mciccone commited on
Commit
0adabed
·
verified ·
1 Parent(s): 2521cbe

Add llama_finetune_mnist_ascii_r16_alpha=32_dropout=0.05_lr0.0001_data_size1000_max_steps=500_seed=123 LoRA model

Browse files
Files changed (19) hide show
  1. .gitattributes +2 -0
  2. llama_finetune_mnist_ascii_r16_alpha=32_dropout=0.05_lr0.0001_data_size1000_max_steps=500_seed=123/README.md +202 -0
  3. llama_finetune_mnist_ascii_r16_alpha=32_dropout=0.05_lr0.0001_data_size1000_max_steps=500_seed=123/adapter_config.json +39 -0
  4. llama_finetune_mnist_ascii_r16_alpha=32_dropout=0.05_lr0.0001_data_size1000_max_steps=500_seed=123/adapter_model.safetensors +3 -0
  5. llama_finetune_mnist_ascii_r16_alpha=32_dropout=0.05_lr0.0001_data_size1000_max_steps=500_seed=123/checkpoint-302/README.md +202 -0
  6. llama_finetune_mnist_ascii_r16_alpha=32_dropout=0.05_lr0.0001_data_size1000_max_steps=500_seed=123/checkpoint-302/adapter_config.json +39 -0
  7. llama_finetune_mnist_ascii_r16_alpha=32_dropout=0.05_lr0.0001_data_size1000_max_steps=500_seed=123/checkpoint-302/adapter_model.safetensors +3 -0
  8. llama_finetune_mnist_ascii_r16_alpha=32_dropout=0.05_lr0.0001_data_size1000_max_steps=500_seed=123/checkpoint-302/optimizer.pt +3 -0
  9. llama_finetune_mnist_ascii_r16_alpha=32_dropout=0.05_lr0.0001_data_size1000_max_steps=500_seed=123/checkpoint-302/rng_state.pth +3 -0
  10. llama_finetune_mnist_ascii_r16_alpha=32_dropout=0.05_lr0.0001_data_size1000_max_steps=500_seed=123/checkpoint-302/scheduler.pt +3 -0
  11. llama_finetune_mnist_ascii_r16_alpha=32_dropout=0.05_lr0.0001_data_size1000_max_steps=500_seed=123/checkpoint-302/special_tokens_map.json +17 -0
  12. llama_finetune_mnist_ascii_r16_alpha=32_dropout=0.05_lr0.0001_data_size1000_max_steps=500_seed=123/checkpoint-302/tokenizer.json +3 -0
  13. llama_finetune_mnist_ascii_r16_alpha=32_dropout=0.05_lr0.0001_data_size1000_max_steps=500_seed=123/checkpoint-302/tokenizer_config.json +2064 -0
  14. llama_finetune_mnist_ascii_r16_alpha=32_dropout=0.05_lr0.0001_data_size1000_max_steps=500_seed=123/checkpoint-302/trainer_state.json +2610 -0
  15. llama_finetune_mnist_ascii_r16_alpha=32_dropout=0.05_lr0.0001_data_size1000_max_steps=500_seed=123/checkpoint-302/training_args.bin +3 -0
  16. llama_finetune_mnist_ascii_r16_alpha=32_dropout=0.05_lr0.0001_data_size1000_max_steps=500_seed=123/special_tokens_map.json +17 -0
  17. llama_finetune_mnist_ascii_r16_alpha=32_dropout=0.05_lr0.0001_data_size1000_max_steps=500_seed=123/tokenizer.json +3 -0
  18. llama_finetune_mnist_ascii_r16_alpha=32_dropout=0.05_lr0.0001_data_size1000_max_steps=500_seed=123/tokenizer_config.json +2064 -0
  19. llama_finetune_mnist_ascii_r16_alpha=32_dropout=0.05_lr0.0001_data_size1000_max_steps=500_seed=123/training_args.bin +3 -0
.gitattributes CHANGED
@@ -39,3 +39,5 @@ llama_finetune_mnist_ascii_r16_alpha=32_dropout=0.05_lr0.0002_data_size1000_max_
39
  llama_finetune_mnist_ascii_r16_alpha=32_dropout=0.05_lr0.0002_data_size1000_max_steps=500_seed=123/tokenizer.json filter=lfs diff=lfs merge=lfs -text
40
  llama_finetune_mnist_ascii_r16_alpha=32_dropout=0.05_lr0.0003_data_size1000_max_steps=500_seed=123/checkpoint-36/tokenizer.json filter=lfs diff=lfs merge=lfs -text
41
  llama_finetune_mnist_ascii_r16_alpha=32_dropout=0.05_lr0.0003_data_size1000_max_steps=500_seed=123/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
39
  llama_finetune_mnist_ascii_r16_alpha=32_dropout=0.05_lr0.0002_data_size1000_max_steps=500_seed=123/tokenizer.json filter=lfs diff=lfs merge=lfs -text
40
  llama_finetune_mnist_ascii_r16_alpha=32_dropout=0.05_lr0.0003_data_size1000_max_steps=500_seed=123/checkpoint-36/tokenizer.json filter=lfs diff=lfs merge=lfs -text
41
  llama_finetune_mnist_ascii_r16_alpha=32_dropout=0.05_lr0.0003_data_size1000_max_steps=500_seed=123/tokenizer.json filter=lfs diff=lfs merge=lfs -text
42
+ llama_finetune_mnist_ascii_r16_alpha=32_dropout=0.05_lr0.0001_data_size1000_max_steps=500_seed=123/checkpoint-302/tokenizer.json filter=lfs diff=lfs merge=lfs -text
43
+ llama_finetune_mnist_ascii_r16_alpha=32_dropout=0.05_lr0.0001_data_size1000_max_steps=500_seed=123/tokenizer.json filter=lfs diff=lfs merge=lfs -text
llama_finetune_mnist_ascii_r16_alpha=32_dropout=0.05_lr0.0001_data_size1000_max_steps=500_seed=123/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Llama-3.1-8B-Instruct
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 0.15.1
llama_finetune_mnist_ascii_r16_alpha=32_dropout=0.05_lr0.0001_data_size1000_max_steps=500_seed=123/adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 32,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 16,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "k_proj",
28
+ "down_proj",
29
+ "q_proj",
30
+ "gate_proj",
31
+ "up_proj",
32
+ "o_proj",
33
+ "v_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
llama_finetune_mnist_ascii_r16_alpha=32_dropout=0.05_lr0.0001_data_size1000_max_steps=500_seed=123/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:678b856c3f06824674fbeb3b59f77c72a9f6fe1f94e5340361f2b325626919f1
3
+ size 167832240
llama_finetune_mnist_ascii_r16_alpha=32_dropout=0.05_lr0.0001_data_size1000_max_steps=500_seed=123/checkpoint-302/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Llama-3.1-8B-Instruct
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 0.15.1
llama_finetune_mnist_ascii_r16_alpha=32_dropout=0.05_lr0.0001_data_size1000_max_steps=500_seed=123/checkpoint-302/adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 32,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 16,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "k_proj",
28
+ "down_proj",
29
+ "q_proj",
30
+ "gate_proj",
31
+ "up_proj",
32
+ "o_proj",
33
+ "v_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
llama_finetune_mnist_ascii_r16_alpha=32_dropout=0.05_lr0.0001_data_size1000_max_steps=500_seed=123/checkpoint-302/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:678b856c3f06824674fbeb3b59f77c72a9f6fe1f94e5340361f2b325626919f1
3
+ size 167832240
llama_finetune_mnist_ascii_r16_alpha=32_dropout=0.05_lr0.0001_data_size1000_max_steps=500_seed=123/checkpoint-302/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b7d2044463f01a2ea76d615e336d370e28dd1577f91bb3fdbf758827df0330e
3
+ size 335922386
llama_finetune_mnist_ascii_r16_alpha=32_dropout=0.05_lr0.0001_data_size1000_max_steps=500_seed=123/checkpoint-302/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:441ccdcbd0067da3a229066c330bfe4f7559fbdebc5574cb80e382dc52000ece
3
+ size 14244
llama_finetune_mnist_ascii_r16_alpha=32_dropout=0.05_lr0.0001_data_size1000_max_steps=500_seed=123/checkpoint-302/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db070975dd1763f0668ee94d9d1994fbf0f527bdd7ae2bcf5bde9d2705ed7743
3
+ size 1064
llama_finetune_mnist_ascii_r16_alpha=32_dropout=0.05_lr0.0001_data_size1000_max_steps=500_seed=123/checkpoint-302/special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|eot_id|>"
17
+ }
llama_finetune_mnist_ascii_r16_alpha=32_dropout=0.05_lr0.0001_data_size1000_max_steps=500_seed=123/checkpoint-302/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
llama_finetune_mnist_ascii_r16_alpha=32_dropout=0.05_lr0.0001_data_size1000_max_steps=500_seed=123/checkpoint-302/tokenizer_config.json ADDED
@@ -0,0 +1,2064 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n {%- for arg_name, arg_val in tool_call.arguments | items %}\n {{- arg_name + '=\"' + arg_val + '\"' }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- else %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {%- endif %}\n {%- if builtin_tools is defined %}\n {#- This means we're in ipython mode #}\n {{- \"<|eom_id|>\" }}\n {%- else %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "extra_special_tokens": {},
2057
+ "model_input_names": [
2058
+ "input_ids",
2059
+ "attention_mask"
2060
+ ],
2061
+ "model_max_length": 131072,
2062
+ "pad_token": "<|eot_id|>",
2063
+ "tokenizer_class": "PreTrainedTokenizer"
2064
+ }
llama_finetune_mnist_ascii_r16_alpha=32_dropout=0.05_lr0.0001_data_size1000_max_steps=500_seed=123/checkpoint-302/trainer_state.json ADDED
@@ -0,0 +1,2610 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 302,
3
+ "best_metric": 0.25816527009010315,
4
+ "best_model_checkpoint": "/leonardo_scratch/fast/IscrC_dynaLORA/moose_experts_loras/mnist_ascii/llama_finetune_mnist_ascii_r16_alpha=32_dropout=0.05_lr0.0001_data_size1000_max_steps=500_seed=123/checkpoint-302",
5
+ "epoch": 4.8,
6
+ "eval_steps": 2,
7
+ "global_step": 302,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.032,
14
+ "grad_norm": 9.013144493103027,
15
+ "learning_rate": 2.0000000000000003e-06,
16
+ "loss": 1.5463,
17
+ "step": 2
18
+ },
19
+ {
20
+ "epoch": 0.032,
21
+ "eval_loss": 1.4439624547958374,
22
+ "eval_mean_token_accuracy": 0.545,
23
+ "eval_num_tokens": 5760.0,
24
+ "eval_runtime": 11.6056,
25
+ "eval_samples_per_second": 17.233,
26
+ "eval_steps_per_second": 17.233,
27
+ "step": 2
28
+ },
29
+ {
30
+ "epoch": 0.064,
31
+ "grad_norm": 7.328917980194092,
32
+ "learning_rate": 6e-06,
33
+ "loss": 1.4863,
34
+ "step": 4
35
+ },
36
+ {
37
+ "epoch": 0.064,
38
+ "eval_loss": 1.4247291088104248,
39
+ "eval_mean_token_accuracy": 0.55,
40
+ "eval_num_tokens": 11739.0,
41
+ "eval_runtime": 11.6559,
42
+ "eval_samples_per_second": 17.159,
43
+ "eval_steps_per_second": 17.159,
44
+ "step": 4
45
+ },
46
+ {
47
+ "epoch": 0.096,
48
+ "grad_norm": 7.1580095291137695,
49
+ "learning_rate": 1e-05,
50
+ "loss": 1.4246,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.096,
55
+ "eval_loss": 1.3795454502105713,
56
+ "eval_mean_token_accuracy": 0.5475,
57
+ "eval_num_tokens": 17723.0,
58
+ "eval_runtime": 11.6615,
59
+ "eval_samples_per_second": 17.15,
60
+ "eval_steps_per_second": 17.15,
61
+ "step": 6
62
+ },
63
+ {
64
+ "epoch": 0.128,
65
+ "grad_norm": 3.38429594039917,
66
+ "learning_rate": 1.4000000000000001e-05,
67
+ "loss": 1.4199,
68
+ "step": 8
69
+ },
70
+ {
71
+ "epoch": 0.128,
72
+ "eval_loss": 1.2731733322143555,
73
+ "eval_mean_token_accuracy": 0.5525,
74
+ "eval_num_tokens": 23615.0,
75
+ "eval_runtime": 11.645,
76
+ "eval_samples_per_second": 17.175,
77
+ "eval_steps_per_second": 17.175,
78
+ "step": 8
79
+ },
80
+ {
81
+ "epoch": 0.16,
82
+ "grad_norm": 3.0774154663085938,
83
+ "learning_rate": 1.8e-05,
84
+ "loss": 1.2612,
85
+ "step": 10
86
+ },
87
+ {
88
+ "epoch": 0.16,
89
+ "eval_loss": 1.1942706108093262,
90
+ "eval_mean_token_accuracy": 0.5525,
91
+ "eval_num_tokens": 29811.0,
92
+ "eval_runtime": 11.5772,
93
+ "eval_samples_per_second": 17.275,
94
+ "eval_steps_per_second": 17.275,
95
+ "step": 10
96
+ },
97
+ {
98
+ "epoch": 0.192,
99
+ "grad_norm": 3.5880250930786133,
100
+ "learning_rate": 2.2000000000000003e-05,
101
+ "loss": 1.1789,
102
+ "step": 12
103
+ },
104
+ {
105
+ "epoch": 0.192,
106
+ "eval_loss": 1.1788699626922607,
107
+ "eval_mean_token_accuracy": 0.54,
108
+ "eval_num_tokens": 35772.0,
109
+ "eval_runtime": 11.6843,
110
+ "eval_samples_per_second": 17.117,
111
+ "eval_steps_per_second": 17.117,
112
+ "step": 12
113
+ },
114
+ {
115
+ "epoch": 0.224,
116
+ "grad_norm": 2.078965902328491,
117
+ "learning_rate": 2.6000000000000002e-05,
118
+ "loss": 1.1819,
119
+ "step": 14
120
+ },
121
+ {
122
+ "epoch": 0.224,
123
+ "eval_loss": 1.1894700527191162,
124
+ "eval_mean_token_accuracy": 0.555,
125
+ "eval_num_tokens": 41639.0,
126
+ "eval_runtime": 11.5754,
127
+ "eval_samples_per_second": 17.278,
128
+ "eval_steps_per_second": 17.278,
129
+ "step": 14
130
+ },
131
+ {
132
+ "epoch": 0.256,
133
+ "grad_norm": 2.9846999645233154,
134
+ "learning_rate": 3e-05,
135
+ "loss": 1.1663,
136
+ "step": 16
137
+ },
138
+ {
139
+ "epoch": 0.256,
140
+ "eval_loss": 1.2054526805877686,
141
+ "eval_mean_token_accuracy": 0.545,
142
+ "eval_num_tokens": 47579.0,
143
+ "eval_runtime": 11.6426,
144
+ "eval_samples_per_second": 17.178,
145
+ "eval_steps_per_second": 17.178,
146
+ "step": 16
147
+ },
148
+ {
149
+ "epoch": 0.288,
150
+ "grad_norm": 2.8348846435546875,
151
+ "learning_rate": 3.4000000000000007e-05,
152
+ "loss": 1.2101,
153
+ "step": 18
154
+ },
155
+ {
156
+ "epoch": 0.288,
157
+ "eval_loss": 1.164050579071045,
158
+ "eval_mean_token_accuracy": 0.555,
159
+ "eval_num_tokens": 53392.0,
160
+ "eval_runtime": 11.6595,
161
+ "eval_samples_per_second": 17.153,
162
+ "eval_steps_per_second": 17.153,
163
+ "step": 18
164
+ },
165
+ {
166
+ "epoch": 0.32,
167
+ "grad_norm": 1.1829537153244019,
168
+ "learning_rate": 3.8e-05,
169
+ "loss": 1.1379,
170
+ "step": 20
171
+ },
172
+ {
173
+ "epoch": 0.32,
174
+ "eval_loss": 1.1561341285705566,
175
+ "eval_mean_token_accuracy": 0.5425,
176
+ "eval_num_tokens": 59239.0,
177
+ "eval_runtime": 11.7232,
178
+ "eval_samples_per_second": 17.06,
179
+ "eval_steps_per_second": 17.06,
180
+ "step": 20
181
+ },
182
+ {
183
+ "epoch": 0.352,
184
+ "grad_norm": 0.7863202691078186,
185
+ "learning_rate": 4.2e-05,
186
+ "loss": 1.1516,
187
+ "step": 22
188
+ },
189
+ {
190
+ "epoch": 0.352,
191
+ "eval_loss": 1.1525884866714478,
192
+ "eval_mean_token_accuracy": 0.5475,
193
+ "eval_num_tokens": 65072.0,
194
+ "eval_runtime": 11.6531,
195
+ "eval_samples_per_second": 17.163,
196
+ "eval_steps_per_second": 17.163,
197
+ "step": 22
198
+ },
199
+ {
200
+ "epoch": 0.384,
201
+ "grad_norm": 0.8392149209976196,
202
+ "learning_rate": 4.600000000000001e-05,
203
+ "loss": 1.1268,
204
+ "step": 24
205
+ },
206
+ {
207
+ "epoch": 0.384,
208
+ "eval_loss": 1.1564841270446777,
209
+ "eval_mean_token_accuracy": 0.5425,
210
+ "eval_num_tokens": 70850.0,
211
+ "eval_runtime": 11.6844,
212
+ "eval_samples_per_second": 17.117,
213
+ "eval_steps_per_second": 17.117,
214
+ "step": 24
215
+ },
216
+ {
217
+ "epoch": 0.416,
218
+ "grad_norm": 0.5043415427207947,
219
+ "learning_rate": 5e-05,
220
+ "loss": 1.1458,
221
+ "step": 26
222
+ },
223
+ {
224
+ "epoch": 0.416,
225
+ "eval_loss": 1.1647623777389526,
226
+ "eval_mean_token_accuracy": 0.565,
227
+ "eval_num_tokens": 76641.0,
228
+ "eval_runtime": 11.6535,
229
+ "eval_samples_per_second": 17.162,
230
+ "eval_steps_per_second": 17.162,
231
+ "step": 26
232
+ },
233
+ {
234
+ "epoch": 0.448,
235
+ "grad_norm": 0.8126670122146606,
236
+ "learning_rate": 5.4000000000000005e-05,
237
+ "loss": 1.133,
238
+ "step": 28
239
+ },
240
+ {
241
+ "epoch": 0.448,
242
+ "eval_loss": 1.1799647808074951,
243
+ "eval_mean_token_accuracy": 0.5575,
244
+ "eval_num_tokens": 82530.0,
245
+ "eval_runtime": 11.7468,
246
+ "eval_samples_per_second": 17.026,
247
+ "eval_steps_per_second": 17.026,
248
+ "step": 28
249
+ },
250
+ {
251
+ "epoch": 0.48,
252
+ "grad_norm": 1.820698857307434,
253
+ "learning_rate": 5.8e-05,
254
+ "loss": 1.1654,
255
+ "step": 30
256
+ },
257
+ {
258
+ "epoch": 0.48,
259
+ "eval_loss": 1.1910687685012817,
260
+ "eval_mean_token_accuracy": 0.545,
261
+ "eval_num_tokens": 88605.0,
262
+ "eval_runtime": 11.7381,
263
+ "eval_samples_per_second": 17.039,
264
+ "eval_steps_per_second": 17.039,
265
+ "step": 30
266
+ },
267
+ {
268
+ "epoch": 0.512,
269
+ "grad_norm": 2.567795515060425,
270
+ "learning_rate": 6.2e-05,
271
+ "loss": 1.1549,
272
+ "step": 32
273
+ },
274
+ {
275
+ "epoch": 0.512,
276
+ "eval_loss": 1.181782841682434,
277
+ "eval_mean_token_accuracy": 0.585,
278
+ "eval_num_tokens": 94689.0,
279
+ "eval_runtime": 11.6964,
280
+ "eval_samples_per_second": 17.099,
281
+ "eval_steps_per_second": 17.099,
282
+ "step": 32
283
+ },
284
+ {
285
+ "epoch": 0.544,
286
+ "grad_norm": 2.052201271057129,
287
+ "learning_rate": 6.6e-05,
288
+ "loss": 1.1773,
289
+ "step": 34
290
+ },
291
+ {
292
+ "epoch": 0.544,
293
+ "eval_loss": 1.1538203954696655,
294
+ "eval_mean_token_accuracy": 0.5725,
295
+ "eval_num_tokens": 100530.0,
296
+ "eval_runtime": 11.634,
297
+ "eval_samples_per_second": 17.191,
298
+ "eval_steps_per_second": 17.191,
299
+ "step": 34
300
+ },
301
+ {
302
+ "epoch": 0.576,
303
+ "grad_norm": 1.9380916357040405,
304
+ "learning_rate": 7e-05,
305
+ "loss": 1.1473,
306
+ "step": 36
307
+ },
308
+ {
309
+ "epoch": 0.576,
310
+ "eval_loss": 1.1465160846710205,
311
+ "eval_mean_token_accuracy": 0.585,
312
+ "eval_num_tokens": 106574.0,
313
+ "eval_runtime": 11.6185,
314
+ "eval_samples_per_second": 17.214,
315
+ "eval_steps_per_second": 17.214,
316
+ "step": 36
317
+ },
318
+ {
319
+ "epoch": 0.608,
320
+ "grad_norm": 0.7976133823394775,
321
+ "learning_rate": 7.4e-05,
322
+ "loss": 1.1402,
323
+ "step": 38
324
+ },
325
+ {
326
+ "epoch": 0.608,
327
+ "eval_loss": 1.137180209159851,
328
+ "eval_mean_token_accuracy": 0.58,
329
+ "eval_num_tokens": 112599.0,
330
+ "eval_runtime": 11.6483,
331
+ "eval_samples_per_second": 17.17,
332
+ "eval_steps_per_second": 17.17,
333
+ "step": 38
334
+ },
335
+ {
336
+ "epoch": 0.64,
337
+ "grad_norm": 9.371255874633789,
338
+ "learning_rate": 7.800000000000001e-05,
339
+ "loss": 1.1693,
340
+ "step": 40
341
+ },
342
+ {
343
+ "epoch": 0.64,
344
+ "eval_loss": 1.2734227180480957,
345
+ "eval_mean_token_accuracy": 0.5425,
346
+ "eval_num_tokens": 118466.0,
347
+ "eval_runtime": 11.6097,
348
+ "eval_samples_per_second": 17.227,
349
+ "eval_steps_per_second": 17.227,
350
+ "step": 40
351
+ },
352
+ {
353
+ "epoch": 0.672,
354
+ "grad_norm": 2.481456756591797,
355
+ "learning_rate": 8.2e-05,
356
+ "loss": 1.2694,
357
+ "step": 42
358
+ },
359
+ {
360
+ "epoch": 0.672,
361
+ "eval_loss": 1.141395926475525,
362
+ "eval_mean_token_accuracy": 0.5725,
363
+ "eval_num_tokens": 124446.0,
364
+ "eval_runtime": 11.5998,
365
+ "eval_samples_per_second": 17.242,
366
+ "eval_steps_per_second": 17.242,
367
+ "step": 42
368
+ },
369
+ {
370
+ "epoch": 0.704,
371
+ "grad_norm": 1.7219722270965576,
372
+ "learning_rate": 8.6e-05,
373
+ "loss": 1.115,
374
+ "step": 44
375
+ },
376
+ {
377
+ "epoch": 0.704,
378
+ "eval_loss": 1.1360538005828857,
379
+ "eval_mean_token_accuracy": 0.5925,
380
+ "eval_num_tokens": 130103.0,
381
+ "eval_runtime": 11.5855,
382
+ "eval_samples_per_second": 17.263,
383
+ "eval_steps_per_second": 17.263,
384
+ "step": 44
385
+ },
386
+ {
387
+ "epoch": 0.736,
388
+ "grad_norm": 2.721323251724243,
389
+ "learning_rate": 9e-05,
390
+ "loss": 1.1638,
391
+ "step": 46
392
+ },
393
+ {
394
+ "epoch": 0.736,
395
+ "eval_loss": 1.1194626092910767,
396
+ "eval_mean_token_accuracy": 0.5875,
397
+ "eval_num_tokens": 135932.0,
398
+ "eval_runtime": 11.6059,
399
+ "eval_samples_per_second": 17.233,
400
+ "eval_steps_per_second": 17.233,
401
+ "step": 46
402
+ },
403
+ {
404
+ "epoch": 0.768,
405
+ "grad_norm": 1.7657800912857056,
406
+ "learning_rate": 9.4e-05,
407
+ "loss": 1.119,
408
+ "step": 48
409
+ },
410
+ {
411
+ "epoch": 0.768,
412
+ "eval_loss": 1.0902725458145142,
413
+ "eval_mean_token_accuracy": 0.595,
414
+ "eval_num_tokens": 142035.0,
415
+ "eval_runtime": 11.5018,
416
+ "eval_samples_per_second": 17.389,
417
+ "eval_steps_per_second": 17.389,
418
+ "step": 48
419
+ },
420
+ {
421
+ "epoch": 0.8,
422
+ "grad_norm": 3.8517637252807617,
423
+ "learning_rate": 9.8e-05,
424
+ "loss": 1.1047,
425
+ "step": 50
426
+ },
427
+ {
428
+ "epoch": 0.8,
429
+ "eval_loss": 1.2831567525863647,
430
+ "eval_mean_token_accuracy": 0.59,
431
+ "eval_num_tokens": 148093.0,
432
+ "eval_runtime": 11.6285,
433
+ "eval_samples_per_second": 17.199,
434
+ "eval_steps_per_second": 17.199,
435
+ "step": 50
436
+ },
437
+ {
438
+ "epoch": 0.832,
439
+ "grad_norm": 3.403735876083374,
440
+ "learning_rate": 9.999878153526974e-05,
441
+ "loss": 1.1048,
442
+ "step": 52
443
+ },
444
+ {
445
+ "epoch": 0.832,
446
+ "eval_loss": 1.0715610980987549,
447
+ "eval_mean_token_accuracy": 0.6125,
448
+ "eval_num_tokens": 153763.0,
449
+ "eval_runtime": 11.6288,
450
+ "eval_samples_per_second": 17.199,
451
+ "eval_steps_per_second": 17.199,
452
+ "step": 52
453
+ },
454
+ {
455
+ "epoch": 0.864,
456
+ "grad_norm": 2.0196611881256104,
457
+ "learning_rate": 9.998903417374228e-05,
458
+ "loss": 1.0575,
459
+ "step": 54
460
+ },
461
+ {
462
+ "epoch": 0.864,
463
+ "eval_loss": 1.0324335098266602,
464
+ "eval_mean_token_accuracy": 0.605,
465
+ "eval_num_tokens": 159772.0,
466
+ "eval_runtime": 11.5772,
467
+ "eval_samples_per_second": 17.275,
468
+ "eval_steps_per_second": 17.275,
469
+ "step": 54
470
+ },
471
+ {
472
+ "epoch": 0.896,
473
+ "grad_norm": 5.482478618621826,
474
+ "learning_rate": 9.99695413509548e-05,
475
+ "loss": 1.052,
476
+ "step": 56
477
+ },
478
+ {
479
+ "epoch": 0.896,
480
+ "eval_loss": 1.103353500366211,
481
+ "eval_mean_token_accuracy": 0.595,
482
+ "eval_num_tokens": 165825.0,
483
+ "eval_runtime": 11.5839,
484
+ "eval_samples_per_second": 17.265,
485
+ "eval_steps_per_second": 17.265,
486
+ "step": 56
487
+ },
488
+ {
489
+ "epoch": 0.928,
490
+ "grad_norm": 6.864939212799072,
491
+ "learning_rate": 9.99403068670717e-05,
492
+ "loss": 1.0159,
493
+ "step": 58
494
+ },
495
+ {
496
+ "epoch": 0.928,
497
+ "eval_loss": 1.0455049276351929,
498
+ "eval_mean_token_accuracy": 0.6025,
499
+ "eval_num_tokens": 171684.0,
500
+ "eval_runtime": 11.6213,
501
+ "eval_samples_per_second": 17.21,
502
+ "eval_steps_per_second": 17.21,
503
+ "step": 58
504
+ },
505
+ {
506
+ "epoch": 0.96,
507
+ "grad_norm": 1.7931485176086426,
508
+ "learning_rate": 9.990133642141359e-05,
509
+ "loss": 1.0654,
510
+ "step": 60
511
+ },
512
+ {
513
+ "epoch": 0.96,
514
+ "eval_loss": 1.0302832126617432,
515
+ "eval_mean_token_accuracy": 0.6,
516
+ "eval_num_tokens": 177701.0,
517
+ "eval_runtime": 11.6169,
518
+ "eval_samples_per_second": 17.216,
519
+ "eval_steps_per_second": 17.216,
520
+ "step": 60
521
+ },
522
+ {
523
+ "epoch": 0.992,
524
+ "grad_norm": 6.742156505584717,
525
+ "learning_rate": 9.985263761134602e-05,
526
+ "loss": 1.1051,
527
+ "step": 62
528
+ },
529
+ {
530
+ "epoch": 0.992,
531
+ "eval_loss": 1.0352920293807983,
532
+ "eval_mean_token_accuracy": 0.6175,
533
+ "eval_num_tokens": 183769.0,
534
+ "eval_runtime": 11.597,
535
+ "eval_samples_per_second": 17.246,
536
+ "eval_steps_per_second": 17.246,
537
+ "step": 62
538
+ },
539
+ {
540
+ "epoch": 1.016,
541
+ "grad_norm": 3.4277539253234863,
542
+ "learning_rate": 9.979421993079852e-05,
543
+ "loss": 0.8868,
544
+ "step": 64
545
+ },
546
+ {
547
+ "epoch": 1.016,
548
+ "eval_loss": 1.0380451679229736,
549
+ "eval_mean_token_accuracy": 0.5975,
550
+ "eval_num_tokens": 188248.0,
551
+ "eval_runtime": 11.5644,
552
+ "eval_samples_per_second": 17.294,
553
+ "eval_steps_per_second": 17.294,
554
+ "step": 64
555
+ },
556
+ {
557
+ "epoch": 1.048,
558
+ "grad_norm": 2.558476448059082,
559
+ "learning_rate": 9.972609476841367e-05,
560
+ "loss": 1.1105,
561
+ "step": 66
562
+ },
563
+ {
564
+ "epoch": 1.048,
565
+ "eval_loss": 1.071835994720459,
566
+ "eval_mean_token_accuracy": 0.5975,
567
+ "eval_num_tokens": 194384.0,
568
+ "eval_runtime": 11.5698,
569
+ "eval_samples_per_second": 17.286,
570
+ "eval_steps_per_second": 17.286,
571
+ "step": 66
572
+ },
573
+ {
574
+ "epoch": 1.08,
575
+ "grad_norm": 6.221016883850098,
576
+ "learning_rate": 9.964827540532685e-05,
577
+ "loss": 1.0216,
578
+ "step": 68
579
+ },
580
+ {
581
+ "epoch": 1.08,
582
+ "eval_loss": 1.0212624073028564,
583
+ "eval_mean_token_accuracy": 0.6425,
584
+ "eval_num_tokens": 200220.0,
585
+ "eval_runtime": 11.5961,
586
+ "eval_samples_per_second": 17.247,
587
+ "eval_steps_per_second": 17.247,
588
+ "step": 68
589
+ },
590
+ {
591
+ "epoch": 1.112,
592
+ "grad_norm": 10.758465766906738,
593
+ "learning_rate": 9.956077701257709e-05,
594
+ "loss": 1.0558,
595
+ "step": 70
596
+ },
597
+ {
598
+ "epoch": 1.112,
599
+ "eval_loss": 1.2903714179992676,
600
+ "eval_mean_token_accuracy": 0.555,
601
+ "eval_num_tokens": 206156.0,
602
+ "eval_runtime": 11.5859,
603
+ "eval_samples_per_second": 17.262,
604
+ "eval_steps_per_second": 17.262,
605
+ "step": 70
606
+ },
607
+ {
608
+ "epoch": 1.144,
609
+ "grad_norm": 6.4681315422058105,
610
+ "learning_rate": 9.946361664814943e-05,
611
+ "loss": 1.5208,
612
+ "step": 72
613
+ },
614
+ {
615
+ "epoch": 1.144,
616
+ "eval_loss": 1.074670433998108,
617
+ "eval_mean_token_accuracy": 0.555,
618
+ "eval_num_tokens": 212093.0,
619
+ "eval_runtime": 11.5853,
620
+ "eval_samples_per_second": 17.263,
621
+ "eval_steps_per_second": 17.263,
622
+ "step": 72
623
+ },
624
+ {
625
+ "epoch": 1.176,
626
+ "grad_norm": 2.195157527923584,
627
+ "learning_rate": 9.93568132536494e-05,
628
+ "loss": 0.9283,
629
+ "step": 74
630
+ },
631
+ {
632
+ "epoch": 1.176,
633
+ "eval_loss": 1.0210366249084473,
634
+ "eval_mean_token_accuracy": 0.6275,
635
+ "eval_num_tokens": 217901.0,
636
+ "eval_runtime": 11.4038,
637
+ "eval_samples_per_second": 17.538,
638
+ "eval_steps_per_second": 17.538,
639
+ "step": 74
640
+ },
641
+ {
642
+ "epoch": 1.208,
643
+ "grad_norm": 2.412698745727539,
644
+ "learning_rate": 9.924038765061042e-05,
645
+ "loss": 1.0165,
646
+ "step": 76
647
+ },
648
+ {
649
+ "epoch": 1.208,
650
+ "eval_loss": 0.9786829948425293,
651
+ "eval_mean_token_accuracy": 0.6725,
652
+ "eval_num_tokens": 223881.0,
653
+ "eval_runtime": 11.4973,
654
+ "eval_samples_per_second": 17.395,
655
+ "eval_steps_per_second": 17.395,
656
+ "step": 76
657
+ },
658
+ {
659
+ "epoch": 1.24,
660
+ "grad_norm": 2.014554738998413,
661
+ "learning_rate": 9.911436253643445e-05,
662
+ "loss": 0.951,
663
+ "step": 78
664
+ },
665
+ {
666
+ "epoch": 1.24,
667
+ "eval_loss": 0.9670297503471375,
668
+ "eval_mean_token_accuracy": 0.6575,
669
+ "eval_num_tokens": 229667.0,
670
+ "eval_runtime": 11.5533,
671
+ "eval_samples_per_second": 17.311,
672
+ "eval_steps_per_second": 17.311,
673
+ "step": 78
674
+ },
675
+ {
676
+ "epoch": 1.272,
677
+ "grad_norm": 2.1351048946380615,
678
+ "learning_rate": 9.89787624799672e-05,
679
+ "loss": 0.8453,
680
+ "step": 80
681
+ },
682
+ {
683
+ "epoch": 1.272,
684
+ "eval_loss": 1.0084736347198486,
685
+ "eval_mean_token_accuracy": 0.6275,
686
+ "eval_num_tokens": 235565.0,
687
+ "eval_runtime": 11.5423,
688
+ "eval_samples_per_second": 17.327,
689
+ "eval_steps_per_second": 17.327,
690
+ "step": 80
691
+ },
692
+ {
693
+ "epoch": 1.304,
694
+ "grad_norm": 2.1966516971588135,
695
+ "learning_rate": 9.88336139167084e-05,
696
+ "loss": 1.0813,
697
+ "step": 82
698
+ },
699
+ {
700
+ "epoch": 1.304,
701
+ "eval_loss": 0.9398559331893921,
702
+ "eval_mean_token_accuracy": 0.6375,
703
+ "eval_num_tokens": 241524.0,
704
+ "eval_runtime": 11.5668,
705
+ "eval_samples_per_second": 17.291,
706
+ "eval_steps_per_second": 17.291,
707
+ "step": 82
708
+ },
709
+ {
710
+ "epoch": 1.336,
711
+ "grad_norm": 3.937615394592285,
712
+ "learning_rate": 9.867894514365802e-05,
713
+ "loss": 0.9133,
714
+ "step": 84
715
+ },
716
+ {
717
+ "epoch": 1.336,
718
+ "eval_loss": 0.9361262321472168,
719
+ "eval_mean_token_accuracy": 0.6225,
720
+ "eval_num_tokens": 247529.0,
721
+ "eval_runtime": 11.5248,
722
+ "eval_samples_per_second": 17.354,
723
+ "eval_steps_per_second": 17.354,
724
+ "step": 84
725
+ },
726
+ {
727
+ "epoch": 1.3679999999999999,
728
+ "grad_norm": 2.589369535446167,
729
+ "learning_rate": 9.851478631379982e-05,
730
+ "loss": 0.8743,
731
+ "step": 86
732
+ },
733
+ {
734
+ "epoch": 1.3679999999999999,
735
+ "eval_loss": 0.9539607763290405,
736
+ "eval_mean_token_accuracy": 0.63,
737
+ "eval_num_tokens": 253397.0,
738
+ "eval_runtime": 11.5633,
739
+ "eval_samples_per_second": 17.296,
740
+ "eval_steps_per_second": 17.296,
741
+ "step": 86
742
+ },
743
+ {
744
+ "epoch": 1.4,
745
+ "grad_norm": 5.9693379402160645,
746
+ "learning_rate": 9.834116943022298e-05,
747
+ "loss": 0.9755,
748
+ "step": 88
749
+ },
750
+ {
751
+ "epoch": 1.4,
752
+ "eval_loss": 0.8547177314758301,
753
+ "eval_mean_token_accuracy": 0.6775,
754
+ "eval_num_tokens": 259421.0,
755
+ "eval_runtime": 11.484,
756
+ "eval_samples_per_second": 17.416,
757
+ "eval_steps_per_second": 17.416,
758
+ "step": 88
759
+ },
760
+ {
761
+ "epoch": 1.432,
762
+ "grad_norm": 2.1944351196289062,
763
+ "learning_rate": 9.815812833988291e-05,
764
+ "loss": 0.7632,
765
+ "step": 90
766
+ },
767
+ {
768
+ "epoch": 1.432,
769
+ "eval_loss": 0.8416257500648499,
770
+ "eval_mean_token_accuracy": 0.685,
771
+ "eval_num_tokens": 265327.0,
772
+ "eval_runtime": 11.7341,
773
+ "eval_samples_per_second": 17.044,
774
+ "eval_steps_per_second": 17.044,
775
+ "step": 90
776
+ },
777
+ {
778
+ "epoch": 1.464,
779
+ "grad_norm": 12.118799209594727,
780
+ "learning_rate": 9.796569872700288e-05,
781
+ "loss": 0.9226,
782
+ "step": 92
783
+ },
784
+ {
785
+ "epoch": 1.464,
786
+ "eval_loss": 0.8677136301994324,
787
+ "eval_mean_token_accuracy": 0.675,
788
+ "eval_num_tokens": 271182.0,
789
+ "eval_runtime": 11.4657,
790
+ "eval_samples_per_second": 17.443,
791
+ "eval_steps_per_second": 17.443,
792
+ "step": 92
793
+ },
794
+ {
795
+ "epoch": 1.496,
796
+ "grad_norm": 10.485864639282227,
797
+ "learning_rate": 9.776391810611718e-05,
798
+ "loss": 0.7533,
799
+ "step": 94
800
+ },
801
+ {
802
+ "epoch": 1.496,
803
+ "eval_loss": 1.0873095989227295,
804
+ "eval_mean_token_accuracy": 0.675,
805
+ "eval_num_tokens": 277149.0,
806
+ "eval_runtime": 11.4793,
807
+ "eval_samples_per_second": 17.423,
808
+ "eval_steps_per_second": 17.423,
809
+ "step": 94
810
+ },
811
+ {
812
+ "epoch": 1.528,
813
+ "grad_norm": 5.520583629608154,
814
+ "learning_rate": 9.755282581475769e-05,
815
+ "loss": 0.8816,
816
+ "step": 96
817
+ },
818
+ {
819
+ "epoch": 1.528,
820
+ "eval_loss": 0.8469552397727966,
821
+ "eval_mean_token_accuracy": 0.6675,
822
+ "eval_num_tokens": 283127.0,
823
+ "eval_runtime": 11.6386,
824
+ "eval_samples_per_second": 17.184,
825
+ "eval_steps_per_second": 17.184,
826
+ "step": 96
827
+ },
828
+ {
829
+ "epoch": 1.56,
830
+ "grad_norm": 8.580490112304688,
831
+ "learning_rate": 9.733246300578483e-05,
832
+ "loss": 1.2178,
833
+ "step": 98
834
+ },
835
+ {
836
+ "epoch": 1.56,
837
+ "eval_loss": 0.8359712958335876,
838
+ "eval_mean_token_accuracy": 0.6725,
839
+ "eval_num_tokens": 288990.0,
840
+ "eval_runtime": 11.6621,
841
+ "eval_samples_per_second": 17.15,
842
+ "eval_steps_per_second": 17.15,
843
+ "step": 98
844
+ },
845
+ {
846
+ "epoch": 1.592,
847
+ "grad_norm": 3.0713951587677,
848
+ "learning_rate": 9.710287263936484e-05,
849
+ "loss": 0.7942,
850
+ "step": 100
851
+ },
852
+ {
853
+ "epoch": 1.592,
854
+ "eval_loss": 0.8671708703041077,
855
+ "eval_mean_token_accuracy": 0.6775,
856
+ "eval_num_tokens": 294998.0,
857
+ "eval_runtime": 11.6218,
858
+ "eval_samples_per_second": 17.209,
859
+ "eval_steps_per_second": 17.209,
860
+ "step": 100
861
+ },
862
+ {
863
+ "epoch": 1.624,
864
+ "grad_norm": 4.100128173828125,
865
+ "learning_rate": 9.686409947459458e-05,
866
+ "loss": 0.8554,
867
+ "step": 102
868
+ },
869
+ {
870
+ "epoch": 1.624,
871
+ "eval_loss": 0.8359519839286804,
872
+ "eval_mean_token_accuracy": 0.6875,
873
+ "eval_num_tokens": 300848.0,
874
+ "eval_runtime": 11.6038,
875
+ "eval_samples_per_second": 17.236,
876
+ "eval_steps_per_second": 17.236,
877
+ "step": 102
878
+ },
879
+ {
880
+ "epoch": 1.6560000000000001,
881
+ "grad_norm": 5.881307125091553,
882
+ "learning_rate": 9.661619006077561e-05,
883
+ "loss": 0.9212,
884
+ "step": 104
885
+ },
886
+ {
887
+ "epoch": 1.6560000000000001,
888
+ "eval_loss": 0.8727825880050659,
889
+ "eval_mean_token_accuracy": 0.6425,
890
+ "eval_num_tokens": 306815.0,
891
+ "eval_runtime": 11.6286,
892
+ "eval_samples_per_second": 17.199,
893
+ "eval_steps_per_second": 17.199,
894
+ "step": 104
895
+ },
896
+ {
897
+ "epoch": 1.688,
898
+ "grad_norm": 3.8210153579711914,
899
+ "learning_rate": 9.635919272833938e-05,
900
+ "loss": 0.7382,
901
+ "step": 106
902
+ },
903
+ {
904
+ "epoch": 1.688,
905
+ "eval_loss": 0.8512636423110962,
906
+ "eval_mean_token_accuracy": 0.645,
907
+ "eval_num_tokens": 312647.0,
908
+ "eval_runtime": 11.6241,
909
+ "eval_samples_per_second": 17.206,
910
+ "eval_steps_per_second": 17.206,
911
+ "step": 106
912
+ },
913
+ {
914
+ "epoch": 1.72,
915
+ "grad_norm": 4.496001720428467,
916
+ "learning_rate": 9.609315757942503e-05,
917
+ "loss": 0.8537,
918
+ "step": 108
919
+ },
920
+ {
921
+ "epoch": 1.72,
922
+ "eval_loss": 1.2372474670410156,
923
+ "eval_mean_token_accuracy": 0.62,
924
+ "eval_num_tokens": 318766.0,
925
+ "eval_runtime": 11.6041,
926
+ "eval_samples_per_second": 17.235,
927
+ "eval_steps_per_second": 17.235,
928
+ "step": 108
929
+ },
930
+ {
931
+ "epoch": 1.752,
932
+ "grad_norm": 13.367856979370117,
933
+ "learning_rate": 9.581813647811198e-05,
934
+ "loss": 1.5711,
935
+ "step": 110
936
+ },
937
+ {
938
+ "epoch": 1.752,
939
+ "eval_loss": 1.149797797203064,
940
+ "eval_mean_token_accuracy": 0.6025,
941
+ "eval_num_tokens": 324508.0,
942
+ "eval_runtime": 11.6661,
943
+ "eval_samples_per_second": 17.144,
944
+ "eval_steps_per_second": 17.144,
945
+ "step": 110
946
+ },
947
+ {
948
+ "epoch": 1.784,
949
+ "grad_norm": 5.717728614807129,
950
+ "learning_rate": 9.553418304030886e-05,
951
+ "loss": 0.9738,
952
+ "step": 112
953
+ },
954
+ {
955
+ "epoch": 1.784,
956
+ "eval_loss": 0.826062023639679,
957
+ "eval_mean_token_accuracy": 0.71,
958
+ "eval_num_tokens": 330420.0,
959
+ "eval_runtime": 11.5373,
960
+ "eval_samples_per_second": 17.335,
961
+ "eval_steps_per_second": 17.335,
962
+ "step": 112
963
+ },
964
+ {
965
+ "epoch": 1.8159999999999998,
966
+ "grad_norm": 2.54892635345459,
967
+ "learning_rate": 9.524135262330098e-05,
968
+ "loss": 0.7612,
969
+ "step": 114
970
+ },
971
+ {
972
+ "epoch": 1.8159999999999998,
973
+ "eval_loss": 0.9210658073425293,
974
+ "eval_mean_token_accuracy": 0.6725,
975
+ "eval_num_tokens": 336449.0,
976
+ "eval_runtime": 11.5633,
977
+ "eval_samples_per_second": 17.296,
978
+ "eval_steps_per_second": 17.296,
979
+ "step": 114
980
+ },
981
+ {
982
+ "epoch": 1.8479999999999999,
983
+ "grad_norm": 6.088118076324463,
984
+ "learning_rate": 9.493970231495835e-05,
985
+ "loss": 0.9332,
986
+ "step": 116
987
+ },
988
+ {
989
+ "epoch": 1.8479999999999999,
990
+ "eval_loss": 0.8408001661300659,
991
+ "eval_mean_token_accuracy": 0.69,
992
+ "eval_num_tokens": 342220.0,
993
+ "eval_runtime": 11.5583,
994
+ "eval_samples_per_second": 17.304,
995
+ "eval_steps_per_second": 17.304,
996
+ "step": 116
997
+ },
998
+ {
999
+ "epoch": 1.88,
1000
+ "grad_norm": 3.3563480377197266,
1001
+ "learning_rate": 9.462929092260628e-05,
1002
+ "loss": 0.8793,
1003
+ "step": 118
1004
+ },
1005
+ {
1006
+ "epoch": 1.88,
1007
+ "eval_loss": 0.8656268119812012,
1008
+ "eval_mean_token_accuracy": 0.725,
1009
+ "eval_num_tokens": 348195.0,
1010
+ "eval_runtime": 11.6702,
1011
+ "eval_samples_per_second": 17.138,
1012
+ "eval_steps_per_second": 17.138,
1013
+ "step": 118
1014
+ },
1015
+ {
1016
+ "epoch": 1.912,
1017
+ "grad_norm": 4.787728309631348,
1018
+ "learning_rate": 9.431017896156074e-05,
1019
+ "loss": 0.8278,
1020
+ "step": 120
1021
+ },
1022
+ {
1023
+ "epoch": 1.912,
1024
+ "eval_loss": 0.7685564160346985,
1025
+ "eval_mean_token_accuracy": 0.745,
1026
+ "eval_num_tokens": 354178.0,
1027
+ "eval_runtime": 11.6435,
1028
+ "eval_samples_per_second": 17.177,
1029
+ "eval_steps_per_second": 17.177,
1030
+ "step": 120
1031
+ },
1032
+ {
1033
+ "epoch": 1.944,
1034
+ "grad_norm": 2.3458027839660645,
1035
+ "learning_rate": 9.398242864333083e-05,
1036
+ "loss": 0.7288,
1037
+ "step": 122
1038
+ },
1039
+ {
1040
+ "epoch": 1.944,
1041
+ "eval_loss": 0.8250694274902344,
1042
+ "eval_mean_token_accuracy": 0.7175,
1043
+ "eval_num_tokens": 360106.0,
1044
+ "eval_runtime": 11.5515,
1045
+ "eval_samples_per_second": 17.314,
1046
+ "eval_steps_per_second": 17.314,
1047
+ "step": 122
1048
+ },
1049
+ {
1050
+ "epoch": 1.976,
1051
+ "grad_norm": 14.79286003112793,
1052
+ "learning_rate": 9.364610386349049e-05,
1053
+ "loss": 0.8432,
1054
+ "step": 124
1055
+ },
1056
+ {
1057
+ "epoch": 1.976,
1058
+ "eval_loss": 0.7326304912567139,
1059
+ "eval_mean_token_accuracy": 0.7125,
1060
+ "eval_num_tokens": 366112.0,
1061
+ "eval_runtime": 11.6557,
1062
+ "eval_samples_per_second": 17.159,
1063
+ "eval_steps_per_second": 17.159,
1064
+ "step": 124
1065
+ },
1066
+ {
1067
+ "epoch": 2.0,
1068
+ "grad_norm": 7.612817287445068,
1069
+ "learning_rate": 9.330127018922194e-05,
1070
+ "loss": 0.8079,
1071
+ "step": 126
1072
+ },
1073
+ {
1074
+ "epoch": 2.0,
1075
+ "eval_loss": 0.8138958811759949,
1076
+ "eval_mean_token_accuracy": 0.7025,
1077
+ "eval_num_tokens": 370580.0,
1078
+ "eval_runtime": 11.5915,
1079
+ "eval_samples_per_second": 17.254,
1080
+ "eval_steps_per_second": 17.254,
1081
+ "step": 126
1082
+ },
1083
+ {
1084
+ "epoch": 2.032,
1085
+ "grad_norm": 2.8889920711517334,
1086
+ "learning_rate": 9.294799484653323e-05,
1087
+ "loss": 0.4227,
1088
+ "step": 128
1089
+ },
1090
+ {
1091
+ "epoch": 2.032,
1092
+ "eval_loss": 0.8597235083580017,
1093
+ "eval_mean_token_accuracy": 0.71,
1094
+ "eval_num_tokens": 376630.0,
1095
+ "eval_runtime": 11.6443,
1096
+ "eval_samples_per_second": 17.176,
1097
+ "eval_steps_per_second": 17.176,
1098
+ "step": 128
1099
+ },
1100
+ {
1101
+ "epoch": 2.064,
1102
+ "grad_norm": 6.3547186851501465,
1103
+ "learning_rate": 9.258634670715238e-05,
1104
+ "loss": 0.6808,
1105
+ "step": 130
1106
+ },
1107
+ {
1108
+ "epoch": 2.064,
1109
+ "eval_loss": 0.6862205266952515,
1110
+ "eval_mean_token_accuracy": 0.75,
1111
+ "eval_num_tokens": 382648.0,
1112
+ "eval_runtime": 11.6321,
1113
+ "eval_samples_per_second": 17.194,
1114
+ "eval_steps_per_second": 17.194,
1115
+ "step": 130
1116
+ },
1117
+ {
1118
+ "epoch": 2.096,
1119
+ "grad_norm": 2.95296573638916,
1120
+ "learning_rate": 9.221639627510076e-05,
1121
+ "loss": 0.7168,
1122
+ "step": 132
1123
+ },
1124
+ {
1125
+ "epoch": 2.096,
1126
+ "eval_loss": 0.7475305199623108,
1127
+ "eval_mean_token_accuracy": 0.6775,
1128
+ "eval_num_tokens": 388513.0,
1129
+ "eval_runtime": 11.6024,
1130
+ "eval_samples_per_second": 17.238,
1131
+ "eval_steps_per_second": 17.238,
1132
+ "step": 132
1133
+ },
1134
+ {
1135
+ "epoch": 2.128,
1136
+ "grad_norm": 5.4269304275512695,
1137
+ "learning_rate": 9.183821567294809e-05,
1138
+ "loss": 0.6498,
1139
+ "step": 134
1140
+ },
1141
+ {
1142
+ "epoch": 2.128,
1143
+ "eval_loss": 0.702393114566803,
1144
+ "eval_mean_token_accuracy": 0.715,
1145
+ "eval_num_tokens": 394418.0,
1146
+ "eval_runtime": 11.5788,
1147
+ "eval_samples_per_second": 17.273,
1148
+ "eval_steps_per_second": 17.273,
1149
+ "step": 134
1150
+ },
1151
+ {
1152
+ "epoch": 2.16,
1153
+ "grad_norm": 3.8211143016815186,
1154
+ "learning_rate": 9.145187862775209e-05,
1155
+ "loss": 0.5681,
1156
+ "step": 136
1157
+ },
1158
+ {
1159
+ "epoch": 2.16,
1160
+ "eval_loss": 0.6857463121414185,
1161
+ "eval_mean_token_accuracy": 0.7225,
1162
+ "eval_num_tokens": 400194.0,
1163
+ "eval_runtime": 11.5703,
1164
+ "eval_samples_per_second": 17.286,
1165
+ "eval_steps_per_second": 17.286,
1166
+ "step": 136
1167
+ },
1168
+ {
1169
+ "epoch": 2.192,
1170
+ "grad_norm": 2.7427375316619873,
1171
+ "learning_rate": 9.105746045668521e-05,
1172
+ "loss": 0.5614,
1173
+ "step": 138
1174
+ },
1175
+ {
1176
+ "epoch": 2.192,
1177
+ "eval_loss": 0.746816873550415,
1178
+ "eval_mean_token_accuracy": 0.7125,
1179
+ "eval_num_tokens": 406144.0,
1180
+ "eval_runtime": 11.6047,
1181
+ "eval_samples_per_second": 17.234,
1182
+ "eval_steps_per_second": 17.234,
1183
+ "step": 138
1184
+ },
1185
+ {
1186
+ "epoch": 2.224,
1187
+ "grad_norm": 6.64992618560791,
1188
+ "learning_rate": 9.065503805235138e-05,
1189
+ "loss": 0.5969,
1190
+ "step": 140
1191
+ },
1192
+ {
1193
+ "epoch": 2.224,
1194
+ "eval_loss": 0.6569748520851135,
1195
+ "eval_mean_token_accuracy": 0.725,
1196
+ "eval_num_tokens": 412084.0,
1197
+ "eval_runtime": 11.5101,
1198
+ "eval_samples_per_second": 17.376,
1199
+ "eval_steps_per_second": 17.376,
1200
+ "step": 140
1201
+ },
1202
+ {
1203
+ "epoch": 2.2560000000000002,
1204
+ "grad_norm": 7.611020088195801,
1205
+ "learning_rate": 9.02446898677957e-05,
1206
+ "loss": 0.6381,
1207
+ "step": 142
1208
+ },
1209
+ {
1210
+ "epoch": 2.2560000000000002,
1211
+ "eval_loss": 0.6332951188087463,
1212
+ "eval_mean_token_accuracy": 0.7325,
1213
+ "eval_num_tokens": 417989.0,
1214
+ "eval_runtime": 11.4802,
1215
+ "eval_samples_per_second": 17.421,
1216
+ "eval_steps_per_second": 17.421,
1217
+ "step": 142
1218
+ },
1219
+ {
1220
+ "epoch": 2.288,
1221
+ "grad_norm": 4.542675018310547,
1222
+ "learning_rate": 8.982649590120982e-05,
1223
+ "loss": 0.4643,
1224
+ "step": 144
1225
+ },
1226
+ {
1227
+ "epoch": 2.288,
1228
+ "eval_loss": 0.6369831562042236,
1229
+ "eval_mean_token_accuracy": 0.765,
1230
+ "eval_num_tokens": 423962.0,
1231
+ "eval_runtime": 11.5332,
1232
+ "eval_samples_per_second": 17.341,
1233
+ "eval_steps_per_second": 17.341,
1234
+ "step": 144
1235
+ },
1236
+ {
1237
+ "epoch": 2.32,
1238
+ "grad_norm": 3.9403574466705322,
1239
+ "learning_rate": 8.940053768033609e-05,
1240
+ "loss": 0.3989,
1241
+ "step": 146
1242
+ },
1243
+ {
1244
+ "epoch": 2.32,
1245
+ "eval_loss": 0.6161526441574097,
1246
+ "eval_mean_token_accuracy": 0.755,
1247
+ "eval_num_tokens": 429847.0,
1248
+ "eval_runtime": 11.5416,
1249
+ "eval_samples_per_second": 17.329,
1250
+ "eval_steps_per_second": 17.329,
1251
+ "step": 146
1252
+ },
1253
+ {
1254
+ "epoch": 2.352,
1255
+ "grad_norm": 9.25675106048584,
1256
+ "learning_rate": 8.896689824657372e-05,
1257
+ "loss": 0.4669,
1258
+ "step": 148
1259
+ },
1260
+ {
1261
+ "epoch": 2.352,
1262
+ "eval_loss": 0.572540283203125,
1263
+ "eval_mean_token_accuracy": 0.765,
1264
+ "eval_num_tokens": 435853.0,
1265
+ "eval_runtime": 11.4761,
1266
+ "eval_samples_per_second": 17.428,
1267
+ "eval_steps_per_second": 17.428,
1268
+ "step": 148
1269
+ },
1270
+ {
1271
+ "epoch": 2.384,
1272
+ "grad_norm": 7.182618141174316,
1273
+ "learning_rate": 8.852566213878947e-05,
1274
+ "loss": 0.4608,
1275
+ "step": 150
1276
+ },
1277
+ {
1278
+ "epoch": 2.384,
1279
+ "eval_loss": 0.5258015990257263,
1280
+ "eval_mean_token_accuracy": 0.7775,
1281
+ "eval_num_tokens": 441908.0,
1282
+ "eval_runtime": 11.4933,
1283
+ "eval_samples_per_second": 17.401,
1284
+ "eval_steps_per_second": 17.401,
1285
+ "step": 150
1286
+ },
1287
+ {
1288
+ "epoch": 2.416,
1289
+ "grad_norm": 4.388311862945557,
1290
+ "learning_rate": 8.807691537683685e-05,
1291
+ "loss": 0.4554,
1292
+ "step": 152
1293
+ },
1294
+ {
1295
+ "epoch": 2.416,
1296
+ "eval_loss": 0.6056587100028992,
1297
+ "eval_mean_token_accuracy": 0.77,
1298
+ "eval_num_tokens": 447885.0,
1299
+ "eval_runtime": 11.489,
1300
+ "eval_samples_per_second": 17.408,
1301
+ "eval_steps_per_second": 17.408,
1302
+ "step": 152
1303
+ },
1304
+ {
1305
+ "epoch": 2.448,
1306
+ "grad_norm": 14.264395713806152,
1307
+ "learning_rate": 8.762074544478623e-05,
1308
+ "loss": 0.682,
1309
+ "step": 154
1310
+ },
1311
+ {
1312
+ "epoch": 2.448,
1313
+ "eval_loss": 0.8352121114730835,
1314
+ "eval_mean_token_accuracy": 0.7225,
1315
+ "eval_num_tokens": 453861.0,
1316
+ "eval_runtime": 11.5128,
1317
+ "eval_samples_per_second": 17.372,
1318
+ "eval_steps_per_second": 17.372,
1319
+ "step": 154
1320
+ },
1321
+ {
1322
+ "epoch": 2.48,
1323
+ "grad_norm": 10.707793235778809,
1324
+ "learning_rate": 8.715724127386972e-05,
1325
+ "loss": 0.4799,
1326
+ "step": 156
1327
+ },
1328
+ {
1329
+ "epoch": 2.48,
1330
+ "eval_loss": 1.2760920524597168,
1331
+ "eval_mean_token_accuracy": 0.7,
1332
+ "eval_num_tokens": 459736.0,
1333
+ "eval_runtime": 11.4855,
1334
+ "eval_samples_per_second": 17.413,
1335
+ "eval_steps_per_second": 17.413,
1336
+ "step": 156
1337
+ },
1338
+ {
1339
+ "epoch": 2.512,
1340
+ "grad_norm": 23.371320724487305,
1341
+ "learning_rate": 8.668649322514382e-05,
1342
+ "loss": 0.9003,
1343
+ "step": 158
1344
+ },
1345
+ {
1346
+ "epoch": 2.512,
1347
+ "eval_loss": 0.9396612644195557,
1348
+ "eval_mean_token_accuracy": 0.725,
1349
+ "eval_num_tokens": 465593.0,
1350
+ "eval_runtime": 11.5076,
1351
+ "eval_samples_per_second": 17.38,
1352
+ "eval_steps_per_second": 17.38,
1353
+ "step": 158
1354
+ },
1355
+ {
1356
+ "epoch": 2.544,
1357
+ "grad_norm": 4.851874351501465,
1358
+ "learning_rate": 8.620859307187339e-05,
1359
+ "loss": 0.5741,
1360
+ "step": 160
1361
+ },
1362
+ {
1363
+ "epoch": 2.544,
1364
+ "eval_loss": 0.6627417802810669,
1365
+ "eval_mean_token_accuracy": 0.765,
1366
+ "eval_num_tokens": 471576.0,
1367
+ "eval_runtime": 11.4972,
1368
+ "eval_samples_per_second": 17.396,
1369
+ "eval_steps_per_second": 17.396,
1370
+ "step": 160
1371
+ },
1372
+ {
1373
+ "epoch": 2.576,
1374
+ "grad_norm": 16.447948455810547,
1375
+ "learning_rate": 8.572363398164017e-05,
1376
+ "loss": 0.727,
1377
+ "step": 162
1378
+ },
1379
+ {
1380
+ "epoch": 2.576,
1381
+ "eval_loss": 0.8404039144515991,
1382
+ "eval_mean_token_accuracy": 0.73,
1383
+ "eval_num_tokens": 477498.0,
1384
+ "eval_runtime": 11.4966,
1385
+ "eval_samples_per_second": 17.396,
1386
+ "eval_steps_per_second": 17.396,
1387
+ "step": 162
1388
+ },
1389
+ {
1390
+ "epoch": 2.608,
1391
+ "grad_norm": 7.180966377258301,
1392
+ "learning_rate": 8.523171049817974e-05,
1393
+ "loss": 0.8075,
1394
+ "step": 164
1395
+ },
1396
+ {
1397
+ "epoch": 2.608,
1398
+ "eval_loss": 0.6463148593902588,
1399
+ "eval_mean_token_accuracy": 0.7525,
1400
+ "eval_num_tokens": 483389.0,
1401
+ "eval_runtime": 11.5144,
1402
+ "eval_samples_per_second": 17.37,
1403
+ "eval_steps_per_second": 17.37,
1404
+ "step": 164
1405
+ },
1406
+ {
1407
+ "epoch": 2.64,
1408
+ "grad_norm": 5.650333404541016,
1409
+ "learning_rate": 8.473291852294987e-05,
1410
+ "loss": 0.6168,
1411
+ "step": 166
1412
+ },
1413
+ {
1414
+ "epoch": 2.64,
1415
+ "eval_loss": 0.5853357315063477,
1416
+ "eval_mean_token_accuracy": 0.77,
1417
+ "eval_num_tokens": 489539.0,
1418
+ "eval_runtime": 11.4914,
1419
+ "eval_samples_per_second": 17.404,
1420
+ "eval_steps_per_second": 17.404,
1421
+ "step": 166
1422
+ },
1423
+ {
1424
+ "epoch": 2.672,
1425
+ "grad_norm": 2.393009901046753,
1426
+ "learning_rate": 8.422735529643444e-05,
1427
+ "loss": 0.5021,
1428
+ "step": 168
1429
+ },
1430
+ {
1431
+ "epoch": 2.672,
1432
+ "eval_loss": 0.6238591074943542,
1433
+ "eval_mean_token_accuracy": 0.74,
1434
+ "eval_num_tokens": 495467.0,
1435
+ "eval_runtime": 11.5047,
1436
+ "eval_samples_per_second": 17.384,
1437
+ "eval_steps_per_second": 17.384,
1438
+ "step": 168
1439
+ },
1440
+ {
1441
+ "epoch": 2.7039999999999997,
1442
+ "grad_norm": 4.689475059509277,
1443
+ "learning_rate": 8.371511937918616e-05,
1444
+ "loss": 0.5988,
1445
+ "step": 170
1446
+ },
1447
+ {
1448
+ "epoch": 2.7039999999999997,
1449
+ "eval_loss": 0.5909990072250366,
1450
+ "eval_mean_token_accuracy": 0.75,
1451
+ "eval_num_tokens": 501494.0,
1452
+ "eval_runtime": 11.4924,
1453
+ "eval_samples_per_second": 17.403,
1454
+ "eval_steps_per_second": 17.403,
1455
+ "step": 170
1456
+ },
1457
+ {
1458
+ "epoch": 2.7359999999999998,
1459
+ "grad_norm": 5.515851974487305,
1460
+ "learning_rate": 8.319631063261209e-05,
1461
+ "loss": 0.5291,
1462
+ "step": 172
1463
+ },
1464
+ {
1465
+ "epoch": 2.7359999999999998,
1466
+ "eval_loss": 0.565418004989624,
1467
+ "eval_mean_token_accuracy": 0.7675,
1468
+ "eval_num_tokens": 507384.0,
1469
+ "eval_runtime": 11.4986,
1470
+ "eval_samples_per_second": 17.393,
1471
+ "eval_steps_per_second": 17.393,
1472
+ "step": 172
1473
+ },
1474
+ {
1475
+ "epoch": 2.768,
1476
+ "grad_norm": 5.807971954345703,
1477
+ "learning_rate": 8.267103019950529e-05,
1478
+ "loss": 0.5464,
1479
+ "step": 174
1480
+ },
1481
+ {
1482
+ "epoch": 2.768,
1483
+ "eval_loss": 0.5476621389389038,
1484
+ "eval_mean_token_accuracy": 0.775,
1485
+ "eval_num_tokens": 513164.0,
1486
+ "eval_runtime": 11.6075,
1487
+ "eval_samples_per_second": 17.23,
1488
+ "eval_steps_per_second": 17.23,
1489
+ "step": 174
1490
+ },
1491
+ {
1492
+ "epoch": 2.8,
1493
+ "grad_norm": 6.8310346603393555,
1494
+ "learning_rate": 8.213938048432697e-05,
1495
+ "loss": 0.5724,
1496
+ "step": 176
1497
+ },
1498
+ {
1499
+ "epoch": 2.8,
1500
+ "eval_loss": 0.6014591455459595,
1501
+ "eval_mean_token_accuracy": 0.7725,
1502
+ "eval_num_tokens": 519107.0,
1503
+ "eval_runtime": 11.5041,
1504
+ "eval_samples_per_second": 17.385,
1505
+ "eval_steps_per_second": 17.385,
1506
+ "step": 176
1507
+ },
1508
+ {
1509
+ "epoch": 2.832,
1510
+ "grad_norm": 6.692939758300781,
1511
+ "learning_rate": 8.160146513324254e-05,
1512
+ "loss": 0.6522,
1513
+ "step": 178
1514
+ },
1515
+ {
1516
+ "epoch": 2.832,
1517
+ "eval_loss": 0.5391299724578857,
1518
+ "eval_mean_token_accuracy": 0.79,
1519
+ "eval_num_tokens": 525097.0,
1520
+ "eval_runtime": 11.4132,
1521
+ "eval_samples_per_second": 17.524,
1522
+ "eval_steps_per_second": 17.524,
1523
+ "step": 178
1524
+ },
1525
+ {
1526
+ "epoch": 2.864,
1527
+ "grad_norm": 3.1155288219451904,
1528
+ "learning_rate": 8.105738901391552e-05,
1529
+ "loss": 0.4778,
1530
+ "step": 180
1531
+ },
1532
+ {
1533
+ "epoch": 2.864,
1534
+ "eval_loss": 0.5624637007713318,
1535
+ "eval_mean_token_accuracy": 0.79,
1536
+ "eval_num_tokens": 531067.0,
1537
+ "eval_runtime": 11.2656,
1538
+ "eval_samples_per_second": 17.753,
1539
+ "eval_steps_per_second": 17.753,
1540
+ "step": 180
1541
+ },
1542
+ {
1543
+ "epoch": 2.896,
1544
+ "grad_norm": 5.285791873931885,
1545
+ "learning_rate": 8.05072581950634e-05,
1546
+ "loss": 0.4572,
1547
+ "step": 182
1548
+ },
1549
+ {
1550
+ "epoch": 2.896,
1551
+ "eval_loss": 0.5314605236053467,
1552
+ "eval_mean_token_accuracy": 0.79,
1553
+ "eval_num_tokens": 536888.0,
1554
+ "eval_runtime": 11.3844,
1555
+ "eval_samples_per_second": 17.568,
1556
+ "eval_steps_per_second": 17.568,
1557
+ "step": 182
1558
+ },
1559
+ {
1560
+ "epoch": 2.928,
1561
+ "grad_norm": 3.78257417678833,
1562
+ "learning_rate": 7.99511799257793e-05,
1563
+ "loss": 0.3595,
1564
+ "step": 184
1565
+ },
1566
+ {
1567
+ "epoch": 2.928,
1568
+ "eval_loss": 0.628775954246521,
1569
+ "eval_mean_token_accuracy": 0.77,
1570
+ "eval_num_tokens": 542683.0,
1571
+ "eval_runtime": 11.4728,
1572
+ "eval_samples_per_second": 17.433,
1573
+ "eval_steps_per_second": 17.433,
1574
+ "step": 184
1575
+ },
1576
+ {
1577
+ "epoch": 2.96,
1578
+ "grad_norm": 11.60348129272461,
1579
+ "learning_rate": 7.938926261462366e-05,
1580
+ "loss": 0.3579,
1581
+ "step": 186
1582
+ },
1583
+ {
1584
+ "epoch": 2.96,
1585
+ "eval_loss": 0.7037776708602905,
1586
+ "eval_mean_token_accuracy": 0.74,
1587
+ "eval_num_tokens": 548406.0,
1588
+ "eval_runtime": 11.4489,
1589
+ "eval_samples_per_second": 17.469,
1590
+ "eval_steps_per_second": 17.469,
1591
+ "step": 186
1592
+ },
1593
+ {
1594
+ "epoch": 2.992,
1595
+ "grad_norm": 6.869882583618164,
1596
+ "learning_rate": 7.882161580848967e-05,
1597
+ "loss": 0.6494,
1598
+ "step": 188
1599
+ },
1600
+ {
1601
+ "epoch": 2.992,
1602
+ "eval_loss": 0.5008761286735535,
1603
+ "eval_mean_token_accuracy": 0.7925,
1604
+ "eval_num_tokens": 554359.0,
1605
+ "eval_runtime": 11.3426,
1606
+ "eval_samples_per_second": 17.633,
1607
+ "eval_steps_per_second": 17.633,
1608
+ "step": 188
1609
+ },
1610
+ {
1611
+ "epoch": 3.016,
1612
+ "grad_norm": 4.442198276519775,
1613
+ "learning_rate": 7.82483501712469e-05,
1614
+ "loss": 0.2481,
1615
+ "step": 190
1616
+ },
1617
+ {
1618
+ "epoch": 3.016,
1619
+ "eval_loss": 0.4715193808078766,
1620
+ "eval_mean_token_accuracy": 0.8,
1621
+ "eval_num_tokens": 558908.0,
1622
+ "eval_runtime": 11.4001,
1623
+ "eval_samples_per_second": 17.544,
1624
+ "eval_steps_per_second": 17.544,
1625
+ "step": 190
1626
+ },
1627
+ {
1628
+ "epoch": 3.048,
1629
+ "grad_norm": 2.963721513748169,
1630
+ "learning_rate": 7.766957746216721e-05,
1631
+ "loss": 0.2361,
1632
+ "step": 192
1633
+ },
1634
+ {
1635
+ "epoch": 3.048,
1636
+ "eval_loss": 0.49056610465049744,
1637
+ "eval_mean_token_accuracy": 0.79,
1638
+ "eval_num_tokens": 564551.0,
1639
+ "eval_runtime": 11.4911,
1640
+ "eval_samples_per_second": 17.405,
1641
+ "eval_steps_per_second": 17.405,
1642
+ "step": 192
1643
+ },
1644
+ {
1645
+ "epoch": 3.08,
1646
+ "grad_norm": 6.097925186157227,
1647
+ "learning_rate": 7.7085410514137e-05,
1648
+ "loss": 0.2673,
1649
+ "step": 194
1650
+ },
1651
+ {
1652
+ "epoch": 3.08,
1653
+ "eval_loss": 0.5469616055488586,
1654
+ "eval_mean_token_accuracy": 0.79,
1655
+ "eval_num_tokens": 570498.0,
1656
+ "eval_runtime": 11.4512,
1657
+ "eval_samples_per_second": 17.465,
1658
+ "eval_steps_per_second": 17.465,
1659
+ "step": 194
1660
+ },
1661
+ {
1662
+ "epoch": 3.112,
1663
+ "grad_norm": 10.341373443603516,
1664
+ "learning_rate": 7.649596321166024e-05,
1665
+ "loss": 0.4327,
1666
+ "step": 196
1667
+ },
1668
+ {
1669
+ "epoch": 3.112,
1670
+ "eval_loss": 0.6369680762290955,
1671
+ "eval_mean_token_accuracy": 0.805,
1672
+ "eval_num_tokens": 576432.0,
1673
+ "eval_runtime": 11.4577,
1674
+ "eval_samples_per_second": 17.456,
1675
+ "eval_steps_per_second": 17.456,
1676
+ "step": 196
1677
+ },
1678
+ {
1679
+ "epoch": 3.144,
1680
+ "grad_norm": 4.3837761878967285,
1681
+ "learning_rate": 7.590135046865651e-05,
1682
+ "loss": 0.3957,
1683
+ "step": 198
1684
+ },
1685
+ {
1686
+ "epoch": 3.144,
1687
+ "eval_loss": 0.4437696039676666,
1688
+ "eval_mean_token_accuracy": 0.8425,
1689
+ "eval_num_tokens": 582547.0,
1690
+ "eval_runtime": 11.4556,
1691
+ "eval_samples_per_second": 17.459,
1692
+ "eval_steps_per_second": 17.459,
1693
+ "step": 198
1694
+ },
1695
+ {
1696
+ "epoch": 3.176,
1697
+ "grad_norm": 3.73852801322937,
1698
+ "learning_rate": 7.530168820605818e-05,
1699
+ "loss": 0.298,
1700
+ "step": 200
1701
+ },
1702
+ {
1703
+ "epoch": 3.176,
1704
+ "eval_loss": 0.4778077006340027,
1705
+ "eval_mean_token_accuracy": 0.815,
1706
+ "eval_num_tokens": 588373.0,
1707
+ "eval_runtime": 11.4324,
1708
+ "eval_samples_per_second": 17.494,
1709
+ "eval_steps_per_second": 17.494,
1710
+ "step": 200
1711
+ },
1712
+ {
1713
+ "epoch": 3.208,
1714
+ "grad_norm": 4.084625244140625,
1715
+ "learning_rate": 7.469709332921155e-05,
1716
+ "loss": 0.2577,
1717
+ "step": 202
1718
+ },
1719
+ {
1720
+ "epoch": 3.208,
1721
+ "eval_loss": 0.4960300922393799,
1722
+ "eval_mean_token_accuracy": 0.81,
1723
+ "eval_num_tokens": 594239.0,
1724
+ "eval_runtime": 11.468,
1725
+ "eval_samples_per_second": 17.44,
1726
+ "eval_steps_per_second": 17.44,
1727
+ "step": 202
1728
+ },
1729
+ {
1730
+ "epoch": 3.24,
1731
+ "grad_norm": 2.560659885406494,
1732
+ "learning_rate": 7.408768370508576e-05,
1733
+ "loss": 0.3833,
1734
+ "step": 204
1735
+ },
1736
+ {
1737
+ "epoch": 3.24,
1738
+ "eval_loss": 0.43789342045783997,
1739
+ "eval_mean_token_accuracy": 0.805,
1740
+ "eval_num_tokens": 600254.0,
1741
+ "eval_runtime": 11.459,
1742
+ "eval_samples_per_second": 17.454,
1743
+ "eval_steps_per_second": 17.454,
1744
+ "step": 204
1745
+ },
1746
+ {
1747
+ "epoch": 3.2720000000000002,
1748
+ "grad_norm": 5.988073348999023,
1749
+ "learning_rate": 7.347357813929454e-05,
1750
+ "loss": 0.3333,
1751
+ "step": 206
1752
+ },
1753
+ {
1754
+ "epoch": 3.2720000000000002,
1755
+ "eval_loss": 0.5336562395095825,
1756
+ "eval_mean_token_accuracy": 0.805,
1757
+ "eval_num_tokens": 606292.0,
1758
+ "eval_runtime": 11.45,
1759
+ "eval_samples_per_second": 17.467,
1760
+ "eval_steps_per_second": 17.467,
1761
+ "step": 206
1762
+ },
1763
+ {
1764
+ "epoch": 3.304,
1765
+ "grad_norm": 4.488523483276367,
1766
+ "learning_rate": 7.285489635293472e-05,
1767
+ "loss": 0.3104,
1768
+ "step": 208
1769
+ },
1770
+ {
1771
+ "epoch": 3.304,
1772
+ "eval_loss": 0.8533282279968262,
1773
+ "eval_mean_token_accuracy": 0.7625,
1774
+ "eval_num_tokens": 612363.0,
1775
+ "eval_runtime": 11.4494,
1776
+ "eval_samples_per_second": 17.468,
1777
+ "eval_steps_per_second": 17.468,
1778
+ "step": 208
1779
+ },
1780
+ {
1781
+ "epoch": 3.336,
1782
+ "grad_norm": 13.163505554199219,
1783
+ "learning_rate": 7.223175895924638e-05,
1784
+ "loss": 0.6206,
1785
+ "step": 210
1786
+ },
1787
+ {
1788
+ "epoch": 3.336,
1789
+ "eval_loss": 0.8010128736495972,
1790
+ "eval_mean_token_accuracy": 0.7625,
1791
+ "eval_num_tokens": 618327.0,
1792
+ "eval_runtime": 11.392,
1793
+ "eval_samples_per_second": 17.556,
1794
+ "eval_steps_per_second": 17.556,
1795
+ "step": 210
1796
+ },
1797
+ {
1798
+ "epoch": 3.368,
1799
+ "grad_norm": 8.656338691711426,
1800
+ "learning_rate": 7.160428744009912e-05,
1801
+ "loss": 0.5604,
1802
+ "step": 212
1803
+ },
1804
+ {
1805
+ "epoch": 3.368,
1806
+ "eval_loss": 0.5337031483650208,
1807
+ "eval_mean_token_accuracy": 0.7925,
1808
+ "eval_num_tokens": 624270.0,
1809
+ "eval_runtime": 11.349,
1810
+ "eval_samples_per_second": 17.623,
1811
+ "eval_steps_per_second": 17.623,
1812
+ "step": 212
1813
+ },
1814
+ {
1815
+ "epoch": 3.4,
1816
+ "grad_norm": 5.020056247711182,
1817
+ "learning_rate": 7.097260412230886e-05,
1818
+ "loss": 0.3663,
1819
+ "step": 214
1820
+ },
1821
+ {
1822
+ "epoch": 3.4,
1823
+ "eval_loss": 0.502609372138977,
1824
+ "eval_mean_token_accuracy": 0.8,
1825
+ "eval_num_tokens": 630049.0,
1826
+ "eval_runtime": 11.2627,
1827
+ "eval_samples_per_second": 17.758,
1828
+ "eval_steps_per_second": 17.758,
1829
+ "step": 214
1830
+ },
1831
+ {
1832
+ "epoch": 3.432,
1833
+ "grad_norm": 3.60333514213562,
1834
+ "learning_rate": 7.033683215379002e-05,
1835
+ "loss": 0.3525,
1836
+ "step": 216
1837
+ },
1838
+ {
1839
+ "epoch": 3.432,
1840
+ "eval_loss": 0.624167799949646,
1841
+ "eval_mean_token_accuracy": 0.7825,
1842
+ "eval_num_tokens": 635925.0,
1843
+ "eval_runtime": 11.3639,
1844
+ "eval_samples_per_second": 17.6,
1845
+ "eval_steps_per_second": 17.6,
1846
+ "step": 216
1847
+ },
1848
+ {
1849
+ "epoch": 3.464,
1850
+ "grad_norm": 7.64975118637085,
1851
+ "learning_rate": 6.969709547954756e-05,
1852
+ "loss": 0.4511,
1853
+ "step": 218
1854
+ },
1855
+ {
1856
+ "epoch": 3.464,
1857
+ "eval_loss": 0.6990913152694702,
1858
+ "eval_mean_token_accuracy": 0.7825,
1859
+ "eval_num_tokens": 641927.0,
1860
+ "eval_runtime": 11.3946,
1861
+ "eval_samples_per_second": 17.552,
1862
+ "eval_steps_per_second": 17.552,
1863
+ "step": 218
1864
+ },
1865
+ {
1866
+ "epoch": 3.496,
1867
+ "grad_norm": 8.035236358642578,
1868
+ "learning_rate": 6.905351881751372e-05,
1869
+ "loss": 0.6857,
1870
+ "step": 220
1871
+ },
1872
+ {
1873
+ "epoch": 3.496,
1874
+ "eval_loss": 0.6006813645362854,
1875
+ "eval_mean_token_accuracy": 0.775,
1876
+ "eval_num_tokens": 647975.0,
1877
+ "eval_runtime": 11.3298,
1878
+ "eval_samples_per_second": 17.653,
1879
+ "eval_steps_per_second": 17.653,
1880
+ "step": 220
1881
+ },
1882
+ {
1883
+ "epoch": 3.528,
1884
+ "grad_norm": 3.130239486694336,
1885
+ "learning_rate": 6.840622763423391e-05,
1886
+ "loss": 0.8284,
1887
+ "step": 222
1888
+ },
1889
+ {
1890
+ "epoch": 3.528,
1891
+ "eval_loss": 0.5212404727935791,
1892
+ "eval_mean_token_accuracy": 0.8025,
1893
+ "eval_num_tokens": 653848.0,
1894
+ "eval_runtime": 11.417,
1895
+ "eval_samples_per_second": 17.518,
1896
+ "eval_steps_per_second": 17.518,
1897
+ "step": 222
1898
+ },
1899
+ {
1900
+ "epoch": 3.56,
1901
+ "grad_norm": 6.3286590576171875,
1902
+ "learning_rate": 6.775534812040685e-05,
1903
+ "loss": 0.586,
1904
+ "step": 224
1905
+ },
1906
+ {
1907
+ "epoch": 3.56,
1908
+ "eval_loss": 0.5590178966522217,
1909
+ "eval_mean_token_accuracy": 0.7725,
1910
+ "eval_num_tokens": 659778.0,
1911
+ "eval_runtime": 11.3593,
1912
+ "eval_samples_per_second": 17.607,
1913
+ "eval_steps_per_second": 17.607,
1914
+ "step": 224
1915
+ },
1916
+ {
1917
+ "epoch": 3.592,
1918
+ "grad_norm": 5.30872106552124,
1919
+ "learning_rate": 6.710100716628344e-05,
1920
+ "loss": 0.4935,
1921
+ "step": 226
1922
+ },
1923
+ {
1924
+ "epoch": 3.592,
1925
+ "eval_loss": 0.4762438237667084,
1926
+ "eval_mean_token_accuracy": 0.8,
1927
+ "eval_num_tokens": 665683.0,
1928
+ "eval_runtime": 11.3502,
1929
+ "eval_samples_per_second": 17.621,
1930
+ "eval_steps_per_second": 17.621,
1931
+ "step": 226
1932
+ },
1933
+ {
1934
+ "epoch": 3.624,
1935
+ "grad_norm": 3.498307466506958,
1936
+ "learning_rate": 6.644333233692916e-05,
1937
+ "loss": 0.2553,
1938
+ "step": 228
1939
+ },
1940
+ {
1941
+ "epoch": 3.624,
1942
+ "eval_loss": 0.3769262731075287,
1943
+ "eval_mean_token_accuracy": 0.8575,
1944
+ "eval_num_tokens": 671577.0,
1945
+ "eval_runtime": 11.3693,
1946
+ "eval_samples_per_second": 17.591,
1947
+ "eval_steps_per_second": 17.591,
1948
+ "step": 228
1949
+ },
1950
+ {
1951
+ "epoch": 3.656,
1952
+ "grad_norm": 5.77377986907959,
1953
+ "learning_rate": 6.578245184735513e-05,
1954
+ "loss": 0.422,
1955
+ "step": 230
1956
+ },
1957
+ {
1958
+ "epoch": 3.656,
1959
+ "eval_loss": 0.4247679114341736,
1960
+ "eval_mean_token_accuracy": 0.875,
1961
+ "eval_num_tokens": 677652.0,
1962
+ "eval_runtime": 11.4058,
1963
+ "eval_samples_per_second": 17.535,
1964
+ "eval_steps_per_second": 17.535,
1965
+ "step": 230
1966
+ },
1967
+ {
1968
+ "epoch": 3.6879999999999997,
1969
+ "grad_norm": 5.382702827453613,
1970
+ "learning_rate": 6.511849453752223e-05,
1971
+ "loss": 0.3615,
1972
+ "step": 232
1973
+ },
1974
+ {
1975
+ "epoch": 3.6879999999999997,
1976
+ "eval_loss": 0.40983787178993225,
1977
+ "eval_mean_token_accuracy": 0.8775,
1978
+ "eval_num_tokens": 683524.0,
1979
+ "eval_runtime": 11.3425,
1980
+ "eval_samples_per_second": 17.633,
1981
+ "eval_steps_per_second": 17.633,
1982
+ "step": 232
1983
+ },
1984
+ {
1985
+ "epoch": 3.7199999999999998,
1986
+ "grad_norm": 6.351858139038086,
1987
+ "learning_rate": 6.445158984722358e-05,
1988
+ "loss": 0.4846,
1989
+ "step": 234
1990
+ },
1991
+ {
1992
+ "epoch": 3.7199999999999998,
1993
+ "eval_loss": 0.4072776436805725,
1994
+ "eval_mean_token_accuracy": 0.8775,
1995
+ "eval_num_tokens": 689468.0,
1996
+ "eval_runtime": 11.3999,
1997
+ "eval_samples_per_second": 17.544,
1998
+ "eval_steps_per_second": 17.544,
1999
+ "step": 234
2000
+ },
2001
+ {
2002
+ "epoch": 3.752,
2003
+ "grad_norm": 8.19200325012207,
2004
+ "learning_rate": 6.378186779084995e-05,
2005
+ "loss": 0.4629,
2006
+ "step": 236
2007
+ },
2008
+ {
2009
+ "epoch": 3.752,
2010
+ "eval_loss": 0.43801605701446533,
2011
+ "eval_mean_token_accuracy": 0.84,
2012
+ "eval_num_tokens": 695287.0,
2013
+ "eval_runtime": 11.4562,
2014
+ "eval_samples_per_second": 17.458,
2015
+ "eval_steps_per_second": 17.458,
2016
+ "step": 236
2017
+ },
2018
+ {
2019
+ "epoch": 3.784,
2020
+ "grad_norm": 3.963613510131836,
2021
+ "learning_rate": 6.310945893204324e-05,
2022
+ "loss": 0.2387,
2023
+ "step": 238
2024
+ },
2025
+ {
2026
+ "epoch": 3.784,
2027
+ "eval_loss": 0.38311469554901123,
2028
+ "eval_mean_token_accuracy": 0.8575,
2029
+ "eval_num_tokens": 700986.0,
2030
+ "eval_runtime": 11.441,
2031
+ "eval_samples_per_second": 17.481,
2032
+ "eval_steps_per_second": 17.481,
2033
+ "step": 238
2034
+ },
2035
+ {
2036
+ "epoch": 3.816,
2037
+ "grad_norm": 4.092259883880615,
2038
+ "learning_rate": 6.243449435824276e-05,
2039
+ "loss": 0.1867,
2040
+ "step": 240
2041
+ },
2042
+ {
2043
+ "epoch": 3.816,
2044
+ "eval_loss": 0.40530699491500854,
2045
+ "eval_mean_token_accuracy": 0.885,
2046
+ "eval_num_tokens": 706834.0,
2047
+ "eval_runtime": 11.372,
2048
+ "eval_samples_per_second": 17.587,
2049
+ "eval_steps_per_second": 17.587,
2050
+ "step": 240
2051
+ },
2052
+ {
2053
+ "epoch": 3.848,
2054
+ "grad_norm": 4.6833319664001465,
2055
+ "learning_rate": 6.17571056551295e-05,
2056
+ "loss": 0.2775,
2057
+ "step": 242
2058
+ },
2059
+ {
2060
+ "epoch": 3.848,
2061
+ "eval_loss": 0.42349615693092346,
2062
+ "eval_mean_token_accuracy": 0.865,
2063
+ "eval_num_tokens": 712917.0,
2064
+ "eval_runtime": 11.5149,
2065
+ "eval_samples_per_second": 17.369,
2066
+ "eval_steps_per_second": 17.369,
2067
+ "step": 242
2068
+ },
2069
+ {
2070
+ "epoch": 3.88,
2071
+ "grad_norm": 6.742552757263184,
2072
+ "learning_rate": 6.107742488097338e-05,
2073
+ "loss": 0.3866,
2074
+ "step": 244
2075
+ },
2076
+ {
2077
+ "epoch": 3.88,
2078
+ "eval_loss": 0.3780156672000885,
2079
+ "eval_mean_token_accuracy": 0.875,
2080
+ "eval_num_tokens": 718858.0,
2081
+ "eval_runtime": 11.4339,
2082
+ "eval_samples_per_second": 17.492,
2083
+ "eval_steps_per_second": 17.492,
2084
+ "step": 244
2085
+ },
2086
+ {
2087
+ "epoch": 3.912,
2088
+ "grad_norm": 5.453954219818115,
2089
+ "learning_rate": 6.0395584540887963e-05,
2090
+ "loss": 0.2173,
2091
+ "step": 246
2092
+ },
2093
+ {
2094
+ "epoch": 3.912,
2095
+ "eval_loss": 0.3653385043144226,
2096
+ "eval_mean_token_accuracy": 0.8875,
2097
+ "eval_num_tokens": 724709.0,
2098
+ "eval_runtime": 11.4826,
2099
+ "eval_samples_per_second": 17.418,
2100
+ "eval_steps_per_second": 17.418,
2101
+ "step": 246
2102
+ },
2103
+ {
2104
+ "epoch": 3.944,
2105
+ "grad_norm": 1.5256761312484741,
2106
+ "learning_rate": 5.97117175609986e-05,
2107
+ "loss": 0.2729,
2108
+ "step": 248
2109
+ },
2110
+ {
2111
+ "epoch": 3.944,
2112
+ "eval_loss": 0.38564562797546387,
2113
+ "eval_mean_token_accuracy": 0.8625,
2114
+ "eval_num_tokens": 730712.0,
2115
+ "eval_runtime": 11.4903,
2116
+ "eval_samples_per_second": 17.406,
2117
+ "eval_steps_per_second": 17.406,
2118
+ "step": 248
2119
+ },
2120
+ {
2121
+ "epoch": 3.976,
2122
+ "grad_norm": 3.0075435638427734,
2123
+ "learning_rate": 5.902595726252801e-05,
2124
+ "loss": 0.1422,
2125
+ "step": 250
2126
+ },
2127
+ {
2128
+ "epoch": 3.976,
2129
+ "eval_loss": 0.4116416871547699,
2130
+ "eval_mean_token_accuracy": 0.8575,
2131
+ "eval_num_tokens": 736567.0,
2132
+ "eval_runtime": 11.521,
2133
+ "eval_samples_per_second": 17.36,
2134
+ "eval_steps_per_second": 17.36,
2135
+ "step": 250
2136
+ },
2137
+ {
2138
+ "epoch": 4.0,
2139
+ "grad_norm": 7.006307125091553,
2140
+ "learning_rate": 5.833843733580512e-05,
2141
+ "loss": 0.3248,
2142
+ "step": 252
2143
+ },
2144
+ {
2145
+ "epoch": 4.0,
2146
+ "eval_loss": 0.40621310472488403,
2147
+ "eval_mean_token_accuracy": 0.8575,
2148
+ "eval_num_tokens": 741160.0,
2149
+ "eval_runtime": 11.4066,
2150
+ "eval_samples_per_second": 17.534,
2151
+ "eval_steps_per_second": 17.534,
2152
+ "step": 252
2153
+ },
2154
+ {
2155
+ "epoch": 4.032,
2156
+ "grad_norm": 3.07350492477417,
2157
+ "learning_rate": 5.764929181420191e-05,
2158
+ "loss": 0.1091,
2159
+ "step": 254
2160
+ },
2161
+ {
2162
+ "epoch": 4.032,
2163
+ "eval_loss": 0.3603956699371338,
2164
+ "eval_mean_token_accuracy": 0.8825,
2165
+ "eval_num_tokens": 747142.0,
2166
+ "eval_runtime": 11.4816,
2167
+ "eval_samples_per_second": 17.419,
2168
+ "eval_steps_per_second": 17.419,
2169
+ "step": 254
2170
+ },
2171
+ {
2172
+ "epoch": 4.064,
2173
+ "grad_norm": 3.1903159618377686,
2174
+ "learning_rate": 5.695865504800327e-05,
2175
+ "loss": 0.1786,
2176
+ "step": 256
2177
+ },
2178
+ {
2179
+ "epoch": 4.064,
2180
+ "eval_loss": 0.3532255291938782,
2181
+ "eval_mean_token_accuracy": 0.8775,
2182
+ "eval_num_tokens": 753082.0,
2183
+ "eval_runtime": 11.4889,
2184
+ "eval_samples_per_second": 17.408,
2185
+ "eval_steps_per_second": 17.408,
2186
+ "step": 256
2187
+ },
2188
+ {
2189
+ "epoch": 4.096,
2190
+ "grad_norm": 3.8832714557647705,
2191
+ "learning_rate": 5.6266661678215216e-05,
2192
+ "loss": 0.2634,
2193
+ "step": 258
2194
+ },
2195
+ {
2196
+ "epoch": 4.096,
2197
+ "eval_loss": 0.36864393949508667,
2198
+ "eval_mean_token_accuracy": 0.8625,
2199
+ "eval_num_tokens": 759111.0,
2200
+ "eval_runtime": 11.5099,
2201
+ "eval_samples_per_second": 17.376,
2202
+ "eval_steps_per_second": 17.376,
2203
+ "step": 258
2204
+ },
2205
+ {
2206
+ "epoch": 4.128,
2207
+ "grad_norm": 4.830361366271973,
2208
+ "learning_rate": 5.557344661031627e-05,
2209
+ "loss": 0.2079,
2210
+ "step": 260
2211
+ },
2212
+ {
2213
+ "epoch": 4.128,
2214
+ "eval_loss": 0.3449659049510956,
2215
+ "eval_mean_token_accuracy": 0.8825,
2216
+ "eval_num_tokens": 764907.0,
2217
+ "eval_runtime": 11.521,
2218
+ "eval_samples_per_second": 17.36,
2219
+ "eval_steps_per_second": 17.36,
2220
+ "step": 260
2221
+ },
2222
+ {
2223
+ "epoch": 4.16,
2224
+ "grad_norm": 1.7749980688095093,
2225
+ "learning_rate": 5.487914498795747e-05,
2226
+ "loss": 0.1563,
2227
+ "step": 262
2228
+ },
2229
+ {
2230
+ "epoch": 4.16,
2231
+ "eval_loss": 0.36110296845436096,
2232
+ "eval_mean_token_accuracy": 0.905,
2233
+ "eval_num_tokens": 770932.0,
2234
+ "eval_runtime": 11.4335,
2235
+ "eval_samples_per_second": 17.492,
2236
+ "eval_steps_per_second": 17.492,
2237
+ "step": 262
2238
+ },
2239
+ {
2240
+ "epoch": 4.192,
2241
+ "grad_norm": 8.26739501953125,
2242
+ "learning_rate": 5.418389216661579e-05,
2243
+ "loss": 0.3026,
2244
+ "step": 264
2245
+ },
2246
+ {
2247
+ "epoch": 4.192,
2248
+ "eval_loss": 0.38699576258659363,
2249
+ "eval_mean_token_accuracy": 0.88,
2250
+ "eval_num_tokens": 776864.0,
2251
+ "eval_runtime": 11.4821,
2252
+ "eval_samples_per_second": 17.418,
2253
+ "eval_steps_per_second": 17.418,
2254
+ "step": 264
2255
+ },
2256
+ {
2257
+ "epoch": 4.224,
2258
+ "grad_norm": 2.8019349575042725,
2259
+ "learning_rate": 5.348782368720626e-05,
2260
+ "loss": 0.2853,
2261
+ "step": 266
2262
+ },
2263
+ {
2264
+ "epoch": 4.224,
2265
+ "eval_loss": 0.34142714738845825,
2266
+ "eval_mean_token_accuracy": 0.9025,
2267
+ "eval_num_tokens": 782840.0,
2268
+ "eval_runtime": 11.4884,
2269
+ "eval_samples_per_second": 17.409,
2270
+ "eval_steps_per_second": 17.409,
2271
+ "step": 266
2272
+ },
2273
+ {
2274
+ "epoch": 4.256,
2275
+ "grad_norm": 3.4463911056518555,
2276
+ "learning_rate": 5.279107524965819e-05,
2277
+ "loss": 0.2078,
2278
+ "step": 268
2279
+ },
2280
+ {
2281
+ "epoch": 4.256,
2282
+ "eval_loss": 0.36096420884132385,
2283
+ "eval_mean_token_accuracy": 0.89,
2284
+ "eval_num_tokens": 788755.0,
2285
+ "eval_runtime": 11.4676,
2286
+ "eval_samples_per_second": 17.44,
2287
+ "eval_steps_per_second": 17.44,
2288
+ "step": 268
2289
+ },
2290
+ {
2291
+ "epoch": 4.288,
2292
+ "grad_norm": 5.433365821838379,
2293
+ "learning_rate": 5.209378268645998e-05,
2294
+ "loss": 0.2143,
2295
+ "step": 270
2296
+ },
2297
+ {
2298
+ "epoch": 4.288,
2299
+ "eval_loss": 0.3592444658279419,
2300
+ "eval_mean_token_accuracy": 0.8725,
2301
+ "eval_num_tokens": 794554.0,
2302
+ "eval_runtime": 11.4965,
2303
+ "eval_samples_per_second": 17.397,
2304
+ "eval_steps_per_second": 17.397,
2305
+ "step": 270
2306
+ },
2307
+ {
2308
+ "epoch": 4.32,
2309
+ "grad_norm": 3.042314052581787,
2310
+ "learning_rate": 5.139608193617845e-05,
2311
+ "loss": 0.2698,
2312
+ "step": 272
2313
+ },
2314
+ {
2315
+ "epoch": 4.32,
2316
+ "eval_loss": 0.3997034430503845,
2317
+ "eval_mean_token_accuracy": 0.86,
2318
+ "eval_num_tokens": 800527.0,
2319
+ "eval_runtime": 11.4184,
2320
+ "eval_samples_per_second": 17.516,
2321
+ "eval_steps_per_second": 17.516,
2322
+ "step": 272
2323
+ },
2324
+ {
2325
+ "epoch": 4.352,
2326
+ "grad_norm": 10.794941902160645,
2327
+ "learning_rate": 5.0698109016957274e-05,
2328
+ "loss": 0.3277,
2329
+ "step": 274
2330
+ },
2331
+ {
2332
+ "epoch": 4.352,
2333
+ "eval_loss": 0.4432468116283417,
2334
+ "eval_mean_token_accuracy": 0.835,
2335
+ "eval_num_tokens": 806629.0,
2336
+ "eval_runtime": 11.4348,
2337
+ "eval_samples_per_second": 17.491,
2338
+ "eval_steps_per_second": 17.491,
2339
+ "step": 274
2340
+ },
2341
+ {
2342
+ "epoch": 4.384,
2343
+ "grad_norm": 2.6515562534332275,
2344
+ "learning_rate": 5e-05,
2345
+ "loss": 0.1165,
2346
+ "step": 276
2347
+ },
2348
+ {
2349
+ "epoch": 4.384,
2350
+ "eval_loss": 0.3831730782985687,
2351
+ "eval_mean_token_accuracy": 0.8725,
2352
+ "eval_num_tokens": 812738.0,
2353
+ "eval_runtime": 11.4379,
2354
+ "eval_samples_per_second": 17.486,
2355
+ "eval_steps_per_second": 17.486,
2356
+ "step": 276
2357
+ },
2358
+ {
2359
+ "epoch": 4.416,
2360
+ "grad_norm": 3.236262798309326,
2361
+ "learning_rate": 4.9301890983042744e-05,
2362
+ "loss": 0.1818,
2363
+ "step": 278
2364
+ },
2365
+ {
2366
+ "epoch": 4.416,
2367
+ "eval_loss": 0.35354024171829224,
2368
+ "eval_mean_token_accuracy": 0.8725,
2369
+ "eval_num_tokens": 818819.0,
2370
+ "eval_runtime": 11.4212,
2371
+ "eval_samples_per_second": 17.511,
2372
+ "eval_steps_per_second": 17.511,
2373
+ "step": 278
2374
+ },
2375
+ {
2376
+ "epoch": 4.448,
2377
+ "grad_norm": 5.583536148071289,
2378
+ "learning_rate": 4.860391806382157e-05,
2379
+ "loss": 0.3041,
2380
+ "step": 280
2381
+ },
2382
+ {
2383
+ "epoch": 4.448,
2384
+ "eval_loss": 0.3540879786014557,
2385
+ "eval_mean_token_accuracy": 0.87,
2386
+ "eval_num_tokens": 824668.0,
2387
+ "eval_runtime": 11.4117,
2388
+ "eval_samples_per_second": 17.526,
2389
+ "eval_steps_per_second": 17.526,
2390
+ "step": 280
2391
+ },
2392
+ {
2393
+ "epoch": 4.48,
2394
+ "grad_norm": 9.713761329650879,
2395
+ "learning_rate": 4.790621731354003e-05,
2396
+ "loss": 0.2985,
2397
+ "step": 282
2398
+ },
2399
+ {
2400
+ "epoch": 4.48,
2401
+ "eval_loss": 0.3587820529937744,
2402
+ "eval_mean_token_accuracy": 0.88,
2403
+ "eval_num_tokens": 830397.0,
2404
+ "eval_runtime": 11.3776,
2405
+ "eval_samples_per_second": 17.578,
2406
+ "eval_steps_per_second": 17.578,
2407
+ "step": 282
2408
+ },
2409
+ {
2410
+ "epoch": 4.5120000000000005,
2411
+ "grad_norm": 3.4866244792938232,
2412
+ "learning_rate": 4.720892475034181e-05,
2413
+ "loss": 0.1989,
2414
+ "step": 284
2415
+ },
2416
+ {
2417
+ "epoch": 4.5120000000000005,
2418
+ "eval_loss": 0.37661635875701904,
2419
+ "eval_mean_token_accuracy": 0.8675,
2420
+ "eval_num_tokens": 836337.0,
2421
+ "eval_runtime": 11.4129,
2422
+ "eval_samples_per_second": 17.524,
2423
+ "eval_steps_per_second": 17.524,
2424
+ "step": 284
2425
+ },
2426
+ {
2427
+ "epoch": 4.5440000000000005,
2428
+ "grad_norm": 5.140746116638184,
2429
+ "learning_rate": 4.6512176312793736e-05,
2430
+ "loss": 0.1841,
2431
+ "step": 286
2432
+ },
2433
+ {
2434
+ "epoch": 4.5440000000000005,
2435
+ "eval_loss": 0.39047709107398987,
2436
+ "eval_mean_token_accuracy": 0.865,
2437
+ "eval_num_tokens": 842314.0,
2438
+ "eval_runtime": 11.444,
2439
+ "eval_samples_per_second": 17.476,
2440
+ "eval_steps_per_second": 17.476,
2441
+ "step": 286
2442
+ },
2443
+ {
2444
+ "epoch": 4.576,
2445
+ "grad_norm": 2.4394001960754395,
2446
+ "learning_rate": 4.5816107833384234e-05,
2447
+ "loss": 0.2127,
2448
+ "step": 288
2449
+ },
2450
+ {
2451
+ "epoch": 4.576,
2452
+ "eval_loss": 0.4071689248085022,
2453
+ "eval_mean_token_accuracy": 0.8525,
2454
+ "eval_num_tokens": 848214.0,
2455
+ "eval_runtime": 11.4066,
2456
+ "eval_samples_per_second": 17.534,
2457
+ "eval_steps_per_second": 17.534,
2458
+ "step": 288
2459
+ },
2460
+ {
2461
+ "epoch": 4.608,
2462
+ "grad_norm": 3.629035711288452,
2463
+ "learning_rate": 4.512085501204253e-05,
2464
+ "loss": 0.2098,
2465
+ "step": 290
2466
+ },
2467
+ {
2468
+ "epoch": 4.608,
2469
+ "eval_loss": 0.37388408184051514,
2470
+ "eval_mean_token_accuracy": 0.865,
2471
+ "eval_num_tokens": 854173.0,
2472
+ "eval_runtime": 11.4769,
2473
+ "eval_samples_per_second": 17.426,
2474
+ "eval_steps_per_second": 17.426,
2475
+ "step": 290
2476
+ },
2477
+ {
2478
+ "epoch": 4.64,
2479
+ "grad_norm": 5.06349515914917,
2480
+ "learning_rate": 4.442655338968373e-05,
2481
+ "loss": 0.2034,
2482
+ "step": 292
2483
+ },
2484
+ {
2485
+ "epoch": 4.64,
2486
+ "eval_loss": 0.33289721608161926,
2487
+ "eval_mean_token_accuracy": 0.875,
2488
+ "eval_num_tokens": 859981.0,
2489
+ "eval_runtime": 11.4579,
2490
+ "eval_samples_per_second": 17.455,
2491
+ "eval_steps_per_second": 17.455,
2492
+ "step": 292
2493
+ },
2494
+ {
2495
+ "epoch": 4.672,
2496
+ "grad_norm": 4.161719799041748,
2497
+ "learning_rate": 4.373333832178478e-05,
2498
+ "loss": 0.1055,
2499
+ "step": 294
2500
+ },
2501
+ {
2502
+ "epoch": 4.672,
2503
+ "eval_loss": 0.2890664339065552,
2504
+ "eval_mean_token_accuracy": 0.8925,
2505
+ "eval_num_tokens": 865762.0,
2506
+ "eval_runtime": 11.4333,
2507
+ "eval_samples_per_second": 17.493,
2508
+ "eval_steps_per_second": 17.493,
2509
+ "step": 294
2510
+ },
2511
+ {
2512
+ "epoch": 4.704,
2513
+ "grad_norm": 3.4958295822143555,
2514
+ "learning_rate": 4.3041344951996746e-05,
2515
+ "loss": 0.1311,
2516
+ "step": 296
2517
+ },
2518
+ {
2519
+ "epoch": 4.704,
2520
+ "eval_loss": 0.26056674122810364,
2521
+ "eval_mean_token_accuracy": 0.91,
2522
+ "eval_num_tokens": 871552.0,
2523
+ "eval_runtime": 11.4678,
2524
+ "eval_samples_per_second": 17.44,
2525
+ "eval_steps_per_second": 17.44,
2526
+ "step": 296
2527
+ },
2528
+ {
2529
+ "epoch": 4.736,
2530
+ "grad_norm": 3.2966129779815674,
2531
+ "learning_rate": 4.23507081857981e-05,
2532
+ "loss": 0.0799,
2533
+ "step": 298
2534
+ },
2535
+ {
2536
+ "epoch": 4.736,
2537
+ "eval_loss": 0.2812807559967041,
2538
+ "eval_mean_token_accuracy": 0.905,
2539
+ "eval_num_tokens": 877574.0,
2540
+ "eval_runtime": 11.4879,
2541
+ "eval_samples_per_second": 17.41,
2542
+ "eval_steps_per_second": 17.41,
2543
+ "step": 298
2544
+ },
2545
+ {
2546
+ "epoch": 4.768,
2547
+ "grad_norm": 3.745723247528076,
2548
+ "learning_rate": 4.166156266419489e-05,
2549
+ "loss": 0.1935,
2550
+ "step": 300
2551
+ },
2552
+ {
2553
+ "epoch": 4.768,
2554
+ "eval_loss": 0.28090521693229675,
2555
+ "eval_mean_token_accuracy": 0.905,
2556
+ "eval_num_tokens": 883355.0,
2557
+ "eval_runtime": 11.6211,
2558
+ "eval_samples_per_second": 17.21,
2559
+ "eval_steps_per_second": 17.21,
2560
+ "step": 300
2561
+ },
2562
+ {
2563
+ "epoch": 4.8,
2564
+ "grad_norm": 11.25948715209961,
2565
+ "learning_rate": 4.0974042737472006e-05,
2566
+ "loss": 0.2654,
2567
+ "step": 302
2568
+ },
2569
+ {
2570
+ "epoch": 4.8,
2571
+ "eval_loss": 0.25816527009010315,
2572
+ "eval_mean_token_accuracy": 0.9175,
2573
+ "eval_num_tokens": 889310.0,
2574
+ "eval_runtime": 11.5086,
2575
+ "eval_samples_per_second": 17.378,
2576
+ "eval_steps_per_second": 17.378,
2577
+ "step": 302
2578
+ }
2579
+ ],
2580
+ "logging_steps": 2,
2581
+ "max_steps": 500,
2582
+ "num_input_tokens_seen": 0,
2583
+ "num_train_epochs": 9,
2584
+ "save_steps": 2,
2585
+ "stateful_callbacks": {
2586
+ "EarlyStoppingCallback": {
2587
+ "args": {
2588
+ "early_stopping_patience": 20,
2589
+ "early_stopping_threshold": 0.0
2590
+ },
2591
+ "attributes": {
2592
+ "early_stopping_patience_counter": 0
2593
+ }
2594
+ },
2595
+ "TrainerControl": {
2596
+ "args": {
2597
+ "should_epoch_stop": false,
2598
+ "should_evaluate": false,
2599
+ "should_log": false,
2600
+ "should_save": true,
2601
+ "should_training_stop": false
2602
+ },
2603
+ "attributes": {}
2604
+ }
2605
+ },
2606
+ "total_flos": 4.026902954975232e+16,
2607
+ "train_batch_size": 1,
2608
+ "trial_name": null,
2609
+ "trial_params": null
2610
+ }
llama_finetune_mnist_ascii_r16_alpha=32_dropout=0.05_lr0.0001_data_size1000_max_steps=500_seed=123/checkpoint-302/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8069af376af6f9e56e5a1d07a412f35a5ba39a82dcb7c95a184e97a2f06f7b5
3
+ size 6008
llama_finetune_mnist_ascii_r16_alpha=32_dropout=0.05_lr0.0001_data_size1000_max_steps=500_seed=123/special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|eot_id|>"
17
+ }
llama_finetune_mnist_ascii_r16_alpha=32_dropout=0.05_lr0.0001_data_size1000_max_steps=500_seed=123/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
llama_finetune_mnist_ascii_r16_alpha=32_dropout=0.05_lr0.0001_data_size1000_max_steps=500_seed=123/tokenizer_config.json ADDED
@@ -0,0 +1,2064 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n {%- for arg_name, arg_val in tool_call.arguments | items %}\n {{- arg_name + '=\"' + arg_val + '\"' }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- else %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {%- endif %}\n {%- if builtin_tools is defined %}\n {#- This means we're in ipython mode #}\n {{- \"<|eom_id|>\" }}\n {%- else %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "extra_special_tokens": {},
2057
+ "model_input_names": [
2058
+ "input_ids",
2059
+ "attention_mask"
2060
+ ],
2061
+ "model_max_length": 131072,
2062
+ "pad_token": "<|eot_id|>",
2063
+ "tokenizer_class": "PreTrainedTokenizer"
2064
+ }
llama_finetune_mnist_ascii_r16_alpha=32_dropout=0.05_lr0.0001_data_size1000_max_steps=500_seed=123/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8069af376af6f9e56e5a1d07a412f35a5ba39a82dcb7c95a184e97a2f06f7b5
3
+ size 6008