356
+ {
2357
+ "epoch": 3.47871235721703,
2358
+ "grad_norm": 0.023155717671394706,
2359
+ "learning_rate": 9.145734302943244e-06,
2360
+ "loss": 1.8323,
2361
+ "step": 3350
2362
+ },
2363
+ {
2364
+ "epoch": 3.4890965732087227,
2365
+ "grad_norm": 0.023096856326372563,
2366
+ "learning_rate": 8.790374024528158e-06,
2367
+ "loss": 1.8176,
2368
+ "step": 3360
2369
+ },
2370
+ {
2371
+ "epoch": 3.4994807892004154,
2372
+ "grad_norm": 0.023683165717421392,
2373
+ "learning_rate": 8.441737517416104e-06,
2374
+ "loss": 1.8353,
2375
+ "step": 3370
2376
+ },
2377
+ {
2378
+ "epoch": 3.509865005192108,
2379
+ "grad_norm": 0.026648422294677784,
2380
+ "learning_rate": 8.09985048231705e-06,
2381
+ "loss": 1.8369,
2382
+ "step": 3380
2383
+ },
2384
+ {
2385
+ "epoch": 3.520249221183801,
2386
+ "grad_norm": 0.02368516502503519,
2387
+ "learning_rate": 7.764738122384807e-06,
2388
+ "loss": 1.8328,
2389
+ "step": 3390
2390
+ },
2391
+ {
2392
+ "epoch": 3.530633437175493,
2393
+ "grad_norm": 0.02401283420739923,
2394
+ "learning_rate": 7.436425141359238e-06,
2395
+ "loss": 1.8362,
2396
+ "step": 3400
2397
+ },
2398
+ {
2399
+ "epoch": 3.5410176531671858,
2400
+ "grad_norm": 0.023007225727798356,
2401
+ "learning_rate": 7.114935741744999e-06,
2402
+ "loss": 1.8446,
2403
+ "step": 3410
2404
+ },
2405
+ {
2406
+ "epoch": 3.5514018691588785,
2407
+ "grad_norm": 0.028298206992187595,
2408
+ "learning_rate": 6.800293623027509e-06,
2409
+ "loss": 1.83,
2410
+ "step": 3420
2411
+ },
2412
+ {
2413
+ "epoch": 3.561786085150571,
2414
+ "grad_norm": 0.028312783843724466,
2415
+ "learning_rate": 6.492521979925792e-06,
2416
+ "loss": 1.8234,
2417
+ "step": 3430
2418
+ },
2419
+ {
2420
+ "epoch": 3.572170301142264,
2421
+ "grad_norm": 0.023040880114570856,
2422
+ "learning_rate": 6.1916435006826865e-06,
2423
+ "loss": 1.8253,
2424
+ "step": 3440
2425
+ },
2426
+ {
2427
+ "epoch": 3.582554517133956,
2428
+ "grad_norm": 0.023618067129400337,
2429
+ "learning_rate": 5.897680365392288e-06,
2430
+ "loss": 1.8365,
2431
+ "step": 3450
2432
+ },
2433
+ {
2434
+ "epoch": 3.5929387331256493,
2435
+ "grad_norm": 0.0243747107934912,
2436
+ "learning_rate": 5.610654244364799e-06,
2437
+ "loss": 1.8327,
2438
+ "step": 3460
2439
+ },
2440
+ {
2441
+ "epoch": 3.6033229491173415,
2442
+ "grad_norm": 0.032204203001453054,
2443
+ "learning_rate": 5.3305862965291945e-06,
2444
+ "loss": 1.8294,
2445
+ "step": 3470
2446
+ },
2447
+ {
2448
+ "epoch": 3.6137071651090342,
2449
+ "grad_norm": 0.021909512415715003,
2450
+ "learning_rate": 5.057497167873348e-06,
2451
+ "loss": 1.8333,
2452
+ "step": 3480
2453
+ },
2454
+ {
2455
+ "epoch": 3.624091381100727,
2456
+ "grad_norm": 0.023030512464740572,
2457
+ "learning_rate": 4.791406989922043e-06,
2458
+ "loss": 1.8324,
2459
+ "step": 3490
2460
+ },
2461
+ {
2462
+ "epoch": 3.6344755970924196,
2463
+ "grad_norm": 0.02270290277171145,
2464
+ "learning_rate": 4.5323353782529274e-06,
2465
+ "loss": 1.8292,
2466
+ "step": 3500
2467
+ }
2468
+ ],
2469
+ "logging_steps": 10,
2470
+ "max_steps": 3852,
2471
+ "num_input_tokens_seen": 0,
2472
+ "num_train_epochs": 4,
2473
+ "save_steps": 100,
2474
+ "stateful_callbacks": {
2475
+ "TrainerControl": {
2476
+ "args": {
2477
+ "should_epoch_stop": false,
2478
+ "should_evaluate": false,
2479
+ "should_log": false,
2480
+ "should_save": true,
2481
+ "should_training_stop": false
2482
+ },
2483
+ "attributes": {}
2484
+ }
2485
+ },
2486
+ "total_flos": 8.676383049488794e+16,
2487
+ "train_batch_size": 2,
2488
+ "trial_name": null,
2489
+ "trial_params": null
2490
+ }
output_model/irish_llama31_lora_data_v3/checkpoint-3500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:deb3c9c3da2188d86dd9d9207fcd992b9c414fe0ccee3dc6f04f97dd4d0c6d5f
3
+ size 7736
output_model/irish_llama31_lora_data_v3/checkpoint-3500/zero_to_fp32.py ADDED
@@ -0,0 +1,592 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #!/usr/bin/env python
2
+
3
+ # Copyright (c) Microsoft Corporation.
4
+ # SPDX-License-Identifier: Apache-2.0
5
+
6
+ # DeepSpeed Team
7
+
8
+ # This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
9
+ # copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
10
+ # the future. Once extracted, the weights don't require DeepSpeed and can be used in any
11
+ # application.
12
+ #
13
+ # example: python zero_to_fp32.py . pytorch_model.bin
14
+
15
+ import argparse
16
+ import torch
17
+ import glob
18
+ import math
19
+ import os
20
+ import re
21
+ from collections import OrderedDict
22
+ from dataclasses import dataclass
23
+
24
+ # while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
25
+ # DeepSpeed data structures it has to be available in the current python environment.
26
+ from deepspeed.utils import logger
27
+ from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
28
+ FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
29
+ FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
30
+
31
+
32
+ @dataclass
33
+ class zero_model_state:
34
+ buffers: dict()
35
+ param_shapes: dict()
36
+ shared_params: list
37
+ ds_version: int
38
+ frozen_param_shapes: dict()
39
+ frozen_param_fragments: dict()
40
+
41
+
42
+ debug = 0
43
+
44
+ # load to cpu
45
+ device = torch.device('cpu')
46
+
47
+
48
+ def atoi(text):
49
+ return int(text) if text.isdigit() else text
50
+
51
+
52
+ def natural_keys(text):
53
+ '''
54
+ alist.sort(key=natural_keys) sorts in human order
55
+ http://nedbatchelder.com/blog/200712/human_sorting.html
56
+ (See Toothy's implementation in the comments)
57
+ '''
58
+ return [atoi(c) for c in re.split(r'(\d+)', text)]
59
+
60
+
61
+ def get_model_state_file(checkpoint_dir, zero_stage):
62
+ if not os.path.isdir(checkpoint_dir):
63
+ raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
64
+
65
+ # there should be only one file
66
+ if zero_stage <= 2:
67
+ file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
68
+ elif zero_stage == 3:
69
+ file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
70
+
71
+ if not os.path.exists(file):
72
+ raise FileNotFoundError(f"can't find model states file at '{file}'")
73
+
74
+ return file
75
+
76
+
77
+ def get_checkpoint_files(checkpoint_dir, glob_pattern):
78
+ # XXX: need to test that this simple glob rule works for multi-node setup too
79
+ ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
80
+
81
+ if len(ckpt_files) == 0:
82
+ raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
83
+
84
+ return ckpt_files
85
+
86
+
87
+ def get_optim_files(checkpoint_dir):
88
+ return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
89
+
90
+
91
+ def get_model_state_files(checkpoint_dir):
92
+ return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
93
+
94
+
95
+ def parse_model_states(files):
96
+ zero_model_states = []
97
+ for file in files:
98
+ state_dict = torch.load(file, map_location=device)
99
+
100
+ if BUFFER_NAMES not in state_dict:
101
+ raise ValueError(f"{file} is not a model state checkpoint")
102
+ buffer_names = state_dict[BUFFER_NAMES]
103
+ if debug:
104
+ print("Found buffers:", buffer_names)
105
+
106
+ # recover just the buffers while restoring them to fp32 if they were saved in fp16
107
+ buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
108
+ param_shapes = state_dict[PARAM_SHAPES]
109
+
110
+ # collect parameters that are included in param_shapes
111
+ param_names = []
112
+ for s in param_shapes:
113
+ for name in s.keys():
114
+ param_names.append(name)
115
+
116
+ # update with frozen parameters
117
+ frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
118
+ if frozen_param_shapes is not None:
119
+ if debug:
120
+ print(f"Found frozen_param_shapes: {frozen_param_shapes}")
121
+ param_names += list(frozen_param_shapes.keys())
122
+
123
+ # handle shared params
124
+ shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
125
+
126
+ ds_version = state_dict.get(DS_VERSION, None)
127
+
128
+ frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
129
+
130
+ z_model_state = zero_model_state(buffers=buffers,
131
+ param_shapes=param_shapes,
132
+ shared_params=shared_params,
133
+ ds_version=ds_version,
134
+ frozen_param_shapes=frozen_param_shapes,
135
+ frozen_param_fragments=frozen_param_fragments)
136
+ zero_model_states.append(z_model_state)
137
+
138
+ return zero_model_states
139
+
140
+
141
+ def parse_optim_states(files, ds_checkpoint_dir):
142
+
143
+ total_files = len(files)
144
+ state_dicts = []
145
+ for f in files:
146
+ state_dict = torch.load(f, map_location=device)
147
+ # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
148
+ # and also handle the case where it was already removed by another helper script
149
+ state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
150
+ state_dicts.append(state_dict)
151
+
152
+ if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
153
+ raise ValueError(f"{files[0]} is not a zero checkpoint")
154
+ zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
155
+ world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
156
+
157
+ # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
158
+ # parameters can be different from data parallelism for non-expert parameters. So we can just
159
+ # use the max of the partition_count to get the dp world_size.
160
+
161
+ if type(world_size) is list:
162
+ world_size = max(world_size)
163
+
164
+ if world_size != total_files:
165
+ raise ValueError(
166
+ f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
167
+ "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
168
+ )
169
+
170
+ # the groups are named differently in each stage
171
+ if zero_stage <= 2:
172
+ fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
173
+ elif zero_stage == 3:
174
+ fp32_groups_key = FP32_FLAT_GROUPS
175
+ else:
176
+ raise ValueError(f"unknown zero stage {zero_stage}")
177
+
178
+ if zero_stage <= 2:
179
+ fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
180
+ elif zero_stage == 3:
181
+ # if there is more than one param group, there will be multiple flattened tensors - one
182
+ # flattened tensor per group - for simplicity merge them into a single tensor
183
+ #
184
+ # XXX: could make the script more memory efficient for when there are multiple groups - it
185
+ # will require matching the sub-lists of param_shapes for each param group flattened tensor
186
+
187
+ fp32_flat_groups = [
188
+ torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
189
+ ]
190
+
191
+ return zero_stage, world_size, fp32_flat_groups
192
+
193
+
194
+ def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir):
195
+ """
196
+ Returns fp32 state_dict reconstructed from ds checkpoint
197
+
198
+ Args:
199
+ - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
200
+
201
+ """
202
+ print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
203
+
204
+ optim_files = get_optim_files(ds_checkpoint_dir)
205
+ zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
206
+ print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
207
+
208
+ model_files = get_model_state_files(ds_checkpoint_dir)
209
+
210
+ zero_model_states = parse_model_states(model_files)
211
+ print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
212
+
213
+ if zero_stage <= 2:
214
+ return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states)
215
+ elif zero_stage == 3:
216
+ return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states)
217
+
218
+
219
+ def _zero2_merge_frozen_params(state_dict, zero_model_states):
220
+ if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
221
+ return
222
+
223
+ frozen_param_shapes = zero_model_states[0].frozen_param_shapes
224
+ frozen_param_fragments = zero_model_states[0].frozen_param_fragments
225
+
226
+ if debug:
227
+ num_elem = sum(s.numel() for s in frozen_param_shapes.values())
228
+ print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
229
+
230
+ wanted_params = len(frozen_param_shapes)
231
+ wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
232
+ avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
233
+ print(f'Frozen params: Have {avail_numel} numels to process.')
234
+ print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
235
+
236
+ total_params = 0
237
+ total_numel = 0
238
+ for name, shape in frozen_param_shapes.items():
239
+ total_params += 1
240
+ unpartitioned_numel = shape.numel()
241
+ total_numel += unpartitioned_numel
242
+
243
+ state_dict[name] = frozen_param_fragments[name]
244
+
245
+ if debug:
246
+ print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
247
+
248
+ print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
249
+
250
+
251
+ def _has_callable(obj, fn):
252
+ attr = getattr(obj, fn, None)
253
+ return callable(attr)
254
+
255
+
256
+ def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
257
+ param_shapes = zero_model_states[0].param_shapes
258
+
259
+ # Reconstruction protocol:
260
+ #
261
+ # XXX: document this
262
+
263
+ if debug:
264
+ for i in range(world_size):
265
+ for j in range(len(fp32_flat_groups[0])):
266
+ print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
267
+
268
+ # XXX: memory usage doubles here (zero2)
269
+ num_param_groups = len(fp32_flat_groups[0])
270
+ merged_single_partition_of_fp32_groups = []
271
+ for i in range(num_param_groups):
272
+ merged_partitions = [sd[i] for sd in fp32_flat_groups]
273
+ full_single_fp32_vector = torch.cat(merged_partitions, 0)
274
+ merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
275
+ avail_numel = sum(
276
+ [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
277
+
278
+ if debug:
279
+ wanted_params = sum([len(shapes) for shapes in param_shapes])
280
+ wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
281
+ # not asserting if there is a mismatch due to possible padding
282
+ print(f"Have {avail_numel} numels to process.")
283
+ print(f"Need {wanted_numel} numels in {wanted_params} params.")
284
+
285
+ # params
286
+ # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
287
+ # out-of-core computing solution
288
+ total_numel = 0
289
+ total_params = 0
290
+ for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
291
+ offset = 0
292
+ avail_numel = full_single_fp32_vector.numel()
293
+ for name, shape in shapes.items():
294
+
295
+ unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
296
+ total_numel += unpartitioned_numel
297
+ total_params += 1
298
+
299
+ if debug:
300
+ print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
301
+ state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
302
+ offset += unpartitioned_numel
303
+
304
+ # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
305
+ # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
306
+ # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
307
+ # live optimizer object, so we are checking that the numbers are within the right range
308
+ align_to = 2 * world_size
309
+
310
+ def zero2_align(x):
311
+ return align_to * math.ceil(x / align_to)
312
+
313
+ if debug:
314
+ print(f"original offset={offset}, avail_numel={avail_numel}")
315
+
316
+ offset = zero2_align(offset)
317
+ avail_numel = zero2_align(avail_numel)
318
+
319
+ if debug:
320
+ print(f"aligned offset={offset}, avail_numel={avail_numel}")
321
+
322
+ # Sanity check
323
+ if offset != avail_numel:
324
+ raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
325
+
326
+ print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
327
+
328
+
329
+ def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states):
330
+ state_dict = OrderedDict()
331
+
332
+ # buffers
333
+ buffers = zero_model_states[0].buffers
334
+ state_dict.update(buffers)
335
+ if debug:
336
+ print(f"added {len(buffers)} buffers")
337
+
338
+ _zero2_merge_frozen_params(state_dict, zero_model_states)
339
+
340
+ _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
341
+
342
+ # recover shared parameters
343
+ for pair in zero_model_states[0].shared_params:
344
+ if pair[1] in state_dict:
345
+ state_dict[pair[0]] = state_dict[pair[1]]
346
+
347
+ return state_dict
348
+
349
+
350
+ def zero3_partitioned_param_info(unpartitioned_numel, world_size):
351
+ remainder = unpartitioned_numel % world_size
352
+ padding_numel = (world_size - remainder) if remainder else 0
353
+ partitioned_numel = math.ceil(unpartitioned_numel / world_size)
354
+ return partitioned_numel, padding_numel
355
+
356
+
357
+ def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
358
+ if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
359
+ return
360
+
361
+ if debug:
362
+ for i in range(world_size):
363
+ num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
364
+ print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
365
+
366
+ frozen_param_shapes = zero_model_states[0].frozen_param_shapes
367
+ wanted_params = len(frozen_param_shapes)
368
+ wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
369
+ avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
370
+ print(f'Frozen params: Have {avail_numel} numels to process.')
371
+ print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
372
+
373
+ total_params = 0
374
+ total_numel = 0
375
+ for name, shape in zero_model_states[0].frozen_param_shapes.items():
376
+ total_params += 1
377
+ unpartitioned_numel = shape.numel()
378
+ total_numel += unpartitioned_numel
379
+
380
+ param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
381
+ state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
382
+
383
+ partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
384
+
385
+ if debug:
386
+ print(
387
+ f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
388
+ )
389
+
390
+ print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
391
+
392
+
393
+ def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
394
+ param_shapes = zero_model_states[0].param_shapes
395
+ avail_numel = fp32_flat_groups[0].numel() * world_size
396
+ # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
397
+ # param, re-consolidating each param, while dealing with padding if any
398
+
399
+ # merge list of dicts, preserving order
400
+ param_shapes = {k: v for d in param_shapes for k, v in d.items()}
401
+
402
+ if debug:
403
+ for i in range(world_size):
404
+ print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
405
+
406
+ wanted_params = len(param_shapes)
407
+ wanted_numel = sum(shape.numel() for shape in param_shapes.values())
408
+ # not asserting if there is a mismatch due to possible padding
409
+ avail_numel = fp32_flat_groups[0].numel() * world_size
410
+ print(f"Trainable params: Have {avail_numel} numels to process.")
411
+ print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
412
+
413
+ # params
414
+ # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
415
+ # out-of-core computing solution
416
+ offset = 0
417
+ total_numel = 0
418
+ total_params = 0
419
+ for name, shape in param_shapes.items():
420
+
421
+ unpartitioned_numel = shape.numel()
422
+ total_numel += unpartitioned_numel
423
+ total_params += 1
424
+
425
+ partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
426
+
427
+ if debug:
428
+ print(
429
+ f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
430
+ )
431
+
432
+ # XXX: memory usage doubles here
433
+ state_dict[name] = torch.cat(
434
+ tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
435
+ 0).narrow(0, 0, unpartitioned_numel).view(shape)
436
+ offset += partitioned_numel
437
+
438
+ offset *= world_size
439
+
440
+ # Sanity check
441
+ if offset != avail_numel:
442
+ raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
443
+
444
+ print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
445
+
446
+
447
+ def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states):
448
+ state_dict = OrderedDict()
449
+
450
+ # buffers
451
+ buffers = zero_model_states[0].buffers
452
+ state_dict.update(buffers)
453
+ if debug:
454
+ print(f"added {len(buffers)} buffers")
455
+
456
+ _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
457
+
458
+ _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
459
+
460
+ # recover shared parameters
461
+ for pair in zero_model_states[0].shared_params:
462
+ if pair[1] in state_dict:
463
+ state_dict[pair[0]] = state_dict[pair[1]]
464
+
465
+ return state_dict
466
+
467
+
468
+ def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None):
469
+ """
470
+ Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
471
+ ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
472
+ via a model hub.
473
+
474
+ Args:
475
+ - ``checkpoint_dir``: path to the desired checkpoint folder
476
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
477
+
478
+ Returns:
479
+ - pytorch ``state_dict``
480
+
481
+ Note: this approach may not work if your application doesn't have sufficient free CPU memory and
482
+ you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
483
+ the checkpoint.
484
+
485
+ A typical usage might be ::
486
+
487
+ from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
488
+ # do the training and checkpoint saving
489
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
490
+ model = model.cpu() # move to cpu
491
+ model.load_state_dict(state_dict)
492
+ # submit to model hub or save the model to share with others
493
+
494
+ In this example the ``model`` will no longer be usable in the deepspeed context of the same
495
+ application. i.e. you will need to re-initialize the deepspeed engine, since
496
+ ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
497
+
498
+ If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
499
+
500
+ """
501
+ if tag is None:
502
+ latest_path = os.path.join(checkpoint_dir, 'latest')
503
+ if os.path.isfile(latest_path):
504
+ with open(latest_path, 'r') as fd:
505
+ tag = fd.read().strip()
506
+ else:
507
+ raise ValueError(f"Unable to find 'latest' file at {latest_path}")
508
+
509
+ ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
510
+
511
+ if not os.path.isdir(ds_checkpoint_dir):
512
+ raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
513
+
514
+ return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir)
515
+
516
+
517
+ def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None):
518
+ """
519
+ Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
520
+ loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
521
+
522
+ Args:
523
+ - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
524
+ - ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
525
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
526
+ """
527
+
528
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
529
+ print(f"Saving fp32 state dict to {output_file}")
530
+ torch.save(state_dict, output_file)
531
+
532
+
533
+ def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
534
+ """
535
+ 1. Put the provided model to cpu
536
+ 2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
537
+ 3. Load it into the provided model
538
+
539
+ Args:
540
+ - ``model``: the model object to update
541
+ - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
542
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
543
+
544
+ Returns:
545
+ - ``model`: modified model
546
+
547
+ Make sure you have plenty of CPU memory available before you call this function. If you don't
548
+ have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
549
+ conveniently placed for you in the checkpoint folder.
550
+
551
+ A typical usage might be ::
552
+
553
+ from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
554
+ model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
555
+ # submit to model hub or save the model to share with others
556
+
557
+ Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
558
+ of the same application. i.e. you will need to re-initialize the deepspeed engine, since
559
+ ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
560
+
561
+ """
562
+ logger.info(f"Extracting fp32 weights")
563
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
564
+
565
+ logger.info(f"Overwriting model with fp32 weights")
566
+ model = model.cpu()
567
+ model.load_state_dict(state_dict, strict=False)
568
+
569
+ return model
570
+
571
+
572
+ if __name__ == "__main__":
573
+
574
+ parser = argparse.ArgumentParser()
575
+ parser.add_argument("checkpoint_dir",
576
+ type=str,
577
+ help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
578
+ parser.add_argument(
579
+ "output_file",
580
+ type=str,
581
+ help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
582
+ parser.add_argument("-t",
583
+ "--tag",
584
+ type=str,
585
+ default=None,
586
+ help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
587
+ parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
588
+ args = parser.parse_args()
589
+
590
+ debug = args.debug
591
+
592
+ convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir, args.output_file, tag=args.tag)