Abhinay123 commited on
Commit
1cd20d1
·
verified ·
1 Parent(s): 36a8552

Upload folder using huggingface_hub

Browse files
Files changed (45) hide show
  1. .gitattributes +4 -0
  2. checkpoints_ia3_llama_class/checkpoint-128000/README.md +202 -0
  3. checkpoints_ia3_llama_class/checkpoint-128000/adapter_config.json +37 -0
  4. checkpoints_ia3_llama_class/checkpoint-128000/adapter_model.safetensors +3 -0
  5. checkpoints_ia3_llama_class/checkpoint-128000/optimizer.pt +3 -0
  6. checkpoints_ia3_llama_class/checkpoint-128000/rng_state.pth +3 -0
  7. checkpoints_ia3_llama_class/checkpoint-128000/scheduler.pt +3 -0
  8. checkpoints_ia3_llama_class/checkpoint-128000/special_tokens_map.json +17 -0
  9. checkpoints_ia3_llama_class/checkpoint-128000/tokenizer.json +3 -0
  10. checkpoints_ia3_llama_class/checkpoint-128000/tokenizer_config.json +2065 -0
  11. checkpoints_ia3_llama_class/checkpoint-128000/trainer_state.json +1970 -0
  12. checkpoints_ia3_llama_class/checkpoint-128000/training_args.bin +3 -0
  13. checkpoints_ia3_llama_class/checkpoint-136000/README.md +202 -0
  14. checkpoints_ia3_llama_class/checkpoint-136000/adapter_config.json +37 -0
  15. checkpoints_ia3_llama_class/checkpoint-136000/adapter_model.safetensors +3 -0
  16. checkpoints_ia3_llama_class/checkpoint-136000/optimizer.pt +3 -0
  17. checkpoints_ia3_llama_class/checkpoint-136000/rng_state.pth +3 -0
  18. checkpoints_ia3_llama_class/checkpoint-136000/scheduler.pt +3 -0
  19. checkpoints_ia3_llama_class/checkpoint-136000/special_tokens_map.json +17 -0
  20. checkpoints_ia3_llama_class/checkpoint-136000/tokenizer.json +3 -0
  21. checkpoints_ia3_llama_class/checkpoint-136000/tokenizer_config.json +2065 -0
  22. checkpoints_ia3_llama_class/checkpoint-136000/trainer_state.json +2091 -0
  23. checkpoints_ia3_llama_class/checkpoint-136000/training_args.bin +3 -0
  24. checkpoints_ia3_llama_class/checkpoint-144000/README.md +202 -0
  25. checkpoints_ia3_llama_class/checkpoint-144000/adapter_config.json +37 -0
  26. checkpoints_ia3_llama_class/checkpoint-144000/adapter_model.safetensors +3 -0
  27. checkpoints_ia3_llama_class/checkpoint-144000/optimizer.pt +3 -0
  28. checkpoints_ia3_llama_class/checkpoint-144000/rng_state.pth +3 -0
  29. checkpoints_ia3_llama_class/checkpoint-144000/scheduler.pt +3 -0
  30. checkpoints_ia3_llama_class/checkpoint-144000/special_tokens_map.json +17 -0
  31. checkpoints_ia3_llama_class/checkpoint-144000/tokenizer.json +3 -0
  32. checkpoints_ia3_llama_class/checkpoint-144000/tokenizer_config.json +2065 -0
  33. checkpoints_ia3_llama_class/checkpoint-144000/trainer_state.json +2212 -0
  34. checkpoints_ia3_llama_class/checkpoint-144000/training_args.bin +3 -0
  35. checkpoints_ia3_llama_class/checkpoint-88000/README.md +202 -0
  36. checkpoints_ia3_llama_class/checkpoint-88000/adapter_config.json +37 -0
  37. checkpoints_ia3_llama_class/checkpoint-88000/adapter_model.safetensors +3 -0
  38. checkpoints_ia3_llama_class/checkpoint-88000/optimizer.pt +3 -0
  39. checkpoints_ia3_llama_class/checkpoint-88000/rng_state.pth +3 -0
  40. checkpoints_ia3_llama_class/checkpoint-88000/scheduler.pt +3 -0
  41. checkpoints_ia3_llama_class/checkpoint-88000/special_tokens_map.json +17 -0
  42. checkpoints_ia3_llama_class/checkpoint-88000/tokenizer.json +3 -0
  43. checkpoints_ia3_llama_class/checkpoint-88000/tokenizer_config.json +2065 -0
  44. checkpoints_ia3_llama_class/checkpoint-88000/trainer_state.json +1365 -0
  45. checkpoints_ia3_llama_class/checkpoint-88000/training_args.bin +3 -0
.gitattributes CHANGED
@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ checkpoints_ia3_llama_class/checkpoint-128000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ checkpoints_ia3_llama_class/checkpoint-136000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ checkpoints_ia3_llama_class/checkpoint-144000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
39
+ checkpoints_ia3_llama_class/checkpoint-88000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
checkpoints_ia3_llama_class/checkpoint-128000/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Llama-3.2-3B-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 0.15.2
checkpoints_ia3_llama_class/checkpoint-128000/adapter_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Llama-3.2-3B-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": 8,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.1,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": [
22
+ "classifier",
23
+ "score"
24
+ ],
25
+ "peft_type": "LORA",
26
+ "r": 8,
27
+ "rank_pattern": {},
28
+ "revision": null,
29
+ "target_modules": [
30
+ "v_proj",
31
+ "k_proj"
32
+ ],
33
+ "task_type": "SEQ_CLS",
34
+ "trainable_token_indices": null,
35
+ "use_dora": false,
36
+ "use_rslora": false
37
+ }
checkpoints_ia3_llama_class/checkpoint-128000/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ca8f29fa53e9fb7cf17f3c02115118a1aefa9f17afe964d39f02423fc92ba02
3
+ size 7428608
checkpoints_ia3_llama_class/checkpoint-128000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc3b4e3a7f18ad8a059f43bc062ea5fde735a9b7e3aaf275dcda6df4707dbcc8
3
+ size 14922618
checkpoints_ia3_llama_class/checkpoint-128000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:343b86fb1e171885cb0c071ab63a50c9013f250625a41bf3aed2309fabd6f8da
3
+ size 14244
checkpoints_ia3_llama_class/checkpoint-128000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e60412e3c3d79bbfabe881173d55a793784442809e8af103c2ef6e16870d2dd
3
+ size 1064
checkpoints_ia3_llama_class/checkpoint-128000/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
+ }
checkpoints_ia3_llama_class/checkpoint-128000/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb55d3601efe3b76b75c99d892f669a53d23df00ee8bac2e67a72152ae2083cd
3
+ size 17210017
checkpoints_ia3_llama_class/checkpoint-128000/tokenizer_config.json ADDED
@@ -0,0 +1,2065 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "128000": {
5
+ "content": "<|begin_of_text|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "128001": {
13
+ "content": "<|end_of_text|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "128002": {
21
+ "content": "<|reserved_special_token_0|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "128003": {
29
+ "content": "<|reserved_special_token_1|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "128004": {
37
+ "content": "<|finetune_right_pad_id|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "128005": {
45
+ "content": "<|reserved_special_token_2|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "128006": {
53
+ "content": "<|start_header_id|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "128007": {
61
+ "content": "<|end_header_id|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "128008": {
69
+ "content": "<|eom_id|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "128009": {
77
+ "content": "<|eot_id|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "128010": {
85
+ "content": "<|python_tag|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "128011": {
93
+ "content": "<|reserved_special_token_3|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "128012": {
101
+ "content": "<|reserved_special_token_4|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "128013": {
109
+ "content": "<|reserved_special_token_5|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "128014": {
117
+ "content": "<|reserved_special_token_6|>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "128015": {
125
+ "content": "<|reserved_special_token_7|>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "128016": {
133
+ "content": "<|reserved_special_token_8|>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "128017": {
141
+ "content": "<|reserved_special_token_9|>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "128018": {
149
+ "content": "<|reserved_special_token_10|>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "128019": {
157
+ "content": "<|reserved_special_token_11|>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "128020": {
165
+ "content": "<|reserved_special_token_12|>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "128021": {
173
+ "content": "<|reserved_special_token_13|>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "128022": {
181
+ "content": "<|reserved_special_token_14|>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "128023": {
189
+ "content": "<|reserved_special_token_15|>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "128024": {
197
+ "content": "<|reserved_special_token_16|>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "128025": {
205
+ "content": "<|reserved_special_token_17|>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "128026": {
213
+ "content": "<|reserved_special_token_18|>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "128027": {
221
+ "content": "<|reserved_special_token_19|>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "128028": {
229
+ "content": "<|reserved_special_token_20|>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "128029": {
237
+ "content": "<|reserved_special_token_21|>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "128030": {
245
+ "content": "<|reserved_special_token_22|>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "128031": {
253
+ "content": "<|reserved_special_token_23|>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "128032": {
261
+ "content": "<|reserved_special_token_24|>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "128033": {
269
+ "content": "<|reserved_special_token_25|>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "128034": {
277
+ "content": "<|reserved_special_token_26|>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "128035": {
285
+ "content": "<|reserved_special_token_27|>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "128036": {
293
+ "content": "<|reserved_special_token_28|>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "128037": {
301
+ "content": "<|reserved_special_token_29|>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "128038": {
309
+ "content": "<|reserved_special_token_30|>",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "128039": {
317
+ "content": "<|reserved_special_token_31|>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "128040": {
325
+ "content": "<|reserved_special_token_32|>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "128041": {
333
+ "content": "<|reserved_special_token_33|>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "128042": {
341
+ "content": "<|reserved_special_token_34|>",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "128043": {
349
+ "content": "<|reserved_special_token_35|>",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "128044": {
357
+ "content": "<|reserved_special_token_36|>",
358
+ "lstrip": false,
359
+ "normalized": false,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "128045": {
365
+ "content": "<|reserved_special_token_37|>",
366
+ "lstrip": false,
367
+ "normalized": false,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "128046": {
373
+ "content": "<|reserved_special_token_38|>",
374
+ "lstrip": false,
375
+ "normalized": false,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "128047": {
381
+ "content": "<|reserved_special_token_39|>",
382
+ "lstrip": false,
383
+ "normalized": false,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "128048": {
389
+ "content": "<|reserved_special_token_40|>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "128049": {
397
+ "content": "<|reserved_special_token_41|>",
398
+ "lstrip": false,
399
+ "normalized": false,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "128050": {
405
+ "content": "<|reserved_special_token_42|>",
406
+ "lstrip": false,
407
+ "normalized": false,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "128051": {
413
+ "content": "<|reserved_special_token_43|>",
414
+ "lstrip": false,
415
+ "normalized": false,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "128052": {
421
+ "content": "<|reserved_special_token_44|>",
422
+ "lstrip": false,
423
+ "normalized": false,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "128053": {
429
+ "content": "<|reserved_special_token_45|>",
430
+ "lstrip": false,
431
+ "normalized": false,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "128054": {
437
+ "content": "<|reserved_special_token_46|>",
438
+ "lstrip": false,
439
+ "normalized": false,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "128055": {
445
+ "content": "<|reserved_special_token_47|>",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "128056": {
453
+ "content": "<|reserved_special_token_48|>",
454
+ "lstrip": false,
455
+ "normalized": false,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "128057": {
461
+ "content": "<|reserved_special_token_49|>",
462
+ "lstrip": false,
463
+ "normalized": false,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "128058": {
469
+ "content": "<|reserved_special_token_50|>",
470
+ "lstrip": false,
471
+ "normalized": false,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "128059": {
477
+ "content": "<|reserved_special_token_51|>",
478
+ "lstrip": false,
479
+ "normalized": false,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "128060": {
485
+ "content": "<|reserved_special_token_52|>",
486
+ "lstrip": false,
487
+ "normalized": false,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "128061": {
493
+ "content": "<|reserved_special_token_53|>",
494
+ "lstrip": false,
495
+ "normalized": false,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "128062": {
501
+ "content": "<|reserved_special_token_54|>",
502
+ "lstrip": false,
503
+ "normalized": false,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "128063": {
509
+ "content": "<|reserved_special_token_55|>",
510
+ "lstrip": false,
511
+ "normalized": false,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "128064": {
517
+ "content": "<|reserved_special_token_56|>",
518
+ "lstrip": false,
519
+ "normalized": false,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "128065": {
525
+ "content": "<|reserved_special_token_57|>",
526
+ "lstrip": false,
527
+ "normalized": false,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "128066": {
533
+ "content": "<|reserved_special_token_58|>",
534
+ "lstrip": false,
535
+ "normalized": false,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "128067": {
541
+ "content": "<|reserved_special_token_59|>",
542
+ "lstrip": false,
543
+ "normalized": false,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "128068": {
549
+ "content": "<|reserved_special_token_60|>",
550
+ "lstrip": false,
551
+ "normalized": false,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "128069": {
557
+ "content": "<|reserved_special_token_61|>",
558
+ "lstrip": false,
559
+ "normalized": false,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "128070": {
565
+ "content": "<|reserved_special_token_62|>",
566
+ "lstrip": false,
567
+ "normalized": false,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "128071": {
573
+ "content": "<|reserved_special_token_63|>",
574
+ "lstrip": false,
575
+ "normalized": false,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "128072": {
581
+ "content": "<|reserved_special_token_64|>",
582
+ "lstrip": false,
583
+ "normalized": false,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "128073": {
589
+ "content": "<|reserved_special_token_65|>",
590
+ "lstrip": false,
591
+ "normalized": false,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "128074": {
597
+ "content": "<|reserved_special_token_66|>",
598
+ "lstrip": false,
599
+ "normalized": false,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "128075": {
605
+ "content": "<|reserved_special_token_67|>",
606
+ "lstrip": false,
607
+ "normalized": false,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "128076": {
613
+ "content": "<|reserved_special_token_68|>",
614
+ "lstrip": false,
615
+ "normalized": false,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "128077": {
621
+ "content": "<|reserved_special_token_69|>",
622
+ "lstrip": false,
623
+ "normalized": false,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "128078": {
629
+ "content": "<|reserved_special_token_70|>",
630
+ "lstrip": false,
631
+ "normalized": false,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "128079": {
637
+ "content": "<|reserved_special_token_71|>",
638
+ "lstrip": false,
639
+ "normalized": false,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "128080": {
645
+ "content": "<|reserved_special_token_72|>",
646
+ "lstrip": false,
647
+ "normalized": false,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "128081": {
653
+ "content": "<|reserved_special_token_73|>",
654
+ "lstrip": false,
655
+ "normalized": false,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "128082": {
661
+ "content": "<|reserved_special_token_74|>",
662
+ "lstrip": false,
663
+ "normalized": false,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "128083": {
669
+ "content": "<|reserved_special_token_75|>",
670
+ "lstrip": false,
671
+ "normalized": false,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "128084": {
677
+ "content": "<|reserved_special_token_76|>",
678
+ "lstrip": false,
679
+ "normalized": false,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "128085": {
685
+ "content": "<|reserved_special_token_77|>",
686
+ "lstrip": false,
687
+ "normalized": false,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "128086": {
693
+ "content": "<|reserved_special_token_78|>",
694
+ "lstrip": false,
695
+ "normalized": false,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "128087": {
701
+ "content": "<|reserved_special_token_79|>",
702
+ "lstrip": false,
703
+ "normalized": false,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "128088": {
709
+ "content": "<|reserved_special_token_80|>",
710
+ "lstrip": false,
711
+ "normalized": false,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "128089": {
717
+ "content": "<|reserved_special_token_81|>",
718
+ "lstrip": false,
719
+ "normalized": false,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "128090": {
725
+ "content": "<|reserved_special_token_82|>",
726
+ "lstrip": false,
727
+ "normalized": false,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "128091": {
733
+ "content": "<|reserved_special_token_83|>",
734
+ "lstrip": false,
735
+ "normalized": false,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "128092": {
741
+ "content": "<|reserved_special_token_84|>",
742
+ "lstrip": false,
743
+ "normalized": false,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "128093": {
749
+ "content": "<|reserved_special_token_85|>",
750
+ "lstrip": false,
751
+ "normalized": false,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "128094": {
757
+ "content": "<|reserved_special_token_86|>",
758
+ "lstrip": false,
759
+ "normalized": false,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "128095": {
765
+ "content": "<|reserved_special_token_87|>",
766
+ "lstrip": false,
767
+ "normalized": false,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "128096": {
773
+ "content": "<|reserved_special_token_88|>",
774
+ "lstrip": false,
775
+ "normalized": false,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "128097": {
781
+ "content": "<|reserved_special_token_89|>",
782
+ "lstrip": false,
783
+ "normalized": false,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "128098": {
789
+ "content": "<|reserved_special_token_90|>",
790
+ "lstrip": false,
791
+ "normalized": false,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "128099": {
797
+ "content": "<|reserved_special_token_91|>",
798
+ "lstrip": false,
799
+ "normalized": false,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "128100": {
805
+ "content": "<|reserved_special_token_92|>",
806
+ "lstrip": false,
807
+ "normalized": false,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "128101": {
813
+ "content": "<|reserved_special_token_93|>",
814
+ "lstrip": false,
815
+ "normalized": false,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "128102": {
821
+ "content": "<|reserved_special_token_94|>",
822
+ "lstrip": false,
823
+ "normalized": false,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": true
827
+ },
828
+ "128103": {
829
+ "content": "<|reserved_special_token_95|>",
830
+ "lstrip": false,
831
+ "normalized": false,
832
+ "rstrip": false,
833
+ "single_word": false,
834
+ "special": true
835
+ },
836
+ "128104": {
837
+ "content": "<|reserved_special_token_96|>",
838
+ "lstrip": false,
839
+ "normalized": false,
840
+ "rstrip": false,
841
+ "single_word": false,
842
+ "special": true
843
+ },
844
+ "128105": {
845
+ "content": "<|reserved_special_token_97|>",
846
+ "lstrip": false,
847
+ "normalized": false,
848
+ "rstrip": false,
849
+ "single_word": false,
850
+ "special": true
851
+ },
852
+ "128106": {
853
+ "content": "<|reserved_special_token_98|>",
854
+ "lstrip": false,
855
+ "normalized": false,
856
+ "rstrip": false,
857
+ "single_word": false,
858
+ "special": true
859
+ },
860
+ "128107": {
861
+ "content": "<|reserved_special_token_99|>",
862
+ "lstrip": false,
863
+ "normalized": false,
864
+ "rstrip": false,
865
+ "single_word": false,
866
+ "special": true
867
+ },
868
+ "128108": {
869
+ "content": "<|reserved_special_token_100|>",
870
+ "lstrip": false,
871
+ "normalized": false,
872
+ "rstrip": false,
873
+ "single_word": false,
874
+ "special": true
875
+ },
876
+ "128109": {
877
+ "content": "<|reserved_special_token_101|>",
878
+ "lstrip": false,
879
+ "normalized": false,
880
+ "rstrip": false,
881
+ "single_word": false,
882
+ "special": true
883
+ },
884
+ "128110": {
885
+ "content": "<|reserved_special_token_102|>",
886
+ "lstrip": false,
887
+ "normalized": false,
888
+ "rstrip": false,
889
+ "single_word": false,
890
+ "special": true
891
+ },
892
+ "128111": {
893
+ "content": "<|reserved_special_token_103|>",
894
+ "lstrip": false,
895
+ "normalized": false,
896
+ "rstrip": false,
897
+ "single_word": false,
898
+ "special": true
899
+ },
900
+ "128112": {
901
+ "content": "<|reserved_special_token_104|>",
902
+ "lstrip": false,
903
+ "normalized": false,
904
+ "rstrip": false,
905
+ "single_word": false,
906
+ "special": true
907
+ },
908
+ "128113": {
909
+ "content": "<|reserved_special_token_105|>",
910
+ "lstrip": false,
911
+ "normalized": false,
912
+ "rstrip": false,
913
+ "single_word": false,
914
+ "special": true
915
+ },
916
+ "128114": {
917
+ "content": "<|reserved_special_token_106|>",
918
+ "lstrip": false,
919
+ "normalized": false,
920
+ "rstrip": false,
921
+ "single_word": false,
922
+ "special": true
923
+ },
924
+ "128115": {
925
+ "content": "<|reserved_special_token_107|>",
926
+ "lstrip": false,
927
+ "normalized": false,
928
+ "rstrip": false,
929
+ "single_word": false,
930
+ "special": true
931
+ },
932
+ "128116": {
933
+ "content": "<|reserved_special_token_108|>",
934
+ "lstrip": false,
935
+ "normalized": false,
936
+ "rstrip": false,
937
+ "single_word": false,
938
+ "special": true
939
+ },
940
+ "128117": {
941
+ "content": "<|reserved_special_token_109|>",
942
+ "lstrip": false,
943
+ "normalized": false,
944
+ "rstrip": false,
945
+ "single_word": false,
946
+ "special": true
947
+ },
948
+ "128118": {
949
+ "content": "<|reserved_special_token_110|>",
950
+ "lstrip": false,
951
+ "normalized": false,
952
+ "rstrip": false,
953
+ "single_word": false,
954
+ "special": true
955
+ },
956
+ "128119": {
957
+ "content": "<|reserved_special_token_111|>",
958
+ "lstrip": false,
959
+ "normalized": false,
960
+ "rstrip": false,
961
+ "single_word": false,
962
+ "special": true
963
+ },
964
+ "128120": {
965
+ "content": "<|reserved_special_token_112|>",
966
+ "lstrip": false,
967
+ "normalized": false,
968
+ "rstrip": false,
969
+ "single_word": false,
970
+ "special": true
971
+ },
972
+ "128121": {
973
+ "content": "<|reserved_special_token_113|>",
974
+ "lstrip": false,
975
+ "normalized": false,
976
+ "rstrip": false,
977
+ "single_word": false,
978
+ "special": true
979
+ },
980
+ "128122": {
981
+ "content": "<|reserved_special_token_114|>",
982
+ "lstrip": false,
983
+ "normalized": false,
984
+ "rstrip": false,
985
+ "single_word": false,
986
+ "special": true
987
+ },
988
+ "128123": {
989
+ "content": "<|reserved_special_token_115|>",
990
+ "lstrip": false,
991
+ "normalized": false,
992
+ "rstrip": false,
993
+ "single_word": false,
994
+ "special": true
995
+ },
996
+ "128124": {
997
+ "content": "<|reserved_special_token_116|>",
998
+ "lstrip": false,
999
+ "normalized": false,
1000
+ "rstrip": false,
1001
+ "single_word": false,
1002
+ "special": true
1003
+ },
1004
+ "128125": {
1005
+ "content": "<|reserved_special_token_117|>",
1006
+ "lstrip": false,
1007
+ "normalized": false,
1008
+ "rstrip": false,
1009
+ "single_word": false,
1010
+ "special": true
1011
+ },
1012
+ "128126": {
1013
+ "content": "<|reserved_special_token_118|>",
1014
+ "lstrip": false,
1015
+ "normalized": false,
1016
+ "rstrip": false,
1017
+ "single_word": false,
1018
+ "special": true
1019
+ },
1020
+ "128127": {
1021
+ "content": "<|reserved_special_token_119|>",
1022
+ "lstrip": false,
1023
+ "normalized": false,
1024
+ "rstrip": false,
1025
+ "single_word": false,
1026
+ "special": true
1027
+ },
1028
+ "128128": {
1029
+ "content": "<|reserved_special_token_120|>",
1030
+ "lstrip": false,
1031
+ "normalized": false,
1032
+ "rstrip": false,
1033
+ "single_word": false,
1034
+ "special": true
1035
+ },
1036
+ "128129": {
1037
+ "content": "<|reserved_special_token_121|>",
1038
+ "lstrip": false,
1039
+ "normalized": false,
1040
+ "rstrip": false,
1041
+ "single_word": false,
1042
+ "special": true
1043
+ },
1044
+ "128130": {
1045
+ "content": "<|reserved_special_token_122|>",
1046
+ "lstrip": false,
1047
+ "normalized": false,
1048
+ "rstrip": false,
1049
+ "single_word": false,
1050
+ "special": true
1051
+ },
1052
+ "128131": {
1053
+ "content": "<|reserved_special_token_123|>",
1054
+ "lstrip": false,
1055
+ "normalized": false,
1056
+ "rstrip": false,
1057
+ "single_word": false,
1058
+ "special": true
1059
+ },
1060
+ "128132": {
1061
+ "content": "<|reserved_special_token_124|>",
1062
+ "lstrip": false,
1063
+ "normalized": false,
1064
+ "rstrip": false,
1065
+ "single_word": false,
1066
+ "special": true
1067
+ },
1068
+ "128133": {
1069
+ "content": "<|reserved_special_token_125|>",
1070
+ "lstrip": false,
1071
+ "normalized": false,
1072
+ "rstrip": false,
1073
+ "single_word": false,
1074
+ "special": true
1075
+ },
1076
+ "128134": {
1077
+ "content": "<|reserved_special_token_126|>",
1078
+ "lstrip": false,
1079
+ "normalized": false,
1080
+ "rstrip": false,
1081
+ "single_word": false,
1082
+ "special": true
1083
+ },
1084
+ "128135": {
1085
+ "content": "<|reserved_special_token_127|>",
1086
+ "lstrip": false,
1087
+ "normalized": false,
1088
+ "rstrip": false,
1089
+ "single_word": false,
1090
+ "special": true
1091
+ },
1092
+ "128136": {
1093
+ "content": "<|reserved_special_token_128|>",
1094
+ "lstrip": false,
1095
+ "normalized": false,
1096
+ "rstrip": false,
1097
+ "single_word": false,
1098
+ "special": true
1099
+ },
1100
+ "128137": {
1101
+ "content": "<|reserved_special_token_129|>",
1102
+ "lstrip": false,
1103
+ "normalized": false,
1104
+ "rstrip": false,
1105
+ "single_word": false,
1106
+ "special": true
1107
+ },
1108
+ "128138": {
1109
+ "content": "<|reserved_special_token_130|>",
1110
+ "lstrip": false,
1111
+ "normalized": false,
1112
+ "rstrip": false,
1113
+ "single_word": false,
1114
+ "special": true
1115
+ },
1116
+ "128139": {
1117
+ "content": "<|reserved_special_token_131|>",
1118
+ "lstrip": false,
1119
+ "normalized": false,
1120
+ "rstrip": false,
1121
+ "single_word": false,
1122
+ "special": true
1123
+ },
1124
+ "128140": {
1125
+ "content": "<|reserved_special_token_132|>",
1126
+ "lstrip": false,
1127
+ "normalized": false,
1128
+ "rstrip": false,
1129
+ "single_word": false,
1130
+ "special": true
1131
+ },
1132
+ "128141": {
1133
+ "content": "<|reserved_special_token_133|>",
1134
+ "lstrip": false,
1135
+ "normalized": false,
1136
+ "rstrip": false,
1137
+ "single_word": false,
1138
+ "special": true
1139
+ },
1140
+ "128142": {
1141
+ "content": "<|reserved_special_token_134|>",
1142
+ "lstrip": false,
1143
+ "normalized": false,
1144
+ "rstrip": false,
1145
+ "single_word": false,
1146
+ "special": true
1147
+ },
1148
+ "128143": {
1149
+ "content": "<|reserved_special_token_135|>",
1150
+ "lstrip": false,
1151
+ "normalized": false,
1152
+ "rstrip": false,
1153
+ "single_word": false,
1154
+ "special": true
1155
+ },
1156
+ "128144": {
1157
+ "content": "<|reserved_special_token_136|>",
1158
+ "lstrip": false,
1159
+ "normalized": false,
1160
+ "rstrip": false,
1161
+ "single_word": false,
1162
+ "special": true
1163
+ },
1164
+ "128145": {
1165
+ "content": "<|reserved_special_token_137|>",
1166
+ "lstrip": false,
1167
+ "normalized": false,
1168
+ "rstrip": false,
1169
+ "single_word": false,
1170
+ "special": true
1171
+ },
1172
+ "128146": {
1173
+ "content": "<|reserved_special_token_138|>",
1174
+ "lstrip": false,
1175
+ "normalized": false,
1176
+ "rstrip": false,
1177
+ "single_word": false,
1178
+ "special": true
1179
+ },
1180
+ "128147": {
1181
+ "content": "<|reserved_special_token_139|>",
1182
+ "lstrip": false,
1183
+ "normalized": false,
1184
+ "rstrip": false,
1185
+ "single_word": false,
1186
+ "special": true
1187
+ },
1188
+ "128148": {
1189
+ "content": "<|reserved_special_token_140|>",
1190
+ "lstrip": false,
1191
+ "normalized": false,
1192
+ "rstrip": false,
1193
+ "single_word": false,
1194
+ "special": true
1195
+ },
1196
+ "128149": {
1197
+ "content": "<|reserved_special_token_141|>",
1198
+ "lstrip": false,
1199
+ "normalized": false,
1200
+ "rstrip": false,
1201
+ "single_word": false,
1202
+ "special": true
1203
+ },
1204
+ "128150": {
1205
+ "content": "<|reserved_special_token_142|>",
1206
+ "lstrip": false,
1207
+ "normalized": false,
1208
+ "rstrip": false,
1209
+ "single_word": false,
1210
+ "special": true
1211
+ },
1212
+ "128151": {
1213
+ "content": "<|reserved_special_token_143|>",
1214
+ "lstrip": false,
1215
+ "normalized": false,
1216
+ "rstrip": false,
1217
+ "single_word": false,
1218
+ "special": true
1219
+ },
1220
+ "128152": {
1221
+ "content": "<|reserved_special_token_144|>",
1222
+ "lstrip": false,
1223
+ "normalized": false,
1224
+ "rstrip": false,
1225
+ "single_word": false,
1226
+ "special": true
1227
+ },
1228
+ "128153": {
1229
+ "content": "<|reserved_special_token_145|>",
1230
+ "lstrip": false,
1231
+ "normalized": false,
1232
+ "rstrip": false,
1233
+ "single_word": false,
1234
+ "special": true
1235
+ },
1236
+ "128154": {
1237
+ "content": "<|reserved_special_token_146|>",
1238
+ "lstrip": false,
1239
+ "normalized": false,
1240
+ "rstrip": false,
1241
+ "single_word": false,
1242
+ "special": true
1243
+ },
1244
+ "128155": {
1245
+ "content": "<|reserved_special_token_147|>",
1246
+ "lstrip": false,
1247
+ "normalized": false,
1248
+ "rstrip": false,
1249
+ "single_word": false,
1250
+ "special": true
1251
+ },
1252
+ "128156": {
1253
+ "content": "<|reserved_special_token_148|>",
1254
+ "lstrip": false,
1255
+ "normalized": false,
1256
+ "rstrip": false,
1257
+ "single_word": false,
1258
+ "special": true
1259
+ },
1260
+ "128157": {
1261
+ "content": "<|reserved_special_token_149|>",
1262
+ "lstrip": false,
1263
+ "normalized": false,
1264
+ "rstrip": false,
1265
+ "single_word": false,
1266
+ "special": true
1267
+ },
1268
+ "128158": {
1269
+ "content": "<|reserved_special_token_150|>",
1270
+ "lstrip": false,
1271
+ "normalized": false,
1272
+ "rstrip": false,
1273
+ "single_word": false,
1274
+ "special": true
1275
+ },
1276
+ "128159": {
1277
+ "content": "<|reserved_special_token_151|>",
1278
+ "lstrip": false,
1279
+ "normalized": false,
1280
+ "rstrip": false,
1281
+ "single_word": false,
1282
+ "special": true
1283
+ },
1284
+ "128160": {
1285
+ "content": "<|reserved_special_token_152|>",
1286
+ "lstrip": false,
1287
+ "normalized": false,
1288
+ "rstrip": false,
1289
+ "single_word": false,
1290
+ "special": true
1291
+ },
1292
+ "128161": {
1293
+ "content": "<|reserved_special_token_153|>",
1294
+ "lstrip": false,
1295
+ "normalized": false,
1296
+ "rstrip": false,
1297
+ "single_word": false,
1298
+ "special": true
1299
+ },
1300
+ "128162": {
1301
+ "content": "<|reserved_special_token_154|>",
1302
+ "lstrip": false,
1303
+ "normalized": false,
1304
+ "rstrip": false,
1305
+ "single_word": false,
1306
+ "special": true
1307
+ },
1308
+ "128163": {
1309
+ "content": "<|reserved_special_token_155|>",
1310
+ "lstrip": false,
1311
+ "normalized": false,
1312
+ "rstrip": false,
1313
+ "single_word": false,
1314
+ "special": true
1315
+ },
1316
+ "128164": {
1317
+ "content": "<|reserved_special_token_156|>",
1318
+ "lstrip": false,
1319
+ "normalized": false,
1320
+ "rstrip": false,
1321
+ "single_word": false,
1322
+ "special": true
1323
+ },
1324
+ "128165": {
1325
+ "content": "<|reserved_special_token_157|>",
1326
+ "lstrip": false,
1327
+ "normalized": false,
1328
+ "rstrip": false,
1329
+ "single_word": false,
1330
+ "special": true
1331
+ },
1332
+ "128166": {
1333
+ "content": "<|reserved_special_token_158|>",
1334
+ "lstrip": false,
1335
+ "normalized": false,
1336
+ "rstrip": false,
1337
+ "single_word": false,
1338
+ "special": true
1339
+ },
1340
+ "128167": {
1341
+ "content": "<|reserved_special_token_159|>",
1342
+ "lstrip": false,
1343
+ "normalized": false,
1344
+ "rstrip": false,
1345
+ "single_word": false,
1346
+ "special": true
1347
+ },
1348
+ "128168": {
1349
+ "content": "<|reserved_special_token_160|>",
1350
+ "lstrip": false,
1351
+ "normalized": false,
1352
+ "rstrip": false,
1353
+ "single_word": false,
1354
+ "special": true
1355
+ },
1356
+ "128169": {
1357
+ "content": "<|reserved_special_token_161|>",
1358
+ "lstrip": false,
1359
+ "normalized": false,
1360
+ "rstrip": false,
1361
+ "single_word": false,
1362
+ "special": true
1363
+ },
1364
+ "128170": {
1365
+ "content": "<|reserved_special_token_162|>",
1366
+ "lstrip": false,
1367
+ "normalized": false,
1368
+ "rstrip": false,
1369
+ "single_word": false,
1370
+ "special": true
1371
+ },
1372
+ "128171": {
1373
+ "content": "<|reserved_special_token_163|>",
1374
+ "lstrip": false,
1375
+ "normalized": false,
1376
+ "rstrip": false,
1377
+ "single_word": false,
1378
+ "special": true
1379
+ },
1380
+ "128172": {
1381
+ "content": "<|reserved_special_token_164|>",
1382
+ "lstrip": false,
1383
+ "normalized": false,
1384
+ "rstrip": false,
1385
+ "single_word": false,
1386
+ "special": true
1387
+ },
1388
+ "128173": {
1389
+ "content": "<|reserved_special_token_165|>",
1390
+ "lstrip": false,
1391
+ "normalized": false,
1392
+ "rstrip": false,
1393
+ "single_word": false,
1394
+ "special": true
1395
+ },
1396
+ "128174": {
1397
+ "content": "<|reserved_special_token_166|>",
1398
+ "lstrip": false,
1399
+ "normalized": false,
1400
+ "rstrip": false,
1401
+ "single_word": false,
1402
+ "special": true
1403
+ },
1404
+ "128175": {
1405
+ "content": "<|reserved_special_token_167|>",
1406
+ "lstrip": false,
1407
+ "normalized": false,
1408
+ "rstrip": false,
1409
+ "single_word": false,
1410
+ "special": true
1411
+ },
1412
+ "128176": {
1413
+ "content": "<|reserved_special_token_168|>",
1414
+ "lstrip": false,
1415
+ "normalized": false,
1416
+ "rstrip": false,
1417
+ "single_word": false,
1418
+ "special": true
1419
+ },
1420
+ "128177": {
1421
+ "content": "<|reserved_special_token_169|>",
1422
+ "lstrip": false,
1423
+ "normalized": false,
1424
+ "rstrip": false,
1425
+ "single_word": false,
1426
+ "special": true
1427
+ },
1428
+ "128178": {
1429
+ "content": "<|reserved_special_token_170|>",
1430
+ "lstrip": false,
1431
+ "normalized": false,
1432
+ "rstrip": false,
1433
+ "single_word": false,
1434
+ "special": true
1435
+ },
1436
+ "128179": {
1437
+ "content": "<|reserved_special_token_171|>",
1438
+ "lstrip": false,
1439
+ "normalized": false,
1440
+ "rstrip": false,
1441
+ "single_word": false,
1442
+ "special": true
1443
+ },
1444
+ "128180": {
1445
+ "content": "<|reserved_special_token_172|>",
1446
+ "lstrip": false,
1447
+ "normalized": false,
1448
+ "rstrip": false,
1449
+ "single_word": false,
1450
+ "special": true
1451
+ },
1452
+ "128181": {
1453
+ "content": "<|reserved_special_token_173|>",
1454
+ "lstrip": false,
1455
+ "normalized": false,
1456
+ "rstrip": false,
1457
+ "single_word": false,
1458
+ "special": true
1459
+ },
1460
+ "128182": {
1461
+ "content": "<|reserved_special_token_174|>",
1462
+ "lstrip": false,
1463
+ "normalized": false,
1464
+ "rstrip": false,
1465
+ "single_word": false,
1466
+ "special": true
1467
+ },
1468
+ "128183": {
1469
+ "content": "<|reserved_special_token_175|>",
1470
+ "lstrip": false,
1471
+ "normalized": false,
1472
+ "rstrip": false,
1473
+ "single_word": false,
1474
+ "special": true
1475
+ },
1476
+ "128184": {
1477
+ "content": "<|reserved_special_token_176|>",
1478
+ "lstrip": false,
1479
+ "normalized": false,
1480
+ "rstrip": false,
1481
+ "single_word": false,
1482
+ "special": true
1483
+ },
1484
+ "128185": {
1485
+ "content": "<|reserved_special_token_177|>",
1486
+ "lstrip": false,
1487
+ "normalized": false,
1488
+ "rstrip": false,
1489
+ "single_word": false,
1490
+ "special": true
1491
+ },
1492
+ "128186": {
1493
+ "content": "<|reserved_special_token_178|>",
1494
+ "lstrip": false,
1495
+ "normalized": false,
1496
+ "rstrip": false,
1497
+ "single_word": false,
1498
+ "special": true
1499
+ },
1500
+ "128187": {
1501
+ "content": "<|reserved_special_token_179|>",
1502
+ "lstrip": false,
1503
+ "normalized": false,
1504
+ "rstrip": false,
1505
+ "single_word": false,
1506
+ "special": true
1507
+ },
1508
+ "128188": {
1509
+ "content": "<|reserved_special_token_180|>",
1510
+ "lstrip": false,
1511
+ "normalized": false,
1512
+ "rstrip": false,
1513
+ "single_word": false,
1514
+ "special": true
1515
+ },
1516
+ "128189": {
1517
+ "content": "<|reserved_special_token_181|>",
1518
+ "lstrip": false,
1519
+ "normalized": false,
1520
+ "rstrip": false,
1521
+ "single_word": false,
1522
+ "special": true
1523
+ },
1524
+ "128190": {
1525
+ "content": "<|reserved_special_token_182|>",
1526
+ "lstrip": false,
1527
+ "normalized": false,
1528
+ "rstrip": false,
1529
+ "single_word": false,
1530
+ "special": true
1531
+ },
1532
+ "128191": {
1533
+ "content": "<|reserved_special_token_183|>",
1534
+ "lstrip": false,
1535
+ "normalized": false,
1536
+ "rstrip": false,
1537
+ "single_word": false,
1538
+ "special": true
1539
+ },
1540
+ "128192": {
1541
+ "content": "<|reserved_special_token_184|>",
1542
+ "lstrip": false,
1543
+ "normalized": false,
1544
+ "rstrip": false,
1545
+ "single_word": false,
1546
+ "special": true
1547
+ },
1548
+ "128193": {
1549
+ "content": "<|reserved_special_token_185|>",
1550
+ "lstrip": false,
1551
+ "normalized": false,
1552
+ "rstrip": false,
1553
+ "single_word": false,
1554
+ "special": true
1555
+ },
1556
+ "128194": {
1557
+ "content": "<|reserved_special_token_186|>",
1558
+ "lstrip": false,
1559
+ "normalized": false,
1560
+ "rstrip": false,
1561
+ "single_word": false,
1562
+ "special": true
1563
+ },
1564
+ "128195": {
1565
+ "content": "<|reserved_special_token_187|>",
1566
+ "lstrip": false,
1567
+ "normalized": false,
1568
+ "rstrip": false,
1569
+ "single_word": false,
1570
+ "special": true
1571
+ },
1572
+ "128196": {
1573
+ "content": "<|reserved_special_token_188|>",
1574
+ "lstrip": false,
1575
+ "normalized": false,
1576
+ "rstrip": false,
1577
+ "single_word": false,
1578
+ "special": true
1579
+ },
1580
+ "128197": {
1581
+ "content": "<|reserved_special_token_189|>",
1582
+ "lstrip": false,
1583
+ "normalized": false,
1584
+ "rstrip": false,
1585
+ "single_word": false,
1586
+ "special": true
1587
+ },
1588
+ "128198": {
1589
+ "content": "<|reserved_special_token_190|>",
1590
+ "lstrip": false,
1591
+ "normalized": false,
1592
+ "rstrip": false,
1593
+ "single_word": false,
1594
+ "special": true
1595
+ },
1596
+ "128199": {
1597
+ "content": "<|reserved_special_token_191|>",
1598
+ "lstrip": false,
1599
+ "normalized": false,
1600
+ "rstrip": false,
1601
+ "single_word": false,
1602
+ "special": true
1603
+ },
1604
+ "128200": {
1605
+ "content": "<|reserved_special_token_192|>",
1606
+ "lstrip": false,
1607
+ "normalized": false,
1608
+ "rstrip": false,
1609
+ "single_word": false,
1610
+ "special": true
1611
+ },
1612
+ "128201": {
1613
+ "content": "<|reserved_special_token_193|>",
1614
+ "lstrip": false,
1615
+ "normalized": false,
1616
+ "rstrip": false,
1617
+ "single_word": false,
1618
+ "special": true
1619
+ },
1620
+ "128202": {
1621
+ "content": "<|reserved_special_token_194|>",
1622
+ "lstrip": false,
1623
+ "normalized": false,
1624
+ "rstrip": false,
1625
+ "single_word": false,
1626
+ "special": true
1627
+ },
1628
+ "128203": {
1629
+ "content": "<|reserved_special_token_195|>",
1630
+ "lstrip": false,
1631
+ "normalized": false,
1632
+ "rstrip": false,
1633
+ "single_word": false,
1634
+ "special": true
1635
+ },
1636
+ "128204": {
1637
+ "content": "<|reserved_special_token_196|>",
1638
+ "lstrip": false,
1639
+ "normalized": false,
1640
+ "rstrip": false,
1641
+ "single_word": false,
1642
+ "special": true
1643
+ },
1644
+ "128205": {
1645
+ "content": "<|reserved_special_token_197|>",
1646
+ "lstrip": false,
1647
+ "normalized": false,
1648
+ "rstrip": false,
1649
+ "single_word": false,
1650
+ "special": true
1651
+ },
1652
+ "128206": {
1653
+ "content": "<|reserved_special_token_198|>",
1654
+ "lstrip": false,
1655
+ "normalized": false,
1656
+ "rstrip": false,
1657
+ "single_word": false,
1658
+ "special": true
1659
+ },
1660
+ "128207": {
1661
+ "content": "<|reserved_special_token_199|>",
1662
+ "lstrip": false,
1663
+ "normalized": false,
1664
+ "rstrip": false,
1665
+ "single_word": false,
1666
+ "special": true
1667
+ },
1668
+ "128208": {
1669
+ "content": "<|reserved_special_token_200|>",
1670
+ "lstrip": false,
1671
+ "normalized": false,
1672
+ "rstrip": false,
1673
+ "single_word": false,
1674
+ "special": true
1675
+ },
1676
+ "128209": {
1677
+ "content": "<|reserved_special_token_201|>",
1678
+ "lstrip": false,
1679
+ "normalized": false,
1680
+ "rstrip": false,
1681
+ "single_word": false,
1682
+ "special": true
1683
+ },
1684
+ "128210": {
1685
+ "content": "<|reserved_special_token_202|>",
1686
+ "lstrip": false,
1687
+ "normalized": false,
1688
+ "rstrip": false,
1689
+ "single_word": false,
1690
+ "special": true
1691
+ },
1692
+ "128211": {
1693
+ "content": "<|reserved_special_token_203|>",
1694
+ "lstrip": false,
1695
+ "normalized": false,
1696
+ "rstrip": false,
1697
+ "single_word": false,
1698
+ "special": true
1699
+ },
1700
+ "128212": {
1701
+ "content": "<|reserved_special_token_204|>",
1702
+ "lstrip": false,
1703
+ "normalized": false,
1704
+ "rstrip": false,
1705
+ "single_word": false,
1706
+ "special": true
1707
+ },
1708
+ "128213": {
1709
+ "content": "<|reserved_special_token_205|>",
1710
+ "lstrip": false,
1711
+ "normalized": false,
1712
+ "rstrip": false,
1713
+ "single_word": false,
1714
+ "special": true
1715
+ },
1716
+ "128214": {
1717
+ "content": "<|reserved_special_token_206|>",
1718
+ "lstrip": false,
1719
+ "normalized": false,
1720
+ "rstrip": false,
1721
+ "single_word": false,
1722
+ "special": true
1723
+ },
1724
+ "128215": {
1725
+ "content": "<|reserved_special_token_207|>",
1726
+ "lstrip": false,
1727
+ "normalized": false,
1728
+ "rstrip": false,
1729
+ "single_word": false,
1730
+ "special": true
1731
+ },
1732
+ "128216": {
1733
+ "content": "<|reserved_special_token_208|>",
1734
+ "lstrip": false,
1735
+ "normalized": false,
1736
+ "rstrip": false,
1737
+ "single_word": false,
1738
+ "special": true
1739
+ },
1740
+ "128217": {
1741
+ "content": "<|reserved_special_token_209|>",
1742
+ "lstrip": false,
1743
+ "normalized": false,
1744
+ "rstrip": false,
1745
+ "single_word": false,
1746
+ "special": true
1747
+ },
1748
+ "128218": {
1749
+ "content": "<|reserved_special_token_210|>",
1750
+ "lstrip": false,
1751
+ "normalized": false,
1752
+ "rstrip": false,
1753
+ "single_word": false,
1754
+ "special": true
1755
+ },
1756
+ "128219": {
1757
+ "content": "<|reserved_special_token_211|>",
1758
+ "lstrip": false,
1759
+ "normalized": false,
1760
+ "rstrip": false,
1761
+ "single_word": false,
1762
+ "special": true
1763
+ },
1764
+ "128220": {
1765
+ "content": "<|reserved_special_token_212|>",
1766
+ "lstrip": false,
1767
+ "normalized": false,
1768
+ "rstrip": false,
1769
+ "single_word": false,
1770
+ "special": true
1771
+ },
1772
+ "128221": {
1773
+ "content": "<|reserved_special_token_213|>",
1774
+ "lstrip": false,
1775
+ "normalized": false,
1776
+ "rstrip": false,
1777
+ "single_word": false,
1778
+ "special": true
1779
+ },
1780
+ "128222": {
1781
+ "content": "<|reserved_special_token_214|>",
1782
+ "lstrip": false,
1783
+ "normalized": false,
1784
+ "rstrip": false,
1785
+ "single_word": false,
1786
+ "special": true
1787
+ },
1788
+ "128223": {
1789
+ "content": "<|reserved_special_token_215|>",
1790
+ "lstrip": false,
1791
+ "normalized": false,
1792
+ "rstrip": false,
1793
+ "single_word": false,
1794
+ "special": true
1795
+ },
1796
+ "128224": {
1797
+ "content": "<|reserved_special_token_216|>",
1798
+ "lstrip": false,
1799
+ "normalized": false,
1800
+ "rstrip": false,
1801
+ "single_word": false,
1802
+ "special": true
1803
+ },
1804
+ "128225": {
1805
+ "content": "<|reserved_special_token_217|>",
1806
+ "lstrip": false,
1807
+ "normalized": false,
1808
+ "rstrip": false,
1809
+ "single_word": false,
1810
+ "special": true
1811
+ },
1812
+ "128226": {
1813
+ "content": "<|reserved_special_token_218|>",
1814
+ "lstrip": false,
1815
+ "normalized": false,
1816
+ "rstrip": false,
1817
+ "single_word": false,
1818
+ "special": true
1819
+ },
1820
+ "128227": {
1821
+ "content": "<|reserved_special_token_219|>",
1822
+ "lstrip": false,
1823
+ "normalized": false,
1824
+ "rstrip": false,
1825
+ "single_word": false,
1826
+ "special": true
1827
+ },
1828
+ "128228": {
1829
+ "content": "<|reserved_special_token_220|>",
1830
+ "lstrip": false,
1831
+ "normalized": false,
1832
+ "rstrip": false,
1833
+ "single_word": false,
1834
+ "special": true
1835
+ },
1836
+ "128229": {
1837
+ "content": "<|reserved_special_token_221|>",
1838
+ "lstrip": false,
1839
+ "normalized": false,
1840
+ "rstrip": false,
1841
+ "single_word": false,
1842
+ "special": true
1843
+ },
1844
+ "128230": {
1845
+ "content": "<|reserved_special_token_222|>",
1846
+ "lstrip": false,
1847
+ "normalized": false,
1848
+ "rstrip": false,
1849
+ "single_word": false,
1850
+ "special": true
1851
+ },
1852
+ "128231": {
1853
+ "content": "<|reserved_special_token_223|>",
1854
+ "lstrip": false,
1855
+ "normalized": false,
1856
+ "rstrip": false,
1857
+ "single_word": false,
1858
+ "special": true
1859
+ },
1860
+ "128232": {
1861
+ "content": "<|reserved_special_token_224|>",
1862
+ "lstrip": false,
1863
+ "normalized": false,
1864
+ "rstrip": false,
1865
+ "single_word": false,
1866
+ "special": true
1867
+ },
1868
+ "128233": {
1869
+ "content": "<|reserved_special_token_225|>",
1870
+ "lstrip": false,
1871
+ "normalized": false,
1872
+ "rstrip": false,
1873
+ "single_word": false,
1874
+ "special": true
1875
+ },
1876
+ "128234": {
1877
+ "content": "<|reserved_special_token_226|>",
1878
+ "lstrip": false,
1879
+ "normalized": false,
1880
+ "rstrip": false,
1881
+ "single_word": false,
1882
+ "special": true
1883
+ },
1884
+ "128235": {
1885
+ "content": "<|reserved_special_token_227|>",
1886
+ "lstrip": false,
1887
+ "normalized": false,
1888
+ "rstrip": false,
1889
+ "single_word": false,
1890
+ "special": true
1891
+ },
1892
+ "128236": {
1893
+ "content": "<|reserved_special_token_228|>",
1894
+ "lstrip": false,
1895
+ "normalized": false,
1896
+ "rstrip": false,
1897
+ "single_word": false,
1898
+ "special": true
1899
+ },
1900
+ "128237": {
1901
+ "content": "<|reserved_special_token_229|>",
1902
+ "lstrip": false,
1903
+ "normalized": false,
1904
+ "rstrip": false,
1905
+ "single_word": false,
1906
+ "special": true
1907
+ },
1908
+ "128238": {
1909
+ "content": "<|reserved_special_token_230|>",
1910
+ "lstrip": false,
1911
+ "normalized": false,
1912
+ "rstrip": false,
1913
+ "single_word": false,
1914
+ "special": true
1915
+ },
1916
+ "128239": {
1917
+ "content": "<|reserved_special_token_231|>",
1918
+ "lstrip": false,
1919
+ "normalized": false,
1920
+ "rstrip": false,
1921
+ "single_word": false,
1922
+ "special": true
1923
+ },
1924
+ "128240": {
1925
+ "content": "<|reserved_special_token_232|>",
1926
+ "lstrip": false,
1927
+ "normalized": false,
1928
+ "rstrip": false,
1929
+ "single_word": false,
1930
+ "special": true
1931
+ },
1932
+ "128241": {
1933
+ "content": "<|reserved_special_token_233|>",
1934
+ "lstrip": false,
1935
+ "normalized": false,
1936
+ "rstrip": false,
1937
+ "single_word": false,
1938
+ "special": true
1939
+ },
1940
+ "128242": {
1941
+ "content": "<|reserved_special_token_234|>",
1942
+ "lstrip": false,
1943
+ "normalized": false,
1944
+ "rstrip": false,
1945
+ "single_word": false,
1946
+ "special": true
1947
+ },
1948
+ "128243": {
1949
+ "content": "<|reserved_special_token_235|>",
1950
+ "lstrip": false,
1951
+ "normalized": false,
1952
+ "rstrip": false,
1953
+ "single_word": false,
1954
+ "special": true
1955
+ },
1956
+ "128244": {
1957
+ "content": "<|reserved_special_token_236|>",
1958
+ "lstrip": false,
1959
+ "normalized": false,
1960
+ "rstrip": false,
1961
+ "single_word": false,
1962
+ "special": true
1963
+ },
1964
+ "128245": {
1965
+ "content": "<|reserved_special_token_237|>",
1966
+ "lstrip": false,
1967
+ "normalized": false,
1968
+ "rstrip": false,
1969
+ "single_word": false,
1970
+ "special": true
1971
+ },
1972
+ "128246": {
1973
+ "content": "<|reserved_special_token_238|>",
1974
+ "lstrip": false,
1975
+ "normalized": false,
1976
+ "rstrip": false,
1977
+ "single_word": false,
1978
+ "special": true
1979
+ },
1980
+ "128247": {
1981
+ "content": "<|reserved_special_token_239|>",
1982
+ "lstrip": false,
1983
+ "normalized": false,
1984
+ "rstrip": false,
1985
+ "single_word": false,
1986
+ "special": true
1987
+ },
1988
+ "128248": {
1989
+ "content": "<|reserved_special_token_240|>",
1990
+ "lstrip": false,
1991
+ "normalized": false,
1992
+ "rstrip": false,
1993
+ "single_word": false,
1994
+ "special": true
1995
+ },
1996
+ "128249": {
1997
+ "content": "<|reserved_special_token_241|>",
1998
+ "lstrip": false,
1999
+ "normalized": false,
2000
+ "rstrip": false,
2001
+ "single_word": false,
2002
+ "special": true
2003
+ },
2004
+ "128250": {
2005
+ "content": "<|reserved_special_token_242|>",
2006
+ "lstrip": false,
2007
+ "normalized": false,
2008
+ "rstrip": false,
2009
+ "single_word": false,
2010
+ "special": true
2011
+ },
2012
+ "128251": {
2013
+ "content": "<|reserved_special_token_243|>",
2014
+ "lstrip": false,
2015
+ "normalized": false,
2016
+ "rstrip": false,
2017
+ "single_word": false,
2018
+ "special": true
2019
+ },
2020
+ "128252": {
2021
+ "content": "<|reserved_special_token_244|>",
2022
+ "lstrip": false,
2023
+ "normalized": false,
2024
+ "rstrip": false,
2025
+ "single_word": false,
2026
+ "special": true
2027
+ },
2028
+ "128253": {
2029
+ "content": "<|reserved_special_token_245|>",
2030
+ "lstrip": false,
2031
+ "normalized": false,
2032
+ "rstrip": false,
2033
+ "single_word": false,
2034
+ "special": true
2035
+ },
2036
+ "128254": {
2037
+ "content": "<|reserved_special_token_246|>",
2038
+ "lstrip": false,
2039
+ "normalized": false,
2040
+ "rstrip": false,
2041
+ "single_word": false,
2042
+ "special": true
2043
+ },
2044
+ "128255": {
2045
+ "content": "<|reserved_special_token_247|>",
2046
+ "lstrip": false,
2047
+ "normalized": false,
2048
+ "rstrip": false,
2049
+ "single_word": false,
2050
+ "special": true
2051
+ }
2052
+ },
2053
+ "bos_token": "<|begin_of_text|>",
2054
+ "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 {%- if strftime_now is defined %}\n {%- set date_string = strftime_now(\"%d %b %Y\") %}\n {%- else %}\n {%- set date_string = \"26 Jul 2024\" %}\n {%- endif %}\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 #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if tools is not none %}\n {{- \"Environment: ipython\\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 {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {{- \"<|eot_id|>\" }}\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",
2055
+ "clean_up_tokenization_spaces": true,
2056
+ "eos_token": "<|eot_id|>",
2057
+ "extra_special_tokens": {},
2058
+ "model_input_names": [
2059
+ "input_ids",
2060
+ "attention_mask"
2061
+ ],
2062
+ "model_max_length": 131072,
2063
+ "pad_token": "<|eot_id|>",
2064
+ "tokenizer_class": "PreTrainedTokenizer"
2065
+ }
checkpoints_ia3_llama_class/checkpoint-128000/trainer_state.json ADDED
@@ -0,0 +1,1970 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 88000,
3
+ "best_metric": 0.936161178019818,
4
+ "best_model_checkpoint": "/home/sujeet-pg/wav2vec2/peft/checkpoints_ia3_llama_class/checkpoint-88000",
5
+ "epoch": 16.0,
6
+ "eval_steps": 500,
7
+ "global_step": 128000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0625,
14
+ "grad_norm": 29.181745529174805,
15
+ "learning_rate": 4.982673611111111e-05,
16
+ "loss": 1.9515,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.125,
21
+ "grad_norm": 84.54170989990234,
22
+ "learning_rate": 4.9653125e-05,
23
+ "loss": 1.4973,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 0.1875,
28
+ "grad_norm": 118.13458251953125,
29
+ "learning_rate": 4.947951388888889e-05,
30
+ "loss": 1.3271,
31
+ "step": 1500
32
+ },
33
+ {
34
+ "epoch": 0.25,
35
+ "grad_norm": 0.062166254967451096,
36
+ "learning_rate": 4.930590277777778e-05,
37
+ "loss": 0.9626,
38
+ "step": 2000
39
+ },
40
+ {
41
+ "epoch": 0.3125,
42
+ "grad_norm": 165.25686645507812,
43
+ "learning_rate": 4.9132291666666665e-05,
44
+ "loss": 0.7346,
45
+ "step": 2500
46
+ },
47
+ {
48
+ "epoch": 0.375,
49
+ "grad_norm": 0.6356489658355713,
50
+ "learning_rate": 4.8958680555555555e-05,
51
+ "loss": 0.8147,
52
+ "step": 3000
53
+ },
54
+ {
55
+ "epoch": 0.4375,
56
+ "grad_norm": 0.012186303734779358,
57
+ "learning_rate": 4.8785069444444445e-05,
58
+ "loss": 0.5557,
59
+ "step": 3500
60
+ },
61
+ {
62
+ "epoch": 0.5,
63
+ "grad_norm": 114.87812805175781,
64
+ "learning_rate": 4.8611458333333335e-05,
65
+ "loss": 0.546,
66
+ "step": 4000
67
+ },
68
+ {
69
+ "epoch": 0.5625,
70
+ "grad_norm": 0.3081382215023041,
71
+ "learning_rate": 4.8437847222222225e-05,
72
+ "loss": 0.5198,
73
+ "step": 4500
74
+ },
75
+ {
76
+ "epoch": 0.625,
77
+ "grad_norm": 0.0013407367514446378,
78
+ "learning_rate": 4.826423611111111e-05,
79
+ "loss": 0.4668,
80
+ "step": 5000
81
+ },
82
+ {
83
+ "epoch": 0.6875,
84
+ "grad_norm": 0.032304372638463974,
85
+ "learning_rate": 4.8090625e-05,
86
+ "loss": 0.4066,
87
+ "step": 5500
88
+ },
89
+ {
90
+ "epoch": 0.75,
91
+ "grad_norm": 0.350352019071579,
92
+ "learning_rate": 4.791701388888889e-05,
93
+ "loss": 0.494,
94
+ "step": 6000
95
+ },
96
+ {
97
+ "epoch": 0.8125,
98
+ "grad_norm": 0.031369373202323914,
99
+ "learning_rate": 4.774340277777778e-05,
100
+ "loss": 0.4372,
101
+ "step": 6500
102
+ },
103
+ {
104
+ "epoch": 0.875,
105
+ "grad_norm": 87.0584716796875,
106
+ "learning_rate": 4.756979166666667e-05,
107
+ "loss": 0.546,
108
+ "step": 7000
109
+ },
110
+ {
111
+ "epoch": 0.9375,
112
+ "grad_norm": 42.25841522216797,
113
+ "learning_rate": 4.739618055555556e-05,
114
+ "loss": 0.4929,
115
+ "step": 7500
116
+ },
117
+ {
118
+ "epoch": 1.0,
119
+ "grad_norm": 0.017110565677285194,
120
+ "learning_rate": 4.722256944444445e-05,
121
+ "loss": 0.4128,
122
+ "step": 8000
123
+ },
124
+ {
125
+ "epoch": 1.0,
126
+ "eval_loss": 0.34961560368537903,
127
+ "eval_pearson": 0.9195974916185884,
128
+ "eval_runtime": 52.203,
129
+ "eval_samples_per_second": 38.312,
130
+ "eval_steps_per_second": 19.156,
131
+ "step": 8000
132
+ },
133
+ {
134
+ "epoch": 1.0625,
135
+ "grad_norm": 39.48343276977539,
136
+ "learning_rate": 4.704895833333334e-05,
137
+ "loss": 0.1769,
138
+ "step": 8500
139
+ },
140
+ {
141
+ "epoch": 1.125,
142
+ "grad_norm": 0.0003292807668913156,
143
+ "learning_rate": 4.687534722222223e-05,
144
+ "loss": 0.3138,
145
+ "step": 9000
146
+ },
147
+ {
148
+ "epoch": 1.1875,
149
+ "grad_norm": 0.0025669685564935207,
150
+ "learning_rate": 4.670173611111111e-05,
151
+ "loss": 0.3529,
152
+ "step": 9500
153
+ },
154
+ {
155
+ "epoch": 1.25,
156
+ "grad_norm": 0.0019228530582040548,
157
+ "learning_rate": 4.6528125e-05,
158
+ "loss": 0.3181,
159
+ "step": 10000
160
+ },
161
+ {
162
+ "epoch": 1.3125,
163
+ "grad_norm": 0.09842195361852646,
164
+ "learning_rate": 4.635451388888889e-05,
165
+ "loss": 0.3358,
166
+ "step": 10500
167
+ },
168
+ {
169
+ "epoch": 1.375,
170
+ "grad_norm": 0.0006872316589578986,
171
+ "learning_rate": 4.618090277777778e-05,
172
+ "loss": 0.3395,
173
+ "step": 11000
174
+ },
175
+ {
176
+ "epoch": 1.4375,
177
+ "grad_norm": 0.008952559903264046,
178
+ "learning_rate": 4.600729166666667e-05,
179
+ "loss": 0.3287,
180
+ "step": 11500
181
+ },
182
+ {
183
+ "epoch": 1.5,
184
+ "grad_norm": 0.0010550743900239468,
185
+ "learning_rate": 4.583368055555556e-05,
186
+ "loss": 0.3742,
187
+ "step": 12000
188
+ },
189
+ {
190
+ "epoch": 1.5625,
191
+ "grad_norm": 0.0011425487464293838,
192
+ "learning_rate": 4.566006944444445e-05,
193
+ "loss": 0.2979,
194
+ "step": 12500
195
+ },
196
+ {
197
+ "epoch": 1.625,
198
+ "grad_norm": 14.729352951049805,
199
+ "learning_rate": 4.5486458333333334e-05,
200
+ "loss": 0.2669,
201
+ "step": 13000
202
+ },
203
+ {
204
+ "epoch": 1.6875,
205
+ "grad_norm": 1.1553162039490417e-05,
206
+ "learning_rate": 4.5312847222222224e-05,
207
+ "loss": 0.3885,
208
+ "step": 13500
209
+ },
210
+ {
211
+ "epoch": 1.75,
212
+ "grad_norm": 0.051722027361392975,
213
+ "learning_rate": 4.5139236111111114e-05,
214
+ "loss": 0.3096,
215
+ "step": 14000
216
+ },
217
+ {
218
+ "epoch": 1.8125,
219
+ "grad_norm": 0.12957464158535004,
220
+ "learning_rate": 4.4965625e-05,
221
+ "loss": 0.3479,
222
+ "step": 14500
223
+ },
224
+ {
225
+ "epoch": 1.875,
226
+ "grad_norm": 0.012610511854290962,
227
+ "learning_rate": 4.479201388888889e-05,
228
+ "loss": 0.432,
229
+ "step": 15000
230
+ },
231
+ {
232
+ "epoch": 1.9375,
233
+ "grad_norm": 0.022952524945139885,
234
+ "learning_rate": 4.461840277777778e-05,
235
+ "loss": 0.2932,
236
+ "step": 15500
237
+ },
238
+ {
239
+ "epoch": 2.0,
240
+ "grad_norm": 3.255659612477757e-05,
241
+ "learning_rate": 4.444479166666667e-05,
242
+ "loss": 0.2544,
243
+ "step": 16000
244
+ },
245
+ {
246
+ "epoch": 2.0,
247
+ "eval_loss": 0.3652373254299164,
248
+ "eval_pearson": 0.9308122796123071,
249
+ "eval_runtime": 52.221,
250
+ "eval_samples_per_second": 38.299,
251
+ "eval_steps_per_second": 19.149,
252
+ "step": 16000
253
+ },
254
+ {
255
+ "epoch": 2.0625,
256
+ "grad_norm": 349.7726135253906,
257
+ "learning_rate": 4.427118055555556e-05,
258
+ "loss": 0.3006,
259
+ "step": 16500
260
+ },
261
+ {
262
+ "epoch": 2.125,
263
+ "grad_norm": 0.05852258577942848,
264
+ "learning_rate": 4.409756944444445e-05,
265
+ "loss": 0.2222,
266
+ "step": 17000
267
+ },
268
+ {
269
+ "epoch": 2.1875,
270
+ "grad_norm": 8.100055129034445e-05,
271
+ "learning_rate": 4.3923958333333337e-05,
272
+ "loss": 0.2253,
273
+ "step": 17500
274
+ },
275
+ {
276
+ "epoch": 2.25,
277
+ "grad_norm": 0.015503599308431149,
278
+ "learning_rate": 4.3750347222222226e-05,
279
+ "loss": 0.301,
280
+ "step": 18000
281
+ },
282
+ {
283
+ "epoch": 2.3125,
284
+ "grad_norm": 0.0007520843064412475,
285
+ "learning_rate": 4.357673611111111e-05,
286
+ "loss": 0.1979,
287
+ "step": 18500
288
+ },
289
+ {
290
+ "epoch": 2.375,
291
+ "grad_norm": 0.0003110193647444248,
292
+ "learning_rate": 4.3403125e-05,
293
+ "loss": 0.2496,
294
+ "step": 19000
295
+ },
296
+ {
297
+ "epoch": 2.4375,
298
+ "grad_norm": 5.800446033477783,
299
+ "learning_rate": 4.322951388888889e-05,
300
+ "loss": 0.3028,
301
+ "step": 19500
302
+ },
303
+ {
304
+ "epoch": 2.5,
305
+ "grad_norm": 2.4347489215870155e-06,
306
+ "learning_rate": 4.305590277777778e-05,
307
+ "loss": 0.2218,
308
+ "step": 20000
309
+ },
310
+ {
311
+ "epoch": 2.5625,
312
+ "grad_norm": 0.972939133644104,
313
+ "learning_rate": 4.288229166666667e-05,
314
+ "loss": 0.2485,
315
+ "step": 20500
316
+ },
317
+ {
318
+ "epoch": 2.625,
319
+ "grad_norm": 1.2701035737991333,
320
+ "learning_rate": 4.270868055555556e-05,
321
+ "loss": 0.179,
322
+ "step": 21000
323
+ },
324
+ {
325
+ "epoch": 2.6875,
326
+ "grad_norm": 0.0001465667737647891,
327
+ "learning_rate": 4.253506944444445e-05,
328
+ "loss": 0.337,
329
+ "step": 21500
330
+ },
331
+ {
332
+ "epoch": 2.75,
333
+ "grad_norm": 188.92559814453125,
334
+ "learning_rate": 4.236145833333334e-05,
335
+ "loss": 0.2353,
336
+ "step": 22000
337
+ },
338
+ {
339
+ "epoch": 2.8125,
340
+ "grad_norm": 0.0020125608425587416,
341
+ "learning_rate": 4.218784722222223e-05,
342
+ "loss": 0.2412,
343
+ "step": 22500
344
+ },
345
+ {
346
+ "epoch": 2.875,
347
+ "grad_norm": 0.030752288177609444,
348
+ "learning_rate": 4.201423611111111e-05,
349
+ "loss": 0.2645,
350
+ "step": 23000
351
+ },
352
+ {
353
+ "epoch": 2.9375,
354
+ "grad_norm": 76.4650650024414,
355
+ "learning_rate": 4.1840625e-05,
356
+ "loss": 0.2856,
357
+ "step": 23500
358
+ },
359
+ {
360
+ "epoch": 3.0,
361
+ "grad_norm": 0.0004072492301929742,
362
+ "learning_rate": 4.166701388888889e-05,
363
+ "loss": 0.2395,
364
+ "step": 24000
365
+ },
366
+ {
367
+ "epoch": 3.0,
368
+ "eval_loss": 0.28703999519348145,
369
+ "eval_pearson": 0.9358259106635223,
370
+ "eval_runtime": 52.1011,
371
+ "eval_samples_per_second": 38.387,
372
+ "eval_steps_per_second": 19.193,
373
+ "step": 24000
374
+ },
375
+ {
376
+ "epoch": 3.0625,
377
+ "grad_norm": 0.007601168937981129,
378
+ "learning_rate": 4.149340277777778e-05,
379
+ "loss": 0.1748,
380
+ "step": 24500
381
+ },
382
+ {
383
+ "epoch": 3.125,
384
+ "grad_norm": 0.026926109567284584,
385
+ "learning_rate": 4.1319791666666665e-05,
386
+ "loss": 0.1542,
387
+ "step": 25000
388
+ },
389
+ {
390
+ "epoch": 3.1875,
391
+ "grad_norm": 1.8115358352661133,
392
+ "learning_rate": 4.1146180555555555e-05,
393
+ "loss": 0.2275,
394
+ "step": 25500
395
+ },
396
+ {
397
+ "epoch": 3.25,
398
+ "grad_norm": 0.06953763216733932,
399
+ "learning_rate": 4.0972569444444445e-05,
400
+ "loss": 0.1706,
401
+ "step": 26000
402
+ },
403
+ {
404
+ "epoch": 3.3125,
405
+ "grad_norm": 0.020493032410740852,
406
+ "learning_rate": 4.0798958333333335e-05,
407
+ "loss": 0.1474,
408
+ "step": 26500
409
+ },
410
+ {
411
+ "epoch": 3.375,
412
+ "grad_norm": 0.005125588737428188,
413
+ "learning_rate": 4.0625347222222225e-05,
414
+ "loss": 0.1723,
415
+ "step": 27000
416
+ },
417
+ {
418
+ "epoch": 3.4375,
419
+ "grad_norm": 5.002508163452148,
420
+ "learning_rate": 4.045173611111111e-05,
421
+ "loss": 0.196,
422
+ "step": 27500
423
+ },
424
+ {
425
+ "epoch": 3.5,
426
+ "grad_norm": 0.000834703678265214,
427
+ "learning_rate": 4.0278125e-05,
428
+ "loss": 0.1449,
429
+ "step": 28000
430
+ },
431
+ {
432
+ "epoch": 3.5625,
433
+ "grad_norm": 0.01109158806502819,
434
+ "learning_rate": 4.010451388888889e-05,
435
+ "loss": 0.2287,
436
+ "step": 28500
437
+ },
438
+ {
439
+ "epoch": 3.625,
440
+ "grad_norm": 9.071109161595814e-06,
441
+ "learning_rate": 3.993090277777778e-05,
442
+ "loss": 0.1955,
443
+ "step": 29000
444
+ },
445
+ {
446
+ "epoch": 3.6875,
447
+ "grad_norm": 0.0006111862603574991,
448
+ "learning_rate": 3.975729166666667e-05,
449
+ "loss": 0.2147,
450
+ "step": 29500
451
+ },
452
+ {
453
+ "epoch": 3.75,
454
+ "grad_norm": 6.614517928937858e-07,
455
+ "learning_rate": 3.958368055555556e-05,
456
+ "loss": 0.2289,
457
+ "step": 30000
458
+ },
459
+ {
460
+ "epoch": 3.8125,
461
+ "grad_norm": 5.0481699872761965e-05,
462
+ "learning_rate": 3.941006944444445e-05,
463
+ "loss": 0.1941,
464
+ "step": 30500
465
+ },
466
+ {
467
+ "epoch": 3.875,
468
+ "grad_norm": 2.837545871734619,
469
+ "learning_rate": 3.923645833333334e-05,
470
+ "loss": 0.1753,
471
+ "step": 31000
472
+ },
473
+ {
474
+ "epoch": 3.9375,
475
+ "grad_norm": 0.00021911883959546685,
476
+ "learning_rate": 3.906284722222223e-05,
477
+ "loss": 0.1967,
478
+ "step": 31500
479
+ },
480
+ {
481
+ "epoch": 4.0,
482
+ "grad_norm": 0.008439241908490658,
483
+ "learning_rate": 3.888923611111111e-05,
484
+ "loss": 0.2341,
485
+ "step": 32000
486
+ },
487
+ {
488
+ "epoch": 4.0,
489
+ "eval_loss": 0.28366541862487793,
490
+ "eval_pearson": 0.9336592859812687,
491
+ "eval_runtime": 52.2768,
492
+ "eval_samples_per_second": 38.258,
493
+ "eval_steps_per_second": 19.129,
494
+ "step": 32000
495
+ },
496
+ {
497
+ "epoch": 4.0625,
498
+ "grad_norm": 3.5697648525238037,
499
+ "learning_rate": 3.8715625e-05,
500
+ "loss": 0.0898,
501
+ "step": 32500
502
+ },
503
+ {
504
+ "epoch": 4.125,
505
+ "grad_norm": 0.005574432201683521,
506
+ "learning_rate": 3.854201388888889e-05,
507
+ "loss": 0.0931,
508
+ "step": 33000
509
+ },
510
+ {
511
+ "epoch": 4.1875,
512
+ "grad_norm": 0.4526767134666443,
513
+ "learning_rate": 3.836840277777778e-05,
514
+ "loss": 0.1269,
515
+ "step": 33500
516
+ },
517
+ {
518
+ "epoch": 4.25,
519
+ "grad_norm": 0.0006220944924280047,
520
+ "learning_rate": 3.819479166666667e-05,
521
+ "loss": 0.1229,
522
+ "step": 34000
523
+ },
524
+ {
525
+ "epoch": 4.3125,
526
+ "grad_norm": 0.0021529244258999825,
527
+ "learning_rate": 3.802118055555556e-05,
528
+ "loss": 0.0941,
529
+ "step": 34500
530
+ },
531
+ {
532
+ "epoch": 4.375,
533
+ "grad_norm": 161.37889099121094,
534
+ "learning_rate": 3.784756944444445e-05,
535
+ "loss": 0.1504,
536
+ "step": 35000
537
+ },
538
+ {
539
+ "epoch": 4.4375,
540
+ "grad_norm": 0.11136477440595627,
541
+ "learning_rate": 3.7673958333333334e-05,
542
+ "loss": 0.1809,
543
+ "step": 35500
544
+ },
545
+ {
546
+ "epoch": 4.5,
547
+ "grad_norm": 0.001285308855585754,
548
+ "learning_rate": 3.7500347222222224e-05,
549
+ "loss": 0.0936,
550
+ "step": 36000
551
+ },
552
+ {
553
+ "epoch": 4.5625,
554
+ "grad_norm": 9.097888687392697e-05,
555
+ "learning_rate": 3.7326736111111114e-05,
556
+ "loss": 0.138,
557
+ "step": 36500
558
+ },
559
+ {
560
+ "epoch": 4.625,
561
+ "grad_norm": 8.100504373942385e-07,
562
+ "learning_rate": 3.7153125e-05,
563
+ "loss": 0.1018,
564
+ "step": 37000
565
+ },
566
+ {
567
+ "epoch": 4.6875,
568
+ "grad_norm": 7.76401338953292e-06,
569
+ "learning_rate": 3.697951388888889e-05,
570
+ "loss": 0.1467,
571
+ "step": 37500
572
+ },
573
+ {
574
+ "epoch": 4.75,
575
+ "grad_norm": 0.00011219551379326731,
576
+ "learning_rate": 3.680590277777778e-05,
577
+ "loss": 0.1253,
578
+ "step": 38000
579
+ },
580
+ {
581
+ "epoch": 4.8125,
582
+ "grad_norm": 6.52613493912213e-07,
583
+ "learning_rate": 3.6632291666666667e-05,
584
+ "loss": 0.1658,
585
+ "step": 38500
586
+ },
587
+ {
588
+ "epoch": 4.875,
589
+ "grad_norm": 0.00043506777728907764,
590
+ "learning_rate": 3.6458680555555557e-05,
591
+ "loss": 0.1746,
592
+ "step": 39000
593
+ },
594
+ {
595
+ "epoch": 4.9375,
596
+ "grad_norm": 0.003737818216904998,
597
+ "learning_rate": 3.6285069444444446e-05,
598
+ "loss": 0.1511,
599
+ "step": 39500
600
+ },
601
+ {
602
+ "epoch": 5.0,
603
+ "grad_norm": 0.0032031103037297726,
604
+ "learning_rate": 3.6111458333333336e-05,
605
+ "loss": 0.1175,
606
+ "step": 40000
607
+ },
608
+ {
609
+ "epoch": 5.0,
610
+ "eval_loss": 0.3400997221469879,
611
+ "eval_pearson": 0.9278541992287661,
612
+ "eval_runtime": 52.4259,
613
+ "eval_samples_per_second": 38.149,
614
+ "eval_steps_per_second": 19.075,
615
+ "step": 40000
616
+ },
617
+ {
618
+ "epoch": 5.0625,
619
+ "grad_norm": 7.578780059702694e-05,
620
+ "learning_rate": 3.5937847222222226e-05,
621
+ "loss": 0.0854,
622
+ "step": 40500
623
+ },
624
+ {
625
+ "epoch": 5.125,
626
+ "grad_norm": 0.00047107384307309985,
627
+ "learning_rate": 3.576423611111111e-05,
628
+ "loss": 0.0978,
629
+ "step": 41000
630
+ },
631
+ {
632
+ "epoch": 5.1875,
633
+ "grad_norm": 1.537612479296513e-05,
634
+ "learning_rate": 3.5590625e-05,
635
+ "loss": 0.0771,
636
+ "step": 41500
637
+ },
638
+ {
639
+ "epoch": 5.25,
640
+ "grad_norm": 0.4128485918045044,
641
+ "learning_rate": 3.541701388888889e-05,
642
+ "loss": 0.0735,
643
+ "step": 42000
644
+ },
645
+ {
646
+ "epoch": 5.3125,
647
+ "grad_norm": 1.5655250549316406,
648
+ "learning_rate": 3.524340277777778e-05,
649
+ "loss": 0.0498,
650
+ "step": 42500
651
+ },
652
+ {
653
+ "epoch": 5.375,
654
+ "grad_norm": 7.616046104885754e-07,
655
+ "learning_rate": 3.506979166666667e-05,
656
+ "loss": 0.0931,
657
+ "step": 43000
658
+ },
659
+ {
660
+ "epoch": 5.4375,
661
+ "grad_norm": 88.26677703857422,
662
+ "learning_rate": 3.489618055555556e-05,
663
+ "loss": 0.0792,
664
+ "step": 43500
665
+ },
666
+ {
667
+ "epoch": 5.5,
668
+ "grad_norm": 5.622899834634154e-07,
669
+ "learning_rate": 3.472256944444445e-05,
670
+ "loss": 0.0598,
671
+ "step": 44000
672
+ },
673
+ {
674
+ "epoch": 5.5625,
675
+ "grad_norm": 3.284021659055725e-07,
676
+ "learning_rate": 3.454895833333334e-05,
677
+ "loss": 0.0569,
678
+ "step": 44500
679
+ },
680
+ {
681
+ "epoch": 5.625,
682
+ "grad_norm": 7.701730646658689e-05,
683
+ "learning_rate": 3.437534722222223e-05,
684
+ "loss": 0.1013,
685
+ "step": 45000
686
+ },
687
+ {
688
+ "epoch": 5.6875,
689
+ "grad_norm": 0.0011569270864129066,
690
+ "learning_rate": 3.420173611111111e-05,
691
+ "loss": 0.0752,
692
+ "step": 45500
693
+ },
694
+ {
695
+ "epoch": 5.75,
696
+ "grad_norm": 0.005151362158358097,
697
+ "learning_rate": 3.4028125e-05,
698
+ "loss": 0.1286,
699
+ "step": 46000
700
+ },
701
+ {
702
+ "epoch": 5.8125,
703
+ "grad_norm": 2.8667493268130784e-08,
704
+ "learning_rate": 3.385451388888889e-05,
705
+ "loss": 0.0628,
706
+ "step": 46500
707
+ },
708
+ {
709
+ "epoch": 5.875,
710
+ "grad_norm": 2.9006994282099186e-06,
711
+ "learning_rate": 3.3680902777777775e-05,
712
+ "loss": 0.0778,
713
+ "step": 47000
714
+ },
715
+ {
716
+ "epoch": 5.9375,
717
+ "grad_norm": 1.4291666047938634e-05,
718
+ "learning_rate": 3.3507291666666665e-05,
719
+ "loss": 0.0939,
720
+ "step": 47500
721
+ },
722
+ {
723
+ "epoch": 6.0,
724
+ "grad_norm": 3.1977786420611665e-05,
725
+ "learning_rate": 3.3333680555555555e-05,
726
+ "loss": 0.0701,
727
+ "step": 48000
728
+ },
729
+ {
730
+ "epoch": 6.0,
731
+ "eval_loss": 0.3394077718257904,
732
+ "eval_pearson": 0.929029551743213,
733
+ "eval_runtime": 52.4713,
734
+ "eval_samples_per_second": 38.116,
735
+ "eval_steps_per_second": 19.058,
736
+ "step": 48000
737
+ },
738
+ {
739
+ "epoch": 6.0625,
740
+ "grad_norm": 2.3781665277056163e-06,
741
+ "learning_rate": 3.3160069444444445e-05,
742
+ "loss": 0.0575,
743
+ "step": 48500
744
+ },
745
+ {
746
+ "epoch": 6.125,
747
+ "grad_norm": 0.00014402755186893046,
748
+ "learning_rate": 3.2986458333333335e-05,
749
+ "loss": 0.0599,
750
+ "step": 49000
751
+ },
752
+ {
753
+ "epoch": 6.1875,
754
+ "grad_norm": 0.0024268697015941143,
755
+ "learning_rate": 3.2812847222222225e-05,
756
+ "loss": 0.0134,
757
+ "step": 49500
758
+ },
759
+ {
760
+ "epoch": 6.25,
761
+ "grad_norm": 2.872504949569702,
762
+ "learning_rate": 3.263923611111111e-05,
763
+ "loss": 0.0529,
764
+ "step": 50000
765
+ },
766
+ {
767
+ "epoch": 6.3125,
768
+ "grad_norm": 0.08783645182847977,
769
+ "learning_rate": 3.2465625e-05,
770
+ "loss": 0.0429,
771
+ "step": 50500
772
+ },
773
+ {
774
+ "epoch": 6.375,
775
+ "grad_norm": 8.48967170715332,
776
+ "learning_rate": 3.229201388888889e-05,
777
+ "loss": 0.0615,
778
+ "step": 51000
779
+ },
780
+ {
781
+ "epoch": 6.4375,
782
+ "grad_norm": 4.978901984031836e-07,
783
+ "learning_rate": 3.211840277777778e-05,
784
+ "loss": 0.0493,
785
+ "step": 51500
786
+ },
787
+ {
788
+ "epoch": 6.5,
789
+ "grad_norm": 1.5710222669440554e-06,
790
+ "learning_rate": 3.194479166666667e-05,
791
+ "loss": 0.0842,
792
+ "step": 52000
793
+ },
794
+ {
795
+ "epoch": 6.5625,
796
+ "grad_norm": 0.0002388143038842827,
797
+ "learning_rate": 3.177118055555556e-05,
798
+ "loss": 0.0322,
799
+ "step": 52500
800
+ },
801
+ {
802
+ "epoch": 6.625,
803
+ "grad_norm": 4.66664324960675e-08,
804
+ "learning_rate": 3.159756944444445e-05,
805
+ "loss": 0.0182,
806
+ "step": 53000
807
+ },
808
+ {
809
+ "epoch": 6.6875,
810
+ "grad_norm": 57.2918586730957,
811
+ "learning_rate": 3.142395833333334e-05,
812
+ "loss": 0.0851,
813
+ "step": 53500
814
+ },
815
+ {
816
+ "epoch": 6.75,
817
+ "grad_norm": 5.3962357924319804e-05,
818
+ "learning_rate": 3.125034722222223e-05,
819
+ "loss": 0.0644,
820
+ "step": 54000
821
+ },
822
+ {
823
+ "epoch": 6.8125,
824
+ "grad_norm": 0.006401342805474997,
825
+ "learning_rate": 3.107673611111111e-05,
826
+ "loss": 0.0943,
827
+ "step": 54500
828
+ },
829
+ {
830
+ "epoch": 6.875,
831
+ "grad_norm": 3.415437390685838e-07,
832
+ "learning_rate": 3.0903125e-05,
833
+ "loss": 0.0967,
834
+ "step": 55000
835
+ },
836
+ {
837
+ "epoch": 6.9375,
838
+ "grad_norm": 5.508160825229425e-07,
839
+ "learning_rate": 3.072951388888889e-05,
840
+ "loss": 0.0507,
841
+ "step": 55500
842
+ },
843
+ {
844
+ "epoch": 7.0,
845
+ "grad_norm": 0.04088839516043663,
846
+ "learning_rate": 3.055590277777778e-05,
847
+ "loss": 0.0139,
848
+ "step": 56000
849
+ },
850
+ {
851
+ "epoch": 7.0,
852
+ "eval_loss": 0.37575554847717285,
853
+ "eval_pearson": 0.9206240663481206,
854
+ "eval_runtime": 52.4561,
855
+ "eval_samples_per_second": 38.127,
856
+ "eval_steps_per_second": 19.064,
857
+ "step": 56000
858
+ },
859
+ {
860
+ "epoch": 7.0625,
861
+ "grad_norm": 0.004823420196771622,
862
+ "learning_rate": 3.0382291666666667e-05,
863
+ "loss": 0.0539,
864
+ "step": 56500
865
+ },
866
+ {
867
+ "epoch": 7.125,
868
+ "grad_norm": 106.49919128417969,
869
+ "learning_rate": 3.0208680555555557e-05,
870
+ "loss": 0.0232,
871
+ "step": 57000
872
+ },
873
+ {
874
+ "epoch": 7.1875,
875
+ "grad_norm": 1.074000238077133e-06,
876
+ "learning_rate": 3.0035069444444447e-05,
877
+ "loss": 0.0187,
878
+ "step": 57500
879
+ },
880
+ {
881
+ "epoch": 7.25,
882
+ "grad_norm": 0.0039020858239382505,
883
+ "learning_rate": 2.9861458333333337e-05,
884
+ "loss": 0.0472,
885
+ "step": 58000
886
+ },
887
+ {
888
+ "epoch": 7.3125,
889
+ "grad_norm": 0.0892600491642952,
890
+ "learning_rate": 2.9687847222222227e-05,
891
+ "loss": 0.0658,
892
+ "step": 58500
893
+ },
894
+ {
895
+ "epoch": 7.375,
896
+ "grad_norm": 0.00350657245144248,
897
+ "learning_rate": 2.951423611111111e-05,
898
+ "loss": 0.0456,
899
+ "step": 59000
900
+ },
901
+ {
902
+ "epoch": 7.4375,
903
+ "grad_norm": 0.0006594175356440246,
904
+ "learning_rate": 2.9340625e-05,
905
+ "loss": 0.0171,
906
+ "step": 59500
907
+ },
908
+ {
909
+ "epoch": 7.5,
910
+ "grad_norm": 92.61225128173828,
911
+ "learning_rate": 2.916701388888889e-05,
912
+ "loss": 0.0274,
913
+ "step": 60000
914
+ },
915
+ {
916
+ "epoch": 7.5625,
917
+ "grad_norm": 3.026230599445512e-09,
918
+ "learning_rate": 2.899340277777778e-05,
919
+ "loss": 0.0471,
920
+ "step": 60500
921
+ },
922
+ {
923
+ "epoch": 7.625,
924
+ "grad_norm": 1.0678179023670964e-05,
925
+ "learning_rate": 2.8819791666666666e-05,
926
+ "loss": 0.0216,
927
+ "step": 61000
928
+ },
929
+ {
930
+ "epoch": 7.6875,
931
+ "grad_norm": 5.752791912527755e-05,
932
+ "learning_rate": 2.8646180555555556e-05,
933
+ "loss": 0.0157,
934
+ "step": 61500
935
+ },
936
+ {
937
+ "epoch": 7.75,
938
+ "grad_norm": 5.118190288543701,
939
+ "learning_rate": 2.8472569444444446e-05,
940
+ "loss": 0.0616,
941
+ "step": 62000
942
+ },
943
+ {
944
+ "epoch": 7.8125,
945
+ "grad_norm": 2.0125851733610034e-05,
946
+ "learning_rate": 2.8298958333333336e-05,
947
+ "loss": 0.0783,
948
+ "step": 62500
949
+ },
950
+ {
951
+ "epoch": 7.875,
952
+ "grad_norm": 161.75416564941406,
953
+ "learning_rate": 2.8125347222222226e-05,
954
+ "loss": 0.0295,
955
+ "step": 63000
956
+ },
957
+ {
958
+ "epoch": 7.9375,
959
+ "grad_norm": 1.577711117306535e-08,
960
+ "learning_rate": 2.795173611111111e-05,
961
+ "loss": 0.0498,
962
+ "step": 63500
963
+ },
964
+ {
965
+ "epoch": 8.0,
966
+ "grad_norm": 5.166618279872637e-07,
967
+ "learning_rate": 2.7778125e-05,
968
+ "loss": 0.0397,
969
+ "step": 64000
970
+ },
971
+ {
972
+ "epoch": 8.0,
973
+ "eval_loss": 0.3336261510848999,
974
+ "eval_pearson": 0.9327475370491191,
975
+ "eval_runtime": 52.4675,
976
+ "eval_samples_per_second": 38.119,
977
+ "eval_steps_per_second": 19.059,
978
+ "step": 64000
979
+ },
980
+ {
981
+ "epoch": 8.0625,
982
+ "grad_norm": 0.0026754948776215315,
983
+ "learning_rate": 2.760451388888889e-05,
984
+ "loss": 0.026,
985
+ "step": 64500
986
+ },
987
+ {
988
+ "epoch": 8.125,
989
+ "grad_norm": 3.3581352454348234e-07,
990
+ "learning_rate": 2.743090277777778e-05,
991
+ "loss": 0.0115,
992
+ "step": 65000
993
+ },
994
+ {
995
+ "epoch": 8.1875,
996
+ "grad_norm": 2.0662416488903546e-07,
997
+ "learning_rate": 2.725729166666667e-05,
998
+ "loss": 0.012,
999
+ "step": 65500
1000
+ },
1001
+ {
1002
+ "epoch": 8.25,
1003
+ "grad_norm": 8.040846921630873e-08,
1004
+ "learning_rate": 2.7083680555555556e-05,
1005
+ "loss": 0.0406,
1006
+ "step": 66000
1007
+ },
1008
+ {
1009
+ "epoch": 8.3125,
1010
+ "grad_norm": 3.422968006816518e-07,
1011
+ "learning_rate": 2.6910069444444446e-05,
1012
+ "loss": 0.0321,
1013
+ "step": 66500
1014
+ },
1015
+ {
1016
+ "epoch": 8.375,
1017
+ "grad_norm": 0.00017860137450043112,
1018
+ "learning_rate": 2.6736458333333336e-05,
1019
+ "loss": 0.0448,
1020
+ "step": 67000
1021
+ },
1022
+ {
1023
+ "epoch": 8.4375,
1024
+ "grad_norm": 1.2621427236680915e-09,
1025
+ "learning_rate": 2.6562847222222225e-05,
1026
+ "loss": 0.0455,
1027
+ "step": 67500
1028
+ },
1029
+ {
1030
+ "epoch": 8.5,
1031
+ "grad_norm": 1.4346144325827481e-06,
1032
+ "learning_rate": 2.638923611111111e-05,
1033
+ "loss": 0.0325,
1034
+ "step": 68000
1035
+ },
1036
+ {
1037
+ "epoch": 8.5625,
1038
+ "grad_norm": 1.2407322174112778e-06,
1039
+ "learning_rate": 2.6215625e-05,
1040
+ "loss": 0.0223,
1041
+ "step": 68500
1042
+ },
1043
+ {
1044
+ "epoch": 8.625,
1045
+ "grad_norm": 3.0256799163908e-06,
1046
+ "learning_rate": 2.604201388888889e-05,
1047
+ "loss": 0.0019,
1048
+ "step": 69000
1049
+ },
1050
+ {
1051
+ "epoch": 8.6875,
1052
+ "grad_norm": 0.007253507152199745,
1053
+ "learning_rate": 2.586840277777778e-05,
1054
+ "loss": 0.0085,
1055
+ "step": 69500
1056
+ },
1057
+ {
1058
+ "epoch": 8.75,
1059
+ "grad_norm": 2.782409467272373e-07,
1060
+ "learning_rate": 2.569479166666667e-05,
1061
+ "loss": 0.0518,
1062
+ "step": 70000
1063
+ },
1064
+ {
1065
+ "epoch": 8.8125,
1066
+ "grad_norm": 0.000820077199023217,
1067
+ "learning_rate": 2.552118055555556e-05,
1068
+ "loss": 0.031,
1069
+ "step": 70500
1070
+ },
1071
+ {
1072
+ "epoch": 8.875,
1073
+ "grad_norm": 2.470728213666007e-05,
1074
+ "learning_rate": 2.5347569444444448e-05,
1075
+ "loss": 0.0354,
1076
+ "step": 71000
1077
+ },
1078
+ {
1079
+ "epoch": 8.9375,
1080
+ "grad_norm": 9.137271263170987e-05,
1081
+ "learning_rate": 2.5173958333333335e-05,
1082
+ "loss": 0.0666,
1083
+ "step": 71500
1084
+ },
1085
+ {
1086
+ "epoch": 9.0,
1087
+ "grad_norm": 0.00029885413823649287,
1088
+ "learning_rate": 2.5000347222222225e-05,
1089
+ "loss": 0.0267,
1090
+ "step": 72000
1091
+ },
1092
+ {
1093
+ "epoch": 9.0,
1094
+ "eval_loss": 0.37894001603126526,
1095
+ "eval_pearson": 0.9279985680079542,
1096
+ "eval_runtime": 52.4816,
1097
+ "eval_samples_per_second": 38.109,
1098
+ "eval_steps_per_second": 19.054,
1099
+ "step": 72000
1100
+ },
1101
+ {
1102
+ "epoch": 9.0625,
1103
+ "grad_norm": 6.724835839122534e-05,
1104
+ "learning_rate": 2.482673611111111e-05,
1105
+ "loss": 0.0044,
1106
+ "step": 72500
1107
+ },
1108
+ {
1109
+ "epoch": 9.125,
1110
+ "grad_norm": 9.228666164595722e-10,
1111
+ "learning_rate": 2.4653125e-05,
1112
+ "loss": 0.0095,
1113
+ "step": 73000
1114
+ },
1115
+ {
1116
+ "epoch": 9.1875,
1117
+ "grad_norm": 0.00011938459647353739,
1118
+ "learning_rate": 2.447951388888889e-05,
1119
+ "loss": 0.0384,
1120
+ "step": 73500
1121
+ },
1122
+ {
1123
+ "epoch": 9.25,
1124
+ "grad_norm": 1.6898056287573127e-09,
1125
+ "learning_rate": 2.4305902777777778e-05,
1126
+ "loss": 0.0182,
1127
+ "step": 74000
1128
+ },
1129
+ {
1130
+ "epoch": 9.3125,
1131
+ "grad_norm": 5.753568288469069e-09,
1132
+ "learning_rate": 2.4132291666666668e-05,
1133
+ "loss": 0.0075,
1134
+ "step": 74500
1135
+ },
1136
+ {
1137
+ "epoch": 9.375,
1138
+ "grad_norm": 5.144208614638046e-08,
1139
+ "learning_rate": 2.3958680555555558e-05,
1140
+ "loss": 0.0172,
1141
+ "step": 75000
1142
+ },
1143
+ {
1144
+ "epoch": 9.4375,
1145
+ "grad_norm": 9.800347200439319e-10,
1146
+ "learning_rate": 2.3785069444444448e-05,
1147
+ "loss": 0.0431,
1148
+ "step": 75500
1149
+ },
1150
+ {
1151
+ "epoch": 9.5,
1152
+ "grad_norm": 5.440585135185749e-11,
1153
+ "learning_rate": 2.3611458333333334e-05,
1154
+ "loss": 0.0109,
1155
+ "step": 76000
1156
+ },
1157
+ {
1158
+ "epoch": 9.5625,
1159
+ "grad_norm": 0.00019604770932346582,
1160
+ "learning_rate": 2.3437847222222224e-05,
1161
+ "loss": 0.0284,
1162
+ "step": 76500
1163
+ },
1164
+ {
1165
+ "epoch": 9.625,
1166
+ "grad_norm": 1.242908239364624,
1167
+ "learning_rate": 2.3264236111111114e-05,
1168
+ "loss": 0.0405,
1169
+ "step": 77000
1170
+ },
1171
+ {
1172
+ "epoch": 9.6875,
1173
+ "grad_norm": 1.540728953841608e-05,
1174
+ "learning_rate": 2.3090625e-05,
1175
+ "loss": 0.0435,
1176
+ "step": 77500
1177
+ },
1178
+ {
1179
+ "epoch": 9.75,
1180
+ "grad_norm": 0.00013433759158942848,
1181
+ "learning_rate": 2.291701388888889e-05,
1182
+ "loss": 0.0181,
1183
+ "step": 78000
1184
+ },
1185
+ {
1186
+ "epoch": 9.8125,
1187
+ "grad_norm": 3.088209687973631e-10,
1188
+ "learning_rate": 2.2743402777777777e-05,
1189
+ "loss": 0.0228,
1190
+ "step": 78500
1191
+ },
1192
+ {
1193
+ "epoch": 9.875,
1194
+ "grad_norm": 0.000814907078165561,
1195
+ "learning_rate": 2.2569791666666667e-05,
1196
+ "loss": 0.0499,
1197
+ "step": 79000
1198
+ },
1199
+ {
1200
+ "epoch": 9.9375,
1201
+ "grad_norm": 1.274260625905299e-07,
1202
+ "learning_rate": 2.2396180555555557e-05,
1203
+ "loss": 0.0316,
1204
+ "step": 79500
1205
+ },
1206
+ {
1207
+ "epoch": 10.0,
1208
+ "grad_norm": 4.301631997805089e-05,
1209
+ "learning_rate": 2.2222569444444447e-05,
1210
+ "loss": 0.015,
1211
+ "step": 80000
1212
+ },
1213
+ {
1214
+ "epoch": 10.0,
1215
+ "eval_loss": 0.38902410864830017,
1216
+ "eval_pearson": 0.9249309324232664,
1217
+ "eval_runtime": 52.3807,
1218
+ "eval_samples_per_second": 38.182,
1219
+ "eval_steps_per_second": 19.091,
1220
+ "step": 80000
1221
+ },
1222
+ {
1223
+ "epoch": 10.0625,
1224
+ "grad_norm": 1.7468665403086447e-10,
1225
+ "learning_rate": 2.2048958333333333e-05,
1226
+ "loss": 0.0081,
1227
+ "step": 80500
1228
+ },
1229
+ {
1230
+ "epoch": 10.125,
1231
+ "grad_norm": 6.71422021696344e-05,
1232
+ "learning_rate": 2.1875347222222223e-05,
1233
+ "loss": 0.0143,
1234
+ "step": 81000
1235
+ },
1236
+ {
1237
+ "epoch": 10.1875,
1238
+ "grad_norm": 3.1802871944819344e-06,
1239
+ "learning_rate": 2.1701736111111113e-05,
1240
+ "loss": 0.029,
1241
+ "step": 81500
1242
+ },
1243
+ {
1244
+ "epoch": 10.25,
1245
+ "grad_norm": 0.014791320078074932,
1246
+ "learning_rate": 2.1528125000000003e-05,
1247
+ "loss": 0.0054,
1248
+ "step": 82000
1249
+ },
1250
+ {
1251
+ "epoch": 10.3125,
1252
+ "grad_norm": 2.0462434235923865e-07,
1253
+ "learning_rate": 2.135451388888889e-05,
1254
+ "loss": 0.0436,
1255
+ "step": 82500
1256
+ },
1257
+ {
1258
+ "epoch": 10.375,
1259
+ "grad_norm": 1.3791065216064453,
1260
+ "learning_rate": 2.1180902777777776e-05,
1261
+ "loss": 0.0181,
1262
+ "step": 83000
1263
+ },
1264
+ {
1265
+ "epoch": 10.4375,
1266
+ "grad_norm": 0.002008361741900444,
1267
+ "learning_rate": 2.1007291666666666e-05,
1268
+ "loss": 0.0082,
1269
+ "step": 83500
1270
+ },
1271
+ {
1272
+ "epoch": 10.5,
1273
+ "grad_norm": 5.804303704337599e-09,
1274
+ "learning_rate": 2.0833680555555556e-05,
1275
+ "loss": 0.0249,
1276
+ "step": 84000
1277
+ },
1278
+ {
1279
+ "epoch": 10.5625,
1280
+ "grad_norm": 0.0007163327536545694,
1281
+ "learning_rate": 2.0660069444444446e-05,
1282
+ "loss": 0.0112,
1283
+ "step": 84500
1284
+ },
1285
+ {
1286
+ "epoch": 10.625,
1287
+ "grad_norm": 0.0001620600960450247,
1288
+ "learning_rate": 2.0486458333333333e-05,
1289
+ "loss": 0.0295,
1290
+ "step": 85000
1291
+ },
1292
+ {
1293
+ "epoch": 10.6875,
1294
+ "grad_norm": 0.05068128928542137,
1295
+ "learning_rate": 2.0312847222222223e-05,
1296
+ "loss": 0.0223,
1297
+ "step": 85500
1298
+ },
1299
+ {
1300
+ "epoch": 10.75,
1301
+ "grad_norm": 0.0007038409821689129,
1302
+ "learning_rate": 2.0139236111111113e-05,
1303
+ "loss": 0.0192,
1304
+ "step": 86000
1305
+ },
1306
+ {
1307
+ "epoch": 10.8125,
1308
+ "grad_norm": 0.024000702425837517,
1309
+ "learning_rate": 1.9965625000000002e-05,
1310
+ "loss": 0.0249,
1311
+ "step": 86500
1312
+ },
1313
+ {
1314
+ "epoch": 10.875,
1315
+ "grad_norm": 3.588341712656984e-07,
1316
+ "learning_rate": 1.9792013888888892e-05,
1317
+ "loss": 0.0429,
1318
+ "step": 87000
1319
+ },
1320
+ {
1321
+ "epoch": 10.9375,
1322
+ "grad_norm": 1.5524047114467976e-07,
1323
+ "learning_rate": 1.961840277777778e-05,
1324
+ "loss": 0.0188,
1325
+ "step": 87500
1326
+ },
1327
+ {
1328
+ "epoch": 11.0,
1329
+ "grad_norm": 2.524126614389388e-07,
1330
+ "learning_rate": 1.944479166666667e-05,
1331
+ "loss": 0.0217,
1332
+ "step": 88000
1333
+ },
1334
+ {
1335
+ "epoch": 11.0,
1336
+ "eval_loss": 0.39052143692970276,
1337
+ "eval_pearson": 0.936161178019818,
1338
+ "eval_runtime": 52.432,
1339
+ "eval_samples_per_second": 38.145,
1340
+ "eval_steps_per_second": 19.072,
1341
+ "step": 88000
1342
+ },
1343
+ {
1344
+ "epoch": 11.0625,
1345
+ "grad_norm": 0.0005805569817312062,
1346
+ "learning_rate": 1.9271180555555555e-05,
1347
+ "loss": 0.0255,
1348
+ "step": 88500
1349
+ },
1350
+ {
1351
+ "epoch": 11.125,
1352
+ "grad_norm": 4.623345546406199e-07,
1353
+ "learning_rate": 1.9097569444444445e-05,
1354
+ "loss": 0.0078,
1355
+ "step": 89000
1356
+ },
1357
+ {
1358
+ "epoch": 11.1875,
1359
+ "grad_norm": 5.301876715435583e-09,
1360
+ "learning_rate": 1.8923958333333332e-05,
1361
+ "loss": 0.005,
1362
+ "step": 89500
1363
+ },
1364
+ {
1365
+ "epoch": 11.25,
1366
+ "grad_norm": 0.09818815439939499,
1367
+ "learning_rate": 1.8750347222222222e-05,
1368
+ "loss": 0.008,
1369
+ "step": 90000
1370
+ },
1371
+ {
1372
+ "epoch": 11.3125,
1373
+ "grad_norm": 1.8287735656485893e-05,
1374
+ "learning_rate": 1.8576736111111112e-05,
1375
+ "loss": 0.0021,
1376
+ "step": 90500
1377
+ },
1378
+ {
1379
+ "epoch": 11.375,
1380
+ "grad_norm": 9.81485072770738e-07,
1381
+ "learning_rate": 1.8403125000000002e-05,
1382
+ "loss": 0.014,
1383
+ "step": 91000
1384
+ },
1385
+ {
1386
+ "epoch": 11.4375,
1387
+ "grad_norm": 0.006411096081137657,
1388
+ "learning_rate": 1.8229513888888892e-05,
1389
+ "loss": 0.0128,
1390
+ "step": 91500
1391
+ },
1392
+ {
1393
+ "epoch": 11.5,
1394
+ "grad_norm": 4.448479778984549e-11,
1395
+ "learning_rate": 1.8055902777777778e-05,
1396
+ "loss": 0.0023,
1397
+ "step": 92000
1398
+ },
1399
+ {
1400
+ "epoch": 11.5625,
1401
+ "grad_norm": 0.012693402357399464,
1402
+ "learning_rate": 1.7882291666666668e-05,
1403
+ "loss": 0.0344,
1404
+ "step": 92500
1405
+ },
1406
+ {
1407
+ "epoch": 11.625,
1408
+ "grad_norm": 6.370872540628625e-08,
1409
+ "learning_rate": 1.7708680555555558e-05,
1410
+ "loss": 0.0258,
1411
+ "step": 93000
1412
+ },
1413
+ {
1414
+ "epoch": 11.6875,
1415
+ "grad_norm": 9.032481429471773e-09,
1416
+ "learning_rate": 1.7535069444444445e-05,
1417
+ "loss": 0.0112,
1418
+ "step": 93500
1419
+ },
1420
+ {
1421
+ "epoch": 11.75,
1422
+ "grad_norm": 0.001719271531328559,
1423
+ "learning_rate": 1.7361458333333335e-05,
1424
+ "loss": 0.0275,
1425
+ "step": 94000
1426
+ },
1427
+ {
1428
+ "epoch": 11.8125,
1429
+ "grad_norm": 7.162652036640793e-05,
1430
+ "learning_rate": 1.718784722222222e-05,
1431
+ "loss": 0.0119,
1432
+ "step": 94500
1433
+ },
1434
+ {
1435
+ "epoch": 11.875,
1436
+ "grad_norm": 1.2189951803520671e-06,
1437
+ "learning_rate": 1.701423611111111e-05,
1438
+ "loss": 0.0392,
1439
+ "step": 95000
1440
+ },
1441
+ {
1442
+ "epoch": 11.9375,
1443
+ "grad_norm": 5.709237484552432e-06,
1444
+ "learning_rate": 1.6840625e-05,
1445
+ "loss": 0.0341,
1446
+ "step": 95500
1447
+ },
1448
+ {
1449
+ "epoch": 12.0,
1450
+ "grad_norm": 1.2266503290447872e-05,
1451
+ "learning_rate": 1.666701388888889e-05,
1452
+ "loss": 0.1026,
1453
+ "step": 96000
1454
+ },
1455
+ {
1456
+ "epoch": 12.0,
1457
+ "eval_loss": 0.42006340622901917,
1458
+ "eval_pearson": 0.9249266863163004,
1459
+ "eval_runtime": 52.4951,
1460
+ "eval_samples_per_second": 38.099,
1461
+ "eval_steps_per_second": 19.049,
1462
+ "step": 96000
1463
+ },
1464
+ {
1465
+ "epoch": 12.0625,
1466
+ "grad_norm": 1.2190711773385488e-09,
1467
+ "learning_rate": 1.6493402777777778e-05,
1468
+ "loss": 0.0118,
1469
+ "step": 96500
1470
+ },
1471
+ {
1472
+ "epoch": 12.125,
1473
+ "grad_norm": 9.660718660597922e-07,
1474
+ "learning_rate": 1.6319791666666668e-05,
1475
+ "loss": 0.0021,
1476
+ "step": 97000
1477
+ },
1478
+ {
1479
+ "epoch": 12.1875,
1480
+ "grad_norm": 0.0003258072247263044,
1481
+ "learning_rate": 1.6146180555555557e-05,
1482
+ "loss": 0.011,
1483
+ "step": 97500
1484
+ },
1485
+ {
1486
+ "epoch": 12.25,
1487
+ "grad_norm": 0.00024601773475296795,
1488
+ "learning_rate": 1.5972569444444447e-05,
1489
+ "loss": 0.0161,
1490
+ "step": 98000
1491
+ },
1492
+ {
1493
+ "epoch": 12.3125,
1494
+ "grad_norm": 2.0050613613875612e-07,
1495
+ "learning_rate": 1.5798958333333334e-05,
1496
+ "loss": 0.0062,
1497
+ "step": 98500
1498
+ },
1499
+ {
1500
+ "epoch": 12.375,
1501
+ "grad_norm": 0.00019162562966812402,
1502
+ "learning_rate": 1.5625347222222224e-05,
1503
+ "loss": 0.0017,
1504
+ "step": 99000
1505
+ },
1506
+ {
1507
+ "epoch": 12.4375,
1508
+ "grad_norm": 5.855550853084424e-07,
1509
+ "learning_rate": 1.545173611111111e-05,
1510
+ "loss": 0.011,
1511
+ "step": 99500
1512
+ },
1513
+ {
1514
+ "epoch": 12.5,
1515
+ "grad_norm": 5.200939631322399e-05,
1516
+ "learning_rate": 1.5278125e-05,
1517
+ "loss": 0.0625,
1518
+ "step": 100000
1519
+ },
1520
+ {
1521
+ "epoch": 12.5625,
1522
+ "grad_norm": 0.0051911999471485615,
1523
+ "learning_rate": 1.510451388888889e-05,
1524
+ "loss": 0.0223,
1525
+ "step": 100500
1526
+ },
1527
+ {
1528
+ "epoch": 12.625,
1529
+ "grad_norm": 0.00023108582536224276,
1530
+ "learning_rate": 1.4930902777777777e-05,
1531
+ "loss": 0.0184,
1532
+ "step": 101000
1533
+ },
1534
+ {
1535
+ "epoch": 12.6875,
1536
+ "grad_norm": 1.2751560461765621e-05,
1537
+ "learning_rate": 1.4757291666666667e-05,
1538
+ "loss": 0.0325,
1539
+ "step": 101500
1540
+ },
1541
+ {
1542
+ "epoch": 12.75,
1543
+ "grad_norm": 0.07260618358850479,
1544
+ "learning_rate": 1.4583680555555557e-05,
1545
+ "loss": 0.0472,
1546
+ "step": 102000
1547
+ },
1548
+ {
1549
+ "epoch": 12.8125,
1550
+ "grad_norm": 1.3546050467994064e-06,
1551
+ "learning_rate": 1.4410069444444447e-05,
1552
+ "loss": 0.0326,
1553
+ "step": 102500
1554
+ },
1555
+ {
1556
+ "epoch": 12.875,
1557
+ "grad_norm": 0.00040618935599923134,
1558
+ "learning_rate": 1.4236458333333333e-05,
1559
+ "loss": 0.0092,
1560
+ "step": 103000
1561
+ },
1562
+ {
1563
+ "epoch": 12.9375,
1564
+ "grad_norm": 3.1089444973986247e-07,
1565
+ "learning_rate": 1.4062847222222223e-05,
1566
+ "loss": 0.0493,
1567
+ "step": 103500
1568
+ },
1569
+ {
1570
+ "epoch": 13.0,
1571
+ "grad_norm": 0.02031463012099266,
1572
+ "learning_rate": 1.3889236111111111e-05,
1573
+ "loss": 0.0344,
1574
+ "step": 104000
1575
+ },
1576
+ {
1577
+ "epoch": 13.0,
1578
+ "eval_loss": 0.3848821818828583,
1579
+ "eval_pearson": 0.9320737941331698,
1580
+ "eval_runtime": 52.3286,
1581
+ "eval_samples_per_second": 38.22,
1582
+ "eval_steps_per_second": 19.11,
1583
+ "step": 104000
1584
+ },
1585
+ {
1586
+ "epoch": 13.0625,
1587
+ "grad_norm": 5.390070782596013e-06,
1588
+ "learning_rate": 1.3715625000000001e-05,
1589
+ "loss": 0.0024,
1590
+ "step": 104500
1591
+ },
1592
+ {
1593
+ "epoch": 13.125,
1594
+ "grad_norm": 0.0009596606250852346,
1595
+ "learning_rate": 1.3542013888888891e-05,
1596
+ "loss": 0.0002,
1597
+ "step": 105000
1598
+ },
1599
+ {
1600
+ "epoch": 13.1875,
1601
+ "grad_norm": 1.6519630889888504e-06,
1602
+ "learning_rate": 1.3368402777777778e-05,
1603
+ "loss": 0.0079,
1604
+ "step": 105500
1605
+ },
1606
+ {
1607
+ "epoch": 13.25,
1608
+ "grad_norm": 2.448989988579342e-08,
1609
+ "learning_rate": 1.3194791666666668e-05,
1610
+ "loss": 0.0153,
1611
+ "step": 106000
1612
+ },
1613
+ {
1614
+ "epoch": 13.3125,
1615
+ "grad_norm": 0.0002976028772536665,
1616
+ "learning_rate": 1.3021180555555556e-05,
1617
+ "loss": 0.0039,
1618
+ "step": 106500
1619
+ },
1620
+ {
1621
+ "epoch": 13.375,
1622
+ "grad_norm": 0.00019340288417879492,
1623
+ "learning_rate": 1.2847569444444446e-05,
1624
+ "loss": 0.0163,
1625
+ "step": 107000
1626
+ },
1627
+ {
1628
+ "epoch": 13.4375,
1629
+ "grad_norm": 0.0057904901914298534,
1630
+ "learning_rate": 1.2673958333333333e-05,
1631
+ "loss": 0.0122,
1632
+ "step": 107500
1633
+ },
1634
+ {
1635
+ "epoch": 13.5,
1636
+ "grad_norm": 9.801337910175789e-06,
1637
+ "learning_rate": 1.2500347222222222e-05,
1638
+ "loss": 0.0379,
1639
+ "step": 108000
1640
+ },
1641
+ {
1642
+ "epoch": 13.5625,
1643
+ "grad_norm": 1.4482387769021443e-06,
1644
+ "learning_rate": 1.2326736111111112e-05,
1645
+ "loss": 0.0114,
1646
+ "step": 108500
1647
+ },
1648
+ {
1649
+ "epoch": 13.625,
1650
+ "grad_norm": 2.1305972040863708e-05,
1651
+ "learning_rate": 1.2153125e-05,
1652
+ "loss": 0.018,
1653
+ "step": 109000
1654
+ },
1655
+ {
1656
+ "epoch": 13.6875,
1657
+ "grad_norm": 0.09945420920848846,
1658
+ "learning_rate": 1.1979513888888889e-05,
1659
+ "loss": 0.0726,
1660
+ "step": 109500
1661
+ },
1662
+ {
1663
+ "epoch": 13.75,
1664
+ "grad_norm": 5.7829329307423905e-06,
1665
+ "learning_rate": 1.1805902777777779e-05,
1666
+ "loss": 0.0193,
1667
+ "step": 110000
1668
+ },
1669
+ {
1670
+ "epoch": 13.8125,
1671
+ "grad_norm": 6.558164386660792e-06,
1672
+ "learning_rate": 1.1632291666666667e-05,
1673
+ "loss": 0.0129,
1674
+ "step": 110500
1675
+ },
1676
+ {
1677
+ "epoch": 13.875,
1678
+ "grad_norm": 4.0651830346405404e-08,
1679
+ "learning_rate": 1.1458680555555557e-05,
1680
+ "loss": 0.0389,
1681
+ "step": 111000
1682
+ },
1683
+ {
1684
+ "epoch": 13.9375,
1685
+ "grad_norm": 1.2806684601684992e-08,
1686
+ "learning_rate": 1.1285069444444445e-05,
1687
+ "loss": 0.0071,
1688
+ "step": 111500
1689
+ },
1690
+ {
1691
+ "epoch": 14.0,
1692
+ "grad_norm": 0.11720628291368484,
1693
+ "learning_rate": 1.1111458333333333e-05,
1694
+ "loss": 0.0115,
1695
+ "step": 112000
1696
+ },
1697
+ {
1698
+ "epoch": 14.0,
1699
+ "eval_loss": 0.4008629620075226,
1700
+ "eval_pearson": 0.9287046075964228,
1701
+ "eval_runtime": 52.1174,
1702
+ "eval_samples_per_second": 38.375,
1703
+ "eval_steps_per_second": 19.187,
1704
+ "step": 112000
1705
+ },
1706
+ {
1707
+ "epoch": 14.0625,
1708
+ "grad_norm": 3.696676298403645e-09,
1709
+ "learning_rate": 1.0937847222222222e-05,
1710
+ "loss": 0.002,
1711
+ "step": 112500
1712
+ },
1713
+ {
1714
+ "epoch": 14.125,
1715
+ "grad_norm": 1.5702152040830697e-06,
1716
+ "learning_rate": 1.0764236111111112e-05,
1717
+ "loss": 0.011,
1718
+ "step": 113000
1719
+ },
1720
+ {
1721
+ "epoch": 14.1875,
1722
+ "grad_norm": 5.9359957958804443e-05,
1723
+ "learning_rate": 1.0590625e-05,
1724
+ "loss": 0.002,
1725
+ "step": 113500
1726
+ },
1727
+ {
1728
+ "epoch": 14.25,
1729
+ "grad_norm": 1.7063765331282177e-11,
1730
+ "learning_rate": 1.041701388888889e-05,
1731
+ "loss": 0.0092,
1732
+ "step": 114000
1733
+ },
1734
+ {
1735
+ "epoch": 14.3125,
1736
+ "grad_norm": 0.0013318562414497137,
1737
+ "learning_rate": 1.0243402777777778e-05,
1738
+ "loss": 0.0037,
1739
+ "step": 114500
1740
+ },
1741
+ {
1742
+ "epoch": 14.375,
1743
+ "grad_norm": 0.00013518838386517018,
1744
+ "learning_rate": 1.0069791666666666e-05,
1745
+ "loss": 0.0253,
1746
+ "step": 115000
1747
+ },
1748
+ {
1749
+ "epoch": 14.4375,
1750
+ "grad_norm": 0.0004931968287564814,
1751
+ "learning_rate": 9.896180555555556e-06,
1752
+ "loss": 0.0002,
1753
+ "step": 115500
1754
+ },
1755
+ {
1756
+ "epoch": 14.5,
1757
+ "grad_norm": 3.0277399787337345e-07,
1758
+ "learning_rate": 9.722569444444445e-06,
1759
+ "loss": 0.0219,
1760
+ "step": 116000
1761
+ },
1762
+ {
1763
+ "epoch": 14.5625,
1764
+ "grad_norm": 0.005195027217268944,
1765
+ "learning_rate": 9.548958333333334e-06,
1766
+ "loss": 0.0144,
1767
+ "step": 116500
1768
+ },
1769
+ {
1770
+ "epoch": 14.625,
1771
+ "grad_norm": 0.028845345601439476,
1772
+ "learning_rate": 9.375347222222223e-06,
1773
+ "loss": 0.0147,
1774
+ "step": 117000
1775
+ },
1776
+ {
1777
+ "epoch": 14.6875,
1778
+ "grad_norm": 2.050080212256944e-07,
1779
+ "learning_rate": 9.201736111111111e-06,
1780
+ "loss": 0.047,
1781
+ "step": 117500
1782
+ },
1783
+ {
1784
+ "epoch": 14.75,
1785
+ "grad_norm": 2.6781076911674973e-08,
1786
+ "learning_rate": 9.028125e-06,
1787
+ "loss": 0.023,
1788
+ "step": 118000
1789
+ },
1790
+ {
1791
+ "epoch": 14.8125,
1792
+ "grad_norm": 4.3490285861480515e-07,
1793
+ "learning_rate": 8.85451388888889e-06,
1794
+ "loss": 0.0397,
1795
+ "step": 118500
1796
+ },
1797
+ {
1798
+ "epoch": 14.875,
1799
+ "grad_norm": 5.553416121983901e-05,
1800
+ "learning_rate": 8.680902777777779e-06,
1801
+ "loss": 0.0129,
1802
+ "step": 119000
1803
+ },
1804
+ {
1805
+ "epoch": 14.9375,
1806
+ "grad_norm": 0.0018387527670711279,
1807
+ "learning_rate": 8.507291666666667e-06,
1808
+ "loss": 0.0117,
1809
+ "step": 119500
1810
+ },
1811
+ {
1812
+ "epoch": 15.0,
1813
+ "grad_norm": 3.0822722846268746e-11,
1814
+ "learning_rate": 8.333680555555556e-06,
1815
+ "loss": 0.0289,
1816
+ "step": 120000
1817
+ },
1818
+ {
1819
+ "epoch": 15.0,
1820
+ "eval_loss": 0.4116508662700653,
1821
+ "eval_pearson": 0.9338347129537201,
1822
+ "eval_runtime": 52.0977,
1823
+ "eval_samples_per_second": 38.389,
1824
+ "eval_steps_per_second": 19.195,
1825
+ "step": 120000
1826
+ },
1827
+ {
1828
+ "epoch": 15.0625,
1829
+ "grad_norm": 0.001994462450966239,
1830
+ "learning_rate": 8.160069444444444e-06,
1831
+ "loss": 0.0078,
1832
+ "step": 120500
1833
+ },
1834
+ {
1835
+ "epoch": 15.125,
1836
+ "grad_norm": 3.360041411770709e-10,
1837
+ "learning_rate": 7.986458333333334e-06,
1838
+ "loss": 0.0157,
1839
+ "step": 121000
1840
+ },
1841
+ {
1842
+ "epoch": 15.1875,
1843
+ "grad_norm": 9.282373980568082e-07,
1844
+ "learning_rate": 7.812847222222222e-06,
1845
+ "loss": 0.0078,
1846
+ "step": 121500
1847
+ },
1848
+ {
1849
+ "epoch": 15.25,
1850
+ "grad_norm": 1.6110238698630042e-09,
1851
+ "learning_rate": 7.639236111111112e-06,
1852
+ "loss": 0.026,
1853
+ "step": 122000
1854
+ },
1855
+ {
1856
+ "epoch": 15.3125,
1857
+ "grad_norm": 2.1387499145930633e-05,
1858
+ "learning_rate": 7.465624999999999e-06,
1859
+ "loss": 0.0182,
1860
+ "step": 122500
1861
+ },
1862
+ {
1863
+ "epoch": 15.375,
1864
+ "grad_norm": 5.649494067005989e-11,
1865
+ "learning_rate": 7.292013888888889e-06,
1866
+ "loss": 0.0106,
1867
+ "step": 123000
1868
+ },
1869
+ {
1870
+ "epoch": 15.4375,
1871
+ "grad_norm": 0.008713332004845142,
1872
+ "learning_rate": 7.118402777777778e-06,
1873
+ "loss": 0.0361,
1874
+ "step": 123500
1875
+ },
1876
+ {
1877
+ "epoch": 15.5,
1878
+ "grad_norm": 1.6483255649291095e-08,
1879
+ "learning_rate": 6.944791666666667e-06,
1880
+ "loss": 0.0187,
1881
+ "step": 124000
1882
+ },
1883
+ {
1884
+ "epoch": 15.5625,
1885
+ "grad_norm": 0.002335034077987075,
1886
+ "learning_rate": 6.7711805555555566e-06,
1887
+ "loss": 0.0055,
1888
+ "step": 124500
1889
+ },
1890
+ {
1891
+ "epoch": 15.625,
1892
+ "grad_norm": 0.03660840913653374,
1893
+ "learning_rate": 6.597569444444445e-06,
1894
+ "loss": 0.0327,
1895
+ "step": 125000
1896
+ },
1897
+ {
1898
+ "epoch": 15.6875,
1899
+ "grad_norm": 1.491520379204303e-06,
1900
+ "learning_rate": 6.423958333333334e-06,
1901
+ "loss": 0.021,
1902
+ "step": 125500
1903
+ },
1904
+ {
1905
+ "epoch": 15.75,
1906
+ "grad_norm": 1.702046326101936e-08,
1907
+ "learning_rate": 6.250347222222222e-06,
1908
+ "loss": 0.0192,
1909
+ "step": 126000
1910
+ },
1911
+ {
1912
+ "epoch": 15.8125,
1913
+ "grad_norm": 4.671832812164212e-06,
1914
+ "learning_rate": 6.076736111111111e-06,
1915
+ "loss": 0.0218,
1916
+ "step": 126500
1917
+ },
1918
+ {
1919
+ "epoch": 15.875,
1920
+ "grad_norm": 3.007305167557206e-06,
1921
+ "learning_rate": 5.903125e-06,
1922
+ "loss": 0.0071,
1923
+ "step": 127000
1924
+ },
1925
+ {
1926
+ "epoch": 15.9375,
1927
+ "grad_norm": 0.00012980301107745618,
1928
+ "learning_rate": 5.7295138888888894e-06,
1929
+ "loss": 0.0128,
1930
+ "step": 127500
1931
+ },
1932
+ {
1933
+ "epoch": 16.0,
1934
+ "grad_norm": 4.560336890335748e-07,
1935
+ "learning_rate": 5.555902777777778e-06,
1936
+ "loss": 0.0095,
1937
+ "step": 128000
1938
+ },
1939
+ {
1940
+ "epoch": 16.0,
1941
+ "eval_loss": 0.39633870124816895,
1942
+ "eval_pearson": 0.9361489441284587,
1943
+ "eval_runtime": 52.1321,
1944
+ "eval_samples_per_second": 38.364,
1945
+ "eval_steps_per_second": 19.182,
1946
+ "step": 128000
1947
+ }
1948
+ ],
1949
+ "logging_steps": 500,
1950
+ "max_steps": 144000,
1951
+ "num_input_tokens_seen": 0,
1952
+ "num_train_epochs": 18,
1953
+ "save_steps": 500,
1954
+ "stateful_callbacks": {
1955
+ "TrainerControl": {
1956
+ "args": {
1957
+ "should_epoch_stop": false,
1958
+ "should_evaluate": false,
1959
+ "should_log": false,
1960
+ "should_save": true,
1961
+ "should_training_stop": false
1962
+ },
1963
+ "attributes": {}
1964
+ }
1965
+ },
1966
+ "total_flos": 1.1787147895953408e+17,
1967
+ "train_batch_size": 2,
1968
+ "trial_name": null,
1969
+ "trial_params": null
1970
+ }
checkpoints_ia3_llama_class/checkpoint-128000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54e6c46c9dda9757cc094892dfdf420dce55879ca8959ffad52b273b74ea2b4a
3
+ size 5368
checkpoints_ia3_llama_class/checkpoint-136000/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Llama-3.2-3B-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 0.15.2
checkpoints_ia3_llama_class/checkpoint-136000/adapter_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Llama-3.2-3B-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": 8,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.1,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": [
22
+ "classifier",
23
+ "score"
24
+ ],
25
+ "peft_type": "LORA",
26
+ "r": 8,
27
+ "rank_pattern": {},
28
+ "revision": null,
29
+ "target_modules": [
30
+ "v_proj",
31
+ "k_proj"
32
+ ],
33
+ "task_type": "SEQ_CLS",
34
+ "trainable_token_indices": null,
35
+ "use_dora": false,
36
+ "use_rslora": false
37
+ }
checkpoints_ia3_llama_class/checkpoint-136000/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bb5dbaf02e6043d093ff92a7be08c082da1c8bfba5e8f05e12aabda68f7e20b
3
+ size 7428608
checkpoints_ia3_llama_class/checkpoint-136000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:257f646d44a5777e384ed98dd7e9ce1d9555bdc942fa48db677b14de7ef86a5c
3
+ size 14922618
checkpoints_ia3_llama_class/checkpoint-136000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b24b6f69869891265446ef3e1fc30132f26bb58ea8f210f89370fae8b6754e6a
3
+ size 14244
checkpoints_ia3_llama_class/checkpoint-136000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3344b5b0debc3729e6a22ae37faf537723e332a9501c6ab92d33750b0352fcbd
3
+ size 1064
checkpoints_ia3_llama_class/checkpoint-136000/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
+ }
checkpoints_ia3_llama_class/checkpoint-136000/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb55d3601efe3b76b75c99d892f669a53d23df00ee8bac2e67a72152ae2083cd
3
+ size 17210017
checkpoints_ia3_llama_class/checkpoint-136000/tokenizer_config.json ADDED
@@ -0,0 +1,2065 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "128000": {
5
+ "content": "<|begin_of_text|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "128001": {
13
+ "content": "<|end_of_text|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "128002": {
21
+ "content": "<|reserved_special_token_0|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "128003": {
29
+ "content": "<|reserved_special_token_1|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "128004": {
37
+ "content": "<|finetune_right_pad_id|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "128005": {
45
+ "content": "<|reserved_special_token_2|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "128006": {
53
+ "content": "<|start_header_id|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "128007": {
61
+ "content": "<|end_header_id|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "128008": {
69
+ "content": "<|eom_id|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "128009": {
77
+ "content": "<|eot_id|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "128010": {
85
+ "content": "<|python_tag|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "128011": {
93
+ "content": "<|reserved_special_token_3|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "128012": {
101
+ "content": "<|reserved_special_token_4|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "128013": {
109
+ "content": "<|reserved_special_token_5|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "128014": {
117
+ "content": "<|reserved_special_token_6|>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "128015": {
125
+ "content": "<|reserved_special_token_7|>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "128016": {
133
+ "content": "<|reserved_special_token_8|>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "128017": {
141
+ "content": "<|reserved_special_token_9|>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "128018": {
149
+ "content": "<|reserved_special_token_10|>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "128019": {
157
+ "content": "<|reserved_special_token_11|>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "128020": {
165
+ "content": "<|reserved_special_token_12|>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "128021": {
173
+ "content": "<|reserved_special_token_13|>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "128022": {
181
+ "content": "<|reserved_special_token_14|>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "128023": {
189
+ "content": "<|reserved_special_token_15|>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "128024": {
197
+ "content": "<|reserved_special_token_16|>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "128025": {
205
+ "content": "<|reserved_special_token_17|>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "128026": {
213
+ "content": "<|reserved_special_token_18|>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "128027": {
221
+ "content": "<|reserved_special_token_19|>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "128028": {
229
+ "content": "<|reserved_special_token_20|>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "128029": {
237
+ "content": "<|reserved_special_token_21|>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "128030": {
245
+ "content": "<|reserved_special_token_22|>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "128031": {
253
+ "content": "<|reserved_special_token_23|>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "128032": {
261
+ "content": "<|reserved_special_token_24|>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "128033": {
269
+ "content": "<|reserved_special_token_25|>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "128034": {
277
+ "content": "<|reserved_special_token_26|>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "128035": {
285
+ "content": "<|reserved_special_token_27|>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "128036": {
293
+ "content": "<|reserved_special_token_28|>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "128037": {
301
+ "content": "<|reserved_special_token_29|>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "128038": {
309
+ "content": "<|reserved_special_token_30|>",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "128039": {
317
+ "content": "<|reserved_special_token_31|>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "128040": {
325
+ "content": "<|reserved_special_token_32|>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "128041": {
333
+ "content": "<|reserved_special_token_33|>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "128042": {
341
+ "content": "<|reserved_special_token_34|>",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "128043": {
349
+ "content": "<|reserved_special_token_35|>",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "128044": {
357
+ "content": "<|reserved_special_token_36|>",
358
+ "lstrip": false,
359
+ "normalized": false,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "128045": {
365
+ "content": "<|reserved_special_token_37|>",
366
+ "lstrip": false,
367
+ "normalized": false,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "128046": {
373
+ "content": "<|reserved_special_token_38|>",
374
+ "lstrip": false,
375
+ "normalized": false,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "128047": {
381
+ "content": "<|reserved_special_token_39|>",
382
+ "lstrip": false,
383
+ "normalized": false,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "128048": {
389
+ "content": "<|reserved_special_token_40|>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "128049": {
397
+ "content": "<|reserved_special_token_41|>",
398
+ "lstrip": false,
399
+ "normalized": false,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "128050": {
405
+ "content": "<|reserved_special_token_42|>",
406
+ "lstrip": false,
407
+ "normalized": false,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "128051": {
413
+ "content": "<|reserved_special_token_43|>",
414
+ "lstrip": false,
415
+ "normalized": false,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "128052": {
421
+ "content": "<|reserved_special_token_44|>",
422
+ "lstrip": false,
423
+ "normalized": false,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "128053": {
429
+ "content": "<|reserved_special_token_45|>",
430
+ "lstrip": false,
431
+ "normalized": false,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "128054": {
437
+ "content": "<|reserved_special_token_46|>",
438
+ "lstrip": false,
439
+ "normalized": false,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "128055": {
445
+ "content": "<|reserved_special_token_47|>",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "128056": {
453
+ "content": "<|reserved_special_token_48|>",
454
+ "lstrip": false,
455
+ "normalized": false,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "128057": {
461
+ "content": "<|reserved_special_token_49|>",
462
+ "lstrip": false,
463
+ "normalized": false,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "128058": {
469
+ "content": "<|reserved_special_token_50|>",
470
+ "lstrip": false,
471
+ "normalized": false,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "128059": {
477
+ "content": "<|reserved_special_token_51|>",
478
+ "lstrip": false,
479
+ "normalized": false,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "128060": {
485
+ "content": "<|reserved_special_token_52|>",
486
+ "lstrip": false,
487
+ "normalized": false,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "128061": {
493
+ "content": "<|reserved_special_token_53|>",
494
+ "lstrip": false,
495
+ "normalized": false,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "128062": {
501
+ "content": "<|reserved_special_token_54|>",
502
+ "lstrip": false,
503
+ "normalized": false,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "128063": {
509
+ "content": "<|reserved_special_token_55|>",
510
+ "lstrip": false,
511
+ "normalized": false,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "128064": {
517
+ "content": "<|reserved_special_token_56|>",
518
+ "lstrip": false,
519
+ "normalized": false,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "128065": {
525
+ "content": "<|reserved_special_token_57|>",
526
+ "lstrip": false,
527
+ "normalized": false,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "128066": {
533
+ "content": "<|reserved_special_token_58|>",
534
+ "lstrip": false,
535
+ "normalized": false,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "128067": {
541
+ "content": "<|reserved_special_token_59|>",
542
+ "lstrip": false,
543
+ "normalized": false,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "128068": {
549
+ "content": "<|reserved_special_token_60|>",
550
+ "lstrip": false,
551
+ "normalized": false,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "128069": {
557
+ "content": "<|reserved_special_token_61|>",
558
+ "lstrip": false,
559
+ "normalized": false,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "128070": {
565
+ "content": "<|reserved_special_token_62|>",
566
+ "lstrip": false,
567
+ "normalized": false,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "128071": {
573
+ "content": "<|reserved_special_token_63|>",
574
+ "lstrip": false,
575
+ "normalized": false,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "128072": {
581
+ "content": "<|reserved_special_token_64|>",
582
+ "lstrip": false,
583
+ "normalized": false,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "128073": {
589
+ "content": "<|reserved_special_token_65|>",
590
+ "lstrip": false,
591
+ "normalized": false,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "128074": {
597
+ "content": "<|reserved_special_token_66|>",
598
+ "lstrip": false,
599
+ "normalized": false,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "128075": {
605
+ "content": "<|reserved_special_token_67|>",
606
+ "lstrip": false,
607
+ "normalized": false,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "128076": {
613
+ "content": "<|reserved_special_token_68|>",
614
+ "lstrip": false,
615
+ "normalized": false,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "128077": {
621
+ "content": "<|reserved_special_token_69|>",
622
+ "lstrip": false,
623
+ "normalized": false,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "128078": {
629
+ "content": "<|reserved_special_token_70|>",
630
+ "lstrip": false,
631
+ "normalized": false,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "128079": {
637
+ "content": "<|reserved_special_token_71|>",
638
+ "lstrip": false,
639
+ "normalized": false,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "128080": {
645
+ "content": "<|reserved_special_token_72|>",
646
+ "lstrip": false,
647
+ "normalized": false,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "128081": {
653
+ "content": "<|reserved_special_token_73|>",
654
+ "lstrip": false,
655
+ "normalized": false,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "128082": {
661
+ "content": "<|reserved_special_token_74|>",
662
+ "lstrip": false,
663
+ "normalized": false,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "128083": {
669
+ "content": "<|reserved_special_token_75|>",
670
+ "lstrip": false,
671
+ "normalized": false,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "128084": {
677
+ "content": "<|reserved_special_token_76|>",
678
+ "lstrip": false,
679
+ "normalized": false,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "128085": {
685
+ "content": "<|reserved_special_token_77|>",
686
+ "lstrip": false,
687
+ "normalized": false,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "128086": {
693
+ "content": "<|reserved_special_token_78|>",
694
+ "lstrip": false,
695
+ "normalized": false,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "128087": {
701
+ "content": "<|reserved_special_token_79|>",
702
+ "lstrip": false,
703
+ "normalized": false,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "128088": {
709
+ "content": "<|reserved_special_token_80|>",
710
+ "lstrip": false,
711
+ "normalized": false,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "128089": {
717
+ "content": "<|reserved_special_token_81|>",
718
+ "lstrip": false,
719
+ "normalized": false,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "128090": {
725
+ "content": "<|reserved_special_token_82|>",
726
+ "lstrip": false,
727
+ "normalized": false,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "128091": {
733
+ "content": "<|reserved_special_token_83|>",
734
+ "lstrip": false,
735
+ "normalized": false,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "128092": {
741
+ "content": "<|reserved_special_token_84|>",
742
+ "lstrip": false,
743
+ "normalized": false,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "128093": {
749
+ "content": "<|reserved_special_token_85|>",
750
+ "lstrip": false,
751
+ "normalized": false,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "128094": {
757
+ "content": "<|reserved_special_token_86|>",
758
+ "lstrip": false,
759
+ "normalized": false,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "128095": {
765
+ "content": "<|reserved_special_token_87|>",
766
+ "lstrip": false,
767
+ "normalized": false,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "128096": {
773
+ "content": "<|reserved_special_token_88|>",
774
+ "lstrip": false,
775
+ "normalized": false,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "128097": {
781
+ "content": "<|reserved_special_token_89|>",
782
+ "lstrip": false,
783
+ "normalized": false,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "128098": {
789
+ "content": "<|reserved_special_token_90|>",
790
+ "lstrip": false,
791
+ "normalized": false,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "128099": {
797
+ "content": "<|reserved_special_token_91|>",
798
+ "lstrip": false,
799
+ "normalized": false,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "128100": {
805
+ "content": "<|reserved_special_token_92|>",
806
+ "lstrip": false,
807
+ "normalized": false,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "128101": {
813
+ "content": "<|reserved_special_token_93|>",
814
+ "lstrip": false,
815
+ "normalized": false,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "128102": {
821
+ "content": "<|reserved_special_token_94|>",
822
+ "lstrip": false,
823
+ "normalized": false,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": true
827
+ },
828
+ "128103": {
829
+ "content": "<|reserved_special_token_95|>",
830
+ "lstrip": false,
831
+ "normalized": false,
832
+ "rstrip": false,
833
+ "single_word": false,
834
+ "special": true
835
+ },
836
+ "128104": {
837
+ "content": "<|reserved_special_token_96|>",
838
+ "lstrip": false,
839
+ "normalized": false,
840
+ "rstrip": false,
841
+ "single_word": false,
842
+ "special": true
843
+ },
844
+ "128105": {
845
+ "content": "<|reserved_special_token_97|>",
846
+ "lstrip": false,
847
+ "normalized": false,
848
+ "rstrip": false,
849
+ "single_word": false,
850
+ "special": true
851
+ },
852
+ "128106": {
853
+ "content": "<|reserved_special_token_98|>",
854
+ "lstrip": false,
855
+ "normalized": false,
856
+ "rstrip": false,
857
+ "single_word": false,
858
+ "special": true
859
+ },
860
+ "128107": {
861
+ "content": "<|reserved_special_token_99|>",
862
+ "lstrip": false,
863
+ "normalized": false,
864
+ "rstrip": false,
865
+ "single_word": false,
866
+ "special": true
867
+ },
868
+ "128108": {
869
+ "content": "<|reserved_special_token_100|>",
870
+ "lstrip": false,
871
+ "normalized": false,
872
+ "rstrip": false,
873
+ "single_word": false,
874
+ "special": true
875
+ },
876
+ "128109": {
877
+ "content": "<|reserved_special_token_101|>",
878
+ "lstrip": false,
879
+ "normalized": false,
880
+ "rstrip": false,
881
+ "single_word": false,
882
+ "special": true
883
+ },
884
+ "128110": {
885
+ "content": "<|reserved_special_token_102|>",
886
+ "lstrip": false,
887
+ "normalized": false,
888
+ "rstrip": false,
889
+ "single_word": false,
890
+ "special": true
891
+ },
892
+ "128111": {
893
+ "content": "<|reserved_special_token_103|>",
894
+ "lstrip": false,
895
+ "normalized": false,
896
+ "rstrip": false,
897
+ "single_word": false,
898
+ "special": true
899
+ },
900
+ "128112": {
901
+ "content": "<|reserved_special_token_104|>",
902
+ "lstrip": false,
903
+ "normalized": false,
904
+ "rstrip": false,
905
+ "single_word": false,
906
+ "special": true
907
+ },
908
+ "128113": {
909
+ "content": "<|reserved_special_token_105|>",
910
+ "lstrip": false,
911
+ "normalized": false,
912
+ "rstrip": false,
913
+ "single_word": false,
914
+ "special": true
915
+ },
916
+ "128114": {
917
+ "content": "<|reserved_special_token_106|>",
918
+ "lstrip": false,
919
+ "normalized": false,
920
+ "rstrip": false,
921
+ "single_word": false,
922
+ "special": true
923
+ },
924
+ "128115": {
925
+ "content": "<|reserved_special_token_107|>",
926
+ "lstrip": false,
927
+ "normalized": false,
928
+ "rstrip": false,
929
+ "single_word": false,
930
+ "special": true
931
+ },
932
+ "128116": {
933
+ "content": "<|reserved_special_token_108|>",
934
+ "lstrip": false,
935
+ "normalized": false,
936
+ "rstrip": false,
937
+ "single_word": false,
938
+ "special": true
939
+ },
940
+ "128117": {
941
+ "content": "<|reserved_special_token_109|>",
942
+ "lstrip": false,
943
+ "normalized": false,
944
+ "rstrip": false,
945
+ "single_word": false,
946
+ "special": true
947
+ },
948
+ "128118": {
949
+ "content": "<|reserved_special_token_110|>",
950
+ "lstrip": false,
951
+ "normalized": false,
952
+ "rstrip": false,
953
+ "single_word": false,
954
+ "special": true
955
+ },
956
+ "128119": {
957
+ "content": "<|reserved_special_token_111|>",
958
+ "lstrip": false,
959
+ "normalized": false,
960
+ "rstrip": false,
961
+ "single_word": false,
962
+ "special": true
963
+ },
964
+ "128120": {
965
+ "content": "<|reserved_special_token_112|>",
966
+ "lstrip": false,
967
+ "normalized": false,
968
+ "rstrip": false,
969
+ "single_word": false,
970
+ "special": true
971
+ },
972
+ "128121": {
973
+ "content": "<|reserved_special_token_113|>",
974
+ "lstrip": false,
975
+ "normalized": false,
976
+ "rstrip": false,
977
+ "single_word": false,
978
+ "special": true
979
+ },
980
+ "128122": {
981
+ "content": "<|reserved_special_token_114|>",
982
+ "lstrip": false,
983
+ "normalized": false,
984
+ "rstrip": false,
985
+ "single_word": false,
986
+ "special": true
987
+ },
988
+ "128123": {
989
+ "content": "<|reserved_special_token_115|>",
990
+ "lstrip": false,
991
+ "normalized": false,
992
+ "rstrip": false,
993
+ "single_word": false,
994
+ "special": true
995
+ },
996
+ "128124": {
997
+ "content": "<|reserved_special_token_116|>",
998
+ "lstrip": false,
999
+ "normalized": false,
1000
+ "rstrip": false,
1001
+ "single_word": false,
1002
+ "special": true
1003
+ },
1004
+ "128125": {
1005
+ "content": "<|reserved_special_token_117|>",
1006
+ "lstrip": false,
1007
+ "normalized": false,
1008
+ "rstrip": false,
1009
+ "single_word": false,
1010
+ "special": true
1011
+ },
1012
+ "128126": {
1013
+ "content": "<|reserved_special_token_118|>",
1014
+ "lstrip": false,
1015
+ "normalized": false,
1016
+ "rstrip": false,
1017
+ "single_word": false,
1018
+ "special": true
1019
+ },
1020
+ "128127": {
1021
+ "content": "<|reserved_special_token_119|>",
1022
+ "lstrip": false,
1023
+ "normalized": false,
1024
+ "rstrip": false,
1025
+ "single_word": false,
1026
+ "special": true
1027
+ },
1028
+ "128128": {
1029
+ "content": "<|reserved_special_token_120|>",
1030
+ "lstrip": false,
1031
+ "normalized": false,
1032
+ "rstrip": false,
1033
+ "single_word": false,
1034
+ "special": true
1035
+ },
1036
+ "128129": {
1037
+ "content": "<|reserved_special_token_121|>",
1038
+ "lstrip": false,
1039
+ "normalized": false,
1040
+ "rstrip": false,
1041
+ "single_word": false,
1042
+ "special": true
1043
+ },
1044
+ "128130": {
1045
+ "content": "<|reserved_special_token_122|>",
1046
+ "lstrip": false,
1047
+ "normalized": false,
1048
+ "rstrip": false,
1049
+ "single_word": false,
1050
+ "special": true
1051
+ },
1052
+ "128131": {
1053
+ "content": "<|reserved_special_token_123|>",
1054
+ "lstrip": false,
1055
+ "normalized": false,
1056
+ "rstrip": false,
1057
+ "single_word": false,
1058
+ "special": true
1059
+ },
1060
+ "128132": {
1061
+ "content": "<|reserved_special_token_124|>",
1062
+ "lstrip": false,
1063
+ "normalized": false,
1064
+ "rstrip": false,
1065
+ "single_word": false,
1066
+ "special": true
1067
+ },
1068
+ "128133": {
1069
+ "content": "<|reserved_special_token_125|>",
1070
+ "lstrip": false,
1071
+ "normalized": false,
1072
+ "rstrip": false,
1073
+ "single_word": false,
1074
+ "special": true
1075
+ },
1076
+ "128134": {
1077
+ "content": "<|reserved_special_token_126|>",
1078
+ "lstrip": false,
1079
+ "normalized": false,
1080
+ "rstrip": false,
1081
+ "single_word": false,
1082
+ "special": true
1083
+ },
1084
+ "128135": {
1085
+ "content": "<|reserved_special_token_127|>",
1086
+ "lstrip": false,
1087
+ "normalized": false,
1088
+ "rstrip": false,
1089
+ "single_word": false,
1090
+ "special": true
1091
+ },
1092
+ "128136": {
1093
+ "content": "<|reserved_special_token_128|>",
1094
+ "lstrip": false,
1095
+ "normalized": false,
1096
+ "rstrip": false,
1097
+ "single_word": false,
1098
+ "special": true
1099
+ },
1100
+ "128137": {
1101
+ "content": "<|reserved_special_token_129|>",
1102
+ "lstrip": false,
1103
+ "normalized": false,
1104
+ "rstrip": false,
1105
+ "single_word": false,
1106
+ "special": true
1107
+ },
1108
+ "128138": {
1109
+ "content": "<|reserved_special_token_130|>",
1110
+ "lstrip": false,
1111
+ "normalized": false,
1112
+ "rstrip": false,
1113
+ "single_word": false,
1114
+ "special": true
1115
+ },
1116
+ "128139": {
1117
+ "content": "<|reserved_special_token_131|>",
1118
+ "lstrip": false,
1119
+ "normalized": false,
1120
+ "rstrip": false,
1121
+ "single_word": false,
1122
+ "special": true
1123
+ },
1124
+ "128140": {
1125
+ "content": "<|reserved_special_token_132|>",
1126
+ "lstrip": false,
1127
+ "normalized": false,
1128
+ "rstrip": false,
1129
+ "single_word": false,
1130
+ "special": true
1131
+ },
1132
+ "128141": {
1133
+ "content": "<|reserved_special_token_133|>",
1134
+ "lstrip": false,
1135
+ "normalized": false,
1136
+ "rstrip": false,
1137
+ "single_word": false,
1138
+ "special": true
1139
+ },
1140
+ "128142": {
1141
+ "content": "<|reserved_special_token_134|>",
1142
+ "lstrip": false,
1143
+ "normalized": false,
1144
+ "rstrip": false,
1145
+ "single_word": false,
1146
+ "special": true
1147
+ },
1148
+ "128143": {
1149
+ "content": "<|reserved_special_token_135|>",
1150
+ "lstrip": false,
1151
+ "normalized": false,
1152
+ "rstrip": false,
1153
+ "single_word": false,
1154
+ "special": true
1155
+ },
1156
+ "128144": {
1157
+ "content": "<|reserved_special_token_136|>",
1158
+ "lstrip": false,
1159
+ "normalized": false,
1160
+ "rstrip": false,
1161
+ "single_word": false,
1162
+ "special": true
1163
+ },
1164
+ "128145": {
1165
+ "content": "<|reserved_special_token_137|>",
1166
+ "lstrip": false,
1167
+ "normalized": false,
1168
+ "rstrip": false,
1169
+ "single_word": false,
1170
+ "special": true
1171
+ },
1172
+ "128146": {
1173
+ "content": "<|reserved_special_token_138|>",
1174
+ "lstrip": false,
1175
+ "normalized": false,
1176
+ "rstrip": false,
1177
+ "single_word": false,
1178
+ "special": true
1179
+ },
1180
+ "128147": {
1181
+ "content": "<|reserved_special_token_139|>",
1182
+ "lstrip": false,
1183
+ "normalized": false,
1184
+ "rstrip": false,
1185
+ "single_word": false,
1186
+ "special": true
1187
+ },
1188
+ "128148": {
1189
+ "content": "<|reserved_special_token_140|>",
1190
+ "lstrip": false,
1191
+ "normalized": false,
1192
+ "rstrip": false,
1193
+ "single_word": false,
1194
+ "special": true
1195
+ },
1196
+ "128149": {
1197
+ "content": "<|reserved_special_token_141|>",
1198
+ "lstrip": false,
1199
+ "normalized": false,
1200
+ "rstrip": false,
1201
+ "single_word": false,
1202
+ "special": true
1203
+ },
1204
+ "128150": {
1205
+ "content": "<|reserved_special_token_142|>",
1206
+ "lstrip": false,
1207
+ "normalized": false,
1208
+ "rstrip": false,
1209
+ "single_word": false,
1210
+ "special": true
1211
+ },
1212
+ "128151": {
1213
+ "content": "<|reserved_special_token_143|>",
1214
+ "lstrip": false,
1215
+ "normalized": false,
1216
+ "rstrip": false,
1217
+ "single_word": false,
1218
+ "special": true
1219
+ },
1220
+ "128152": {
1221
+ "content": "<|reserved_special_token_144|>",
1222
+ "lstrip": false,
1223
+ "normalized": false,
1224
+ "rstrip": false,
1225
+ "single_word": false,
1226
+ "special": true
1227
+ },
1228
+ "128153": {
1229
+ "content": "<|reserved_special_token_145|>",
1230
+ "lstrip": false,
1231
+ "normalized": false,
1232
+ "rstrip": false,
1233
+ "single_word": false,
1234
+ "special": true
1235
+ },
1236
+ "128154": {
1237
+ "content": "<|reserved_special_token_146|>",
1238
+ "lstrip": false,
1239
+ "normalized": false,
1240
+ "rstrip": false,
1241
+ "single_word": false,
1242
+ "special": true
1243
+ },
1244
+ "128155": {
1245
+ "content": "<|reserved_special_token_147|>",
1246
+ "lstrip": false,
1247
+ "normalized": false,
1248
+ "rstrip": false,
1249
+ "single_word": false,
1250
+ "special": true
1251
+ },
1252
+ "128156": {
1253
+ "content": "<|reserved_special_token_148|>",
1254
+ "lstrip": false,
1255
+ "normalized": false,
1256
+ "rstrip": false,
1257
+ "single_word": false,
1258
+ "special": true
1259
+ },
1260
+ "128157": {
1261
+ "content": "<|reserved_special_token_149|>",
1262
+ "lstrip": false,
1263
+ "normalized": false,
1264
+ "rstrip": false,
1265
+ "single_word": false,
1266
+ "special": true
1267
+ },
1268
+ "128158": {
1269
+ "content": "<|reserved_special_token_150|>",
1270
+ "lstrip": false,
1271
+ "normalized": false,
1272
+ "rstrip": false,
1273
+ "single_word": false,
1274
+ "special": true
1275
+ },
1276
+ "128159": {
1277
+ "content": "<|reserved_special_token_151|>",
1278
+ "lstrip": false,
1279
+ "normalized": false,
1280
+ "rstrip": false,
1281
+ "single_word": false,
1282
+ "special": true
1283
+ },
1284
+ "128160": {
1285
+ "content": "<|reserved_special_token_152|>",
1286
+ "lstrip": false,
1287
+ "normalized": false,
1288
+ "rstrip": false,
1289
+ "single_word": false,
1290
+ "special": true
1291
+ },
1292
+ "128161": {
1293
+ "content": "<|reserved_special_token_153|>",
1294
+ "lstrip": false,
1295
+ "normalized": false,
1296
+ "rstrip": false,
1297
+ "single_word": false,
1298
+ "special": true
1299
+ },
1300
+ "128162": {
1301
+ "content": "<|reserved_special_token_154|>",
1302
+ "lstrip": false,
1303
+ "normalized": false,
1304
+ "rstrip": false,
1305
+ "single_word": false,
1306
+ "special": true
1307
+ },
1308
+ "128163": {
1309
+ "content": "<|reserved_special_token_155|>",
1310
+ "lstrip": false,
1311
+ "normalized": false,
1312
+ "rstrip": false,
1313
+ "single_word": false,
1314
+ "special": true
1315
+ },
1316
+ "128164": {
1317
+ "content": "<|reserved_special_token_156|>",
1318
+ "lstrip": false,
1319
+ "normalized": false,
1320
+ "rstrip": false,
1321
+ "single_word": false,
1322
+ "special": true
1323
+ },
1324
+ "128165": {
1325
+ "content": "<|reserved_special_token_157|>",
1326
+ "lstrip": false,
1327
+ "normalized": false,
1328
+ "rstrip": false,
1329
+ "single_word": false,
1330
+ "special": true
1331
+ },
1332
+ "128166": {
1333
+ "content": "<|reserved_special_token_158|>",
1334
+ "lstrip": false,
1335
+ "normalized": false,
1336
+ "rstrip": false,
1337
+ "single_word": false,
1338
+ "special": true
1339
+ },
1340
+ "128167": {
1341
+ "content": "<|reserved_special_token_159|>",
1342
+ "lstrip": false,
1343
+ "normalized": false,
1344
+ "rstrip": false,
1345
+ "single_word": false,
1346
+ "special": true
1347
+ },
1348
+ "128168": {
1349
+ "content": "<|reserved_special_token_160|>",
1350
+ "lstrip": false,
1351
+ "normalized": false,
1352
+ "rstrip": false,
1353
+ "single_word": false,
1354
+ "special": true
1355
+ },
1356
+ "128169": {
1357
+ "content": "<|reserved_special_token_161|>",
1358
+ "lstrip": false,
1359
+ "normalized": false,
1360
+ "rstrip": false,
1361
+ "single_word": false,
1362
+ "special": true
1363
+ },
1364
+ "128170": {
1365
+ "content": "<|reserved_special_token_162|>",
1366
+ "lstrip": false,
1367
+ "normalized": false,
1368
+ "rstrip": false,
1369
+ "single_word": false,
1370
+ "special": true
1371
+ },
1372
+ "128171": {
1373
+ "content": "<|reserved_special_token_163|>",
1374
+ "lstrip": false,
1375
+ "normalized": false,
1376
+ "rstrip": false,
1377
+ "single_word": false,
1378
+ "special": true
1379
+ },
1380
+ "128172": {
1381
+ "content": "<|reserved_special_token_164|>",
1382
+ "lstrip": false,
1383
+ "normalized": false,
1384
+ "rstrip": false,
1385
+ "single_word": false,
1386
+ "special": true
1387
+ },
1388
+ "128173": {
1389
+ "content": "<|reserved_special_token_165|>",
1390
+ "lstrip": false,
1391
+ "normalized": false,
1392
+ "rstrip": false,
1393
+ "single_word": false,
1394
+ "special": true
1395
+ },
1396
+ "128174": {
1397
+ "content": "<|reserved_special_token_166|>",
1398
+ "lstrip": false,
1399
+ "normalized": false,
1400
+ "rstrip": false,
1401
+ "single_word": false,
1402
+ "special": true
1403
+ },
1404
+ "128175": {
1405
+ "content": "<|reserved_special_token_167|>",
1406
+ "lstrip": false,
1407
+ "normalized": false,
1408
+ "rstrip": false,
1409
+ "single_word": false,
1410
+ "special": true
1411
+ },
1412
+ "128176": {
1413
+ "content": "<|reserved_special_token_168|>",
1414
+ "lstrip": false,
1415
+ "normalized": false,
1416
+ "rstrip": false,
1417
+ "single_word": false,
1418
+ "special": true
1419
+ },
1420
+ "128177": {
1421
+ "content": "<|reserved_special_token_169|>",
1422
+ "lstrip": false,
1423
+ "normalized": false,
1424
+ "rstrip": false,
1425
+ "single_word": false,
1426
+ "special": true
1427
+ },
1428
+ "128178": {
1429
+ "content": "<|reserved_special_token_170|>",
1430
+ "lstrip": false,
1431
+ "normalized": false,
1432
+ "rstrip": false,
1433
+ "single_word": false,
1434
+ "special": true
1435
+ },
1436
+ "128179": {
1437
+ "content": "<|reserved_special_token_171|>",
1438
+ "lstrip": false,
1439
+ "normalized": false,
1440
+ "rstrip": false,
1441
+ "single_word": false,
1442
+ "special": true
1443
+ },
1444
+ "128180": {
1445
+ "content": "<|reserved_special_token_172|>",
1446
+ "lstrip": false,
1447
+ "normalized": false,
1448
+ "rstrip": false,
1449
+ "single_word": false,
1450
+ "special": true
1451
+ },
1452
+ "128181": {
1453
+ "content": "<|reserved_special_token_173|>",
1454
+ "lstrip": false,
1455
+ "normalized": false,
1456
+ "rstrip": false,
1457
+ "single_word": false,
1458
+ "special": true
1459
+ },
1460
+ "128182": {
1461
+ "content": "<|reserved_special_token_174|>",
1462
+ "lstrip": false,
1463
+ "normalized": false,
1464
+ "rstrip": false,
1465
+ "single_word": false,
1466
+ "special": true
1467
+ },
1468
+ "128183": {
1469
+ "content": "<|reserved_special_token_175|>",
1470
+ "lstrip": false,
1471
+ "normalized": false,
1472
+ "rstrip": false,
1473
+ "single_word": false,
1474
+ "special": true
1475
+ },
1476
+ "128184": {
1477
+ "content": "<|reserved_special_token_176|>",
1478
+ "lstrip": false,
1479
+ "normalized": false,
1480
+ "rstrip": false,
1481
+ "single_word": false,
1482
+ "special": true
1483
+ },
1484
+ "128185": {
1485
+ "content": "<|reserved_special_token_177|>",
1486
+ "lstrip": false,
1487
+ "normalized": false,
1488
+ "rstrip": false,
1489
+ "single_word": false,
1490
+ "special": true
1491
+ },
1492
+ "128186": {
1493
+ "content": "<|reserved_special_token_178|>",
1494
+ "lstrip": false,
1495
+ "normalized": false,
1496
+ "rstrip": false,
1497
+ "single_word": false,
1498
+ "special": true
1499
+ },
1500
+ "128187": {
1501
+ "content": "<|reserved_special_token_179|>",
1502
+ "lstrip": false,
1503
+ "normalized": false,
1504
+ "rstrip": false,
1505
+ "single_word": false,
1506
+ "special": true
1507
+ },
1508
+ "128188": {
1509
+ "content": "<|reserved_special_token_180|>",
1510
+ "lstrip": false,
1511
+ "normalized": false,
1512
+ "rstrip": false,
1513
+ "single_word": false,
1514
+ "special": true
1515
+ },
1516
+ "128189": {
1517
+ "content": "<|reserved_special_token_181|>",
1518
+ "lstrip": false,
1519
+ "normalized": false,
1520
+ "rstrip": false,
1521
+ "single_word": false,
1522
+ "special": true
1523
+ },
1524
+ "128190": {
1525
+ "content": "<|reserved_special_token_182|>",
1526
+ "lstrip": false,
1527
+ "normalized": false,
1528
+ "rstrip": false,
1529
+ "single_word": false,
1530
+ "special": true
1531
+ },
1532
+ "128191": {
1533
+ "content": "<|reserved_special_token_183|>",
1534
+ "lstrip": false,
1535
+ "normalized": false,
1536
+ "rstrip": false,
1537
+ "single_word": false,
1538
+ "special": true
1539
+ },
1540
+ "128192": {
1541
+ "content": "<|reserved_special_token_184|>",
1542
+ "lstrip": false,
1543
+ "normalized": false,
1544
+ "rstrip": false,
1545
+ "single_word": false,
1546
+ "special": true
1547
+ },
1548
+ "128193": {
1549
+ "content": "<|reserved_special_token_185|>",
1550
+ "lstrip": false,
1551
+ "normalized": false,
1552
+ "rstrip": false,
1553
+ "single_word": false,
1554
+ "special": true
1555
+ },
1556
+ "128194": {
1557
+ "content": "<|reserved_special_token_186|>",
1558
+ "lstrip": false,
1559
+ "normalized": false,
1560
+ "rstrip": false,
1561
+ "single_word": false,
1562
+ "special": true
1563
+ },
1564
+ "128195": {
1565
+ "content": "<|reserved_special_token_187|>",
1566
+ "lstrip": false,
1567
+ "normalized": false,
1568
+ "rstrip": false,
1569
+ "single_word": false,
1570
+ "special": true
1571
+ },
1572
+ "128196": {
1573
+ "content": "<|reserved_special_token_188|>",
1574
+ "lstrip": false,
1575
+ "normalized": false,
1576
+ "rstrip": false,
1577
+ "single_word": false,
1578
+ "special": true
1579
+ },
1580
+ "128197": {
1581
+ "content": "<|reserved_special_token_189|>",
1582
+ "lstrip": false,
1583
+ "normalized": false,
1584
+ "rstrip": false,
1585
+ "single_word": false,
1586
+ "special": true
1587
+ },
1588
+ "128198": {
1589
+ "content": "<|reserved_special_token_190|>",
1590
+ "lstrip": false,
1591
+ "normalized": false,
1592
+ "rstrip": false,
1593
+ "single_word": false,
1594
+ "special": true
1595
+ },
1596
+ "128199": {
1597
+ "content": "<|reserved_special_token_191|>",
1598
+ "lstrip": false,
1599
+ "normalized": false,
1600
+ "rstrip": false,
1601
+ "single_word": false,
1602
+ "special": true
1603
+ },
1604
+ "128200": {
1605
+ "content": "<|reserved_special_token_192|>",
1606
+ "lstrip": false,
1607
+ "normalized": false,
1608
+ "rstrip": false,
1609
+ "single_word": false,
1610
+ "special": true
1611
+ },
1612
+ "128201": {
1613
+ "content": "<|reserved_special_token_193|>",
1614
+ "lstrip": false,
1615
+ "normalized": false,
1616
+ "rstrip": false,
1617
+ "single_word": false,
1618
+ "special": true
1619
+ },
1620
+ "128202": {
1621
+ "content": "<|reserved_special_token_194|>",
1622
+ "lstrip": false,
1623
+ "normalized": false,
1624
+ "rstrip": false,
1625
+ "single_word": false,
1626
+ "special": true
1627
+ },
1628
+ "128203": {
1629
+ "content": "<|reserved_special_token_195|>",
1630
+ "lstrip": false,
1631
+ "normalized": false,
1632
+ "rstrip": false,
1633
+ "single_word": false,
1634
+ "special": true
1635
+ },
1636
+ "128204": {
1637
+ "content": "<|reserved_special_token_196|>",
1638
+ "lstrip": false,
1639
+ "normalized": false,
1640
+ "rstrip": false,
1641
+ "single_word": false,
1642
+ "special": true
1643
+ },
1644
+ "128205": {
1645
+ "content": "<|reserved_special_token_197|>",
1646
+ "lstrip": false,
1647
+ "normalized": false,
1648
+ "rstrip": false,
1649
+ "single_word": false,
1650
+ "special": true
1651
+ },
1652
+ "128206": {
1653
+ "content": "<|reserved_special_token_198|>",
1654
+ "lstrip": false,
1655
+ "normalized": false,
1656
+ "rstrip": false,
1657
+ "single_word": false,
1658
+ "special": true
1659
+ },
1660
+ "128207": {
1661
+ "content": "<|reserved_special_token_199|>",
1662
+ "lstrip": false,
1663
+ "normalized": false,
1664
+ "rstrip": false,
1665
+ "single_word": false,
1666
+ "special": true
1667
+ },
1668
+ "128208": {
1669
+ "content": "<|reserved_special_token_200|>",
1670
+ "lstrip": false,
1671
+ "normalized": false,
1672
+ "rstrip": false,
1673
+ "single_word": false,
1674
+ "special": true
1675
+ },
1676
+ "128209": {
1677
+ "content": "<|reserved_special_token_201|>",
1678
+ "lstrip": false,
1679
+ "normalized": false,
1680
+ "rstrip": false,
1681
+ "single_word": false,
1682
+ "special": true
1683
+ },
1684
+ "128210": {
1685
+ "content": "<|reserved_special_token_202|>",
1686
+ "lstrip": false,
1687
+ "normalized": false,
1688
+ "rstrip": false,
1689
+ "single_word": false,
1690
+ "special": true
1691
+ },
1692
+ "128211": {
1693
+ "content": "<|reserved_special_token_203|>",
1694
+ "lstrip": false,
1695
+ "normalized": false,
1696
+ "rstrip": false,
1697
+ "single_word": false,
1698
+ "special": true
1699
+ },
1700
+ "128212": {
1701
+ "content": "<|reserved_special_token_204|>",
1702
+ "lstrip": false,
1703
+ "normalized": false,
1704
+ "rstrip": false,
1705
+ "single_word": false,
1706
+ "special": true
1707
+ },
1708
+ "128213": {
1709
+ "content": "<|reserved_special_token_205|>",
1710
+ "lstrip": false,
1711
+ "normalized": false,
1712
+ "rstrip": false,
1713
+ "single_word": false,
1714
+ "special": true
1715
+ },
1716
+ "128214": {
1717
+ "content": "<|reserved_special_token_206|>",
1718
+ "lstrip": false,
1719
+ "normalized": false,
1720
+ "rstrip": false,
1721
+ "single_word": false,
1722
+ "special": true
1723
+ },
1724
+ "128215": {
1725
+ "content": "<|reserved_special_token_207|>",
1726
+ "lstrip": false,
1727
+ "normalized": false,
1728
+ "rstrip": false,
1729
+ "single_word": false,
1730
+ "special": true
1731
+ },
1732
+ "128216": {
1733
+ "content": "<|reserved_special_token_208|>",
1734
+ "lstrip": false,
1735
+ "normalized": false,
1736
+ "rstrip": false,
1737
+ "single_word": false,
1738
+ "special": true
1739
+ },
1740
+ "128217": {
1741
+ "content": "<|reserved_special_token_209|>",
1742
+ "lstrip": false,
1743
+ "normalized": false,
1744
+ "rstrip": false,
1745
+ "single_word": false,
1746
+ "special": true
1747
+ },
1748
+ "128218": {
1749
+ "content": "<|reserved_special_token_210|>",
1750
+ "lstrip": false,
1751
+ "normalized": false,
1752
+ "rstrip": false,
1753
+ "single_word": false,
1754
+ "special": true
1755
+ },
1756
+ "128219": {
1757
+ "content": "<|reserved_special_token_211|>",
1758
+ "lstrip": false,
1759
+ "normalized": false,
1760
+ "rstrip": false,
1761
+ "single_word": false,
1762
+ "special": true
1763
+ },
1764
+ "128220": {
1765
+ "content": "<|reserved_special_token_212|>",
1766
+ "lstrip": false,
1767
+ "normalized": false,
1768
+ "rstrip": false,
1769
+ "single_word": false,
1770
+ "special": true
1771
+ },
1772
+ "128221": {
1773
+ "content": "<|reserved_special_token_213|>",
1774
+ "lstrip": false,
1775
+ "normalized": false,
1776
+ "rstrip": false,
1777
+ "single_word": false,
1778
+ "special": true
1779
+ },
1780
+ "128222": {
1781
+ "content": "<|reserved_special_token_214|>",
1782
+ "lstrip": false,
1783
+ "normalized": false,
1784
+ "rstrip": false,
1785
+ "single_word": false,
1786
+ "special": true
1787
+ },
1788
+ "128223": {
1789
+ "content": "<|reserved_special_token_215|>",
1790
+ "lstrip": false,
1791
+ "normalized": false,
1792
+ "rstrip": false,
1793
+ "single_word": false,
1794
+ "special": true
1795
+ },
1796
+ "128224": {
1797
+ "content": "<|reserved_special_token_216|>",
1798
+ "lstrip": false,
1799
+ "normalized": false,
1800
+ "rstrip": false,
1801
+ "single_word": false,
1802
+ "special": true
1803
+ },
1804
+ "128225": {
1805
+ "content": "<|reserved_special_token_217|>",
1806
+ "lstrip": false,
1807
+ "normalized": false,
1808
+ "rstrip": false,
1809
+ "single_word": false,
1810
+ "special": true
1811
+ },
1812
+ "128226": {
1813
+ "content": "<|reserved_special_token_218|>",
1814
+ "lstrip": false,
1815
+ "normalized": false,
1816
+ "rstrip": false,
1817
+ "single_word": false,
1818
+ "special": true
1819
+ },
1820
+ "128227": {
1821
+ "content": "<|reserved_special_token_219|>",
1822
+ "lstrip": false,
1823
+ "normalized": false,
1824
+ "rstrip": false,
1825
+ "single_word": false,
1826
+ "special": true
1827
+ },
1828
+ "128228": {
1829
+ "content": "<|reserved_special_token_220|>",
1830
+ "lstrip": false,
1831
+ "normalized": false,
1832
+ "rstrip": false,
1833
+ "single_word": false,
1834
+ "special": true
1835
+ },
1836
+ "128229": {
1837
+ "content": "<|reserved_special_token_221|>",
1838
+ "lstrip": false,
1839
+ "normalized": false,
1840
+ "rstrip": false,
1841
+ "single_word": false,
1842
+ "special": true
1843
+ },
1844
+ "128230": {
1845
+ "content": "<|reserved_special_token_222|>",
1846
+ "lstrip": false,
1847
+ "normalized": false,
1848
+ "rstrip": false,
1849
+ "single_word": false,
1850
+ "special": true
1851
+ },
1852
+ "128231": {
1853
+ "content": "<|reserved_special_token_223|>",
1854
+ "lstrip": false,
1855
+ "normalized": false,
1856
+ "rstrip": false,
1857
+ "single_word": false,
1858
+ "special": true
1859
+ },
1860
+ "128232": {
1861
+ "content": "<|reserved_special_token_224|>",
1862
+ "lstrip": false,
1863
+ "normalized": false,
1864
+ "rstrip": false,
1865
+ "single_word": false,
1866
+ "special": true
1867
+ },
1868
+ "128233": {
1869
+ "content": "<|reserved_special_token_225|>",
1870
+ "lstrip": false,
1871
+ "normalized": false,
1872
+ "rstrip": false,
1873
+ "single_word": false,
1874
+ "special": true
1875
+ },
1876
+ "128234": {
1877
+ "content": "<|reserved_special_token_226|>",
1878
+ "lstrip": false,
1879
+ "normalized": false,
1880
+ "rstrip": false,
1881
+ "single_word": false,
1882
+ "special": true
1883
+ },
1884
+ "128235": {
1885
+ "content": "<|reserved_special_token_227|>",
1886
+ "lstrip": false,
1887
+ "normalized": false,
1888
+ "rstrip": false,
1889
+ "single_word": false,
1890
+ "special": true
1891
+ },
1892
+ "128236": {
1893
+ "content": "<|reserved_special_token_228|>",
1894
+ "lstrip": false,
1895
+ "normalized": false,
1896
+ "rstrip": false,
1897
+ "single_word": false,
1898
+ "special": true
1899
+ },
1900
+ "128237": {
1901
+ "content": "<|reserved_special_token_229|>",
1902
+ "lstrip": false,
1903
+ "normalized": false,
1904
+ "rstrip": false,
1905
+ "single_word": false,
1906
+ "special": true
1907
+ },
1908
+ "128238": {
1909
+ "content": "<|reserved_special_token_230|>",
1910
+ "lstrip": false,
1911
+ "normalized": false,
1912
+ "rstrip": false,
1913
+ "single_word": false,
1914
+ "special": true
1915
+ },
1916
+ "128239": {
1917
+ "content": "<|reserved_special_token_231|>",
1918
+ "lstrip": false,
1919
+ "normalized": false,
1920
+ "rstrip": false,
1921
+ "single_word": false,
1922
+ "special": true
1923
+ },
1924
+ "128240": {
1925
+ "content": "<|reserved_special_token_232|>",
1926
+ "lstrip": false,
1927
+ "normalized": false,
1928
+ "rstrip": false,
1929
+ "single_word": false,
1930
+ "special": true
1931
+ },
1932
+ "128241": {
1933
+ "content": "<|reserved_special_token_233|>",
1934
+ "lstrip": false,
1935
+ "normalized": false,
1936
+ "rstrip": false,
1937
+ "single_word": false,
1938
+ "special": true
1939
+ },
1940
+ "128242": {
1941
+ "content": "<|reserved_special_token_234|>",
1942
+ "lstrip": false,
1943
+ "normalized": false,
1944
+ "rstrip": false,
1945
+ "single_word": false,
1946
+ "special": true
1947
+ },
1948
+ "128243": {
1949
+ "content": "<|reserved_special_token_235|>",
1950
+ "lstrip": false,
1951
+ "normalized": false,
1952
+ "rstrip": false,
1953
+ "single_word": false,
1954
+ "special": true
1955
+ },
1956
+ "128244": {
1957
+ "content": "<|reserved_special_token_236|>",
1958
+ "lstrip": false,
1959
+ "normalized": false,
1960
+ "rstrip": false,
1961
+ "single_word": false,
1962
+ "special": true
1963
+ },
1964
+ "128245": {
1965
+ "content": "<|reserved_special_token_237|>",
1966
+ "lstrip": false,
1967
+ "normalized": false,
1968
+ "rstrip": false,
1969
+ "single_word": false,
1970
+ "special": true
1971
+ },
1972
+ "128246": {
1973
+ "content": "<|reserved_special_token_238|>",
1974
+ "lstrip": false,
1975
+ "normalized": false,
1976
+ "rstrip": false,
1977
+ "single_word": false,
1978
+ "special": true
1979
+ },
1980
+ "128247": {
1981
+ "content": "<|reserved_special_token_239|>",
1982
+ "lstrip": false,
1983
+ "normalized": false,
1984
+ "rstrip": false,
1985
+ "single_word": false,
1986
+ "special": true
1987
+ },
1988
+ "128248": {
1989
+ "content": "<|reserved_special_token_240|>",
1990
+ "lstrip": false,
1991
+ "normalized": false,
1992
+ "rstrip": false,
1993
+ "single_word": false,
1994
+ "special": true
1995
+ },
1996
+ "128249": {
1997
+ "content": "<|reserved_special_token_241|>",
1998
+ "lstrip": false,
1999
+ "normalized": false,
2000
+ "rstrip": false,
2001
+ "single_word": false,
2002
+ "special": true
2003
+ },
2004
+ "128250": {
2005
+ "content": "<|reserved_special_token_242|>",
2006
+ "lstrip": false,
2007
+ "normalized": false,
2008
+ "rstrip": false,
2009
+ "single_word": false,
2010
+ "special": true
2011
+ },
2012
+ "128251": {
2013
+ "content": "<|reserved_special_token_243|>",
2014
+ "lstrip": false,
2015
+ "normalized": false,
2016
+ "rstrip": false,
2017
+ "single_word": false,
2018
+ "special": true
2019
+ },
2020
+ "128252": {
2021
+ "content": "<|reserved_special_token_244|>",
2022
+ "lstrip": false,
2023
+ "normalized": false,
2024
+ "rstrip": false,
2025
+ "single_word": false,
2026
+ "special": true
2027
+ },
2028
+ "128253": {
2029
+ "content": "<|reserved_special_token_245|>",
2030
+ "lstrip": false,
2031
+ "normalized": false,
2032
+ "rstrip": false,
2033
+ "single_word": false,
2034
+ "special": true
2035
+ },
2036
+ "128254": {
2037
+ "content": "<|reserved_special_token_246|>",
2038
+ "lstrip": false,
2039
+ "normalized": false,
2040
+ "rstrip": false,
2041
+ "single_word": false,
2042
+ "special": true
2043
+ },
2044
+ "128255": {
2045
+ "content": "<|reserved_special_token_247|>",
2046
+ "lstrip": false,
2047
+ "normalized": false,
2048
+ "rstrip": false,
2049
+ "single_word": false,
2050
+ "special": true
2051
+ }
2052
+ },
2053
+ "bos_token": "<|begin_of_text|>",
2054
+ "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 {%- if strftime_now is defined %}\n {%- set date_string = strftime_now(\"%d %b %Y\") %}\n {%- else %}\n {%- set date_string = \"26 Jul 2024\" %}\n {%- endif %}\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 #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if tools is not none %}\n {{- \"Environment: ipython\\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 {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {{- \"<|eot_id|>\" }}\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",
2055
+ "clean_up_tokenization_spaces": true,
2056
+ "eos_token": "<|eot_id|>",
2057
+ "extra_special_tokens": {},
2058
+ "model_input_names": [
2059
+ "input_ids",
2060
+ "attention_mask"
2061
+ ],
2062
+ "model_max_length": 131072,
2063
+ "pad_token": "<|eot_id|>",
2064
+ "tokenizer_class": "PreTrainedTokenizer"
2065
+ }
checkpoints_ia3_llama_class/checkpoint-136000/trainer_state.json ADDED
@@ -0,0 +1,2091 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 88000,
3
+ "best_metric": 0.936161178019818,
4
+ "best_model_checkpoint": "/home/sujeet-pg/wav2vec2/peft/checkpoints_ia3_llama_class/checkpoint-88000",
5
+ "epoch": 17.0,
6
+ "eval_steps": 500,
7
+ "global_step": 136000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0625,
14
+ "grad_norm": 29.181745529174805,
15
+ "learning_rate": 4.982673611111111e-05,
16
+ "loss": 1.9515,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.125,
21
+ "grad_norm": 84.54170989990234,
22
+ "learning_rate": 4.9653125e-05,
23
+ "loss": 1.4973,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 0.1875,
28
+ "grad_norm": 118.13458251953125,
29
+ "learning_rate": 4.947951388888889e-05,
30
+ "loss": 1.3271,
31
+ "step": 1500
32
+ },
33
+ {
34
+ "epoch": 0.25,
35
+ "grad_norm": 0.062166254967451096,
36
+ "learning_rate": 4.930590277777778e-05,
37
+ "loss": 0.9626,
38
+ "step": 2000
39
+ },
40
+ {
41
+ "epoch": 0.3125,
42
+ "grad_norm": 165.25686645507812,
43
+ "learning_rate": 4.9132291666666665e-05,
44
+ "loss": 0.7346,
45
+ "step": 2500
46
+ },
47
+ {
48
+ "epoch": 0.375,
49
+ "grad_norm": 0.6356489658355713,
50
+ "learning_rate": 4.8958680555555555e-05,
51
+ "loss": 0.8147,
52
+ "step": 3000
53
+ },
54
+ {
55
+ "epoch": 0.4375,
56
+ "grad_norm": 0.012186303734779358,
57
+ "learning_rate": 4.8785069444444445e-05,
58
+ "loss": 0.5557,
59
+ "step": 3500
60
+ },
61
+ {
62
+ "epoch": 0.5,
63
+ "grad_norm": 114.87812805175781,
64
+ "learning_rate": 4.8611458333333335e-05,
65
+ "loss": 0.546,
66
+ "step": 4000
67
+ },
68
+ {
69
+ "epoch": 0.5625,
70
+ "grad_norm": 0.3081382215023041,
71
+ "learning_rate": 4.8437847222222225e-05,
72
+ "loss": 0.5198,
73
+ "step": 4500
74
+ },
75
+ {
76
+ "epoch": 0.625,
77
+ "grad_norm": 0.0013407367514446378,
78
+ "learning_rate": 4.826423611111111e-05,
79
+ "loss": 0.4668,
80
+ "step": 5000
81
+ },
82
+ {
83
+ "epoch": 0.6875,
84
+ "grad_norm": 0.032304372638463974,
85
+ "learning_rate": 4.8090625e-05,
86
+ "loss": 0.4066,
87
+ "step": 5500
88
+ },
89
+ {
90
+ "epoch": 0.75,
91
+ "grad_norm": 0.350352019071579,
92
+ "learning_rate": 4.791701388888889e-05,
93
+ "loss": 0.494,
94
+ "step": 6000
95
+ },
96
+ {
97
+ "epoch": 0.8125,
98
+ "grad_norm": 0.031369373202323914,
99
+ "learning_rate": 4.774340277777778e-05,
100
+ "loss": 0.4372,
101
+ "step": 6500
102
+ },
103
+ {
104
+ "epoch": 0.875,
105
+ "grad_norm": 87.0584716796875,
106
+ "learning_rate": 4.756979166666667e-05,
107
+ "loss": 0.546,
108
+ "step": 7000
109
+ },
110
+ {
111
+ "epoch": 0.9375,
112
+ "grad_norm": 42.25841522216797,
113
+ "learning_rate": 4.739618055555556e-05,
114
+ "loss": 0.4929,
115
+ "step": 7500
116
+ },
117
+ {
118
+ "epoch": 1.0,
119
+ "grad_norm": 0.017110565677285194,
120
+ "learning_rate": 4.722256944444445e-05,
121
+ "loss": 0.4128,
122
+ "step": 8000
123
+ },
124
+ {
125
+ "epoch": 1.0,
126
+ "eval_loss": 0.34961560368537903,
127
+ "eval_pearson": 0.9195974916185884,
128
+ "eval_runtime": 52.203,
129
+ "eval_samples_per_second": 38.312,
130
+ "eval_steps_per_second": 19.156,
131
+ "step": 8000
132
+ },
133
+ {
134
+ "epoch": 1.0625,
135
+ "grad_norm": 39.48343276977539,
136
+ "learning_rate": 4.704895833333334e-05,
137
+ "loss": 0.1769,
138
+ "step": 8500
139
+ },
140
+ {
141
+ "epoch": 1.125,
142
+ "grad_norm": 0.0003292807668913156,
143
+ "learning_rate": 4.687534722222223e-05,
144
+ "loss": 0.3138,
145
+ "step": 9000
146
+ },
147
+ {
148
+ "epoch": 1.1875,
149
+ "grad_norm": 0.0025669685564935207,
150
+ "learning_rate": 4.670173611111111e-05,
151
+ "loss": 0.3529,
152
+ "step": 9500
153
+ },
154
+ {
155
+ "epoch": 1.25,
156
+ "grad_norm": 0.0019228530582040548,
157
+ "learning_rate": 4.6528125e-05,
158
+ "loss": 0.3181,
159
+ "step": 10000
160
+ },
161
+ {
162
+ "epoch": 1.3125,
163
+ "grad_norm": 0.09842195361852646,
164
+ "learning_rate": 4.635451388888889e-05,
165
+ "loss": 0.3358,
166
+ "step": 10500
167
+ },
168
+ {
169
+ "epoch": 1.375,
170
+ "grad_norm": 0.0006872316589578986,
171
+ "learning_rate": 4.618090277777778e-05,
172
+ "loss": 0.3395,
173
+ "step": 11000
174
+ },
175
+ {
176
+ "epoch": 1.4375,
177
+ "grad_norm": 0.008952559903264046,
178
+ "learning_rate": 4.600729166666667e-05,
179
+ "loss": 0.3287,
180
+ "step": 11500
181
+ },
182
+ {
183
+ "epoch": 1.5,
184
+ "grad_norm": 0.0010550743900239468,
185
+ "learning_rate": 4.583368055555556e-05,
186
+ "loss": 0.3742,
187
+ "step": 12000
188
+ },
189
+ {
190
+ "epoch": 1.5625,
191
+ "grad_norm": 0.0011425487464293838,
192
+ "learning_rate": 4.566006944444445e-05,
193
+ "loss": 0.2979,
194
+ "step": 12500
195
+ },
196
+ {
197
+ "epoch": 1.625,
198
+ "grad_norm": 14.729352951049805,
199
+ "learning_rate": 4.5486458333333334e-05,
200
+ "loss": 0.2669,
201
+ "step": 13000
202
+ },
203
+ {
204
+ "epoch": 1.6875,
205
+ "grad_norm": 1.1553162039490417e-05,
206
+ "learning_rate": 4.5312847222222224e-05,
207
+ "loss": 0.3885,
208
+ "step": 13500
209
+ },
210
+ {
211
+ "epoch": 1.75,
212
+ "grad_norm": 0.051722027361392975,
213
+ "learning_rate": 4.5139236111111114e-05,
214
+ "loss": 0.3096,
215
+ "step": 14000
216
+ },
217
+ {
218
+ "epoch": 1.8125,
219
+ "grad_norm": 0.12957464158535004,
220
+ "learning_rate": 4.4965625e-05,
221
+ "loss": 0.3479,
222
+ "step": 14500
223
+ },
224
+ {
225
+ "epoch": 1.875,
226
+ "grad_norm": 0.012610511854290962,
227
+ "learning_rate": 4.479201388888889e-05,
228
+ "loss": 0.432,
229
+ "step": 15000
230
+ },
231
+ {
232
+ "epoch": 1.9375,
233
+ "grad_norm": 0.022952524945139885,
234
+ "learning_rate": 4.461840277777778e-05,
235
+ "loss": 0.2932,
236
+ "step": 15500
237
+ },
238
+ {
239
+ "epoch": 2.0,
240
+ "grad_norm": 3.255659612477757e-05,
241
+ "learning_rate": 4.444479166666667e-05,
242
+ "loss": 0.2544,
243
+ "step": 16000
244
+ },
245
+ {
246
+ "epoch": 2.0,
247
+ "eval_loss": 0.3652373254299164,
248
+ "eval_pearson": 0.9308122796123071,
249
+ "eval_runtime": 52.221,
250
+ "eval_samples_per_second": 38.299,
251
+ "eval_steps_per_second": 19.149,
252
+ "step": 16000
253
+ },
254
+ {
255
+ "epoch": 2.0625,
256
+ "grad_norm": 349.7726135253906,
257
+ "learning_rate": 4.427118055555556e-05,
258
+ "loss": 0.3006,
259
+ "step": 16500
260
+ },
261
+ {
262
+ "epoch": 2.125,
263
+ "grad_norm": 0.05852258577942848,
264
+ "learning_rate": 4.409756944444445e-05,
265
+ "loss": 0.2222,
266
+ "step": 17000
267
+ },
268
+ {
269
+ "epoch": 2.1875,
270
+ "grad_norm": 8.100055129034445e-05,
271
+ "learning_rate": 4.3923958333333337e-05,
272
+ "loss": 0.2253,
273
+ "step": 17500
274
+ },
275
+ {
276
+ "epoch": 2.25,
277
+ "grad_norm": 0.015503599308431149,
278
+ "learning_rate": 4.3750347222222226e-05,
279
+ "loss": 0.301,
280
+ "step": 18000
281
+ },
282
+ {
283
+ "epoch": 2.3125,
284
+ "grad_norm": 0.0007520843064412475,
285
+ "learning_rate": 4.357673611111111e-05,
286
+ "loss": 0.1979,
287
+ "step": 18500
288
+ },
289
+ {
290
+ "epoch": 2.375,
291
+ "grad_norm": 0.0003110193647444248,
292
+ "learning_rate": 4.3403125e-05,
293
+ "loss": 0.2496,
294
+ "step": 19000
295
+ },
296
+ {
297
+ "epoch": 2.4375,
298
+ "grad_norm": 5.800446033477783,
299
+ "learning_rate": 4.322951388888889e-05,
300
+ "loss": 0.3028,
301
+ "step": 19500
302
+ },
303
+ {
304
+ "epoch": 2.5,
305
+ "grad_norm": 2.4347489215870155e-06,
306
+ "learning_rate": 4.305590277777778e-05,
307
+ "loss": 0.2218,
308
+ "step": 20000
309
+ },
310
+ {
311
+ "epoch": 2.5625,
312
+ "grad_norm": 0.972939133644104,
313
+ "learning_rate": 4.288229166666667e-05,
314
+ "loss": 0.2485,
315
+ "step": 20500
316
+ },
317
+ {
318
+ "epoch": 2.625,
319
+ "grad_norm": 1.2701035737991333,
320
+ "learning_rate": 4.270868055555556e-05,
321
+ "loss": 0.179,
322
+ "step": 21000
323
+ },
324
+ {
325
+ "epoch": 2.6875,
326
+ "grad_norm": 0.0001465667737647891,
327
+ "learning_rate": 4.253506944444445e-05,
328
+ "loss": 0.337,
329
+ "step": 21500
330
+ },
331
+ {
332
+ "epoch": 2.75,
333
+ "grad_norm": 188.92559814453125,
334
+ "learning_rate": 4.236145833333334e-05,
335
+ "loss": 0.2353,
336
+ "step": 22000
337
+ },
338
+ {
339
+ "epoch": 2.8125,
340
+ "grad_norm": 0.0020125608425587416,
341
+ "learning_rate": 4.218784722222223e-05,
342
+ "loss": 0.2412,
343
+ "step": 22500
344
+ },
345
+ {
346
+ "epoch": 2.875,
347
+ "grad_norm": 0.030752288177609444,
348
+ "learning_rate": 4.201423611111111e-05,
349
+ "loss": 0.2645,
350
+ "step": 23000
351
+ },
352
+ {
353
+ "epoch": 2.9375,
354
+ "grad_norm": 76.4650650024414,
355
+ "learning_rate": 4.1840625e-05,
356
+ "loss": 0.2856,
357
+ "step": 23500
358
+ },
359
+ {
360
+ "epoch": 3.0,
361
+ "grad_norm": 0.0004072492301929742,
362
+ "learning_rate": 4.166701388888889e-05,
363
+ "loss": 0.2395,
364
+ "step": 24000
365
+ },
366
+ {
367
+ "epoch": 3.0,
368
+ "eval_loss": 0.28703999519348145,
369
+ "eval_pearson": 0.9358259106635223,
370
+ "eval_runtime": 52.1011,
371
+ "eval_samples_per_second": 38.387,
372
+ "eval_steps_per_second": 19.193,
373
+ "step": 24000
374
+ },
375
+ {
376
+ "epoch": 3.0625,
377
+ "grad_norm": 0.007601168937981129,
378
+ "learning_rate": 4.149340277777778e-05,
379
+ "loss": 0.1748,
380
+ "step": 24500
381
+ },
382
+ {
383
+ "epoch": 3.125,
384
+ "grad_norm": 0.026926109567284584,
385
+ "learning_rate": 4.1319791666666665e-05,
386
+ "loss": 0.1542,
387
+ "step": 25000
388
+ },
389
+ {
390
+ "epoch": 3.1875,
391
+ "grad_norm": 1.8115358352661133,
392
+ "learning_rate": 4.1146180555555555e-05,
393
+ "loss": 0.2275,
394
+ "step": 25500
395
+ },
396
+ {
397
+ "epoch": 3.25,
398
+ "grad_norm": 0.06953763216733932,
399
+ "learning_rate": 4.0972569444444445e-05,
400
+ "loss": 0.1706,
401
+ "step": 26000
402
+ },
403
+ {
404
+ "epoch": 3.3125,
405
+ "grad_norm": 0.020493032410740852,
406
+ "learning_rate": 4.0798958333333335e-05,
407
+ "loss": 0.1474,
408
+ "step": 26500
409
+ },
410
+ {
411
+ "epoch": 3.375,
412
+ "grad_norm": 0.005125588737428188,
413
+ "learning_rate": 4.0625347222222225e-05,
414
+ "loss": 0.1723,
415
+ "step": 27000
416
+ },
417
+ {
418
+ "epoch": 3.4375,
419
+ "grad_norm": 5.002508163452148,
420
+ "learning_rate": 4.045173611111111e-05,
421
+ "loss": 0.196,
422
+ "step": 27500
423
+ },
424
+ {
425
+ "epoch": 3.5,
426
+ "grad_norm": 0.000834703678265214,
427
+ "learning_rate": 4.0278125e-05,
428
+ "loss": 0.1449,
429
+ "step": 28000
430
+ },
431
+ {
432
+ "epoch": 3.5625,
433
+ "grad_norm": 0.01109158806502819,
434
+ "learning_rate": 4.010451388888889e-05,
435
+ "loss": 0.2287,
436
+ "step": 28500
437
+ },
438
+ {
439
+ "epoch": 3.625,
440
+ "grad_norm": 9.071109161595814e-06,
441
+ "learning_rate": 3.993090277777778e-05,
442
+ "loss": 0.1955,
443
+ "step": 29000
444
+ },
445
+ {
446
+ "epoch": 3.6875,
447
+ "grad_norm": 0.0006111862603574991,
448
+ "learning_rate": 3.975729166666667e-05,
449
+ "loss": 0.2147,
450
+ "step": 29500
451
+ },
452
+ {
453
+ "epoch": 3.75,
454
+ "grad_norm": 6.614517928937858e-07,
455
+ "learning_rate": 3.958368055555556e-05,
456
+ "loss": 0.2289,
457
+ "step": 30000
458
+ },
459
+ {
460
+ "epoch": 3.8125,
461
+ "grad_norm": 5.0481699872761965e-05,
462
+ "learning_rate": 3.941006944444445e-05,
463
+ "loss": 0.1941,
464
+ "step": 30500
465
+ },
466
+ {
467
+ "epoch": 3.875,
468
+ "grad_norm": 2.837545871734619,
469
+ "learning_rate": 3.923645833333334e-05,
470
+ "loss": 0.1753,
471
+ "step": 31000
472
+ },
473
+ {
474
+ "epoch": 3.9375,
475
+ "grad_norm": 0.00021911883959546685,
476
+ "learning_rate": 3.906284722222223e-05,
477
+ "loss": 0.1967,
478
+ "step": 31500
479
+ },
480
+ {
481
+ "epoch": 4.0,
482
+ "grad_norm": 0.008439241908490658,
483
+ "learning_rate": 3.888923611111111e-05,
484
+ "loss": 0.2341,
485
+ "step": 32000
486
+ },
487
+ {
488
+ "epoch": 4.0,
489
+ "eval_loss": 0.28366541862487793,
490
+ "eval_pearson": 0.9336592859812687,
491
+ "eval_runtime": 52.2768,
492
+ "eval_samples_per_second": 38.258,
493
+ "eval_steps_per_second": 19.129,
494
+ "step": 32000
495
+ },
496
+ {
497
+ "epoch": 4.0625,
498
+ "grad_norm": 3.5697648525238037,
499
+ "learning_rate": 3.8715625e-05,
500
+ "loss": 0.0898,
501
+ "step": 32500
502
+ },
503
+ {
504
+ "epoch": 4.125,
505
+ "grad_norm": 0.005574432201683521,
506
+ "learning_rate": 3.854201388888889e-05,
507
+ "loss": 0.0931,
508
+ "step": 33000
509
+ },
510
+ {
511
+ "epoch": 4.1875,
512
+ "grad_norm": 0.4526767134666443,
513
+ "learning_rate": 3.836840277777778e-05,
514
+ "loss": 0.1269,
515
+ "step": 33500
516
+ },
517
+ {
518
+ "epoch": 4.25,
519
+ "grad_norm": 0.0006220944924280047,
520
+ "learning_rate": 3.819479166666667e-05,
521
+ "loss": 0.1229,
522
+ "step": 34000
523
+ },
524
+ {
525
+ "epoch": 4.3125,
526
+ "grad_norm": 0.0021529244258999825,
527
+ "learning_rate": 3.802118055555556e-05,
528
+ "loss": 0.0941,
529
+ "step": 34500
530
+ },
531
+ {
532
+ "epoch": 4.375,
533
+ "grad_norm": 161.37889099121094,
534
+ "learning_rate": 3.784756944444445e-05,
535
+ "loss": 0.1504,
536
+ "step": 35000
537
+ },
538
+ {
539
+ "epoch": 4.4375,
540
+ "grad_norm": 0.11136477440595627,
541
+ "learning_rate": 3.7673958333333334e-05,
542
+ "loss": 0.1809,
543
+ "step": 35500
544
+ },
545
+ {
546
+ "epoch": 4.5,
547
+ "grad_norm": 0.001285308855585754,
548
+ "learning_rate": 3.7500347222222224e-05,
549
+ "loss": 0.0936,
550
+ "step": 36000
551
+ },
552
+ {
553
+ "epoch": 4.5625,
554
+ "grad_norm": 9.097888687392697e-05,
555
+ "learning_rate": 3.7326736111111114e-05,
556
+ "loss": 0.138,
557
+ "step": 36500
558
+ },
559
+ {
560
+ "epoch": 4.625,
561
+ "grad_norm": 8.100504373942385e-07,
562
+ "learning_rate": 3.7153125e-05,
563
+ "loss": 0.1018,
564
+ "step": 37000
565
+ },
566
+ {
567
+ "epoch": 4.6875,
568
+ "grad_norm": 7.76401338953292e-06,
569
+ "learning_rate": 3.697951388888889e-05,
570
+ "loss": 0.1467,
571
+ "step": 37500
572
+ },
573
+ {
574
+ "epoch": 4.75,
575
+ "grad_norm": 0.00011219551379326731,
576
+ "learning_rate": 3.680590277777778e-05,
577
+ "loss": 0.1253,
578
+ "step": 38000
579
+ },
580
+ {
581
+ "epoch": 4.8125,
582
+ "grad_norm": 6.52613493912213e-07,
583
+ "learning_rate": 3.6632291666666667e-05,
584
+ "loss": 0.1658,
585
+ "step": 38500
586
+ },
587
+ {
588
+ "epoch": 4.875,
589
+ "grad_norm": 0.00043506777728907764,
590
+ "learning_rate": 3.6458680555555557e-05,
591
+ "loss": 0.1746,
592
+ "step": 39000
593
+ },
594
+ {
595
+ "epoch": 4.9375,
596
+ "grad_norm": 0.003737818216904998,
597
+ "learning_rate": 3.6285069444444446e-05,
598
+ "loss": 0.1511,
599
+ "step": 39500
600
+ },
601
+ {
602
+ "epoch": 5.0,
603
+ "grad_norm": 0.0032031103037297726,
604
+ "learning_rate": 3.6111458333333336e-05,
605
+ "loss": 0.1175,
606
+ "step": 40000
607
+ },
608
+ {
609
+ "epoch": 5.0,
610
+ "eval_loss": 0.3400997221469879,
611
+ "eval_pearson": 0.9278541992287661,
612
+ "eval_runtime": 52.4259,
613
+ "eval_samples_per_second": 38.149,
614
+ "eval_steps_per_second": 19.075,
615
+ "step": 40000
616
+ },
617
+ {
618
+ "epoch": 5.0625,
619
+ "grad_norm": 7.578780059702694e-05,
620
+ "learning_rate": 3.5937847222222226e-05,
621
+ "loss": 0.0854,
622
+ "step": 40500
623
+ },
624
+ {
625
+ "epoch": 5.125,
626
+ "grad_norm": 0.00047107384307309985,
627
+ "learning_rate": 3.576423611111111e-05,
628
+ "loss": 0.0978,
629
+ "step": 41000
630
+ },
631
+ {
632
+ "epoch": 5.1875,
633
+ "grad_norm": 1.537612479296513e-05,
634
+ "learning_rate": 3.5590625e-05,
635
+ "loss": 0.0771,
636
+ "step": 41500
637
+ },
638
+ {
639
+ "epoch": 5.25,
640
+ "grad_norm": 0.4128485918045044,
641
+ "learning_rate": 3.541701388888889e-05,
642
+ "loss": 0.0735,
643
+ "step": 42000
644
+ },
645
+ {
646
+ "epoch": 5.3125,
647
+ "grad_norm": 1.5655250549316406,
648
+ "learning_rate": 3.524340277777778e-05,
649
+ "loss": 0.0498,
650
+ "step": 42500
651
+ },
652
+ {
653
+ "epoch": 5.375,
654
+ "grad_norm": 7.616046104885754e-07,
655
+ "learning_rate": 3.506979166666667e-05,
656
+ "loss": 0.0931,
657
+ "step": 43000
658
+ },
659
+ {
660
+ "epoch": 5.4375,
661
+ "grad_norm": 88.26677703857422,
662
+ "learning_rate": 3.489618055555556e-05,
663
+ "loss": 0.0792,
664
+ "step": 43500
665
+ },
666
+ {
667
+ "epoch": 5.5,
668
+ "grad_norm": 5.622899834634154e-07,
669
+ "learning_rate": 3.472256944444445e-05,
670
+ "loss": 0.0598,
671
+ "step": 44000
672
+ },
673
+ {
674
+ "epoch": 5.5625,
675
+ "grad_norm": 3.284021659055725e-07,
676
+ "learning_rate": 3.454895833333334e-05,
677
+ "loss": 0.0569,
678
+ "step": 44500
679
+ },
680
+ {
681
+ "epoch": 5.625,
682
+ "grad_norm": 7.701730646658689e-05,
683
+ "learning_rate": 3.437534722222223e-05,
684
+ "loss": 0.1013,
685
+ "step": 45000
686
+ },
687
+ {
688
+ "epoch": 5.6875,
689
+ "grad_norm": 0.0011569270864129066,
690
+ "learning_rate": 3.420173611111111e-05,
691
+ "loss": 0.0752,
692
+ "step": 45500
693
+ },
694
+ {
695
+ "epoch": 5.75,
696
+ "grad_norm": 0.005151362158358097,
697
+ "learning_rate": 3.4028125e-05,
698
+ "loss": 0.1286,
699
+ "step": 46000
700
+ },
701
+ {
702
+ "epoch": 5.8125,
703
+ "grad_norm": 2.8667493268130784e-08,
704
+ "learning_rate": 3.385451388888889e-05,
705
+ "loss": 0.0628,
706
+ "step": 46500
707
+ },
708
+ {
709
+ "epoch": 5.875,
710
+ "grad_norm": 2.9006994282099186e-06,
711
+ "learning_rate": 3.3680902777777775e-05,
712
+ "loss": 0.0778,
713
+ "step": 47000
714
+ },
715
+ {
716
+ "epoch": 5.9375,
717
+ "grad_norm": 1.4291666047938634e-05,
718
+ "learning_rate": 3.3507291666666665e-05,
719
+ "loss": 0.0939,
720
+ "step": 47500
721
+ },
722
+ {
723
+ "epoch": 6.0,
724
+ "grad_norm": 3.1977786420611665e-05,
725
+ "learning_rate": 3.3333680555555555e-05,
726
+ "loss": 0.0701,
727
+ "step": 48000
728
+ },
729
+ {
730
+ "epoch": 6.0,
731
+ "eval_loss": 0.3394077718257904,
732
+ "eval_pearson": 0.929029551743213,
733
+ "eval_runtime": 52.4713,
734
+ "eval_samples_per_second": 38.116,
735
+ "eval_steps_per_second": 19.058,
736
+ "step": 48000
737
+ },
738
+ {
739
+ "epoch": 6.0625,
740
+ "grad_norm": 2.3781665277056163e-06,
741
+ "learning_rate": 3.3160069444444445e-05,
742
+ "loss": 0.0575,
743
+ "step": 48500
744
+ },
745
+ {
746
+ "epoch": 6.125,
747
+ "grad_norm": 0.00014402755186893046,
748
+ "learning_rate": 3.2986458333333335e-05,
749
+ "loss": 0.0599,
750
+ "step": 49000
751
+ },
752
+ {
753
+ "epoch": 6.1875,
754
+ "grad_norm": 0.0024268697015941143,
755
+ "learning_rate": 3.2812847222222225e-05,
756
+ "loss": 0.0134,
757
+ "step": 49500
758
+ },
759
+ {
760
+ "epoch": 6.25,
761
+ "grad_norm": 2.872504949569702,
762
+ "learning_rate": 3.263923611111111e-05,
763
+ "loss": 0.0529,
764
+ "step": 50000
765
+ },
766
+ {
767
+ "epoch": 6.3125,
768
+ "grad_norm": 0.08783645182847977,
769
+ "learning_rate": 3.2465625e-05,
770
+ "loss": 0.0429,
771
+ "step": 50500
772
+ },
773
+ {
774
+ "epoch": 6.375,
775
+ "grad_norm": 8.48967170715332,
776
+ "learning_rate": 3.229201388888889e-05,
777
+ "loss": 0.0615,
778
+ "step": 51000
779
+ },
780
+ {
781
+ "epoch": 6.4375,
782
+ "grad_norm": 4.978901984031836e-07,
783
+ "learning_rate": 3.211840277777778e-05,
784
+ "loss": 0.0493,
785
+ "step": 51500
786
+ },
787
+ {
788
+ "epoch": 6.5,
789
+ "grad_norm": 1.5710222669440554e-06,
790
+ "learning_rate": 3.194479166666667e-05,
791
+ "loss": 0.0842,
792
+ "step": 52000
793
+ },
794
+ {
795
+ "epoch": 6.5625,
796
+ "grad_norm": 0.0002388143038842827,
797
+ "learning_rate": 3.177118055555556e-05,
798
+ "loss": 0.0322,
799
+ "step": 52500
800
+ },
801
+ {
802
+ "epoch": 6.625,
803
+ "grad_norm": 4.66664324960675e-08,
804
+ "learning_rate": 3.159756944444445e-05,
805
+ "loss": 0.0182,
806
+ "step": 53000
807
+ },
808
+ {
809
+ "epoch": 6.6875,
810
+ "grad_norm": 57.2918586730957,
811
+ "learning_rate": 3.142395833333334e-05,
812
+ "loss": 0.0851,
813
+ "step": 53500
814
+ },
815
+ {
816
+ "epoch": 6.75,
817
+ "grad_norm": 5.3962357924319804e-05,
818
+ "learning_rate": 3.125034722222223e-05,
819
+ "loss": 0.0644,
820
+ "step": 54000
821
+ },
822
+ {
823
+ "epoch": 6.8125,
824
+ "grad_norm": 0.006401342805474997,
825
+ "learning_rate": 3.107673611111111e-05,
826
+ "loss": 0.0943,
827
+ "step": 54500
828
+ },
829
+ {
830
+ "epoch": 6.875,
831
+ "grad_norm": 3.415437390685838e-07,
832
+ "learning_rate": 3.0903125e-05,
833
+ "loss": 0.0967,
834
+ "step": 55000
835
+ },
836
+ {
837
+ "epoch": 6.9375,
838
+ "grad_norm": 5.508160825229425e-07,
839
+ "learning_rate": 3.072951388888889e-05,
840
+ "loss": 0.0507,
841
+ "step": 55500
842
+ },
843
+ {
844
+ "epoch": 7.0,
845
+ "grad_norm": 0.04088839516043663,
846
+ "learning_rate": 3.055590277777778e-05,
847
+ "loss": 0.0139,
848
+ "step": 56000
849
+ },
850
+ {
851
+ "epoch": 7.0,
852
+ "eval_loss": 0.37575554847717285,
853
+ "eval_pearson": 0.9206240663481206,
854
+ "eval_runtime": 52.4561,
855
+ "eval_samples_per_second": 38.127,
856
+ "eval_steps_per_second": 19.064,
857
+ "step": 56000
858
+ },
859
+ {
860
+ "epoch": 7.0625,
861
+ "grad_norm": 0.004823420196771622,
862
+ "learning_rate": 3.0382291666666667e-05,
863
+ "loss": 0.0539,
864
+ "step": 56500
865
+ },
866
+ {
867
+ "epoch": 7.125,
868
+ "grad_norm": 106.49919128417969,
869
+ "learning_rate": 3.0208680555555557e-05,
870
+ "loss": 0.0232,
871
+ "step": 57000
872
+ },
873
+ {
874
+ "epoch": 7.1875,
875
+ "grad_norm": 1.074000238077133e-06,
876
+ "learning_rate": 3.0035069444444447e-05,
877
+ "loss": 0.0187,
878
+ "step": 57500
879
+ },
880
+ {
881
+ "epoch": 7.25,
882
+ "grad_norm": 0.0039020858239382505,
883
+ "learning_rate": 2.9861458333333337e-05,
884
+ "loss": 0.0472,
885
+ "step": 58000
886
+ },
887
+ {
888
+ "epoch": 7.3125,
889
+ "grad_norm": 0.0892600491642952,
890
+ "learning_rate": 2.9687847222222227e-05,
891
+ "loss": 0.0658,
892
+ "step": 58500
893
+ },
894
+ {
895
+ "epoch": 7.375,
896
+ "grad_norm": 0.00350657245144248,
897
+ "learning_rate": 2.951423611111111e-05,
898
+ "loss": 0.0456,
899
+ "step": 59000
900
+ },
901
+ {
902
+ "epoch": 7.4375,
903
+ "grad_norm": 0.0006594175356440246,
904
+ "learning_rate": 2.9340625e-05,
905
+ "loss": 0.0171,
906
+ "step": 59500
907
+ },
908
+ {
909
+ "epoch": 7.5,
910
+ "grad_norm": 92.61225128173828,
911
+ "learning_rate": 2.916701388888889e-05,
912
+ "loss": 0.0274,
913
+ "step": 60000
914
+ },
915
+ {
916
+ "epoch": 7.5625,
917
+ "grad_norm": 3.026230599445512e-09,
918
+ "learning_rate": 2.899340277777778e-05,
919
+ "loss": 0.0471,
920
+ "step": 60500
921
+ },
922
+ {
923
+ "epoch": 7.625,
924
+ "grad_norm": 1.0678179023670964e-05,
925
+ "learning_rate": 2.8819791666666666e-05,
926
+ "loss": 0.0216,
927
+ "step": 61000
928
+ },
929
+ {
930
+ "epoch": 7.6875,
931
+ "grad_norm": 5.752791912527755e-05,
932
+ "learning_rate": 2.8646180555555556e-05,
933
+ "loss": 0.0157,
934
+ "step": 61500
935
+ },
936
+ {
937
+ "epoch": 7.75,
938
+ "grad_norm": 5.118190288543701,
939
+ "learning_rate": 2.8472569444444446e-05,
940
+ "loss": 0.0616,
941
+ "step": 62000
942
+ },
943
+ {
944
+ "epoch": 7.8125,
945
+ "grad_norm": 2.0125851733610034e-05,
946
+ "learning_rate": 2.8298958333333336e-05,
947
+ "loss": 0.0783,
948
+ "step": 62500
949
+ },
950
+ {
951
+ "epoch": 7.875,
952
+ "grad_norm": 161.75416564941406,
953
+ "learning_rate": 2.8125347222222226e-05,
954
+ "loss": 0.0295,
955
+ "step": 63000
956
+ },
957
+ {
958
+ "epoch": 7.9375,
959
+ "grad_norm": 1.577711117306535e-08,
960
+ "learning_rate": 2.795173611111111e-05,
961
+ "loss": 0.0498,
962
+ "step": 63500
963
+ },
964
+ {
965
+ "epoch": 8.0,
966
+ "grad_norm": 5.166618279872637e-07,
967
+ "learning_rate": 2.7778125e-05,
968
+ "loss": 0.0397,
969
+ "step": 64000
970
+ },
971
+ {
972
+ "epoch": 8.0,
973
+ "eval_loss": 0.3336261510848999,
974
+ "eval_pearson": 0.9327475370491191,
975
+ "eval_runtime": 52.4675,
976
+ "eval_samples_per_second": 38.119,
977
+ "eval_steps_per_second": 19.059,
978
+ "step": 64000
979
+ },
980
+ {
981
+ "epoch": 8.0625,
982
+ "grad_norm": 0.0026754948776215315,
983
+ "learning_rate": 2.760451388888889e-05,
984
+ "loss": 0.026,
985
+ "step": 64500
986
+ },
987
+ {
988
+ "epoch": 8.125,
989
+ "grad_norm": 3.3581352454348234e-07,
990
+ "learning_rate": 2.743090277777778e-05,
991
+ "loss": 0.0115,
992
+ "step": 65000
993
+ },
994
+ {
995
+ "epoch": 8.1875,
996
+ "grad_norm": 2.0662416488903546e-07,
997
+ "learning_rate": 2.725729166666667e-05,
998
+ "loss": 0.012,
999
+ "step": 65500
1000
+ },
1001
+ {
1002
+ "epoch": 8.25,
1003
+ "grad_norm": 8.040846921630873e-08,
1004
+ "learning_rate": 2.7083680555555556e-05,
1005
+ "loss": 0.0406,
1006
+ "step": 66000
1007
+ },
1008
+ {
1009
+ "epoch": 8.3125,
1010
+ "grad_norm": 3.422968006816518e-07,
1011
+ "learning_rate": 2.6910069444444446e-05,
1012
+ "loss": 0.0321,
1013
+ "step": 66500
1014
+ },
1015
+ {
1016
+ "epoch": 8.375,
1017
+ "grad_norm": 0.00017860137450043112,
1018
+ "learning_rate": 2.6736458333333336e-05,
1019
+ "loss": 0.0448,
1020
+ "step": 67000
1021
+ },
1022
+ {
1023
+ "epoch": 8.4375,
1024
+ "grad_norm": 1.2621427236680915e-09,
1025
+ "learning_rate": 2.6562847222222225e-05,
1026
+ "loss": 0.0455,
1027
+ "step": 67500
1028
+ },
1029
+ {
1030
+ "epoch": 8.5,
1031
+ "grad_norm": 1.4346144325827481e-06,
1032
+ "learning_rate": 2.638923611111111e-05,
1033
+ "loss": 0.0325,
1034
+ "step": 68000
1035
+ },
1036
+ {
1037
+ "epoch": 8.5625,
1038
+ "grad_norm": 1.2407322174112778e-06,
1039
+ "learning_rate": 2.6215625e-05,
1040
+ "loss": 0.0223,
1041
+ "step": 68500
1042
+ },
1043
+ {
1044
+ "epoch": 8.625,
1045
+ "grad_norm": 3.0256799163908e-06,
1046
+ "learning_rate": 2.604201388888889e-05,
1047
+ "loss": 0.0019,
1048
+ "step": 69000
1049
+ },
1050
+ {
1051
+ "epoch": 8.6875,
1052
+ "grad_norm": 0.007253507152199745,
1053
+ "learning_rate": 2.586840277777778e-05,
1054
+ "loss": 0.0085,
1055
+ "step": 69500
1056
+ },
1057
+ {
1058
+ "epoch": 8.75,
1059
+ "grad_norm": 2.782409467272373e-07,
1060
+ "learning_rate": 2.569479166666667e-05,
1061
+ "loss": 0.0518,
1062
+ "step": 70000
1063
+ },
1064
+ {
1065
+ "epoch": 8.8125,
1066
+ "grad_norm": 0.000820077199023217,
1067
+ "learning_rate": 2.552118055555556e-05,
1068
+ "loss": 0.031,
1069
+ "step": 70500
1070
+ },
1071
+ {
1072
+ "epoch": 8.875,
1073
+ "grad_norm": 2.470728213666007e-05,
1074
+ "learning_rate": 2.5347569444444448e-05,
1075
+ "loss": 0.0354,
1076
+ "step": 71000
1077
+ },
1078
+ {
1079
+ "epoch": 8.9375,
1080
+ "grad_norm": 9.137271263170987e-05,
1081
+ "learning_rate": 2.5173958333333335e-05,
1082
+ "loss": 0.0666,
1083
+ "step": 71500
1084
+ },
1085
+ {
1086
+ "epoch": 9.0,
1087
+ "grad_norm": 0.00029885413823649287,
1088
+ "learning_rate": 2.5000347222222225e-05,
1089
+ "loss": 0.0267,
1090
+ "step": 72000
1091
+ },
1092
+ {
1093
+ "epoch": 9.0,
1094
+ "eval_loss": 0.37894001603126526,
1095
+ "eval_pearson": 0.9279985680079542,
1096
+ "eval_runtime": 52.4816,
1097
+ "eval_samples_per_second": 38.109,
1098
+ "eval_steps_per_second": 19.054,
1099
+ "step": 72000
1100
+ },
1101
+ {
1102
+ "epoch": 9.0625,
1103
+ "grad_norm": 6.724835839122534e-05,
1104
+ "learning_rate": 2.482673611111111e-05,
1105
+ "loss": 0.0044,
1106
+ "step": 72500
1107
+ },
1108
+ {
1109
+ "epoch": 9.125,
1110
+ "grad_norm": 9.228666164595722e-10,
1111
+ "learning_rate": 2.4653125e-05,
1112
+ "loss": 0.0095,
1113
+ "step": 73000
1114
+ },
1115
+ {
1116
+ "epoch": 9.1875,
1117
+ "grad_norm": 0.00011938459647353739,
1118
+ "learning_rate": 2.447951388888889e-05,
1119
+ "loss": 0.0384,
1120
+ "step": 73500
1121
+ },
1122
+ {
1123
+ "epoch": 9.25,
1124
+ "grad_norm": 1.6898056287573127e-09,
1125
+ "learning_rate": 2.4305902777777778e-05,
1126
+ "loss": 0.0182,
1127
+ "step": 74000
1128
+ },
1129
+ {
1130
+ "epoch": 9.3125,
1131
+ "grad_norm": 5.753568288469069e-09,
1132
+ "learning_rate": 2.4132291666666668e-05,
1133
+ "loss": 0.0075,
1134
+ "step": 74500
1135
+ },
1136
+ {
1137
+ "epoch": 9.375,
1138
+ "grad_norm": 5.144208614638046e-08,
1139
+ "learning_rate": 2.3958680555555558e-05,
1140
+ "loss": 0.0172,
1141
+ "step": 75000
1142
+ },
1143
+ {
1144
+ "epoch": 9.4375,
1145
+ "grad_norm": 9.800347200439319e-10,
1146
+ "learning_rate": 2.3785069444444448e-05,
1147
+ "loss": 0.0431,
1148
+ "step": 75500
1149
+ },
1150
+ {
1151
+ "epoch": 9.5,
1152
+ "grad_norm": 5.440585135185749e-11,
1153
+ "learning_rate": 2.3611458333333334e-05,
1154
+ "loss": 0.0109,
1155
+ "step": 76000
1156
+ },
1157
+ {
1158
+ "epoch": 9.5625,
1159
+ "grad_norm": 0.00019604770932346582,
1160
+ "learning_rate": 2.3437847222222224e-05,
1161
+ "loss": 0.0284,
1162
+ "step": 76500
1163
+ },
1164
+ {
1165
+ "epoch": 9.625,
1166
+ "grad_norm": 1.242908239364624,
1167
+ "learning_rate": 2.3264236111111114e-05,
1168
+ "loss": 0.0405,
1169
+ "step": 77000
1170
+ },
1171
+ {
1172
+ "epoch": 9.6875,
1173
+ "grad_norm": 1.540728953841608e-05,
1174
+ "learning_rate": 2.3090625e-05,
1175
+ "loss": 0.0435,
1176
+ "step": 77500
1177
+ },
1178
+ {
1179
+ "epoch": 9.75,
1180
+ "grad_norm": 0.00013433759158942848,
1181
+ "learning_rate": 2.291701388888889e-05,
1182
+ "loss": 0.0181,
1183
+ "step": 78000
1184
+ },
1185
+ {
1186
+ "epoch": 9.8125,
1187
+ "grad_norm": 3.088209687973631e-10,
1188
+ "learning_rate": 2.2743402777777777e-05,
1189
+ "loss": 0.0228,
1190
+ "step": 78500
1191
+ },
1192
+ {
1193
+ "epoch": 9.875,
1194
+ "grad_norm": 0.000814907078165561,
1195
+ "learning_rate": 2.2569791666666667e-05,
1196
+ "loss": 0.0499,
1197
+ "step": 79000
1198
+ },
1199
+ {
1200
+ "epoch": 9.9375,
1201
+ "grad_norm": 1.274260625905299e-07,
1202
+ "learning_rate": 2.2396180555555557e-05,
1203
+ "loss": 0.0316,
1204
+ "step": 79500
1205
+ },
1206
+ {
1207
+ "epoch": 10.0,
1208
+ "grad_norm": 4.301631997805089e-05,
1209
+ "learning_rate": 2.2222569444444447e-05,
1210
+ "loss": 0.015,
1211
+ "step": 80000
1212
+ },
1213
+ {
1214
+ "epoch": 10.0,
1215
+ "eval_loss": 0.38902410864830017,
1216
+ "eval_pearson": 0.9249309324232664,
1217
+ "eval_runtime": 52.3807,
1218
+ "eval_samples_per_second": 38.182,
1219
+ "eval_steps_per_second": 19.091,
1220
+ "step": 80000
1221
+ },
1222
+ {
1223
+ "epoch": 10.0625,
1224
+ "grad_norm": 1.7468665403086447e-10,
1225
+ "learning_rate": 2.2048958333333333e-05,
1226
+ "loss": 0.0081,
1227
+ "step": 80500
1228
+ },
1229
+ {
1230
+ "epoch": 10.125,
1231
+ "grad_norm": 6.71422021696344e-05,
1232
+ "learning_rate": 2.1875347222222223e-05,
1233
+ "loss": 0.0143,
1234
+ "step": 81000
1235
+ },
1236
+ {
1237
+ "epoch": 10.1875,
1238
+ "grad_norm": 3.1802871944819344e-06,
1239
+ "learning_rate": 2.1701736111111113e-05,
1240
+ "loss": 0.029,
1241
+ "step": 81500
1242
+ },
1243
+ {
1244
+ "epoch": 10.25,
1245
+ "grad_norm": 0.014791320078074932,
1246
+ "learning_rate": 2.1528125000000003e-05,
1247
+ "loss": 0.0054,
1248
+ "step": 82000
1249
+ },
1250
+ {
1251
+ "epoch": 10.3125,
1252
+ "grad_norm": 2.0462434235923865e-07,
1253
+ "learning_rate": 2.135451388888889e-05,
1254
+ "loss": 0.0436,
1255
+ "step": 82500
1256
+ },
1257
+ {
1258
+ "epoch": 10.375,
1259
+ "grad_norm": 1.3791065216064453,
1260
+ "learning_rate": 2.1180902777777776e-05,
1261
+ "loss": 0.0181,
1262
+ "step": 83000
1263
+ },
1264
+ {
1265
+ "epoch": 10.4375,
1266
+ "grad_norm": 0.002008361741900444,
1267
+ "learning_rate": 2.1007291666666666e-05,
1268
+ "loss": 0.0082,
1269
+ "step": 83500
1270
+ },
1271
+ {
1272
+ "epoch": 10.5,
1273
+ "grad_norm": 5.804303704337599e-09,
1274
+ "learning_rate": 2.0833680555555556e-05,
1275
+ "loss": 0.0249,
1276
+ "step": 84000
1277
+ },
1278
+ {
1279
+ "epoch": 10.5625,
1280
+ "grad_norm": 0.0007163327536545694,
1281
+ "learning_rate": 2.0660069444444446e-05,
1282
+ "loss": 0.0112,
1283
+ "step": 84500
1284
+ },
1285
+ {
1286
+ "epoch": 10.625,
1287
+ "grad_norm": 0.0001620600960450247,
1288
+ "learning_rate": 2.0486458333333333e-05,
1289
+ "loss": 0.0295,
1290
+ "step": 85000
1291
+ },
1292
+ {
1293
+ "epoch": 10.6875,
1294
+ "grad_norm": 0.05068128928542137,
1295
+ "learning_rate": 2.0312847222222223e-05,
1296
+ "loss": 0.0223,
1297
+ "step": 85500
1298
+ },
1299
+ {
1300
+ "epoch": 10.75,
1301
+ "grad_norm": 0.0007038409821689129,
1302
+ "learning_rate": 2.0139236111111113e-05,
1303
+ "loss": 0.0192,
1304
+ "step": 86000
1305
+ },
1306
+ {
1307
+ "epoch": 10.8125,
1308
+ "grad_norm": 0.024000702425837517,
1309
+ "learning_rate": 1.9965625000000002e-05,
1310
+ "loss": 0.0249,
1311
+ "step": 86500
1312
+ },
1313
+ {
1314
+ "epoch": 10.875,
1315
+ "grad_norm": 3.588341712656984e-07,
1316
+ "learning_rate": 1.9792013888888892e-05,
1317
+ "loss": 0.0429,
1318
+ "step": 87000
1319
+ },
1320
+ {
1321
+ "epoch": 10.9375,
1322
+ "grad_norm": 1.5524047114467976e-07,
1323
+ "learning_rate": 1.961840277777778e-05,
1324
+ "loss": 0.0188,
1325
+ "step": 87500
1326
+ },
1327
+ {
1328
+ "epoch": 11.0,
1329
+ "grad_norm": 2.524126614389388e-07,
1330
+ "learning_rate": 1.944479166666667e-05,
1331
+ "loss": 0.0217,
1332
+ "step": 88000
1333
+ },
1334
+ {
1335
+ "epoch": 11.0,
1336
+ "eval_loss": 0.39052143692970276,
1337
+ "eval_pearson": 0.936161178019818,
1338
+ "eval_runtime": 52.432,
1339
+ "eval_samples_per_second": 38.145,
1340
+ "eval_steps_per_second": 19.072,
1341
+ "step": 88000
1342
+ },
1343
+ {
1344
+ "epoch": 11.0625,
1345
+ "grad_norm": 0.0005805569817312062,
1346
+ "learning_rate": 1.9271180555555555e-05,
1347
+ "loss": 0.0255,
1348
+ "step": 88500
1349
+ },
1350
+ {
1351
+ "epoch": 11.125,
1352
+ "grad_norm": 4.623345546406199e-07,
1353
+ "learning_rate": 1.9097569444444445e-05,
1354
+ "loss": 0.0078,
1355
+ "step": 89000
1356
+ },
1357
+ {
1358
+ "epoch": 11.1875,
1359
+ "grad_norm": 5.301876715435583e-09,
1360
+ "learning_rate": 1.8923958333333332e-05,
1361
+ "loss": 0.005,
1362
+ "step": 89500
1363
+ },
1364
+ {
1365
+ "epoch": 11.25,
1366
+ "grad_norm": 0.09818815439939499,
1367
+ "learning_rate": 1.8750347222222222e-05,
1368
+ "loss": 0.008,
1369
+ "step": 90000
1370
+ },
1371
+ {
1372
+ "epoch": 11.3125,
1373
+ "grad_norm": 1.8287735656485893e-05,
1374
+ "learning_rate": 1.8576736111111112e-05,
1375
+ "loss": 0.0021,
1376
+ "step": 90500
1377
+ },
1378
+ {
1379
+ "epoch": 11.375,
1380
+ "grad_norm": 9.81485072770738e-07,
1381
+ "learning_rate": 1.8403125000000002e-05,
1382
+ "loss": 0.014,
1383
+ "step": 91000
1384
+ },
1385
+ {
1386
+ "epoch": 11.4375,
1387
+ "grad_norm": 0.006411096081137657,
1388
+ "learning_rate": 1.8229513888888892e-05,
1389
+ "loss": 0.0128,
1390
+ "step": 91500
1391
+ },
1392
+ {
1393
+ "epoch": 11.5,
1394
+ "grad_norm": 4.448479778984549e-11,
1395
+ "learning_rate": 1.8055902777777778e-05,
1396
+ "loss": 0.0023,
1397
+ "step": 92000
1398
+ },
1399
+ {
1400
+ "epoch": 11.5625,
1401
+ "grad_norm": 0.012693402357399464,
1402
+ "learning_rate": 1.7882291666666668e-05,
1403
+ "loss": 0.0344,
1404
+ "step": 92500
1405
+ },
1406
+ {
1407
+ "epoch": 11.625,
1408
+ "grad_norm": 6.370872540628625e-08,
1409
+ "learning_rate": 1.7708680555555558e-05,
1410
+ "loss": 0.0258,
1411
+ "step": 93000
1412
+ },
1413
+ {
1414
+ "epoch": 11.6875,
1415
+ "grad_norm": 9.032481429471773e-09,
1416
+ "learning_rate": 1.7535069444444445e-05,
1417
+ "loss": 0.0112,
1418
+ "step": 93500
1419
+ },
1420
+ {
1421
+ "epoch": 11.75,
1422
+ "grad_norm": 0.001719271531328559,
1423
+ "learning_rate": 1.7361458333333335e-05,
1424
+ "loss": 0.0275,
1425
+ "step": 94000
1426
+ },
1427
+ {
1428
+ "epoch": 11.8125,
1429
+ "grad_norm": 7.162652036640793e-05,
1430
+ "learning_rate": 1.718784722222222e-05,
1431
+ "loss": 0.0119,
1432
+ "step": 94500
1433
+ },
1434
+ {
1435
+ "epoch": 11.875,
1436
+ "grad_norm": 1.2189951803520671e-06,
1437
+ "learning_rate": 1.701423611111111e-05,
1438
+ "loss": 0.0392,
1439
+ "step": 95000
1440
+ },
1441
+ {
1442
+ "epoch": 11.9375,
1443
+ "grad_norm": 5.709237484552432e-06,
1444
+ "learning_rate": 1.6840625e-05,
1445
+ "loss": 0.0341,
1446
+ "step": 95500
1447
+ },
1448
+ {
1449
+ "epoch": 12.0,
1450
+ "grad_norm": 1.2266503290447872e-05,
1451
+ "learning_rate": 1.666701388888889e-05,
1452
+ "loss": 0.1026,
1453
+ "step": 96000
1454
+ },
1455
+ {
1456
+ "epoch": 12.0,
1457
+ "eval_loss": 0.42006340622901917,
1458
+ "eval_pearson": 0.9249266863163004,
1459
+ "eval_runtime": 52.4951,
1460
+ "eval_samples_per_second": 38.099,
1461
+ "eval_steps_per_second": 19.049,
1462
+ "step": 96000
1463
+ },
1464
+ {
1465
+ "epoch": 12.0625,
1466
+ "grad_norm": 1.2190711773385488e-09,
1467
+ "learning_rate": 1.6493402777777778e-05,
1468
+ "loss": 0.0118,
1469
+ "step": 96500
1470
+ },
1471
+ {
1472
+ "epoch": 12.125,
1473
+ "grad_norm": 9.660718660597922e-07,
1474
+ "learning_rate": 1.6319791666666668e-05,
1475
+ "loss": 0.0021,
1476
+ "step": 97000
1477
+ },
1478
+ {
1479
+ "epoch": 12.1875,
1480
+ "grad_norm": 0.0003258072247263044,
1481
+ "learning_rate": 1.6146180555555557e-05,
1482
+ "loss": 0.011,
1483
+ "step": 97500
1484
+ },
1485
+ {
1486
+ "epoch": 12.25,
1487
+ "grad_norm": 0.00024601773475296795,
1488
+ "learning_rate": 1.5972569444444447e-05,
1489
+ "loss": 0.0161,
1490
+ "step": 98000
1491
+ },
1492
+ {
1493
+ "epoch": 12.3125,
1494
+ "grad_norm": 2.0050613613875612e-07,
1495
+ "learning_rate": 1.5798958333333334e-05,
1496
+ "loss": 0.0062,
1497
+ "step": 98500
1498
+ },
1499
+ {
1500
+ "epoch": 12.375,
1501
+ "grad_norm": 0.00019162562966812402,
1502
+ "learning_rate": 1.5625347222222224e-05,
1503
+ "loss": 0.0017,
1504
+ "step": 99000
1505
+ },
1506
+ {
1507
+ "epoch": 12.4375,
1508
+ "grad_norm": 5.855550853084424e-07,
1509
+ "learning_rate": 1.545173611111111e-05,
1510
+ "loss": 0.011,
1511
+ "step": 99500
1512
+ },
1513
+ {
1514
+ "epoch": 12.5,
1515
+ "grad_norm": 5.200939631322399e-05,
1516
+ "learning_rate": 1.5278125e-05,
1517
+ "loss": 0.0625,
1518
+ "step": 100000
1519
+ },
1520
+ {
1521
+ "epoch": 12.5625,
1522
+ "grad_norm": 0.0051911999471485615,
1523
+ "learning_rate": 1.510451388888889e-05,
1524
+ "loss": 0.0223,
1525
+ "step": 100500
1526
+ },
1527
+ {
1528
+ "epoch": 12.625,
1529
+ "grad_norm": 0.00023108582536224276,
1530
+ "learning_rate": 1.4930902777777777e-05,
1531
+ "loss": 0.0184,
1532
+ "step": 101000
1533
+ },
1534
+ {
1535
+ "epoch": 12.6875,
1536
+ "grad_norm": 1.2751560461765621e-05,
1537
+ "learning_rate": 1.4757291666666667e-05,
1538
+ "loss": 0.0325,
1539
+ "step": 101500
1540
+ },
1541
+ {
1542
+ "epoch": 12.75,
1543
+ "grad_norm": 0.07260618358850479,
1544
+ "learning_rate": 1.4583680555555557e-05,
1545
+ "loss": 0.0472,
1546
+ "step": 102000
1547
+ },
1548
+ {
1549
+ "epoch": 12.8125,
1550
+ "grad_norm": 1.3546050467994064e-06,
1551
+ "learning_rate": 1.4410069444444447e-05,
1552
+ "loss": 0.0326,
1553
+ "step": 102500
1554
+ },
1555
+ {
1556
+ "epoch": 12.875,
1557
+ "grad_norm": 0.00040618935599923134,
1558
+ "learning_rate": 1.4236458333333333e-05,
1559
+ "loss": 0.0092,
1560
+ "step": 103000
1561
+ },
1562
+ {
1563
+ "epoch": 12.9375,
1564
+ "grad_norm": 3.1089444973986247e-07,
1565
+ "learning_rate": 1.4062847222222223e-05,
1566
+ "loss": 0.0493,
1567
+ "step": 103500
1568
+ },
1569
+ {
1570
+ "epoch": 13.0,
1571
+ "grad_norm": 0.02031463012099266,
1572
+ "learning_rate": 1.3889236111111111e-05,
1573
+ "loss": 0.0344,
1574
+ "step": 104000
1575
+ },
1576
+ {
1577
+ "epoch": 13.0,
1578
+ "eval_loss": 0.3848821818828583,
1579
+ "eval_pearson": 0.9320737941331698,
1580
+ "eval_runtime": 52.3286,
1581
+ "eval_samples_per_second": 38.22,
1582
+ "eval_steps_per_second": 19.11,
1583
+ "step": 104000
1584
+ },
1585
+ {
1586
+ "epoch": 13.0625,
1587
+ "grad_norm": 5.390070782596013e-06,
1588
+ "learning_rate": 1.3715625000000001e-05,
1589
+ "loss": 0.0024,
1590
+ "step": 104500
1591
+ },
1592
+ {
1593
+ "epoch": 13.125,
1594
+ "grad_norm": 0.0009596606250852346,
1595
+ "learning_rate": 1.3542013888888891e-05,
1596
+ "loss": 0.0002,
1597
+ "step": 105000
1598
+ },
1599
+ {
1600
+ "epoch": 13.1875,
1601
+ "grad_norm": 1.6519630889888504e-06,
1602
+ "learning_rate": 1.3368402777777778e-05,
1603
+ "loss": 0.0079,
1604
+ "step": 105500
1605
+ },
1606
+ {
1607
+ "epoch": 13.25,
1608
+ "grad_norm": 2.448989988579342e-08,
1609
+ "learning_rate": 1.3194791666666668e-05,
1610
+ "loss": 0.0153,
1611
+ "step": 106000
1612
+ },
1613
+ {
1614
+ "epoch": 13.3125,
1615
+ "grad_norm": 0.0002976028772536665,
1616
+ "learning_rate": 1.3021180555555556e-05,
1617
+ "loss": 0.0039,
1618
+ "step": 106500
1619
+ },
1620
+ {
1621
+ "epoch": 13.375,
1622
+ "grad_norm": 0.00019340288417879492,
1623
+ "learning_rate": 1.2847569444444446e-05,
1624
+ "loss": 0.0163,
1625
+ "step": 107000
1626
+ },
1627
+ {
1628
+ "epoch": 13.4375,
1629
+ "grad_norm": 0.0057904901914298534,
1630
+ "learning_rate": 1.2673958333333333e-05,
1631
+ "loss": 0.0122,
1632
+ "step": 107500
1633
+ },
1634
+ {
1635
+ "epoch": 13.5,
1636
+ "grad_norm": 9.801337910175789e-06,
1637
+ "learning_rate": 1.2500347222222222e-05,
1638
+ "loss": 0.0379,
1639
+ "step": 108000
1640
+ },
1641
+ {
1642
+ "epoch": 13.5625,
1643
+ "grad_norm": 1.4482387769021443e-06,
1644
+ "learning_rate": 1.2326736111111112e-05,
1645
+ "loss": 0.0114,
1646
+ "step": 108500
1647
+ },
1648
+ {
1649
+ "epoch": 13.625,
1650
+ "grad_norm": 2.1305972040863708e-05,
1651
+ "learning_rate": 1.2153125e-05,
1652
+ "loss": 0.018,
1653
+ "step": 109000
1654
+ },
1655
+ {
1656
+ "epoch": 13.6875,
1657
+ "grad_norm": 0.09945420920848846,
1658
+ "learning_rate": 1.1979513888888889e-05,
1659
+ "loss": 0.0726,
1660
+ "step": 109500
1661
+ },
1662
+ {
1663
+ "epoch": 13.75,
1664
+ "grad_norm": 5.7829329307423905e-06,
1665
+ "learning_rate": 1.1805902777777779e-05,
1666
+ "loss": 0.0193,
1667
+ "step": 110000
1668
+ },
1669
+ {
1670
+ "epoch": 13.8125,
1671
+ "grad_norm": 6.558164386660792e-06,
1672
+ "learning_rate": 1.1632291666666667e-05,
1673
+ "loss": 0.0129,
1674
+ "step": 110500
1675
+ },
1676
+ {
1677
+ "epoch": 13.875,
1678
+ "grad_norm": 4.0651830346405404e-08,
1679
+ "learning_rate": 1.1458680555555557e-05,
1680
+ "loss": 0.0389,
1681
+ "step": 111000
1682
+ },
1683
+ {
1684
+ "epoch": 13.9375,
1685
+ "grad_norm": 1.2806684601684992e-08,
1686
+ "learning_rate": 1.1285069444444445e-05,
1687
+ "loss": 0.0071,
1688
+ "step": 111500
1689
+ },
1690
+ {
1691
+ "epoch": 14.0,
1692
+ "grad_norm": 0.11720628291368484,
1693
+ "learning_rate": 1.1111458333333333e-05,
1694
+ "loss": 0.0115,
1695
+ "step": 112000
1696
+ },
1697
+ {
1698
+ "epoch": 14.0,
1699
+ "eval_loss": 0.4008629620075226,
1700
+ "eval_pearson": 0.9287046075964228,
1701
+ "eval_runtime": 52.1174,
1702
+ "eval_samples_per_second": 38.375,
1703
+ "eval_steps_per_second": 19.187,
1704
+ "step": 112000
1705
+ },
1706
+ {
1707
+ "epoch": 14.0625,
1708
+ "grad_norm": 3.696676298403645e-09,
1709
+ "learning_rate": 1.0937847222222222e-05,
1710
+ "loss": 0.002,
1711
+ "step": 112500
1712
+ },
1713
+ {
1714
+ "epoch": 14.125,
1715
+ "grad_norm": 1.5702152040830697e-06,
1716
+ "learning_rate": 1.0764236111111112e-05,
1717
+ "loss": 0.011,
1718
+ "step": 113000
1719
+ },
1720
+ {
1721
+ "epoch": 14.1875,
1722
+ "grad_norm": 5.9359957958804443e-05,
1723
+ "learning_rate": 1.0590625e-05,
1724
+ "loss": 0.002,
1725
+ "step": 113500
1726
+ },
1727
+ {
1728
+ "epoch": 14.25,
1729
+ "grad_norm": 1.7063765331282177e-11,
1730
+ "learning_rate": 1.041701388888889e-05,
1731
+ "loss": 0.0092,
1732
+ "step": 114000
1733
+ },
1734
+ {
1735
+ "epoch": 14.3125,
1736
+ "grad_norm": 0.0013318562414497137,
1737
+ "learning_rate": 1.0243402777777778e-05,
1738
+ "loss": 0.0037,
1739
+ "step": 114500
1740
+ },
1741
+ {
1742
+ "epoch": 14.375,
1743
+ "grad_norm": 0.00013518838386517018,
1744
+ "learning_rate": 1.0069791666666666e-05,
1745
+ "loss": 0.0253,
1746
+ "step": 115000
1747
+ },
1748
+ {
1749
+ "epoch": 14.4375,
1750
+ "grad_norm": 0.0004931968287564814,
1751
+ "learning_rate": 9.896180555555556e-06,
1752
+ "loss": 0.0002,
1753
+ "step": 115500
1754
+ },
1755
+ {
1756
+ "epoch": 14.5,
1757
+ "grad_norm": 3.0277399787337345e-07,
1758
+ "learning_rate": 9.722569444444445e-06,
1759
+ "loss": 0.0219,
1760
+ "step": 116000
1761
+ },
1762
+ {
1763
+ "epoch": 14.5625,
1764
+ "grad_norm": 0.005195027217268944,
1765
+ "learning_rate": 9.548958333333334e-06,
1766
+ "loss": 0.0144,
1767
+ "step": 116500
1768
+ },
1769
+ {
1770
+ "epoch": 14.625,
1771
+ "grad_norm": 0.028845345601439476,
1772
+ "learning_rate": 9.375347222222223e-06,
1773
+ "loss": 0.0147,
1774
+ "step": 117000
1775
+ },
1776
+ {
1777
+ "epoch": 14.6875,
1778
+ "grad_norm": 2.050080212256944e-07,
1779
+ "learning_rate": 9.201736111111111e-06,
1780
+ "loss": 0.047,
1781
+ "step": 117500
1782
+ },
1783
+ {
1784
+ "epoch": 14.75,
1785
+ "grad_norm": 2.6781076911674973e-08,
1786
+ "learning_rate": 9.028125e-06,
1787
+ "loss": 0.023,
1788
+ "step": 118000
1789
+ },
1790
+ {
1791
+ "epoch": 14.8125,
1792
+ "grad_norm": 4.3490285861480515e-07,
1793
+ "learning_rate": 8.85451388888889e-06,
1794
+ "loss": 0.0397,
1795
+ "step": 118500
1796
+ },
1797
+ {
1798
+ "epoch": 14.875,
1799
+ "grad_norm": 5.553416121983901e-05,
1800
+ "learning_rate": 8.680902777777779e-06,
1801
+ "loss": 0.0129,
1802
+ "step": 119000
1803
+ },
1804
+ {
1805
+ "epoch": 14.9375,
1806
+ "grad_norm": 0.0018387527670711279,
1807
+ "learning_rate": 8.507291666666667e-06,
1808
+ "loss": 0.0117,
1809
+ "step": 119500
1810
+ },
1811
+ {
1812
+ "epoch": 15.0,
1813
+ "grad_norm": 3.0822722846268746e-11,
1814
+ "learning_rate": 8.333680555555556e-06,
1815
+ "loss": 0.0289,
1816
+ "step": 120000
1817
+ },
1818
+ {
1819
+ "epoch": 15.0,
1820
+ "eval_loss": 0.4116508662700653,
1821
+ "eval_pearson": 0.9338347129537201,
1822
+ "eval_runtime": 52.0977,
1823
+ "eval_samples_per_second": 38.389,
1824
+ "eval_steps_per_second": 19.195,
1825
+ "step": 120000
1826
+ },
1827
+ {
1828
+ "epoch": 15.0625,
1829
+ "grad_norm": 0.001994462450966239,
1830
+ "learning_rate": 8.160069444444444e-06,
1831
+ "loss": 0.0078,
1832
+ "step": 120500
1833
+ },
1834
+ {
1835
+ "epoch": 15.125,
1836
+ "grad_norm": 3.360041411770709e-10,
1837
+ "learning_rate": 7.986458333333334e-06,
1838
+ "loss": 0.0157,
1839
+ "step": 121000
1840
+ },
1841
+ {
1842
+ "epoch": 15.1875,
1843
+ "grad_norm": 9.282373980568082e-07,
1844
+ "learning_rate": 7.812847222222222e-06,
1845
+ "loss": 0.0078,
1846
+ "step": 121500
1847
+ },
1848
+ {
1849
+ "epoch": 15.25,
1850
+ "grad_norm": 1.6110238698630042e-09,
1851
+ "learning_rate": 7.639236111111112e-06,
1852
+ "loss": 0.026,
1853
+ "step": 122000
1854
+ },
1855
+ {
1856
+ "epoch": 15.3125,
1857
+ "grad_norm": 2.1387499145930633e-05,
1858
+ "learning_rate": 7.465624999999999e-06,
1859
+ "loss": 0.0182,
1860
+ "step": 122500
1861
+ },
1862
+ {
1863
+ "epoch": 15.375,
1864
+ "grad_norm": 5.649494067005989e-11,
1865
+ "learning_rate": 7.292013888888889e-06,
1866
+ "loss": 0.0106,
1867
+ "step": 123000
1868
+ },
1869
+ {
1870
+ "epoch": 15.4375,
1871
+ "grad_norm": 0.008713332004845142,
1872
+ "learning_rate": 7.118402777777778e-06,
1873
+ "loss": 0.0361,
1874
+ "step": 123500
1875
+ },
1876
+ {
1877
+ "epoch": 15.5,
1878
+ "grad_norm": 1.6483255649291095e-08,
1879
+ "learning_rate": 6.944791666666667e-06,
1880
+ "loss": 0.0187,
1881
+ "step": 124000
1882
+ },
1883
+ {
1884
+ "epoch": 15.5625,
1885
+ "grad_norm": 0.002335034077987075,
1886
+ "learning_rate": 6.7711805555555566e-06,
1887
+ "loss": 0.0055,
1888
+ "step": 124500
1889
+ },
1890
+ {
1891
+ "epoch": 15.625,
1892
+ "grad_norm": 0.03660840913653374,
1893
+ "learning_rate": 6.597569444444445e-06,
1894
+ "loss": 0.0327,
1895
+ "step": 125000
1896
+ },
1897
+ {
1898
+ "epoch": 15.6875,
1899
+ "grad_norm": 1.491520379204303e-06,
1900
+ "learning_rate": 6.423958333333334e-06,
1901
+ "loss": 0.021,
1902
+ "step": 125500
1903
+ },
1904
+ {
1905
+ "epoch": 15.75,
1906
+ "grad_norm": 1.702046326101936e-08,
1907
+ "learning_rate": 6.250347222222222e-06,
1908
+ "loss": 0.0192,
1909
+ "step": 126000
1910
+ },
1911
+ {
1912
+ "epoch": 15.8125,
1913
+ "grad_norm": 4.671832812164212e-06,
1914
+ "learning_rate": 6.076736111111111e-06,
1915
+ "loss": 0.0218,
1916
+ "step": 126500
1917
+ },
1918
+ {
1919
+ "epoch": 15.875,
1920
+ "grad_norm": 3.007305167557206e-06,
1921
+ "learning_rate": 5.903125e-06,
1922
+ "loss": 0.0071,
1923
+ "step": 127000
1924
+ },
1925
+ {
1926
+ "epoch": 15.9375,
1927
+ "grad_norm": 0.00012980301107745618,
1928
+ "learning_rate": 5.7295138888888894e-06,
1929
+ "loss": 0.0128,
1930
+ "step": 127500
1931
+ },
1932
+ {
1933
+ "epoch": 16.0,
1934
+ "grad_norm": 4.560336890335748e-07,
1935
+ "learning_rate": 5.555902777777778e-06,
1936
+ "loss": 0.0095,
1937
+ "step": 128000
1938
+ },
1939
+ {
1940
+ "epoch": 16.0,
1941
+ "eval_loss": 0.39633870124816895,
1942
+ "eval_pearson": 0.9361489441284587,
1943
+ "eval_runtime": 52.1321,
1944
+ "eval_samples_per_second": 38.364,
1945
+ "eval_steps_per_second": 19.182,
1946
+ "step": 128000
1947
+ },
1948
+ {
1949
+ "epoch": 16.0625,
1950
+ "grad_norm": 4.1626062596833435e-09,
1951
+ "learning_rate": 5.382291666666667e-06,
1952
+ "loss": 0.0022,
1953
+ "step": 128500
1954
+ },
1955
+ {
1956
+ "epoch": 16.125,
1957
+ "grad_norm": 0.001842322526499629,
1958
+ "learning_rate": 5.208680555555556e-06,
1959
+ "loss": 0.0141,
1960
+ "step": 129000
1961
+ },
1962
+ {
1963
+ "epoch": 16.1875,
1964
+ "grad_norm": 3.6366621714023495e-08,
1965
+ "learning_rate": 5.035069444444444e-06,
1966
+ "loss": 0.0233,
1967
+ "step": 129500
1968
+ },
1969
+ {
1970
+ "epoch": 16.25,
1971
+ "grad_norm": 1.9658939436340006e-06,
1972
+ "learning_rate": 4.861458333333334e-06,
1973
+ "loss": 0.0049,
1974
+ "step": 130000
1975
+ },
1976
+ {
1977
+ "epoch": 16.3125,
1978
+ "grad_norm": 8.618873835075647e-06,
1979
+ "learning_rate": 4.687847222222222e-06,
1980
+ "loss": 0.0038,
1981
+ "step": 130500
1982
+ },
1983
+ {
1984
+ "epoch": 16.375,
1985
+ "grad_norm": 3.656549552033539e-08,
1986
+ "learning_rate": 4.514236111111111e-06,
1987
+ "loss": 0.0025,
1988
+ "step": 131000
1989
+ },
1990
+ {
1991
+ "epoch": 16.4375,
1992
+ "grad_norm": 3.9857341107563116e-06,
1993
+ "learning_rate": 4.3406250000000005e-06,
1994
+ "loss": 0.0113,
1995
+ "step": 131500
1996
+ },
1997
+ {
1998
+ "epoch": 16.5,
1999
+ "grad_norm": 1.3211584359851258e-07,
2000
+ "learning_rate": 4.167013888888889e-06,
2001
+ "loss": 0.0091,
2002
+ "step": 132000
2003
+ },
2004
+ {
2005
+ "epoch": 16.5625,
2006
+ "grad_norm": 0.012276459485292435,
2007
+ "learning_rate": 3.993402777777778e-06,
2008
+ "loss": 0.0068,
2009
+ "step": 132500
2010
+ },
2011
+ {
2012
+ "epoch": 16.625,
2013
+ "grad_norm": 0.0287026297301054,
2014
+ "learning_rate": 3.819791666666667e-06,
2015
+ "loss": 0.0386,
2016
+ "step": 133000
2017
+ },
2018
+ {
2019
+ "epoch": 16.6875,
2020
+ "grad_norm": 1.2811213423447043e-07,
2021
+ "learning_rate": 3.6461805555555556e-06,
2022
+ "loss": 0.0,
2023
+ "step": 133500
2024
+ },
2025
+ {
2026
+ "epoch": 16.75,
2027
+ "grad_norm": 3.6252565394079284e-08,
2028
+ "learning_rate": 3.4725694444444442e-06,
2029
+ "loss": 0.0048,
2030
+ "step": 134000
2031
+ },
2032
+ {
2033
+ "epoch": 16.8125,
2034
+ "grad_norm": 0.007136507425457239,
2035
+ "learning_rate": 3.2989583333333338e-06,
2036
+ "loss": 0.0093,
2037
+ "step": 134500
2038
+ },
2039
+ {
2040
+ "epoch": 16.875,
2041
+ "grad_norm": 0.00022970048303250223,
2042
+ "learning_rate": 3.1253472222222224e-06,
2043
+ "loss": 0.0201,
2044
+ "step": 135000
2045
+ },
2046
+ {
2047
+ "epoch": 16.9375,
2048
+ "grad_norm": 1.450917920919892e-06,
2049
+ "learning_rate": 2.9517361111111115e-06,
2050
+ "loss": 0.0207,
2051
+ "step": 135500
2052
+ },
2053
+ {
2054
+ "epoch": 17.0,
2055
+ "grad_norm": 4.926808472305311e-08,
2056
+ "learning_rate": 2.778125e-06,
2057
+ "loss": 0.0254,
2058
+ "step": 136000
2059
+ },
2060
+ {
2061
+ "epoch": 17.0,
2062
+ "eval_loss": 0.36975476145744324,
2063
+ "eval_pearson": 0.9265418354468642,
2064
+ "eval_runtime": 52.4565,
2065
+ "eval_samples_per_second": 38.127,
2066
+ "eval_steps_per_second": 19.063,
2067
+ "step": 136000
2068
+ }
2069
+ ],
2070
+ "logging_steps": 500,
2071
+ "max_steps": 144000,
2072
+ "num_input_tokens_seen": 0,
2073
+ "num_train_epochs": 18,
2074
+ "save_steps": 500,
2075
+ "stateful_callbacks": {
2076
+ "TrainerControl": {
2077
+ "args": {
2078
+ "should_epoch_stop": false,
2079
+ "should_evaluate": false,
2080
+ "should_log": false,
2081
+ "should_save": true,
2082
+ "should_training_stop": false
2083
+ },
2084
+ "attributes": {}
2085
+ }
2086
+ },
2087
+ "total_flos": 1.2524419411141018e+17,
2088
+ "train_batch_size": 2,
2089
+ "trial_name": null,
2090
+ "trial_params": null
2091
+ }
checkpoints_ia3_llama_class/checkpoint-136000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54e6c46c9dda9757cc094892dfdf420dce55879ca8959ffad52b273b74ea2b4a
3
+ size 5368
checkpoints_ia3_llama_class/checkpoint-144000/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Llama-3.2-3B-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 0.15.2
checkpoints_ia3_llama_class/checkpoint-144000/adapter_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Llama-3.2-3B-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": 8,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.1,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": [
22
+ "classifier",
23
+ "score"
24
+ ],
25
+ "peft_type": "LORA",
26
+ "r": 8,
27
+ "rank_pattern": {},
28
+ "revision": null,
29
+ "target_modules": [
30
+ "v_proj",
31
+ "k_proj"
32
+ ],
33
+ "task_type": "SEQ_CLS",
34
+ "trainable_token_indices": null,
35
+ "use_dora": false,
36
+ "use_rslora": false
37
+ }
checkpoints_ia3_llama_class/checkpoint-144000/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c260cda8ceb59e4b14aaa1db25365a37c4ccd09cd58d0d7bdebfb806b87829e4
3
+ size 7428608
checkpoints_ia3_llama_class/checkpoint-144000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:074d7973372a5d7ea23bd9d315d5331f985720ceca67d2282a301f3269e6b4a3
3
+ size 14922618
checkpoints_ia3_llama_class/checkpoint-144000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8903584982ed966ddb3e790f06922cb8ef36373d8f73613be12e092682b3fc44
3
+ size 14244
checkpoints_ia3_llama_class/checkpoint-144000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99214dec9930361c48ca8025d8543340ff8f93d4fd960d45e89f804ee70b676c
3
+ size 1064
checkpoints_ia3_llama_class/checkpoint-144000/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
+ }
checkpoints_ia3_llama_class/checkpoint-144000/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb55d3601efe3b76b75c99d892f669a53d23df00ee8bac2e67a72152ae2083cd
3
+ size 17210017
checkpoints_ia3_llama_class/checkpoint-144000/tokenizer_config.json ADDED
@@ -0,0 +1,2065 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "128000": {
5
+ "content": "<|begin_of_text|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "128001": {
13
+ "content": "<|end_of_text|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "128002": {
21
+ "content": "<|reserved_special_token_0|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "128003": {
29
+ "content": "<|reserved_special_token_1|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "128004": {
37
+ "content": "<|finetune_right_pad_id|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "128005": {
45
+ "content": "<|reserved_special_token_2|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "128006": {
53
+ "content": "<|start_header_id|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "128007": {
61
+ "content": "<|end_header_id|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "128008": {
69
+ "content": "<|eom_id|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "128009": {
77
+ "content": "<|eot_id|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "128010": {
85
+ "content": "<|python_tag|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "128011": {
93
+ "content": "<|reserved_special_token_3|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "128012": {
101
+ "content": "<|reserved_special_token_4|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "128013": {
109
+ "content": "<|reserved_special_token_5|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "128014": {
117
+ "content": "<|reserved_special_token_6|>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "128015": {
125
+ "content": "<|reserved_special_token_7|>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "128016": {
133
+ "content": "<|reserved_special_token_8|>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "128017": {
141
+ "content": "<|reserved_special_token_9|>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "128018": {
149
+ "content": "<|reserved_special_token_10|>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "128019": {
157
+ "content": "<|reserved_special_token_11|>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "128020": {
165
+ "content": "<|reserved_special_token_12|>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "128021": {
173
+ "content": "<|reserved_special_token_13|>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "128022": {
181
+ "content": "<|reserved_special_token_14|>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "128023": {
189
+ "content": "<|reserved_special_token_15|>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "128024": {
197
+ "content": "<|reserved_special_token_16|>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "128025": {
205
+ "content": "<|reserved_special_token_17|>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "128026": {
213
+ "content": "<|reserved_special_token_18|>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "128027": {
221
+ "content": "<|reserved_special_token_19|>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "128028": {
229
+ "content": "<|reserved_special_token_20|>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "128029": {
237
+ "content": "<|reserved_special_token_21|>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "128030": {
245
+ "content": "<|reserved_special_token_22|>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "128031": {
253
+ "content": "<|reserved_special_token_23|>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "128032": {
261
+ "content": "<|reserved_special_token_24|>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "128033": {
269
+ "content": "<|reserved_special_token_25|>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "128034": {
277
+ "content": "<|reserved_special_token_26|>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "128035": {
285
+ "content": "<|reserved_special_token_27|>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "128036": {
293
+ "content": "<|reserved_special_token_28|>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "128037": {
301
+ "content": "<|reserved_special_token_29|>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "128038": {
309
+ "content": "<|reserved_special_token_30|>",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "128039": {
317
+ "content": "<|reserved_special_token_31|>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "128040": {
325
+ "content": "<|reserved_special_token_32|>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "128041": {
333
+ "content": "<|reserved_special_token_33|>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "128042": {
341
+ "content": "<|reserved_special_token_34|>",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "128043": {
349
+ "content": "<|reserved_special_token_35|>",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "128044": {
357
+ "content": "<|reserved_special_token_36|>",
358
+ "lstrip": false,
359
+ "normalized": false,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "128045": {
365
+ "content": "<|reserved_special_token_37|>",
366
+ "lstrip": false,
367
+ "normalized": false,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "128046": {
373
+ "content": "<|reserved_special_token_38|>",
374
+ "lstrip": false,
375
+ "normalized": false,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "128047": {
381
+ "content": "<|reserved_special_token_39|>",
382
+ "lstrip": false,
383
+ "normalized": false,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "128048": {
389
+ "content": "<|reserved_special_token_40|>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "128049": {
397
+ "content": "<|reserved_special_token_41|>",
398
+ "lstrip": false,
399
+ "normalized": false,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "128050": {
405
+ "content": "<|reserved_special_token_42|>",
406
+ "lstrip": false,
407
+ "normalized": false,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "128051": {
413
+ "content": "<|reserved_special_token_43|>",
414
+ "lstrip": false,
415
+ "normalized": false,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "128052": {
421
+ "content": "<|reserved_special_token_44|>",
422
+ "lstrip": false,
423
+ "normalized": false,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "128053": {
429
+ "content": "<|reserved_special_token_45|>",
430
+ "lstrip": false,
431
+ "normalized": false,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "128054": {
437
+ "content": "<|reserved_special_token_46|>",
438
+ "lstrip": false,
439
+ "normalized": false,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "128055": {
445
+ "content": "<|reserved_special_token_47|>",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "128056": {
453
+ "content": "<|reserved_special_token_48|>",
454
+ "lstrip": false,
455
+ "normalized": false,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "128057": {
461
+ "content": "<|reserved_special_token_49|>",
462
+ "lstrip": false,
463
+ "normalized": false,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "128058": {
469
+ "content": "<|reserved_special_token_50|>",
470
+ "lstrip": false,
471
+ "normalized": false,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "128059": {
477
+ "content": "<|reserved_special_token_51|>",
478
+ "lstrip": false,
479
+ "normalized": false,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "128060": {
485
+ "content": "<|reserved_special_token_52|>",
486
+ "lstrip": false,
487
+ "normalized": false,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "128061": {
493
+ "content": "<|reserved_special_token_53|>",
494
+ "lstrip": false,
495
+ "normalized": false,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "128062": {
501
+ "content": "<|reserved_special_token_54|>",
502
+ "lstrip": false,
503
+ "normalized": false,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "128063": {
509
+ "content": "<|reserved_special_token_55|>",
510
+ "lstrip": false,
511
+ "normalized": false,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "128064": {
517
+ "content": "<|reserved_special_token_56|>",
518
+ "lstrip": false,
519
+ "normalized": false,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "128065": {
525
+ "content": "<|reserved_special_token_57|>",
526
+ "lstrip": false,
527
+ "normalized": false,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "128066": {
533
+ "content": "<|reserved_special_token_58|>",
534
+ "lstrip": false,
535
+ "normalized": false,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "128067": {
541
+ "content": "<|reserved_special_token_59|>",
542
+ "lstrip": false,
543
+ "normalized": false,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "128068": {
549
+ "content": "<|reserved_special_token_60|>",
550
+ "lstrip": false,
551
+ "normalized": false,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "128069": {
557
+ "content": "<|reserved_special_token_61|>",
558
+ "lstrip": false,
559
+ "normalized": false,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "128070": {
565
+ "content": "<|reserved_special_token_62|>",
566
+ "lstrip": false,
567
+ "normalized": false,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "128071": {
573
+ "content": "<|reserved_special_token_63|>",
574
+ "lstrip": false,
575
+ "normalized": false,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "128072": {
581
+ "content": "<|reserved_special_token_64|>",
582
+ "lstrip": false,
583
+ "normalized": false,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "128073": {
589
+ "content": "<|reserved_special_token_65|>",
590
+ "lstrip": false,
591
+ "normalized": false,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "128074": {
597
+ "content": "<|reserved_special_token_66|>",
598
+ "lstrip": false,
599
+ "normalized": false,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "128075": {
605
+ "content": "<|reserved_special_token_67|>",
606
+ "lstrip": false,
607
+ "normalized": false,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "128076": {
613
+ "content": "<|reserved_special_token_68|>",
614
+ "lstrip": false,
615
+ "normalized": false,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "128077": {
621
+ "content": "<|reserved_special_token_69|>",
622
+ "lstrip": false,
623
+ "normalized": false,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "128078": {
629
+ "content": "<|reserved_special_token_70|>",
630
+ "lstrip": false,
631
+ "normalized": false,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "128079": {
637
+ "content": "<|reserved_special_token_71|>",
638
+ "lstrip": false,
639
+ "normalized": false,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "128080": {
645
+ "content": "<|reserved_special_token_72|>",
646
+ "lstrip": false,
647
+ "normalized": false,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "128081": {
653
+ "content": "<|reserved_special_token_73|>",
654
+ "lstrip": false,
655
+ "normalized": false,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "128082": {
661
+ "content": "<|reserved_special_token_74|>",
662
+ "lstrip": false,
663
+ "normalized": false,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "128083": {
669
+ "content": "<|reserved_special_token_75|>",
670
+ "lstrip": false,
671
+ "normalized": false,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "128084": {
677
+ "content": "<|reserved_special_token_76|>",
678
+ "lstrip": false,
679
+ "normalized": false,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "128085": {
685
+ "content": "<|reserved_special_token_77|>",
686
+ "lstrip": false,
687
+ "normalized": false,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "128086": {
693
+ "content": "<|reserved_special_token_78|>",
694
+ "lstrip": false,
695
+ "normalized": false,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "128087": {
701
+ "content": "<|reserved_special_token_79|>",
702
+ "lstrip": false,
703
+ "normalized": false,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "128088": {
709
+ "content": "<|reserved_special_token_80|>",
710
+ "lstrip": false,
711
+ "normalized": false,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "128089": {
717
+ "content": "<|reserved_special_token_81|>",
718
+ "lstrip": false,
719
+ "normalized": false,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "128090": {
725
+ "content": "<|reserved_special_token_82|>",
726
+ "lstrip": false,
727
+ "normalized": false,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "128091": {
733
+ "content": "<|reserved_special_token_83|>",
734
+ "lstrip": false,
735
+ "normalized": false,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "128092": {
741
+ "content": "<|reserved_special_token_84|>",
742
+ "lstrip": false,
743
+ "normalized": false,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "128093": {
749
+ "content": "<|reserved_special_token_85|>",
750
+ "lstrip": false,
751
+ "normalized": false,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "128094": {
757
+ "content": "<|reserved_special_token_86|>",
758
+ "lstrip": false,
759
+ "normalized": false,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "128095": {
765
+ "content": "<|reserved_special_token_87|>",
766
+ "lstrip": false,
767
+ "normalized": false,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "128096": {
773
+ "content": "<|reserved_special_token_88|>",
774
+ "lstrip": false,
775
+ "normalized": false,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "128097": {
781
+ "content": "<|reserved_special_token_89|>",
782
+ "lstrip": false,
783
+ "normalized": false,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "128098": {
789
+ "content": "<|reserved_special_token_90|>",
790
+ "lstrip": false,
791
+ "normalized": false,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "128099": {
797
+ "content": "<|reserved_special_token_91|>",
798
+ "lstrip": false,
799
+ "normalized": false,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "128100": {
805
+ "content": "<|reserved_special_token_92|>",
806
+ "lstrip": false,
807
+ "normalized": false,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "128101": {
813
+ "content": "<|reserved_special_token_93|>",
814
+ "lstrip": false,
815
+ "normalized": false,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "128102": {
821
+ "content": "<|reserved_special_token_94|>",
822
+ "lstrip": false,
823
+ "normalized": false,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": true
827
+ },
828
+ "128103": {
829
+ "content": "<|reserved_special_token_95|>",
830
+ "lstrip": false,
831
+ "normalized": false,
832
+ "rstrip": false,
833
+ "single_word": false,
834
+ "special": true
835
+ },
836
+ "128104": {
837
+ "content": "<|reserved_special_token_96|>",
838
+ "lstrip": false,
839
+ "normalized": false,
840
+ "rstrip": false,
841
+ "single_word": false,
842
+ "special": true
843
+ },
844
+ "128105": {
845
+ "content": "<|reserved_special_token_97|>",
846
+ "lstrip": false,
847
+ "normalized": false,
848
+ "rstrip": false,
849
+ "single_word": false,
850
+ "special": true
851
+ },
852
+ "128106": {
853
+ "content": "<|reserved_special_token_98|>",
854
+ "lstrip": false,
855
+ "normalized": false,
856
+ "rstrip": false,
857
+ "single_word": false,
858
+ "special": true
859
+ },
860
+ "128107": {
861
+ "content": "<|reserved_special_token_99|>",
862
+ "lstrip": false,
863
+ "normalized": false,
864
+ "rstrip": false,
865
+ "single_word": false,
866
+ "special": true
867
+ },
868
+ "128108": {
869
+ "content": "<|reserved_special_token_100|>",
870
+ "lstrip": false,
871
+ "normalized": false,
872
+ "rstrip": false,
873
+ "single_word": false,
874
+ "special": true
875
+ },
876
+ "128109": {
877
+ "content": "<|reserved_special_token_101|>",
878
+ "lstrip": false,
879
+ "normalized": false,
880
+ "rstrip": false,
881
+ "single_word": false,
882
+ "special": true
883
+ },
884
+ "128110": {
885
+ "content": "<|reserved_special_token_102|>",
886
+ "lstrip": false,
887
+ "normalized": false,
888
+ "rstrip": false,
889
+ "single_word": false,
890
+ "special": true
891
+ },
892
+ "128111": {
893
+ "content": "<|reserved_special_token_103|>",
894
+ "lstrip": false,
895
+ "normalized": false,
896
+ "rstrip": false,
897
+ "single_word": false,
898
+ "special": true
899
+ },
900
+ "128112": {
901
+ "content": "<|reserved_special_token_104|>",
902
+ "lstrip": false,
903
+ "normalized": false,
904
+ "rstrip": false,
905
+ "single_word": false,
906
+ "special": true
907
+ },
908
+ "128113": {
909
+ "content": "<|reserved_special_token_105|>",
910
+ "lstrip": false,
911
+ "normalized": false,
912
+ "rstrip": false,
913
+ "single_word": false,
914
+ "special": true
915
+ },
916
+ "128114": {
917
+ "content": "<|reserved_special_token_106|>",
918
+ "lstrip": false,
919
+ "normalized": false,
920
+ "rstrip": false,
921
+ "single_word": false,
922
+ "special": true
923
+ },
924
+ "128115": {
925
+ "content": "<|reserved_special_token_107|>",
926
+ "lstrip": false,
927
+ "normalized": false,
928
+ "rstrip": false,
929
+ "single_word": false,
930
+ "special": true
931
+ },
932
+ "128116": {
933
+ "content": "<|reserved_special_token_108|>",
934
+ "lstrip": false,
935
+ "normalized": false,
936
+ "rstrip": false,
937
+ "single_word": false,
938
+ "special": true
939
+ },
940
+ "128117": {
941
+ "content": "<|reserved_special_token_109|>",
942
+ "lstrip": false,
943
+ "normalized": false,
944
+ "rstrip": false,
945
+ "single_word": false,
946
+ "special": true
947
+ },
948
+ "128118": {
949
+ "content": "<|reserved_special_token_110|>",
950
+ "lstrip": false,
951
+ "normalized": false,
952
+ "rstrip": false,
953
+ "single_word": false,
954
+ "special": true
955
+ },
956
+ "128119": {
957
+ "content": "<|reserved_special_token_111|>",
958
+ "lstrip": false,
959
+ "normalized": false,
960
+ "rstrip": false,
961
+ "single_word": false,
962
+ "special": true
963
+ },
964
+ "128120": {
965
+ "content": "<|reserved_special_token_112|>",
966
+ "lstrip": false,
967
+ "normalized": false,
968
+ "rstrip": false,
969
+ "single_word": false,
970
+ "special": true
971
+ },
972
+ "128121": {
973
+ "content": "<|reserved_special_token_113|>",
974
+ "lstrip": false,
975
+ "normalized": false,
976
+ "rstrip": false,
977
+ "single_word": false,
978
+ "special": true
979
+ },
980
+ "128122": {
981
+ "content": "<|reserved_special_token_114|>",
982
+ "lstrip": false,
983
+ "normalized": false,
984
+ "rstrip": false,
985
+ "single_word": false,
986
+ "special": true
987
+ },
988
+ "128123": {
989
+ "content": "<|reserved_special_token_115|>",
990
+ "lstrip": false,
991
+ "normalized": false,
992
+ "rstrip": false,
993
+ "single_word": false,
994
+ "special": true
995
+ },
996
+ "128124": {
997
+ "content": "<|reserved_special_token_116|>",
998
+ "lstrip": false,
999
+ "normalized": false,
1000
+ "rstrip": false,
1001
+ "single_word": false,
1002
+ "special": true
1003
+ },
1004
+ "128125": {
1005
+ "content": "<|reserved_special_token_117|>",
1006
+ "lstrip": false,
1007
+ "normalized": false,
1008
+ "rstrip": false,
1009
+ "single_word": false,
1010
+ "special": true
1011
+ },
1012
+ "128126": {
1013
+ "content": "<|reserved_special_token_118|>",
1014
+ "lstrip": false,
1015
+ "normalized": false,
1016
+ "rstrip": false,
1017
+ "single_word": false,
1018
+ "special": true
1019
+ },
1020
+ "128127": {
1021
+ "content": "<|reserved_special_token_119|>",
1022
+ "lstrip": false,
1023
+ "normalized": false,
1024
+ "rstrip": false,
1025
+ "single_word": false,
1026
+ "special": true
1027
+ },
1028
+ "128128": {
1029
+ "content": "<|reserved_special_token_120|>",
1030
+ "lstrip": false,
1031
+ "normalized": false,
1032
+ "rstrip": false,
1033
+ "single_word": false,
1034
+ "special": true
1035
+ },
1036
+ "128129": {
1037
+ "content": "<|reserved_special_token_121|>",
1038
+ "lstrip": false,
1039
+ "normalized": false,
1040
+ "rstrip": false,
1041
+ "single_word": false,
1042
+ "special": true
1043
+ },
1044
+ "128130": {
1045
+ "content": "<|reserved_special_token_122|>",
1046
+ "lstrip": false,
1047
+ "normalized": false,
1048
+ "rstrip": false,
1049
+ "single_word": false,
1050
+ "special": true
1051
+ },
1052
+ "128131": {
1053
+ "content": "<|reserved_special_token_123|>",
1054
+ "lstrip": false,
1055
+ "normalized": false,
1056
+ "rstrip": false,
1057
+ "single_word": false,
1058
+ "special": true
1059
+ },
1060
+ "128132": {
1061
+ "content": "<|reserved_special_token_124|>",
1062
+ "lstrip": false,
1063
+ "normalized": false,
1064
+ "rstrip": false,
1065
+ "single_word": false,
1066
+ "special": true
1067
+ },
1068
+ "128133": {
1069
+ "content": "<|reserved_special_token_125|>",
1070
+ "lstrip": false,
1071
+ "normalized": false,
1072
+ "rstrip": false,
1073
+ "single_word": false,
1074
+ "special": true
1075
+ },
1076
+ "128134": {
1077
+ "content": "<|reserved_special_token_126|>",
1078
+ "lstrip": false,
1079
+ "normalized": false,
1080
+ "rstrip": false,
1081
+ "single_word": false,
1082
+ "special": true
1083
+ },
1084
+ "128135": {
1085
+ "content": "<|reserved_special_token_127|>",
1086
+ "lstrip": false,
1087
+ "normalized": false,
1088
+ "rstrip": false,
1089
+ "single_word": false,
1090
+ "special": true
1091
+ },
1092
+ "128136": {
1093
+ "content": "<|reserved_special_token_128|>",
1094
+ "lstrip": false,
1095
+ "normalized": false,
1096
+ "rstrip": false,
1097
+ "single_word": false,
1098
+ "special": true
1099
+ },
1100
+ "128137": {
1101
+ "content": "<|reserved_special_token_129|>",
1102
+ "lstrip": false,
1103
+ "normalized": false,
1104
+ "rstrip": false,
1105
+ "single_word": false,
1106
+ "special": true
1107
+ },
1108
+ "128138": {
1109
+ "content": "<|reserved_special_token_130|>",
1110
+ "lstrip": false,
1111
+ "normalized": false,
1112
+ "rstrip": false,
1113
+ "single_word": false,
1114
+ "special": true
1115
+ },
1116
+ "128139": {
1117
+ "content": "<|reserved_special_token_131|>",
1118
+ "lstrip": false,
1119
+ "normalized": false,
1120
+ "rstrip": false,
1121
+ "single_word": false,
1122
+ "special": true
1123
+ },
1124
+ "128140": {
1125
+ "content": "<|reserved_special_token_132|>",
1126
+ "lstrip": false,
1127
+ "normalized": false,
1128
+ "rstrip": false,
1129
+ "single_word": false,
1130
+ "special": true
1131
+ },
1132
+ "128141": {
1133
+ "content": "<|reserved_special_token_133|>",
1134
+ "lstrip": false,
1135
+ "normalized": false,
1136
+ "rstrip": false,
1137
+ "single_word": false,
1138
+ "special": true
1139
+ },
1140
+ "128142": {
1141
+ "content": "<|reserved_special_token_134|>",
1142
+ "lstrip": false,
1143
+ "normalized": false,
1144
+ "rstrip": false,
1145
+ "single_word": false,
1146
+ "special": true
1147
+ },
1148
+ "128143": {
1149
+ "content": "<|reserved_special_token_135|>",
1150
+ "lstrip": false,
1151
+ "normalized": false,
1152
+ "rstrip": false,
1153
+ "single_word": false,
1154
+ "special": true
1155
+ },
1156
+ "128144": {
1157
+ "content": "<|reserved_special_token_136|>",
1158
+ "lstrip": false,
1159
+ "normalized": false,
1160
+ "rstrip": false,
1161
+ "single_word": false,
1162
+ "special": true
1163
+ },
1164
+ "128145": {
1165
+ "content": "<|reserved_special_token_137|>",
1166
+ "lstrip": false,
1167
+ "normalized": false,
1168
+ "rstrip": false,
1169
+ "single_word": false,
1170
+ "special": true
1171
+ },
1172
+ "128146": {
1173
+ "content": "<|reserved_special_token_138|>",
1174
+ "lstrip": false,
1175
+ "normalized": false,
1176
+ "rstrip": false,
1177
+ "single_word": false,
1178
+ "special": true
1179
+ },
1180
+ "128147": {
1181
+ "content": "<|reserved_special_token_139|>",
1182
+ "lstrip": false,
1183
+ "normalized": false,
1184
+ "rstrip": false,
1185
+ "single_word": false,
1186
+ "special": true
1187
+ },
1188
+ "128148": {
1189
+ "content": "<|reserved_special_token_140|>",
1190
+ "lstrip": false,
1191
+ "normalized": false,
1192
+ "rstrip": false,
1193
+ "single_word": false,
1194
+ "special": true
1195
+ },
1196
+ "128149": {
1197
+ "content": "<|reserved_special_token_141|>",
1198
+ "lstrip": false,
1199
+ "normalized": false,
1200
+ "rstrip": false,
1201
+ "single_word": false,
1202
+ "special": true
1203
+ },
1204
+ "128150": {
1205
+ "content": "<|reserved_special_token_142|>",
1206
+ "lstrip": false,
1207
+ "normalized": false,
1208
+ "rstrip": false,
1209
+ "single_word": false,
1210
+ "special": true
1211
+ },
1212
+ "128151": {
1213
+ "content": "<|reserved_special_token_143|>",
1214
+ "lstrip": false,
1215
+ "normalized": false,
1216
+ "rstrip": false,
1217
+ "single_word": false,
1218
+ "special": true
1219
+ },
1220
+ "128152": {
1221
+ "content": "<|reserved_special_token_144|>",
1222
+ "lstrip": false,
1223
+ "normalized": false,
1224
+ "rstrip": false,
1225
+ "single_word": false,
1226
+ "special": true
1227
+ },
1228
+ "128153": {
1229
+ "content": "<|reserved_special_token_145|>",
1230
+ "lstrip": false,
1231
+ "normalized": false,
1232
+ "rstrip": false,
1233
+ "single_word": false,
1234
+ "special": true
1235
+ },
1236
+ "128154": {
1237
+ "content": "<|reserved_special_token_146|>",
1238
+ "lstrip": false,
1239
+ "normalized": false,
1240
+ "rstrip": false,
1241
+ "single_word": false,
1242
+ "special": true
1243
+ },
1244
+ "128155": {
1245
+ "content": "<|reserved_special_token_147|>",
1246
+ "lstrip": false,
1247
+ "normalized": false,
1248
+ "rstrip": false,
1249
+ "single_word": false,
1250
+ "special": true
1251
+ },
1252
+ "128156": {
1253
+ "content": "<|reserved_special_token_148|>",
1254
+ "lstrip": false,
1255
+ "normalized": false,
1256
+ "rstrip": false,
1257
+ "single_word": false,
1258
+ "special": true
1259
+ },
1260
+ "128157": {
1261
+ "content": "<|reserved_special_token_149|>",
1262
+ "lstrip": false,
1263
+ "normalized": false,
1264
+ "rstrip": false,
1265
+ "single_word": false,
1266
+ "special": true
1267
+ },
1268
+ "128158": {
1269
+ "content": "<|reserved_special_token_150|>",
1270
+ "lstrip": false,
1271
+ "normalized": false,
1272
+ "rstrip": false,
1273
+ "single_word": false,
1274
+ "special": true
1275
+ },
1276
+ "128159": {
1277
+ "content": "<|reserved_special_token_151|>",
1278
+ "lstrip": false,
1279
+ "normalized": false,
1280
+ "rstrip": false,
1281
+ "single_word": false,
1282
+ "special": true
1283
+ },
1284
+ "128160": {
1285
+ "content": "<|reserved_special_token_152|>",
1286
+ "lstrip": false,
1287
+ "normalized": false,
1288
+ "rstrip": false,
1289
+ "single_word": false,
1290
+ "special": true
1291
+ },
1292
+ "128161": {
1293
+ "content": "<|reserved_special_token_153|>",
1294
+ "lstrip": false,
1295
+ "normalized": false,
1296
+ "rstrip": false,
1297
+ "single_word": false,
1298
+ "special": true
1299
+ },
1300
+ "128162": {
1301
+ "content": "<|reserved_special_token_154|>",
1302
+ "lstrip": false,
1303
+ "normalized": false,
1304
+ "rstrip": false,
1305
+ "single_word": false,
1306
+ "special": true
1307
+ },
1308
+ "128163": {
1309
+ "content": "<|reserved_special_token_155|>",
1310
+ "lstrip": false,
1311
+ "normalized": false,
1312
+ "rstrip": false,
1313
+ "single_word": false,
1314
+ "special": true
1315
+ },
1316
+ "128164": {
1317
+ "content": "<|reserved_special_token_156|>",
1318
+ "lstrip": false,
1319
+ "normalized": false,
1320
+ "rstrip": false,
1321
+ "single_word": false,
1322
+ "special": true
1323
+ },
1324
+ "128165": {
1325
+ "content": "<|reserved_special_token_157|>",
1326
+ "lstrip": false,
1327
+ "normalized": false,
1328
+ "rstrip": false,
1329
+ "single_word": false,
1330
+ "special": true
1331
+ },
1332
+ "128166": {
1333
+ "content": "<|reserved_special_token_158|>",
1334
+ "lstrip": false,
1335
+ "normalized": false,
1336
+ "rstrip": false,
1337
+ "single_word": false,
1338
+ "special": true
1339
+ },
1340
+ "128167": {
1341
+ "content": "<|reserved_special_token_159|>",
1342
+ "lstrip": false,
1343
+ "normalized": false,
1344
+ "rstrip": false,
1345
+ "single_word": false,
1346
+ "special": true
1347
+ },
1348
+ "128168": {
1349
+ "content": "<|reserved_special_token_160|>",
1350
+ "lstrip": false,
1351
+ "normalized": false,
1352
+ "rstrip": false,
1353
+ "single_word": false,
1354
+ "special": true
1355
+ },
1356
+ "128169": {
1357
+ "content": "<|reserved_special_token_161|>",
1358
+ "lstrip": false,
1359
+ "normalized": false,
1360
+ "rstrip": false,
1361
+ "single_word": false,
1362
+ "special": true
1363
+ },
1364
+ "128170": {
1365
+ "content": "<|reserved_special_token_162|>",
1366
+ "lstrip": false,
1367
+ "normalized": false,
1368
+ "rstrip": false,
1369
+ "single_word": false,
1370
+ "special": true
1371
+ },
1372
+ "128171": {
1373
+ "content": "<|reserved_special_token_163|>",
1374
+ "lstrip": false,
1375
+ "normalized": false,
1376
+ "rstrip": false,
1377
+ "single_word": false,
1378
+ "special": true
1379
+ },
1380
+ "128172": {
1381
+ "content": "<|reserved_special_token_164|>",
1382
+ "lstrip": false,
1383
+ "normalized": false,
1384
+ "rstrip": false,
1385
+ "single_word": false,
1386
+ "special": true
1387
+ },
1388
+ "128173": {
1389
+ "content": "<|reserved_special_token_165|>",
1390
+ "lstrip": false,
1391
+ "normalized": false,
1392
+ "rstrip": false,
1393
+ "single_word": false,
1394
+ "special": true
1395
+ },
1396
+ "128174": {
1397
+ "content": "<|reserved_special_token_166|>",
1398
+ "lstrip": false,
1399
+ "normalized": false,
1400
+ "rstrip": false,
1401
+ "single_word": false,
1402
+ "special": true
1403
+ },
1404
+ "128175": {
1405
+ "content": "<|reserved_special_token_167|>",
1406
+ "lstrip": false,
1407
+ "normalized": false,
1408
+ "rstrip": false,
1409
+ "single_word": false,
1410
+ "special": true
1411
+ },
1412
+ "128176": {
1413
+ "content": "<|reserved_special_token_168|>",
1414
+ "lstrip": false,
1415
+ "normalized": false,
1416
+ "rstrip": false,
1417
+ "single_word": false,
1418
+ "special": true
1419
+ },
1420
+ "128177": {
1421
+ "content": "<|reserved_special_token_169|>",
1422
+ "lstrip": false,
1423
+ "normalized": false,
1424
+ "rstrip": false,
1425
+ "single_word": false,
1426
+ "special": true
1427
+ },
1428
+ "128178": {
1429
+ "content": "<|reserved_special_token_170|>",
1430
+ "lstrip": false,
1431
+ "normalized": false,
1432
+ "rstrip": false,
1433
+ "single_word": false,
1434
+ "special": true
1435
+ },
1436
+ "128179": {
1437
+ "content": "<|reserved_special_token_171|>",
1438
+ "lstrip": false,
1439
+ "normalized": false,
1440
+ "rstrip": false,
1441
+ "single_word": false,
1442
+ "special": true
1443
+ },
1444
+ "128180": {
1445
+ "content": "<|reserved_special_token_172|>",
1446
+ "lstrip": false,
1447
+ "normalized": false,
1448
+ "rstrip": false,
1449
+ "single_word": false,
1450
+ "special": true
1451
+ },
1452
+ "128181": {
1453
+ "content": "<|reserved_special_token_173|>",
1454
+ "lstrip": false,
1455
+ "normalized": false,
1456
+ "rstrip": false,
1457
+ "single_word": false,
1458
+ "special": true
1459
+ },
1460
+ "128182": {
1461
+ "content": "<|reserved_special_token_174|>",
1462
+ "lstrip": false,
1463
+ "normalized": false,
1464
+ "rstrip": false,
1465
+ "single_word": false,
1466
+ "special": true
1467
+ },
1468
+ "128183": {
1469
+ "content": "<|reserved_special_token_175|>",
1470
+ "lstrip": false,
1471
+ "normalized": false,
1472
+ "rstrip": false,
1473
+ "single_word": false,
1474
+ "special": true
1475
+ },
1476
+ "128184": {
1477
+ "content": "<|reserved_special_token_176|>",
1478
+ "lstrip": false,
1479
+ "normalized": false,
1480
+ "rstrip": false,
1481
+ "single_word": false,
1482
+ "special": true
1483
+ },
1484
+ "128185": {
1485
+ "content": "<|reserved_special_token_177|>",
1486
+ "lstrip": false,
1487
+ "normalized": false,
1488
+ "rstrip": false,
1489
+ "single_word": false,
1490
+ "special": true
1491
+ },
1492
+ "128186": {
1493
+ "content": "<|reserved_special_token_178|>",
1494
+ "lstrip": false,
1495
+ "normalized": false,
1496
+ "rstrip": false,
1497
+ "single_word": false,
1498
+ "special": true
1499
+ },
1500
+ "128187": {
1501
+ "content": "<|reserved_special_token_179|>",
1502
+ "lstrip": false,
1503
+ "normalized": false,
1504
+ "rstrip": false,
1505
+ "single_word": false,
1506
+ "special": true
1507
+ },
1508
+ "128188": {
1509
+ "content": "<|reserved_special_token_180|>",
1510
+ "lstrip": false,
1511
+ "normalized": false,
1512
+ "rstrip": false,
1513
+ "single_word": false,
1514
+ "special": true
1515
+ },
1516
+ "128189": {
1517
+ "content": "<|reserved_special_token_181|>",
1518
+ "lstrip": false,
1519
+ "normalized": false,
1520
+ "rstrip": false,
1521
+ "single_word": false,
1522
+ "special": true
1523
+ },
1524
+ "128190": {
1525
+ "content": "<|reserved_special_token_182|>",
1526
+ "lstrip": false,
1527
+ "normalized": false,
1528
+ "rstrip": false,
1529
+ "single_word": false,
1530
+ "special": true
1531
+ },
1532
+ "128191": {
1533
+ "content": "<|reserved_special_token_183|>",
1534
+ "lstrip": false,
1535
+ "normalized": false,
1536
+ "rstrip": false,
1537
+ "single_word": false,
1538
+ "special": true
1539
+ },
1540
+ "128192": {
1541
+ "content": "<|reserved_special_token_184|>",
1542
+ "lstrip": false,
1543
+ "normalized": false,
1544
+ "rstrip": false,
1545
+ "single_word": false,
1546
+ "special": true
1547
+ },
1548
+ "128193": {
1549
+ "content": "<|reserved_special_token_185|>",
1550
+ "lstrip": false,
1551
+ "normalized": false,
1552
+ "rstrip": false,
1553
+ "single_word": false,
1554
+ "special": true
1555
+ },
1556
+ "128194": {
1557
+ "content": "<|reserved_special_token_186|>",
1558
+ "lstrip": false,
1559
+ "normalized": false,
1560
+ "rstrip": false,
1561
+ "single_word": false,
1562
+ "special": true
1563
+ },
1564
+ "128195": {
1565
+ "content": "<|reserved_special_token_187|>",
1566
+ "lstrip": false,
1567
+ "normalized": false,
1568
+ "rstrip": false,
1569
+ "single_word": false,
1570
+ "special": true
1571
+ },
1572
+ "128196": {
1573
+ "content": "<|reserved_special_token_188|>",
1574
+ "lstrip": false,
1575
+ "normalized": false,
1576
+ "rstrip": false,
1577
+ "single_word": false,
1578
+ "special": true
1579
+ },
1580
+ "128197": {
1581
+ "content": "<|reserved_special_token_189|>",
1582
+ "lstrip": false,
1583
+ "normalized": false,
1584
+ "rstrip": false,
1585
+ "single_word": false,
1586
+ "special": true
1587
+ },
1588
+ "128198": {
1589
+ "content": "<|reserved_special_token_190|>",
1590
+ "lstrip": false,
1591
+ "normalized": false,
1592
+ "rstrip": false,
1593
+ "single_word": false,
1594
+ "special": true
1595
+ },
1596
+ "128199": {
1597
+ "content": "<|reserved_special_token_191|>",
1598
+ "lstrip": false,
1599
+ "normalized": false,
1600
+ "rstrip": false,
1601
+ "single_word": false,
1602
+ "special": true
1603
+ },
1604
+ "128200": {
1605
+ "content": "<|reserved_special_token_192|>",
1606
+ "lstrip": false,
1607
+ "normalized": false,
1608
+ "rstrip": false,
1609
+ "single_word": false,
1610
+ "special": true
1611
+ },
1612
+ "128201": {
1613
+ "content": "<|reserved_special_token_193|>",
1614
+ "lstrip": false,
1615
+ "normalized": false,
1616
+ "rstrip": false,
1617
+ "single_word": false,
1618
+ "special": true
1619
+ },
1620
+ "128202": {
1621
+ "content": "<|reserved_special_token_194|>",
1622
+ "lstrip": false,
1623
+ "normalized": false,
1624
+ "rstrip": false,
1625
+ "single_word": false,
1626
+ "special": true
1627
+ },
1628
+ "128203": {
1629
+ "content": "<|reserved_special_token_195|>",
1630
+ "lstrip": false,
1631
+ "normalized": false,
1632
+ "rstrip": false,
1633
+ "single_word": false,
1634
+ "special": true
1635
+ },
1636
+ "128204": {
1637
+ "content": "<|reserved_special_token_196|>",
1638
+ "lstrip": false,
1639
+ "normalized": false,
1640
+ "rstrip": false,
1641
+ "single_word": false,
1642
+ "special": true
1643
+ },
1644
+ "128205": {
1645
+ "content": "<|reserved_special_token_197|>",
1646
+ "lstrip": false,
1647
+ "normalized": false,
1648
+ "rstrip": false,
1649
+ "single_word": false,
1650
+ "special": true
1651
+ },
1652
+ "128206": {
1653
+ "content": "<|reserved_special_token_198|>",
1654
+ "lstrip": false,
1655
+ "normalized": false,
1656
+ "rstrip": false,
1657
+ "single_word": false,
1658
+ "special": true
1659
+ },
1660
+ "128207": {
1661
+ "content": "<|reserved_special_token_199|>",
1662
+ "lstrip": false,
1663
+ "normalized": false,
1664
+ "rstrip": false,
1665
+ "single_word": false,
1666
+ "special": true
1667
+ },
1668
+ "128208": {
1669
+ "content": "<|reserved_special_token_200|>",
1670
+ "lstrip": false,
1671
+ "normalized": false,
1672
+ "rstrip": false,
1673
+ "single_word": false,
1674
+ "special": true
1675
+ },
1676
+ "128209": {
1677
+ "content": "<|reserved_special_token_201|>",
1678
+ "lstrip": false,
1679
+ "normalized": false,
1680
+ "rstrip": false,
1681
+ "single_word": false,
1682
+ "special": true
1683
+ },
1684
+ "128210": {
1685
+ "content": "<|reserved_special_token_202|>",
1686
+ "lstrip": false,
1687
+ "normalized": false,
1688
+ "rstrip": false,
1689
+ "single_word": false,
1690
+ "special": true
1691
+ },
1692
+ "128211": {
1693
+ "content": "<|reserved_special_token_203|>",
1694
+ "lstrip": false,
1695
+ "normalized": false,
1696
+ "rstrip": false,
1697
+ "single_word": false,
1698
+ "special": true
1699
+ },
1700
+ "128212": {
1701
+ "content": "<|reserved_special_token_204|>",
1702
+ "lstrip": false,
1703
+ "normalized": false,
1704
+ "rstrip": false,
1705
+ "single_word": false,
1706
+ "special": true
1707
+ },
1708
+ "128213": {
1709
+ "content": "<|reserved_special_token_205|>",
1710
+ "lstrip": false,
1711
+ "normalized": false,
1712
+ "rstrip": false,
1713
+ "single_word": false,
1714
+ "special": true
1715
+ },
1716
+ "128214": {
1717
+ "content": "<|reserved_special_token_206|>",
1718
+ "lstrip": false,
1719
+ "normalized": false,
1720
+ "rstrip": false,
1721
+ "single_word": false,
1722
+ "special": true
1723
+ },
1724
+ "128215": {
1725
+ "content": "<|reserved_special_token_207|>",
1726
+ "lstrip": false,
1727
+ "normalized": false,
1728
+ "rstrip": false,
1729
+ "single_word": false,
1730
+ "special": true
1731
+ },
1732
+ "128216": {
1733
+ "content": "<|reserved_special_token_208|>",
1734
+ "lstrip": false,
1735
+ "normalized": false,
1736
+ "rstrip": false,
1737
+ "single_word": false,
1738
+ "special": true
1739
+ },
1740
+ "128217": {
1741
+ "content": "<|reserved_special_token_209|>",
1742
+ "lstrip": false,
1743
+ "normalized": false,
1744
+ "rstrip": false,
1745
+ "single_word": false,
1746
+ "special": true
1747
+ },
1748
+ "128218": {
1749
+ "content": "<|reserved_special_token_210|>",
1750
+ "lstrip": false,
1751
+ "normalized": false,
1752
+ "rstrip": false,
1753
+ "single_word": false,
1754
+ "special": true
1755
+ },
1756
+ "128219": {
1757
+ "content": "<|reserved_special_token_211|>",
1758
+ "lstrip": false,
1759
+ "normalized": false,
1760
+ "rstrip": false,
1761
+ "single_word": false,
1762
+ "special": true
1763
+ },
1764
+ "128220": {
1765
+ "content": "<|reserved_special_token_212|>",
1766
+ "lstrip": false,
1767
+ "normalized": false,
1768
+ "rstrip": false,
1769
+ "single_word": false,
1770
+ "special": true
1771
+ },
1772
+ "128221": {
1773
+ "content": "<|reserved_special_token_213|>",
1774
+ "lstrip": false,
1775
+ "normalized": false,
1776
+ "rstrip": false,
1777
+ "single_word": false,
1778
+ "special": true
1779
+ },
1780
+ "128222": {
1781
+ "content": "<|reserved_special_token_214|>",
1782
+ "lstrip": false,
1783
+ "normalized": false,
1784
+ "rstrip": false,
1785
+ "single_word": false,
1786
+ "special": true
1787
+ },
1788
+ "128223": {
1789
+ "content": "<|reserved_special_token_215|>",
1790
+ "lstrip": false,
1791
+ "normalized": false,
1792
+ "rstrip": false,
1793
+ "single_word": false,
1794
+ "special": true
1795
+ },
1796
+ "128224": {
1797
+ "content": "<|reserved_special_token_216|>",
1798
+ "lstrip": false,
1799
+ "normalized": false,
1800
+ "rstrip": false,
1801
+ "single_word": false,
1802
+ "special": true
1803
+ },
1804
+ "128225": {
1805
+ "content": "<|reserved_special_token_217|>",
1806
+ "lstrip": false,
1807
+ "normalized": false,
1808
+ "rstrip": false,
1809
+ "single_word": false,
1810
+ "special": true
1811
+ },
1812
+ "128226": {
1813
+ "content": "<|reserved_special_token_218|>",
1814
+ "lstrip": false,
1815
+ "normalized": false,
1816
+ "rstrip": false,
1817
+ "single_word": false,
1818
+ "special": true
1819
+ },
1820
+ "128227": {
1821
+ "content": "<|reserved_special_token_219|>",
1822
+ "lstrip": false,
1823
+ "normalized": false,
1824
+ "rstrip": false,
1825
+ "single_word": false,
1826
+ "special": true
1827
+ },
1828
+ "128228": {
1829
+ "content": "<|reserved_special_token_220|>",
1830
+ "lstrip": false,
1831
+ "normalized": false,
1832
+ "rstrip": false,
1833
+ "single_word": false,
1834
+ "special": true
1835
+ },
1836
+ "128229": {
1837
+ "content": "<|reserved_special_token_221|>",
1838
+ "lstrip": false,
1839
+ "normalized": false,
1840
+ "rstrip": false,
1841
+ "single_word": false,
1842
+ "special": true
1843
+ },
1844
+ "128230": {
1845
+ "content": "<|reserved_special_token_222|>",
1846
+ "lstrip": false,
1847
+ "normalized": false,
1848
+ "rstrip": false,
1849
+ "single_word": false,
1850
+ "special": true
1851
+ },
1852
+ "128231": {
1853
+ "content": "<|reserved_special_token_223|>",
1854
+ "lstrip": false,
1855
+ "normalized": false,
1856
+ "rstrip": false,
1857
+ "single_word": false,
1858
+ "special": true
1859
+ },
1860
+ "128232": {
1861
+ "content": "<|reserved_special_token_224|>",
1862
+ "lstrip": false,
1863
+ "normalized": false,
1864
+ "rstrip": false,
1865
+ "single_word": false,
1866
+ "special": true
1867
+ },
1868
+ "128233": {
1869
+ "content": "<|reserved_special_token_225|>",
1870
+ "lstrip": false,
1871
+ "normalized": false,
1872
+ "rstrip": false,
1873
+ "single_word": false,
1874
+ "special": true
1875
+ },
1876
+ "128234": {
1877
+ "content": "<|reserved_special_token_226|>",
1878
+ "lstrip": false,
1879
+ "normalized": false,
1880
+ "rstrip": false,
1881
+ "single_word": false,
1882
+ "special": true
1883
+ },
1884
+ "128235": {
1885
+ "content": "<|reserved_special_token_227|>",
1886
+ "lstrip": false,
1887
+ "normalized": false,
1888
+ "rstrip": false,
1889
+ "single_word": false,
1890
+ "special": true
1891
+ },
1892
+ "128236": {
1893
+ "content": "<|reserved_special_token_228|>",
1894
+ "lstrip": false,
1895
+ "normalized": false,
1896
+ "rstrip": false,
1897
+ "single_word": false,
1898
+ "special": true
1899
+ },
1900
+ "128237": {
1901
+ "content": "<|reserved_special_token_229|>",
1902
+ "lstrip": false,
1903
+ "normalized": false,
1904
+ "rstrip": false,
1905
+ "single_word": false,
1906
+ "special": true
1907
+ },
1908
+ "128238": {
1909
+ "content": "<|reserved_special_token_230|>",
1910
+ "lstrip": false,
1911
+ "normalized": false,
1912
+ "rstrip": false,
1913
+ "single_word": false,
1914
+ "special": true
1915
+ },
1916
+ "128239": {
1917
+ "content": "<|reserved_special_token_231|>",
1918
+ "lstrip": false,
1919
+ "normalized": false,
1920
+ "rstrip": false,
1921
+ "single_word": false,
1922
+ "special": true
1923
+ },
1924
+ "128240": {
1925
+ "content": "<|reserved_special_token_232|>",
1926
+ "lstrip": false,
1927
+ "normalized": false,
1928
+ "rstrip": false,
1929
+ "single_word": false,
1930
+ "special": true
1931
+ },
1932
+ "128241": {
1933
+ "content": "<|reserved_special_token_233|>",
1934
+ "lstrip": false,
1935
+ "normalized": false,
1936
+ "rstrip": false,
1937
+ "single_word": false,
1938
+ "special": true
1939
+ },
1940
+ "128242": {
1941
+ "content": "<|reserved_special_token_234|>",
1942
+ "lstrip": false,
1943
+ "normalized": false,
1944
+ "rstrip": false,
1945
+ "single_word": false,
1946
+ "special": true
1947
+ },
1948
+ "128243": {
1949
+ "content": "<|reserved_special_token_235|>",
1950
+ "lstrip": false,
1951
+ "normalized": false,
1952
+ "rstrip": false,
1953
+ "single_word": false,
1954
+ "special": true
1955
+ },
1956
+ "128244": {
1957
+ "content": "<|reserved_special_token_236|>",
1958
+ "lstrip": false,
1959
+ "normalized": false,
1960
+ "rstrip": false,
1961
+ "single_word": false,
1962
+ "special": true
1963
+ },
1964
+ "128245": {
1965
+ "content": "<|reserved_special_token_237|>",
1966
+ "lstrip": false,
1967
+ "normalized": false,
1968
+ "rstrip": false,
1969
+ "single_word": false,
1970
+ "special": true
1971
+ },
1972
+ "128246": {
1973
+ "content": "<|reserved_special_token_238|>",
1974
+ "lstrip": false,
1975
+ "normalized": false,
1976
+ "rstrip": false,
1977
+ "single_word": false,
1978
+ "special": true
1979
+ },
1980
+ "128247": {
1981
+ "content": "<|reserved_special_token_239|>",
1982
+ "lstrip": false,
1983
+ "normalized": false,
1984
+ "rstrip": false,
1985
+ "single_word": false,
1986
+ "special": true
1987
+ },
1988
+ "128248": {
1989
+ "content": "<|reserved_special_token_240|>",
1990
+ "lstrip": false,
1991
+ "normalized": false,
1992
+ "rstrip": false,
1993
+ "single_word": false,
1994
+ "special": true
1995
+ },
1996
+ "128249": {
1997
+ "content": "<|reserved_special_token_241|>",
1998
+ "lstrip": false,
1999
+ "normalized": false,
2000
+ "rstrip": false,
2001
+ "single_word": false,
2002
+ "special": true
2003
+ },
2004
+ "128250": {
2005
+ "content": "<|reserved_special_token_242|>",
2006
+ "lstrip": false,
2007
+ "normalized": false,
2008
+ "rstrip": false,
2009
+ "single_word": false,
2010
+ "special": true
2011
+ },
2012
+ "128251": {
2013
+ "content": "<|reserved_special_token_243|>",
2014
+ "lstrip": false,
2015
+ "normalized": false,
2016
+ "rstrip": false,
2017
+ "single_word": false,
2018
+ "special": true
2019
+ },
2020
+ "128252": {
2021
+ "content": "<|reserved_special_token_244|>",
2022
+ "lstrip": false,
2023
+ "normalized": false,
2024
+ "rstrip": false,
2025
+ "single_word": false,
2026
+ "special": true
2027
+ },
2028
+ "128253": {
2029
+ "content": "<|reserved_special_token_245|>",
2030
+ "lstrip": false,
2031
+ "normalized": false,
2032
+ "rstrip": false,
2033
+ "single_word": false,
2034
+ "special": true
2035
+ },
2036
+ "128254": {
2037
+ "content": "<|reserved_special_token_246|>",
2038
+ "lstrip": false,
2039
+ "normalized": false,
2040
+ "rstrip": false,
2041
+ "single_word": false,
2042
+ "special": true
2043
+ },
2044
+ "128255": {
2045
+ "content": "<|reserved_special_token_247|>",
2046
+ "lstrip": false,
2047
+ "normalized": false,
2048
+ "rstrip": false,
2049
+ "single_word": false,
2050
+ "special": true
2051
+ }
2052
+ },
2053
+ "bos_token": "<|begin_of_text|>",
2054
+ "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 {%- if strftime_now is defined %}\n {%- set date_string = strftime_now(\"%d %b %Y\") %}\n {%- else %}\n {%- set date_string = \"26 Jul 2024\" %}\n {%- endif %}\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 #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if tools is not none %}\n {{- \"Environment: ipython\\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 {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {{- \"<|eot_id|>\" }}\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",
2055
+ "clean_up_tokenization_spaces": true,
2056
+ "eos_token": "<|eot_id|>",
2057
+ "extra_special_tokens": {},
2058
+ "model_input_names": [
2059
+ "input_ids",
2060
+ "attention_mask"
2061
+ ],
2062
+ "model_max_length": 131072,
2063
+ "pad_token": "<|eot_id|>",
2064
+ "tokenizer_class": "PreTrainedTokenizer"
2065
+ }
checkpoints_ia3_llama_class/checkpoint-144000/trainer_state.json ADDED
@@ -0,0 +1,2212 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 88000,
3
+ "best_metric": 0.936161178019818,
4
+ "best_model_checkpoint": "/home/sujeet-pg/wav2vec2/peft/checkpoints_ia3_llama_class/checkpoint-88000",
5
+ "epoch": 18.0,
6
+ "eval_steps": 500,
7
+ "global_step": 144000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0625,
14
+ "grad_norm": 29.181745529174805,
15
+ "learning_rate": 4.982673611111111e-05,
16
+ "loss": 1.9515,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.125,
21
+ "grad_norm": 84.54170989990234,
22
+ "learning_rate": 4.9653125e-05,
23
+ "loss": 1.4973,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 0.1875,
28
+ "grad_norm": 118.13458251953125,
29
+ "learning_rate": 4.947951388888889e-05,
30
+ "loss": 1.3271,
31
+ "step": 1500
32
+ },
33
+ {
34
+ "epoch": 0.25,
35
+ "grad_norm": 0.062166254967451096,
36
+ "learning_rate": 4.930590277777778e-05,
37
+ "loss": 0.9626,
38
+ "step": 2000
39
+ },
40
+ {
41
+ "epoch": 0.3125,
42
+ "grad_norm": 165.25686645507812,
43
+ "learning_rate": 4.9132291666666665e-05,
44
+ "loss": 0.7346,
45
+ "step": 2500
46
+ },
47
+ {
48
+ "epoch": 0.375,
49
+ "grad_norm": 0.6356489658355713,
50
+ "learning_rate": 4.8958680555555555e-05,
51
+ "loss": 0.8147,
52
+ "step": 3000
53
+ },
54
+ {
55
+ "epoch": 0.4375,
56
+ "grad_norm": 0.012186303734779358,
57
+ "learning_rate": 4.8785069444444445e-05,
58
+ "loss": 0.5557,
59
+ "step": 3500
60
+ },
61
+ {
62
+ "epoch": 0.5,
63
+ "grad_norm": 114.87812805175781,
64
+ "learning_rate": 4.8611458333333335e-05,
65
+ "loss": 0.546,
66
+ "step": 4000
67
+ },
68
+ {
69
+ "epoch": 0.5625,
70
+ "grad_norm": 0.3081382215023041,
71
+ "learning_rate": 4.8437847222222225e-05,
72
+ "loss": 0.5198,
73
+ "step": 4500
74
+ },
75
+ {
76
+ "epoch": 0.625,
77
+ "grad_norm": 0.0013407367514446378,
78
+ "learning_rate": 4.826423611111111e-05,
79
+ "loss": 0.4668,
80
+ "step": 5000
81
+ },
82
+ {
83
+ "epoch": 0.6875,
84
+ "grad_norm": 0.032304372638463974,
85
+ "learning_rate": 4.8090625e-05,
86
+ "loss": 0.4066,
87
+ "step": 5500
88
+ },
89
+ {
90
+ "epoch": 0.75,
91
+ "grad_norm": 0.350352019071579,
92
+ "learning_rate": 4.791701388888889e-05,
93
+ "loss": 0.494,
94
+ "step": 6000
95
+ },
96
+ {
97
+ "epoch": 0.8125,
98
+ "grad_norm": 0.031369373202323914,
99
+ "learning_rate": 4.774340277777778e-05,
100
+ "loss": 0.4372,
101
+ "step": 6500
102
+ },
103
+ {
104
+ "epoch": 0.875,
105
+ "grad_norm": 87.0584716796875,
106
+ "learning_rate": 4.756979166666667e-05,
107
+ "loss": 0.546,
108
+ "step": 7000
109
+ },
110
+ {
111
+ "epoch": 0.9375,
112
+ "grad_norm": 42.25841522216797,
113
+ "learning_rate": 4.739618055555556e-05,
114
+ "loss": 0.4929,
115
+ "step": 7500
116
+ },
117
+ {
118
+ "epoch": 1.0,
119
+ "grad_norm": 0.017110565677285194,
120
+ "learning_rate": 4.722256944444445e-05,
121
+ "loss": 0.4128,
122
+ "step": 8000
123
+ },
124
+ {
125
+ "epoch": 1.0,
126
+ "eval_loss": 0.34961560368537903,
127
+ "eval_pearson": 0.9195974916185884,
128
+ "eval_runtime": 52.203,
129
+ "eval_samples_per_second": 38.312,
130
+ "eval_steps_per_second": 19.156,
131
+ "step": 8000
132
+ },
133
+ {
134
+ "epoch": 1.0625,
135
+ "grad_norm": 39.48343276977539,
136
+ "learning_rate": 4.704895833333334e-05,
137
+ "loss": 0.1769,
138
+ "step": 8500
139
+ },
140
+ {
141
+ "epoch": 1.125,
142
+ "grad_norm": 0.0003292807668913156,
143
+ "learning_rate": 4.687534722222223e-05,
144
+ "loss": 0.3138,
145
+ "step": 9000
146
+ },
147
+ {
148
+ "epoch": 1.1875,
149
+ "grad_norm": 0.0025669685564935207,
150
+ "learning_rate": 4.670173611111111e-05,
151
+ "loss": 0.3529,
152
+ "step": 9500
153
+ },
154
+ {
155
+ "epoch": 1.25,
156
+ "grad_norm": 0.0019228530582040548,
157
+ "learning_rate": 4.6528125e-05,
158
+ "loss": 0.3181,
159
+ "step": 10000
160
+ },
161
+ {
162
+ "epoch": 1.3125,
163
+ "grad_norm": 0.09842195361852646,
164
+ "learning_rate": 4.635451388888889e-05,
165
+ "loss": 0.3358,
166
+ "step": 10500
167
+ },
168
+ {
169
+ "epoch": 1.375,
170
+ "grad_norm": 0.0006872316589578986,
171
+ "learning_rate": 4.618090277777778e-05,
172
+ "loss": 0.3395,
173
+ "step": 11000
174
+ },
175
+ {
176
+ "epoch": 1.4375,
177
+ "grad_norm": 0.008952559903264046,
178
+ "learning_rate": 4.600729166666667e-05,
179
+ "loss": 0.3287,
180
+ "step": 11500
181
+ },
182
+ {
183
+ "epoch": 1.5,
184
+ "grad_norm": 0.0010550743900239468,
185
+ "learning_rate": 4.583368055555556e-05,
186
+ "loss": 0.3742,
187
+ "step": 12000
188
+ },
189
+ {
190
+ "epoch": 1.5625,
191
+ "grad_norm": 0.0011425487464293838,
192
+ "learning_rate": 4.566006944444445e-05,
193
+ "loss": 0.2979,
194
+ "step": 12500
195
+ },
196
+ {
197
+ "epoch": 1.625,
198
+ "grad_norm": 14.729352951049805,
199
+ "learning_rate": 4.5486458333333334e-05,
200
+ "loss": 0.2669,
201
+ "step": 13000
202
+ },
203
+ {
204
+ "epoch": 1.6875,
205
+ "grad_norm": 1.1553162039490417e-05,
206
+ "learning_rate": 4.5312847222222224e-05,
207
+ "loss": 0.3885,
208
+ "step": 13500
209
+ },
210
+ {
211
+ "epoch": 1.75,
212
+ "grad_norm": 0.051722027361392975,
213
+ "learning_rate": 4.5139236111111114e-05,
214
+ "loss": 0.3096,
215
+ "step": 14000
216
+ },
217
+ {
218
+ "epoch": 1.8125,
219
+ "grad_norm": 0.12957464158535004,
220
+ "learning_rate": 4.4965625e-05,
221
+ "loss": 0.3479,
222
+ "step": 14500
223
+ },
224
+ {
225
+ "epoch": 1.875,
226
+ "grad_norm": 0.012610511854290962,
227
+ "learning_rate": 4.479201388888889e-05,
228
+ "loss": 0.432,
229
+ "step": 15000
230
+ },
231
+ {
232
+ "epoch": 1.9375,
233
+ "grad_norm": 0.022952524945139885,
234
+ "learning_rate": 4.461840277777778e-05,
235
+ "loss": 0.2932,
236
+ "step": 15500
237
+ },
238
+ {
239
+ "epoch": 2.0,
240
+ "grad_norm": 3.255659612477757e-05,
241
+ "learning_rate": 4.444479166666667e-05,
242
+ "loss": 0.2544,
243
+ "step": 16000
244
+ },
245
+ {
246
+ "epoch": 2.0,
247
+ "eval_loss": 0.3652373254299164,
248
+ "eval_pearson": 0.9308122796123071,
249
+ "eval_runtime": 52.221,
250
+ "eval_samples_per_second": 38.299,
251
+ "eval_steps_per_second": 19.149,
252
+ "step": 16000
253
+ },
254
+ {
255
+ "epoch": 2.0625,
256
+ "grad_norm": 349.7726135253906,
257
+ "learning_rate": 4.427118055555556e-05,
258
+ "loss": 0.3006,
259
+ "step": 16500
260
+ },
261
+ {
262
+ "epoch": 2.125,
263
+ "grad_norm": 0.05852258577942848,
264
+ "learning_rate": 4.409756944444445e-05,
265
+ "loss": 0.2222,
266
+ "step": 17000
267
+ },
268
+ {
269
+ "epoch": 2.1875,
270
+ "grad_norm": 8.100055129034445e-05,
271
+ "learning_rate": 4.3923958333333337e-05,
272
+ "loss": 0.2253,
273
+ "step": 17500
274
+ },
275
+ {
276
+ "epoch": 2.25,
277
+ "grad_norm": 0.015503599308431149,
278
+ "learning_rate": 4.3750347222222226e-05,
279
+ "loss": 0.301,
280
+ "step": 18000
281
+ },
282
+ {
283
+ "epoch": 2.3125,
284
+ "grad_norm": 0.0007520843064412475,
285
+ "learning_rate": 4.357673611111111e-05,
286
+ "loss": 0.1979,
287
+ "step": 18500
288
+ },
289
+ {
290
+ "epoch": 2.375,
291
+ "grad_norm": 0.0003110193647444248,
292
+ "learning_rate": 4.3403125e-05,
293
+ "loss": 0.2496,
294
+ "step": 19000
295
+ },
296
+ {
297
+ "epoch": 2.4375,
298
+ "grad_norm": 5.800446033477783,
299
+ "learning_rate": 4.322951388888889e-05,
300
+ "loss": 0.3028,
301
+ "step": 19500
302
+ },
303
+ {
304
+ "epoch": 2.5,
305
+ "grad_norm": 2.4347489215870155e-06,
306
+ "learning_rate": 4.305590277777778e-05,
307
+ "loss": 0.2218,
308
+ "step": 20000
309
+ },
310
+ {
311
+ "epoch": 2.5625,
312
+ "grad_norm": 0.972939133644104,
313
+ "learning_rate": 4.288229166666667e-05,
314
+ "loss": 0.2485,
315
+ "step": 20500
316
+ },
317
+ {
318
+ "epoch": 2.625,
319
+ "grad_norm": 1.2701035737991333,
320
+ "learning_rate": 4.270868055555556e-05,
321
+ "loss": 0.179,
322
+ "step": 21000
323
+ },
324
+ {
325
+ "epoch": 2.6875,
326
+ "grad_norm": 0.0001465667737647891,
327
+ "learning_rate": 4.253506944444445e-05,
328
+ "loss": 0.337,
329
+ "step": 21500
330
+ },
331
+ {
332
+ "epoch": 2.75,
333
+ "grad_norm": 188.92559814453125,
334
+ "learning_rate": 4.236145833333334e-05,
335
+ "loss": 0.2353,
336
+ "step": 22000
337
+ },
338
+ {
339
+ "epoch": 2.8125,
340
+ "grad_norm": 0.0020125608425587416,
341
+ "learning_rate": 4.218784722222223e-05,
342
+ "loss": 0.2412,
343
+ "step": 22500
344
+ },
345
+ {
346
+ "epoch": 2.875,
347
+ "grad_norm": 0.030752288177609444,
348
+ "learning_rate": 4.201423611111111e-05,
349
+ "loss": 0.2645,
350
+ "step": 23000
351
+ },
352
+ {
353
+ "epoch": 2.9375,
354
+ "grad_norm": 76.4650650024414,
355
+ "learning_rate": 4.1840625e-05,
356
+ "loss": 0.2856,
357
+ "step": 23500
358
+ },
359
+ {
360
+ "epoch": 3.0,
361
+ "grad_norm": 0.0004072492301929742,
362
+ "learning_rate": 4.166701388888889e-05,
363
+ "loss": 0.2395,
364
+ "step": 24000
365
+ },
366
+ {
367
+ "epoch": 3.0,
368
+ "eval_loss": 0.28703999519348145,
369
+ "eval_pearson": 0.9358259106635223,
370
+ "eval_runtime": 52.1011,
371
+ "eval_samples_per_second": 38.387,
372
+ "eval_steps_per_second": 19.193,
373
+ "step": 24000
374
+ },
375
+ {
376
+ "epoch": 3.0625,
377
+ "grad_norm": 0.007601168937981129,
378
+ "learning_rate": 4.149340277777778e-05,
379
+ "loss": 0.1748,
380
+ "step": 24500
381
+ },
382
+ {
383
+ "epoch": 3.125,
384
+ "grad_norm": 0.026926109567284584,
385
+ "learning_rate": 4.1319791666666665e-05,
386
+ "loss": 0.1542,
387
+ "step": 25000
388
+ },
389
+ {
390
+ "epoch": 3.1875,
391
+ "grad_norm": 1.8115358352661133,
392
+ "learning_rate": 4.1146180555555555e-05,
393
+ "loss": 0.2275,
394
+ "step": 25500
395
+ },
396
+ {
397
+ "epoch": 3.25,
398
+ "grad_norm": 0.06953763216733932,
399
+ "learning_rate": 4.0972569444444445e-05,
400
+ "loss": 0.1706,
401
+ "step": 26000
402
+ },
403
+ {
404
+ "epoch": 3.3125,
405
+ "grad_norm": 0.020493032410740852,
406
+ "learning_rate": 4.0798958333333335e-05,
407
+ "loss": 0.1474,
408
+ "step": 26500
409
+ },
410
+ {
411
+ "epoch": 3.375,
412
+ "grad_norm": 0.005125588737428188,
413
+ "learning_rate": 4.0625347222222225e-05,
414
+ "loss": 0.1723,
415
+ "step": 27000
416
+ },
417
+ {
418
+ "epoch": 3.4375,
419
+ "grad_norm": 5.002508163452148,
420
+ "learning_rate": 4.045173611111111e-05,
421
+ "loss": 0.196,
422
+ "step": 27500
423
+ },
424
+ {
425
+ "epoch": 3.5,
426
+ "grad_norm": 0.000834703678265214,
427
+ "learning_rate": 4.0278125e-05,
428
+ "loss": 0.1449,
429
+ "step": 28000
430
+ },
431
+ {
432
+ "epoch": 3.5625,
433
+ "grad_norm": 0.01109158806502819,
434
+ "learning_rate": 4.010451388888889e-05,
435
+ "loss": 0.2287,
436
+ "step": 28500
437
+ },
438
+ {
439
+ "epoch": 3.625,
440
+ "grad_norm": 9.071109161595814e-06,
441
+ "learning_rate": 3.993090277777778e-05,
442
+ "loss": 0.1955,
443
+ "step": 29000
444
+ },
445
+ {
446
+ "epoch": 3.6875,
447
+ "grad_norm": 0.0006111862603574991,
448
+ "learning_rate": 3.975729166666667e-05,
449
+ "loss": 0.2147,
450
+ "step": 29500
451
+ },
452
+ {
453
+ "epoch": 3.75,
454
+ "grad_norm": 6.614517928937858e-07,
455
+ "learning_rate": 3.958368055555556e-05,
456
+ "loss": 0.2289,
457
+ "step": 30000
458
+ },
459
+ {
460
+ "epoch": 3.8125,
461
+ "grad_norm": 5.0481699872761965e-05,
462
+ "learning_rate": 3.941006944444445e-05,
463
+ "loss": 0.1941,
464
+ "step": 30500
465
+ },
466
+ {
467
+ "epoch": 3.875,
468
+ "grad_norm": 2.837545871734619,
469
+ "learning_rate": 3.923645833333334e-05,
470
+ "loss": 0.1753,
471
+ "step": 31000
472
+ },
473
+ {
474
+ "epoch": 3.9375,
475
+ "grad_norm": 0.00021911883959546685,
476
+ "learning_rate": 3.906284722222223e-05,
477
+ "loss": 0.1967,
478
+ "step": 31500
479
+ },
480
+ {
481
+ "epoch": 4.0,
482
+ "grad_norm": 0.008439241908490658,
483
+ "learning_rate": 3.888923611111111e-05,
484
+ "loss": 0.2341,
485
+ "step": 32000
486
+ },
487
+ {
488
+ "epoch": 4.0,
489
+ "eval_loss": 0.28366541862487793,
490
+ "eval_pearson": 0.9336592859812687,
491
+ "eval_runtime": 52.2768,
492
+ "eval_samples_per_second": 38.258,
493
+ "eval_steps_per_second": 19.129,
494
+ "step": 32000
495
+ },
496
+ {
497
+ "epoch": 4.0625,
498
+ "grad_norm": 3.5697648525238037,
499
+ "learning_rate": 3.8715625e-05,
500
+ "loss": 0.0898,
501
+ "step": 32500
502
+ },
503
+ {
504
+ "epoch": 4.125,
505
+ "grad_norm": 0.005574432201683521,
506
+ "learning_rate": 3.854201388888889e-05,
507
+ "loss": 0.0931,
508
+ "step": 33000
509
+ },
510
+ {
511
+ "epoch": 4.1875,
512
+ "grad_norm": 0.4526767134666443,
513
+ "learning_rate": 3.836840277777778e-05,
514
+ "loss": 0.1269,
515
+ "step": 33500
516
+ },
517
+ {
518
+ "epoch": 4.25,
519
+ "grad_norm": 0.0006220944924280047,
520
+ "learning_rate": 3.819479166666667e-05,
521
+ "loss": 0.1229,
522
+ "step": 34000
523
+ },
524
+ {
525
+ "epoch": 4.3125,
526
+ "grad_norm": 0.0021529244258999825,
527
+ "learning_rate": 3.802118055555556e-05,
528
+ "loss": 0.0941,
529
+ "step": 34500
530
+ },
531
+ {
532
+ "epoch": 4.375,
533
+ "grad_norm": 161.37889099121094,
534
+ "learning_rate": 3.784756944444445e-05,
535
+ "loss": 0.1504,
536
+ "step": 35000
537
+ },
538
+ {
539
+ "epoch": 4.4375,
540
+ "grad_norm": 0.11136477440595627,
541
+ "learning_rate": 3.7673958333333334e-05,
542
+ "loss": 0.1809,
543
+ "step": 35500
544
+ },
545
+ {
546
+ "epoch": 4.5,
547
+ "grad_norm": 0.001285308855585754,
548
+ "learning_rate": 3.7500347222222224e-05,
549
+ "loss": 0.0936,
550
+ "step": 36000
551
+ },
552
+ {
553
+ "epoch": 4.5625,
554
+ "grad_norm": 9.097888687392697e-05,
555
+ "learning_rate": 3.7326736111111114e-05,
556
+ "loss": 0.138,
557
+ "step": 36500
558
+ },
559
+ {
560
+ "epoch": 4.625,
561
+ "grad_norm": 8.100504373942385e-07,
562
+ "learning_rate": 3.7153125e-05,
563
+ "loss": 0.1018,
564
+ "step": 37000
565
+ },
566
+ {
567
+ "epoch": 4.6875,
568
+ "grad_norm": 7.76401338953292e-06,
569
+ "learning_rate": 3.697951388888889e-05,
570
+ "loss": 0.1467,
571
+ "step": 37500
572
+ },
573
+ {
574
+ "epoch": 4.75,
575
+ "grad_norm": 0.00011219551379326731,
576
+ "learning_rate": 3.680590277777778e-05,
577
+ "loss": 0.1253,
578
+ "step": 38000
579
+ },
580
+ {
581
+ "epoch": 4.8125,
582
+ "grad_norm": 6.52613493912213e-07,
583
+ "learning_rate": 3.6632291666666667e-05,
584
+ "loss": 0.1658,
585
+ "step": 38500
586
+ },
587
+ {
588
+ "epoch": 4.875,
589
+ "grad_norm": 0.00043506777728907764,
590
+ "learning_rate": 3.6458680555555557e-05,
591
+ "loss": 0.1746,
592
+ "step": 39000
593
+ },
594
+ {
595
+ "epoch": 4.9375,
596
+ "grad_norm": 0.003737818216904998,
597
+ "learning_rate": 3.6285069444444446e-05,
598
+ "loss": 0.1511,
599
+ "step": 39500
600
+ },
601
+ {
602
+ "epoch": 5.0,
603
+ "grad_norm": 0.0032031103037297726,
604
+ "learning_rate": 3.6111458333333336e-05,
605
+ "loss": 0.1175,
606
+ "step": 40000
607
+ },
608
+ {
609
+ "epoch": 5.0,
610
+ "eval_loss": 0.3400997221469879,
611
+ "eval_pearson": 0.9278541992287661,
612
+ "eval_runtime": 52.4259,
613
+ "eval_samples_per_second": 38.149,
614
+ "eval_steps_per_second": 19.075,
615
+ "step": 40000
616
+ },
617
+ {
618
+ "epoch": 5.0625,
619
+ "grad_norm": 7.578780059702694e-05,
620
+ "learning_rate": 3.5937847222222226e-05,
621
+ "loss": 0.0854,
622
+ "step": 40500
623
+ },
624
+ {
625
+ "epoch": 5.125,
626
+ "grad_norm": 0.00047107384307309985,
627
+ "learning_rate": 3.576423611111111e-05,
628
+ "loss": 0.0978,
629
+ "step": 41000
630
+ },
631
+ {
632
+ "epoch": 5.1875,
633
+ "grad_norm": 1.537612479296513e-05,
634
+ "learning_rate": 3.5590625e-05,
635
+ "loss": 0.0771,
636
+ "step": 41500
637
+ },
638
+ {
639
+ "epoch": 5.25,
640
+ "grad_norm": 0.4128485918045044,
641
+ "learning_rate": 3.541701388888889e-05,
642
+ "loss": 0.0735,
643
+ "step": 42000
644
+ },
645
+ {
646
+ "epoch": 5.3125,
647
+ "grad_norm": 1.5655250549316406,
648
+ "learning_rate": 3.524340277777778e-05,
649
+ "loss": 0.0498,
650
+ "step": 42500
651
+ },
652
+ {
653
+ "epoch": 5.375,
654
+ "grad_norm": 7.616046104885754e-07,
655
+ "learning_rate": 3.506979166666667e-05,
656
+ "loss": 0.0931,
657
+ "step": 43000
658
+ },
659
+ {
660
+ "epoch": 5.4375,
661
+ "grad_norm": 88.26677703857422,
662
+ "learning_rate": 3.489618055555556e-05,
663
+ "loss": 0.0792,
664
+ "step": 43500
665
+ },
666
+ {
667
+ "epoch": 5.5,
668
+ "grad_norm": 5.622899834634154e-07,
669
+ "learning_rate": 3.472256944444445e-05,
670
+ "loss": 0.0598,
671
+ "step": 44000
672
+ },
673
+ {
674
+ "epoch": 5.5625,
675
+ "grad_norm": 3.284021659055725e-07,
676
+ "learning_rate": 3.454895833333334e-05,
677
+ "loss": 0.0569,
678
+ "step": 44500
679
+ },
680
+ {
681
+ "epoch": 5.625,
682
+ "grad_norm": 7.701730646658689e-05,
683
+ "learning_rate": 3.437534722222223e-05,
684
+ "loss": 0.1013,
685
+ "step": 45000
686
+ },
687
+ {
688
+ "epoch": 5.6875,
689
+ "grad_norm": 0.0011569270864129066,
690
+ "learning_rate": 3.420173611111111e-05,
691
+ "loss": 0.0752,
692
+ "step": 45500
693
+ },
694
+ {
695
+ "epoch": 5.75,
696
+ "grad_norm": 0.005151362158358097,
697
+ "learning_rate": 3.4028125e-05,
698
+ "loss": 0.1286,
699
+ "step": 46000
700
+ },
701
+ {
702
+ "epoch": 5.8125,
703
+ "grad_norm": 2.8667493268130784e-08,
704
+ "learning_rate": 3.385451388888889e-05,
705
+ "loss": 0.0628,
706
+ "step": 46500
707
+ },
708
+ {
709
+ "epoch": 5.875,
710
+ "grad_norm": 2.9006994282099186e-06,
711
+ "learning_rate": 3.3680902777777775e-05,
712
+ "loss": 0.0778,
713
+ "step": 47000
714
+ },
715
+ {
716
+ "epoch": 5.9375,
717
+ "grad_norm": 1.4291666047938634e-05,
718
+ "learning_rate": 3.3507291666666665e-05,
719
+ "loss": 0.0939,
720
+ "step": 47500
721
+ },
722
+ {
723
+ "epoch": 6.0,
724
+ "grad_norm": 3.1977786420611665e-05,
725
+ "learning_rate": 3.3333680555555555e-05,
726
+ "loss": 0.0701,
727
+ "step": 48000
728
+ },
729
+ {
730
+ "epoch": 6.0,
731
+ "eval_loss": 0.3394077718257904,
732
+ "eval_pearson": 0.929029551743213,
733
+ "eval_runtime": 52.4713,
734
+ "eval_samples_per_second": 38.116,
735
+ "eval_steps_per_second": 19.058,
736
+ "step": 48000
737
+ },
738
+ {
739
+ "epoch": 6.0625,
740
+ "grad_norm": 2.3781665277056163e-06,
741
+ "learning_rate": 3.3160069444444445e-05,
742
+ "loss": 0.0575,
743
+ "step": 48500
744
+ },
745
+ {
746
+ "epoch": 6.125,
747
+ "grad_norm": 0.00014402755186893046,
748
+ "learning_rate": 3.2986458333333335e-05,
749
+ "loss": 0.0599,
750
+ "step": 49000
751
+ },
752
+ {
753
+ "epoch": 6.1875,
754
+ "grad_norm": 0.0024268697015941143,
755
+ "learning_rate": 3.2812847222222225e-05,
756
+ "loss": 0.0134,
757
+ "step": 49500
758
+ },
759
+ {
760
+ "epoch": 6.25,
761
+ "grad_norm": 2.872504949569702,
762
+ "learning_rate": 3.263923611111111e-05,
763
+ "loss": 0.0529,
764
+ "step": 50000
765
+ },
766
+ {
767
+ "epoch": 6.3125,
768
+ "grad_norm": 0.08783645182847977,
769
+ "learning_rate": 3.2465625e-05,
770
+ "loss": 0.0429,
771
+ "step": 50500
772
+ },
773
+ {
774
+ "epoch": 6.375,
775
+ "grad_norm": 8.48967170715332,
776
+ "learning_rate": 3.229201388888889e-05,
777
+ "loss": 0.0615,
778
+ "step": 51000
779
+ },
780
+ {
781
+ "epoch": 6.4375,
782
+ "grad_norm": 4.978901984031836e-07,
783
+ "learning_rate": 3.211840277777778e-05,
784
+ "loss": 0.0493,
785
+ "step": 51500
786
+ },
787
+ {
788
+ "epoch": 6.5,
789
+ "grad_norm": 1.5710222669440554e-06,
790
+ "learning_rate": 3.194479166666667e-05,
791
+ "loss": 0.0842,
792
+ "step": 52000
793
+ },
794
+ {
795
+ "epoch": 6.5625,
796
+ "grad_norm": 0.0002388143038842827,
797
+ "learning_rate": 3.177118055555556e-05,
798
+ "loss": 0.0322,
799
+ "step": 52500
800
+ },
801
+ {
802
+ "epoch": 6.625,
803
+ "grad_norm": 4.66664324960675e-08,
804
+ "learning_rate": 3.159756944444445e-05,
805
+ "loss": 0.0182,
806
+ "step": 53000
807
+ },
808
+ {
809
+ "epoch": 6.6875,
810
+ "grad_norm": 57.2918586730957,
811
+ "learning_rate": 3.142395833333334e-05,
812
+ "loss": 0.0851,
813
+ "step": 53500
814
+ },
815
+ {
816
+ "epoch": 6.75,
817
+ "grad_norm": 5.3962357924319804e-05,
818
+ "learning_rate": 3.125034722222223e-05,
819
+ "loss": 0.0644,
820
+ "step": 54000
821
+ },
822
+ {
823
+ "epoch": 6.8125,
824
+ "grad_norm": 0.006401342805474997,
825
+ "learning_rate": 3.107673611111111e-05,
826
+ "loss": 0.0943,
827
+ "step": 54500
828
+ },
829
+ {
830
+ "epoch": 6.875,
831
+ "grad_norm": 3.415437390685838e-07,
832
+ "learning_rate": 3.0903125e-05,
833
+ "loss": 0.0967,
834
+ "step": 55000
835
+ },
836
+ {
837
+ "epoch": 6.9375,
838
+ "grad_norm": 5.508160825229425e-07,
839
+ "learning_rate": 3.072951388888889e-05,
840
+ "loss": 0.0507,
841
+ "step": 55500
842
+ },
843
+ {
844
+ "epoch": 7.0,
845
+ "grad_norm": 0.04088839516043663,
846
+ "learning_rate": 3.055590277777778e-05,
847
+ "loss": 0.0139,
848
+ "step": 56000
849
+ },
850
+ {
851
+ "epoch": 7.0,
852
+ "eval_loss": 0.37575554847717285,
853
+ "eval_pearson": 0.9206240663481206,
854
+ "eval_runtime": 52.4561,
855
+ "eval_samples_per_second": 38.127,
856
+ "eval_steps_per_second": 19.064,
857
+ "step": 56000
858
+ },
859
+ {
860
+ "epoch": 7.0625,
861
+ "grad_norm": 0.004823420196771622,
862
+ "learning_rate": 3.0382291666666667e-05,
863
+ "loss": 0.0539,
864
+ "step": 56500
865
+ },
866
+ {
867
+ "epoch": 7.125,
868
+ "grad_norm": 106.49919128417969,
869
+ "learning_rate": 3.0208680555555557e-05,
870
+ "loss": 0.0232,
871
+ "step": 57000
872
+ },
873
+ {
874
+ "epoch": 7.1875,
875
+ "grad_norm": 1.074000238077133e-06,
876
+ "learning_rate": 3.0035069444444447e-05,
877
+ "loss": 0.0187,
878
+ "step": 57500
879
+ },
880
+ {
881
+ "epoch": 7.25,
882
+ "grad_norm": 0.0039020858239382505,
883
+ "learning_rate": 2.9861458333333337e-05,
884
+ "loss": 0.0472,
885
+ "step": 58000
886
+ },
887
+ {
888
+ "epoch": 7.3125,
889
+ "grad_norm": 0.0892600491642952,
890
+ "learning_rate": 2.9687847222222227e-05,
891
+ "loss": 0.0658,
892
+ "step": 58500
893
+ },
894
+ {
895
+ "epoch": 7.375,
896
+ "grad_norm": 0.00350657245144248,
897
+ "learning_rate": 2.951423611111111e-05,
898
+ "loss": 0.0456,
899
+ "step": 59000
900
+ },
901
+ {
902
+ "epoch": 7.4375,
903
+ "grad_norm": 0.0006594175356440246,
904
+ "learning_rate": 2.9340625e-05,
905
+ "loss": 0.0171,
906
+ "step": 59500
907
+ },
908
+ {
909
+ "epoch": 7.5,
910
+ "grad_norm": 92.61225128173828,
911
+ "learning_rate": 2.916701388888889e-05,
912
+ "loss": 0.0274,
913
+ "step": 60000
914
+ },
915
+ {
916
+ "epoch": 7.5625,
917
+ "grad_norm": 3.026230599445512e-09,
918
+ "learning_rate": 2.899340277777778e-05,
919
+ "loss": 0.0471,
920
+ "step": 60500
921
+ },
922
+ {
923
+ "epoch": 7.625,
924
+ "grad_norm": 1.0678179023670964e-05,
925
+ "learning_rate": 2.8819791666666666e-05,
926
+ "loss": 0.0216,
927
+ "step": 61000
928
+ },
929
+ {
930
+ "epoch": 7.6875,
931
+ "grad_norm": 5.752791912527755e-05,
932
+ "learning_rate": 2.8646180555555556e-05,
933
+ "loss": 0.0157,
934
+ "step": 61500
935
+ },
936
+ {
937
+ "epoch": 7.75,
938
+ "grad_norm": 5.118190288543701,
939
+ "learning_rate": 2.8472569444444446e-05,
940
+ "loss": 0.0616,
941
+ "step": 62000
942
+ },
943
+ {
944
+ "epoch": 7.8125,
945
+ "grad_norm": 2.0125851733610034e-05,
946
+ "learning_rate": 2.8298958333333336e-05,
947
+ "loss": 0.0783,
948
+ "step": 62500
949
+ },
950
+ {
951
+ "epoch": 7.875,
952
+ "grad_norm": 161.75416564941406,
953
+ "learning_rate": 2.8125347222222226e-05,
954
+ "loss": 0.0295,
955
+ "step": 63000
956
+ },
957
+ {
958
+ "epoch": 7.9375,
959
+ "grad_norm": 1.577711117306535e-08,
960
+ "learning_rate": 2.795173611111111e-05,
961
+ "loss": 0.0498,
962
+ "step": 63500
963
+ },
964
+ {
965
+ "epoch": 8.0,
966
+ "grad_norm": 5.166618279872637e-07,
967
+ "learning_rate": 2.7778125e-05,
968
+ "loss": 0.0397,
969
+ "step": 64000
970
+ },
971
+ {
972
+ "epoch": 8.0,
973
+ "eval_loss": 0.3336261510848999,
974
+ "eval_pearson": 0.9327475370491191,
975
+ "eval_runtime": 52.4675,
976
+ "eval_samples_per_second": 38.119,
977
+ "eval_steps_per_second": 19.059,
978
+ "step": 64000
979
+ },
980
+ {
981
+ "epoch": 8.0625,
982
+ "grad_norm": 0.0026754948776215315,
983
+ "learning_rate": 2.760451388888889e-05,
984
+ "loss": 0.026,
985
+ "step": 64500
986
+ },
987
+ {
988
+ "epoch": 8.125,
989
+ "grad_norm": 3.3581352454348234e-07,
990
+ "learning_rate": 2.743090277777778e-05,
991
+ "loss": 0.0115,
992
+ "step": 65000
993
+ },
994
+ {
995
+ "epoch": 8.1875,
996
+ "grad_norm": 2.0662416488903546e-07,
997
+ "learning_rate": 2.725729166666667e-05,
998
+ "loss": 0.012,
999
+ "step": 65500
1000
+ },
1001
+ {
1002
+ "epoch": 8.25,
1003
+ "grad_norm": 8.040846921630873e-08,
1004
+ "learning_rate": 2.7083680555555556e-05,
1005
+ "loss": 0.0406,
1006
+ "step": 66000
1007
+ },
1008
+ {
1009
+ "epoch": 8.3125,
1010
+ "grad_norm": 3.422968006816518e-07,
1011
+ "learning_rate": 2.6910069444444446e-05,
1012
+ "loss": 0.0321,
1013
+ "step": 66500
1014
+ },
1015
+ {
1016
+ "epoch": 8.375,
1017
+ "grad_norm": 0.00017860137450043112,
1018
+ "learning_rate": 2.6736458333333336e-05,
1019
+ "loss": 0.0448,
1020
+ "step": 67000
1021
+ },
1022
+ {
1023
+ "epoch": 8.4375,
1024
+ "grad_norm": 1.2621427236680915e-09,
1025
+ "learning_rate": 2.6562847222222225e-05,
1026
+ "loss": 0.0455,
1027
+ "step": 67500
1028
+ },
1029
+ {
1030
+ "epoch": 8.5,
1031
+ "grad_norm": 1.4346144325827481e-06,
1032
+ "learning_rate": 2.638923611111111e-05,
1033
+ "loss": 0.0325,
1034
+ "step": 68000
1035
+ },
1036
+ {
1037
+ "epoch": 8.5625,
1038
+ "grad_norm": 1.2407322174112778e-06,
1039
+ "learning_rate": 2.6215625e-05,
1040
+ "loss": 0.0223,
1041
+ "step": 68500
1042
+ },
1043
+ {
1044
+ "epoch": 8.625,
1045
+ "grad_norm": 3.0256799163908e-06,
1046
+ "learning_rate": 2.604201388888889e-05,
1047
+ "loss": 0.0019,
1048
+ "step": 69000
1049
+ },
1050
+ {
1051
+ "epoch": 8.6875,
1052
+ "grad_norm": 0.007253507152199745,
1053
+ "learning_rate": 2.586840277777778e-05,
1054
+ "loss": 0.0085,
1055
+ "step": 69500
1056
+ },
1057
+ {
1058
+ "epoch": 8.75,
1059
+ "grad_norm": 2.782409467272373e-07,
1060
+ "learning_rate": 2.569479166666667e-05,
1061
+ "loss": 0.0518,
1062
+ "step": 70000
1063
+ },
1064
+ {
1065
+ "epoch": 8.8125,
1066
+ "grad_norm": 0.000820077199023217,
1067
+ "learning_rate": 2.552118055555556e-05,
1068
+ "loss": 0.031,
1069
+ "step": 70500
1070
+ },
1071
+ {
1072
+ "epoch": 8.875,
1073
+ "grad_norm": 2.470728213666007e-05,
1074
+ "learning_rate": 2.5347569444444448e-05,
1075
+ "loss": 0.0354,
1076
+ "step": 71000
1077
+ },
1078
+ {
1079
+ "epoch": 8.9375,
1080
+ "grad_norm": 9.137271263170987e-05,
1081
+ "learning_rate": 2.5173958333333335e-05,
1082
+ "loss": 0.0666,
1083
+ "step": 71500
1084
+ },
1085
+ {
1086
+ "epoch": 9.0,
1087
+ "grad_norm": 0.00029885413823649287,
1088
+ "learning_rate": 2.5000347222222225e-05,
1089
+ "loss": 0.0267,
1090
+ "step": 72000
1091
+ },
1092
+ {
1093
+ "epoch": 9.0,
1094
+ "eval_loss": 0.37894001603126526,
1095
+ "eval_pearson": 0.9279985680079542,
1096
+ "eval_runtime": 52.4816,
1097
+ "eval_samples_per_second": 38.109,
1098
+ "eval_steps_per_second": 19.054,
1099
+ "step": 72000
1100
+ },
1101
+ {
1102
+ "epoch": 9.0625,
1103
+ "grad_norm": 6.724835839122534e-05,
1104
+ "learning_rate": 2.482673611111111e-05,
1105
+ "loss": 0.0044,
1106
+ "step": 72500
1107
+ },
1108
+ {
1109
+ "epoch": 9.125,
1110
+ "grad_norm": 9.228666164595722e-10,
1111
+ "learning_rate": 2.4653125e-05,
1112
+ "loss": 0.0095,
1113
+ "step": 73000
1114
+ },
1115
+ {
1116
+ "epoch": 9.1875,
1117
+ "grad_norm": 0.00011938459647353739,
1118
+ "learning_rate": 2.447951388888889e-05,
1119
+ "loss": 0.0384,
1120
+ "step": 73500
1121
+ },
1122
+ {
1123
+ "epoch": 9.25,
1124
+ "grad_norm": 1.6898056287573127e-09,
1125
+ "learning_rate": 2.4305902777777778e-05,
1126
+ "loss": 0.0182,
1127
+ "step": 74000
1128
+ },
1129
+ {
1130
+ "epoch": 9.3125,
1131
+ "grad_norm": 5.753568288469069e-09,
1132
+ "learning_rate": 2.4132291666666668e-05,
1133
+ "loss": 0.0075,
1134
+ "step": 74500
1135
+ },
1136
+ {
1137
+ "epoch": 9.375,
1138
+ "grad_norm": 5.144208614638046e-08,
1139
+ "learning_rate": 2.3958680555555558e-05,
1140
+ "loss": 0.0172,
1141
+ "step": 75000
1142
+ },
1143
+ {
1144
+ "epoch": 9.4375,
1145
+ "grad_norm": 9.800347200439319e-10,
1146
+ "learning_rate": 2.3785069444444448e-05,
1147
+ "loss": 0.0431,
1148
+ "step": 75500
1149
+ },
1150
+ {
1151
+ "epoch": 9.5,
1152
+ "grad_norm": 5.440585135185749e-11,
1153
+ "learning_rate": 2.3611458333333334e-05,
1154
+ "loss": 0.0109,
1155
+ "step": 76000
1156
+ },
1157
+ {
1158
+ "epoch": 9.5625,
1159
+ "grad_norm": 0.00019604770932346582,
1160
+ "learning_rate": 2.3437847222222224e-05,
1161
+ "loss": 0.0284,
1162
+ "step": 76500
1163
+ },
1164
+ {
1165
+ "epoch": 9.625,
1166
+ "grad_norm": 1.242908239364624,
1167
+ "learning_rate": 2.3264236111111114e-05,
1168
+ "loss": 0.0405,
1169
+ "step": 77000
1170
+ },
1171
+ {
1172
+ "epoch": 9.6875,
1173
+ "grad_norm": 1.540728953841608e-05,
1174
+ "learning_rate": 2.3090625e-05,
1175
+ "loss": 0.0435,
1176
+ "step": 77500
1177
+ },
1178
+ {
1179
+ "epoch": 9.75,
1180
+ "grad_norm": 0.00013433759158942848,
1181
+ "learning_rate": 2.291701388888889e-05,
1182
+ "loss": 0.0181,
1183
+ "step": 78000
1184
+ },
1185
+ {
1186
+ "epoch": 9.8125,
1187
+ "grad_norm": 3.088209687973631e-10,
1188
+ "learning_rate": 2.2743402777777777e-05,
1189
+ "loss": 0.0228,
1190
+ "step": 78500
1191
+ },
1192
+ {
1193
+ "epoch": 9.875,
1194
+ "grad_norm": 0.000814907078165561,
1195
+ "learning_rate": 2.2569791666666667e-05,
1196
+ "loss": 0.0499,
1197
+ "step": 79000
1198
+ },
1199
+ {
1200
+ "epoch": 9.9375,
1201
+ "grad_norm": 1.274260625905299e-07,
1202
+ "learning_rate": 2.2396180555555557e-05,
1203
+ "loss": 0.0316,
1204
+ "step": 79500
1205
+ },
1206
+ {
1207
+ "epoch": 10.0,
1208
+ "grad_norm": 4.301631997805089e-05,
1209
+ "learning_rate": 2.2222569444444447e-05,
1210
+ "loss": 0.015,
1211
+ "step": 80000
1212
+ },
1213
+ {
1214
+ "epoch": 10.0,
1215
+ "eval_loss": 0.38902410864830017,
1216
+ "eval_pearson": 0.9249309324232664,
1217
+ "eval_runtime": 52.3807,
1218
+ "eval_samples_per_second": 38.182,
1219
+ "eval_steps_per_second": 19.091,
1220
+ "step": 80000
1221
+ },
1222
+ {
1223
+ "epoch": 10.0625,
1224
+ "grad_norm": 1.7468665403086447e-10,
1225
+ "learning_rate": 2.2048958333333333e-05,
1226
+ "loss": 0.0081,
1227
+ "step": 80500
1228
+ },
1229
+ {
1230
+ "epoch": 10.125,
1231
+ "grad_norm": 6.71422021696344e-05,
1232
+ "learning_rate": 2.1875347222222223e-05,
1233
+ "loss": 0.0143,
1234
+ "step": 81000
1235
+ },
1236
+ {
1237
+ "epoch": 10.1875,
1238
+ "grad_norm": 3.1802871944819344e-06,
1239
+ "learning_rate": 2.1701736111111113e-05,
1240
+ "loss": 0.029,
1241
+ "step": 81500
1242
+ },
1243
+ {
1244
+ "epoch": 10.25,
1245
+ "grad_norm": 0.014791320078074932,
1246
+ "learning_rate": 2.1528125000000003e-05,
1247
+ "loss": 0.0054,
1248
+ "step": 82000
1249
+ },
1250
+ {
1251
+ "epoch": 10.3125,
1252
+ "grad_norm": 2.0462434235923865e-07,
1253
+ "learning_rate": 2.135451388888889e-05,
1254
+ "loss": 0.0436,
1255
+ "step": 82500
1256
+ },
1257
+ {
1258
+ "epoch": 10.375,
1259
+ "grad_norm": 1.3791065216064453,
1260
+ "learning_rate": 2.1180902777777776e-05,
1261
+ "loss": 0.0181,
1262
+ "step": 83000
1263
+ },
1264
+ {
1265
+ "epoch": 10.4375,
1266
+ "grad_norm": 0.002008361741900444,
1267
+ "learning_rate": 2.1007291666666666e-05,
1268
+ "loss": 0.0082,
1269
+ "step": 83500
1270
+ },
1271
+ {
1272
+ "epoch": 10.5,
1273
+ "grad_norm": 5.804303704337599e-09,
1274
+ "learning_rate": 2.0833680555555556e-05,
1275
+ "loss": 0.0249,
1276
+ "step": 84000
1277
+ },
1278
+ {
1279
+ "epoch": 10.5625,
1280
+ "grad_norm": 0.0007163327536545694,
1281
+ "learning_rate": 2.0660069444444446e-05,
1282
+ "loss": 0.0112,
1283
+ "step": 84500
1284
+ },
1285
+ {
1286
+ "epoch": 10.625,
1287
+ "grad_norm": 0.0001620600960450247,
1288
+ "learning_rate": 2.0486458333333333e-05,
1289
+ "loss": 0.0295,
1290
+ "step": 85000
1291
+ },
1292
+ {
1293
+ "epoch": 10.6875,
1294
+ "grad_norm": 0.05068128928542137,
1295
+ "learning_rate": 2.0312847222222223e-05,
1296
+ "loss": 0.0223,
1297
+ "step": 85500
1298
+ },
1299
+ {
1300
+ "epoch": 10.75,
1301
+ "grad_norm": 0.0007038409821689129,
1302
+ "learning_rate": 2.0139236111111113e-05,
1303
+ "loss": 0.0192,
1304
+ "step": 86000
1305
+ },
1306
+ {
1307
+ "epoch": 10.8125,
1308
+ "grad_norm": 0.024000702425837517,
1309
+ "learning_rate": 1.9965625000000002e-05,
1310
+ "loss": 0.0249,
1311
+ "step": 86500
1312
+ },
1313
+ {
1314
+ "epoch": 10.875,
1315
+ "grad_norm": 3.588341712656984e-07,
1316
+ "learning_rate": 1.9792013888888892e-05,
1317
+ "loss": 0.0429,
1318
+ "step": 87000
1319
+ },
1320
+ {
1321
+ "epoch": 10.9375,
1322
+ "grad_norm": 1.5524047114467976e-07,
1323
+ "learning_rate": 1.961840277777778e-05,
1324
+ "loss": 0.0188,
1325
+ "step": 87500
1326
+ },
1327
+ {
1328
+ "epoch": 11.0,
1329
+ "grad_norm": 2.524126614389388e-07,
1330
+ "learning_rate": 1.944479166666667e-05,
1331
+ "loss": 0.0217,
1332
+ "step": 88000
1333
+ },
1334
+ {
1335
+ "epoch": 11.0,
1336
+ "eval_loss": 0.39052143692970276,
1337
+ "eval_pearson": 0.936161178019818,
1338
+ "eval_runtime": 52.432,
1339
+ "eval_samples_per_second": 38.145,
1340
+ "eval_steps_per_second": 19.072,
1341
+ "step": 88000
1342
+ },
1343
+ {
1344
+ "epoch": 11.0625,
1345
+ "grad_norm": 0.0005805569817312062,
1346
+ "learning_rate": 1.9271180555555555e-05,
1347
+ "loss": 0.0255,
1348
+ "step": 88500
1349
+ },
1350
+ {
1351
+ "epoch": 11.125,
1352
+ "grad_norm": 4.623345546406199e-07,
1353
+ "learning_rate": 1.9097569444444445e-05,
1354
+ "loss": 0.0078,
1355
+ "step": 89000
1356
+ },
1357
+ {
1358
+ "epoch": 11.1875,
1359
+ "grad_norm": 5.301876715435583e-09,
1360
+ "learning_rate": 1.8923958333333332e-05,
1361
+ "loss": 0.005,
1362
+ "step": 89500
1363
+ },
1364
+ {
1365
+ "epoch": 11.25,
1366
+ "grad_norm": 0.09818815439939499,
1367
+ "learning_rate": 1.8750347222222222e-05,
1368
+ "loss": 0.008,
1369
+ "step": 90000
1370
+ },
1371
+ {
1372
+ "epoch": 11.3125,
1373
+ "grad_norm": 1.8287735656485893e-05,
1374
+ "learning_rate": 1.8576736111111112e-05,
1375
+ "loss": 0.0021,
1376
+ "step": 90500
1377
+ },
1378
+ {
1379
+ "epoch": 11.375,
1380
+ "grad_norm": 9.81485072770738e-07,
1381
+ "learning_rate": 1.8403125000000002e-05,
1382
+ "loss": 0.014,
1383
+ "step": 91000
1384
+ },
1385
+ {
1386
+ "epoch": 11.4375,
1387
+ "grad_norm": 0.006411096081137657,
1388
+ "learning_rate": 1.8229513888888892e-05,
1389
+ "loss": 0.0128,
1390
+ "step": 91500
1391
+ },
1392
+ {
1393
+ "epoch": 11.5,
1394
+ "grad_norm": 4.448479778984549e-11,
1395
+ "learning_rate": 1.8055902777777778e-05,
1396
+ "loss": 0.0023,
1397
+ "step": 92000
1398
+ },
1399
+ {
1400
+ "epoch": 11.5625,
1401
+ "grad_norm": 0.012693402357399464,
1402
+ "learning_rate": 1.7882291666666668e-05,
1403
+ "loss": 0.0344,
1404
+ "step": 92500
1405
+ },
1406
+ {
1407
+ "epoch": 11.625,
1408
+ "grad_norm": 6.370872540628625e-08,
1409
+ "learning_rate": 1.7708680555555558e-05,
1410
+ "loss": 0.0258,
1411
+ "step": 93000
1412
+ },
1413
+ {
1414
+ "epoch": 11.6875,
1415
+ "grad_norm": 9.032481429471773e-09,
1416
+ "learning_rate": 1.7535069444444445e-05,
1417
+ "loss": 0.0112,
1418
+ "step": 93500
1419
+ },
1420
+ {
1421
+ "epoch": 11.75,
1422
+ "grad_norm": 0.001719271531328559,
1423
+ "learning_rate": 1.7361458333333335e-05,
1424
+ "loss": 0.0275,
1425
+ "step": 94000
1426
+ },
1427
+ {
1428
+ "epoch": 11.8125,
1429
+ "grad_norm": 7.162652036640793e-05,
1430
+ "learning_rate": 1.718784722222222e-05,
1431
+ "loss": 0.0119,
1432
+ "step": 94500
1433
+ },
1434
+ {
1435
+ "epoch": 11.875,
1436
+ "grad_norm": 1.2189951803520671e-06,
1437
+ "learning_rate": 1.701423611111111e-05,
1438
+ "loss": 0.0392,
1439
+ "step": 95000
1440
+ },
1441
+ {
1442
+ "epoch": 11.9375,
1443
+ "grad_norm": 5.709237484552432e-06,
1444
+ "learning_rate": 1.6840625e-05,
1445
+ "loss": 0.0341,
1446
+ "step": 95500
1447
+ },
1448
+ {
1449
+ "epoch": 12.0,
1450
+ "grad_norm": 1.2266503290447872e-05,
1451
+ "learning_rate": 1.666701388888889e-05,
1452
+ "loss": 0.1026,
1453
+ "step": 96000
1454
+ },
1455
+ {
1456
+ "epoch": 12.0,
1457
+ "eval_loss": 0.42006340622901917,
1458
+ "eval_pearson": 0.9249266863163004,
1459
+ "eval_runtime": 52.4951,
1460
+ "eval_samples_per_second": 38.099,
1461
+ "eval_steps_per_second": 19.049,
1462
+ "step": 96000
1463
+ },
1464
+ {
1465
+ "epoch": 12.0625,
1466
+ "grad_norm": 1.2190711773385488e-09,
1467
+ "learning_rate": 1.6493402777777778e-05,
1468
+ "loss": 0.0118,
1469
+ "step": 96500
1470
+ },
1471
+ {
1472
+ "epoch": 12.125,
1473
+ "grad_norm": 9.660718660597922e-07,
1474
+ "learning_rate": 1.6319791666666668e-05,
1475
+ "loss": 0.0021,
1476
+ "step": 97000
1477
+ },
1478
+ {
1479
+ "epoch": 12.1875,
1480
+ "grad_norm": 0.0003258072247263044,
1481
+ "learning_rate": 1.6146180555555557e-05,
1482
+ "loss": 0.011,
1483
+ "step": 97500
1484
+ },
1485
+ {
1486
+ "epoch": 12.25,
1487
+ "grad_norm": 0.00024601773475296795,
1488
+ "learning_rate": 1.5972569444444447e-05,
1489
+ "loss": 0.0161,
1490
+ "step": 98000
1491
+ },
1492
+ {
1493
+ "epoch": 12.3125,
1494
+ "grad_norm": 2.0050613613875612e-07,
1495
+ "learning_rate": 1.5798958333333334e-05,
1496
+ "loss": 0.0062,
1497
+ "step": 98500
1498
+ },
1499
+ {
1500
+ "epoch": 12.375,
1501
+ "grad_norm": 0.00019162562966812402,
1502
+ "learning_rate": 1.5625347222222224e-05,
1503
+ "loss": 0.0017,
1504
+ "step": 99000
1505
+ },
1506
+ {
1507
+ "epoch": 12.4375,
1508
+ "grad_norm": 5.855550853084424e-07,
1509
+ "learning_rate": 1.545173611111111e-05,
1510
+ "loss": 0.011,
1511
+ "step": 99500
1512
+ },
1513
+ {
1514
+ "epoch": 12.5,
1515
+ "grad_norm": 5.200939631322399e-05,
1516
+ "learning_rate": 1.5278125e-05,
1517
+ "loss": 0.0625,
1518
+ "step": 100000
1519
+ },
1520
+ {
1521
+ "epoch": 12.5625,
1522
+ "grad_norm": 0.0051911999471485615,
1523
+ "learning_rate": 1.510451388888889e-05,
1524
+ "loss": 0.0223,
1525
+ "step": 100500
1526
+ },
1527
+ {
1528
+ "epoch": 12.625,
1529
+ "grad_norm": 0.00023108582536224276,
1530
+ "learning_rate": 1.4930902777777777e-05,
1531
+ "loss": 0.0184,
1532
+ "step": 101000
1533
+ },
1534
+ {
1535
+ "epoch": 12.6875,
1536
+ "grad_norm": 1.2751560461765621e-05,
1537
+ "learning_rate": 1.4757291666666667e-05,
1538
+ "loss": 0.0325,
1539
+ "step": 101500
1540
+ },
1541
+ {
1542
+ "epoch": 12.75,
1543
+ "grad_norm": 0.07260618358850479,
1544
+ "learning_rate": 1.4583680555555557e-05,
1545
+ "loss": 0.0472,
1546
+ "step": 102000
1547
+ },
1548
+ {
1549
+ "epoch": 12.8125,
1550
+ "grad_norm": 1.3546050467994064e-06,
1551
+ "learning_rate": 1.4410069444444447e-05,
1552
+ "loss": 0.0326,
1553
+ "step": 102500
1554
+ },
1555
+ {
1556
+ "epoch": 12.875,
1557
+ "grad_norm": 0.00040618935599923134,
1558
+ "learning_rate": 1.4236458333333333e-05,
1559
+ "loss": 0.0092,
1560
+ "step": 103000
1561
+ },
1562
+ {
1563
+ "epoch": 12.9375,
1564
+ "grad_norm": 3.1089444973986247e-07,
1565
+ "learning_rate": 1.4062847222222223e-05,
1566
+ "loss": 0.0493,
1567
+ "step": 103500
1568
+ },
1569
+ {
1570
+ "epoch": 13.0,
1571
+ "grad_norm": 0.02031463012099266,
1572
+ "learning_rate": 1.3889236111111111e-05,
1573
+ "loss": 0.0344,
1574
+ "step": 104000
1575
+ },
1576
+ {
1577
+ "epoch": 13.0,
1578
+ "eval_loss": 0.3848821818828583,
1579
+ "eval_pearson": 0.9320737941331698,
1580
+ "eval_runtime": 52.3286,
1581
+ "eval_samples_per_second": 38.22,
1582
+ "eval_steps_per_second": 19.11,
1583
+ "step": 104000
1584
+ },
1585
+ {
1586
+ "epoch": 13.0625,
1587
+ "grad_norm": 5.390070782596013e-06,
1588
+ "learning_rate": 1.3715625000000001e-05,
1589
+ "loss": 0.0024,
1590
+ "step": 104500
1591
+ },
1592
+ {
1593
+ "epoch": 13.125,
1594
+ "grad_norm": 0.0009596606250852346,
1595
+ "learning_rate": 1.3542013888888891e-05,
1596
+ "loss": 0.0002,
1597
+ "step": 105000
1598
+ },
1599
+ {
1600
+ "epoch": 13.1875,
1601
+ "grad_norm": 1.6519630889888504e-06,
1602
+ "learning_rate": 1.3368402777777778e-05,
1603
+ "loss": 0.0079,
1604
+ "step": 105500
1605
+ },
1606
+ {
1607
+ "epoch": 13.25,
1608
+ "grad_norm": 2.448989988579342e-08,
1609
+ "learning_rate": 1.3194791666666668e-05,
1610
+ "loss": 0.0153,
1611
+ "step": 106000
1612
+ },
1613
+ {
1614
+ "epoch": 13.3125,
1615
+ "grad_norm": 0.0002976028772536665,
1616
+ "learning_rate": 1.3021180555555556e-05,
1617
+ "loss": 0.0039,
1618
+ "step": 106500
1619
+ },
1620
+ {
1621
+ "epoch": 13.375,
1622
+ "grad_norm": 0.00019340288417879492,
1623
+ "learning_rate": 1.2847569444444446e-05,
1624
+ "loss": 0.0163,
1625
+ "step": 107000
1626
+ },
1627
+ {
1628
+ "epoch": 13.4375,
1629
+ "grad_norm": 0.0057904901914298534,
1630
+ "learning_rate": 1.2673958333333333e-05,
1631
+ "loss": 0.0122,
1632
+ "step": 107500
1633
+ },
1634
+ {
1635
+ "epoch": 13.5,
1636
+ "grad_norm": 9.801337910175789e-06,
1637
+ "learning_rate": 1.2500347222222222e-05,
1638
+ "loss": 0.0379,
1639
+ "step": 108000
1640
+ },
1641
+ {
1642
+ "epoch": 13.5625,
1643
+ "grad_norm": 1.4482387769021443e-06,
1644
+ "learning_rate": 1.2326736111111112e-05,
1645
+ "loss": 0.0114,
1646
+ "step": 108500
1647
+ },
1648
+ {
1649
+ "epoch": 13.625,
1650
+ "grad_norm": 2.1305972040863708e-05,
1651
+ "learning_rate": 1.2153125e-05,
1652
+ "loss": 0.018,
1653
+ "step": 109000
1654
+ },
1655
+ {
1656
+ "epoch": 13.6875,
1657
+ "grad_norm": 0.09945420920848846,
1658
+ "learning_rate": 1.1979513888888889e-05,
1659
+ "loss": 0.0726,
1660
+ "step": 109500
1661
+ },
1662
+ {
1663
+ "epoch": 13.75,
1664
+ "grad_norm": 5.7829329307423905e-06,
1665
+ "learning_rate": 1.1805902777777779e-05,
1666
+ "loss": 0.0193,
1667
+ "step": 110000
1668
+ },
1669
+ {
1670
+ "epoch": 13.8125,
1671
+ "grad_norm": 6.558164386660792e-06,
1672
+ "learning_rate": 1.1632291666666667e-05,
1673
+ "loss": 0.0129,
1674
+ "step": 110500
1675
+ },
1676
+ {
1677
+ "epoch": 13.875,
1678
+ "grad_norm": 4.0651830346405404e-08,
1679
+ "learning_rate": 1.1458680555555557e-05,
1680
+ "loss": 0.0389,
1681
+ "step": 111000
1682
+ },
1683
+ {
1684
+ "epoch": 13.9375,
1685
+ "grad_norm": 1.2806684601684992e-08,
1686
+ "learning_rate": 1.1285069444444445e-05,
1687
+ "loss": 0.0071,
1688
+ "step": 111500
1689
+ },
1690
+ {
1691
+ "epoch": 14.0,
1692
+ "grad_norm": 0.11720628291368484,
1693
+ "learning_rate": 1.1111458333333333e-05,
1694
+ "loss": 0.0115,
1695
+ "step": 112000
1696
+ },
1697
+ {
1698
+ "epoch": 14.0,
1699
+ "eval_loss": 0.4008629620075226,
1700
+ "eval_pearson": 0.9287046075964228,
1701
+ "eval_runtime": 52.1174,
1702
+ "eval_samples_per_second": 38.375,
1703
+ "eval_steps_per_second": 19.187,
1704
+ "step": 112000
1705
+ },
1706
+ {
1707
+ "epoch": 14.0625,
1708
+ "grad_norm": 3.696676298403645e-09,
1709
+ "learning_rate": 1.0937847222222222e-05,
1710
+ "loss": 0.002,
1711
+ "step": 112500
1712
+ },
1713
+ {
1714
+ "epoch": 14.125,
1715
+ "grad_norm": 1.5702152040830697e-06,
1716
+ "learning_rate": 1.0764236111111112e-05,
1717
+ "loss": 0.011,
1718
+ "step": 113000
1719
+ },
1720
+ {
1721
+ "epoch": 14.1875,
1722
+ "grad_norm": 5.9359957958804443e-05,
1723
+ "learning_rate": 1.0590625e-05,
1724
+ "loss": 0.002,
1725
+ "step": 113500
1726
+ },
1727
+ {
1728
+ "epoch": 14.25,
1729
+ "grad_norm": 1.7063765331282177e-11,
1730
+ "learning_rate": 1.041701388888889e-05,
1731
+ "loss": 0.0092,
1732
+ "step": 114000
1733
+ },
1734
+ {
1735
+ "epoch": 14.3125,
1736
+ "grad_norm": 0.0013318562414497137,
1737
+ "learning_rate": 1.0243402777777778e-05,
1738
+ "loss": 0.0037,
1739
+ "step": 114500
1740
+ },
1741
+ {
1742
+ "epoch": 14.375,
1743
+ "grad_norm": 0.00013518838386517018,
1744
+ "learning_rate": 1.0069791666666666e-05,
1745
+ "loss": 0.0253,
1746
+ "step": 115000
1747
+ },
1748
+ {
1749
+ "epoch": 14.4375,
1750
+ "grad_norm": 0.0004931968287564814,
1751
+ "learning_rate": 9.896180555555556e-06,
1752
+ "loss": 0.0002,
1753
+ "step": 115500
1754
+ },
1755
+ {
1756
+ "epoch": 14.5,
1757
+ "grad_norm": 3.0277399787337345e-07,
1758
+ "learning_rate": 9.722569444444445e-06,
1759
+ "loss": 0.0219,
1760
+ "step": 116000
1761
+ },
1762
+ {
1763
+ "epoch": 14.5625,
1764
+ "grad_norm": 0.005195027217268944,
1765
+ "learning_rate": 9.548958333333334e-06,
1766
+ "loss": 0.0144,
1767
+ "step": 116500
1768
+ },
1769
+ {
1770
+ "epoch": 14.625,
1771
+ "grad_norm": 0.028845345601439476,
1772
+ "learning_rate": 9.375347222222223e-06,
1773
+ "loss": 0.0147,
1774
+ "step": 117000
1775
+ },
1776
+ {
1777
+ "epoch": 14.6875,
1778
+ "grad_norm": 2.050080212256944e-07,
1779
+ "learning_rate": 9.201736111111111e-06,
1780
+ "loss": 0.047,
1781
+ "step": 117500
1782
+ },
1783
+ {
1784
+ "epoch": 14.75,
1785
+ "grad_norm": 2.6781076911674973e-08,
1786
+ "learning_rate": 9.028125e-06,
1787
+ "loss": 0.023,
1788
+ "step": 118000
1789
+ },
1790
+ {
1791
+ "epoch": 14.8125,
1792
+ "grad_norm": 4.3490285861480515e-07,
1793
+ "learning_rate": 8.85451388888889e-06,
1794
+ "loss": 0.0397,
1795
+ "step": 118500
1796
+ },
1797
+ {
1798
+ "epoch": 14.875,
1799
+ "grad_norm": 5.553416121983901e-05,
1800
+ "learning_rate": 8.680902777777779e-06,
1801
+ "loss": 0.0129,
1802
+ "step": 119000
1803
+ },
1804
+ {
1805
+ "epoch": 14.9375,
1806
+ "grad_norm": 0.0018387527670711279,
1807
+ "learning_rate": 8.507291666666667e-06,
1808
+ "loss": 0.0117,
1809
+ "step": 119500
1810
+ },
1811
+ {
1812
+ "epoch": 15.0,
1813
+ "grad_norm": 3.0822722846268746e-11,
1814
+ "learning_rate": 8.333680555555556e-06,
1815
+ "loss": 0.0289,
1816
+ "step": 120000
1817
+ },
1818
+ {
1819
+ "epoch": 15.0,
1820
+ "eval_loss": 0.4116508662700653,
1821
+ "eval_pearson": 0.9338347129537201,
1822
+ "eval_runtime": 52.0977,
1823
+ "eval_samples_per_second": 38.389,
1824
+ "eval_steps_per_second": 19.195,
1825
+ "step": 120000
1826
+ },
1827
+ {
1828
+ "epoch": 15.0625,
1829
+ "grad_norm": 0.001994462450966239,
1830
+ "learning_rate": 8.160069444444444e-06,
1831
+ "loss": 0.0078,
1832
+ "step": 120500
1833
+ },
1834
+ {
1835
+ "epoch": 15.125,
1836
+ "grad_norm": 3.360041411770709e-10,
1837
+ "learning_rate": 7.986458333333334e-06,
1838
+ "loss": 0.0157,
1839
+ "step": 121000
1840
+ },
1841
+ {
1842
+ "epoch": 15.1875,
1843
+ "grad_norm": 9.282373980568082e-07,
1844
+ "learning_rate": 7.812847222222222e-06,
1845
+ "loss": 0.0078,
1846
+ "step": 121500
1847
+ },
1848
+ {
1849
+ "epoch": 15.25,
1850
+ "grad_norm": 1.6110238698630042e-09,
1851
+ "learning_rate": 7.639236111111112e-06,
1852
+ "loss": 0.026,
1853
+ "step": 122000
1854
+ },
1855
+ {
1856
+ "epoch": 15.3125,
1857
+ "grad_norm": 2.1387499145930633e-05,
1858
+ "learning_rate": 7.465624999999999e-06,
1859
+ "loss": 0.0182,
1860
+ "step": 122500
1861
+ },
1862
+ {
1863
+ "epoch": 15.375,
1864
+ "grad_norm": 5.649494067005989e-11,
1865
+ "learning_rate": 7.292013888888889e-06,
1866
+ "loss": 0.0106,
1867
+ "step": 123000
1868
+ },
1869
+ {
1870
+ "epoch": 15.4375,
1871
+ "grad_norm": 0.008713332004845142,
1872
+ "learning_rate": 7.118402777777778e-06,
1873
+ "loss": 0.0361,
1874
+ "step": 123500
1875
+ },
1876
+ {
1877
+ "epoch": 15.5,
1878
+ "grad_norm": 1.6483255649291095e-08,
1879
+ "learning_rate": 6.944791666666667e-06,
1880
+ "loss": 0.0187,
1881
+ "step": 124000
1882
+ },
1883
+ {
1884
+ "epoch": 15.5625,
1885
+ "grad_norm": 0.002335034077987075,
1886
+ "learning_rate": 6.7711805555555566e-06,
1887
+ "loss": 0.0055,
1888
+ "step": 124500
1889
+ },
1890
+ {
1891
+ "epoch": 15.625,
1892
+ "grad_norm": 0.03660840913653374,
1893
+ "learning_rate": 6.597569444444445e-06,
1894
+ "loss": 0.0327,
1895
+ "step": 125000
1896
+ },
1897
+ {
1898
+ "epoch": 15.6875,
1899
+ "grad_norm": 1.491520379204303e-06,
1900
+ "learning_rate": 6.423958333333334e-06,
1901
+ "loss": 0.021,
1902
+ "step": 125500
1903
+ },
1904
+ {
1905
+ "epoch": 15.75,
1906
+ "grad_norm": 1.702046326101936e-08,
1907
+ "learning_rate": 6.250347222222222e-06,
1908
+ "loss": 0.0192,
1909
+ "step": 126000
1910
+ },
1911
+ {
1912
+ "epoch": 15.8125,
1913
+ "grad_norm": 4.671832812164212e-06,
1914
+ "learning_rate": 6.076736111111111e-06,
1915
+ "loss": 0.0218,
1916
+ "step": 126500
1917
+ },
1918
+ {
1919
+ "epoch": 15.875,
1920
+ "grad_norm": 3.007305167557206e-06,
1921
+ "learning_rate": 5.903125e-06,
1922
+ "loss": 0.0071,
1923
+ "step": 127000
1924
+ },
1925
+ {
1926
+ "epoch": 15.9375,
1927
+ "grad_norm": 0.00012980301107745618,
1928
+ "learning_rate": 5.7295138888888894e-06,
1929
+ "loss": 0.0128,
1930
+ "step": 127500
1931
+ },
1932
+ {
1933
+ "epoch": 16.0,
1934
+ "grad_norm": 4.560336890335748e-07,
1935
+ "learning_rate": 5.555902777777778e-06,
1936
+ "loss": 0.0095,
1937
+ "step": 128000
1938
+ },
1939
+ {
1940
+ "epoch": 16.0,
1941
+ "eval_loss": 0.39633870124816895,
1942
+ "eval_pearson": 0.9361489441284587,
1943
+ "eval_runtime": 52.1321,
1944
+ "eval_samples_per_second": 38.364,
1945
+ "eval_steps_per_second": 19.182,
1946
+ "step": 128000
1947
+ },
1948
+ {
1949
+ "epoch": 16.0625,
1950
+ "grad_norm": 4.1626062596833435e-09,
1951
+ "learning_rate": 5.382291666666667e-06,
1952
+ "loss": 0.0022,
1953
+ "step": 128500
1954
+ },
1955
+ {
1956
+ "epoch": 16.125,
1957
+ "grad_norm": 0.001842322526499629,
1958
+ "learning_rate": 5.208680555555556e-06,
1959
+ "loss": 0.0141,
1960
+ "step": 129000
1961
+ },
1962
+ {
1963
+ "epoch": 16.1875,
1964
+ "grad_norm": 3.6366621714023495e-08,
1965
+ "learning_rate": 5.035069444444444e-06,
1966
+ "loss": 0.0233,
1967
+ "step": 129500
1968
+ },
1969
+ {
1970
+ "epoch": 16.25,
1971
+ "grad_norm": 1.9658939436340006e-06,
1972
+ "learning_rate": 4.861458333333334e-06,
1973
+ "loss": 0.0049,
1974
+ "step": 130000
1975
+ },
1976
+ {
1977
+ "epoch": 16.3125,
1978
+ "grad_norm": 8.618873835075647e-06,
1979
+ "learning_rate": 4.687847222222222e-06,
1980
+ "loss": 0.0038,
1981
+ "step": 130500
1982
+ },
1983
+ {
1984
+ "epoch": 16.375,
1985
+ "grad_norm": 3.656549552033539e-08,
1986
+ "learning_rate": 4.514236111111111e-06,
1987
+ "loss": 0.0025,
1988
+ "step": 131000
1989
+ },
1990
+ {
1991
+ "epoch": 16.4375,
1992
+ "grad_norm": 3.9857341107563116e-06,
1993
+ "learning_rate": 4.3406250000000005e-06,
1994
+ "loss": 0.0113,
1995
+ "step": 131500
1996
+ },
1997
+ {
1998
+ "epoch": 16.5,
1999
+ "grad_norm": 1.3211584359851258e-07,
2000
+ "learning_rate": 4.167013888888889e-06,
2001
+ "loss": 0.0091,
2002
+ "step": 132000
2003
+ },
2004
+ {
2005
+ "epoch": 16.5625,
2006
+ "grad_norm": 0.012276459485292435,
2007
+ "learning_rate": 3.993402777777778e-06,
2008
+ "loss": 0.0068,
2009
+ "step": 132500
2010
+ },
2011
+ {
2012
+ "epoch": 16.625,
2013
+ "grad_norm": 0.0287026297301054,
2014
+ "learning_rate": 3.819791666666667e-06,
2015
+ "loss": 0.0386,
2016
+ "step": 133000
2017
+ },
2018
+ {
2019
+ "epoch": 16.6875,
2020
+ "grad_norm": 1.2811213423447043e-07,
2021
+ "learning_rate": 3.6461805555555556e-06,
2022
+ "loss": 0.0,
2023
+ "step": 133500
2024
+ },
2025
+ {
2026
+ "epoch": 16.75,
2027
+ "grad_norm": 3.6252565394079284e-08,
2028
+ "learning_rate": 3.4725694444444442e-06,
2029
+ "loss": 0.0048,
2030
+ "step": 134000
2031
+ },
2032
+ {
2033
+ "epoch": 16.8125,
2034
+ "grad_norm": 0.007136507425457239,
2035
+ "learning_rate": 3.2989583333333338e-06,
2036
+ "loss": 0.0093,
2037
+ "step": 134500
2038
+ },
2039
+ {
2040
+ "epoch": 16.875,
2041
+ "grad_norm": 0.00022970048303250223,
2042
+ "learning_rate": 3.1253472222222224e-06,
2043
+ "loss": 0.0201,
2044
+ "step": 135000
2045
+ },
2046
+ {
2047
+ "epoch": 16.9375,
2048
+ "grad_norm": 1.450917920919892e-06,
2049
+ "learning_rate": 2.9517361111111115e-06,
2050
+ "loss": 0.0207,
2051
+ "step": 135500
2052
+ },
2053
+ {
2054
+ "epoch": 17.0,
2055
+ "grad_norm": 4.926808472305311e-08,
2056
+ "learning_rate": 2.778125e-06,
2057
+ "loss": 0.0254,
2058
+ "step": 136000
2059
+ },
2060
+ {
2061
+ "epoch": 17.0,
2062
+ "eval_loss": 0.36975476145744324,
2063
+ "eval_pearson": 0.9265418354468642,
2064
+ "eval_runtime": 52.4565,
2065
+ "eval_samples_per_second": 38.127,
2066
+ "eval_steps_per_second": 19.063,
2067
+ "step": 136000
2068
+ },
2069
+ {
2070
+ "epoch": 17.0625,
2071
+ "grad_norm": 9.686777205017427e-13,
2072
+ "learning_rate": 2.604513888888889e-06,
2073
+ "loss": 0.0023,
2074
+ "step": 136500
2075
+ },
2076
+ {
2077
+ "epoch": 17.125,
2078
+ "grad_norm": 1.9179442460881546e-06,
2079
+ "learning_rate": 2.430902777777778e-06,
2080
+ "loss": 0.0082,
2081
+ "step": 137000
2082
+ },
2083
+ {
2084
+ "epoch": 17.1875,
2085
+ "grad_norm": 1.2164252439106349e-05,
2086
+ "learning_rate": 2.257291666666667e-06,
2087
+ "loss": 0.0046,
2088
+ "step": 137500
2089
+ },
2090
+ {
2091
+ "epoch": 17.25,
2092
+ "grad_norm": 4.2734385474751946e-10,
2093
+ "learning_rate": 2.0836805555555557e-06,
2094
+ "loss": 0.0019,
2095
+ "step": 138000
2096
+ },
2097
+ {
2098
+ "epoch": 17.3125,
2099
+ "grad_norm": 0.0007651239866390824,
2100
+ "learning_rate": 1.9100694444444444e-06,
2101
+ "loss": 0.003,
2102
+ "step": 138500
2103
+ },
2104
+ {
2105
+ "epoch": 17.375,
2106
+ "grad_norm": 0.001468669855967164,
2107
+ "learning_rate": 1.7364583333333333e-06,
2108
+ "loss": 0.0019,
2109
+ "step": 139000
2110
+ },
2111
+ {
2112
+ "epoch": 17.4375,
2113
+ "grad_norm": 0.00026872969465330243,
2114
+ "learning_rate": 1.5628472222222221e-06,
2115
+ "loss": 0.0099,
2116
+ "step": 139500
2117
+ },
2118
+ {
2119
+ "epoch": 17.5,
2120
+ "grad_norm": 1.7162893755084951e-06,
2121
+ "learning_rate": 1.389236111111111e-06,
2122
+ "loss": 0.0048,
2123
+ "step": 140000
2124
+ },
2125
+ {
2126
+ "epoch": 17.5625,
2127
+ "grad_norm": 0.0008746526436880231,
2128
+ "learning_rate": 1.2156250000000001e-06,
2129
+ "loss": 0.0102,
2130
+ "step": 140500
2131
+ },
2132
+ {
2133
+ "epoch": 17.625,
2134
+ "grad_norm": 1.9161303498549387e-05,
2135
+ "learning_rate": 1.042013888888889e-06,
2136
+ "loss": 0.006,
2137
+ "step": 141000
2138
+ },
2139
+ {
2140
+ "epoch": 17.6875,
2141
+ "grad_norm": 3.897320244306002e-09,
2142
+ "learning_rate": 8.684027777777779e-07,
2143
+ "loss": 0.0039,
2144
+ "step": 141500
2145
+ },
2146
+ {
2147
+ "epoch": 17.75,
2148
+ "grad_norm": 8.191513245492388e-09,
2149
+ "learning_rate": 6.947916666666666e-07,
2150
+ "loss": 0.012,
2151
+ "step": 142000
2152
+ },
2153
+ {
2154
+ "epoch": 17.8125,
2155
+ "grad_norm": 3.0659169425462096e-08,
2156
+ "learning_rate": 5.211805555555555e-07,
2157
+ "loss": 0.0234,
2158
+ "step": 142500
2159
+ },
2160
+ {
2161
+ "epoch": 17.875,
2162
+ "grad_norm": 6.148510589554235e-10,
2163
+ "learning_rate": 3.4756944444444446e-07,
2164
+ "loss": 0.0108,
2165
+ "step": 143000
2166
+ },
2167
+ {
2168
+ "epoch": 17.9375,
2169
+ "grad_norm": 2.9518602673306304e-08,
2170
+ "learning_rate": 1.7395833333333334e-07,
2171
+ "loss": 0.0126,
2172
+ "step": 143500
2173
+ },
2174
+ {
2175
+ "epoch": 18.0,
2176
+ "grad_norm": 6.439736898755655e-05,
2177
+ "learning_rate": 3.4722222222222225e-10,
2178
+ "loss": 0.0168,
2179
+ "step": 144000
2180
+ },
2181
+ {
2182
+ "epoch": 18.0,
2183
+ "eval_loss": 0.3779836893081665,
2184
+ "eval_pearson": 0.9271653083172758,
2185
+ "eval_runtime": 52.2326,
2186
+ "eval_samples_per_second": 38.29,
2187
+ "eval_steps_per_second": 19.145,
2188
+ "step": 144000
2189
+ }
2190
+ ],
2191
+ "logging_steps": 500,
2192
+ "max_steps": 144000,
2193
+ "num_input_tokens_seen": 0,
2194
+ "num_train_epochs": 18,
2195
+ "save_steps": 500,
2196
+ "stateful_callbacks": {
2197
+ "TrainerControl": {
2198
+ "args": {
2199
+ "should_epoch_stop": false,
2200
+ "should_evaluate": false,
2201
+ "should_log": false,
2202
+ "should_save": true,
2203
+ "should_training_stop": true
2204
+ },
2205
+ "attributes": {}
2206
+ }
2207
+ },
2208
+ "total_flos": 1.3261954936291738e+17,
2209
+ "train_batch_size": 2,
2210
+ "trial_name": null,
2211
+ "trial_params": null
2212
+ }
checkpoints_ia3_llama_class/checkpoint-144000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54e6c46c9dda9757cc094892dfdf420dce55879ca8959ffad52b273b74ea2b4a
3
+ size 5368
checkpoints_ia3_llama_class/checkpoint-88000/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Llama-3.2-3B-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 0.15.2
checkpoints_ia3_llama_class/checkpoint-88000/adapter_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Llama-3.2-3B-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": 8,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.1,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": [
22
+ "classifier",
23
+ "score"
24
+ ],
25
+ "peft_type": "LORA",
26
+ "r": 8,
27
+ "rank_pattern": {},
28
+ "revision": null,
29
+ "target_modules": [
30
+ "v_proj",
31
+ "k_proj"
32
+ ],
33
+ "task_type": "SEQ_CLS",
34
+ "trainable_token_indices": null,
35
+ "use_dora": false,
36
+ "use_rslora": false
37
+ }
checkpoints_ia3_llama_class/checkpoint-88000/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:292be273c76abcf482d039e9517790335319fa94393283ad831d08cc70881542
3
+ size 7428608
checkpoints_ia3_llama_class/checkpoint-88000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c89b39ba4ca270b0b53008ece921b5dbfb0d4cffc6d3f00a54473b0e9a907fb5
3
+ size 14922618
checkpoints_ia3_llama_class/checkpoint-88000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48c809000a71cf2b6d50c4a9b216bb9bbd20805c096c8869807aa81b54ce8d12
3
+ size 14244
checkpoints_ia3_llama_class/checkpoint-88000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af2aad6cc65ccaceb8d19eafea3c62866b50b1a4b4dea664ab5cbf9af8d70967
3
+ size 1064
checkpoints_ia3_llama_class/checkpoint-88000/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
+ }
checkpoints_ia3_llama_class/checkpoint-88000/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb55d3601efe3b76b75c99d892f669a53d23df00ee8bac2e67a72152ae2083cd
3
+ size 17210017
checkpoints_ia3_llama_class/checkpoint-88000/tokenizer_config.json ADDED
@@ -0,0 +1,2065 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "128000": {
5
+ "content": "<|begin_of_text|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "128001": {
13
+ "content": "<|end_of_text|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "128002": {
21
+ "content": "<|reserved_special_token_0|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "128003": {
29
+ "content": "<|reserved_special_token_1|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "128004": {
37
+ "content": "<|finetune_right_pad_id|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "128005": {
45
+ "content": "<|reserved_special_token_2|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "128006": {
53
+ "content": "<|start_header_id|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "128007": {
61
+ "content": "<|end_header_id|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "128008": {
69
+ "content": "<|eom_id|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "128009": {
77
+ "content": "<|eot_id|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "128010": {
85
+ "content": "<|python_tag|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "128011": {
93
+ "content": "<|reserved_special_token_3|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "128012": {
101
+ "content": "<|reserved_special_token_4|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "128013": {
109
+ "content": "<|reserved_special_token_5|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "128014": {
117
+ "content": "<|reserved_special_token_6|>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "128015": {
125
+ "content": "<|reserved_special_token_7|>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "128016": {
133
+ "content": "<|reserved_special_token_8|>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "128017": {
141
+ "content": "<|reserved_special_token_9|>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "128018": {
149
+ "content": "<|reserved_special_token_10|>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "128019": {
157
+ "content": "<|reserved_special_token_11|>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "128020": {
165
+ "content": "<|reserved_special_token_12|>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "128021": {
173
+ "content": "<|reserved_special_token_13|>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "128022": {
181
+ "content": "<|reserved_special_token_14|>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "128023": {
189
+ "content": "<|reserved_special_token_15|>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "128024": {
197
+ "content": "<|reserved_special_token_16|>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "128025": {
205
+ "content": "<|reserved_special_token_17|>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "128026": {
213
+ "content": "<|reserved_special_token_18|>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "128027": {
221
+ "content": "<|reserved_special_token_19|>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "128028": {
229
+ "content": "<|reserved_special_token_20|>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "128029": {
237
+ "content": "<|reserved_special_token_21|>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "128030": {
245
+ "content": "<|reserved_special_token_22|>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "128031": {
253
+ "content": "<|reserved_special_token_23|>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "128032": {
261
+ "content": "<|reserved_special_token_24|>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "128033": {
269
+ "content": "<|reserved_special_token_25|>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "128034": {
277
+ "content": "<|reserved_special_token_26|>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "128035": {
285
+ "content": "<|reserved_special_token_27|>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "128036": {
293
+ "content": "<|reserved_special_token_28|>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "128037": {
301
+ "content": "<|reserved_special_token_29|>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "128038": {
309
+ "content": "<|reserved_special_token_30|>",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "128039": {
317
+ "content": "<|reserved_special_token_31|>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "128040": {
325
+ "content": "<|reserved_special_token_32|>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "128041": {
333
+ "content": "<|reserved_special_token_33|>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "128042": {
341
+ "content": "<|reserved_special_token_34|>",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "128043": {
349
+ "content": "<|reserved_special_token_35|>",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "128044": {
357
+ "content": "<|reserved_special_token_36|>",
358
+ "lstrip": false,
359
+ "normalized": false,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "128045": {
365
+ "content": "<|reserved_special_token_37|>",
366
+ "lstrip": false,
367
+ "normalized": false,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "128046": {
373
+ "content": "<|reserved_special_token_38|>",
374
+ "lstrip": false,
375
+ "normalized": false,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "128047": {
381
+ "content": "<|reserved_special_token_39|>",
382
+ "lstrip": false,
383
+ "normalized": false,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "128048": {
389
+ "content": "<|reserved_special_token_40|>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "128049": {
397
+ "content": "<|reserved_special_token_41|>",
398
+ "lstrip": false,
399
+ "normalized": false,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "128050": {
405
+ "content": "<|reserved_special_token_42|>",
406
+ "lstrip": false,
407
+ "normalized": false,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "128051": {
413
+ "content": "<|reserved_special_token_43|>",
414
+ "lstrip": false,
415
+ "normalized": false,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "128052": {
421
+ "content": "<|reserved_special_token_44|>",
422
+ "lstrip": false,
423
+ "normalized": false,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "128053": {
429
+ "content": "<|reserved_special_token_45|>",
430
+ "lstrip": false,
431
+ "normalized": false,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "128054": {
437
+ "content": "<|reserved_special_token_46|>",
438
+ "lstrip": false,
439
+ "normalized": false,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "128055": {
445
+ "content": "<|reserved_special_token_47|>",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "128056": {
453
+ "content": "<|reserved_special_token_48|>",
454
+ "lstrip": false,
455
+ "normalized": false,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "128057": {
461
+ "content": "<|reserved_special_token_49|>",
462
+ "lstrip": false,
463
+ "normalized": false,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "128058": {
469
+ "content": "<|reserved_special_token_50|>",
470
+ "lstrip": false,
471
+ "normalized": false,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "128059": {
477
+ "content": "<|reserved_special_token_51|>",
478
+ "lstrip": false,
479
+ "normalized": false,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "128060": {
485
+ "content": "<|reserved_special_token_52|>",
486
+ "lstrip": false,
487
+ "normalized": false,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "128061": {
493
+ "content": "<|reserved_special_token_53|>",
494
+ "lstrip": false,
495
+ "normalized": false,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "128062": {
501
+ "content": "<|reserved_special_token_54|>",
502
+ "lstrip": false,
503
+ "normalized": false,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "128063": {
509
+ "content": "<|reserved_special_token_55|>",
510
+ "lstrip": false,
511
+ "normalized": false,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "128064": {
517
+ "content": "<|reserved_special_token_56|>",
518
+ "lstrip": false,
519
+ "normalized": false,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "128065": {
525
+ "content": "<|reserved_special_token_57|>",
526
+ "lstrip": false,
527
+ "normalized": false,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "128066": {
533
+ "content": "<|reserved_special_token_58|>",
534
+ "lstrip": false,
535
+ "normalized": false,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "128067": {
541
+ "content": "<|reserved_special_token_59|>",
542
+ "lstrip": false,
543
+ "normalized": false,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "128068": {
549
+ "content": "<|reserved_special_token_60|>",
550
+ "lstrip": false,
551
+ "normalized": false,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "128069": {
557
+ "content": "<|reserved_special_token_61|>",
558
+ "lstrip": false,
559
+ "normalized": false,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "128070": {
565
+ "content": "<|reserved_special_token_62|>",
566
+ "lstrip": false,
567
+ "normalized": false,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "128071": {
573
+ "content": "<|reserved_special_token_63|>",
574
+ "lstrip": false,
575
+ "normalized": false,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "128072": {
581
+ "content": "<|reserved_special_token_64|>",
582
+ "lstrip": false,
583
+ "normalized": false,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "128073": {
589
+ "content": "<|reserved_special_token_65|>",
590
+ "lstrip": false,
591
+ "normalized": false,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "128074": {
597
+ "content": "<|reserved_special_token_66|>",
598
+ "lstrip": false,
599
+ "normalized": false,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "128075": {
605
+ "content": "<|reserved_special_token_67|>",
606
+ "lstrip": false,
607
+ "normalized": false,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "128076": {
613
+ "content": "<|reserved_special_token_68|>",
614
+ "lstrip": false,
615
+ "normalized": false,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "128077": {
621
+ "content": "<|reserved_special_token_69|>",
622
+ "lstrip": false,
623
+ "normalized": false,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "128078": {
629
+ "content": "<|reserved_special_token_70|>",
630
+ "lstrip": false,
631
+ "normalized": false,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "128079": {
637
+ "content": "<|reserved_special_token_71|>",
638
+ "lstrip": false,
639
+ "normalized": false,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "128080": {
645
+ "content": "<|reserved_special_token_72|>",
646
+ "lstrip": false,
647
+ "normalized": false,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "128081": {
653
+ "content": "<|reserved_special_token_73|>",
654
+ "lstrip": false,
655
+ "normalized": false,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "128082": {
661
+ "content": "<|reserved_special_token_74|>",
662
+ "lstrip": false,
663
+ "normalized": false,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "128083": {
669
+ "content": "<|reserved_special_token_75|>",
670
+ "lstrip": false,
671
+ "normalized": false,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "128084": {
677
+ "content": "<|reserved_special_token_76|>",
678
+ "lstrip": false,
679
+ "normalized": false,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "128085": {
685
+ "content": "<|reserved_special_token_77|>",
686
+ "lstrip": false,
687
+ "normalized": false,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "128086": {
693
+ "content": "<|reserved_special_token_78|>",
694
+ "lstrip": false,
695
+ "normalized": false,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "128087": {
701
+ "content": "<|reserved_special_token_79|>",
702
+ "lstrip": false,
703
+ "normalized": false,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "128088": {
709
+ "content": "<|reserved_special_token_80|>",
710
+ "lstrip": false,
711
+ "normalized": false,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "128089": {
717
+ "content": "<|reserved_special_token_81|>",
718
+ "lstrip": false,
719
+ "normalized": false,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "128090": {
725
+ "content": "<|reserved_special_token_82|>",
726
+ "lstrip": false,
727
+ "normalized": false,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "128091": {
733
+ "content": "<|reserved_special_token_83|>",
734
+ "lstrip": false,
735
+ "normalized": false,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "128092": {
741
+ "content": "<|reserved_special_token_84|>",
742
+ "lstrip": false,
743
+ "normalized": false,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "128093": {
749
+ "content": "<|reserved_special_token_85|>",
750
+ "lstrip": false,
751
+ "normalized": false,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "128094": {
757
+ "content": "<|reserved_special_token_86|>",
758
+ "lstrip": false,
759
+ "normalized": false,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "128095": {
765
+ "content": "<|reserved_special_token_87|>",
766
+ "lstrip": false,
767
+ "normalized": false,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "128096": {
773
+ "content": "<|reserved_special_token_88|>",
774
+ "lstrip": false,
775
+ "normalized": false,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "128097": {
781
+ "content": "<|reserved_special_token_89|>",
782
+ "lstrip": false,
783
+ "normalized": false,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "128098": {
789
+ "content": "<|reserved_special_token_90|>",
790
+ "lstrip": false,
791
+ "normalized": false,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "128099": {
797
+ "content": "<|reserved_special_token_91|>",
798
+ "lstrip": false,
799
+ "normalized": false,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "128100": {
805
+ "content": "<|reserved_special_token_92|>",
806
+ "lstrip": false,
807
+ "normalized": false,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "128101": {
813
+ "content": "<|reserved_special_token_93|>",
814
+ "lstrip": false,
815
+ "normalized": false,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "128102": {
821
+ "content": "<|reserved_special_token_94|>",
822
+ "lstrip": false,
823
+ "normalized": false,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": true
827
+ },
828
+ "128103": {
829
+ "content": "<|reserved_special_token_95|>",
830
+ "lstrip": false,
831
+ "normalized": false,
832
+ "rstrip": false,
833
+ "single_word": false,
834
+ "special": true
835
+ },
836
+ "128104": {
837
+ "content": "<|reserved_special_token_96|>",
838
+ "lstrip": false,
839
+ "normalized": false,
840
+ "rstrip": false,
841
+ "single_word": false,
842
+ "special": true
843
+ },
844
+ "128105": {
845
+ "content": "<|reserved_special_token_97|>",
846
+ "lstrip": false,
847
+ "normalized": false,
848
+ "rstrip": false,
849
+ "single_word": false,
850
+ "special": true
851
+ },
852
+ "128106": {
853
+ "content": "<|reserved_special_token_98|>",
854
+ "lstrip": false,
855
+ "normalized": false,
856
+ "rstrip": false,
857
+ "single_word": false,
858
+ "special": true
859
+ },
860
+ "128107": {
861
+ "content": "<|reserved_special_token_99|>",
862
+ "lstrip": false,
863
+ "normalized": false,
864
+ "rstrip": false,
865
+ "single_word": false,
866
+ "special": true
867
+ },
868
+ "128108": {
869
+ "content": "<|reserved_special_token_100|>",
870
+ "lstrip": false,
871
+ "normalized": false,
872
+ "rstrip": false,
873
+ "single_word": false,
874
+ "special": true
875
+ },
876
+ "128109": {
877
+ "content": "<|reserved_special_token_101|>",
878
+ "lstrip": false,
879
+ "normalized": false,
880
+ "rstrip": false,
881
+ "single_word": false,
882
+ "special": true
883
+ },
884
+ "128110": {
885
+ "content": "<|reserved_special_token_102|>",
886
+ "lstrip": false,
887
+ "normalized": false,
888
+ "rstrip": false,
889
+ "single_word": false,
890
+ "special": true
891
+ },
892
+ "128111": {
893
+ "content": "<|reserved_special_token_103|>",
894
+ "lstrip": false,
895
+ "normalized": false,
896
+ "rstrip": false,
897
+ "single_word": false,
898
+ "special": true
899
+ },
900
+ "128112": {
901
+ "content": "<|reserved_special_token_104|>",
902
+ "lstrip": false,
903
+ "normalized": false,
904
+ "rstrip": false,
905
+ "single_word": false,
906
+ "special": true
907
+ },
908
+ "128113": {
909
+ "content": "<|reserved_special_token_105|>",
910
+ "lstrip": false,
911
+ "normalized": false,
912
+ "rstrip": false,
913
+ "single_word": false,
914
+ "special": true
915
+ },
916
+ "128114": {
917
+ "content": "<|reserved_special_token_106|>",
918
+ "lstrip": false,
919
+ "normalized": false,
920
+ "rstrip": false,
921
+ "single_word": false,
922
+ "special": true
923
+ },
924
+ "128115": {
925
+ "content": "<|reserved_special_token_107|>",
926
+ "lstrip": false,
927
+ "normalized": false,
928
+ "rstrip": false,
929
+ "single_word": false,
930
+ "special": true
931
+ },
932
+ "128116": {
933
+ "content": "<|reserved_special_token_108|>",
934
+ "lstrip": false,
935
+ "normalized": false,
936
+ "rstrip": false,
937
+ "single_word": false,
938
+ "special": true
939
+ },
940
+ "128117": {
941
+ "content": "<|reserved_special_token_109|>",
942
+ "lstrip": false,
943
+ "normalized": false,
944
+ "rstrip": false,
945
+ "single_word": false,
946
+ "special": true
947
+ },
948
+ "128118": {
949
+ "content": "<|reserved_special_token_110|>",
950
+ "lstrip": false,
951
+ "normalized": false,
952
+ "rstrip": false,
953
+ "single_word": false,
954
+ "special": true
955
+ },
956
+ "128119": {
957
+ "content": "<|reserved_special_token_111|>",
958
+ "lstrip": false,
959
+ "normalized": false,
960
+ "rstrip": false,
961
+ "single_word": false,
962
+ "special": true
963
+ },
964
+ "128120": {
965
+ "content": "<|reserved_special_token_112|>",
966
+ "lstrip": false,
967
+ "normalized": false,
968
+ "rstrip": false,
969
+ "single_word": false,
970
+ "special": true
971
+ },
972
+ "128121": {
973
+ "content": "<|reserved_special_token_113|>",
974
+ "lstrip": false,
975
+ "normalized": false,
976
+ "rstrip": false,
977
+ "single_word": false,
978
+ "special": true
979
+ },
980
+ "128122": {
981
+ "content": "<|reserved_special_token_114|>",
982
+ "lstrip": false,
983
+ "normalized": false,
984
+ "rstrip": false,
985
+ "single_word": false,
986
+ "special": true
987
+ },
988
+ "128123": {
989
+ "content": "<|reserved_special_token_115|>",
990
+ "lstrip": false,
991
+ "normalized": false,
992
+ "rstrip": false,
993
+ "single_word": false,
994
+ "special": true
995
+ },
996
+ "128124": {
997
+ "content": "<|reserved_special_token_116|>",
998
+ "lstrip": false,
999
+ "normalized": false,
1000
+ "rstrip": false,
1001
+ "single_word": false,
1002
+ "special": true
1003
+ },
1004
+ "128125": {
1005
+ "content": "<|reserved_special_token_117|>",
1006
+ "lstrip": false,
1007
+ "normalized": false,
1008
+ "rstrip": false,
1009
+ "single_word": false,
1010
+ "special": true
1011
+ },
1012
+ "128126": {
1013
+ "content": "<|reserved_special_token_118|>",
1014
+ "lstrip": false,
1015
+ "normalized": false,
1016
+ "rstrip": false,
1017
+ "single_word": false,
1018
+ "special": true
1019
+ },
1020
+ "128127": {
1021
+ "content": "<|reserved_special_token_119|>",
1022
+ "lstrip": false,
1023
+ "normalized": false,
1024
+ "rstrip": false,
1025
+ "single_word": false,
1026
+ "special": true
1027
+ },
1028
+ "128128": {
1029
+ "content": "<|reserved_special_token_120|>",
1030
+ "lstrip": false,
1031
+ "normalized": false,
1032
+ "rstrip": false,
1033
+ "single_word": false,
1034
+ "special": true
1035
+ },
1036
+ "128129": {
1037
+ "content": "<|reserved_special_token_121|>",
1038
+ "lstrip": false,
1039
+ "normalized": false,
1040
+ "rstrip": false,
1041
+ "single_word": false,
1042
+ "special": true
1043
+ },
1044
+ "128130": {
1045
+ "content": "<|reserved_special_token_122|>",
1046
+ "lstrip": false,
1047
+ "normalized": false,
1048
+ "rstrip": false,
1049
+ "single_word": false,
1050
+ "special": true
1051
+ },
1052
+ "128131": {
1053
+ "content": "<|reserved_special_token_123|>",
1054
+ "lstrip": false,
1055
+ "normalized": false,
1056
+ "rstrip": false,
1057
+ "single_word": false,
1058
+ "special": true
1059
+ },
1060
+ "128132": {
1061
+ "content": "<|reserved_special_token_124|>",
1062
+ "lstrip": false,
1063
+ "normalized": false,
1064
+ "rstrip": false,
1065
+ "single_word": false,
1066
+ "special": true
1067
+ },
1068
+ "128133": {
1069
+ "content": "<|reserved_special_token_125|>",
1070
+ "lstrip": false,
1071
+ "normalized": false,
1072
+ "rstrip": false,
1073
+ "single_word": false,
1074
+ "special": true
1075
+ },
1076
+ "128134": {
1077
+ "content": "<|reserved_special_token_126|>",
1078
+ "lstrip": false,
1079
+ "normalized": false,
1080
+ "rstrip": false,
1081
+ "single_word": false,
1082
+ "special": true
1083
+ },
1084
+ "128135": {
1085
+ "content": "<|reserved_special_token_127|>",
1086
+ "lstrip": false,
1087
+ "normalized": false,
1088
+ "rstrip": false,
1089
+ "single_word": false,
1090
+ "special": true
1091
+ },
1092
+ "128136": {
1093
+ "content": "<|reserved_special_token_128|>",
1094
+ "lstrip": false,
1095
+ "normalized": false,
1096
+ "rstrip": false,
1097
+ "single_word": false,
1098
+ "special": true
1099
+ },
1100
+ "128137": {
1101
+ "content": "<|reserved_special_token_129|>",
1102
+ "lstrip": false,
1103
+ "normalized": false,
1104
+ "rstrip": false,
1105
+ "single_word": false,
1106
+ "special": true
1107
+ },
1108
+ "128138": {
1109
+ "content": "<|reserved_special_token_130|>",
1110
+ "lstrip": false,
1111
+ "normalized": false,
1112
+ "rstrip": false,
1113
+ "single_word": false,
1114
+ "special": true
1115
+ },
1116
+ "128139": {
1117
+ "content": "<|reserved_special_token_131|>",
1118
+ "lstrip": false,
1119
+ "normalized": false,
1120
+ "rstrip": false,
1121
+ "single_word": false,
1122
+ "special": true
1123
+ },
1124
+ "128140": {
1125
+ "content": "<|reserved_special_token_132|>",
1126
+ "lstrip": false,
1127
+ "normalized": false,
1128
+ "rstrip": false,
1129
+ "single_word": false,
1130
+ "special": true
1131
+ },
1132
+ "128141": {
1133
+ "content": "<|reserved_special_token_133|>",
1134
+ "lstrip": false,
1135
+ "normalized": false,
1136
+ "rstrip": false,
1137
+ "single_word": false,
1138
+ "special": true
1139
+ },
1140
+ "128142": {
1141
+ "content": "<|reserved_special_token_134|>",
1142
+ "lstrip": false,
1143
+ "normalized": false,
1144
+ "rstrip": false,
1145
+ "single_word": false,
1146
+ "special": true
1147
+ },
1148
+ "128143": {
1149
+ "content": "<|reserved_special_token_135|>",
1150
+ "lstrip": false,
1151
+ "normalized": false,
1152
+ "rstrip": false,
1153
+ "single_word": false,
1154
+ "special": true
1155
+ },
1156
+ "128144": {
1157
+ "content": "<|reserved_special_token_136|>",
1158
+ "lstrip": false,
1159
+ "normalized": false,
1160
+ "rstrip": false,
1161
+ "single_word": false,
1162
+ "special": true
1163
+ },
1164
+ "128145": {
1165
+ "content": "<|reserved_special_token_137|>",
1166
+ "lstrip": false,
1167
+ "normalized": false,
1168
+ "rstrip": false,
1169
+ "single_word": false,
1170
+ "special": true
1171
+ },
1172
+ "128146": {
1173
+ "content": "<|reserved_special_token_138|>",
1174
+ "lstrip": false,
1175
+ "normalized": false,
1176
+ "rstrip": false,
1177
+ "single_word": false,
1178
+ "special": true
1179
+ },
1180
+ "128147": {
1181
+ "content": "<|reserved_special_token_139|>",
1182
+ "lstrip": false,
1183
+ "normalized": false,
1184
+ "rstrip": false,
1185
+ "single_word": false,
1186
+ "special": true
1187
+ },
1188
+ "128148": {
1189
+ "content": "<|reserved_special_token_140|>",
1190
+ "lstrip": false,
1191
+ "normalized": false,
1192
+ "rstrip": false,
1193
+ "single_word": false,
1194
+ "special": true
1195
+ },
1196
+ "128149": {
1197
+ "content": "<|reserved_special_token_141|>",
1198
+ "lstrip": false,
1199
+ "normalized": false,
1200
+ "rstrip": false,
1201
+ "single_word": false,
1202
+ "special": true
1203
+ },
1204
+ "128150": {
1205
+ "content": "<|reserved_special_token_142|>",
1206
+ "lstrip": false,
1207
+ "normalized": false,
1208
+ "rstrip": false,
1209
+ "single_word": false,
1210
+ "special": true
1211
+ },
1212
+ "128151": {
1213
+ "content": "<|reserved_special_token_143|>",
1214
+ "lstrip": false,
1215
+ "normalized": false,
1216
+ "rstrip": false,
1217
+ "single_word": false,
1218
+ "special": true
1219
+ },
1220
+ "128152": {
1221
+ "content": "<|reserved_special_token_144|>",
1222
+ "lstrip": false,
1223
+ "normalized": false,
1224
+ "rstrip": false,
1225
+ "single_word": false,
1226
+ "special": true
1227
+ },
1228
+ "128153": {
1229
+ "content": "<|reserved_special_token_145|>",
1230
+ "lstrip": false,
1231
+ "normalized": false,
1232
+ "rstrip": false,
1233
+ "single_word": false,
1234
+ "special": true
1235
+ },
1236
+ "128154": {
1237
+ "content": "<|reserved_special_token_146|>",
1238
+ "lstrip": false,
1239
+ "normalized": false,
1240
+ "rstrip": false,
1241
+ "single_word": false,
1242
+ "special": true
1243
+ },
1244
+ "128155": {
1245
+ "content": "<|reserved_special_token_147|>",
1246
+ "lstrip": false,
1247
+ "normalized": false,
1248
+ "rstrip": false,
1249
+ "single_word": false,
1250
+ "special": true
1251
+ },
1252
+ "128156": {
1253
+ "content": "<|reserved_special_token_148|>",
1254
+ "lstrip": false,
1255
+ "normalized": false,
1256
+ "rstrip": false,
1257
+ "single_word": false,
1258
+ "special": true
1259
+ },
1260
+ "128157": {
1261
+ "content": "<|reserved_special_token_149|>",
1262
+ "lstrip": false,
1263
+ "normalized": false,
1264
+ "rstrip": false,
1265
+ "single_word": false,
1266
+ "special": true
1267
+ },
1268
+ "128158": {
1269
+ "content": "<|reserved_special_token_150|>",
1270
+ "lstrip": false,
1271
+ "normalized": false,
1272
+ "rstrip": false,
1273
+ "single_word": false,
1274
+ "special": true
1275
+ },
1276
+ "128159": {
1277
+ "content": "<|reserved_special_token_151|>",
1278
+ "lstrip": false,
1279
+ "normalized": false,
1280
+ "rstrip": false,
1281
+ "single_word": false,
1282
+ "special": true
1283
+ },
1284
+ "128160": {
1285
+ "content": "<|reserved_special_token_152|>",
1286
+ "lstrip": false,
1287
+ "normalized": false,
1288
+ "rstrip": false,
1289
+ "single_word": false,
1290
+ "special": true
1291
+ },
1292
+ "128161": {
1293
+ "content": "<|reserved_special_token_153|>",
1294
+ "lstrip": false,
1295
+ "normalized": false,
1296
+ "rstrip": false,
1297
+ "single_word": false,
1298
+ "special": true
1299
+ },
1300
+ "128162": {
1301
+ "content": "<|reserved_special_token_154|>",
1302
+ "lstrip": false,
1303
+ "normalized": false,
1304
+ "rstrip": false,
1305
+ "single_word": false,
1306
+ "special": true
1307
+ },
1308
+ "128163": {
1309
+ "content": "<|reserved_special_token_155|>",
1310
+ "lstrip": false,
1311
+ "normalized": false,
1312
+ "rstrip": false,
1313
+ "single_word": false,
1314
+ "special": true
1315
+ },
1316
+ "128164": {
1317
+ "content": "<|reserved_special_token_156|>",
1318
+ "lstrip": false,
1319
+ "normalized": false,
1320
+ "rstrip": false,
1321
+ "single_word": false,
1322
+ "special": true
1323
+ },
1324
+ "128165": {
1325
+ "content": "<|reserved_special_token_157|>",
1326
+ "lstrip": false,
1327
+ "normalized": false,
1328
+ "rstrip": false,
1329
+ "single_word": false,
1330
+ "special": true
1331
+ },
1332
+ "128166": {
1333
+ "content": "<|reserved_special_token_158|>",
1334
+ "lstrip": false,
1335
+ "normalized": false,
1336
+ "rstrip": false,
1337
+ "single_word": false,
1338
+ "special": true
1339
+ },
1340
+ "128167": {
1341
+ "content": "<|reserved_special_token_159|>",
1342
+ "lstrip": false,
1343
+ "normalized": false,
1344
+ "rstrip": false,
1345
+ "single_word": false,
1346
+ "special": true
1347
+ },
1348
+ "128168": {
1349
+ "content": "<|reserved_special_token_160|>",
1350
+ "lstrip": false,
1351
+ "normalized": false,
1352
+ "rstrip": false,
1353
+ "single_word": false,
1354
+ "special": true
1355
+ },
1356
+ "128169": {
1357
+ "content": "<|reserved_special_token_161|>",
1358
+ "lstrip": false,
1359
+ "normalized": false,
1360
+ "rstrip": false,
1361
+ "single_word": false,
1362
+ "special": true
1363
+ },
1364
+ "128170": {
1365
+ "content": "<|reserved_special_token_162|>",
1366
+ "lstrip": false,
1367
+ "normalized": false,
1368
+ "rstrip": false,
1369
+ "single_word": false,
1370
+ "special": true
1371
+ },
1372
+ "128171": {
1373
+ "content": "<|reserved_special_token_163|>",
1374
+ "lstrip": false,
1375
+ "normalized": false,
1376
+ "rstrip": false,
1377
+ "single_word": false,
1378
+ "special": true
1379
+ },
1380
+ "128172": {
1381
+ "content": "<|reserved_special_token_164|>",
1382
+ "lstrip": false,
1383
+ "normalized": false,
1384
+ "rstrip": false,
1385
+ "single_word": false,
1386
+ "special": true
1387
+ },
1388
+ "128173": {
1389
+ "content": "<|reserved_special_token_165|>",
1390
+ "lstrip": false,
1391
+ "normalized": false,
1392
+ "rstrip": false,
1393
+ "single_word": false,
1394
+ "special": true
1395
+ },
1396
+ "128174": {
1397
+ "content": "<|reserved_special_token_166|>",
1398
+ "lstrip": false,
1399
+ "normalized": false,
1400
+ "rstrip": false,
1401
+ "single_word": false,
1402
+ "special": true
1403
+ },
1404
+ "128175": {
1405
+ "content": "<|reserved_special_token_167|>",
1406
+ "lstrip": false,
1407
+ "normalized": false,
1408
+ "rstrip": false,
1409
+ "single_word": false,
1410
+ "special": true
1411
+ },
1412
+ "128176": {
1413
+ "content": "<|reserved_special_token_168|>",
1414
+ "lstrip": false,
1415
+ "normalized": false,
1416
+ "rstrip": false,
1417
+ "single_word": false,
1418
+ "special": true
1419
+ },
1420
+ "128177": {
1421
+ "content": "<|reserved_special_token_169|>",
1422
+ "lstrip": false,
1423
+ "normalized": false,
1424
+ "rstrip": false,
1425
+ "single_word": false,
1426
+ "special": true
1427
+ },
1428
+ "128178": {
1429
+ "content": "<|reserved_special_token_170|>",
1430
+ "lstrip": false,
1431
+ "normalized": false,
1432
+ "rstrip": false,
1433
+ "single_word": false,
1434
+ "special": true
1435
+ },
1436
+ "128179": {
1437
+ "content": "<|reserved_special_token_171|>",
1438
+ "lstrip": false,
1439
+ "normalized": false,
1440
+ "rstrip": false,
1441
+ "single_word": false,
1442
+ "special": true
1443
+ },
1444
+ "128180": {
1445
+ "content": "<|reserved_special_token_172|>",
1446
+ "lstrip": false,
1447
+ "normalized": false,
1448
+ "rstrip": false,
1449
+ "single_word": false,
1450
+ "special": true
1451
+ },
1452
+ "128181": {
1453
+ "content": "<|reserved_special_token_173|>",
1454
+ "lstrip": false,
1455
+ "normalized": false,
1456
+ "rstrip": false,
1457
+ "single_word": false,
1458
+ "special": true
1459
+ },
1460
+ "128182": {
1461
+ "content": "<|reserved_special_token_174|>",
1462
+ "lstrip": false,
1463
+ "normalized": false,
1464
+ "rstrip": false,
1465
+ "single_word": false,
1466
+ "special": true
1467
+ },
1468
+ "128183": {
1469
+ "content": "<|reserved_special_token_175|>",
1470
+ "lstrip": false,
1471
+ "normalized": false,
1472
+ "rstrip": false,
1473
+ "single_word": false,
1474
+ "special": true
1475
+ },
1476
+ "128184": {
1477
+ "content": "<|reserved_special_token_176|>",
1478
+ "lstrip": false,
1479
+ "normalized": false,
1480
+ "rstrip": false,
1481
+ "single_word": false,
1482
+ "special": true
1483
+ },
1484
+ "128185": {
1485
+ "content": "<|reserved_special_token_177|>",
1486
+ "lstrip": false,
1487
+ "normalized": false,
1488
+ "rstrip": false,
1489
+ "single_word": false,
1490
+ "special": true
1491
+ },
1492
+ "128186": {
1493
+ "content": "<|reserved_special_token_178|>",
1494
+ "lstrip": false,
1495
+ "normalized": false,
1496
+ "rstrip": false,
1497
+ "single_word": false,
1498
+ "special": true
1499
+ },
1500
+ "128187": {
1501
+ "content": "<|reserved_special_token_179|>",
1502
+ "lstrip": false,
1503
+ "normalized": false,
1504
+ "rstrip": false,
1505
+ "single_word": false,
1506
+ "special": true
1507
+ },
1508
+ "128188": {
1509
+ "content": "<|reserved_special_token_180|>",
1510
+ "lstrip": false,
1511
+ "normalized": false,
1512
+ "rstrip": false,
1513
+ "single_word": false,
1514
+ "special": true
1515
+ },
1516
+ "128189": {
1517
+ "content": "<|reserved_special_token_181|>",
1518
+ "lstrip": false,
1519
+ "normalized": false,
1520
+ "rstrip": false,
1521
+ "single_word": false,
1522
+ "special": true
1523
+ },
1524
+ "128190": {
1525
+ "content": "<|reserved_special_token_182|>",
1526
+ "lstrip": false,
1527
+ "normalized": false,
1528
+ "rstrip": false,
1529
+ "single_word": false,
1530
+ "special": true
1531
+ },
1532
+ "128191": {
1533
+ "content": "<|reserved_special_token_183|>",
1534
+ "lstrip": false,
1535
+ "normalized": false,
1536
+ "rstrip": false,
1537
+ "single_word": false,
1538
+ "special": true
1539
+ },
1540
+ "128192": {
1541
+ "content": "<|reserved_special_token_184|>",
1542
+ "lstrip": false,
1543
+ "normalized": false,
1544
+ "rstrip": false,
1545
+ "single_word": false,
1546
+ "special": true
1547
+ },
1548
+ "128193": {
1549
+ "content": "<|reserved_special_token_185|>",
1550
+ "lstrip": false,
1551
+ "normalized": false,
1552
+ "rstrip": false,
1553
+ "single_word": false,
1554
+ "special": true
1555
+ },
1556
+ "128194": {
1557
+ "content": "<|reserved_special_token_186|>",
1558
+ "lstrip": false,
1559
+ "normalized": false,
1560
+ "rstrip": false,
1561
+ "single_word": false,
1562
+ "special": true
1563
+ },
1564
+ "128195": {
1565
+ "content": "<|reserved_special_token_187|>",
1566
+ "lstrip": false,
1567
+ "normalized": false,
1568
+ "rstrip": false,
1569
+ "single_word": false,
1570
+ "special": true
1571
+ },
1572
+ "128196": {
1573
+ "content": "<|reserved_special_token_188|>",
1574
+ "lstrip": false,
1575
+ "normalized": false,
1576
+ "rstrip": false,
1577
+ "single_word": false,
1578
+ "special": true
1579
+ },
1580
+ "128197": {
1581
+ "content": "<|reserved_special_token_189|>",
1582
+ "lstrip": false,
1583
+ "normalized": false,
1584
+ "rstrip": false,
1585
+ "single_word": false,
1586
+ "special": true
1587
+ },
1588
+ "128198": {
1589
+ "content": "<|reserved_special_token_190|>",
1590
+ "lstrip": false,
1591
+ "normalized": false,
1592
+ "rstrip": false,
1593
+ "single_word": false,
1594
+ "special": true
1595
+ },
1596
+ "128199": {
1597
+ "content": "<|reserved_special_token_191|>",
1598
+ "lstrip": false,
1599
+ "normalized": false,
1600
+ "rstrip": false,
1601
+ "single_word": false,
1602
+ "special": true
1603
+ },
1604
+ "128200": {
1605
+ "content": "<|reserved_special_token_192|>",
1606
+ "lstrip": false,
1607
+ "normalized": false,
1608
+ "rstrip": false,
1609
+ "single_word": false,
1610
+ "special": true
1611
+ },
1612
+ "128201": {
1613
+ "content": "<|reserved_special_token_193|>",
1614
+ "lstrip": false,
1615
+ "normalized": false,
1616
+ "rstrip": false,
1617
+ "single_word": false,
1618
+ "special": true
1619
+ },
1620
+ "128202": {
1621
+ "content": "<|reserved_special_token_194|>",
1622
+ "lstrip": false,
1623
+ "normalized": false,
1624
+ "rstrip": false,
1625
+ "single_word": false,
1626
+ "special": true
1627
+ },
1628
+ "128203": {
1629
+ "content": "<|reserved_special_token_195|>",
1630
+ "lstrip": false,
1631
+ "normalized": false,
1632
+ "rstrip": false,
1633
+ "single_word": false,
1634
+ "special": true
1635
+ },
1636
+ "128204": {
1637
+ "content": "<|reserved_special_token_196|>",
1638
+ "lstrip": false,
1639
+ "normalized": false,
1640
+ "rstrip": false,
1641
+ "single_word": false,
1642
+ "special": true
1643
+ },
1644
+ "128205": {
1645
+ "content": "<|reserved_special_token_197|>",
1646
+ "lstrip": false,
1647
+ "normalized": false,
1648
+ "rstrip": false,
1649
+ "single_word": false,
1650
+ "special": true
1651
+ },
1652
+ "128206": {
1653
+ "content": "<|reserved_special_token_198|>",
1654
+ "lstrip": false,
1655
+ "normalized": false,
1656
+ "rstrip": false,
1657
+ "single_word": false,
1658
+ "special": true
1659
+ },
1660
+ "128207": {
1661
+ "content": "<|reserved_special_token_199|>",
1662
+ "lstrip": false,
1663
+ "normalized": false,
1664
+ "rstrip": false,
1665
+ "single_word": false,
1666
+ "special": true
1667
+ },
1668
+ "128208": {
1669
+ "content": "<|reserved_special_token_200|>",
1670
+ "lstrip": false,
1671
+ "normalized": false,
1672
+ "rstrip": false,
1673
+ "single_word": false,
1674
+ "special": true
1675
+ },
1676
+ "128209": {
1677
+ "content": "<|reserved_special_token_201|>",
1678
+ "lstrip": false,
1679
+ "normalized": false,
1680
+ "rstrip": false,
1681
+ "single_word": false,
1682
+ "special": true
1683
+ },
1684
+ "128210": {
1685
+ "content": "<|reserved_special_token_202|>",
1686
+ "lstrip": false,
1687
+ "normalized": false,
1688
+ "rstrip": false,
1689
+ "single_word": false,
1690
+ "special": true
1691
+ },
1692
+ "128211": {
1693
+ "content": "<|reserved_special_token_203|>",
1694
+ "lstrip": false,
1695
+ "normalized": false,
1696
+ "rstrip": false,
1697
+ "single_word": false,
1698
+ "special": true
1699
+ },
1700
+ "128212": {
1701
+ "content": "<|reserved_special_token_204|>",
1702
+ "lstrip": false,
1703
+ "normalized": false,
1704
+ "rstrip": false,
1705
+ "single_word": false,
1706
+ "special": true
1707
+ },
1708
+ "128213": {
1709
+ "content": "<|reserved_special_token_205|>",
1710
+ "lstrip": false,
1711
+ "normalized": false,
1712
+ "rstrip": false,
1713
+ "single_word": false,
1714
+ "special": true
1715
+ },
1716
+ "128214": {
1717
+ "content": "<|reserved_special_token_206|>",
1718
+ "lstrip": false,
1719
+ "normalized": false,
1720
+ "rstrip": false,
1721
+ "single_word": false,
1722
+ "special": true
1723
+ },
1724
+ "128215": {
1725
+ "content": "<|reserved_special_token_207|>",
1726
+ "lstrip": false,
1727
+ "normalized": false,
1728
+ "rstrip": false,
1729
+ "single_word": false,
1730
+ "special": true
1731
+ },
1732
+ "128216": {
1733
+ "content": "<|reserved_special_token_208|>",
1734
+ "lstrip": false,
1735
+ "normalized": false,
1736
+ "rstrip": false,
1737
+ "single_word": false,
1738
+ "special": true
1739
+ },
1740
+ "128217": {
1741
+ "content": "<|reserved_special_token_209|>",
1742
+ "lstrip": false,
1743
+ "normalized": false,
1744
+ "rstrip": false,
1745
+ "single_word": false,
1746
+ "special": true
1747
+ },
1748
+ "128218": {
1749
+ "content": "<|reserved_special_token_210|>",
1750
+ "lstrip": false,
1751
+ "normalized": false,
1752
+ "rstrip": false,
1753
+ "single_word": false,
1754
+ "special": true
1755
+ },
1756
+ "128219": {
1757
+ "content": "<|reserved_special_token_211|>",
1758
+ "lstrip": false,
1759
+ "normalized": false,
1760
+ "rstrip": false,
1761
+ "single_word": false,
1762
+ "special": true
1763
+ },
1764
+ "128220": {
1765
+ "content": "<|reserved_special_token_212|>",
1766
+ "lstrip": false,
1767
+ "normalized": false,
1768
+ "rstrip": false,
1769
+ "single_word": false,
1770
+ "special": true
1771
+ },
1772
+ "128221": {
1773
+ "content": "<|reserved_special_token_213|>",
1774
+ "lstrip": false,
1775
+ "normalized": false,
1776
+ "rstrip": false,
1777
+ "single_word": false,
1778
+ "special": true
1779
+ },
1780
+ "128222": {
1781
+ "content": "<|reserved_special_token_214|>",
1782
+ "lstrip": false,
1783
+ "normalized": false,
1784
+ "rstrip": false,
1785
+ "single_word": false,
1786
+ "special": true
1787
+ },
1788
+ "128223": {
1789
+ "content": "<|reserved_special_token_215|>",
1790
+ "lstrip": false,
1791
+ "normalized": false,
1792
+ "rstrip": false,
1793
+ "single_word": false,
1794
+ "special": true
1795
+ },
1796
+ "128224": {
1797
+ "content": "<|reserved_special_token_216|>",
1798
+ "lstrip": false,
1799
+ "normalized": false,
1800
+ "rstrip": false,
1801
+ "single_word": false,
1802
+ "special": true
1803
+ },
1804
+ "128225": {
1805
+ "content": "<|reserved_special_token_217|>",
1806
+ "lstrip": false,
1807
+ "normalized": false,
1808
+ "rstrip": false,
1809
+ "single_word": false,
1810
+ "special": true
1811
+ },
1812
+ "128226": {
1813
+ "content": "<|reserved_special_token_218|>",
1814
+ "lstrip": false,
1815
+ "normalized": false,
1816
+ "rstrip": false,
1817
+ "single_word": false,
1818
+ "special": true
1819
+ },
1820
+ "128227": {
1821
+ "content": "<|reserved_special_token_219|>",
1822
+ "lstrip": false,
1823
+ "normalized": false,
1824
+ "rstrip": false,
1825
+ "single_word": false,
1826
+ "special": true
1827
+ },
1828
+ "128228": {
1829
+ "content": "<|reserved_special_token_220|>",
1830
+ "lstrip": false,
1831
+ "normalized": false,
1832
+ "rstrip": false,
1833
+ "single_word": false,
1834
+ "special": true
1835
+ },
1836
+ "128229": {
1837
+ "content": "<|reserved_special_token_221|>",
1838
+ "lstrip": false,
1839
+ "normalized": false,
1840
+ "rstrip": false,
1841
+ "single_word": false,
1842
+ "special": true
1843
+ },
1844
+ "128230": {
1845
+ "content": "<|reserved_special_token_222|>",
1846
+ "lstrip": false,
1847
+ "normalized": false,
1848
+ "rstrip": false,
1849
+ "single_word": false,
1850
+ "special": true
1851
+ },
1852
+ "128231": {
1853
+ "content": "<|reserved_special_token_223|>",
1854
+ "lstrip": false,
1855
+ "normalized": false,
1856
+ "rstrip": false,
1857
+ "single_word": false,
1858
+ "special": true
1859
+ },
1860
+ "128232": {
1861
+ "content": "<|reserved_special_token_224|>",
1862
+ "lstrip": false,
1863
+ "normalized": false,
1864
+ "rstrip": false,
1865
+ "single_word": false,
1866
+ "special": true
1867
+ },
1868
+ "128233": {
1869
+ "content": "<|reserved_special_token_225|>",
1870
+ "lstrip": false,
1871
+ "normalized": false,
1872
+ "rstrip": false,
1873
+ "single_word": false,
1874
+ "special": true
1875
+ },
1876
+ "128234": {
1877
+ "content": "<|reserved_special_token_226|>",
1878
+ "lstrip": false,
1879
+ "normalized": false,
1880
+ "rstrip": false,
1881
+ "single_word": false,
1882
+ "special": true
1883
+ },
1884
+ "128235": {
1885
+ "content": "<|reserved_special_token_227|>",
1886
+ "lstrip": false,
1887
+ "normalized": false,
1888
+ "rstrip": false,
1889
+ "single_word": false,
1890
+ "special": true
1891
+ },
1892
+ "128236": {
1893
+ "content": "<|reserved_special_token_228|>",
1894
+ "lstrip": false,
1895
+ "normalized": false,
1896
+ "rstrip": false,
1897
+ "single_word": false,
1898
+ "special": true
1899
+ },
1900
+ "128237": {
1901
+ "content": "<|reserved_special_token_229|>",
1902
+ "lstrip": false,
1903
+ "normalized": false,
1904
+ "rstrip": false,
1905
+ "single_word": false,
1906
+ "special": true
1907
+ },
1908
+ "128238": {
1909
+ "content": "<|reserved_special_token_230|>",
1910
+ "lstrip": false,
1911
+ "normalized": false,
1912
+ "rstrip": false,
1913
+ "single_word": false,
1914
+ "special": true
1915
+ },
1916
+ "128239": {
1917
+ "content": "<|reserved_special_token_231|>",
1918
+ "lstrip": false,
1919
+ "normalized": false,
1920
+ "rstrip": false,
1921
+ "single_word": false,
1922
+ "special": true
1923
+ },
1924
+ "128240": {
1925
+ "content": "<|reserved_special_token_232|>",
1926
+ "lstrip": false,
1927
+ "normalized": false,
1928
+ "rstrip": false,
1929
+ "single_word": false,
1930
+ "special": true
1931
+ },
1932
+ "128241": {
1933
+ "content": "<|reserved_special_token_233|>",
1934
+ "lstrip": false,
1935
+ "normalized": false,
1936
+ "rstrip": false,
1937
+ "single_word": false,
1938
+ "special": true
1939
+ },
1940
+ "128242": {
1941
+ "content": "<|reserved_special_token_234|>",
1942
+ "lstrip": false,
1943
+ "normalized": false,
1944
+ "rstrip": false,
1945
+ "single_word": false,
1946
+ "special": true
1947
+ },
1948
+ "128243": {
1949
+ "content": "<|reserved_special_token_235|>",
1950
+ "lstrip": false,
1951
+ "normalized": false,
1952
+ "rstrip": false,
1953
+ "single_word": false,
1954
+ "special": true
1955
+ },
1956
+ "128244": {
1957
+ "content": "<|reserved_special_token_236|>",
1958
+ "lstrip": false,
1959
+ "normalized": false,
1960
+ "rstrip": false,
1961
+ "single_word": false,
1962
+ "special": true
1963
+ },
1964
+ "128245": {
1965
+ "content": "<|reserved_special_token_237|>",
1966
+ "lstrip": false,
1967
+ "normalized": false,
1968
+ "rstrip": false,
1969
+ "single_word": false,
1970
+ "special": true
1971
+ },
1972
+ "128246": {
1973
+ "content": "<|reserved_special_token_238|>",
1974
+ "lstrip": false,
1975
+ "normalized": false,
1976
+ "rstrip": false,
1977
+ "single_word": false,
1978
+ "special": true
1979
+ },
1980
+ "128247": {
1981
+ "content": "<|reserved_special_token_239|>",
1982
+ "lstrip": false,
1983
+ "normalized": false,
1984
+ "rstrip": false,
1985
+ "single_word": false,
1986
+ "special": true
1987
+ },
1988
+ "128248": {
1989
+ "content": "<|reserved_special_token_240|>",
1990
+ "lstrip": false,
1991
+ "normalized": false,
1992
+ "rstrip": false,
1993
+ "single_word": false,
1994
+ "special": true
1995
+ },
1996
+ "128249": {
1997
+ "content": "<|reserved_special_token_241|>",
1998
+ "lstrip": false,
1999
+ "normalized": false,
2000
+ "rstrip": false,
2001
+ "single_word": false,
2002
+ "special": true
2003
+ },
2004
+ "128250": {
2005
+ "content": "<|reserved_special_token_242|>",
2006
+ "lstrip": false,
2007
+ "normalized": false,
2008
+ "rstrip": false,
2009
+ "single_word": false,
2010
+ "special": true
2011
+ },
2012
+ "128251": {
2013
+ "content": "<|reserved_special_token_243|>",
2014
+ "lstrip": false,
2015
+ "normalized": false,
2016
+ "rstrip": false,
2017
+ "single_word": false,
2018
+ "special": true
2019
+ },
2020
+ "128252": {
2021
+ "content": "<|reserved_special_token_244|>",
2022
+ "lstrip": false,
2023
+ "normalized": false,
2024
+ "rstrip": false,
2025
+ "single_word": false,
2026
+ "special": true
2027
+ },
2028
+ "128253": {
2029
+ "content": "<|reserved_special_token_245|>",
2030
+ "lstrip": false,
2031
+ "normalized": false,
2032
+ "rstrip": false,
2033
+ "single_word": false,
2034
+ "special": true
2035
+ },
2036
+ "128254": {
2037
+ "content": "<|reserved_special_token_246|>",
2038
+ "lstrip": false,
2039
+ "normalized": false,
2040
+ "rstrip": false,
2041
+ "single_word": false,
2042
+ "special": true
2043
+ },
2044
+ "128255": {
2045
+ "content": "<|reserved_special_token_247|>",
2046
+ "lstrip": false,
2047
+ "normalized": false,
2048
+ "rstrip": false,
2049
+ "single_word": false,
2050
+ "special": true
2051
+ }
2052
+ },
2053
+ "bos_token": "<|begin_of_text|>",
2054
+ "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 {%- if strftime_now is defined %}\n {%- set date_string = strftime_now(\"%d %b %Y\") %}\n {%- else %}\n {%- set date_string = \"26 Jul 2024\" %}\n {%- endif %}\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 #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if tools is not none %}\n {{- \"Environment: ipython\\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 {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {{- \"<|eot_id|>\" }}\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",
2055
+ "clean_up_tokenization_spaces": true,
2056
+ "eos_token": "<|eot_id|>",
2057
+ "extra_special_tokens": {},
2058
+ "model_input_names": [
2059
+ "input_ids",
2060
+ "attention_mask"
2061
+ ],
2062
+ "model_max_length": 131072,
2063
+ "pad_token": "<|eot_id|>",
2064
+ "tokenizer_class": "PreTrainedTokenizer"
2065
+ }
checkpoints_ia3_llama_class/checkpoint-88000/trainer_state.json ADDED
@@ -0,0 +1,1365 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 88000,
3
+ "best_metric": 0.936161178019818,
4
+ "best_model_checkpoint": "/home/sujeet-pg/wav2vec2/peft/checkpoints_ia3_llama_class/checkpoint-88000",
5
+ "epoch": 11.0,
6
+ "eval_steps": 500,
7
+ "global_step": 88000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0625,
14
+ "grad_norm": 29.181745529174805,
15
+ "learning_rate": 4.982673611111111e-05,
16
+ "loss": 1.9515,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.125,
21
+ "grad_norm": 84.54170989990234,
22
+ "learning_rate": 4.9653125e-05,
23
+ "loss": 1.4973,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 0.1875,
28
+ "grad_norm": 118.13458251953125,
29
+ "learning_rate": 4.947951388888889e-05,
30
+ "loss": 1.3271,
31
+ "step": 1500
32
+ },
33
+ {
34
+ "epoch": 0.25,
35
+ "grad_norm": 0.062166254967451096,
36
+ "learning_rate": 4.930590277777778e-05,
37
+ "loss": 0.9626,
38
+ "step": 2000
39
+ },
40
+ {
41
+ "epoch": 0.3125,
42
+ "grad_norm": 165.25686645507812,
43
+ "learning_rate": 4.9132291666666665e-05,
44
+ "loss": 0.7346,
45
+ "step": 2500
46
+ },
47
+ {
48
+ "epoch": 0.375,
49
+ "grad_norm": 0.6356489658355713,
50
+ "learning_rate": 4.8958680555555555e-05,
51
+ "loss": 0.8147,
52
+ "step": 3000
53
+ },
54
+ {
55
+ "epoch": 0.4375,
56
+ "grad_norm": 0.012186303734779358,
57
+ "learning_rate": 4.8785069444444445e-05,
58
+ "loss": 0.5557,
59
+ "step": 3500
60
+ },
61
+ {
62
+ "epoch": 0.5,
63
+ "grad_norm": 114.87812805175781,
64
+ "learning_rate": 4.8611458333333335e-05,
65
+ "loss": 0.546,
66
+ "step": 4000
67
+ },
68
+ {
69
+ "epoch": 0.5625,
70
+ "grad_norm": 0.3081382215023041,
71
+ "learning_rate": 4.8437847222222225e-05,
72
+ "loss": 0.5198,
73
+ "step": 4500
74
+ },
75
+ {
76
+ "epoch": 0.625,
77
+ "grad_norm": 0.0013407367514446378,
78
+ "learning_rate": 4.826423611111111e-05,
79
+ "loss": 0.4668,
80
+ "step": 5000
81
+ },
82
+ {
83
+ "epoch": 0.6875,
84
+ "grad_norm": 0.032304372638463974,
85
+ "learning_rate": 4.8090625e-05,
86
+ "loss": 0.4066,
87
+ "step": 5500
88
+ },
89
+ {
90
+ "epoch": 0.75,
91
+ "grad_norm": 0.350352019071579,
92
+ "learning_rate": 4.791701388888889e-05,
93
+ "loss": 0.494,
94
+ "step": 6000
95
+ },
96
+ {
97
+ "epoch": 0.8125,
98
+ "grad_norm": 0.031369373202323914,
99
+ "learning_rate": 4.774340277777778e-05,
100
+ "loss": 0.4372,
101
+ "step": 6500
102
+ },
103
+ {
104
+ "epoch": 0.875,
105
+ "grad_norm": 87.0584716796875,
106
+ "learning_rate": 4.756979166666667e-05,
107
+ "loss": 0.546,
108
+ "step": 7000
109
+ },
110
+ {
111
+ "epoch": 0.9375,
112
+ "grad_norm": 42.25841522216797,
113
+ "learning_rate": 4.739618055555556e-05,
114
+ "loss": 0.4929,
115
+ "step": 7500
116
+ },
117
+ {
118
+ "epoch": 1.0,
119
+ "grad_norm": 0.017110565677285194,
120
+ "learning_rate": 4.722256944444445e-05,
121
+ "loss": 0.4128,
122
+ "step": 8000
123
+ },
124
+ {
125
+ "epoch": 1.0,
126
+ "eval_loss": 0.34961560368537903,
127
+ "eval_pearson": 0.9195974916185884,
128
+ "eval_runtime": 52.203,
129
+ "eval_samples_per_second": 38.312,
130
+ "eval_steps_per_second": 19.156,
131
+ "step": 8000
132
+ },
133
+ {
134
+ "epoch": 1.0625,
135
+ "grad_norm": 39.48343276977539,
136
+ "learning_rate": 4.704895833333334e-05,
137
+ "loss": 0.1769,
138
+ "step": 8500
139
+ },
140
+ {
141
+ "epoch": 1.125,
142
+ "grad_norm": 0.0003292807668913156,
143
+ "learning_rate": 4.687534722222223e-05,
144
+ "loss": 0.3138,
145
+ "step": 9000
146
+ },
147
+ {
148
+ "epoch": 1.1875,
149
+ "grad_norm": 0.0025669685564935207,
150
+ "learning_rate": 4.670173611111111e-05,
151
+ "loss": 0.3529,
152
+ "step": 9500
153
+ },
154
+ {
155
+ "epoch": 1.25,
156
+ "grad_norm": 0.0019228530582040548,
157
+ "learning_rate": 4.6528125e-05,
158
+ "loss": 0.3181,
159
+ "step": 10000
160
+ },
161
+ {
162
+ "epoch": 1.3125,
163
+ "grad_norm": 0.09842195361852646,
164
+ "learning_rate": 4.635451388888889e-05,
165
+ "loss": 0.3358,
166
+ "step": 10500
167
+ },
168
+ {
169
+ "epoch": 1.375,
170
+ "grad_norm": 0.0006872316589578986,
171
+ "learning_rate": 4.618090277777778e-05,
172
+ "loss": 0.3395,
173
+ "step": 11000
174
+ },
175
+ {
176
+ "epoch": 1.4375,
177
+ "grad_norm": 0.008952559903264046,
178
+ "learning_rate": 4.600729166666667e-05,
179
+ "loss": 0.3287,
180
+ "step": 11500
181
+ },
182
+ {
183
+ "epoch": 1.5,
184
+ "grad_norm": 0.0010550743900239468,
185
+ "learning_rate": 4.583368055555556e-05,
186
+ "loss": 0.3742,
187
+ "step": 12000
188
+ },
189
+ {
190
+ "epoch": 1.5625,
191
+ "grad_norm": 0.0011425487464293838,
192
+ "learning_rate": 4.566006944444445e-05,
193
+ "loss": 0.2979,
194
+ "step": 12500
195
+ },
196
+ {
197
+ "epoch": 1.625,
198
+ "grad_norm": 14.729352951049805,
199
+ "learning_rate": 4.5486458333333334e-05,
200
+ "loss": 0.2669,
201
+ "step": 13000
202
+ },
203
+ {
204
+ "epoch": 1.6875,
205
+ "grad_norm": 1.1553162039490417e-05,
206
+ "learning_rate": 4.5312847222222224e-05,
207
+ "loss": 0.3885,
208
+ "step": 13500
209
+ },
210
+ {
211
+ "epoch": 1.75,
212
+ "grad_norm": 0.051722027361392975,
213
+ "learning_rate": 4.5139236111111114e-05,
214
+ "loss": 0.3096,
215
+ "step": 14000
216
+ },
217
+ {
218
+ "epoch": 1.8125,
219
+ "grad_norm": 0.12957464158535004,
220
+ "learning_rate": 4.4965625e-05,
221
+ "loss": 0.3479,
222
+ "step": 14500
223
+ },
224
+ {
225
+ "epoch": 1.875,
226
+ "grad_norm": 0.012610511854290962,
227
+ "learning_rate": 4.479201388888889e-05,
228
+ "loss": 0.432,
229
+ "step": 15000
230
+ },
231
+ {
232
+ "epoch": 1.9375,
233
+ "grad_norm": 0.022952524945139885,
234
+ "learning_rate": 4.461840277777778e-05,
235
+ "loss": 0.2932,
236
+ "step": 15500
237
+ },
238
+ {
239
+ "epoch": 2.0,
240
+ "grad_norm": 3.255659612477757e-05,
241
+ "learning_rate": 4.444479166666667e-05,
242
+ "loss": 0.2544,
243
+ "step": 16000
244
+ },
245
+ {
246
+ "epoch": 2.0,
247
+ "eval_loss": 0.3652373254299164,
248
+ "eval_pearson": 0.9308122796123071,
249
+ "eval_runtime": 52.221,
250
+ "eval_samples_per_second": 38.299,
251
+ "eval_steps_per_second": 19.149,
252
+ "step": 16000
253
+ },
254
+ {
255
+ "epoch": 2.0625,
256
+ "grad_norm": 349.7726135253906,
257
+ "learning_rate": 4.427118055555556e-05,
258
+ "loss": 0.3006,
259
+ "step": 16500
260
+ },
261
+ {
262
+ "epoch": 2.125,
263
+ "grad_norm": 0.05852258577942848,
264
+ "learning_rate": 4.409756944444445e-05,
265
+ "loss": 0.2222,
266
+ "step": 17000
267
+ },
268
+ {
269
+ "epoch": 2.1875,
270
+ "grad_norm": 8.100055129034445e-05,
271
+ "learning_rate": 4.3923958333333337e-05,
272
+ "loss": 0.2253,
273
+ "step": 17500
274
+ },
275
+ {
276
+ "epoch": 2.25,
277
+ "grad_norm": 0.015503599308431149,
278
+ "learning_rate": 4.3750347222222226e-05,
279
+ "loss": 0.301,
280
+ "step": 18000
281
+ },
282
+ {
283
+ "epoch": 2.3125,
284
+ "grad_norm": 0.0007520843064412475,
285
+ "learning_rate": 4.357673611111111e-05,
286
+ "loss": 0.1979,
287
+ "step": 18500
288
+ },
289
+ {
290
+ "epoch": 2.375,
291
+ "grad_norm": 0.0003110193647444248,
292
+ "learning_rate": 4.3403125e-05,
293
+ "loss": 0.2496,
294
+ "step": 19000
295
+ },
296
+ {
297
+ "epoch": 2.4375,
298
+ "grad_norm": 5.800446033477783,
299
+ "learning_rate": 4.322951388888889e-05,
300
+ "loss": 0.3028,
301
+ "step": 19500
302
+ },
303
+ {
304
+ "epoch": 2.5,
305
+ "grad_norm": 2.4347489215870155e-06,
306
+ "learning_rate": 4.305590277777778e-05,
307
+ "loss": 0.2218,
308
+ "step": 20000
309
+ },
310
+ {
311
+ "epoch": 2.5625,
312
+ "grad_norm": 0.972939133644104,
313
+ "learning_rate": 4.288229166666667e-05,
314
+ "loss": 0.2485,
315
+ "step": 20500
316
+ },
317
+ {
318
+ "epoch": 2.625,
319
+ "grad_norm": 1.2701035737991333,
320
+ "learning_rate": 4.270868055555556e-05,
321
+ "loss": 0.179,
322
+ "step": 21000
323
+ },
324
+ {
325
+ "epoch": 2.6875,
326
+ "grad_norm": 0.0001465667737647891,
327
+ "learning_rate": 4.253506944444445e-05,
328
+ "loss": 0.337,
329
+ "step": 21500
330
+ },
331
+ {
332
+ "epoch": 2.75,
333
+ "grad_norm": 188.92559814453125,
334
+ "learning_rate": 4.236145833333334e-05,
335
+ "loss": 0.2353,
336
+ "step": 22000
337
+ },
338
+ {
339
+ "epoch": 2.8125,
340
+ "grad_norm": 0.0020125608425587416,
341
+ "learning_rate": 4.218784722222223e-05,
342
+ "loss": 0.2412,
343
+ "step": 22500
344
+ },
345
+ {
346
+ "epoch": 2.875,
347
+ "grad_norm": 0.030752288177609444,
348
+ "learning_rate": 4.201423611111111e-05,
349
+ "loss": 0.2645,
350
+ "step": 23000
351
+ },
352
+ {
353
+ "epoch": 2.9375,
354
+ "grad_norm": 76.4650650024414,
355
+ "learning_rate": 4.1840625e-05,
356
+ "loss": 0.2856,
357
+ "step": 23500
358
+ },
359
+ {
360
+ "epoch": 3.0,
361
+ "grad_norm": 0.0004072492301929742,
362
+ "learning_rate": 4.166701388888889e-05,
363
+ "loss": 0.2395,
364
+ "step": 24000
365
+ },
366
+ {
367
+ "epoch": 3.0,
368
+ "eval_loss": 0.28703999519348145,
369
+ "eval_pearson": 0.9358259106635223,
370
+ "eval_runtime": 52.1011,
371
+ "eval_samples_per_second": 38.387,
372
+ "eval_steps_per_second": 19.193,
373
+ "step": 24000
374
+ },
375
+ {
376
+ "epoch": 3.0625,
377
+ "grad_norm": 0.007601168937981129,
378
+ "learning_rate": 4.149340277777778e-05,
379
+ "loss": 0.1748,
380
+ "step": 24500
381
+ },
382
+ {
383
+ "epoch": 3.125,
384
+ "grad_norm": 0.026926109567284584,
385
+ "learning_rate": 4.1319791666666665e-05,
386
+ "loss": 0.1542,
387
+ "step": 25000
388
+ },
389
+ {
390
+ "epoch": 3.1875,
391
+ "grad_norm": 1.8115358352661133,
392
+ "learning_rate": 4.1146180555555555e-05,
393
+ "loss": 0.2275,
394
+ "step": 25500
395
+ },
396
+ {
397
+ "epoch": 3.25,
398
+ "grad_norm": 0.06953763216733932,
399
+ "learning_rate": 4.0972569444444445e-05,
400
+ "loss": 0.1706,
401
+ "step": 26000
402
+ },
403
+ {
404
+ "epoch": 3.3125,
405
+ "grad_norm": 0.020493032410740852,
406
+ "learning_rate": 4.0798958333333335e-05,
407
+ "loss": 0.1474,
408
+ "step": 26500
409
+ },
410
+ {
411
+ "epoch": 3.375,
412
+ "grad_norm": 0.005125588737428188,
413
+ "learning_rate": 4.0625347222222225e-05,
414
+ "loss": 0.1723,
415
+ "step": 27000
416
+ },
417
+ {
418
+ "epoch": 3.4375,
419
+ "grad_norm": 5.002508163452148,
420
+ "learning_rate": 4.045173611111111e-05,
421
+ "loss": 0.196,
422
+ "step": 27500
423
+ },
424
+ {
425
+ "epoch": 3.5,
426
+ "grad_norm": 0.000834703678265214,
427
+ "learning_rate": 4.0278125e-05,
428
+ "loss": 0.1449,
429
+ "step": 28000
430
+ },
431
+ {
432
+ "epoch": 3.5625,
433
+ "grad_norm": 0.01109158806502819,
434
+ "learning_rate": 4.010451388888889e-05,
435
+ "loss": 0.2287,
436
+ "step": 28500
437
+ },
438
+ {
439
+ "epoch": 3.625,
440
+ "grad_norm": 9.071109161595814e-06,
441
+ "learning_rate": 3.993090277777778e-05,
442
+ "loss": 0.1955,
443
+ "step": 29000
444
+ },
445
+ {
446
+ "epoch": 3.6875,
447
+ "grad_norm": 0.0006111862603574991,
448
+ "learning_rate": 3.975729166666667e-05,
449
+ "loss": 0.2147,
450
+ "step": 29500
451
+ },
452
+ {
453
+ "epoch": 3.75,
454
+ "grad_norm": 6.614517928937858e-07,
455
+ "learning_rate": 3.958368055555556e-05,
456
+ "loss": 0.2289,
457
+ "step": 30000
458
+ },
459
+ {
460
+ "epoch": 3.8125,
461
+ "grad_norm": 5.0481699872761965e-05,
462
+ "learning_rate": 3.941006944444445e-05,
463
+ "loss": 0.1941,
464
+ "step": 30500
465
+ },
466
+ {
467
+ "epoch": 3.875,
468
+ "grad_norm": 2.837545871734619,
469
+ "learning_rate": 3.923645833333334e-05,
470
+ "loss": 0.1753,
471
+ "step": 31000
472
+ },
473
+ {
474
+ "epoch": 3.9375,
475
+ "grad_norm": 0.00021911883959546685,
476
+ "learning_rate": 3.906284722222223e-05,
477
+ "loss": 0.1967,
478
+ "step": 31500
479
+ },
480
+ {
481
+ "epoch": 4.0,
482
+ "grad_norm": 0.008439241908490658,
483
+ "learning_rate": 3.888923611111111e-05,
484
+ "loss": 0.2341,
485
+ "step": 32000
486
+ },
487
+ {
488
+ "epoch": 4.0,
489
+ "eval_loss": 0.28366541862487793,
490
+ "eval_pearson": 0.9336592859812687,
491
+ "eval_runtime": 52.2768,
492
+ "eval_samples_per_second": 38.258,
493
+ "eval_steps_per_second": 19.129,
494
+ "step": 32000
495
+ },
496
+ {
497
+ "epoch": 4.0625,
498
+ "grad_norm": 3.5697648525238037,
499
+ "learning_rate": 3.8715625e-05,
500
+ "loss": 0.0898,
501
+ "step": 32500
502
+ },
503
+ {
504
+ "epoch": 4.125,
505
+ "grad_norm": 0.005574432201683521,
506
+ "learning_rate": 3.854201388888889e-05,
507
+ "loss": 0.0931,
508
+ "step": 33000
509
+ },
510
+ {
511
+ "epoch": 4.1875,
512
+ "grad_norm": 0.4526767134666443,
513
+ "learning_rate": 3.836840277777778e-05,
514
+ "loss": 0.1269,
515
+ "step": 33500
516
+ },
517
+ {
518
+ "epoch": 4.25,
519
+ "grad_norm": 0.0006220944924280047,
520
+ "learning_rate": 3.819479166666667e-05,
521
+ "loss": 0.1229,
522
+ "step": 34000
523
+ },
524
+ {
525
+ "epoch": 4.3125,
526
+ "grad_norm": 0.0021529244258999825,
527
+ "learning_rate": 3.802118055555556e-05,
528
+ "loss": 0.0941,
529
+ "step": 34500
530
+ },
531
+ {
532
+ "epoch": 4.375,
533
+ "grad_norm": 161.37889099121094,
534
+ "learning_rate": 3.784756944444445e-05,
535
+ "loss": 0.1504,
536
+ "step": 35000
537
+ },
538
+ {
539
+ "epoch": 4.4375,
540
+ "grad_norm": 0.11136477440595627,
541
+ "learning_rate": 3.7673958333333334e-05,
542
+ "loss": 0.1809,
543
+ "step": 35500
544
+ },
545
+ {
546
+ "epoch": 4.5,
547
+ "grad_norm": 0.001285308855585754,
548
+ "learning_rate": 3.7500347222222224e-05,
549
+ "loss": 0.0936,
550
+ "step": 36000
551
+ },
552
+ {
553
+ "epoch": 4.5625,
554
+ "grad_norm": 9.097888687392697e-05,
555
+ "learning_rate": 3.7326736111111114e-05,
556
+ "loss": 0.138,
557
+ "step": 36500
558
+ },
559
+ {
560
+ "epoch": 4.625,
561
+ "grad_norm": 8.100504373942385e-07,
562
+ "learning_rate": 3.7153125e-05,
563
+ "loss": 0.1018,
564
+ "step": 37000
565
+ },
566
+ {
567
+ "epoch": 4.6875,
568
+ "grad_norm": 7.76401338953292e-06,
569
+ "learning_rate": 3.697951388888889e-05,
570
+ "loss": 0.1467,
571
+ "step": 37500
572
+ },
573
+ {
574
+ "epoch": 4.75,
575
+ "grad_norm": 0.00011219551379326731,
576
+ "learning_rate": 3.680590277777778e-05,
577
+ "loss": 0.1253,
578
+ "step": 38000
579
+ },
580
+ {
581
+ "epoch": 4.8125,
582
+ "grad_norm": 6.52613493912213e-07,
583
+ "learning_rate": 3.6632291666666667e-05,
584
+ "loss": 0.1658,
585
+ "step": 38500
586
+ },
587
+ {
588
+ "epoch": 4.875,
589
+ "grad_norm": 0.00043506777728907764,
590
+ "learning_rate": 3.6458680555555557e-05,
591
+ "loss": 0.1746,
592
+ "step": 39000
593
+ },
594
+ {
595
+ "epoch": 4.9375,
596
+ "grad_norm": 0.003737818216904998,
597
+ "learning_rate": 3.6285069444444446e-05,
598
+ "loss": 0.1511,
599
+ "step": 39500
600
+ },
601
+ {
602
+ "epoch": 5.0,
603
+ "grad_norm": 0.0032031103037297726,
604
+ "learning_rate": 3.6111458333333336e-05,
605
+ "loss": 0.1175,
606
+ "step": 40000
607
+ },
608
+ {
609
+ "epoch": 5.0,
610
+ "eval_loss": 0.3400997221469879,
611
+ "eval_pearson": 0.9278541992287661,
612
+ "eval_runtime": 52.4259,
613
+ "eval_samples_per_second": 38.149,
614
+ "eval_steps_per_second": 19.075,
615
+ "step": 40000
616
+ },
617
+ {
618
+ "epoch": 5.0625,
619
+ "grad_norm": 7.578780059702694e-05,
620
+ "learning_rate": 3.5937847222222226e-05,
621
+ "loss": 0.0854,
622
+ "step": 40500
623
+ },
624
+ {
625
+ "epoch": 5.125,
626
+ "grad_norm": 0.00047107384307309985,
627
+ "learning_rate": 3.576423611111111e-05,
628
+ "loss": 0.0978,
629
+ "step": 41000
630
+ },
631
+ {
632
+ "epoch": 5.1875,
633
+ "grad_norm": 1.537612479296513e-05,
634
+ "learning_rate": 3.5590625e-05,
635
+ "loss": 0.0771,
636
+ "step": 41500
637
+ },
638
+ {
639
+ "epoch": 5.25,
640
+ "grad_norm": 0.4128485918045044,
641
+ "learning_rate": 3.541701388888889e-05,
642
+ "loss": 0.0735,
643
+ "step": 42000
644
+ },
645
+ {
646
+ "epoch": 5.3125,
647
+ "grad_norm": 1.5655250549316406,
648
+ "learning_rate": 3.524340277777778e-05,
649
+ "loss": 0.0498,
650
+ "step": 42500
651
+ },
652
+ {
653
+ "epoch": 5.375,
654
+ "grad_norm": 7.616046104885754e-07,
655
+ "learning_rate": 3.506979166666667e-05,
656
+ "loss": 0.0931,
657
+ "step": 43000
658
+ },
659
+ {
660
+ "epoch": 5.4375,
661
+ "grad_norm": 88.26677703857422,
662
+ "learning_rate": 3.489618055555556e-05,
663
+ "loss": 0.0792,
664
+ "step": 43500
665
+ },
666
+ {
667
+ "epoch": 5.5,
668
+ "grad_norm": 5.622899834634154e-07,
669
+ "learning_rate": 3.472256944444445e-05,
670
+ "loss": 0.0598,
671
+ "step": 44000
672
+ },
673
+ {
674
+ "epoch": 5.5625,
675
+ "grad_norm": 3.284021659055725e-07,
676
+ "learning_rate": 3.454895833333334e-05,
677
+ "loss": 0.0569,
678
+ "step": 44500
679
+ },
680
+ {
681
+ "epoch": 5.625,
682
+ "grad_norm": 7.701730646658689e-05,
683
+ "learning_rate": 3.437534722222223e-05,
684
+ "loss": 0.1013,
685
+ "step": 45000
686
+ },
687
+ {
688
+ "epoch": 5.6875,
689
+ "grad_norm": 0.0011569270864129066,
690
+ "learning_rate": 3.420173611111111e-05,
691
+ "loss": 0.0752,
692
+ "step": 45500
693
+ },
694
+ {
695
+ "epoch": 5.75,
696
+ "grad_norm": 0.005151362158358097,
697
+ "learning_rate": 3.4028125e-05,
698
+ "loss": 0.1286,
699
+ "step": 46000
700
+ },
701
+ {
702
+ "epoch": 5.8125,
703
+ "grad_norm": 2.8667493268130784e-08,
704
+ "learning_rate": 3.385451388888889e-05,
705
+ "loss": 0.0628,
706
+ "step": 46500
707
+ },
708
+ {
709
+ "epoch": 5.875,
710
+ "grad_norm": 2.9006994282099186e-06,
711
+ "learning_rate": 3.3680902777777775e-05,
712
+ "loss": 0.0778,
713
+ "step": 47000
714
+ },
715
+ {
716
+ "epoch": 5.9375,
717
+ "grad_norm": 1.4291666047938634e-05,
718
+ "learning_rate": 3.3507291666666665e-05,
719
+ "loss": 0.0939,
720
+ "step": 47500
721
+ },
722
+ {
723
+ "epoch": 6.0,
724
+ "grad_norm": 3.1977786420611665e-05,
725
+ "learning_rate": 3.3333680555555555e-05,
726
+ "loss": 0.0701,
727
+ "step": 48000
728
+ },
729
+ {
730
+ "epoch": 6.0,
731
+ "eval_loss": 0.3394077718257904,
732
+ "eval_pearson": 0.929029551743213,
733
+ "eval_runtime": 52.4713,
734
+ "eval_samples_per_second": 38.116,
735
+ "eval_steps_per_second": 19.058,
736
+ "step": 48000
737
+ },
738
+ {
739
+ "epoch": 6.0625,
740
+ "grad_norm": 2.3781665277056163e-06,
741
+ "learning_rate": 3.3160069444444445e-05,
742
+ "loss": 0.0575,
743
+ "step": 48500
744
+ },
745
+ {
746
+ "epoch": 6.125,
747
+ "grad_norm": 0.00014402755186893046,
748
+ "learning_rate": 3.2986458333333335e-05,
749
+ "loss": 0.0599,
750
+ "step": 49000
751
+ },
752
+ {
753
+ "epoch": 6.1875,
754
+ "grad_norm": 0.0024268697015941143,
755
+ "learning_rate": 3.2812847222222225e-05,
756
+ "loss": 0.0134,
757
+ "step": 49500
758
+ },
759
+ {
760
+ "epoch": 6.25,
761
+ "grad_norm": 2.872504949569702,
762
+ "learning_rate": 3.263923611111111e-05,
763
+ "loss": 0.0529,
764
+ "step": 50000
765
+ },
766
+ {
767
+ "epoch": 6.3125,
768
+ "grad_norm": 0.08783645182847977,
769
+ "learning_rate": 3.2465625e-05,
770
+ "loss": 0.0429,
771
+ "step": 50500
772
+ },
773
+ {
774
+ "epoch": 6.375,
775
+ "grad_norm": 8.48967170715332,
776
+ "learning_rate": 3.229201388888889e-05,
777
+ "loss": 0.0615,
778
+ "step": 51000
779
+ },
780
+ {
781
+ "epoch": 6.4375,
782
+ "grad_norm": 4.978901984031836e-07,
783
+ "learning_rate": 3.211840277777778e-05,
784
+ "loss": 0.0493,
785
+ "step": 51500
786
+ },
787
+ {
788
+ "epoch": 6.5,
789
+ "grad_norm": 1.5710222669440554e-06,
790
+ "learning_rate": 3.194479166666667e-05,
791
+ "loss": 0.0842,
792
+ "step": 52000
793
+ },
794
+ {
795
+ "epoch": 6.5625,
796
+ "grad_norm": 0.0002388143038842827,
797
+ "learning_rate": 3.177118055555556e-05,
798
+ "loss": 0.0322,
799
+ "step": 52500
800
+ },
801
+ {
802
+ "epoch": 6.625,
803
+ "grad_norm": 4.66664324960675e-08,
804
+ "learning_rate": 3.159756944444445e-05,
805
+ "loss": 0.0182,
806
+ "step": 53000
807
+ },
808
+ {
809
+ "epoch": 6.6875,
810
+ "grad_norm": 57.2918586730957,
811
+ "learning_rate": 3.142395833333334e-05,
812
+ "loss": 0.0851,
813
+ "step": 53500
814
+ },
815
+ {
816
+ "epoch": 6.75,
817
+ "grad_norm": 5.3962357924319804e-05,
818
+ "learning_rate": 3.125034722222223e-05,
819
+ "loss": 0.0644,
820
+ "step": 54000
821
+ },
822
+ {
823
+ "epoch": 6.8125,
824
+ "grad_norm": 0.006401342805474997,
825
+ "learning_rate": 3.107673611111111e-05,
826
+ "loss": 0.0943,
827
+ "step": 54500
828
+ },
829
+ {
830
+ "epoch": 6.875,
831
+ "grad_norm": 3.415437390685838e-07,
832
+ "learning_rate": 3.0903125e-05,
833
+ "loss": 0.0967,
834
+ "step": 55000
835
+ },
836
+ {
837
+ "epoch": 6.9375,
838
+ "grad_norm": 5.508160825229425e-07,
839
+ "learning_rate": 3.072951388888889e-05,
840
+ "loss": 0.0507,
841
+ "step": 55500
842
+ },
843
+ {
844
+ "epoch": 7.0,
845
+ "grad_norm": 0.04088839516043663,
846
+ "learning_rate": 3.055590277777778e-05,
847
+ "loss": 0.0139,
848
+ "step": 56000
849
+ },
850
+ {
851
+ "epoch": 7.0,
852
+ "eval_loss": 0.37575554847717285,
853
+ "eval_pearson": 0.9206240663481206,
854
+ "eval_runtime": 52.4561,
855
+ "eval_samples_per_second": 38.127,
856
+ "eval_steps_per_second": 19.064,
857
+ "step": 56000
858
+ },
859
+ {
860
+ "epoch": 7.0625,
861
+ "grad_norm": 0.004823420196771622,
862
+ "learning_rate": 3.0382291666666667e-05,
863
+ "loss": 0.0539,
864
+ "step": 56500
865
+ },
866
+ {
867
+ "epoch": 7.125,
868
+ "grad_norm": 106.49919128417969,
869
+ "learning_rate": 3.0208680555555557e-05,
870
+ "loss": 0.0232,
871
+ "step": 57000
872
+ },
873
+ {
874
+ "epoch": 7.1875,
875
+ "grad_norm": 1.074000238077133e-06,
876
+ "learning_rate": 3.0035069444444447e-05,
877
+ "loss": 0.0187,
878
+ "step": 57500
879
+ },
880
+ {
881
+ "epoch": 7.25,
882
+ "grad_norm": 0.0039020858239382505,
883
+ "learning_rate": 2.9861458333333337e-05,
884
+ "loss": 0.0472,
885
+ "step": 58000
886
+ },
887
+ {
888
+ "epoch": 7.3125,
889
+ "grad_norm": 0.0892600491642952,
890
+ "learning_rate": 2.9687847222222227e-05,
891
+ "loss": 0.0658,
892
+ "step": 58500
893
+ },
894
+ {
895
+ "epoch": 7.375,
896
+ "grad_norm": 0.00350657245144248,
897
+ "learning_rate": 2.951423611111111e-05,
898
+ "loss": 0.0456,
899
+ "step": 59000
900
+ },
901
+ {
902
+ "epoch": 7.4375,
903
+ "grad_norm": 0.0006594175356440246,
904
+ "learning_rate": 2.9340625e-05,
905
+ "loss": 0.0171,
906
+ "step": 59500
907
+ },
908
+ {
909
+ "epoch": 7.5,
910
+ "grad_norm": 92.61225128173828,
911
+ "learning_rate": 2.916701388888889e-05,
912
+ "loss": 0.0274,
913
+ "step": 60000
914
+ },
915
+ {
916
+ "epoch": 7.5625,
917
+ "grad_norm": 3.026230599445512e-09,
918
+ "learning_rate": 2.899340277777778e-05,
919
+ "loss": 0.0471,
920
+ "step": 60500
921
+ },
922
+ {
923
+ "epoch": 7.625,
924
+ "grad_norm": 1.0678179023670964e-05,
925
+ "learning_rate": 2.8819791666666666e-05,
926
+ "loss": 0.0216,
927
+ "step": 61000
928
+ },
929
+ {
930
+ "epoch": 7.6875,
931
+ "grad_norm": 5.752791912527755e-05,
932
+ "learning_rate": 2.8646180555555556e-05,
933
+ "loss": 0.0157,
934
+ "step": 61500
935
+ },
936
+ {
937
+ "epoch": 7.75,
938
+ "grad_norm": 5.118190288543701,
939
+ "learning_rate": 2.8472569444444446e-05,
940
+ "loss": 0.0616,
941
+ "step": 62000
942
+ },
943
+ {
944
+ "epoch": 7.8125,
945
+ "grad_norm": 2.0125851733610034e-05,
946
+ "learning_rate": 2.8298958333333336e-05,
947
+ "loss": 0.0783,
948
+ "step": 62500
949
+ },
950
+ {
951
+ "epoch": 7.875,
952
+ "grad_norm": 161.75416564941406,
953
+ "learning_rate": 2.8125347222222226e-05,
954
+ "loss": 0.0295,
955
+ "step": 63000
956
+ },
957
+ {
958
+ "epoch": 7.9375,
959
+ "grad_norm": 1.577711117306535e-08,
960
+ "learning_rate": 2.795173611111111e-05,
961
+ "loss": 0.0498,
962
+ "step": 63500
963
+ },
964
+ {
965
+ "epoch": 8.0,
966
+ "grad_norm": 5.166618279872637e-07,
967
+ "learning_rate": 2.7778125e-05,
968
+ "loss": 0.0397,
969
+ "step": 64000
970
+ },
971
+ {
972
+ "epoch": 8.0,
973
+ "eval_loss": 0.3336261510848999,
974
+ "eval_pearson": 0.9327475370491191,
975
+ "eval_runtime": 52.4675,
976
+ "eval_samples_per_second": 38.119,
977
+ "eval_steps_per_second": 19.059,
978
+ "step": 64000
979
+ },
980
+ {
981
+ "epoch": 8.0625,
982
+ "grad_norm": 0.0026754948776215315,
983
+ "learning_rate": 2.760451388888889e-05,
984
+ "loss": 0.026,
985
+ "step": 64500
986
+ },
987
+ {
988
+ "epoch": 8.125,
989
+ "grad_norm": 3.3581352454348234e-07,
990
+ "learning_rate": 2.743090277777778e-05,
991
+ "loss": 0.0115,
992
+ "step": 65000
993
+ },
994
+ {
995
+ "epoch": 8.1875,
996
+ "grad_norm": 2.0662416488903546e-07,
997
+ "learning_rate": 2.725729166666667e-05,
998
+ "loss": 0.012,
999
+ "step": 65500
1000
+ },
1001
+ {
1002
+ "epoch": 8.25,
1003
+ "grad_norm": 8.040846921630873e-08,
1004
+ "learning_rate": 2.7083680555555556e-05,
1005
+ "loss": 0.0406,
1006
+ "step": 66000
1007
+ },
1008
+ {
1009
+ "epoch": 8.3125,
1010
+ "grad_norm": 3.422968006816518e-07,
1011
+ "learning_rate": 2.6910069444444446e-05,
1012
+ "loss": 0.0321,
1013
+ "step": 66500
1014
+ },
1015
+ {
1016
+ "epoch": 8.375,
1017
+ "grad_norm": 0.00017860137450043112,
1018
+ "learning_rate": 2.6736458333333336e-05,
1019
+ "loss": 0.0448,
1020
+ "step": 67000
1021
+ },
1022
+ {
1023
+ "epoch": 8.4375,
1024
+ "grad_norm": 1.2621427236680915e-09,
1025
+ "learning_rate": 2.6562847222222225e-05,
1026
+ "loss": 0.0455,
1027
+ "step": 67500
1028
+ },
1029
+ {
1030
+ "epoch": 8.5,
1031
+ "grad_norm": 1.4346144325827481e-06,
1032
+ "learning_rate": 2.638923611111111e-05,
1033
+ "loss": 0.0325,
1034
+ "step": 68000
1035
+ },
1036
+ {
1037
+ "epoch": 8.5625,
1038
+ "grad_norm": 1.2407322174112778e-06,
1039
+ "learning_rate": 2.6215625e-05,
1040
+ "loss": 0.0223,
1041
+ "step": 68500
1042
+ },
1043
+ {
1044
+ "epoch": 8.625,
1045
+ "grad_norm": 3.0256799163908e-06,
1046
+ "learning_rate": 2.604201388888889e-05,
1047
+ "loss": 0.0019,
1048
+ "step": 69000
1049
+ },
1050
+ {
1051
+ "epoch": 8.6875,
1052
+ "grad_norm": 0.007253507152199745,
1053
+ "learning_rate": 2.586840277777778e-05,
1054
+ "loss": 0.0085,
1055
+ "step": 69500
1056
+ },
1057
+ {
1058
+ "epoch": 8.75,
1059
+ "grad_norm": 2.782409467272373e-07,
1060
+ "learning_rate": 2.569479166666667e-05,
1061
+ "loss": 0.0518,
1062
+ "step": 70000
1063
+ },
1064
+ {
1065
+ "epoch": 8.8125,
1066
+ "grad_norm": 0.000820077199023217,
1067
+ "learning_rate": 2.552118055555556e-05,
1068
+ "loss": 0.031,
1069
+ "step": 70500
1070
+ },
1071
+ {
1072
+ "epoch": 8.875,
1073
+ "grad_norm": 2.470728213666007e-05,
1074
+ "learning_rate": 2.5347569444444448e-05,
1075
+ "loss": 0.0354,
1076
+ "step": 71000
1077
+ },
1078
+ {
1079
+ "epoch": 8.9375,
1080
+ "grad_norm": 9.137271263170987e-05,
1081
+ "learning_rate": 2.5173958333333335e-05,
1082
+ "loss": 0.0666,
1083
+ "step": 71500
1084
+ },
1085
+ {
1086
+ "epoch": 9.0,
1087
+ "grad_norm": 0.00029885413823649287,
1088
+ "learning_rate": 2.5000347222222225e-05,
1089
+ "loss": 0.0267,
1090
+ "step": 72000
1091
+ },
1092
+ {
1093
+ "epoch": 9.0,
1094
+ "eval_loss": 0.37894001603126526,
1095
+ "eval_pearson": 0.9279985680079542,
1096
+ "eval_runtime": 52.4816,
1097
+ "eval_samples_per_second": 38.109,
1098
+ "eval_steps_per_second": 19.054,
1099
+ "step": 72000
1100
+ },
1101
+ {
1102
+ "epoch": 9.0625,
1103
+ "grad_norm": 6.724835839122534e-05,
1104
+ "learning_rate": 2.482673611111111e-05,
1105
+ "loss": 0.0044,
1106
+ "step": 72500
1107
+ },
1108
+ {
1109
+ "epoch": 9.125,
1110
+ "grad_norm": 9.228666164595722e-10,
1111
+ "learning_rate": 2.4653125e-05,
1112
+ "loss": 0.0095,
1113
+ "step": 73000
1114
+ },
1115
+ {
1116
+ "epoch": 9.1875,
1117
+ "grad_norm": 0.00011938459647353739,
1118
+ "learning_rate": 2.447951388888889e-05,
1119
+ "loss": 0.0384,
1120
+ "step": 73500
1121
+ },
1122
+ {
1123
+ "epoch": 9.25,
1124
+ "grad_norm": 1.6898056287573127e-09,
1125
+ "learning_rate": 2.4305902777777778e-05,
1126
+ "loss": 0.0182,
1127
+ "step": 74000
1128
+ },
1129
+ {
1130
+ "epoch": 9.3125,
1131
+ "grad_norm": 5.753568288469069e-09,
1132
+ "learning_rate": 2.4132291666666668e-05,
1133
+ "loss": 0.0075,
1134
+ "step": 74500
1135
+ },
1136
+ {
1137
+ "epoch": 9.375,
1138
+ "grad_norm": 5.144208614638046e-08,
1139
+ "learning_rate": 2.3958680555555558e-05,
1140
+ "loss": 0.0172,
1141
+ "step": 75000
1142
+ },
1143
+ {
1144
+ "epoch": 9.4375,
1145
+ "grad_norm": 9.800347200439319e-10,
1146
+ "learning_rate": 2.3785069444444448e-05,
1147
+ "loss": 0.0431,
1148
+ "step": 75500
1149
+ },
1150
+ {
1151
+ "epoch": 9.5,
1152
+ "grad_norm": 5.440585135185749e-11,
1153
+ "learning_rate": 2.3611458333333334e-05,
1154
+ "loss": 0.0109,
1155
+ "step": 76000
1156
+ },
1157
+ {
1158
+ "epoch": 9.5625,
1159
+ "grad_norm": 0.00019604770932346582,
1160
+ "learning_rate": 2.3437847222222224e-05,
1161
+ "loss": 0.0284,
1162
+ "step": 76500
1163
+ },
1164
+ {
1165
+ "epoch": 9.625,
1166
+ "grad_norm": 1.242908239364624,
1167
+ "learning_rate": 2.3264236111111114e-05,
1168
+ "loss": 0.0405,
1169
+ "step": 77000
1170
+ },
1171
+ {
1172
+ "epoch": 9.6875,
1173
+ "grad_norm": 1.540728953841608e-05,
1174
+ "learning_rate": 2.3090625e-05,
1175
+ "loss": 0.0435,
1176
+ "step": 77500
1177
+ },
1178
+ {
1179
+ "epoch": 9.75,
1180
+ "grad_norm": 0.00013433759158942848,
1181
+ "learning_rate": 2.291701388888889e-05,
1182
+ "loss": 0.0181,
1183
+ "step": 78000
1184
+ },
1185
+ {
1186
+ "epoch": 9.8125,
1187
+ "grad_norm": 3.088209687973631e-10,
1188
+ "learning_rate": 2.2743402777777777e-05,
1189
+ "loss": 0.0228,
1190
+ "step": 78500
1191
+ },
1192
+ {
1193
+ "epoch": 9.875,
1194
+ "grad_norm": 0.000814907078165561,
1195
+ "learning_rate": 2.2569791666666667e-05,
1196
+ "loss": 0.0499,
1197
+ "step": 79000
1198
+ },
1199
+ {
1200
+ "epoch": 9.9375,
1201
+ "grad_norm": 1.274260625905299e-07,
1202
+ "learning_rate": 2.2396180555555557e-05,
1203
+ "loss": 0.0316,
1204
+ "step": 79500
1205
+ },
1206
+ {
1207
+ "epoch": 10.0,
1208
+ "grad_norm": 4.301631997805089e-05,
1209
+ "learning_rate": 2.2222569444444447e-05,
1210
+ "loss": 0.015,
1211
+ "step": 80000
1212
+ },
1213
+ {
1214
+ "epoch": 10.0,
1215
+ "eval_loss": 0.38902410864830017,
1216
+ "eval_pearson": 0.9249309324232664,
1217
+ "eval_runtime": 52.3807,
1218
+ "eval_samples_per_second": 38.182,
1219
+ "eval_steps_per_second": 19.091,
1220
+ "step": 80000
1221
+ },
1222
+ {
1223
+ "epoch": 10.0625,
1224
+ "grad_norm": 1.7468665403086447e-10,
1225
+ "learning_rate": 2.2048958333333333e-05,
1226
+ "loss": 0.0081,
1227
+ "step": 80500
1228
+ },
1229
+ {
1230
+ "epoch": 10.125,
1231
+ "grad_norm": 6.71422021696344e-05,
1232
+ "learning_rate": 2.1875347222222223e-05,
1233
+ "loss": 0.0143,
1234
+ "step": 81000
1235
+ },
1236
+ {
1237
+ "epoch": 10.1875,
1238
+ "grad_norm": 3.1802871944819344e-06,
1239
+ "learning_rate": 2.1701736111111113e-05,
1240
+ "loss": 0.029,
1241
+ "step": 81500
1242
+ },
1243
+ {
1244
+ "epoch": 10.25,
1245
+ "grad_norm": 0.014791320078074932,
1246
+ "learning_rate": 2.1528125000000003e-05,
1247
+ "loss": 0.0054,
1248
+ "step": 82000
1249
+ },
1250
+ {
1251
+ "epoch": 10.3125,
1252
+ "grad_norm": 2.0462434235923865e-07,
1253
+ "learning_rate": 2.135451388888889e-05,
1254
+ "loss": 0.0436,
1255
+ "step": 82500
1256
+ },
1257
+ {
1258
+ "epoch": 10.375,
1259
+ "grad_norm": 1.3791065216064453,
1260
+ "learning_rate": 2.1180902777777776e-05,
1261
+ "loss": 0.0181,
1262
+ "step": 83000
1263
+ },
1264
+ {
1265
+ "epoch": 10.4375,
1266
+ "grad_norm": 0.002008361741900444,
1267
+ "learning_rate": 2.1007291666666666e-05,
1268
+ "loss": 0.0082,
1269
+ "step": 83500
1270
+ },
1271
+ {
1272
+ "epoch": 10.5,
1273
+ "grad_norm": 5.804303704337599e-09,
1274
+ "learning_rate": 2.0833680555555556e-05,
1275
+ "loss": 0.0249,
1276
+ "step": 84000
1277
+ },
1278
+ {
1279
+ "epoch": 10.5625,
1280
+ "grad_norm": 0.0007163327536545694,
1281
+ "learning_rate": 2.0660069444444446e-05,
1282
+ "loss": 0.0112,
1283
+ "step": 84500
1284
+ },
1285
+ {
1286
+ "epoch": 10.625,
1287
+ "grad_norm": 0.0001620600960450247,
1288
+ "learning_rate": 2.0486458333333333e-05,
1289
+ "loss": 0.0295,
1290
+ "step": 85000
1291
+ },
1292
+ {
1293
+ "epoch": 10.6875,
1294
+ "grad_norm": 0.05068128928542137,
1295
+ "learning_rate": 2.0312847222222223e-05,
1296
+ "loss": 0.0223,
1297
+ "step": 85500
1298
+ },
1299
+ {
1300
+ "epoch": 10.75,
1301
+ "grad_norm": 0.0007038409821689129,
1302
+ "learning_rate": 2.0139236111111113e-05,
1303
+ "loss": 0.0192,
1304
+ "step": 86000
1305
+ },
1306
+ {
1307
+ "epoch": 10.8125,
1308
+ "grad_norm": 0.024000702425837517,
1309
+ "learning_rate": 1.9965625000000002e-05,
1310
+ "loss": 0.0249,
1311
+ "step": 86500
1312
+ },
1313
+ {
1314
+ "epoch": 10.875,
1315
+ "grad_norm": 3.588341712656984e-07,
1316
+ "learning_rate": 1.9792013888888892e-05,
1317
+ "loss": 0.0429,
1318
+ "step": 87000
1319
+ },
1320
+ {
1321
+ "epoch": 10.9375,
1322
+ "grad_norm": 1.5524047114467976e-07,
1323
+ "learning_rate": 1.961840277777778e-05,
1324
+ "loss": 0.0188,
1325
+ "step": 87500
1326
+ },
1327
+ {
1328
+ "epoch": 11.0,
1329
+ "grad_norm": 2.524126614389388e-07,
1330
+ "learning_rate": 1.944479166666667e-05,
1331
+ "loss": 0.0217,
1332
+ "step": 88000
1333
+ },
1334
+ {
1335
+ "epoch": 11.0,
1336
+ "eval_loss": 0.39052143692970276,
1337
+ "eval_pearson": 0.936161178019818,
1338
+ "eval_runtime": 52.432,
1339
+ "eval_samples_per_second": 38.145,
1340
+ "eval_steps_per_second": 19.072,
1341
+ "step": 88000
1342
+ }
1343
+ ],
1344
+ "logging_steps": 500,
1345
+ "max_steps": 144000,
1346
+ "num_input_tokens_seen": 0,
1347
+ "num_train_epochs": 18,
1348
+ "save_steps": 500,
1349
+ "stateful_callbacks": {
1350
+ "TrainerControl": {
1351
+ "args": {
1352
+ "should_epoch_stop": false,
1353
+ "should_evaluate": false,
1354
+ "should_log": false,
1355
+ "should_save": true,
1356
+ "should_training_stop": false
1357
+ },
1358
+ "attributes": {}
1359
+ }
1360
+ },
1361
+ "total_flos": 8.104679389856563e+16,
1362
+ "train_batch_size": 2,
1363
+ "trial_name": null,
1364
+ "trial_params": null
1365
+ }
checkpoints_ia3_llama_class/checkpoint-88000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54e6c46c9dda9757cc094892dfdf420dce55879ca8959ffad52b273b74ea2b4a
3
+ size 5368