Hugging Face's logo

ugaoo
/
xp165

Safetensors
nemotron-nas
custom_code
4-bit precision
bitsandbytes
Model card Files
xet
Community
ugaoo commited on
Commit
a946c49
·
verified ·
1 Parent(s): 5dee541

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +6 -0
  2. adapter_config.json +42 -0
  3. checkpoint-109/README.md +202 -0
  4. checkpoint-109/adapter_config.json +42 -0
  5. checkpoint-109/adapter_model.safetensors +3 -0
  6. checkpoint-109/global_step109/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
  7. checkpoint-109/global_step109/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
  8. checkpoint-109/global_step109/mp_rank_00_model_states.pt +3 -0
  9. checkpoint-109/latest +1 -0
  10. checkpoint-109/rng_state_0.pth +3 -0
  11. checkpoint-109/rng_state_1.pth +3 -0
  12. checkpoint-109/scheduler.pt +3 -0
  13. checkpoint-109/special_tokens_map.json +23 -0
  14. checkpoint-109/tokenizer.json +3 -0
  15. checkpoint-109/tokenizer_config.json +2064 -0
  16. checkpoint-109/trainer_state.json +796 -0
  17. checkpoint-109/training_args.bin +3 -0
  18. checkpoint-109/zero_to_fp32.py +604 -0
  19. checkpoint-218/README.md +202 -0
  20. checkpoint-218/adapter_config.json +42 -0
  21. checkpoint-218/adapter_model.safetensors +3 -0
  22. checkpoint-218/global_step217/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
  23. checkpoint-218/global_step217/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
  24. checkpoint-218/global_step217/mp_rank_00_model_states.pt +3 -0
  25. checkpoint-218/latest +1 -0
  26. checkpoint-218/rng_state_0.pth +3 -0
  27. checkpoint-218/rng_state_1.pth +3 -0
  28. checkpoint-218/scheduler.pt +3 -0
  29. checkpoint-218/special_tokens_map.json +23 -0
  30. checkpoint-218/tokenizer.json +3 -0
  31. checkpoint-218/tokenizer_config.json +2064 -0
  32. checkpoint-218/trainer_state.json +1559 -0
  33. checkpoint-218/training_args.bin +3 -0
  34. checkpoint-218/zero_to_fp32.py +604 -0
  35. checkpoint-327/README.md +202 -0
  36. checkpoint-327/adapter_config.json +42 -0
  37. checkpoint-327/adapter_model.safetensors +3 -0
  38. checkpoint-327/global_step325/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
  39. checkpoint-327/global_step325/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
  40. checkpoint-327/global_step325/mp_rank_00_model_states.pt +3 -0
  41. checkpoint-327/latest +1 -0
  42. checkpoint-327/rng_state_0.pth +3 -0
  43. checkpoint-327/rng_state_1.pth +3 -0
  44. checkpoint-327/scheduler.pt +3 -0
  45. checkpoint-327/special_tokens_map.json +23 -0
  46. checkpoint-327/tokenizer.json +3 -0
  47. checkpoint-327/tokenizer_config.json +2064 -0
  48. checkpoint-327/trainer_state.json +2322 -0
  49. checkpoint-327/training_args.bin +3 -0
  50. checkpoint-327/zero_to_fp32.py +604 -0
.gitattributes CHANGED
@@ -33,3 +33,9 @@ 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
+ checkpoint-109/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint-218/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ checkpoint-327/tokenizer.json filter=lfs diff=lfs merge=lfs -text
39
+ checkpoint-436/tokenizer.json filter=lfs diff=lfs merge=lfs -text
40
+ checkpoint-545/tokenizer.json filter=lfs diff=lfs merge=lfs -text
41
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
adapter_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "nvidia/Llama-3_3-Nemotron-Super-49B-v1",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": null,
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": 512,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": [
22
+ "embed_tokens",
23
+ "lm_head"
24
+ ],
25
+ "peft_type": "LORA",
26
+ "r": 256,
27
+ "rank_pattern": {},
28
+ "revision": null,
29
+ "target_modules": [
30
+ "o_proj",
31
+ "gate_proj",
32
+ "q_proj",
33
+ "k_proj",
34
+ "v_proj",
35
+ "up_proj",
36
+ "down_proj"
37
+ ],
38
+ "task_type": "CAUSAL_LM",
39
+ "trainable_token_indices": null,
40
+ "use_dora": false,
41
+ "use_rslora": false
42
+ }
checkpoint-109/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: nvidia/Llama-3_3-Nemotron-Super-49B-v1
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 0.15.0
checkpoint-109/adapter_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "nvidia/Llama-3_3-Nemotron-Super-49B-v1",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": null,
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": 512,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": [
22
+ "embed_tokens",
23
+ "lm_head"
24
+ ],
25
+ "peft_type": "LORA",
26
+ "r": 256,
27
+ "rank_pattern": {},
28
+ "revision": null,
29
+ "target_modules": [
30
+ "o_proj",
31
+ "gate_proj",
32
+ "q_proj",
33
+ "k_proj",
34
+ "v_proj",
35
+ "up_proj",
36
+ "down_proj"
37
+ ],
38
+ "task_type": "CAUSAL_LM",
39
+ "trainable_token_indices": null,
40
+ "use_dora": false,
41
+ "use_rslora": false
42
+ }
checkpoint-109/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a7f32affafdc09c369bba68357ca31956e8086ce7701e04e04ea6756072bf79
3
+ size 9016826528
checkpoint-109/global_step109/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:279ec51cd173960a46dd5270a1aa392dc73ae653e4967424eea6f330d95891a6
3
+ size 27050164444
checkpoint-109/global_step109/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad9840509fc381eea5d1004bd82f0efc0f7640e851b0b457bb116718ad3bc4ba
3
+ size 27050169884
checkpoint-109/global_step109/mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:163f84be3c633a9af23549b2f2ce50102524def58bf0d451800acd13c59b6cd6
3
+ size 9776788601
checkpoint-109/latest ADDED
@@ -0,0 +1 @@
 
 
1
+ global_step109
checkpoint-109/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43d83a11dba599c305208d485dc434bc95abca3c8b9c33dc1de687c354f3ef0d
3
+ size 14512
checkpoint-109/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5b35da1af2f35f904ecb92a644c838c9e9006e646cc823d7d615ed5cc45d4e0
3
+ size 14512
checkpoint-109/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d452b3b665e980d65823f2d1807a5ce26dba0d3a7ea072f6413bae99f16bc430
3
+ size 1064
checkpoint-109/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": {
17
+ "content": "<|end_of_text|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
checkpoint-109/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
checkpoint-109/tokenizer_config.json ADDED
@@ -0,0 +1,2064 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{{- bos_token }}{%- if messages[0]['role'] == 'system' %}{%- set system_message = messages[0]['content']|trim %}{%- set messages = messages[1:] %}{%- else %}{%- set system_message = \"\" %}{%- endif %}{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}{{- system_message }}{{- \"<|eot_id|>\" }}{%- for message in messages %}{%- if message['role'] == 'assistant' and '</think>' in message['content'] %}{%- set content = message['content'].split('</think>')[-1].lstrip() %}{%- else %}{%- set content = message['content'] %}{%- endif %}{{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n' + content | trim + '<|eot_id|>' }}{%- endfor %}{%- if add_generation_prompt %}{{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}{%- endif %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "extra_special_tokens": {},
2057
+ "model_input_names": [
2058
+ "input_ids",
2059
+ "attention_mask"
2060
+ ],
2061
+ "model_max_length": 131072,
2062
+ "pad_token": "<|end_of_text|>",
2063
+ "tokenizer_class": "PreTrainedTokenizer"
2064
+ }
checkpoint-109/trainer_state.json ADDED
@@ -0,0 +1,796 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9969512195121951,
5
+ "eval_steps": 500,
6
+ "global_step": 109,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.009146341463414634,
13
+ "grad_norm": 40.05127716064453,
14
+ "learning_rate": 5.0000000000000004e-08,
15
+ "loss": 5.1282,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.018292682926829267,
20
+ "grad_norm": 39.01039505004883,
21
+ "learning_rate": 1.0000000000000001e-07,
22
+ "loss": 5.0586,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.027439024390243903,
27
+ "grad_norm": 40.20766067504883,
28
+ "learning_rate": 1.5000000000000002e-07,
29
+ "loss": 5.0311,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.036585365853658534,
34
+ "grad_norm": 38.70350646972656,
35
+ "learning_rate": 2.0000000000000002e-07,
36
+ "loss": 5.1598,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.04573170731707317,
41
+ "grad_norm": 39.230979919433594,
42
+ "learning_rate": 2.5000000000000004e-07,
43
+ "loss": 5.0812,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.054878048780487805,
48
+ "grad_norm": 39.45293045043945,
49
+ "learning_rate": 3.0000000000000004e-07,
50
+ "loss": 5.0841,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.06402439024390244,
55
+ "grad_norm": 38.92170333862305,
56
+ "learning_rate": 3.5000000000000004e-07,
57
+ "loss": 5.022,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.07317073170731707,
62
+ "grad_norm": 38.932369232177734,
63
+ "learning_rate": 4.0000000000000003e-07,
64
+ "loss": 5.0876,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.08231707317073171,
69
+ "grad_norm": 39.60245132446289,
70
+ "learning_rate": 4.5000000000000003e-07,
71
+ "loss": 5.0798,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.09146341463414634,
76
+ "grad_norm": 39.53607177734375,
77
+ "learning_rate": 5.000000000000001e-07,
78
+ "loss": 5.0105,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.10060975609756098,
83
+ "grad_norm": 39.50700378417969,
84
+ "learning_rate": 5.5e-07,
85
+ "loss": 4.9951,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.10975609756097561,
90
+ "grad_norm": 39.52376174926758,
91
+ "learning_rate": 6.000000000000001e-07,
92
+ "loss": 4.9163,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.11890243902439024,
97
+ "grad_norm": 39.15214157104492,
98
+ "learning_rate": 6.5e-07,
99
+ "loss": 4.9634,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.12804878048780488,
104
+ "grad_norm": 37.795066833496094,
105
+ "learning_rate": 7.000000000000001e-07,
106
+ "loss": 4.819,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.13719512195121952,
111
+ "grad_norm": 38.23014450073242,
112
+ "learning_rate": 7.5e-07,
113
+ "loss": 4.8756,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.14634146341463414,
118
+ "grad_norm": 38.57551574707031,
119
+ "learning_rate": 8.000000000000001e-07,
120
+ "loss": 4.81,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.15548780487804878,
125
+ "grad_norm": 36.06121063232422,
126
+ "learning_rate": 8.500000000000001e-07,
127
+ "loss": 4.7901,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.16463414634146342,
132
+ "grad_norm": 34.38008117675781,
133
+ "learning_rate": 9.000000000000001e-07,
134
+ "loss": 4.5775,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.17378048780487804,
139
+ "grad_norm": 32.60890579223633,
140
+ "learning_rate": 9.500000000000001e-07,
141
+ "loss": 4.3737,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.18292682926829268,
146
+ "grad_norm": 31.983110427856445,
147
+ "learning_rate": 1.0000000000000002e-06,
148
+ "loss": 4.3773,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.19207317073170732,
153
+ "grad_norm": 27.69571876525879,
154
+ "learning_rate": 1.0500000000000001e-06,
155
+ "loss": 4.1276,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.20121951219512196,
160
+ "grad_norm": 26.542314529418945,
161
+ "learning_rate": 1.1e-06,
162
+ "loss": 4.0641,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.21036585365853658,
167
+ "grad_norm": 23.26603126525879,
168
+ "learning_rate": 1.1500000000000002e-06,
169
+ "loss": 4.0197,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.21951219512195122,
174
+ "grad_norm": 21.04385757446289,
175
+ "learning_rate": 1.2000000000000002e-06,
176
+ "loss": 4.0179,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.22865853658536586,
181
+ "grad_norm": 19.790103912353516,
182
+ "learning_rate": 1.25e-06,
183
+ "loss": 3.8334,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.23780487804878048,
188
+ "grad_norm": 18.2396183013916,
189
+ "learning_rate": 1.3e-06,
190
+ "loss": 3.7027,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.24695121951219512,
195
+ "grad_norm": 18.725860595703125,
196
+ "learning_rate": 1.3500000000000002e-06,
197
+ "loss": 3.7268,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.25609756097560976,
202
+ "grad_norm": 18.91561508178711,
203
+ "learning_rate": 1.4000000000000001e-06,
204
+ "loss": 3.52,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.2652439024390244,
209
+ "grad_norm": 18.196651458740234,
210
+ "learning_rate": 1.45e-06,
211
+ "loss": 3.4765,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.27439024390243905,
216
+ "grad_norm": 17.778606414794922,
217
+ "learning_rate": 1.5e-06,
218
+ "loss": 3.3573,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.28353658536585363,
223
+ "grad_norm": 16.23012924194336,
224
+ "learning_rate": 1.5500000000000002e-06,
225
+ "loss": 3.2783,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.2926829268292683,
230
+ "grad_norm": 15.836565017700195,
231
+ "learning_rate": 1.6000000000000001e-06,
232
+ "loss": 3.2319,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.3018292682926829,
237
+ "grad_norm": 11.919289588928223,
238
+ "learning_rate": 1.6500000000000003e-06,
239
+ "loss": 3.1345,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.31097560975609756,
244
+ "grad_norm": 11.086843490600586,
245
+ "learning_rate": 1.7000000000000002e-06,
246
+ "loss": 3.1153,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.3201219512195122,
251
+ "grad_norm": 7.563486576080322,
252
+ "learning_rate": 1.75e-06,
253
+ "loss": 2.9784,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.32926829268292684,
258
+ "grad_norm": 7.60545539855957,
259
+ "learning_rate": 1.8000000000000001e-06,
260
+ "loss": 2.8568,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.3384146341463415,
265
+ "grad_norm": 7.071218013763428,
266
+ "learning_rate": 1.85e-06,
267
+ "loss": 2.8879,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.3475609756097561,
272
+ "grad_norm": 8.200672149658203,
273
+ "learning_rate": 1.9000000000000002e-06,
274
+ "loss": 2.7437,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.3567073170731707,
279
+ "grad_norm": 12.079374313354492,
280
+ "learning_rate": 1.9500000000000004e-06,
281
+ "loss": 2.7589,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.36585365853658536,
286
+ "grad_norm": 12.21938705444336,
287
+ "learning_rate": 2.0000000000000003e-06,
288
+ "loss": 2.7098,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.375,
293
+ "grad_norm": 10.224228858947754,
294
+ "learning_rate": 2.05e-06,
295
+ "loss": 2.6803,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.38414634146341464,
300
+ "grad_norm": 10.054616928100586,
301
+ "learning_rate": 2.1000000000000002e-06,
302
+ "loss": 2.4658,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.3932926829268293,
307
+ "grad_norm": 8.074049949645996,
308
+ "learning_rate": 2.15e-06,
309
+ "loss": 2.6341,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.4024390243902439,
314
+ "grad_norm": 5.721987724304199,
315
+ "learning_rate": 2.2e-06,
316
+ "loss": 2.3848,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.4115853658536585,
321
+ "grad_norm": 4.646566390991211,
322
+ "learning_rate": 2.25e-06,
323
+ "loss": 2.4323,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.42073170731707316,
328
+ "grad_norm": 4.591104984283447,
329
+ "learning_rate": 2.3000000000000004e-06,
330
+ "loss": 2.4022,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.4298780487804878,
335
+ "grad_norm": 4.822715759277344,
336
+ "learning_rate": 2.35e-06,
337
+ "loss": 2.2768,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.43902439024390244,
342
+ "grad_norm": 5.176568984985352,
343
+ "learning_rate": 2.4000000000000003e-06,
344
+ "loss": 2.281,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.4481707317073171,
349
+ "grad_norm": 4.731242656707764,
350
+ "learning_rate": 2.4500000000000003e-06,
351
+ "loss": 2.235,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.4573170731707317,
356
+ "grad_norm": 4.6343865394592285,
357
+ "learning_rate": 2.5e-06,
358
+ "loss": 2.1465,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.46646341463414637,
363
+ "grad_norm": 4.669382095336914,
364
+ "learning_rate": 2.55e-06,
365
+ "loss": 2.0969,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.47560975609756095,
370
+ "grad_norm": 4.207769870758057,
371
+ "learning_rate": 2.6e-06,
372
+ "loss": 2.0308,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.4847560975609756,
377
+ "grad_norm": 5.222470760345459,
378
+ "learning_rate": 2.6500000000000005e-06,
379
+ "loss": 1.9445,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.49390243902439024,
384
+ "grad_norm": 5.10925817489624,
385
+ "learning_rate": 2.7000000000000004e-06,
386
+ "loss": 1.7763,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.5030487804878049,
391
+ "grad_norm": 4.8151044845581055,
392
+ "learning_rate": 2.7500000000000004e-06,
393
+ "loss": 1.7661,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.5121951219512195,
398
+ "grad_norm": 6.155700206756592,
399
+ "learning_rate": 2.8000000000000003e-06,
400
+ "loss": 1.6665,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.5213414634146342,
405
+ "grad_norm": 4.719021320343018,
406
+ "learning_rate": 2.85e-06,
407
+ "loss": 1.5532,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.5304878048780488,
412
+ "grad_norm": 4.591799259185791,
413
+ "learning_rate": 2.9e-06,
414
+ "loss": 1.5244,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.5396341463414634,
419
+ "grad_norm": 5.483795642852783,
420
+ "learning_rate": 2.95e-06,
421
+ "loss": 1.3816,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.5487804878048781,
426
+ "grad_norm": 4.32553768157959,
427
+ "learning_rate": 3e-06,
428
+ "loss": 1.4268,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.5579268292682927,
433
+ "grad_norm": 8.296231269836426,
434
+ "learning_rate": 3.05e-06,
435
+ "loss": 1.2887,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.5670731707317073,
440
+ "grad_norm": 5.07594108581543,
441
+ "learning_rate": 3.1000000000000004e-06,
442
+ "loss": 1.228,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.5762195121951219,
447
+ "grad_norm": 8.427435874938965,
448
+ "learning_rate": 3.1500000000000003e-06,
449
+ "loss": 1.1724,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.5853658536585366,
454
+ "grad_norm": 22.45092010498047,
455
+ "learning_rate": 3.2000000000000003e-06,
456
+ "loss": 1.0871,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.5945121951219512,
461
+ "grad_norm": 20.67412567138672,
462
+ "learning_rate": 3.2500000000000002e-06,
463
+ "loss": 1.0108,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.6036585365853658,
468
+ "grad_norm": 4.921634674072266,
469
+ "learning_rate": 3.3000000000000006e-06,
470
+ "loss": 0.9775,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.6128048780487805,
475
+ "grad_norm": 4.477286338806152,
476
+ "learning_rate": 3.3500000000000005e-06,
477
+ "loss": 0.9554,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.6219512195121951,
482
+ "grad_norm": 8.190194129943848,
483
+ "learning_rate": 3.4000000000000005e-06,
484
+ "loss": 0.8583,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.6310975609756098,
489
+ "grad_norm": 29.21201515197754,
490
+ "learning_rate": 3.45e-06,
491
+ "loss": 0.8499,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.6402439024390244,
496
+ "grad_norm": 33.81047439575195,
497
+ "learning_rate": 3.5e-06,
498
+ "loss": 0.858,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.649390243902439,
503
+ "grad_norm": 3.5125606060028076,
504
+ "learning_rate": 3.5500000000000003e-06,
505
+ "loss": 0.7227,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.6585365853658537,
510
+ "grad_norm": 18.493423461914062,
511
+ "learning_rate": 3.6000000000000003e-06,
512
+ "loss": 0.7447,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.6676829268292683,
517
+ "grad_norm": 24.923927307128906,
518
+ "learning_rate": 3.65e-06,
519
+ "loss": 0.8423,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.676829268292683,
524
+ "grad_norm": 9.870631217956543,
525
+ "learning_rate": 3.7e-06,
526
+ "loss": 0.6934,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.6859756097560976,
531
+ "grad_norm": 20.598569869995117,
532
+ "learning_rate": 3.7500000000000005e-06,
533
+ "loss": 0.7005,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.6951219512195121,
538
+ "grad_norm": 30.662466049194336,
539
+ "learning_rate": 3.8000000000000005e-06,
540
+ "loss": 0.6226,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.7042682926829268,
545
+ "grad_norm": 28.930774688720703,
546
+ "learning_rate": 3.85e-06,
547
+ "loss": 0.6357,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.7134146341463414,
552
+ "grad_norm": 7.140467166900635,
553
+ "learning_rate": 3.900000000000001e-06,
554
+ "loss": 0.6129,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.7225609756097561,
559
+ "grad_norm": 6.322911739349365,
560
+ "learning_rate": 3.95e-06,
561
+ "loss": 0.6086,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.7317073170731707,
566
+ "grad_norm": 5.404141426086426,
567
+ "learning_rate": 4.000000000000001e-06,
568
+ "loss": 0.5986,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.7408536585365854,
573
+ "grad_norm": 24.445228576660156,
574
+ "learning_rate": 4.05e-06,
575
+ "loss": 0.5932,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.75,
580
+ "grad_norm": 14.275381088256836,
581
+ "learning_rate": 4.1e-06,
582
+ "loss": 0.5286,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.7591463414634146,
587
+ "grad_norm": 9.77132511138916,
588
+ "learning_rate": 4.15e-06,
589
+ "loss": 0.4814,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.7682926829268293,
594
+ "grad_norm": 11.043930053710938,
595
+ "learning_rate": 4.2000000000000004e-06,
596
+ "loss": 0.4953,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.7774390243902439,
601
+ "grad_norm": 3.1333775520324707,
602
+ "learning_rate": 4.25e-06,
603
+ "loss": 0.4794,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.7865853658536586,
608
+ "grad_norm": 9.50448989868164,
609
+ "learning_rate": 4.3e-06,
610
+ "loss": 0.4451,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.7957317073170732,
615
+ "grad_norm": 5.867074489593506,
616
+ "learning_rate": 4.350000000000001e-06,
617
+ "loss": 0.4224,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 0.8048780487804879,
622
+ "grad_norm": 12.556106567382812,
623
+ "learning_rate": 4.4e-06,
624
+ "loss": 0.4224,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 0.8140243902439024,
629
+ "grad_norm": 7.916622638702393,
630
+ "learning_rate": 4.450000000000001e-06,
631
+ "loss": 0.4091,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 0.823170731707317,
636
+ "grad_norm": 2.970932722091675,
637
+ "learning_rate": 4.5e-06,
638
+ "loss": 0.4181,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 0.8323170731707317,
643
+ "grad_norm": 17.468870162963867,
644
+ "learning_rate": 4.5500000000000005e-06,
645
+ "loss": 0.4031,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 0.8414634146341463,
650
+ "grad_norm": 15.861083984375,
651
+ "learning_rate": 4.600000000000001e-06,
652
+ "loss": 0.3604,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 0.850609756097561,
657
+ "grad_norm": 6.715958118438721,
658
+ "learning_rate": 4.65e-06,
659
+ "loss": 0.3489,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 0.8597560975609756,
664
+ "grad_norm": 5.439844608306885,
665
+ "learning_rate": 4.7e-06,
666
+ "loss": 0.3339,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 0.8689024390243902,
671
+ "grad_norm": 4.650434494018555,
672
+ "learning_rate": 4.75e-06,
673
+ "loss": 0.3189,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 0.8780487804878049,
678
+ "grad_norm": 15.319528579711914,
679
+ "learning_rate": 4.800000000000001e-06,
680
+ "loss": 0.3347,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 0.8871951219512195,
685
+ "grad_norm": 5.151925563812256,
686
+ "learning_rate": 4.85e-06,
687
+ "loss": 0.3043,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 0.8963414634146342,
692
+ "grad_norm": 6.351178169250488,
693
+ "learning_rate": 4.9000000000000005e-06,
694
+ "loss": 0.2939,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 0.9054878048780488,
699
+ "grad_norm": 3.942911148071289,
700
+ "learning_rate": 4.95e-06,
701
+ "loss": 0.2887,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 0.9146341463414634,
706
+ "grad_norm": 3.0885493755340576,
707
+ "learning_rate": 5e-06,
708
+ "loss": 0.2992,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 0.9237804878048781,
713
+ "grad_norm": 7.023274898529053,
714
+ "learning_rate": 4.999959803423605e-06,
715
+ "loss": 0.2607,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 0.9329268292682927,
720
+ "grad_norm": 8.774216651916504,
721
+ "learning_rate": 4.9998392149870315e-06,
722
+ "loss": 0.2674,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 0.9420731707317073,
727
+ "grad_norm": 3.5439791679382324,
728
+ "learning_rate": 4.999638238568072e-06,
729
+ "loss": 0.2602,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 0.9512195121951219,
734
+ "grad_norm": 7.669381618499756,
735
+ "learning_rate": 4.999356880629579e-06,
736
+ "loss": 0.2718,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 0.9603658536585366,
741
+ "grad_norm": 6.9407854080200195,
742
+ "learning_rate": 4.998995150219252e-06,
743
+ "loss": 0.2494,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 0.9695121951219512,
748
+ "grad_norm": 12.144411087036133,
749
+ "learning_rate": 4.998553058969352e-06,
750
+ "loss": 0.2297,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 0.9786585365853658,
755
+ "grad_norm": 6.956138610839844,
756
+ "learning_rate": 4.998030621096322e-06,
757
+ "loss": 0.2386,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 0.9878048780487805,
762
+ "grad_norm": 8.304037094116211,
763
+ "learning_rate": 4.997427853400333e-06,
764
+ "loss": 0.23,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 0.9969512195121951,
769
+ "grad_norm": 7.031365394592285,
770
+ "learning_rate": 4.996744775264743e-06,
771
+ "loss": 0.2346,
772
+ "step": 109
773
+ }
774
+ ],
775
+ "logging_steps": 1,
776
+ "max_steps": 654,
777
+ "num_input_tokens_seen": 0,
778
+ "num_train_epochs": 6,
779
+ "save_steps": 109,
780
+ "stateful_callbacks": {
781
+ "TrainerControl": {
782
+ "args": {
783
+ "should_epoch_stop": false,
784
+ "should_evaluate": false,
785
+ "should_log": false,
786
+ "should_save": true,
787
+ "should_training_stop": false
788
+ },
789
+ "attributes": {}
790
+ }
791
+ },
792
+ "total_flos": 3.308236123527971e+18,
793
+ "train_batch_size": 4,
794
+ "trial_name": null,
795
+ "trial_params": null
796
+ }
checkpoint-109/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14990b8399bb8d39b746405b094f7eea1041d93488de8433b2d415de16ff957a
3
+ size 7928
checkpoint-109/zero_to_fp32.py ADDED
@@ -0,0 +1,604 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #!/usr/bin/env python
2
+
3
+ # Copyright (c) Microsoft Corporation.
4
+ # SPDX-License-Identifier: Apache-2.0
5
+
6
+ # DeepSpeed Team
7
+
8
+ # This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
9
+ # copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
10
+ # the future. Once extracted, the weights don't require DeepSpeed and can be used in any
11
+ # application.
12
+ #
13
+ # example: python zero_to_fp32.py . pytorch_model.bin
14
+
15
+ import argparse
16
+ import torch
17
+ import glob
18
+ import math
19
+ import os
20
+ import re
21
+ from collections import OrderedDict
22
+ from dataclasses import dataclass
23
+
24
+ # while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
25
+ # DeepSpeed data structures it has to be available in the current python environment.
26
+ from deepspeed.utils import logger
27
+ from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
28
+ FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
29
+ FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
30
+
31
+
32
+ @dataclass
33
+ class zero_model_state:
34
+ buffers: dict()
35
+ param_shapes: dict()
36
+ shared_params: list
37
+ ds_version: int
38
+ frozen_param_shapes: dict()
39
+ frozen_param_fragments: dict()
40
+
41
+
42
+ debug = 0
43
+
44
+ # load to cpu
45
+ device = torch.device('cpu')
46
+
47
+
48
+ def atoi(text):
49
+ return int(text) if text.isdigit() else text
50
+
51
+
52
+ def natural_keys(text):
53
+ '''
54
+ alist.sort(key=natural_keys) sorts in human order
55
+ http://nedbatchelder.com/blog/200712/human_sorting.html
56
+ (See Toothy's implementation in the comments)
57
+ '''
58
+ return [atoi(c) for c in re.split(r'(\d+)', text)]
59
+
60
+
61
+ def get_model_state_file(checkpoint_dir, zero_stage):
62
+ if not os.path.isdir(checkpoint_dir):
63
+ raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
64
+
65
+ # there should be only one file
66
+ if zero_stage <= 2:
67
+ file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
68
+ elif zero_stage == 3:
69
+ file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
70
+
71
+ if not os.path.exists(file):
72
+ raise FileNotFoundError(f"can't find model states file at '{file}'")
73
+
74
+ return file
75
+
76
+
77
+ def get_checkpoint_files(checkpoint_dir, glob_pattern):
78
+ # XXX: need to test that this simple glob rule works for multi-node setup too
79
+ ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
80
+
81
+ if len(ckpt_files) == 0:
82
+ raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
83
+
84
+ return ckpt_files
85
+
86
+
87
+ def get_optim_files(checkpoint_dir):
88
+ return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
89
+
90
+
91
+ def get_model_state_files(checkpoint_dir):
92
+ return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
93
+
94
+
95
+ def parse_model_states(files):
96
+ zero_model_states = []
97
+ for file in files:
98
+ state_dict = torch.load(file, map_location=device)
99
+
100
+ if BUFFER_NAMES not in state_dict:
101
+ raise ValueError(f"{file} is not a model state checkpoint")
102
+ buffer_names = state_dict[BUFFER_NAMES]
103
+ if debug:
104
+ print("Found buffers:", buffer_names)
105
+
106
+ # recover just the buffers while restoring them to fp32 if they were saved in fp16
107
+ buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
108
+ param_shapes = state_dict[PARAM_SHAPES]
109
+
110
+ # collect parameters that are included in param_shapes
111
+ param_names = []
112
+ for s in param_shapes:
113
+ for name in s.keys():
114
+ param_names.append(name)
115
+
116
+ # update with frozen parameters
117
+ frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
118
+ if frozen_param_shapes is not None:
119
+ if debug:
120
+ print(f"Found frozen_param_shapes: {frozen_param_shapes}")
121
+ param_names += list(frozen_param_shapes.keys())
122
+
123
+ # handle shared params
124
+ shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
125
+
126
+ ds_version = state_dict.get(DS_VERSION, None)
127
+
128
+ frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
129
+
130
+ z_model_state = zero_model_state(buffers=buffers,
131
+ param_shapes=param_shapes,
132
+ shared_params=shared_params,
133
+ ds_version=ds_version,
134
+ frozen_param_shapes=frozen_param_shapes,
135
+ frozen_param_fragments=frozen_param_fragments)
136
+ zero_model_states.append(z_model_state)
137
+
138
+ return zero_model_states
139
+
140
+
141
+ def parse_optim_states(files, ds_checkpoint_dir):
142
+
143
+ total_files = len(files)
144
+ state_dicts = []
145
+ for f in files:
146
+ state_dict = torch.load(f, map_location=device)
147
+ # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
148
+ # and also handle the case where it was already removed by another helper script
149
+ state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
150
+ state_dicts.append(state_dict)
151
+
152
+ if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
153
+ raise ValueError(f"{files[0]} is not a zero checkpoint")
154
+ zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
155
+ world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
156
+
157
+ # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
158
+ # parameters can be different from data parallelism for non-expert parameters. So we can just
159
+ # use the max of the partition_count to get the dp world_size.
160
+
161
+ if type(world_size) is list:
162
+ world_size = max(world_size)
163
+
164
+ if world_size != total_files:
165
+ raise ValueError(
166
+ f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
167
+ "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
168
+ )
169
+
170
+ # the groups are named differently in each stage
171
+ if zero_stage <= 2:
172
+ fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
173
+ elif zero_stage == 3:
174
+ fp32_groups_key = FP32_FLAT_GROUPS
175
+ else:
176
+ raise ValueError(f"unknown zero stage {zero_stage}")
177
+
178
+ if zero_stage <= 2:
179
+ fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
180
+ elif zero_stage == 3:
181
+ # if there is more than one param group, there will be multiple flattened tensors - one
182
+ # flattened tensor per group - for simplicity merge them into a single tensor
183
+ #
184
+ # XXX: could make the script more memory efficient for when there are multiple groups - it
185
+ # will require matching the sub-lists of param_shapes for each param group flattened tensor
186
+
187
+ fp32_flat_groups = [
188
+ torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
189
+ ]
190
+
191
+ return zero_stage, world_size, fp32_flat_groups
192
+
193
+
194
+ def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
195
+ """
196
+ Returns fp32 state_dict reconstructed from ds checkpoint
197
+
198
+ Args:
199
+ - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
200
+
201
+ """
202
+ print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
203
+
204
+ optim_files = get_optim_files(ds_checkpoint_dir)
205
+ zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
206
+ print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
207
+
208
+ model_files = get_model_state_files(ds_checkpoint_dir)
209
+
210
+ zero_model_states = parse_model_states(model_files)
211
+ print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
212
+
213
+ if zero_stage <= 2:
214
+ return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
215
+ exclude_frozen_parameters)
216
+ elif zero_stage == 3:
217
+ return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
218
+ exclude_frozen_parameters)
219
+
220
+
221
+ def _zero2_merge_frozen_params(state_dict, zero_model_states):
222
+ if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
223
+ return
224
+
225
+ frozen_param_shapes = zero_model_states[0].frozen_param_shapes
226
+ frozen_param_fragments = zero_model_states[0].frozen_param_fragments
227
+
228
+ if debug:
229
+ num_elem = sum(s.numel() for s in frozen_param_shapes.values())
230
+ print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
231
+
232
+ wanted_params = len(frozen_param_shapes)
233
+ wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
234
+ avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
235
+ print(f'Frozen params: Have {avail_numel} numels to process.')
236
+ print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
237
+
238
+ total_params = 0
239
+ total_numel = 0
240
+ for name, shape in frozen_param_shapes.items():
241
+ total_params += 1
242
+ unpartitioned_numel = shape.numel()
243
+ total_numel += unpartitioned_numel
244
+
245
+ state_dict[name] = frozen_param_fragments[name]
246
+
247
+ if debug:
248
+ print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
249
+
250
+ print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
251
+
252
+
253
+ def _has_callable(obj, fn):
254
+ attr = getattr(obj, fn, None)
255
+ return callable(attr)
256
+
257
+
258
+ def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
259
+ param_shapes = zero_model_states[0].param_shapes
260
+
261
+ # Reconstruction protocol:
262
+ #
263
+ # XXX: document this
264
+
265
+ if debug:
266
+ for i in range(world_size):
267
+ for j in range(len(fp32_flat_groups[0])):
268
+ print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
269
+
270
+ # XXX: memory usage doubles here (zero2)
271
+ num_param_groups = len(fp32_flat_groups[0])
272
+ merged_single_partition_of_fp32_groups = []
273
+ for i in range(num_param_groups):
274
+ merged_partitions = [sd[i] for sd in fp32_flat_groups]
275
+ full_single_fp32_vector = torch.cat(merged_partitions, 0)
276
+ merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
277
+ avail_numel = sum(
278
+ [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
279
+
280
+ if debug:
281
+ wanted_params = sum([len(shapes) for shapes in param_shapes])
282
+ wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
283
+ # not asserting if there is a mismatch due to possible padding
284
+ print(f"Have {avail_numel} numels to process.")
285
+ print(f"Need {wanted_numel} numels in {wanted_params} params.")
286
+
287
+ # params
288
+ # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
289
+ # out-of-core computing solution
290
+ total_numel = 0
291
+ total_params = 0
292
+ for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
293
+ offset = 0
294
+ avail_numel = full_single_fp32_vector.numel()
295
+ for name, shape in shapes.items():
296
+
297
+ unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
298
+ total_numel += unpartitioned_numel
299
+ total_params += 1
300
+
301
+ if debug:
302
+ print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
303
+ state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
304
+ offset += unpartitioned_numel
305
+
306
+ # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
307
+ # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
308
+ # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
309
+ # live optimizer object, so we are checking that the numbers are within the right range
310
+ align_to = 2 * world_size
311
+
312
+ def zero2_align(x):
313
+ return align_to * math.ceil(x / align_to)
314
+
315
+ if debug:
316
+ print(f"original offset={offset}, avail_numel={avail_numel}")
317
+
318
+ offset = zero2_align(offset)
319
+ avail_numel = zero2_align(avail_numel)
320
+
321
+ if debug:
322
+ print(f"aligned offset={offset}, avail_numel={avail_numel}")
323
+
324
+ # Sanity check
325
+ if offset != avail_numel:
326
+ raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
327
+
328
+ print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
329
+
330
+
331
+ def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
332
+ exclude_frozen_parameters):
333
+ state_dict = OrderedDict()
334
+
335
+ # buffers
336
+ buffers = zero_model_states[0].buffers
337
+ state_dict.update(buffers)
338
+ if debug:
339
+ print(f"added {len(buffers)} buffers")
340
+
341
+ if not exclude_frozen_parameters:
342
+ _zero2_merge_frozen_params(state_dict, zero_model_states)
343
+
344
+ _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
345
+
346
+ # recover shared parameters
347
+ for pair in zero_model_states[0].shared_params:
348
+ if pair[1] in state_dict:
349
+ state_dict[pair[0]] = state_dict[pair[1]]
350
+
351
+ return state_dict
352
+
353
+
354
+ def zero3_partitioned_param_info(unpartitioned_numel, world_size):
355
+ remainder = unpartitioned_numel % world_size
356
+ padding_numel = (world_size - remainder) if remainder else 0
357
+ partitioned_numel = math.ceil(unpartitioned_numel / world_size)
358
+ return partitioned_numel, padding_numel
359
+
360
+
361
+ def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
362
+ if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
363
+ return
364
+
365
+ if debug:
366
+ for i in range(world_size):
367
+ num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
368
+ print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
369
+
370
+ frozen_param_shapes = zero_model_states[0].frozen_param_shapes
371
+ wanted_params = len(frozen_param_shapes)
372
+ wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
373
+ avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
374
+ print(f'Frozen params: Have {avail_numel} numels to process.')
375
+ print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
376
+
377
+ total_params = 0
378
+ total_numel = 0
379
+ for name, shape in zero_model_states[0].frozen_param_shapes.items():
380
+ total_params += 1
381
+ unpartitioned_numel = shape.numel()
382
+ total_numel += unpartitioned_numel
383
+
384
+ param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
385
+ state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
386
+
387
+ partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
388
+
389
+ if debug:
390
+ print(
391
+ f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
392
+ )
393
+
394
+ print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
395
+
396
+
397
+ def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
398
+ param_shapes = zero_model_states[0].param_shapes
399
+ avail_numel = fp32_flat_groups[0].numel() * world_size
400
+ # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
401
+ # param, re-consolidating each param, while dealing with padding if any
402
+
403
+ # merge list of dicts, preserving order
404
+ param_shapes = {k: v for d in param_shapes for k, v in d.items()}
405
+
406
+ if debug:
407
+ for i in range(world_size):
408
+ print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
409
+
410
+ wanted_params = len(param_shapes)
411
+ wanted_numel = sum(shape.numel() for shape in param_shapes.values())
412
+ # not asserting if there is a mismatch due to possible padding
413
+ avail_numel = fp32_flat_groups[0].numel() * world_size
414
+ print(f"Trainable params: Have {avail_numel} numels to process.")
415
+ print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
416
+
417
+ # params
418
+ # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
419
+ # out-of-core computing solution
420
+ offset = 0
421
+ total_numel = 0
422
+ total_params = 0
423
+ for name, shape in param_shapes.items():
424
+
425
+ unpartitioned_numel = shape.numel()
426
+ total_numel += unpartitioned_numel
427
+ total_params += 1
428
+
429
+ partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
430
+
431
+ if debug:
432
+ print(
433
+ f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
434
+ )
435
+
436
+ # XXX: memory usage doubles here
437
+ state_dict[name] = torch.cat(
438
+ tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
439
+ 0).narrow(0, 0, unpartitioned_numel).view(shape)
440
+ offset += partitioned_numel
441
+
442
+ offset *= world_size
443
+
444
+ # Sanity check
445
+ if offset != avail_numel:
446
+ raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
447
+
448
+ print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
449
+
450
+
451
+ def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
452
+ exclude_frozen_parameters):
453
+ state_dict = OrderedDict()
454
+
455
+ # buffers
456
+ buffers = zero_model_states[0].buffers
457
+ state_dict.update(buffers)
458
+ if debug:
459
+ print(f"added {len(buffers)} buffers")
460
+
461
+ if not exclude_frozen_parameters:
462
+ _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
463
+
464
+ _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
465
+
466
+ # recover shared parameters
467
+ for pair in zero_model_states[0].shared_params:
468
+ if pair[1] in state_dict:
469
+ state_dict[pair[0]] = state_dict[pair[1]]
470
+
471
+ return state_dict
472
+
473
+
474
+ def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
475
+ """
476
+ Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
477
+ ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
478
+ via a model hub.
479
+
480
+ Args:
481
+ - ``checkpoint_dir``: path to the desired checkpoint folder
482
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
483
+ - ``exclude_frozen_parameters``: exclude frozen parameters
484
+
485
+ Returns:
486
+ - pytorch ``state_dict``
487
+
488
+ Note: this approach may not work if your application doesn't have sufficient free CPU memory and
489
+ you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
490
+ the checkpoint.
491
+
492
+ A typical usage might be ::
493
+
494
+ from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
495
+ # do the training and checkpoint saving
496
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
497
+ model = model.cpu() # move to cpu
498
+ model.load_state_dict(state_dict)
499
+ # submit to model hub or save the model to share with others
500
+
501
+ In this example the ``model`` will no longer be usable in the deepspeed context of the same
502
+ application. i.e. you will need to re-initialize the deepspeed engine, since
503
+ ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
504
+
505
+ If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
506
+
507
+ """
508
+ if tag is None:
509
+ latest_path = os.path.join(checkpoint_dir, 'latest')
510
+ if os.path.isfile(latest_path):
511
+ with open(latest_path, 'r') as fd:
512
+ tag = fd.read().strip()
513
+ else:
514
+ raise ValueError(f"Unable to find 'latest' file at {latest_path}")
515
+
516
+ ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
517
+
518
+ if not os.path.isdir(ds_checkpoint_dir):
519
+ raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
520
+
521
+ return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
522
+
523
+
524
+ def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None, exclude_frozen_parameters=False):
525
+ """
526
+ Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
527
+ loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
528
+
529
+ Args:
530
+ - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
531
+ - ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
532
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
533
+ - ``exclude_frozen_parameters``: exclude frozen parameters
534
+ """
535
+
536
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
537
+ print(f"Saving fp32 state dict to {output_file}")
538
+ torch.save(state_dict, output_file)
539
+
540
+
541
+ def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
542
+ """
543
+ 1. Put the provided model to cpu
544
+ 2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
545
+ 3. Load it into the provided model
546
+
547
+ Args:
548
+ - ``model``: the model object to update
549
+ - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
550
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
551
+
552
+ Returns:
553
+ - ``model`: modified model
554
+
555
+ Make sure you have plenty of CPU memory available before you call this function. If you don't
556
+ have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
557
+ conveniently placed for you in the checkpoint folder.
558
+
559
+ A typical usage might be ::
560
+
561
+ from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
562
+ model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
563
+ # submit to model hub or save the model to share with others
564
+
565
+ Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
566
+ of the same application. i.e. you will need to re-initialize the deepspeed engine, since
567
+ ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
568
+
569
+ """
570
+ logger.info(f"Extracting fp32 weights")
571
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
572
+
573
+ logger.info(f"Overwriting model with fp32 weights")
574
+ model = model.cpu()
575
+ model.load_state_dict(state_dict, strict=False)
576
+
577
+ return model
578
+
579
+
580
+ if __name__ == "__main__":
581
+
582
+ parser = argparse.ArgumentParser()
583
+ parser.add_argument("checkpoint_dir",
584
+ type=str,
585
+ help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
586
+ parser.add_argument(
587
+ "output_file",
588
+ type=str,
589
+ help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
590
+ parser.add_argument("-t",
591
+ "--tag",
592
+ type=str,
593
+ default=None,
594
+ help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
595
+ parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
596
+ parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
597
+ args = parser.parse_args()
598
+
599
+ debug = args.debug
600
+
601
+ convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
602
+ args.output_file,
603
+ tag=args.tag,
604
+ exclude_frozen_parameters=args.exclude_frozen_parameters)
checkpoint-218/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: nvidia/Llama-3_3-Nemotron-Super-49B-v1
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 0.15.0
checkpoint-218/adapter_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "nvidia/Llama-3_3-Nemotron-Super-49B-v1",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": null,
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": 512,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": [
22
+ "embed_tokens",
23
+ "lm_head"
24
+ ],
25
+ "peft_type": "LORA",
26
+ "r": 256,
27
+ "rank_pattern": {},
28
+ "revision": null,
29
+ "target_modules": [
30
+ "o_proj",
31
+ "gate_proj",
32
+ "q_proj",
33
+ "k_proj",
34
+ "v_proj",
35
+ "up_proj",
36
+ "down_proj"
37
+ ],
38
+ "task_type": "CAUSAL_LM",
39
+ "trainable_token_indices": null,
40
+ "use_dora": false,
41
+ "use_rslora": false
42
+ }
checkpoint-218/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b76fdaabeb0342548ab74dece3dcaef2498cd01d11ae6496e161b50f85d39886
3
+ size 9016826528
checkpoint-218/global_step217/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb254d842a0bd3ac4dc30619d358c802076f2ae5a8a1d7b220ef274adcb63e50
3
+ size 27050164444
checkpoint-218/global_step217/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c224fcc95287ab5f4cbea9ba6ab0ab3f61c93b93fe2482cba1cfcbbc438f1bb
3
+ size 27050169884
checkpoint-218/global_step217/mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90a15492216e48ac85875cb87b3ab32a526439c0341ca98b34dc9ae767d8123e
3
+ size 9776788601
checkpoint-218/latest ADDED
@@ -0,0 +1 @@
 
 
1
+ global_step217
checkpoint-218/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15e06bff2ae5de048d5791e7d5b33c487c72cb4c6226bbe98529b686c66d1960
3
+ size 14512
checkpoint-218/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ebf3b1d63337eb96a8c9ec5fb78befa637a5ae4dce16a50b68163cfabe6dd02
3
+ size 14512
checkpoint-218/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33fe6cc8ba4774c5504d871fd373473a25f477a0e4a445a512e0595aa3abfbab
3
+ size 1064
checkpoint-218/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": {
17
+ "content": "<|end_of_text|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
checkpoint-218/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
checkpoint-218/tokenizer_config.json ADDED
@@ -0,0 +1,2064 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{{- bos_token }}{%- if messages[0]['role'] == 'system' %}{%- set system_message = messages[0]['content']|trim %}{%- set messages = messages[1:] %}{%- else %}{%- set system_message = \"\" %}{%- endif %}{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}{{- system_message }}{{- \"<|eot_id|>\" }}{%- for message in messages %}{%- if message['role'] == 'assistant' and '</think>' in message['content'] %}{%- set content = message['content'].split('</think>')[-1].lstrip() %}{%- else %}{%- set content = message['content'] %}{%- endif %}{{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n' + content | trim + '<|eot_id|>' }}{%- endfor %}{%- if add_generation_prompt %}{{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}{%- endif %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "extra_special_tokens": {},
2057
+ "model_input_names": [
2058
+ "input_ids",
2059
+ "attention_mask"
2060
+ ],
2061
+ "model_max_length": 131072,
2062
+ "pad_token": "<|end_of_text|>",
2063
+ "tokenizer_class": "PreTrainedTokenizer"
2064
+ }
checkpoint-218/trainer_state.json ADDED
@@ -0,0 +1,1559 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.9878048780487805,
5
+ "eval_steps": 500,
6
+ "global_step": 218,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.009146341463414634,
13
+ "grad_norm": 40.05127716064453,
14
+ "learning_rate": 5.0000000000000004e-08,
15
+ "loss": 5.1282,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.018292682926829267,
20
+ "grad_norm": 39.01039505004883,
21
+ "learning_rate": 1.0000000000000001e-07,
22
+ "loss": 5.0586,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.027439024390243903,
27
+ "grad_norm": 40.20766067504883,
28
+ "learning_rate": 1.5000000000000002e-07,
29
+ "loss": 5.0311,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.036585365853658534,
34
+ "grad_norm": 38.70350646972656,
35
+ "learning_rate": 2.0000000000000002e-07,
36
+ "loss": 5.1598,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.04573170731707317,
41
+ "grad_norm": 39.230979919433594,
42
+ "learning_rate": 2.5000000000000004e-07,
43
+ "loss": 5.0812,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.054878048780487805,
48
+ "grad_norm": 39.45293045043945,
49
+ "learning_rate": 3.0000000000000004e-07,
50
+ "loss": 5.0841,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.06402439024390244,
55
+ "grad_norm": 38.92170333862305,
56
+ "learning_rate": 3.5000000000000004e-07,
57
+ "loss": 5.022,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.07317073170731707,
62
+ "grad_norm": 38.932369232177734,
63
+ "learning_rate": 4.0000000000000003e-07,
64
+ "loss": 5.0876,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.08231707317073171,
69
+ "grad_norm": 39.60245132446289,
70
+ "learning_rate": 4.5000000000000003e-07,
71
+ "loss": 5.0798,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.09146341463414634,
76
+ "grad_norm": 39.53607177734375,
77
+ "learning_rate": 5.000000000000001e-07,
78
+ "loss": 5.0105,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.10060975609756098,
83
+ "grad_norm": 39.50700378417969,
84
+ "learning_rate": 5.5e-07,
85
+ "loss": 4.9951,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.10975609756097561,
90
+ "grad_norm": 39.52376174926758,
91
+ "learning_rate": 6.000000000000001e-07,
92
+ "loss": 4.9163,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.11890243902439024,
97
+ "grad_norm": 39.15214157104492,
98
+ "learning_rate": 6.5e-07,
99
+ "loss": 4.9634,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.12804878048780488,
104
+ "grad_norm": 37.795066833496094,
105
+ "learning_rate": 7.000000000000001e-07,
106
+ "loss": 4.819,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.13719512195121952,
111
+ "grad_norm": 38.23014450073242,
112
+ "learning_rate": 7.5e-07,
113
+ "loss": 4.8756,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.14634146341463414,
118
+ "grad_norm": 38.57551574707031,
119
+ "learning_rate": 8.000000000000001e-07,
120
+ "loss": 4.81,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.15548780487804878,
125
+ "grad_norm": 36.06121063232422,
126
+ "learning_rate": 8.500000000000001e-07,
127
+ "loss": 4.7901,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.16463414634146342,
132
+ "grad_norm": 34.38008117675781,
133
+ "learning_rate": 9.000000000000001e-07,
134
+ "loss": 4.5775,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.17378048780487804,
139
+ "grad_norm": 32.60890579223633,
140
+ "learning_rate": 9.500000000000001e-07,
141
+ "loss": 4.3737,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.18292682926829268,
146
+ "grad_norm": 31.983110427856445,
147
+ "learning_rate": 1.0000000000000002e-06,
148
+ "loss": 4.3773,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.19207317073170732,
153
+ "grad_norm": 27.69571876525879,
154
+ "learning_rate": 1.0500000000000001e-06,
155
+ "loss": 4.1276,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.20121951219512196,
160
+ "grad_norm": 26.542314529418945,
161
+ "learning_rate": 1.1e-06,
162
+ "loss": 4.0641,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.21036585365853658,
167
+ "grad_norm": 23.26603126525879,
168
+ "learning_rate": 1.1500000000000002e-06,
169
+ "loss": 4.0197,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.21951219512195122,
174
+ "grad_norm": 21.04385757446289,
175
+ "learning_rate": 1.2000000000000002e-06,
176
+ "loss": 4.0179,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.22865853658536586,
181
+ "grad_norm": 19.790103912353516,
182
+ "learning_rate": 1.25e-06,
183
+ "loss": 3.8334,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.23780487804878048,
188
+ "grad_norm": 18.2396183013916,
189
+ "learning_rate": 1.3e-06,
190
+ "loss": 3.7027,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.24695121951219512,
195
+ "grad_norm": 18.725860595703125,
196
+ "learning_rate": 1.3500000000000002e-06,
197
+ "loss": 3.7268,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.25609756097560976,
202
+ "grad_norm": 18.91561508178711,
203
+ "learning_rate": 1.4000000000000001e-06,
204
+ "loss": 3.52,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.2652439024390244,
209
+ "grad_norm": 18.196651458740234,
210
+ "learning_rate": 1.45e-06,
211
+ "loss": 3.4765,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.27439024390243905,
216
+ "grad_norm": 17.778606414794922,
217
+ "learning_rate": 1.5e-06,
218
+ "loss": 3.3573,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.28353658536585363,
223
+ "grad_norm": 16.23012924194336,
224
+ "learning_rate": 1.5500000000000002e-06,
225
+ "loss": 3.2783,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.2926829268292683,
230
+ "grad_norm": 15.836565017700195,
231
+ "learning_rate": 1.6000000000000001e-06,
232
+ "loss": 3.2319,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.3018292682926829,
237
+ "grad_norm": 11.919289588928223,
238
+ "learning_rate": 1.6500000000000003e-06,
239
+ "loss": 3.1345,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.31097560975609756,
244
+ "grad_norm": 11.086843490600586,
245
+ "learning_rate": 1.7000000000000002e-06,
246
+ "loss": 3.1153,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.3201219512195122,
251
+ "grad_norm": 7.563486576080322,
252
+ "learning_rate": 1.75e-06,
253
+ "loss": 2.9784,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.32926829268292684,
258
+ "grad_norm": 7.60545539855957,
259
+ "learning_rate": 1.8000000000000001e-06,
260
+ "loss": 2.8568,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.3384146341463415,
265
+ "grad_norm": 7.071218013763428,
266
+ "learning_rate": 1.85e-06,
267
+ "loss": 2.8879,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.3475609756097561,
272
+ "grad_norm": 8.200672149658203,
273
+ "learning_rate": 1.9000000000000002e-06,
274
+ "loss": 2.7437,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.3567073170731707,
279
+ "grad_norm": 12.079374313354492,
280
+ "learning_rate": 1.9500000000000004e-06,
281
+ "loss": 2.7589,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.36585365853658536,
286
+ "grad_norm": 12.21938705444336,
287
+ "learning_rate": 2.0000000000000003e-06,
288
+ "loss": 2.7098,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.375,
293
+ "grad_norm": 10.224228858947754,
294
+ "learning_rate": 2.05e-06,
295
+ "loss": 2.6803,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.38414634146341464,
300
+ "grad_norm": 10.054616928100586,
301
+ "learning_rate": 2.1000000000000002e-06,
302
+ "loss": 2.4658,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.3932926829268293,
307
+ "grad_norm": 8.074049949645996,
308
+ "learning_rate": 2.15e-06,
309
+ "loss": 2.6341,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.4024390243902439,
314
+ "grad_norm": 5.721987724304199,
315
+ "learning_rate": 2.2e-06,
316
+ "loss": 2.3848,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.4115853658536585,
321
+ "grad_norm": 4.646566390991211,
322
+ "learning_rate": 2.25e-06,
323
+ "loss": 2.4323,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.42073170731707316,
328
+ "grad_norm": 4.591104984283447,
329
+ "learning_rate": 2.3000000000000004e-06,
330
+ "loss": 2.4022,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.4298780487804878,
335
+ "grad_norm": 4.822715759277344,
336
+ "learning_rate": 2.35e-06,
337
+ "loss": 2.2768,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.43902439024390244,
342
+ "grad_norm": 5.176568984985352,
343
+ "learning_rate": 2.4000000000000003e-06,
344
+ "loss": 2.281,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.4481707317073171,
349
+ "grad_norm": 4.731242656707764,
350
+ "learning_rate": 2.4500000000000003e-06,
351
+ "loss": 2.235,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.4573170731707317,
356
+ "grad_norm": 4.6343865394592285,
357
+ "learning_rate": 2.5e-06,
358
+ "loss": 2.1465,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.46646341463414637,
363
+ "grad_norm": 4.669382095336914,
364
+ "learning_rate": 2.55e-06,
365
+ "loss": 2.0969,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.47560975609756095,
370
+ "grad_norm": 4.207769870758057,
371
+ "learning_rate": 2.6e-06,
372
+ "loss": 2.0308,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.4847560975609756,
377
+ "grad_norm": 5.222470760345459,
378
+ "learning_rate": 2.6500000000000005e-06,
379
+ "loss": 1.9445,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.49390243902439024,
384
+ "grad_norm": 5.10925817489624,
385
+ "learning_rate": 2.7000000000000004e-06,
386
+ "loss": 1.7763,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.5030487804878049,
391
+ "grad_norm": 4.8151044845581055,
392
+ "learning_rate": 2.7500000000000004e-06,
393
+ "loss": 1.7661,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.5121951219512195,
398
+ "grad_norm": 6.155700206756592,
399
+ "learning_rate": 2.8000000000000003e-06,
400
+ "loss": 1.6665,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.5213414634146342,
405
+ "grad_norm": 4.719021320343018,
406
+ "learning_rate": 2.85e-06,
407
+ "loss": 1.5532,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.5304878048780488,
412
+ "grad_norm": 4.591799259185791,
413
+ "learning_rate": 2.9e-06,
414
+ "loss": 1.5244,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.5396341463414634,
419
+ "grad_norm": 5.483795642852783,
420
+ "learning_rate": 2.95e-06,
421
+ "loss": 1.3816,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.5487804878048781,
426
+ "grad_norm": 4.32553768157959,
427
+ "learning_rate": 3e-06,
428
+ "loss": 1.4268,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.5579268292682927,
433
+ "grad_norm": 8.296231269836426,
434
+ "learning_rate": 3.05e-06,
435
+ "loss": 1.2887,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.5670731707317073,
440
+ "grad_norm": 5.07594108581543,
441
+ "learning_rate": 3.1000000000000004e-06,
442
+ "loss": 1.228,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.5762195121951219,
447
+ "grad_norm": 8.427435874938965,
448
+ "learning_rate": 3.1500000000000003e-06,
449
+ "loss": 1.1724,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.5853658536585366,
454
+ "grad_norm": 22.45092010498047,
455
+ "learning_rate": 3.2000000000000003e-06,
456
+ "loss": 1.0871,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.5945121951219512,
461
+ "grad_norm": 20.67412567138672,
462
+ "learning_rate": 3.2500000000000002e-06,
463
+ "loss": 1.0108,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.6036585365853658,
468
+ "grad_norm": 4.921634674072266,
469
+ "learning_rate": 3.3000000000000006e-06,
470
+ "loss": 0.9775,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.6128048780487805,
475
+ "grad_norm": 4.477286338806152,
476
+ "learning_rate": 3.3500000000000005e-06,
477
+ "loss": 0.9554,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.6219512195121951,
482
+ "grad_norm": 8.190194129943848,
483
+ "learning_rate": 3.4000000000000005e-06,
484
+ "loss": 0.8583,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.6310975609756098,
489
+ "grad_norm": 29.21201515197754,
490
+ "learning_rate": 3.45e-06,
491
+ "loss": 0.8499,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.6402439024390244,
496
+ "grad_norm": 33.81047439575195,
497
+ "learning_rate": 3.5e-06,
498
+ "loss": 0.858,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.649390243902439,
503
+ "grad_norm": 3.5125606060028076,
504
+ "learning_rate": 3.5500000000000003e-06,
505
+ "loss": 0.7227,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.6585365853658537,
510
+ "grad_norm": 18.493423461914062,
511
+ "learning_rate": 3.6000000000000003e-06,
512
+ "loss": 0.7447,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.6676829268292683,
517
+ "grad_norm": 24.923927307128906,
518
+ "learning_rate": 3.65e-06,
519
+ "loss": 0.8423,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.676829268292683,
524
+ "grad_norm": 9.870631217956543,
525
+ "learning_rate": 3.7e-06,
526
+ "loss": 0.6934,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.6859756097560976,
531
+ "grad_norm": 20.598569869995117,
532
+ "learning_rate": 3.7500000000000005e-06,
533
+ "loss": 0.7005,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.6951219512195121,
538
+ "grad_norm": 30.662466049194336,
539
+ "learning_rate": 3.8000000000000005e-06,
540
+ "loss": 0.6226,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.7042682926829268,
545
+ "grad_norm": 28.930774688720703,
546
+ "learning_rate": 3.85e-06,
547
+ "loss": 0.6357,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.7134146341463414,
552
+ "grad_norm": 7.140467166900635,
553
+ "learning_rate": 3.900000000000001e-06,
554
+ "loss": 0.6129,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.7225609756097561,
559
+ "grad_norm": 6.322911739349365,
560
+ "learning_rate": 3.95e-06,
561
+ "loss": 0.6086,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.7317073170731707,
566
+ "grad_norm": 5.404141426086426,
567
+ "learning_rate": 4.000000000000001e-06,
568
+ "loss": 0.5986,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.7408536585365854,
573
+ "grad_norm": 24.445228576660156,
574
+ "learning_rate": 4.05e-06,
575
+ "loss": 0.5932,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.75,
580
+ "grad_norm": 14.275381088256836,
581
+ "learning_rate": 4.1e-06,
582
+ "loss": 0.5286,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.7591463414634146,
587
+ "grad_norm": 9.77132511138916,
588
+ "learning_rate": 4.15e-06,
589
+ "loss": 0.4814,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.7682926829268293,
594
+ "grad_norm": 11.043930053710938,
595
+ "learning_rate": 4.2000000000000004e-06,
596
+ "loss": 0.4953,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.7774390243902439,
601
+ "grad_norm": 3.1333775520324707,
602
+ "learning_rate": 4.25e-06,
603
+ "loss": 0.4794,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.7865853658536586,
608
+ "grad_norm": 9.50448989868164,
609
+ "learning_rate": 4.3e-06,
610
+ "loss": 0.4451,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.7957317073170732,
615
+ "grad_norm": 5.867074489593506,
616
+ "learning_rate": 4.350000000000001e-06,
617
+ "loss": 0.4224,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 0.8048780487804879,
622
+ "grad_norm": 12.556106567382812,
623
+ "learning_rate": 4.4e-06,
624
+ "loss": 0.4224,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 0.8140243902439024,
629
+ "grad_norm": 7.916622638702393,
630
+ "learning_rate": 4.450000000000001e-06,
631
+ "loss": 0.4091,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 0.823170731707317,
636
+ "grad_norm": 2.970932722091675,
637
+ "learning_rate": 4.5e-06,
638
+ "loss": 0.4181,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 0.8323170731707317,
643
+ "grad_norm": 17.468870162963867,
644
+ "learning_rate": 4.5500000000000005e-06,
645
+ "loss": 0.4031,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 0.8414634146341463,
650
+ "grad_norm": 15.861083984375,
651
+ "learning_rate": 4.600000000000001e-06,
652
+ "loss": 0.3604,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 0.850609756097561,
657
+ "grad_norm": 6.715958118438721,
658
+ "learning_rate": 4.65e-06,
659
+ "loss": 0.3489,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 0.8597560975609756,
664
+ "grad_norm": 5.439844608306885,
665
+ "learning_rate": 4.7e-06,
666
+ "loss": 0.3339,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 0.8689024390243902,
671
+ "grad_norm": 4.650434494018555,
672
+ "learning_rate": 4.75e-06,
673
+ "loss": 0.3189,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 0.8780487804878049,
678
+ "grad_norm": 15.319528579711914,
679
+ "learning_rate": 4.800000000000001e-06,
680
+ "loss": 0.3347,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 0.8871951219512195,
685
+ "grad_norm": 5.151925563812256,
686
+ "learning_rate": 4.85e-06,
687
+ "loss": 0.3043,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 0.8963414634146342,
692
+ "grad_norm": 6.351178169250488,
693
+ "learning_rate": 4.9000000000000005e-06,
694
+ "loss": 0.2939,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 0.9054878048780488,
699
+ "grad_norm": 3.942911148071289,
700
+ "learning_rate": 4.95e-06,
701
+ "loss": 0.2887,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 0.9146341463414634,
706
+ "grad_norm": 3.0885493755340576,
707
+ "learning_rate": 5e-06,
708
+ "loss": 0.2992,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 0.9237804878048781,
713
+ "grad_norm": 7.023274898529053,
714
+ "learning_rate": 4.999959803423605e-06,
715
+ "loss": 0.2607,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 0.9329268292682927,
720
+ "grad_norm": 8.774216651916504,
721
+ "learning_rate": 4.9998392149870315e-06,
722
+ "loss": 0.2674,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 0.9420731707317073,
727
+ "grad_norm": 3.5439791679382324,
728
+ "learning_rate": 4.999638238568072e-06,
729
+ "loss": 0.2602,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 0.9512195121951219,
734
+ "grad_norm": 7.669381618499756,
735
+ "learning_rate": 4.999356880629579e-06,
736
+ "loss": 0.2718,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 0.9603658536585366,
741
+ "grad_norm": 6.9407854080200195,
742
+ "learning_rate": 4.998995150219252e-06,
743
+ "loss": 0.2494,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 0.9695121951219512,
748
+ "grad_norm": 12.144411087036133,
749
+ "learning_rate": 4.998553058969352e-06,
750
+ "loss": 0.2297,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 0.9786585365853658,
755
+ "grad_norm": 6.956138610839844,
756
+ "learning_rate": 4.998030621096322e-06,
757
+ "loss": 0.2386,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 0.9878048780487805,
762
+ "grad_norm": 8.304037094116211,
763
+ "learning_rate": 4.997427853400333e-06,
764
+ "loss": 0.23,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 0.9969512195121951,
769
+ "grad_norm": 7.031365394592285,
770
+ "learning_rate": 4.996744775264743e-06,
771
+ "loss": 0.2346,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 1.0,
776
+ "grad_norm": 7.031365394592285,
777
+ "learning_rate": 4.9959814086554735e-06,
778
+ "loss": 0.0739,
779
+ "step": 110
780
+ },
781
+ {
782
+ "epoch": 1.0091463414634145,
783
+ "grad_norm": 2.084608793258667,
784
+ "learning_rate": 4.995137778120306e-06,
785
+ "loss": 0.2422,
786
+ "step": 111
787
+ },
788
+ {
789
+ "epoch": 1.0182926829268293,
790
+ "grad_norm": 38.12245178222656,
791
+ "learning_rate": 4.994213910788085e-06,
792
+ "loss": 0.1992,
793
+ "step": 112
794
+ },
795
+ {
796
+ "epoch": 1.0274390243902438,
797
+ "grad_norm": 2.817565441131592,
798
+ "learning_rate": 4.993209836367856e-06,
799
+ "loss": 0.1882,
800
+ "step": 113
801
+ },
802
+ {
803
+ "epoch": 1.0365853658536586,
804
+ "grad_norm": 11.774249076843262,
805
+ "learning_rate": 4.9921255871479e-06,
806
+ "loss": 0.2235,
807
+ "step": 114
808
+ },
809
+ {
810
+ "epoch": 1.045731707317073,
811
+ "grad_norm": 2.3362019062042236,
812
+ "learning_rate": 4.9909611979947046e-06,
813
+ "loss": 0.1875,
814
+ "step": 115
815
+ },
816
+ {
817
+ "epoch": 1.0548780487804879,
818
+ "grad_norm": 1.9516818523406982,
819
+ "learning_rate": 4.989716706351835e-06,
820
+ "loss": 0.1858,
821
+ "step": 116
822
+ },
823
+ {
824
+ "epoch": 1.0640243902439024,
825
+ "grad_norm": 1.5484645366668701,
826
+ "learning_rate": 4.9883921522387336e-06,
827
+ "loss": 0.1845,
828
+ "step": 117
829
+ },
830
+ {
831
+ "epoch": 1.0731707317073171,
832
+ "grad_norm": 7.430396556854248,
833
+ "learning_rate": 4.986987578249433e-06,
834
+ "loss": 0.184,
835
+ "step": 118
836
+ },
837
+ {
838
+ "epoch": 1.0823170731707317,
839
+ "grad_norm": 2.0725948810577393,
840
+ "learning_rate": 4.9855030295511845e-06,
841
+ "loss": 0.177,
842
+ "step": 119
843
+ },
844
+ {
845
+ "epoch": 1.0914634146341464,
846
+ "grad_norm": 4.836520671844482,
847
+ "learning_rate": 4.98393855388301e-06,
848
+ "loss": 0.1744,
849
+ "step": 120
850
+ },
851
+ {
852
+ "epoch": 1.100609756097561,
853
+ "grad_norm": 5.22581672668457,
854
+ "learning_rate": 4.982294201554162e-06,
855
+ "loss": 0.1599,
856
+ "step": 121
857
+ },
858
+ {
859
+ "epoch": 1.1097560975609757,
860
+ "grad_norm": 5.406208038330078,
861
+ "learning_rate": 4.980570025442507e-06,
862
+ "loss": 0.1645,
863
+ "step": 122
864
+ },
865
+ {
866
+ "epoch": 1.1189024390243902,
867
+ "grad_norm": 8.736640930175781,
868
+ "learning_rate": 4.978766080992827e-06,
869
+ "loss": 0.1943,
870
+ "step": 123
871
+ },
872
+ {
873
+ "epoch": 1.1280487804878048,
874
+ "grad_norm": 9.184198379516602,
875
+ "learning_rate": 4.976882426215035e-06,
876
+ "loss": 0.1753,
877
+ "step": 124
878
+ },
879
+ {
880
+ "epoch": 1.1371951219512195,
881
+ "grad_norm": 5.317800521850586,
882
+ "learning_rate": 4.974919121682307e-06,
883
+ "loss": 0.1897,
884
+ "step": 125
885
+ },
886
+ {
887
+ "epoch": 1.146341463414634,
888
+ "grad_norm": 11.803364753723145,
889
+ "learning_rate": 4.972876230529143e-06,
890
+ "loss": 0.1516,
891
+ "step": 126
892
+ },
893
+ {
894
+ "epoch": 1.1554878048780488,
895
+ "grad_norm": 31.74310302734375,
896
+ "learning_rate": 4.9707538184493255e-06,
897
+ "loss": 0.1947,
898
+ "step": 127
899
+ },
900
+ {
901
+ "epoch": 1.1646341463414633,
902
+ "grad_norm": 1.956932783126831,
903
+ "learning_rate": 4.968551953693813e-06,
904
+ "loss": 0.1708,
905
+ "step": 128
906
+ },
907
+ {
908
+ "epoch": 1.173780487804878,
909
+ "grad_norm": 4.64445686340332,
910
+ "learning_rate": 4.966270707068548e-06,
911
+ "loss": 0.1711,
912
+ "step": 129
913
+ },
914
+ {
915
+ "epoch": 1.1829268292682926,
916
+ "grad_norm": 4.442819595336914,
917
+ "learning_rate": 4.963910151932171e-06,
918
+ "loss": 0.1572,
919
+ "step": 130
920
+ },
921
+ {
922
+ "epoch": 1.1920731707317074,
923
+ "grad_norm": 1.9702759981155396,
924
+ "learning_rate": 4.961470364193673e-06,
925
+ "loss": 0.1364,
926
+ "step": 131
927
+ },
928
+ {
929
+ "epoch": 1.201219512195122,
930
+ "grad_norm": 7.816587448120117,
931
+ "learning_rate": 4.9589514223099425e-06,
932
+ "loss": 0.1624,
933
+ "step": 132
934
+ },
935
+ {
936
+ "epoch": 1.2103658536585367,
937
+ "grad_norm": 61.18424606323242,
938
+ "learning_rate": 4.956353407283252e-06,
939
+ "loss": 0.26,
940
+ "step": 133
941
+ },
942
+ {
943
+ "epoch": 1.2195121951219512,
944
+ "grad_norm": 15.649847984313965,
945
+ "learning_rate": 4.9536764026586505e-06,
946
+ "loss": 0.1543,
947
+ "step": 134
948
+ },
949
+ {
950
+ "epoch": 1.228658536585366,
951
+ "grad_norm": 2.249363660812378,
952
+ "learning_rate": 4.950920494521274e-06,
953
+ "loss": 0.152,
954
+ "step": 135
955
+ },
956
+ {
957
+ "epoch": 1.2378048780487805,
958
+ "grad_norm": 4.055661678314209,
959
+ "learning_rate": 4.948085771493579e-06,
960
+ "loss": 0.1402,
961
+ "step": 136
962
+ },
963
+ {
964
+ "epoch": 1.2469512195121952,
965
+ "grad_norm": 2.2803292274475098,
966
+ "learning_rate": 4.945172324732496e-06,
967
+ "loss": 0.1427,
968
+ "step": 137
969
+ },
970
+ {
971
+ "epoch": 1.2560975609756098,
972
+ "grad_norm": 2.5540456771850586,
973
+ "learning_rate": 4.942180247926492e-06,
974
+ "loss": 0.143,
975
+ "step": 138
976
+ },
977
+ {
978
+ "epoch": 1.2652439024390243,
979
+ "grad_norm": 8.80340576171875,
980
+ "learning_rate": 4.939109637292563e-06,
981
+ "loss": 0.1569,
982
+ "step": 139
983
+ },
984
+ {
985
+ "epoch": 1.274390243902439,
986
+ "grad_norm": 3.1077523231506348,
987
+ "learning_rate": 4.935960591573136e-06,
988
+ "loss": 0.1313,
989
+ "step": 140
990
+ },
991
+ {
992
+ "epoch": 1.2835365853658536,
993
+ "grad_norm": 1.2506815195083618,
994
+ "learning_rate": 4.932733212032896e-06,
995
+ "loss": 0.137,
996
+ "step": 141
997
+ },
998
+ {
999
+ "epoch": 1.2926829268292683,
1000
+ "grad_norm": 2.4397666454315186,
1001
+ "learning_rate": 4.929427602455532e-06,
1002
+ "loss": 0.1408,
1003
+ "step": 142
1004
+ },
1005
+ {
1006
+ "epoch": 1.3018292682926829,
1007
+ "grad_norm": 1.7658663988113403,
1008
+ "learning_rate": 4.926043869140392e-06,
1009
+ "loss": 0.133,
1010
+ "step": 143
1011
+ },
1012
+ {
1013
+ "epoch": 1.3109756097560976,
1014
+ "grad_norm": 1.0473108291625977,
1015
+ "learning_rate": 4.922582120899072e-06,
1016
+ "loss": 0.1358,
1017
+ "step": 144
1018
+ },
1019
+ {
1020
+ "epoch": 1.3201219512195121,
1021
+ "grad_norm": 5.566607475280762,
1022
+ "learning_rate": 4.919042469051916e-06,
1023
+ "loss": 0.1237,
1024
+ "step": 145
1025
+ },
1026
+ {
1027
+ "epoch": 1.329268292682927,
1028
+ "grad_norm": 1.0360139608383179,
1029
+ "learning_rate": 4.915425027424429e-06,
1030
+ "loss": 0.1274,
1031
+ "step": 146
1032
+ },
1033
+ {
1034
+ "epoch": 1.3384146341463414,
1035
+ "grad_norm": 1.9091176986694336,
1036
+ "learning_rate": 4.911729912343631e-06,
1037
+ "loss": 0.1439,
1038
+ "step": 147
1039
+ },
1040
+ {
1041
+ "epoch": 1.3475609756097562,
1042
+ "grad_norm": 1.5727638006210327,
1043
+ "learning_rate": 4.907957242634299e-06,
1044
+ "loss": 0.1259,
1045
+ "step": 148
1046
+ },
1047
+ {
1048
+ "epoch": 1.3567073170731707,
1049
+ "grad_norm": 1.0574792623519897,
1050
+ "learning_rate": 4.9041071396151585e-06,
1051
+ "loss": 0.142,
1052
+ "step": 149
1053
+ },
1054
+ {
1055
+ "epoch": 1.3658536585365852,
1056
+ "grad_norm": 8.020130157470703,
1057
+ "learning_rate": 4.900179727094978e-06,
1058
+ "loss": 0.1392,
1059
+ "step": 150
1060
+ },
1061
+ {
1062
+ "epoch": 1.375,
1063
+ "grad_norm": 3.156255006790161,
1064
+ "learning_rate": 4.896175131368587e-06,
1065
+ "loss": 0.152,
1066
+ "step": 151
1067
+ },
1068
+ {
1069
+ "epoch": 1.3841463414634148,
1070
+ "grad_norm": 2.3956990242004395,
1071
+ "learning_rate": 4.892093481212817e-06,
1072
+ "loss": 0.1244,
1073
+ "step": 152
1074
+ },
1075
+ {
1076
+ "epoch": 1.3932926829268293,
1077
+ "grad_norm": 2.6058578491210938,
1078
+ "learning_rate": 4.887934907882357e-06,
1079
+ "loss": 0.1271,
1080
+ "step": 153
1081
+ },
1082
+ {
1083
+ "epoch": 1.4024390243902438,
1084
+ "grad_norm": 1.7173289060592651,
1085
+ "learning_rate": 4.883699545105535e-06,
1086
+ "loss": 0.1257,
1087
+ "step": 154
1088
+ },
1089
+ {
1090
+ "epoch": 1.4115853658536586,
1091
+ "grad_norm": 2.2237367630004883,
1092
+ "learning_rate": 4.8793875290800186e-06,
1093
+ "loss": 0.127,
1094
+ "step": 155
1095
+ },
1096
+ {
1097
+ "epoch": 1.420731707317073,
1098
+ "grad_norm": 6.997623920440674,
1099
+ "learning_rate": 4.874998998468433e-06,
1100
+ "loss": 0.1454,
1101
+ "step": 156
1102
+ },
1103
+ {
1104
+ "epoch": 1.4298780487804879,
1105
+ "grad_norm": 10.645139694213867,
1106
+ "learning_rate": 4.870534094393903e-06,
1107
+ "loss": 0.1402,
1108
+ "step": 157
1109
+ },
1110
+ {
1111
+ "epoch": 1.4390243902439024,
1112
+ "grad_norm": 1.5808072090148926,
1113
+ "learning_rate": 4.865992960435514e-06,
1114
+ "loss": 0.1156,
1115
+ "step": 158
1116
+ },
1117
+ {
1118
+ "epoch": 1.4481707317073171,
1119
+ "grad_norm": 0.990803062915802,
1120
+ "learning_rate": 4.861375742623697e-06,
1121
+ "loss": 0.1286,
1122
+ "step": 159
1123
+ },
1124
+ {
1125
+ "epoch": 1.4573170731707317,
1126
+ "grad_norm": 1.5008662939071655,
1127
+ "learning_rate": 4.856682589435531e-06,
1128
+ "loss": 0.1282,
1129
+ "step": 160
1130
+ },
1131
+ {
1132
+ "epoch": 1.4664634146341464,
1133
+ "grad_norm": 1.772304892539978,
1134
+ "learning_rate": 4.851913651789968e-06,
1135
+ "loss": 0.1308,
1136
+ "step": 161
1137
+ },
1138
+ {
1139
+ "epoch": 1.475609756097561,
1140
+ "grad_norm": 1.201061487197876,
1141
+ "learning_rate": 4.847069083042982e-06,
1142
+ "loss": 0.1198,
1143
+ "step": 162
1144
+ },
1145
+ {
1146
+ "epoch": 1.4847560975609757,
1147
+ "grad_norm": 0.6147828698158264,
1148
+ "learning_rate": 4.8421490389826344e-06,
1149
+ "loss": 0.1138,
1150
+ "step": 163
1151
+ },
1152
+ {
1153
+ "epoch": 1.4939024390243902,
1154
+ "grad_norm": 1.3990256786346436,
1155
+ "learning_rate": 4.837153677824068e-06,
1156
+ "loss": 0.1205,
1157
+ "step": 164
1158
+ },
1159
+ {
1160
+ "epoch": 1.5030487804878048,
1161
+ "grad_norm": 1.6977574825286865,
1162
+ "learning_rate": 4.832083160204414e-06,
1163
+ "loss": 0.1128,
1164
+ "step": 165
1165
+ },
1166
+ {
1167
+ "epoch": 1.5121951219512195,
1168
+ "grad_norm": 2.4056453704833984,
1169
+ "learning_rate": 4.826937649177632e-06,
1170
+ "loss": 0.1184,
1171
+ "step": 166
1172
+ },
1173
+ {
1174
+ "epoch": 1.5213414634146343,
1175
+ "grad_norm": 2.7455694675445557,
1176
+ "learning_rate": 4.821717310209265e-06,
1177
+ "loss": 0.123,
1178
+ "step": 167
1179
+ },
1180
+ {
1181
+ "epoch": 1.5304878048780488,
1182
+ "grad_norm": 1.8243584632873535,
1183
+ "learning_rate": 4.816422311171115e-06,
1184
+ "loss": 0.1198,
1185
+ "step": 168
1186
+ },
1187
+ {
1188
+ "epoch": 1.5396341463414633,
1189
+ "grad_norm": 0.8920577764511108,
1190
+ "learning_rate": 4.811052822335849e-06,
1191
+ "loss": 0.1088,
1192
+ "step": 169
1193
+ },
1194
+ {
1195
+ "epoch": 1.548780487804878,
1196
+ "grad_norm": 1.6639117002487183,
1197
+ "learning_rate": 4.805609016371522e-06,
1198
+ "loss": 0.1231,
1199
+ "step": 170
1200
+ },
1201
+ {
1202
+ "epoch": 1.5579268292682928,
1203
+ "grad_norm": 1.383026123046875,
1204
+ "learning_rate": 4.800091068336024e-06,
1205
+ "loss": 0.1207,
1206
+ "step": 171
1207
+ },
1208
+ {
1209
+ "epoch": 1.5670731707317072,
1210
+ "grad_norm": 1.6599416732788086,
1211
+ "learning_rate": 4.79449915567145e-06,
1212
+ "loss": 0.1206,
1213
+ "step": 172
1214
+ },
1215
+ {
1216
+ "epoch": 1.576219512195122,
1217
+ "grad_norm": 1.5868676900863647,
1218
+ "learning_rate": 4.788833458198395e-06,
1219
+ "loss": 0.1158,
1220
+ "step": 173
1221
+ },
1222
+ {
1223
+ "epoch": 1.5853658536585367,
1224
+ "grad_norm": 1.0154211521148682,
1225
+ "learning_rate": 4.783094158110175e-06,
1226
+ "loss": 0.1091,
1227
+ "step": 174
1228
+ },
1229
+ {
1230
+ "epoch": 1.5945121951219512,
1231
+ "grad_norm": 2.1514394283294678,
1232
+ "learning_rate": 4.7772814399669585e-06,
1233
+ "loss": 0.1109,
1234
+ "step": 175
1235
+ },
1236
+ {
1237
+ "epoch": 1.6036585365853657,
1238
+ "grad_norm": 0.7475085258483887,
1239
+ "learning_rate": 4.7713954906898415e-06,
1240
+ "loss": 0.1162,
1241
+ "step": 176
1242
+ },
1243
+ {
1244
+ "epoch": 1.6128048780487805,
1245
+ "grad_norm": 0.8523163795471191,
1246
+ "learning_rate": 4.7654364995548325e-06,
1247
+ "loss": 0.1238,
1248
+ "step": 177
1249
+ },
1250
+ {
1251
+ "epoch": 1.6219512195121952,
1252
+ "grad_norm": 1.5456233024597168,
1253
+ "learning_rate": 4.759404658186765e-06,
1254
+ "loss": 0.1163,
1255
+ "step": 178
1256
+ },
1257
+ {
1258
+ "epoch": 1.6310975609756098,
1259
+ "grad_norm": 1.123340129852295,
1260
+ "learning_rate": 4.753300160553137e-06,
1261
+ "loss": 0.1104,
1262
+ "step": 179
1263
+ },
1264
+ {
1265
+ "epoch": 1.6402439024390243,
1266
+ "grad_norm": 1.16841721534729,
1267
+ "learning_rate": 4.747123202957871e-06,
1268
+ "loss": 0.1099,
1269
+ "step": 180
1270
+ },
1271
+ {
1272
+ "epoch": 1.649390243902439,
1273
+ "grad_norm": 2.025221109390259,
1274
+ "learning_rate": 4.740873984035009e-06,
1275
+ "loss": 0.1157,
1276
+ "step": 181
1277
+ },
1278
+ {
1279
+ "epoch": 1.6585365853658538,
1280
+ "grad_norm": 3.876469373703003,
1281
+ "learning_rate": 4.734552704742314e-06,
1282
+ "loss": 0.1122,
1283
+ "step": 182
1284
+ },
1285
+ {
1286
+ "epoch": 1.6676829268292683,
1287
+ "grad_norm": 1.5562145709991455,
1288
+ "learning_rate": 4.728159568354814e-06,
1289
+ "loss": 0.1127,
1290
+ "step": 183
1291
+ },
1292
+ {
1293
+ "epoch": 1.6768292682926829,
1294
+ "grad_norm": 1.4691755771636963,
1295
+ "learning_rate": 4.721694780458266e-06,
1296
+ "loss": 0.1182,
1297
+ "step": 184
1298
+ },
1299
+ {
1300
+ "epoch": 1.6859756097560976,
1301
+ "grad_norm": 1.9529973268508911,
1302
+ "learning_rate": 4.715158548942541e-06,
1303
+ "loss": 0.1153,
1304
+ "step": 185
1305
+ },
1306
+ {
1307
+ "epoch": 1.6951219512195121,
1308
+ "grad_norm": 1.9065771102905273,
1309
+ "learning_rate": 4.708551083994944e-06,
1310
+ "loss": 0.1163,
1311
+ "step": 186
1312
+ },
1313
+ {
1314
+ "epoch": 1.7042682926829267,
1315
+ "grad_norm": 1.0964735746383667,
1316
+ "learning_rate": 4.701872598093452e-06,
1317
+ "loss": 0.114,
1318
+ "step": 187
1319
+ },
1320
+ {
1321
+ "epoch": 1.7134146341463414,
1322
+ "grad_norm": 1.0885926485061646,
1323
+ "learning_rate": 4.695123305999877e-06,
1324
+ "loss": 0.114,
1325
+ "step": 188
1326
+ },
1327
+ {
1328
+ "epoch": 1.7225609756097562,
1329
+ "grad_norm": 1.1777565479278564,
1330
+ "learning_rate": 4.688303424752969e-06,
1331
+ "loss": 0.1116,
1332
+ "step": 189
1333
+ },
1334
+ {
1335
+ "epoch": 1.7317073170731707,
1336
+ "grad_norm": 1.3686976432800293,
1337
+ "learning_rate": 4.6814131736614286e-06,
1338
+ "loss": 0.1081,
1339
+ "step": 190
1340
+ },
1341
+ {
1342
+ "epoch": 1.7408536585365852,
1343
+ "grad_norm": 0.8220391869544983,
1344
+ "learning_rate": 4.674452774296861e-06,
1345
+ "loss": 0.1091,
1346
+ "step": 191
1347
+ },
1348
+ {
1349
+ "epoch": 1.75,
1350
+ "grad_norm": 1.073935866355896,
1351
+ "learning_rate": 4.667422450486646e-06,
1352
+ "loss": 0.1148,
1353
+ "step": 192
1354
+ },
1355
+ {
1356
+ "epoch": 1.7591463414634148,
1357
+ "grad_norm": 1.389614224433899,
1358
+ "learning_rate": 4.660322428306741e-06,
1359
+ "loss": 0.1134,
1360
+ "step": 193
1361
+ },
1362
+ {
1363
+ "epoch": 1.7682926829268293,
1364
+ "grad_norm": 1.349023699760437,
1365
+ "learning_rate": 4.653152936074413e-06,
1366
+ "loss": 0.1056,
1367
+ "step": 194
1368
+ },
1369
+ {
1370
+ "epoch": 1.7774390243902438,
1371
+ "grad_norm": 1.0334906578063965,
1372
+ "learning_rate": 4.645914204340898e-06,
1373
+ "loss": 0.113,
1374
+ "step": 195
1375
+ },
1376
+ {
1377
+ "epoch": 1.7865853658536586,
1378
+ "grad_norm": 18.6312313079834,
1379
+ "learning_rate": 4.638606465883979e-06,
1380
+ "loss": 0.1351,
1381
+ "step": 196
1382
+ },
1383
+ {
1384
+ "epoch": 1.7957317073170733,
1385
+ "grad_norm": 0.7669345736503601,
1386
+ "learning_rate": 4.6312299557005125e-06,
1387
+ "loss": 0.1097,
1388
+ "step": 197
1389
+ },
1390
+ {
1391
+ "epoch": 1.8048780487804879,
1392
+ "grad_norm": 2.1091127395629883,
1393
+ "learning_rate": 4.623784910998862e-06,
1394
+ "loss": 0.1122,
1395
+ "step": 198
1396
+ },
1397
+ {
1398
+ "epoch": 1.8140243902439024,
1399
+ "grad_norm": 0.8031914830207825,
1400
+ "learning_rate": 4.616271571191273e-06,
1401
+ "loss": 0.1109,
1402
+ "step": 199
1403
+ },
1404
+ {
1405
+ "epoch": 1.8231707317073171,
1406
+ "grad_norm": 2.1154661178588867,
1407
+ "learning_rate": 4.608690177886177e-06,
1408
+ "loss": 0.1131,
1409
+ "step": 200
1410
+ },
1411
+ {
1412
+ "epoch": 1.8323170731707317,
1413
+ "grad_norm": 1.4946709871292114,
1414
+ "learning_rate": 4.6010409748804165e-06,
1415
+ "loss": 0.1136,
1416
+ "step": 201
1417
+ },
1418
+ {
1419
+ "epoch": 1.8414634146341462,
1420
+ "grad_norm": 1.0509642362594604,
1421
+ "learning_rate": 4.593324208151412e-06,
1422
+ "loss": 0.1162,
1423
+ "step": 202
1424
+ },
1425
+ {
1426
+ "epoch": 1.850609756097561,
1427
+ "grad_norm": 0.8742370009422302,
1428
+ "learning_rate": 4.585540125849244e-06,
1429
+ "loss": 0.1102,
1430
+ "step": 203
1431
+ },
1432
+ {
1433
+ "epoch": 1.8597560975609757,
1434
+ "grad_norm": 1.1283056735992432,
1435
+ "learning_rate": 4.577688978288681e-06,
1436
+ "loss": 0.1104,
1437
+ "step": 204
1438
+ },
1439
+ {
1440
+ "epoch": 1.8689024390243902,
1441
+ "grad_norm": 1.0081048011779785,
1442
+ "learning_rate": 4.569771017941125e-06,
1443
+ "loss": 0.1119,
1444
+ "step": 205
1445
+ },
1446
+ {
1447
+ "epoch": 1.8780487804878048,
1448
+ "grad_norm": 0.7291656732559204,
1449
+ "learning_rate": 4.561786499426494e-06,
1450
+ "loss": 0.1103,
1451
+ "step": 206
1452
+ },
1453
+ {
1454
+ "epoch": 1.8871951219512195,
1455
+ "grad_norm": 1.144096851348877,
1456
+ "learning_rate": 4.5537356795050346e-06,
1457
+ "loss": 0.1125,
1458
+ "step": 207
1459
+ },
1460
+ {
1461
+ "epoch": 1.8963414634146343,
1462
+ "grad_norm": 0.7317456603050232,
1463
+ "learning_rate": 4.545618817069066e-06,
1464
+ "loss": 0.1105,
1465
+ "step": 208
1466
+ },
1467
+ {
1468
+ "epoch": 1.9054878048780488,
1469
+ "grad_norm": 1.1636486053466797,
1470
+ "learning_rate": 4.537436173134653e-06,
1471
+ "loss": 0.1091,
1472
+ "step": 209
1473
+ },
1474
+ {
1475
+ "epoch": 1.9146341463414633,
1476
+ "grad_norm": 0.6319037675857544,
1477
+ "learning_rate": 4.529188010833212e-06,
1478
+ "loss": 0.1088,
1479
+ "step": 210
1480
+ },
1481
+ {
1482
+ "epoch": 1.923780487804878,
1483
+ "grad_norm": 0.7535589933395386,
1484
+ "learning_rate": 4.520874595403053e-06,
1485
+ "loss": 0.1041,
1486
+ "step": 211
1487
+ },
1488
+ {
1489
+ "epoch": 1.9329268292682928,
1490
+ "grad_norm": 1.0461041927337646,
1491
+ "learning_rate": 4.512496194180846e-06,
1492
+ "loss": 0.1129,
1493
+ "step": 212
1494
+ },
1495
+ {
1496
+ "epoch": 1.9420731707317072,
1497
+ "grad_norm": 0.6124874949455261,
1498
+ "learning_rate": 4.5040530765930275e-06,
1499
+ "loss": 0.1113,
1500
+ "step": 213
1501
+ },
1502
+ {
1503
+ "epoch": 1.951219512195122,
1504
+ "grad_norm": 0.8516119122505188,
1505
+ "learning_rate": 4.495545514147134e-06,
1506
+ "loss": 0.1112,
1507
+ "step": 214
1508
+ },
1509
+ {
1510
+ "epoch": 1.9603658536585367,
1511
+ "grad_norm": 0.8919075131416321,
1512
+ "learning_rate": 4.486973780423073e-06,
1513
+ "loss": 0.1089,
1514
+ "step": 215
1515
+ },
1516
+ {
1517
+ "epoch": 1.9695121951219512,
1518
+ "grad_norm": 1.2183221578598022,
1519
+ "learning_rate": 4.478338151064323e-06,
1520
+ "loss": 0.1156,
1521
+ "step": 216
1522
+ },
1523
+ {
1524
+ "epoch": 1.9786585365853657,
1525
+ "grad_norm": 1.0123646259307861,
1526
+ "learning_rate": 4.4696389037690734e-06,
1527
+ "loss": 0.1077,
1528
+ "step": 217
1529
+ },
1530
+ {
1531
+ "epoch": 1.9878048780487805,
1532
+ "grad_norm": 0.8304896950721741,
1533
+ "learning_rate": 4.460876318281291e-06,
1534
+ "loss": 0.1051,
1535
+ "step": 218
1536
+ }
1537
+ ],
1538
+ "logging_steps": 1,
1539
+ "max_steps": 654,
1540
+ "num_input_tokens_seen": 0,
1541
+ "num_train_epochs": 6,
1542
+ "save_steps": 109,
1543
+ "stateful_callbacks": {
1544
+ "TrainerControl": {
1545
+ "args": {
1546
+ "should_epoch_stop": false,
1547
+ "should_evaluate": false,
1548
+ "should_log": false,
1549
+ "should_save": true,
1550
+ "should_training_stop": false
1551
+ },
1552
+ "attributes": {}
1553
+ }
1554
+ },
1555
+ "total_flos": 6.596238386615288e+18,
1556
+ "train_batch_size": 4,
1557
+ "trial_name": null,
1558
+ "trial_params": null
1559
+ }
checkpoint-218/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14990b8399bb8d39b746405b094f7eea1041d93488de8433b2d415de16ff957a
3
+ size 7928
checkpoint-218/zero_to_fp32.py ADDED
@@ -0,0 +1,604 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #!/usr/bin/env python
2
+
3
+ # Copyright (c) Microsoft Corporation.
4
+ # SPDX-License-Identifier: Apache-2.0
5
+
6
+ # DeepSpeed Team
7
+
8
+ # This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
9
+ # copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
10
+ # the future. Once extracted, the weights don't require DeepSpeed and can be used in any
11
+ # application.
12
+ #
13
+ # example: python zero_to_fp32.py . pytorch_model.bin
14
+
15
+ import argparse
16
+ import torch
17
+ import glob
18
+ import math
19
+ import os
20
+ import re
21
+ from collections import OrderedDict
22
+ from dataclasses import dataclass
23
+
24
+ # while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
25
+ # DeepSpeed data structures it has to be available in the current python environment.
26
+ from deepspeed.utils import logger
27
+ from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
28
+ FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
29
+ FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
30
+
31
+
32
+ @dataclass
33
+ class zero_model_state:
34
+ buffers: dict()
35
+ param_shapes: dict()
36
+ shared_params: list
37
+ ds_version: int
38
+ frozen_param_shapes: dict()
39
+ frozen_param_fragments: dict()
40
+
41
+
42
+ debug = 0
43
+
44
+ # load to cpu
45
+ device = torch.device('cpu')
46
+
47
+
48
+ def atoi(text):
49
+ return int(text) if text.isdigit() else text
50
+
51
+
52
+ def natural_keys(text):
53
+ '''
54
+ alist.sort(key=natural_keys) sorts in human order
55
+ http://nedbatchelder.com/blog/200712/human_sorting.html
56
+ (See Toothy's implementation in the comments)
57
+ '''
58
+ return [atoi(c) for c in re.split(r'(\d+)', text)]
59
+
60
+
61
+ def get_model_state_file(checkpoint_dir, zero_stage):
62
+ if not os.path.isdir(checkpoint_dir):
63
+ raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
64
+
65
+ # there should be only one file
66
+ if zero_stage <= 2:
67
+ file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
68
+ elif zero_stage == 3:
69
+ file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
70
+
71
+ if not os.path.exists(file):
72
+ raise FileNotFoundError(f"can't find model states file at '{file}'")
73
+
74
+ return file
75
+
76
+
77
+ def get_checkpoint_files(checkpoint_dir, glob_pattern):
78
+ # XXX: need to test that this simple glob rule works for multi-node setup too
79
+ ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
80
+
81
+ if len(ckpt_files) == 0:
82
+ raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
83
+
84
+ return ckpt_files
85
+
86
+
87
+ def get_optim_files(checkpoint_dir):
88
+ return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
89
+
90
+
91
+ def get_model_state_files(checkpoint_dir):
92
+ return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
93
+
94
+
95
+ def parse_model_states(files):
96
+ zero_model_states = []
97
+ for file in files:
98
+ state_dict = torch.load(file, map_location=device)
99
+
100
+ if BUFFER_NAMES not in state_dict:
101
+ raise ValueError(f"{file} is not a model state checkpoint")
102
+ buffer_names = state_dict[BUFFER_NAMES]
103
+ if debug:
104
+ print("Found buffers:", buffer_names)
105
+
106
+ # recover just the buffers while restoring them to fp32 if they were saved in fp16
107
+ buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
108
+ param_shapes = state_dict[PARAM_SHAPES]
109
+
110
+ # collect parameters that are included in param_shapes
111
+ param_names = []
112
+ for s in param_shapes:
113
+ for name in s.keys():
114
+ param_names.append(name)
115
+
116
+ # update with frozen parameters
117
+ frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
118
+ if frozen_param_shapes is not None:
119
+ if debug:
120
+ print(f"Found frozen_param_shapes: {frozen_param_shapes}")
121
+ param_names += list(frozen_param_shapes.keys())
122
+
123
+ # handle shared params
124
+ shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
125
+
126
+ ds_version = state_dict.get(DS_VERSION, None)
127
+
128
+ frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
129
+
130
+ z_model_state = zero_model_state(buffers=buffers,
131
+ param_shapes=param_shapes,
132
+ shared_params=shared_params,
133
+ ds_version=ds_version,
134
+ frozen_param_shapes=frozen_param_shapes,
135
+ frozen_param_fragments=frozen_param_fragments)
136
+ zero_model_states.append(z_model_state)
137
+
138
+ return zero_model_states
139
+
140
+
141
+ def parse_optim_states(files, ds_checkpoint_dir):
142
+
143
+ total_files = len(files)
144
+ state_dicts = []
145
+ for f in files:
146
+ state_dict = torch.load(f, map_location=device)
147
+ # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
148
+ # and also handle the case where it was already removed by another helper script
149
+ state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
150
+ state_dicts.append(state_dict)
151
+
152
+ if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
153
+ raise ValueError(f"{files[0]} is not a zero checkpoint")
154
+ zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
155
+ world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
156
+
157
+ # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
158
+ # parameters can be different from data parallelism for non-expert parameters. So we can just
159
+ # use the max of the partition_count to get the dp world_size.
160
+
161
+ if type(world_size) is list:
162
+ world_size = max(world_size)
163
+
164
+ if world_size != total_files:
165
+ raise ValueError(
166
+ f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
167
+ "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
168
+ )
169
+
170
+ # the groups are named differently in each stage
171
+ if zero_stage <= 2:
172
+ fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
173
+ elif zero_stage == 3:
174
+ fp32_groups_key = FP32_FLAT_GROUPS
175
+ else:
176
+ raise ValueError(f"unknown zero stage {zero_stage}")
177
+
178
+ if zero_stage <= 2:
179
+ fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
180
+ elif zero_stage == 3:
181
+ # if there is more than one param group, there will be multiple flattened tensors - one
182
+ # flattened tensor per group - for simplicity merge them into a single tensor
183
+ #
184
+ # XXX: could make the script more memory efficient for when there are multiple groups - it
185
+ # will require matching the sub-lists of param_shapes for each param group flattened tensor
186
+
187
+ fp32_flat_groups = [
188
+ torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
189
+ ]
190
+
191
+ return zero_stage, world_size, fp32_flat_groups
192
+
193
+
194
+ def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
195
+ """
196
+ Returns fp32 state_dict reconstructed from ds checkpoint
197
+
198
+ Args:
199
+ - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
200
+
201
+ """
202
+ print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
203
+
204
+ optim_files = get_optim_files(ds_checkpoint_dir)
205
+ zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
206
+ print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
207
+
208
+ model_files = get_model_state_files(ds_checkpoint_dir)
209
+
210
+ zero_model_states = parse_model_states(model_files)
211
+ print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
212
+
213
+ if zero_stage <= 2:
214
+ return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
215
+ exclude_frozen_parameters)
216
+ elif zero_stage == 3:
217
+ return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
218
+ exclude_frozen_parameters)
219
+
220
+
221
+ def _zero2_merge_frozen_params(state_dict, zero_model_states):
222
+ if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
223
+ return
224
+
225
+ frozen_param_shapes = zero_model_states[0].frozen_param_shapes
226
+ frozen_param_fragments = zero_model_states[0].frozen_param_fragments
227
+
228
+ if debug:
229
+ num_elem = sum(s.numel() for s in frozen_param_shapes.values())
230
+ print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
231
+
232
+ wanted_params = len(frozen_param_shapes)
233
+ wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
234
+ avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
235
+ print(f'Frozen params: Have {avail_numel} numels to process.')
236
+ print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
237
+
238
+ total_params = 0
239
+ total_numel = 0
240
+ for name, shape in frozen_param_shapes.items():
241
+ total_params += 1
242
+ unpartitioned_numel = shape.numel()
243
+ total_numel += unpartitioned_numel
244
+
245
+ state_dict[name] = frozen_param_fragments[name]
246
+
247
+ if debug:
248
+ print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
249
+
250
+ print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
251
+
252
+
253
+ def _has_callable(obj, fn):
254
+ attr = getattr(obj, fn, None)
255
+ return callable(attr)
256
+
257
+
258
+ def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
259
+ param_shapes = zero_model_states[0].param_shapes
260
+
261
+ # Reconstruction protocol:
262
+ #
263
+ # XXX: document this
264
+
265
+ if debug:
266
+ for i in range(world_size):
267
+ for j in range(len(fp32_flat_groups[0])):
268
+ print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
269
+
270
+ # XXX: memory usage doubles here (zero2)
271
+ num_param_groups = len(fp32_flat_groups[0])
272
+ merged_single_partition_of_fp32_groups = []
273
+ for i in range(num_param_groups):
274
+ merged_partitions = [sd[i] for sd in fp32_flat_groups]
275
+ full_single_fp32_vector = torch.cat(merged_partitions, 0)
276
+ merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
277
+ avail_numel = sum(
278
+ [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
279
+
280
+ if debug:
281
+ wanted_params = sum([len(shapes) for shapes in param_shapes])
282
+ wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
283
+ # not asserting if there is a mismatch due to possible padding
284
+ print(f"Have {avail_numel} numels to process.")
285
+ print(f"Need {wanted_numel} numels in {wanted_params} params.")
286
+
287
+ # params
288
+ # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
289
+ # out-of-core computing solution
290
+ total_numel = 0
291
+ total_params = 0
292
+ for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
293
+ offset = 0
294
+ avail_numel = full_single_fp32_vector.numel()
295
+ for name, shape in shapes.items():
296
+
297
+ unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
298
+ total_numel += unpartitioned_numel
299
+ total_params += 1
300
+
301
+ if debug:
302
+ print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
303
+ state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
304
+ offset += unpartitioned_numel
305
+
306
+ # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
307
+ # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
308
+ # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
309
+ # live optimizer object, so we are checking that the numbers are within the right range
310
+ align_to = 2 * world_size
311
+
312
+ def zero2_align(x):
313
+ return align_to * math.ceil(x / align_to)
314
+
315
+ if debug:
316
+ print(f"original offset={offset}, avail_numel={avail_numel}")
317
+
318
+ offset = zero2_align(offset)
319
+ avail_numel = zero2_align(avail_numel)
320
+
321
+ if debug:
322
+ print(f"aligned offset={offset}, avail_numel={avail_numel}")
323
+
324
+ # Sanity check
325
+ if offset != avail_numel:
326
+ raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
327
+
328
+ print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
329
+
330
+
331
+ def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
332
+ exclude_frozen_parameters):
333
+ state_dict = OrderedDict()
334
+
335
+ # buffers
336
+ buffers = zero_model_states[0].buffers
337
+ state_dict.update(buffers)
338
+ if debug:
339
+ print(f"added {len(buffers)} buffers")
340
+
341
+ if not exclude_frozen_parameters:
342
+ _zero2_merge_frozen_params(state_dict, zero_model_states)
343
+
344
+ _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
345
+
346
+ # recover shared parameters
347
+ for pair in zero_model_states[0].shared_params:
348
+ if pair[1] in state_dict:
349
+ state_dict[pair[0]] = state_dict[pair[1]]
350
+
351
+ return state_dict
352
+
353
+
354
+ def zero3_partitioned_param_info(unpartitioned_numel, world_size):
355
+ remainder = unpartitioned_numel % world_size
356
+ padding_numel = (world_size - remainder) if remainder else 0
357
+ partitioned_numel = math.ceil(unpartitioned_numel / world_size)
358
+ return partitioned_numel, padding_numel
359
+
360
+
361
+ def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
362
+ if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
363
+ return
364
+
365
+ if debug:
366
+ for i in range(world_size):
367
+ num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
368
+ print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
369
+
370
+ frozen_param_shapes = zero_model_states[0].frozen_param_shapes
371
+ wanted_params = len(frozen_param_shapes)
372
+ wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
373
+ avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
374
+ print(f'Frozen params: Have {avail_numel} numels to process.')
375
+ print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
376
+
377
+ total_params = 0
378
+ total_numel = 0
379
+ for name, shape in zero_model_states[0].frozen_param_shapes.items():
380
+ total_params += 1
381
+ unpartitioned_numel = shape.numel()
382
+ total_numel += unpartitioned_numel
383
+
384
+ param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
385
+ state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
386
+
387
+ partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
388
+
389
+ if debug:
390
+ print(
391
+ f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
392
+ )
393
+
394
+ print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
395
+
396
+
397
+ def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
398
+ param_shapes = zero_model_states[0].param_shapes
399
+ avail_numel = fp32_flat_groups[0].numel() * world_size
400
+ # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
401
+ # param, re-consolidating each param, while dealing with padding if any
402
+
403
+ # merge list of dicts, preserving order
404
+ param_shapes = {k: v for d in param_shapes for k, v in d.items()}
405
+
406
+ if debug:
407
+ for i in range(world_size):
408
+ print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
409
+
410
+ wanted_params = len(param_shapes)
411
+ wanted_numel = sum(shape.numel() for shape in param_shapes.values())
412
+ # not asserting if there is a mismatch due to possible padding
413
+ avail_numel = fp32_flat_groups[0].numel() * world_size
414
+ print(f"Trainable params: Have {avail_numel} numels to process.")
415
+ print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
416
+
417
+ # params
418
+ # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
419
+ # out-of-core computing solution
420
+ offset = 0
421
+ total_numel = 0
422
+ total_params = 0
423
+ for name, shape in param_shapes.items():
424
+
425
+ unpartitioned_numel = shape.numel()
426
+ total_numel += unpartitioned_numel
427
+ total_params += 1
428
+
429
+ partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
430
+
431
+ if debug:
432
+ print(
433
+ f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
434
+ )
435
+
436
+ # XXX: memory usage doubles here
437
+ state_dict[name] = torch.cat(
438
+ tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
439
+ 0).narrow(0, 0, unpartitioned_numel).view(shape)
440
+ offset += partitioned_numel
441
+
442
+ offset *= world_size
443
+
444
+ # Sanity check
445
+ if offset != avail_numel:
446
+ raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
447
+
448
+ print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
449
+
450
+
451
+ def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
452
+ exclude_frozen_parameters):
453
+ state_dict = OrderedDict()
454
+
455
+ # buffers
456
+ buffers = zero_model_states[0].buffers
457
+ state_dict.update(buffers)
458
+ if debug:
459
+ print(f"added {len(buffers)} buffers")
460
+
461
+ if not exclude_frozen_parameters:
462
+ _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
463
+
464
+ _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
465
+
466
+ # recover shared parameters
467
+ for pair in zero_model_states[0].shared_params:
468
+ if pair[1] in state_dict:
469
+ state_dict[pair[0]] = state_dict[pair[1]]
470
+
471
+ return state_dict
472
+
473
+
474
+ def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
475
+ """
476
+ Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
477
+ ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
478
+ via a model hub.
479
+
480
+ Args:
481
+ - ``checkpoint_dir``: path to the desired checkpoint folder
482
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
483
+ - ``exclude_frozen_parameters``: exclude frozen parameters
484
+
485
+ Returns:
486
+ - pytorch ``state_dict``
487
+
488
+ Note: this approach may not work if your application doesn't have sufficient free CPU memory and
489
+ you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
490
+ the checkpoint.
491
+
492
+ A typical usage might be ::
493
+
494
+ from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
495
+ # do the training and checkpoint saving
496
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
497
+ model = model.cpu() # move to cpu
498
+ model.load_state_dict(state_dict)
499
+ # submit to model hub or save the model to share with others
500
+
501
+ In this example the ``model`` will no longer be usable in the deepspeed context of the same
502
+ application. i.e. you will need to re-initialize the deepspeed engine, since
503
+ ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
504
+
505
+ If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
506
+
507
+ """
508
+ if tag is None:
509
+ latest_path = os.path.join(checkpoint_dir, 'latest')
510
+ if os.path.isfile(latest_path):
511
+ with open(latest_path, 'r') as fd:
512
+ tag = fd.read().strip()
513
+ else:
514
+ raise ValueError(f"Unable to find 'latest' file at {latest_path}")
515
+
516
+ ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
517
+
518
+ if not os.path.isdir(ds_checkpoint_dir):
519
+ raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
520
+
521
+ return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
522
+
523
+
524
+ def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None, exclude_frozen_parameters=False):
525
+ """
526
+ Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
527
+ loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
528
+
529
+ Args:
530
+ - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
531
+ - ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
532
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
533
+ - ``exclude_frozen_parameters``: exclude frozen parameters
534
+ """
535
+
536
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
537
+ print(f"Saving fp32 state dict to {output_file}")
538
+ torch.save(state_dict, output_file)
539
+
540
+
541
+ def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
542
+ """
543
+ 1. Put the provided model to cpu
544
+ 2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
545
+ 3. Load it into the provided model
546
+
547
+ Args:
548
+ - ``model``: the model object to update
549
+ - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
550
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
551
+
552
+ Returns:
553
+ - ``model`: modified model
554
+
555
+ Make sure you have plenty of CPU memory available before you call this function. If you don't
556
+ have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
557
+ conveniently placed for you in the checkpoint folder.
558
+
559
+ A typical usage might be ::
560
+
561
+ from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
562
+ model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
563
+ # submit to model hub or save the model to share with others
564
+
565
+ Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
566
+ of the same application. i.e. you will need to re-initialize the deepspeed engine, since
567
+ ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
568
+
569
+ """
570
+ logger.info(f"Extracting fp32 weights")
571
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
572
+
573
+ logger.info(f"Overwriting model with fp32 weights")
574
+ model = model.cpu()
575
+ model.load_state_dict(state_dict, strict=False)
576
+
577
+ return model
578
+
579
+
580
+ if __name__ == "__main__":
581
+
582
+ parser = argparse.ArgumentParser()
583
+ parser.add_argument("checkpoint_dir",
584
+ type=str,
585
+ help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
586
+ parser.add_argument(
587
+ "output_file",
588
+ type=str,
589
+ help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
590
+ parser.add_argument("-t",
591
+ "--tag",
592
+ type=str,
593
+ default=None,
594
+ help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
595
+ parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
596
+ parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
597
+ args = parser.parse_args()
598
+
599
+ debug = args.debug
600
+
601
+ convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
602
+ args.output_file,
603
+ tag=args.tag,
604
+ exclude_frozen_parameters=args.exclude_frozen_parameters)
checkpoint-327/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: nvidia/Llama-3_3-Nemotron-Super-49B-v1
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 0.15.0
checkpoint-327/adapter_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "nvidia/Llama-3_3-Nemotron-Super-49B-v1",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": null,
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": 512,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": [
22
+ "embed_tokens",
23
+ "lm_head"
24
+ ],
25
+ "peft_type": "LORA",
26
+ "r": 256,
27
+ "rank_pattern": {},
28
+ "revision": null,
29
+ "target_modules": [
30
+ "o_proj",
31
+ "gate_proj",
32
+ "q_proj",
33
+ "k_proj",
34
+ "v_proj",
35
+ "up_proj",
36
+ "down_proj"
37
+ ],
38
+ "task_type": "CAUSAL_LM",
39
+ "trainable_token_indices": null,
40
+ "use_dora": false,
41
+ "use_rslora": false
42
+ }
checkpoint-327/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d620bd29d88e3647a2bc20da73d7fe5daacdf69ec4f7bc8816822938990f9ca4
3
+ size 9016826528
checkpoint-327/global_step325/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0aa6143e3b7567d68ae5bac2900c59b05360971f22acd8951e381ae366e7174f
3
+ size 27050164444
checkpoint-327/global_step325/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b99cd7827c26ccf545a1ec7dbdbe94f74707dd6f761fbb236820267b5bfc6b4
3
+ size 27050169884
checkpoint-327/global_step325/mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d9ab4337f0fac6fc42407ce95f838dbaebdc8ad25d72e549fa1d724037edd72
3
+ size 9776788601
checkpoint-327/latest ADDED
@@ -0,0 +1 @@
 
 
1
+ global_step325
checkpoint-327/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2183b1ee437e8522807ae949aeccbd2ecf48cec72acf37954502988e8ac403c7
3
+ size 14512
checkpoint-327/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:969dc41f723773ef09d6e241849358b8c3af28880c6659185ad61f83d16d7dc9
3
+ size 14512
checkpoint-327/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eecf9ae6fa50caf9c774ed15f04010c8de6904c7d2ff6be7c7f21e4e1a0bdec5
3
+ size 1064
checkpoint-327/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": {
17
+ "content": "<|end_of_text|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
checkpoint-327/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
checkpoint-327/tokenizer_config.json ADDED
@@ -0,0 +1,2064 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{{- bos_token }}{%- if messages[0]['role'] == 'system' %}{%- set system_message = messages[0]['content']|trim %}{%- set messages = messages[1:] %}{%- else %}{%- set system_message = \"\" %}{%- endif %}{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}{{- system_message }}{{- \"<|eot_id|>\" }}{%- for message in messages %}{%- if message['role'] == 'assistant' and '</think>' in message['content'] %}{%- set content = message['content'].split('</think>')[-1].lstrip() %}{%- else %}{%- set content = message['content'] %}{%- endif %}{{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n' + content | trim + '<|eot_id|>' }}{%- endfor %}{%- if add_generation_prompt %}{{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}{%- endif %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "extra_special_tokens": {},
2057
+ "model_input_names": [
2058
+ "input_ids",
2059
+ "attention_mask"
2060
+ ],
2061
+ "model_max_length": 131072,
2062
+ "pad_token": "<|end_of_text|>",
2063
+ "tokenizer_class": "PreTrainedTokenizer"
2064
+ }
checkpoint-327/trainer_state.json ADDED
@@ -0,0 +1,2322 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.9786585365853657,
5
+ "eval_steps": 500,
6
+ "global_step": 327,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.009146341463414634,
13
+ "grad_norm": 40.05127716064453,
14
+ "learning_rate": 5.0000000000000004e-08,
15
+ "loss": 5.1282,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.018292682926829267,
20
+ "grad_norm": 39.01039505004883,
21
+ "learning_rate": 1.0000000000000001e-07,
22
+ "loss": 5.0586,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.027439024390243903,
27
+ "grad_norm": 40.20766067504883,
28
+ "learning_rate": 1.5000000000000002e-07,
29
+ "loss": 5.0311,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.036585365853658534,
34
+ "grad_norm": 38.70350646972656,
35
+ "learning_rate": 2.0000000000000002e-07,
36
+ "loss": 5.1598,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.04573170731707317,
41
+ "grad_norm": 39.230979919433594,
42
+ "learning_rate": 2.5000000000000004e-07,
43
+ "loss": 5.0812,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.054878048780487805,
48
+ "grad_norm": 39.45293045043945,
49
+ "learning_rate": 3.0000000000000004e-07,
50
+ "loss": 5.0841,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.06402439024390244,
55
+ "grad_norm": 38.92170333862305,
56
+ "learning_rate": 3.5000000000000004e-07,
57
+ "loss": 5.022,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.07317073170731707,
62
+ "grad_norm": 38.932369232177734,
63
+ "learning_rate": 4.0000000000000003e-07,
64
+ "loss": 5.0876,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.08231707317073171,
69
+ "grad_norm": 39.60245132446289,
70
+ "learning_rate": 4.5000000000000003e-07,
71
+ "loss": 5.0798,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.09146341463414634,
76
+ "grad_norm": 39.53607177734375,
77
+ "learning_rate": 5.000000000000001e-07,
78
+ "loss": 5.0105,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.10060975609756098,
83
+ "grad_norm": 39.50700378417969,
84
+ "learning_rate": 5.5e-07,
85
+ "loss": 4.9951,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.10975609756097561,
90
+ "grad_norm": 39.52376174926758,
91
+ "learning_rate": 6.000000000000001e-07,
92
+ "loss": 4.9163,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.11890243902439024,
97
+ "grad_norm": 39.15214157104492,
98
+ "learning_rate": 6.5e-07,
99
+ "loss": 4.9634,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.12804878048780488,
104
+ "grad_norm": 37.795066833496094,
105
+ "learning_rate": 7.000000000000001e-07,
106
+ "loss": 4.819,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.13719512195121952,
111
+ "grad_norm": 38.23014450073242,
112
+ "learning_rate": 7.5e-07,
113
+ "loss": 4.8756,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.14634146341463414,
118
+ "grad_norm": 38.57551574707031,
119
+ "learning_rate": 8.000000000000001e-07,
120
+ "loss": 4.81,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.15548780487804878,
125
+ "grad_norm": 36.06121063232422,
126
+ "learning_rate": 8.500000000000001e-07,
127
+ "loss": 4.7901,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.16463414634146342,
132
+ "grad_norm": 34.38008117675781,
133
+ "learning_rate": 9.000000000000001e-07,
134
+ "loss": 4.5775,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.17378048780487804,
139
+ "grad_norm": 32.60890579223633,
140
+ "learning_rate": 9.500000000000001e-07,
141
+ "loss": 4.3737,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.18292682926829268,
146
+ "grad_norm": 31.983110427856445,
147
+ "learning_rate": 1.0000000000000002e-06,
148
+ "loss": 4.3773,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.19207317073170732,
153
+ "grad_norm": 27.69571876525879,
154
+ "learning_rate": 1.0500000000000001e-06,
155
+ "loss": 4.1276,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.20121951219512196,
160
+ "grad_norm": 26.542314529418945,
161
+ "learning_rate": 1.1e-06,
162
+ "loss": 4.0641,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.21036585365853658,
167
+ "grad_norm": 23.26603126525879,
168
+ "learning_rate": 1.1500000000000002e-06,
169
+ "loss": 4.0197,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.21951219512195122,
174
+ "grad_norm": 21.04385757446289,
175
+ "learning_rate": 1.2000000000000002e-06,
176
+ "loss": 4.0179,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.22865853658536586,
181
+ "grad_norm": 19.790103912353516,
182
+ "learning_rate": 1.25e-06,
183
+ "loss": 3.8334,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.23780487804878048,
188
+ "grad_norm": 18.2396183013916,
189
+ "learning_rate": 1.3e-06,
190
+ "loss": 3.7027,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.24695121951219512,
195
+ "grad_norm": 18.725860595703125,
196
+ "learning_rate": 1.3500000000000002e-06,
197
+ "loss": 3.7268,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.25609756097560976,
202
+ "grad_norm": 18.91561508178711,
203
+ "learning_rate": 1.4000000000000001e-06,
204
+ "loss": 3.52,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.2652439024390244,
209
+ "grad_norm": 18.196651458740234,
210
+ "learning_rate": 1.45e-06,
211
+ "loss": 3.4765,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.27439024390243905,
216
+ "grad_norm": 17.778606414794922,
217
+ "learning_rate": 1.5e-06,
218
+ "loss": 3.3573,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.28353658536585363,
223
+ "grad_norm": 16.23012924194336,
224
+ "learning_rate": 1.5500000000000002e-06,
225
+ "loss": 3.2783,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.2926829268292683,
230
+ "grad_norm": 15.836565017700195,
231
+ "learning_rate": 1.6000000000000001e-06,
232
+ "loss": 3.2319,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.3018292682926829,
237
+ "grad_norm": 11.919289588928223,
238
+ "learning_rate": 1.6500000000000003e-06,
239
+ "loss": 3.1345,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.31097560975609756,
244
+ "grad_norm": 11.086843490600586,
245
+ "learning_rate": 1.7000000000000002e-06,
246
+ "loss": 3.1153,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.3201219512195122,
251
+ "grad_norm": 7.563486576080322,
252
+ "learning_rate": 1.75e-06,
253
+ "loss": 2.9784,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.32926829268292684,
258
+ "grad_norm": 7.60545539855957,
259
+ "learning_rate": 1.8000000000000001e-06,
260
+ "loss": 2.8568,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.3384146341463415,
265
+ "grad_norm": 7.071218013763428,
266
+ "learning_rate": 1.85e-06,
267
+ "loss": 2.8879,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.3475609756097561,
272
+ "grad_norm": 8.200672149658203,
273
+ "learning_rate": 1.9000000000000002e-06,
274
+ "loss": 2.7437,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.3567073170731707,
279
+ "grad_norm": 12.079374313354492,
280
+ "learning_rate": 1.9500000000000004e-06,
281
+ "loss": 2.7589,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.36585365853658536,
286
+ "grad_norm": 12.21938705444336,
287
+ "learning_rate": 2.0000000000000003e-06,
288
+ "loss": 2.7098,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.375,
293
+ "grad_norm": 10.224228858947754,
294
+ "learning_rate": 2.05e-06,
295
+ "loss": 2.6803,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.38414634146341464,
300
+ "grad_norm": 10.054616928100586,
301
+ "learning_rate": 2.1000000000000002e-06,
302
+ "loss": 2.4658,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.3932926829268293,
307
+ "grad_norm": 8.074049949645996,
308
+ "learning_rate": 2.15e-06,
309
+ "loss": 2.6341,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.4024390243902439,
314
+ "grad_norm": 5.721987724304199,
315
+ "learning_rate": 2.2e-06,
316
+ "loss": 2.3848,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.4115853658536585,
321
+ "grad_norm": 4.646566390991211,
322
+ "learning_rate": 2.25e-06,
323
+ "loss": 2.4323,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.42073170731707316,
328
+ "grad_norm": 4.591104984283447,
329
+ "learning_rate": 2.3000000000000004e-06,
330
+ "loss": 2.4022,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.4298780487804878,
335
+ "grad_norm": 4.822715759277344,
336
+ "learning_rate": 2.35e-06,
337
+ "loss": 2.2768,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.43902439024390244,
342
+ "grad_norm": 5.176568984985352,
343
+ "learning_rate": 2.4000000000000003e-06,
344
+ "loss": 2.281,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.4481707317073171,
349
+ "grad_norm": 4.731242656707764,
350
+ "learning_rate": 2.4500000000000003e-06,
351
+ "loss": 2.235,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.4573170731707317,
356
+ "grad_norm": 4.6343865394592285,
357
+ "learning_rate": 2.5e-06,
358
+ "loss": 2.1465,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.46646341463414637,
363
+ "grad_norm": 4.669382095336914,
364
+ "learning_rate": 2.55e-06,
365
+ "loss": 2.0969,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.47560975609756095,
370
+ "grad_norm": 4.207769870758057,
371
+ "learning_rate": 2.6e-06,
372
+ "loss": 2.0308,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.4847560975609756,
377
+ "grad_norm": 5.222470760345459,
378
+ "learning_rate": 2.6500000000000005e-06,
379
+ "loss": 1.9445,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.49390243902439024,
384
+ "grad_norm": 5.10925817489624,
385
+ "learning_rate": 2.7000000000000004e-06,
386
+ "loss": 1.7763,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.5030487804878049,
391
+ "grad_norm": 4.8151044845581055,
392
+ "learning_rate": 2.7500000000000004e-06,
393
+ "loss": 1.7661,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.5121951219512195,
398
+ "grad_norm": 6.155700206756592,
399
+ "learning_rate": 2.8000000000000003e-06,
400
+ "loss": 1.6665,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.5213414634146342,
405
+ "grad_norm": 4.719021320343018,
406
+ "learning_rate": 2.85e-06,
407
+ "loss": 1.5532,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.5304878048780488,
412
+ "grad_norm": 4.591799259185791,
413
+ "learning_rate": 2.9e-06,
414
+ "loss": 1.5244,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.5396341463414634,
419
+ "grad_norm": 5.483795642852783,
420
+ "learning_rate": 2.95e-06,
421
+ "loss": 1.3816,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.5487804878048781,
426
+ "grad_norm": 4.32553768157959,
427
+ "learning_rate": 3e-06,
428
+ "loss": 1.4268,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.5579268292682927,
433
+ "grad_norm": 8.296231269836426,
434
+ "learning_rate": 3.05e-06,
435
+ "loss": 1.2887,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.5670731707317073,
440
+ "grad_norm": 5.07594108581543,
441
+ "learning_rate": 3.1000000000000004e-06,
442
+ "loss": 1.228,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.5762195121951219,
447
+ "grad_norm": 8.427435874938965,
448
+ "learning_rate": 3.1500000000000003e-06,
449
+ "loss": 1.1724,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.5853658536585366,
454
+ "grad_norm": 22.45092010498047,
455
+ "learning_rate": 3.2000000000000003e-06,
456
+ "loss": 1.0871,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.5945121951219512,
461
+ "grad_norm": 20.67412567138672,
462
+ "learning_rate": 3.2500000000000002e-06,
463
+ "loss": 1.0108,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.6036585365853658,
468
+ "grad_norm": 4.921634674072266,
469
+ "learning_rate": 3.3000000000000006e-06,
470
+ "loss": 0.9775,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.6128048780487805,
475
+ "grad_norm": 4.477286338806152,
476
+ "learning_rate": 3.3500000000000005e-06,
477
+ "loss": 0.9554,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.6219512195121951,
482
+ "grad_norm": 8.190194129943848,
483
+ "learning_rate": 3.4000000000000005e-06,
484
+ "loss": 0.8583,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.6310975609756098,
489
+ "grad_norm": 29.21201515197754,
490
+ "learning_rate": 3.45e-06,
491
+ "loss": 0.8499,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.6402439024390244,
496
+ "grad_norm": 33.81047439575195,
497
+ "learning_rate": 3.5e-06,
498
+ "loss": 0.858,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.649390243902439,
503
+ "grad_norm": 3.5125606060028076,
504
+ "learning_rate": 3.5500000000000003e-06,
505
+ "loss": 0.7227,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.6585365853658537,
510
+ "grad_norm": 18.493423461914062,
511
+ "learning_rate": 3.6000000000000003e-06,
512
+ "loss": 0.7447,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.6676829268292683,
517
+ "grad_norm": 24.923927307128906,
518
+ "learning_rate": 3.65e-06,
519
+ "loss": 0.8423,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.676829268292683,
524
+ "grad_norm": 9.870631217956543,
525
+ "learning_rate": 3.7e-06,
526
+ "loss": 0.6934,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.6859756097560976,
531
+ "grad_norm": 20.598569869995117,
532
+ "learning_rate": 3.7500000000000005e-06,
533
+ "loss": 0.7005,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.6951219512195121,
538
+ "grad_norm": 30.662466049194336,
539
+ "learning_rate": 3.8000000000000005e-06,
540
+ "loss": 0.6226,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.7042682926829268,
545
+ "grad_norm": 28.930774688720703,
546
+ "learning_rate": 3.85e-06,
547
+ "loss": 0.6357,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.7134146341463414,
552
+ "grad_norm": 7.140467166900635,
553
+ "learning_rate": 3.900000000000001e-06,
554
+ "loss": 0.6129,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.7225609756097561,
559
+ "grad_norm": 6.322911739349365,
560
+ "learning_rate": 3.95e-06,
561
+ "loss": 0.6086,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.7317073170731707,
566
+ "grad_norm": 5.404141426086426,
567
+ "learning_rate": 4.000000000000001e-06,
568
+ "loss": 0.5986,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.7408536585365854,
573
+ "grad_norm": 24.445228576660156,
574
+ "learning_rate": 4.05e-06,
575
+ "loss": 0.5932,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.75,
580
+ "grad_norm": 14.275381088256836,
581
+ "learning_rate": 4.1e-06,
582
+ "loss": 0.5286,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.7591463414634146,
587
+ "grad_norm": 9.77132511138916,
588
+ "learning_rate": 4.15e-06,
589
+ "loss": 0.4814,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.7682926829268293,
594
+ "grad_norm": 11.043930053710938,
595
+ "learning_rate": 4.2000000000000004e-06,
596
+ "loss": 0.4953,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.7774390243902439,
601
+ "grad_norm": 3.1333775520324707,
602
+ "learning_rate": 4.25e-06,
603
+ "loss": 0.4794,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.7865853658536586,
608
+ "grad_norm": 9.50448989868164,
609
+ "learning_rate": 4.3e-06,
610
+ "loss": 0.4451,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.7957317073170732,
615
+ "grad_norm": 5.867074489593506,
616
+ "learning_rate": 4.350000000000001e-06,
617
+ "loss": 0.4224,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 0.8048780487804879,
622
+ "grad_norm": 12.556106567382812,
623
+ "learning_rate": 4.4e-06,
624
+ "loss": 0.4224,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 0.8140243902439024,
629
+ "grad_norm": 7.916622638702393,
630
+ "learning_rate": 4.450000000000001e-06,
631
+ "loss": 0.4091,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 0.823170731707317,
636
+ "grad_norm": 2.970932722091675,
637
+ "learning_rate": 4.5e-06,
638
+ "loss": 0.4181,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 0.8323170731707317,
643
+ "grad_norm": 17.468870162963867,
644
+ "learning_rate": 4.5500000000000005e-06,
645
+ "loss": 0.4031,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 0.8414634146341463,
650
+ "grad_norm": 15.861083984375,
651
+ "learning_rate": 4.600000000000001e-06,
652
+ "loss": 0.3604,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 0.850609756097561,
657
+ "grad_norm": 6.715958118438721,
658
+ "learning_rate": 4.65e-06,
659
+ "loss": 0.3489,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 0.8597560975609756,
664
+ "grad_norm": 5.439844608306885,
665
+ "learning_rate": 4.7e-06,
666
+ "loss": 0.3339,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 0.8689024390243902,
671
+ "grad_norm": 4.650434494018555,
672
+ "learning_rate": 4.75e-06,
673
+ "loss": 0.3189,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 0.8780487804878049,
678
+ "grad_norm": 15.319528579711914,
679
+ "learning_rate": 4.800000000000001e-06,
680
+ "loss": 0.3347,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 0.8871951219512195,
685
+ "grad_norm": 5.151925563812256,
686
+ "learning_rate": 4.85e-06,
687
+ "loss": 0.3043,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 0.8963414634146342,
692
+ "grad_norm": 6.351178169250488,
693
+ "learning_rate": 4.9000000000000005e-06,
694
+ "loss": 0.2939,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 0.9054878048780488,
699
+ "grad_norm": 3.942911148071289,
700
+ "learning_rate": 4.95e-06,
701
+ "loss": 0.2887,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 0.9146341463414634,
706
+ "grad_norm": 3.0885493755340576,
707
+ "learning_rate": 5e-06,
708
+ "loss": 0.2992,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 0.9237804878048781,
713
+ "grad_norm": 7.023274898529053,
714
+ "learning_rate": 4.999959803423605e-06,
715
+ "loss": 0.2607,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 0.9329268292682927,
720
+ "grad_norm": 8.774216651916504,
721
+ "learning_rate": 4.9998392149870315e-06,
722
+ "loss": 0.2674,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 0.9420731707317073,
727
+ "grad_norm": 3.5439791679382324,
728
+ "learning_rate": 4.999638238568072e-06,
729
+ "loss": 0.2602,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 0.9512195121951219,
734
+ "grad_norm": 7.669381618499756,
735
+ "learning_rate": 4.999356880629579e-06,
736
+ "loss": 0.2718,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 0.9603658536585366,
741
+ "grad_norm": 6.9407854080200195,
742
+ "learning_rate": 4.998995150219252e-06,
743
+ "loss": 0.2494,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 0.9695121951219512,
748
+ "grad_norm": 12.144411087036133,
749
+ "learning_rate": 4.998553058969352e-06,
750
+ "loss": 0.2297,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 0.9786585365853658,
755
+ "grad_norm": 6.956138610839844,
756
+ "learning_rate": 4.998030621096322e-06,
757
+ "loss": 0.2386,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 0.9878048780487805,
762
+ "grad_norm": 8.304037094116211,
763
+ "learning_rate": 4.997427853400333e-06,
764
+ "loss": 0.23,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 0.9969512195121951,
769
+ "grad_norm": 7.031365394592285,
770
+ "learning_rate": 4.996744775264743e-06,
771
+ "loss": 0.2346,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 1.0,
776
+ "grad_norm": 7.031365394592285,
777
+ "learning_rate": 4.9959814086554735e-06,
778
+ "loss": 0.0739,
779
+ "step": 110
780
+ },
781
+ {
782
+ "epoch": 1.0091463414634145,
783
+ "grad_norm": 2.084608793258667,
784
+ "learning_rate": 4.995137778120306e-06,
785
+ "loss": 0.2422,
786
+ "step": 111
787
+ },
788
+ {
789
+ "epoch": 1.0182926829268293,
790
+ "grad_norm": 38.12245178222656,
791
+ "learning_rate": 4.994213910788085e-06,
792
+ "loss": 0.1992,
793
+ "step": 112
794
+ },
795
+ {
796
+ "epoch": 1.0274390243902438,
797
+ "grad_norm": 2.817565441131592,
798
+ "learning_rate": 4.993209836367856e-06,
799
+ "loss": 0.1882,
800
+ "step": 113
801
+ },
802
+ {
803
+ "epoch": 1.0365853658536586,
804
+ "grad_norm": 11.774249076843262,
805
+ "learning_rate": 4.9921255871479e-06,
806
+ "loss": 0.2235,
807
+ "step": 114
808
+ },
809
+ {
810
+ "epoch": 1.045731707317073,
811
+ "grad_norm": 2.3362019062042236,
812
+ "learning_rate": 4.9909611979947046e-06,
813
+ "loss": 0.1875,
814
+ "step": 115
815
+ },
816
+ {
817
+ "epoch": 1.0548780487804879,
818
+ "grad_norm": 1.9516818523406982,
819
+ "learning_rate": 4.989716706351835e-06,
820
+ "loss": 0.1858,
821
+ "step": 116
822
+ },
823
+ {
824
+ "epoch": 1.0640243902439024,
825
+ "grad_norm": 1.5484645366668701,
826
+ "learning_rate": 4.9883921522387336e-06,
827
+ "loss": 0.1845,
828
+ "step": 117
829
+ },
830
+ {
831
+ "epoch": 1.0731707317073171,
832
+ "grad_norm": 7.430396556854248,
833
+ "learning_rate": 4.986987578249433e-06,
834
+ "loss": 0.184,
835
+ "step": 118
836
+ },
837
+ {
838
+ "epoch": 1.0823170731707317,
839
+ "grad_norm": 2.0725948810577393,
840
+ "learning_rate": 4.9855030295511845e-06,
841
+ "loss": 0.177,
842
+ "step": 119
843
+ },
844
+ {
845
+ "epoch": 1.0914634146341464,
846
+ "grad_norm": 4.836520671844482,
847
+ "learning_rate": 4.98393855388301e-06,
848
+ "loss": 0.1744,
849
+ "step": 120
850
+ },
851
+ {
852
+ "epoch": 1.100609756097561,
853
+ "grad_norm": 5.22581672668457,
854
+ "learning_rate": 4.982294201554162e-06,
855
+ "loss": 0.1599,
856
+ "step": 121
857
+ },
858
+ {
859
+ "epoch": 1.1097560975609757,
860
+ "grad_norm": 5.406208038330078,
861
+ "learning_rate": 4.980570025442507e-06,
862
+ "loss": 0.1645,
863
+ "step": 122
864
+ },
865
+ {
866
+ "epoch": 1.1189024390243902,
867
+ "grad_norm": 8.736640930175781,
868
+ "learning_rate": 4.978766080992827e-06,
869
+ "loss": 0.1943,
870
+ "step": 123
871
+ },
872
+ {
873
+ "epoch": 1.1280487804878048,
874
+ "grad_norm": 9.184198379516602,
875
+ "learning_rate": 4.976882426215035e-06,
876
+ "loss": 0.1753,
877
+ "step": 124
878
+ },
879
+ {
880
+ "epoch": 1.1371951219512195,
881
+ "grad_norm": 5.317800521850586,
882
+ "learning_rate": 4.974919121682307e-06,
883
+ "loss": 0.1897,
884
+ "step": 125
885
+ },
886
+ {
887
+ "epoch": 1.146341463414634,
888
+ "grad_norm": 11.803364753723145,
889
+ "learning_rate": 4.972876230529143e-06,
890
+ "loss": 0.1516,
891
+ "step": 126
892
+ },
893
+ {
894
+ "epoch": 1.1554878048780488,
895
+ "grad_norm": 31.74310302734375,
896
+ "learning_rate": 4.9707538184493255e-06,
897
+ "loss": 0.1947,
898
+ "step": 127
899
+ },
900
+ {
901
+ "epoch": 1.1646341463414633,
902
+ "grad_norm": 1.956932783126831,
903
+ "learning_rate": 4.968551953693813e-06,
904
+ "loss": 0.1708,
905
+ "step": 128
906
+ },
907
+ {
908
+ "epoch": 1.173780487804878,
909
+ "grad_norm": 4.64445686340332,
910
+ "learning_rate": 4.966270707068548e-06,
911
+ "loss": 0.1711,
912
+ "step": 129
913
+ },
914
+ {
915
+ "epoch": 1.1829268292682926,
916
+ "grad_norm": 4.442819595336914,
917
+ "learning_rate": 4.963910151932171e-06,
918
+ "loss": 0.1572,
919
+ "step": 130
920
+ },
921
+ {
922
+ "epoch": 1.1920731707317074,
923
+ "grad_norm": 1.9702759981155396,
924
+ "learning_rate": 4.961470364193673e-06,
925
+ "loss": 0.1364,
926
+ "step": 131
927
+ },
928
+ {
929
+ "epoch": 1.201219512195122,
930
+ "grad_norm": 7.816587448120117,
931
+ "learning_rate": 4.9589514223099425e-06,
932
+ "loss": 0.1624,
933
+ "step": 132
934
+ },
935
+ {
936
+ "epoch": 1.2103658536585367,
937
+ "grad_norm": 61.18424606323242,
938
+ "learning_rate": 4.956353407283252e-06,
939
+ "loss": 0.26,
940
+ "step": 133
941
+ },
942
+ {
943
+ "epoch": 1.2195121951219512,
944
+ "grad_norm": 15.649847984313965,
945
+ "learning_rate": 4.9536764026586505e-06,
946
+ "loss": 0.1543,
947
+ "step": 134
948
+ },
949
+ {
950
+ "epoch": 1.228658536585366,
951
+ "grad_norm": 2.249363660812378,
952
+ "learning_rate": 4.950920494521274e-06,
953
+ "loss": 0.152,
954
+ "step": 135
955
+ },
956
+ {
957
+ "epoch": 1.2378048780487805,
958
+ "grad_norm": 4.055661678314209,
959
+ "learning_rate": 4.948085771493579e-06,
960
+ "loss": 0.1402,
961
+ "step": 136
962
+ },
963
+ {
964
+ "epoch": 1.2469512195121952,
965
+ "grad_norm": 2.2803292274475098,
966
+ "learning_rate": 4.945172324732496e-06,
967
+ "loss": 0.1427,
968
+ "step": 137
969
+ },
970
+ {
971
+ "epoch": 1.2560975609756098,
972
+ "grad_norm": 2.5540456771850586,
973
+ "learning_rate": 4.942180247926492e-06,
974
+ "loss": 0.143,
975
+ "step": 138
976
+ },
977
+ {
978
+ "epoch": 1.2652439024390243,
979
+ "grad_norm": 8.80340576171875,
980
+ "learning_rate": 4.939109637292563e-06,
981
+ "loss": 0.1569,
982
+ "step": 139
983
+ },
984
+ {
985
+ "epoch": 1.274390243902439,
986
+ "grad_norm": 3.1077523231506348,
987
+ "learning_rate": 4.935960591573136e-06,
988
+ "loss": 0.1313,
989
+ "step": 140
990
+ },
991
+ {
992
+ "epoch": 1.2835365853658536,
993
+ "grad_norm": 1.2506815195083618,
994
+ "learning_rate": 4.932733212032896e-06,
995
+ "loss": 0.137,
996
+ "step": 141
997
+ },
998
+ {
999
+ "epoch": 1.2926829268292683,
1000
+ "grad_norm": 2.4397666454315186,
1001
+ "learning_rate": 4.929427602455532e-06,
1002
+ "loss": 0.1408,
1003
+ "step": 142
1004
+ },
1005
+ {
1006
+ "epoch": 1.3018292682926829,
1007
+ "grad_norm": 1.7658663988113403,
1008
+ "learning_rate": 4.926043869140392e-06,
1009
+ "loss": 0.133,
1010
+ "step": 143
1011
+ },
1012
+ {
1013
+ "epoch": 1.3109756097560976,
1014
+ "grad_norm": 1.0473108291625977,
1015
+ "learning_rate": 4.922582120899072e-06,
1016
+ "loss": 0.1358,
1017
+ "step": 144
1018
+ },
1019
+ {
1020
+ "epoch": 1.3201219512195121,
1021
+ "grad_norm": 5.566607475280762,
1022
+ "learning_rate": 4.919042469051916e-06,
1023
+ "loss": 0.1237,
1024
+ "step": 145
1025
+ },
1026
+ {
1027
+ "epoch": 1.329268292682927,
1028
+ "grad_norm": 1.0360139608383179,
1029
+ "learning_rate": 4.915425027424429e-06,
1030
+ "loss": 0.1274,
1031
+ "step": 146
1032
+ },
1033
+ {
1034
+ "epoch": 1.3384146341463414,
1035
+ "grad_norm": 1.9091176986694336,
1036
+ "learning_rate": 4.911729912343631e-06,
1037
+ "loss": 0.1439,
1038
+ "step": 147
1039
+ },
1040
+ {
1041
+ "epoch": 1.3475609756097562,
1042
+ "grad_norm": 1.5727638006210327,
1043
+ "learning_rate": 4.907957242634299e-06,
1044
+ "loss": 0.1259,
1045
+ "step": 148
1046
+ },
1047
+ {
1048
+ "epoch": 1.3567073170731707,
1049
+ "grad_norm": 1.0574792623519897,
1050
+ "learning_rate": 4.9041071396151585e-06,
1051
+ "loss": 0.142,
1052
+ "step": 149
1053
+ },
1054
+ {
1055
+ "epoch": 1.3658536585365852,
1056
+ "grad_norm": 8.020130157470703,
1057
+ "learning_rate": 4.900179727094978e-06,
1058
+ "loss": 0.1392,
1059
+ "step": 150
1060
+ },
1061
+ {
1062
+ "epoch": 1.375,
1063
+ "grad_norm": 3.156255006790161,
1064
+ "learning_rate": 4.896175131368587e-06,
1065
+ "loss": 0.152,
1066
+ "step": 151
1067
+ },
1068
+ {
1069
+ "epoch": 1.3841463414634148,
1070
+ "grad_norm": 2.3956990242004395,
1071
+ "learning_rate": 4.892093481212817e-06,
1072
+ "loss": 0.1244,
1073
+ "step": 152
1074
+ },
1075
+ {
1076
+ "epoch": 1.3932926829268293,
1077
+ "grad_norm": 2.6058578491210938,
1078
+ "learning_rate": 4.887934907882357e-06,
1079
+ "loss": 0.1271,
1080
+ "step": 153
1081
+ },
1082
+ {
1083
+ "epoch": 1.4024390243902438,
1084
+ "grad_norm": 1.7173289060592651,
1085
+ "learning_rate": 4.883699545105535e-06,
1086
+ "loss": 0.1257,
1087
+ "step": 154
1088
+ },
1089
+ {
1090
+ "epoch": 1.4115853658536586,
1091
+ "grad_norm": 2.2237367630004883,
1092
+ "learning_rate": 4.8793875290800186e-06,
1093
+ "loss": 0.127,
1094
+ "step": 155
1095
+ },
1096
+ {
1097
+ "epoch": 1.420731707317073,
1098
+ "grad_norm": 6.997623920440674,
1099
+ "learning_rate": 4.874998998468433e-06,
1100
+ "loss": 0.1454,
1101
+ "step": 156
1102
+ },
1103
+ {
1104
+ "epoch": 1.4298780487804879,
1105
+ "grad_norm": 10.645139694213867,
1106
+ "learning_rate": 4.870534094393903e-06,
1107
+ "loss": 0.1402,
1108
+ "step": 157
1109
+ },
1110
+ {
1111
+ "epoch": 1.4390243902439024,
1112
+ "grad_norm": 1.5808072090148926,
1113
+ "learning_rate": 4.865992960435514e-06,
1114
+ "loss": 0.1156,
1115
+ "step": 158
1116
+ },
1117
+ {
1118
+ "epoch": 1.4481707317073171,
1119
+ "grad_norm": 0.990803062915802,
1120
+ "learning_rate": 4.861375742623697e-06,
1121
+ "loss": 0.1286,
1122
+ "step": 159
1123
+ },
1124
+ {
1125
+ "epoch": 1.4573170731707317,
1126
+ "grad_norm": 1.5008662939071655,
1127
+ "learning_rate": 4.856682589435531e-06,
1128
+ "loss": 0.1282,
1129
+ "step": 160
1130
+ },
1131
+ {
1132
+ "epoch": 1.4664634146341464,
1133
+ "grad_norm": 1.772304892539978,
1134
+ "learning_rate": 4.851913651789968e-06,
1135
+ "loss": 0.1308,
1136
+ "step": 161
1137
+ },
1138
+ {
1139
+ "epoch": 1.475609756097561,
1140
+ "grad_norm": 1.201061487197876,
1141
+ "learning_rate": 4.847069083042982e-06,
1142
+ "loss": 0.1198,
1143
+ "step": 162
1144
+ },
1145
+ {
1146
+ "epoch": 1.4847560975609757,
1147
+ "grad_norm": 0.6147828698158264,
1148
+ "learning_rate": 4.8421490389826344e-06,
1149
+ "loss": 0.1138,
1150
+ "step": 163
1151
+ },
1152
+ {
1153
+ "epoch": 1.4939024390243902,
1154
+ "grad_norm": 1.3990256786346436,
1155
+ "learning_rate": 4.837153677824068e-06,
1156
+ "loss": 0.1205,
1157
+ "step": 164
1158
+ },
1159
+ {
1160
+ "epoch": 1.5030487804878048,
1161
+ "grad_norm": 1.6977574825286865,
1162
+ "learning_rate": 4.832083160204414e-06,
1163
+ "loss": 0.1128,
1164
+ "step": 165
1165
+ },
1166
+ {
1167
+ "epoch": 1.5121951219512195,
1168
+ "grad_norm": 2.4056453704833984,
1169
+ "learning_rate": 4.826937649177632e-06,
1170
+ "loss": 0.1184,
1171
+ "step": 166
1172
+ },
1173
+ {
1174
+ "epoch": 1.5213414634146343,
1175
+ "grad_norm": 2.7455694675445557,
1176
+ "learning_rate": 4.821717310209265e-06,
1177
+ "loss": 0.123,
1178
+ "step": 167
1179
+ },
1180
+ {
1181
+ "epoch": 1.5304878048780488,
1182
+ "grad_norm": 1.8243584632873535,
1183
+ "learning_rate": 4.816422311171115e-06,
1184
+ "loss": 0.1198,
1185
+ "step": 168
1186
+ },
1187
+ {
1188
+ "epoch": 1.5396341463414633,
1189
+ "grad_norm": 0.8920577764511108,
1190
+ "learning_rate": 4.811052822335849e-06,
1191
+ "loss": 0.1088,
1192
+ "step": 169
1193
+ },
1194
+ {
1195
+ "epoch": 1.548780487804878,
1196
+ "grad_norm": 1.6639117002487183,
1197
+ "learning_rate": 4.805609016371522e-06,
1198
+ "loss": 0.1231,
1199
+ "step": 170
1200
+ },
1201
+ {
1202
+ "epoch": 1.5579268292682928,
1203
+ "grad_norm": 1.383026123046875,
1204
+ "learning_rate": 4.800091068336024e-06,
1205
+ "loss": 0.1207,
1206
+ "step": 171
1207
+ },
1208
+ {
1209
+ "epoch": 1.5670731707317072,
1210
+ "grad_norm": 1.6599416732788086,
1211
+ "learning_rate": 4.79449915567145e-06,
1212
+ "loss": 0.1206,
1213
+ "step": 172
1214
+ },
1215
+ {
1216
+ "epoch": 1.576219512195122,
1217
+ "grad_norm": 1.5868676900863647,
1218
+ "learning_rate": 4.788833458198395e-06,
1219
+ "loss": 0.1158,
1220
+ "step": 173
1221
+ },
1222
+ {
1223
+ "epoch": 1.5853658536585367,
1224
+ "grad_norm": 1.0154211521148682,
1225
+ "learning_rate": 4.783094158110175e-06,
1226
+ "loss": 0.1091,
1227
+ "step": 174
1228
+ },
1229
+ {
1230
+ "epoch": 1.5945121951219512,
1231
+ "grad_norm": 2.1514394283294678,
1232
+ "learning_rate": 4.7772814399669585e-06,
1233
+ "loss": 0.1109,
1234
+ "step": 175
1235
+ },
1236
+ {
1237
+ "epoch": 1.6036585365853657,
1238
+ "grad_norm": 0.7475085258483887,
1239
+ "learning_rate": 4.7713954906898415e-06,
1240
+ "loss": 0.1162,
1241
+ "step": 176
1242
+ },
1243
+ {
1244
+ "epoch": 1.6128048780487805,
1245
+ "grad_norm": 0.8523163795471191,
1246
+ "learning_rate": 4.7654364995548325e-06,
1247
+ "loss": 0.1238,
1248
+ "step": 177
1249
+ },
1250
+ {
1251
+ "epoch": 1.6219512195121952,
1252
+ "grad_norm": 1.5456233024597168,
1253
+ "learning_rate": 4.759404658186765e-06,
1254
+ "loss": 0.1163,
1255
+ "step": 178
1256
+ },
1257
+ {
1258
+ "epoch": 1.6310975609756098,
1259
+ "grad_norm": 1.123340129852295,
1260
+ "learning_rate": 4.753300160553137e-06,
1261
+ "loss": 0.1104,
1262
+ "step": 179
1263
+ },
1264
+ {
1265
+ "epoch": 1.6402439024390243,
1266
+ "grad_norm": 1.16841721534729,
1267
+ "learning_rate": 4.747123202957871e-06,
1268
+ "loss": 0.1099,
1269
+ "step": 180
1270
+ },
1271
+ {
1272
+ "epoch": 1.649390243902439,
1273
+ "grad_norm": 2.025221109390259,
1274
+ "learning_rate": 4.740873984035009e-06,
1275
+ "loss": 0.1157,
1276
+ "step": 181
1277
+ },
1278
+ {
1279
+ "epoch": 1.6585365853658538,
1280
+ "grad_norm": 3.876469373703003,
1281
+ "learning_rate": 4.734552704742314e-06,
1282
+ "loss": 0.1122,
1283
+ "step": 182
1284
+ },
1285
+ {
1286
+ "epoch": 1.6676829268292683,
1287
+ "grad_norm": 1.5562145709991455,
1288
+ "learning_rate": 4.728159568354814e-06,
1289
+ "loss": 0.1127,
1290
+ "step": 183
1291
+ },
1292
+ {
1293
+ "epoch": 1.6768292682926829,
1294
+ "grad_norm": 1.4691755771636963,
1295
+ "learning_rate": 4.721694780458266e-06,
1296
+ "loss": 0.1182,
1297
+ "step": 184
1298
+ },
1299
+ {
1300
+ "epoch": 1.6859756097560976,
1301
+ "grad_norm": 1.9529973268508911,
1302
+ "learning_rate": 4.715158548942541e-06,
1303
+ "loss": 0.1153,
1304
+ "step": 185
1305
+ },
1306
+ {
1307
+ "epoch": 1.6951219512195121,
1308
+ "grad_norm": 1.9065771102905273,
1309
+ "learning_rate": 4.708551083994944e-06,
1310
+ "loss": 0.1163,
1311
+ "step": 186
1312
+ },
1313
+ {
1314
+ "epoch": 1.7042682926829267,
1315
+ "grad_norm": 1.0964735746383667,
1316
+ "learning_rate": 4.701872598093452e-06,
1317
+ "loss": 0.114,
1318
+ "step": 187
1319
+ },
1320
+ {
1321
+ "epoch": 1.7134146341463414,
1322
+ "grad_norm": 1.0885926485061646,
1323
+ "learning_rate": 4.695123305999877e-06,
1324
+ "loss": 0.114,
1325
+ "step": 188
1326
+ },
1327
+ {
1328
+ "epoch": 1.7225609756097562,
1329
+ "grad_norm": 1.1777565479278564,
1330
+ "learning_rate": 4.688303424752969e-06,
1331
+ "loss": 0.1116,
1332
+ "step": 189
1333
+ },
1334
+ {
1335
+ "epoch": 1.7317073170731707,
1336
+ "grad_norm": 1.3686976432800293,
1337
+ "learning_rate": 4.6814131736614286e-06,
1338
+ "loss": 0.1081,
1339
+ "step": 190
1340
+ },
1341
+ {
1342
+ "epoch": 1.7408536585365852,
1343
+ "grad_norm": 0.8220391869544983,
1344
+ "learning_rate": 4.674452774296861e-06,
1345
+ "loss": 0.1091,
1346
+ "step": 191
1347
+ },
1348
+ {
1349
+ "epoch": 1.75,
1350
+ "grad_norm": 1.073935866355896,
1351
+ "learning_rate": 4.667422450486646e-06,
1352
+ "loss": 0.1148,
1353
+ "step": 192
1354
+ },
1355
+ {
1356
+ "epoch": 1.7591463414634148,
1357
+ "grad_norm": 1.389614224433899,
1358
+ "learning_rate": 4.660322428306741e-06,
1359
+ "loss": 0.1134,
1360
+ "step": 193
1361
+ },
1362
+ {
1363
+ "epoch": 1.7682926829268293,
1364
+ "grad_norm": 1.349023699760437,
1365
+ "learning_rate": 4.653152936074413e-06,
1366
+ "loss": 0.1056,
1367
+ "step": 194
1368
+ },
1369
+ {
1370
+ "epoch": 1.7774390243902438,
1371
+ "grad_norm": 1.0334906578063965,
1372
+ "learning_rate": 4.645914204340898e-06,
1373
+ "loss": 0.113,
1374
+ "step": 195
1375
+ },
1376
+ {
1377
+ "epoch": 1.7865853658536586,
1378
+ "grad_norm": 18.6312313079834,
1379
+ "learning_rate": 4.638606465883979e-06,
1380
+ "loss": 0.1351,
1381
+ "step": 196
1382
+ },
1383
+ {
1384
+ "epoch": 1.7957317073170733,
1385
+ "grad_norm": 0.7669345736503601,
1386
+ "learning_rate": 4.6312299557005125e-06,
1387
+ "loss": 0.1097,
1388
+ "step": 197
1389
+ },
1390
+ {
1391
+ "epoch": 1.8048780487804879,
1392
+ "grad_norm": 2.1091127395629883,
1393
+ "learning_rate": 4.623784910998862e-06,
1394
+ "loss": 0.1122,
1395
+ "step": 198
1396
+ },
1397
+ {
1398
+ "epoch": 1.8140243902439024,
1399
+ "grad_norm": 0.8031914830207825,
1400
+ "learning_rate": 4.616271571191273e-06,
1401
+ "loss": 0.1109,
1402
+ "step": 199
1403
+ },
1404
+ {
1405
+ "epoch": 1.8231707317073171,
1406
+ "grad_norm": 2.1154661178588867,
1407
+ "learning_rate": 4.608690177886177e-06,
1408
+ "loss": 0.1131,
1409
+ "step": 200
1410
+ },
1411
+ {
1412
+ "epoch": 1.8323170731707317,
1413
+ "grad_norm": 1.4946709871292114,
1414
+ "learning_rate": 4.6010409748804165e-06,
1415
+ "loss": 0.1136,
1416
+ "step": 201
1417
+ },
1418
+ {
1419
+ "epoch": 1.8414634146341462,
1420
+ "grad_norm": 1.0509642362594604,
1421
+ "learning_rate": 4.593324208151412e-06,
1422
+ "loss": 0.1162,
1423
+ "step": 202
1424
+ },
1425
+ {
1426
+ "epoch": 1.850609756097561,
1427
+ "grad_norm": 0.8742370009422302,
1428
+ "learning_rate": 4.585540125849244e-06,
1429
+ "loss": 0.1102,
1430
+ "step": 203
1431
+ },
1432
+ {
1433
+ "epoch": 1.8597560975609757,
1434
+ "grad_norm": 1.1283056735992432,
1435
+ "learning_rate": 4.577688978288681e-06,
1436
+ "loss": 0.1104,
1437
+ "step": 204
1438
+ },
1439
+ {
1440
+ "epoch": 1.8689024390243902,
1441
+ "grad_norm": 1.0081048011779785,
1442
+ "learning_rate": 4.569771017941125e-06,
1443
+ "loss": 0.1119,
1444
+ "step": 205
1445
+ },
1446
+ {
1447
+ "epoch": 1.8780487804878048,
1448
+ "grad_norm": 0.7291656732559204,
1449
+ "learning_rate": 4.561786499426494e-06,
1450
+ "loss": 0.1103,
1451
+ "step": 206
1452
+ },
1453
+ {
1454
+ "epoch": 1.8871951219512195,
1455
+ "grad_norm": 1.144096851348877,
1456
+ "learning_rate": 4.5537356795050346e-06,
1457
+ "loss": 0.1125,
1458
+ "step": 207
1459
+ },
1460
+ {
1461
+ "epoch": 1.8963414634146343,
1462
+ "grad_norm": 0.7317456603050232,
1463
+ "learning_rate": 4.545618817069066e-06,
1464
+ "loss": 0.1105,
1465
+ "step": 208
1466
+ },
1467
+ {
1468
+ "epoch": 1.9054878048780488,
1469
+ "grad_norm": 1.1636486053466797,
1470
+ "learning_rate": 4.537436173134653e-06,
1471
+ "loss": 0.1091,
1472
+ "step": 209
1473
+ },
1474
+ {
1475
+ "epoch": 1.9146341463414633,
1476
+ "grad_norm": 0.6319037675857544,
1477
+ "learning_rate": 4.529188010833212e-06,
1478
+ "loss": 0.1088,
1479
+ "step": 210
1480
+ },
1481
+ {
1482
+ "epoch": 1.923780487804878,
1483
+ "grad_norm": 0.7535589933395386,
1484
+ "learning_rate": 4.520874595403053e-06,
1485
+ "loss": 0.1041,
1486
+ "step": 211
1487
+ },
1488
+ {
1489
+ "epoch": 1.9329268292682928,
1490
+ "grad_norm": 1.0461041927337646,
1491
+ "learning_rate": 4.512496194180846e-06,
1492
+ "loss": 0.1129,
1493
+ "step": 212
1494
+ },
1495
+ {
1496
+ "epoch": 1.9420731707317072,
1497
+ "grad_norm": 0.6124874949455261,
1498
+ "learning_rate": 4.5040530765930275e-06,
1499
+ "loss": 0.1113,
1500
+ "step": 213
1501
+ },
1502
+ {
1503
+ "epoch": 1.951219512195122,
1504
+ "grad_norm": 0.8516119122505188,
1505
+ "learning_rate": 4.495545514147134e-06,
1506
+ "loss": 0.1112,
1507
+ "step": 214
1508
+ },
1509
+ {
1510
+ "epoch": 1.9603658536585367,
1511
+ "grad_norm": 0.8919075131416321,
1512
+ "learning_rate": 4.486973780423073e-06,
1513
+ "loss": 0.1089,
1514
+ "step": 215
1515
+ },
1516
+ {
1517
+ "epoch": 1.9695121951219512,
1518
+ "grad_norm": 1.2183221578598022,
1519
+ "learning_rate": 4.478338151064323e-06,
1520
+ "loss": 0.1156,
1521
+ "step": 216
1522
+ },
1523
+ {
1524
+ "epoch": 1.9786585365853657,
1525
+ "grad_norm": 1.0123646259307861,
1526
+ "learning_rate": 4.4696389037690734e-06,
1527
+ "loss": 0.1077,
1528
+ "step": 217
1529
+ },
1530
+ {
1531
+ "epoch": 1.9878048780487805,
1532
+ "grad_norm": 0.8304896950721741,
1533
+ "learning_rate": 4.460876318281291e-06,
1534
+ "loss": 0.1051,
1535
+ "step": 218
1536
+ },
1537
+ {
1538
+ "epoch": 1.9969512195121952,
1539
+ "grad_norm": 0.5879438519477844,
1540
+ "learning_rate": 4.452050676381725e-06,
1541
+ "loss": 0.1064,
1542
+ "step": 219
1543
+ },
1544
+ {
1545
+ "epoch": 2.0,
1546
+ "grad_norm": 0.5879438519477844,
1547
+ "learning_rate": 4.443162261878846e-06,
1548
+ "loss": 0.0344,
1549
+ "step": 220
1550
+ },
1551
+ {
1552
+ "epoch": 2.0091463414634148,
1553
+ "grad_norm": 0.8598087430000305,
1554
+ "learning_rate": 4.434211360599721e-06,
1555
+ "loss": 0.1071,
1556
+ "step": 221
1557
+ },
1558
+ {
1559
+ "epoch": 2.018292682926829,
1560
+ "grad_norm": 0.5539699196815491,
1561
+ "learning_rate": 4.425198260380818e-06,
1562
+ "loss": 0.1095,
1563
+ "step": 222
1564
+ },
1565
+ {
1566
+ "epoch": 2.027439024390244,
1567
+ "grad_norm": 0.4581831395626068,
1568
+ "learning_rate": 4.416123251058756e-06,
1569
+ "loss": 0.104,
1570
+ "step": 223
1571
+ },
1572
+ {
1573
+ "epoch": 2.0365853658536586,
1574
+ "grad_norm": 0.550529420375824,
1575
+ "learning_rate": 4.406986624460979e-06,
1576
+ "loss": 0.1049,
1577
+ "step": 224
1578
+ },
1579
+ {
1580
+ "epoch": 2.0457317073170733,
1581
+ "grad_norm": 0.749291181564331,
1582
+ "learning_rate": 4.397788674396374e-06,
1583
+ "loss": 0.1091,
1584
+ "step": 225
1585
+ },
1586
+ {
1587
+ "epoch": 2.0548780487804876,
1588
+ "grad_norm": 0.7612536549568176,
1589
+ "learning_rate": 4.3885296966458225e-06,
1590
+ "loss": 0.1045,
1591
+ "step": 226
1592
+ },
1593
+ {
1594
+ "epoch": 2.0640243902439024,
1595
+ "grad_norm": 0.6671517491340637,
1596
+ "learning_rate": 4.37920998895269e-06,
1597
+ "loss": 0.1057,
1598
+ "step": 227
1599
+ },
1600
+ {
1601
+ "epoch": 2.073170731707317,
1602
+ "grad_norm": 0.5838347673416138,
1603
+ "learning_rate": 4.369829851013251e-06,
1604
+ "loss": 0.1061,
1605
+ "step": 228
1606
+ },
1607
+ {
1608
+ "epoch": 2.082317073170732,
1609
+ "grad_norm": 1.937151312828064,
1610
+ "learning_rate": 4.36038958446705e-06,
1611
+ "loss": 0.1074,
1612
+ "step": 229
1613
+ },
1614
+ {
1615
+ "epoch": 2.091463414634146,
1616
+ "grad_norm": 0.8083934187889099,
1617
+ "learning_rate": 4.350889492887202e-06,
1618
+ "loss": 0.1096,
1619
+ "step": 230
1620
+ },
1621
+ {
1622
+ "epoch": 2.100609756097561,
1623
+ "grad_norm": 0.6810253262519836,
1624
+ "learning_rate": 4.341329881770635e-06,
1625
+ "loss": 0.1024,
1626
+ "step": 231
1627
+ },
1628
+ {
1629
+ "epoch": 2.1097560975609757,
1630
+ "grad_norm": 0.8901084065437317,
1631
+ "learning_rate": 4.331711058528259e-06,
1632
+ "loss": 0.1064,
1633
+ "step": 232
1634
+ },
1635
+ {
1636
+ "epoch": 2.1189024390243905,
1637
+ "grad_norm": 0.34419459104537964,
1638
+ "learning_rate": 4.322033332475084e-06,
1639
+ "loss": 0.1074,
1640
+ "step": 233
1641
+ },
1642
+ {
1643
+ "epoch": 2.1280487804878048,
1644
+ "grad_norm": 0.8596321940422058,
1645
+ "learning_rate": 4.312297014820275e-06,
1646
+ "loss": 0.1061,
1647
+ "step": 234
1648
+ },
1649
+ {
1650
+ "epoch": 2.1371951219512195,
1651
+ "grad_norm": 0.8391798138618469,
1652
+ "learning_rate": 4.302502418657138e-06,
1653
+ "loss": 0.107,
1654
+ "step": 235
1655
+ },
1656
+ {
1657
+ "epoch": 2.1463414634146343,
1658
+ "grad_norm": 0.7193841338157654,
1659
+ "learning_rate": 4.292649858953063e-06,
1660
+ "loss": 0.1083,
1661
+ "step": 236
1662
+ },
1663
+ {
1664
+ "epoch": 2.1554878048780486,
1665
+ "grad_norm": 1.5975165367126465,
1666
+ "learning_rate": 4.282739652539384e-06,
1667
+ "loss": 0.109,
1668
+ "step": 237
1669
+ },
1670
+ {
1671
+ "epoch": 2.1646341463414633,
1672
+ "grad_norm": 0.9933533072471619,
1673
+ "learning_rate": 4.272772118101195e-06,
1674
+ "loss": 0.1073,
1675
+ "step": 238
1676
+ },
1677
+ {
1678
+ "epoch": 2.173780487804878,
1679
+ "grad_norm": 0.9281901717185974,
1680
+ "learning_rate": 4.262747576167106e-06,
1681
+ "loss": 0.1066,
1682
+ "step": 239
1683
+ },
1684
+ {
1685
+ "epoch": 2.182926829268293,
1686
+ "grad_norm": 3.2005884647369385,
1687
+ "learning_rate": 4.2526663490989264e-06,
1688
+ "loss": 0.1106,
1689
+ "step": 240
1690
+ },
1691
+ {
1692
+ "epoch": 2.192073170731707,
1693
+ "grad_norm": 1.084905982017517,
1694
+ "learning_rate": 4.24252876108131e-06,
1695
+ "loss": 0.1047,
1696
+ "step": 241
1697
+ },
1698
+ {
1699
+ "epoch": 2.201219512195122,
1700
+ "grad_norm": 0.5345124006271362,
1701
+ "learning_rate": 4.232335138111321e-06,
1702
+ "loss": 0.1027,
1703
+ "step": 242
1704
+ },
1705
+ {
1706
+ "epoch": 2.2103658536585367,
1707
+ "grad_norm": 0.6235584020614624,
1708
+ "learning_rate": 4.222085807987954e-06,
1709
+ "loss": 0.1032,
1710
+ "step": 243
1711
+ },
1712
+ {
1713
+ "epoch": 2.2195121951219514,
1714
+ "grad_norm": 0.9797384738922119,
1715
+ "learning_rate": 4.211781100301596e-06,
1716
+ "loss": 0.1082,
1717
+ "step": 244
1718
+ },
1719
+ {
1720
+ "epoch": 2.2286585365853657,
1721
+ "grad_norm": 0.3665165901184082,
1722
+ "learning_rate": 4.201421346423421e-06,
1723
+ "loss": 0.1057,
1724
+ "step": 245
1725
+ },
1726
+ {
1727
+ "epoch": 2.2378048780487805,
1728
+ "grad_norm": 1.232487440109253,
1729
+ "learning_rate": 4.19100687949474e-06,
1730
+ "loss": 0.1088,
1731
+ "step": 246
1732
+ },
1733
+ {
1734
+ "epoch": 2.2469512195121952,
1735
+ "grad_norm": 0.8028481602668762,
1736
+ "learning_rate": 4.180538034416287e-06,
1737
+ "loss": 0.1119,
1738
+ "step": 247
1739
+ },
1740
+ {
1741
+ "epoch": 2.2560975609756095,
1742
+ "grad_norm": 1.094025731086731,
1743
+ "learning_rate": 4.1700151478374436e-06,
1744
+ "loss": 0.1033,
1745
+ "step": 248
1746
+ },
1747
+ {
1748
+ "epoch": 2.2652439024390243,
1749
+ "grad_norm": 1.0119608640670776,
1750
+ "learning_rate": 4.159438558145425e-06,
1751
+ "loss": 0.108,
1752
+ "step": 249
1753
+ },
1754
+ {
1755
+ "epoch": 2.274390243902439,
1756
+ "grad_norm": 0.6864210963249207,
1757
+ "learning_rate": 4.148808605454385e-06,
1758
+ "loss": 0.1072,
1759
+ "step": 250
1760
+ },
1761
+ {
1762
+ "epoch": 2.283536585365854,
1763
+ "grad_norm": 0.8415966629981995,
1764
+ "learning_rate": 4.138125631594488e-06,
1765
+ "loss": 0.1052,
1766
+ "step": 251
1767
+ },
1768
+ {
1769
+ "epoch": 2.292682926829268,
1770
+ "grad_norm": 0.7150280475616455,
1771
+ "learning_rate": 4.127389980100916e-06,
1772
+ "loss": 0.1049,
1773
+ "step": 252
1774
+ },
1775
+ {
1776
+ "epoch": 2.301829268292683,
1777
+ "grad_norm": 1.2521971464157104,
1778
+ "learning_rate": 4.116601996202815e-06,
1779
+ "loss": 0.1078,
1780
+ "step": 253
1781
+ },
1782
+ {
1783
+ "epoch": 2.3109756097560976,
1784
+ "grad_norm": 0.8204450011253357,
1785
+ "learning_rate": 4.1057620268122e-06,
1786
+ "loss": 0.1078,
1787
+ "step": 254
1788
+ },
1789
+ {
1790
+ "epoch": 2.3201219512195124,
1791
+ "grad_norm": 1.0992320775985718,
1792
+ "learning_rate": 4.0948704205128e-06,
1793
+ "loss": 0.1063,
1794
+ "step": 255
1795
+ },
1796
+ {
1797
+ "epoch": 2.3292682926829267,
1798
+ "grad_norm": 0.4928065240383148,
1799
+ "learning_rate": 4.08392752754884e-06,
1800
+ "loss": 0.1076,
1801
+ "step": 256
1802
+ },
1803
+ {
1804
+ "epoch": 2.3384146341463414,
1805
+ "grad_norm": 1.1588791608810425,
1806
+ "learning_rate": 4.072933699813788e-06,
1807
+ "loss": 0.1075,
1808
+ "step": 257
1809
+ },
1810
+ {
1811
+ "epoch": 2.347560975609756,
1812
+ "grad_norm": 0.5810270309448242,
1813
+ "learning_rate": 4.061889290839032e-06,
1814
+ "loss": 0.107,
1815
+ "step": 258
1816
+ },
1817
+ {
1818
+ "epoch": 2.3567073170731705,
1819
+ "grad_norm": 0.8428746461868286,
1820
+ "learning_rate": 4.050794655782515e-06,
1821
+ "loss": 0.1057,
1822
+ "step": 259
1823
+ },
1824
+ {
1825
+ "epoch": 2.3658536585365852,
1826
+ "grad_norm": 1.4898464679718018,
1827
+ "learning_rate": 4.039650151417316e-06,
1828
+ "loss": 0.1043,
1829
+ "step": 260
1830
+ },
1831
+ {
1832
+ "epoch": 2.375,
1833
+ "grad_norm": 0.8613987565040588,
1834
+ "learning_rate": 4.028456136120169e-06,
1835
+ "loss": 0.1011,
1836
+ "step": 261
1837
+ },
1838
+ {
1839
+ "epoch": 2.3841463414634148,
1840
+ "grad_norm": 0.7771743535995483,
1841
+ "learning_rate": 4.017212969859948e-06,
1842
+ "loss": 0.1073,
1843
+ "step": 262
1844
+ },
1845
+ {
1846
+ "epoch": 2.3932926829268295,
1847
+ "grad_norm": 0.4884893596172333,
1848
+ "learning_rate": 4.0059210141860875e-06,
1849
+ "loss": 0.104,
1850
+ "step": 263
1851
+ },
1852
+ {
1853
+ "epoch": 2.402439024390244,
1854
+ "grad_norm": 0.8188875317573547,
1855
+ "learning_rate": 3.994580632216952e-06,
1856
+ "loss": 0.1043,
1857
+ "step": 264
1858
+ },
1859
+ {
1860
+ "epoch": 2.4115853658536586,
1861
+ "grad_norm": 0.814239501953125,
1862
+ "learning_rate": 3.9831921886281675e-06,
1863
+ "loss": 0.1073,
1864
+ "step": 265
1865
+ },
1866
+ {
1867
+ "epoch": 2.4207317073170733,
1868
+ "grad_norm": 1.029391884803772,
1869
+ "learning_rate": 3.971756049640888e-06,
1870
+ "loss": 0.103,
1871
+ "step": 266
1872
+ },
1873
+ {
1874
+ "epoch": 2.4298780487804876,
1875
+ "grad_norm": 0.3826993405818939,
1876
+ "learning_rate": 3.96027258301002e-06,
1877
+ "loss": 0.1089,
1878
+ "step": 267
1879
+ },
1880
+ {
1881
+ "epoch": 2.4390243902439024,
1882
+ "grad_norm": 0.5306946039199829,
1883
+ "learning_rate": 3.9487421580123995e-06,
1884
+ "loss": 0.1086,
1885
+ "step": 268
1886
+ },
1887
+ {
1888
+ "epoch": 2.448170731707317,
1889
+ "grad_norm": 1.286549687385559,
1890
+ "learning_rate": 3.937165145434914e-06,
1891
+ "loss": 0.1085,
1892
+ "step": 269
1893
+ },
1894
+ {
1895
+ "epoch": 2.457317073170732,
1896
+ "grad_norm": 1.5009950399398804,
1897
+ "learning_rate": 3.92554191756258e-06,
1898
+ "loss": 0.1068,
1899
+ "step": 270
1900
+ },
1901
+ {
1902
+ "epoch": 2.466463414634146,
1903
+ "grad_norm": 0.9225317239761353,
1904
+ "learning_rate": 3.9138728481665696e-06,
1905
+ "loss": 0.1059,
1906
+ "step": 271
1907
+ },
1908
+ {
1909
+ "epoch": 2.475609756097561,
1910
+ "grad_norm": 0.5062177181243896,
1911
+ "learning_rate": 3.902158312492196e-06,
1912
+ "loss": 0.1089,
1913
+ "step": 272
1914
+ },
1915
+ {
1916
+ "epoch": 2.4847560975609757,
1917
+ "grad_norm": 0.6272971630096436,
1918
+ "learning_rate": 3.8903986872468416e-06,
1919
+ "loss": 0.1099,
1920
+ "step": 273
1921
+ },
1922
+ {
1923
+ "epoch": 2.4939024390243905,
1924
+ "grad_norm": 1.207027554512024,
1925
+ "learning_rate": 3.878594350587844e-06,
1926
+ "loss": 0.1086,
1927
+ "step": 274
1928
+ },
1929
+ {
1930
+ "epoch": 2.5030487804878048,
1931
+ "grad_norm": 0.8417999744415283,
1932
+ "learning_rate": 3.866745682110343e-06,
1933
+ "loss": 0.1091,
1934
+ "step": 275
1935
+ },
1936
+ {
1937
+ "epoch": 2.5121951219512195,
1938
+ "grad_norm": 0.5926170945167542,
1939
+ "learning_rate": 3.854853062835062e-06,
1940
+ "loss": 0.1081,
1941
+ "step": 276
1942
+ },
1943
+ {
1944
+ "epoch": 2.5213414634146343,
1945
+ "grad_norm": 0.5806312561035156,
1946
+ "learning_rate": 3.842916875196066e-06,
1947
+ "loss": 0.1057,
1948
+ "step": 277
1949
+ },
1950
+ {
1951
+ "epoch": 2.5304878048780486,
1952
+ "grad_norm": 1.2453746795654297,
1953
+ "learning_rate": 3.830937503028457e-06,
1954
+ "loss": 0.1086,
1955
+ "step": 278
1956
+ },
1957
+ {
1958
+ "epoch": 2.5396341463414633,
1959
+ "grad_norm": 0.32152408361434937,
1960
+ "learning_rate": 3.818915331556032e-06,
1961
+ "loss": 0.1076,
1962
+ "step": 279
1963
+ },
1964
+ {
1965
+ "epoch": 2.548780487804878,
1966
+ "grad_norm": 0.5756719708442688,
1967
+ "learning_rate": 3.8068507473789016e-06,
1968
+ "loss": 0.1057,
1969
+ "step": 280
1970
+ },
1971
+ {
1972
+ "epoch": 2.557926829268293,
1973
+ "grad_norm": 0.9345139861106873,
1974
+ "learning_rate": 3.7947441384610473e-06,
1975
+ "loss": 0.1043,
1976
+ "step": 281
1977
+ },
1978
+ {
1979
+ "epoch": 2.567073170731707,
1980
+ "grad_norm": 0.6475419998168945,
1981
+ "learning_rate": 3.7825958941178538e-06,
1982
+ "loss": 0.1046,
1983
+ "step": 282
1984
+ },
1985
+ {
1986
+ "epoch": 2.576219512195122,
1987
+ "grad_norm": 0.7345425486564636,
1988
+ "learning_rate": 3.770406405003586e-06,
1989
+ "loss": 0.1042,
1990
+ "step": 283
1991
+ },
1992
+ {
1993
+ "epoch": 2.5853658536585367,
1994
+ "grad_norm": 0.769500195980072,
1995
+ "learning_rate": 3.758176063098829e-06,
1996
+ "loss": 0.1048,
1997
+ "step": 284
1998
+ },
1999
+ {
2000
+ "epoch": 2.5945121951219514,
2001
+ "grad_norm": 0.5934444665908813,
2002
+ "learning_rate": 3.745905261697881e-06,
2003
+ "loss": 0.1086,
2004
+ "step": 285
2005
+ },
2006
+ {
2007
+ "epoch": 2.6036585365853657,
2008
+ "grad_norm": 0.5718421936035156,
2009
+ "learning_rate": 3.7335943953961063e-06,
2010
+ "loss": 0.1027,
2011
+ "step": 286
2012
+ },
2013
+ {
2014
+ "epoch": 2.6128048780487805,
2015
+ "grad_norm": 0.6114512085914612,
2016
+ "learning_rate": 3.721243860077247e-06,
2017
+ "loss": 0.1091,
2018
+ "step": 287
2019
+ },
2020
+ {
2021
+ "epoch": 2.6219512195121952,
2022
+ "grad_norm": 0.5620512366294861,
2023
+ "learning_rate": 3.708854052900693e-06,
2024
+ "loss": 0.1088,
2025
+ "step": 288
2026
+ },
2027
+ {
2028
+ "epoch": 2.6310975609756095,
2029
+ "grad_norm": 0.6152999997138977,
2030
+ "learning_rate": 3.696425372288708e-06,
2031
+ "loss": 0.1035,
2032
+ "step": 289
2033
+ },
2034
+ {
2035
+ "epoch": 2.6402439024390243,
2036
+ "grad_norm": 0.9731057286262512,
2037
+ "learning_rate": 3.68395821791362e-06,
2038
+ "loss": 0.1066,
2039
+ "step": 290
2040
+ },
2041
+ {
2042
+ "epoch": 2.649390243902439,
2043
+ "grad_norm": 0.49733713269233704,
2044
+ "learning_rate": 3.6714529906849683e-06,
2045
+ "loss": 0.1045,
2046
+ "step": 291
2047
+ },
2048
+ {
2049
+ "epoch": 2.658536585365854,
2050
+ "grad_norm": 0.49706941843032837,
2051
+ "learning_rate": 3.65891009273661e-06,
2052
+ "loss": 0.1035,
2053
+ "step": 292
2054
+ },
2055
+ {
2056
+ "epoch": 2.6676829268292686,
2057
+ "grad_norm": 0.32593467831611633,
2058
+ "learning_rate": 3.6463299274137883e-06,
2059
+ "loss": 0.1017,
2060
+ "step": 293
2061
+ },
2062
+ {
2063
+ "epoch": 2.676829268292683,
2064
+ "grad_norm": 0.4569077491760254,
2065
+ "learning_rate": 3.6337128992601665e-06,
2066
+ "loss": 0.1061,
2067
+ "step": 294
2068
+ },
2069
+ {
2070
+ "epoch": 2.6859756097560976,
2071
+ "grad_norm": 0.5540208220481873,
2072
+ "learning_rate": 3.621059414004811e-06,
2073
+ "loss": 0.106,
2074
+ "step": 295
2075
+ },
2076
+ {
2077
+ "epoch": 2.6951219512195124,
2078
+ "grad_norm": 0.9319402575492859,
2079
+ "learning_rate": 3.6083698785491537e-06,
2080
+ "loss": 0.1042,
2081
+ "step": 296
2082
+ },
2083
+ {
2084
+ "epoch": 2.7042682926829267,
2085
+ "grad_norm": 0.795711874961853,
2086
+ "learning_rate": 3.595644700953898e-06,
2087
+ "loss": 0.104,
2088
+ "step": 297
2089
+ },
2090
+ {
2091
+ "epoch": 2.7134146341463414,
2092
+ "grad_norm": 0.4707932472229004,
2093
+ "learning_rate": 3.582884290425903e-06,
2094
+ "loss": 0.1087,
2095
+ "step": 298
2096
+ },
2097
+ {
2098
+ "epoch": 2.722560975609756,
2099
+ "grad_norm": 0.7709797620773315,
2100
+ "learning_rate": 3.5700890573050224e-06,
2101
+ "loss": 0.107,
2102
+ "step": 299
2103
+ },
2104
+ {
2105
+ "epoch": 2.7317073170731705,
2106
+ "grad_norm": 1.1342726945877075,
2107
+ "learning_rate": 3.5572594130509074e-06,
2108
+ "loss": 0.1029,
2109
+ "step": 300
2110
+ },
2111
+ {
2112
+ "epoch": 2.7408536585365852,
2113
+ "grad_norm": 0.9055543541908264,
2114
+ "learning_rate": 3.544395770229781e-06,
2115
+ "loss": 0.1087,
2116
+ "step": 301
2117
+ },
2118
+ {
2119
+ "epoch": 2.75,
2120
+ "grad_norm": 1.084656000137329,
2121
+ "learning_rate": 3.531498542501161e-06,
2122
+ "loss": 0.1044,
2123
+ "step": 302
2124
+ },
2125
+ {
2126
+ "epoch": 2.7591463414634148,
2127
+ "grad_norm": 0.5991970300674438,
2128
+ "learning_rate": 3.51856814460457e-06,
2129
+ "loss": 0.1064,
2130
+ "step": 303
2131
+ },
2132
+ {
2133
+ "epoch": 2.7682926829268295,
2134
+ "grad_norm": 1.7364325523376465,
2135
+ "learning_rate": 3.5056049923461873e-06,
2136
+ "loss": 0.1079,
2137
+ "step": 304
2138
+ },
2139
+ {
2140
+ "epoch": 2.777439024390244,
2141
+ "grad_norm": 0.4037036895751953,
2142
+ "learning_rate": 3.4926095025854863e-06,
2143
+ "loss": 0.1058,
2144
+ "step": 305
2145
+ },
2146
+ {
2147
+ "epoch": 2.7865853658536586,
2148
+ "grad_norm": 0.8944678902626038,
2149
+ "learning_rate": 3.479582093221824e-06,
2150
+ "loss": 0.1064,
2151
+ "step": 306
2152
+ },
2153
+ {
2154
+ "epoch": 2.7957317073170733,
2155
+ "grad_norm": 0.5730510950088501,
2156
+ "learning_rate": 3.4665231831810055e-06,
2157
+ "loss": 0.1055,
2158
+ "step": 307
2159
+ },
2160
+ {
2161
+ "epoch": 2.8048780487804876,
2162
+ "grad_norm": 0.519359827041626,
2163
+ "learning_rate": 3.45343319240181e-06,
2164
+ "loss": 0.1069,
2165
+ "step": 308
2166
+ },
2167
+ {
2168
+ "epoch": 2.8140243902439024,
2169
+ "grad_norm": 0.6074658632278442,
2170
+ "learning_rate": 3.44031254182249e-06,
2171
+ "loss": 0.1058,
2172
+ "step": 309
2173
+ },
2174
+ {
2175
+ "epoch": 2.823170731707317,
2176
+ "grad_norm": 0.37584108114242554,
2177
+ "learning_rate": 3.4271616533672312e-06,
2178
+ "loss": 0.1052,
2179
+ "step": 310
2180
+ },
2181
+ {
2182
+ "epoch": 2.8323170731707314,
2183
+ "grad_norm": 0.7730855941772461,
2184
+ "learning_rate": 3.413980949932589e-06,
2185
+ "loss": 0.1037,
2186
+ "step": 311
2187
+ },
2188
+ {
2189
+ "epoch": 2.841463414634146,
2190
+ "grad_norm": 0.9912458062171936,
2191
+ "learning_rate": 3.4007708553738837e-06,
2192
+ "loss": 0.1039,
2193
+ "step": 312
2194
+ },
2195
+ {
2196
+ "epoch": 2.850609756097561,
2197
+ "grad_norm": 0.36861947178840637,
2198
+ "learning_rate": 3.3875317944915765e-06,
2199
+ "loss": 0.1083,
2200
+ "step": 313
2201
+ },
2202
+ {
2203
+ "epoch": 2.8597560975609757,
2204
+ "grad_norm": 0.6069959402084351,
2205
+ "learning_rate": 3.3742641930176044e-06,
2206
+ "loss": 0.1063,
2207
+ "step": 314
2208
+ },
2209
+ {
2210
+ "epoch": 2.8689024390243905,
2211
+ "grad_norm": 0.5478480458259583,
2212
+ "learning_rate": 3.3609684776016932e-06,
2213
+ "loss": 0.1033,
2214
+ "step": 315
2215
+ },
2216
+ {
2217
+ "epoch": 2.8780487804878048,
2218
+ "grad_norm": 0.8352198004722595,
2219
+ "learning_rate": 3.3476450757976353e-06,
2220
+ "loss": 0.1026,
2221
+ "step": 316
2222
+ },
2223
+ {
2224
+ "epoch": 2.8871951219512195,
2225
+ "grad_norm": 0.32641175389289856,
2226
+ "learning_rate": 3.3342944160495405e-06,
2227
+ "loss": 0.1065,
2228
+ "step": 317
2229
+ },
2230
+ {
2231
+ "epoch": 2.8963414634146343,
2232
+ "grad_norm": 0.8076167702674866,
2233
+ "learning_rate": 3.3209169276780612e-06,
2234
+ "loss": 0.105,
2235
+ "step": 318
2236
+ },
2237
+ {
2238
+ "epoch": 2.9054878048780486,
2239
+ "grad_norm": 0.3602111041545868,
2240
+ "learning_rate": 3.307513040866584e-06,
2241
+ "loss": 0.106,
2242
+ "step": 319
2243
+ },
2244
+ {
2245
+ "epoch": 2.9146341463414633,
2246
+ "grad_norm": 0.227371945977211,
2247
+ "learning_rate": 3.2940831866473967e-06,
2248
+ "loss": 0.1029,
2249
+ "step": 320
2250
+ },
2251
+ {
2252
+ "epoch": 2.923780487804878,
2253
+ "grad_norm": 0.5158879160881042,
2254
+ "learning_rate": 3.280627796887828e-06,
2255
+ "loss": 0.1046,
2256
+ "step": 321
2257
+ },
2258
+ {
2259
+ "epoch": 2.932926829268293,
2260
+ "grad_norm": 1.0091784000396729,
2261
+ "learning_rate": 3.2671473042763603e-06,
2262
+ "loss": 0.1063,
2263
+ "step": 322
2264
+ },
2265
+ {
2266
+ "epoch": 2.942073170731707,
2267
+ "grad_norm": 0.9310367107391357,
2268
+ "learning_rate": 3.2536421423087137e-06,
2269
+ "loss": 0.1015,
2270
+ "step": 323
2271
+ },
2272
+ {
2273
+ "epoch": 2.951219512195122,
2274
+ "grad_norm": 0.7602329254150391,
2275
+ "learning_rate": 3.2401127452739106e-06,
2276
+ "loss": 0.1061,
2277
+ "step": 324
2278
+ },
2279
+ {
2280
+ "epoch": 2.9603658536585367,
2281
+ "grad_norm": 0.3374696671962738,
2282
+ "learning_rate": 3.2265595482403002e-06,
2283
+ "loss": 0.1049,
2284
+ "step": 325
2285
+ },
2286
+ {
2287
+ "epoch": 2.9695121951219514,
2288
+ "grad_norm": 0.8469128012657166,
2289
+ "learning_rate": 3.212982987041582e-06,
2290
+ "loss": 0.1059,
2291
+ "step": 326
2292
+ },
2293
+ {
2294
+ "epoch": 2.9786585365853657,
2295
+ "grad_norm": 0.7546894550323486,
2296
+ "learning_rate": 3.199383498262777e-06,
2297
+ "loss": 0.1067,
2298
+ "step": 327
2299
+ }
2300
+ ],
2301
+ "logging_steps": 1,
2302
+ "max_steps": 654,
2303
+ "num_input_tokens_seen": 0,
2304
+ "num_train_epochs": 6,
2305
+ "save_steps": 109,
2306
+ "stateful_callbacks": {
2307
+ "TrainerControl": {
2308
+ "args": {
2309
+ "should_epoch_stop": false,
2310
+ "should_evaluate": false,
2311
+ "should_log": false,
2312
+ "should_save": true,
2313
+ "should_training_stop": false
2314
+ },
2315
+ "attributes": {}
2316
+ }
2317
+ },
2318
+ "total_flos": 9.884240649702605e+18,
2319
+ "train_batch_size": 4,
2320
+ "trial_name": null,
2321
+ "trial_params": null
2322
+ }
checkpoint-327/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14990b8399bb8d39b746405b094f7eea1041d93488de8433b2d415de16ff957a
3
+ size 7928
checkpoint-327/zero_to_fp32.py ADDED
@@ -0,0 +1,604 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #!/usr/bin/env python
2
+
3
+ # Copyright (c) Microsoft Corporation.
4
+ # SPDX-License-Identifier: Apache-2.0
5
+
6
+ # DeepSpeed Team
7
+
8
+ # This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
9
+ # copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
10
+ # the future. Once extracted, the weights don't require DeepSpeed and can be used in any
11
+ # application.
12
+ #
13
+ # example: python zero_to_fp32.py . pytorch_model.bin
14
+
15
+ import argparse
16
+ import torch
17
+ import glob
18
+ import math
19
+ import os
20
+ import re
21
+ from collections import OrderedDict
22
+ from dataclasses import dataclass
23
+
24
+ # while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
25
+ # DeepSpeed data structures it has to be available in the current python environment.
26
+ from deepspeed.utils import logger
27
+ from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
28
+ FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
29
+ FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
30
+
31
+
32
+ @dataclass
33
+ class zero_model_state:
34
+ buffers: dict()
35
+ param_shapes: dict()
36
+ shared_params: list
37
+ ds_version: int
38
+ frozen_param_shapes: dict()
39
+ frozen_param_fragments: dict()
40
+
41
+
42
+ debug = 0
43
+
44
+ # load to cpu
45
+ device = torch.device('cpu')
46
+
47
+
48
+ def atoi(text):
49
+ return int(text) if text.isdigit() else text
50
+
51
+
52
+ def natural_keys(text):
53
+ '''
54
+ alist.sort(key=natural_keys) sorts in human order
55
+ http://nedbatchelder.com/blog/200712/human_sorting.html
56
+ (See Toothy's implementation in the comments)
57
+ '''
58
+ return [atoi(c) for c in re.split(r'(\d+)', text)]
59
+
60
+
61
+ def get_model_state_file(checkpoint_dir, zero_stage):
62
+ if not os.path.isdir(checkpoint_dir):
63
+ raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
64
+
65
+ # there should be only one file
66
+ if zero_stage <= 2:
67
+ file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
68
+ elif zero_stage == 3:
69
+ file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
70
+
71
+ if not os.path.exists(file):
72
+ raise FileNotFoundError(f"can't find model states file at '{file}'")
73
+
74
+ return file
75
+
76
+
77
+ def get_checkpoint_files(checkpoint_dir, glob_pattern):
78
+ # XXX: need to test that this simple glob rule works for multi-node setup too
79
+ ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
80
+
81
+ if len(ckpt_files) == 0:
82
+ raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
83
+
84
+ return ckpt_files
85
+
86
+
87
+ def get_optim_files(checkpoint_dir):
88
+ return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
89
+
90
+
91
+ def get_model_state_files(checkpoint_dir):
92
+ return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
93
+
94
+
95
+ def parse_model_states(files):
96
+ zero_model_states = []
97
+ for file in files:
98
+ state_dict = torch.load(file, map_location=device)
99
+
100
+ if BUFFER_NAMES not in state_dict:
101
+ raise ValueError(f"{file} is not a model state checkpoint")
102
+ buffer_names = state_dict[BUFFER_NAMES]
103
+ if debug:
104
+ print("Found buffers:", buffer_names)
105
+
106
+ # recover just the buffers while restoring them to fp32 if they were saved in fp16
107
+ buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
108
+ param_shapes = state_dict[PARAM_SHAPES]
109
+
110
+ # collect parameters that are included in param_shapes
111
+ param_names = []
112
+ for s in param_shapes:
113
+ for name in s.keys():
114
+ param_names.append(name)
115
+
116
+ # update with frozen parameters
117
+ frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
118
+ if frozen_param_shapes is not None:
119
+ if debug:
120
+ print(f"Found frozen_param_shapes: {frozen_param_shapes}")
121
+ param_names += list(frozen_param_shapes.keys())
122
+
123
+ # handle shared params
124
+ shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
125
+
126
+ ds_version = state_dict.get(DS_VERSION, None)
127
+
128
+ frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
129
+
130
+ z_model_state = zero_model_state(buffers=buffers,
131
+ param_shapes=param_shapes,
132
+ shared_params=shared_params,
133
+ ds_version=ds_version,
134
+ frozen_param_shapes=frozen_param_shapes,
135
+ frozen_param_fragments=frozen_param_fragments)
136
+ zero_model_states.append(z_model_state)
137
+
138
+ return zero_model_states
139
+
140
+
141
+ def parse_optim_states(files, ds_checkpoint_dir):
142
+
143
+ total_files = len(files)
144
+ state_dicts = []
145
+ for f in files:
146
+ state_dict = torch.load(f, map_location=device)
147
+ # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
148
+ # and also handle the case where it was already removed by another helper script
149
+ state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
150
+ state_dicts.append(state_dict)
151
+
152
+ if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
153
+ raise ValueError(f"{files[0]} is not a zero checkpoint")
154
+ zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
155
+ world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
156
+
157
+ # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
158
+ # parameters can be different from data parallelism for non-expert parameters. So we can just
159
+ # use the max of the partition_count to get the dp world_size.
160
+
161
+ if type(world_size) is list:
162
+ world_size = max(world_size)
163
+
164
+ if world_size != total_files:
165
+ raise ValueError(
166
+ f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
167
+ "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
168
+ )
169
+
170
+ # the groups are named differently in each stage
171
+ if zero_stage <= 2:
172
+ fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
173
+ elif zero_stage == 3:
174
+ fp32_groups_key = FP32_FLAT_GROUPS
175
+ else:
176
+ raise ValueError(f"unknown zero stage {zero_stage}")
177
+
178
+ if zero_stage <= 2:
179
+ fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
180
+ elif zero_stage == 3:
181
+ # if there is more than one param group, there will be multiple flattened tensors - one
182
+ # flattened tensor per group - for simplicity merge them into a single tensor
183
+ #
184
+ # XXX: could make the script more memory efficient for when there are multiple groups - it
185
+ # will require matching the sub-lists of param_shapes for each param group flattened tensor
186
+
187
+ fp32_flat_groups = [
188
+ torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
189
+ ]
190
+
191
+ return zero_stage, world_size, fp32_flat_groups
192
+
193
+
194
+ def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
195
+ """
196
+ Returns fp32 state_dict reconstructed from ds checkpoint
197
+
198
+ Args:
199
+ - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
200
+
201
+ """
202
+ print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
203
+
204
+ optim_files = get_optim_files(ds_checkpoint_dir)
205
+ zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
206
+ print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
207
+
208
+ model_files = get_model_state_files(ds_checkpoint_dir)
209
+
210
+ zero_model_states = parse_model_states(model_files)
211
+ print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
212
+
213
+ if zero_stage <= 2:
214
+ return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
215
+ exclude_frozen_parameters)
216
+ elif zero_stage == 3:
217
+ return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
218
+ exclude_frozen_parameters)
219
+
220
+
221
+ def _zero2_merge_frozen_params(state_dict, zero_model_states):
222
+ if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
223
+ return
224
+
225
+ frozen_param_shapes = zero_model_states[0].frozen_param_shapes
226
+ frozen_param_fragments = zero_model_states[0].frozen_param_fragments
227
+
228
+ if debug:
229
+ num_elem = sum(s.numel() for s in frozen_param_shapes.values())
230
+ print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
231
+
232
+ wanted_params = len(frozen_param_shapes)
233
+ wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
234
+ avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
235
+ print(f'Frozen params: Have {avail_numel} numels to process.')
236
+ print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
237
+
238
+ total_params = 0
239
+ total_numel = 0
240
+ for name, shape in frozen_param_shapes.items():
241
+ total_params += 1
242
+ unpartitioned_numel = shape.numel()
243
+ total_numel += unpartitioned_numel
244
+
245
+ state_dict[name] = frozen_param_fragments[name]
246
+
247
+ if debug:
248
+ print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
249
+
250
+ print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
251
+
252
+
253
+ def _has_callable(obj, fn):
254
+ attr = getattr(obj, fn, None)
255
+ return callable(attr)
256
+
257
+
258
+ def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
259
+ param_shapes = zero_model_states[0].param_shapes
260
+
261
+ # Reconstruction protocol:
262
+ #
263
+ # XXX: document this
264
+
265
+ if debug:
266
+ for i in range(world_size):
267
+ for j in range(len(fp32_flat_groups[0])):
268
+ print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
269
+
270
+ # XXX: memory usage doubles here (zero2)
271
+ num_param_groups = len(fp32_flat_groups[0])
272
+ merged_single_partition_of_fp32_groups = []
273
+ for i in range(num_param_groups):
274
+ merged_partitions = [sd[i] for sd in fp32_flat_groups]
275
+ full_single_fp32_vector = torch.cat(merged_partitions, 0)
276
+ merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
277
+ avail_numel = sum(
278
+ [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
279
+
280
+ if debug:
281
+ wanted_params = sum([len(shapes) for shapes in param_shapes])
282
+ wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
283
+ # not asserting if there is a mismatch due to possible padding
284
+ print(f"Have {avail_numel} numels to process.")
285
+ print(f"Need {wanted_numel} numels in {wanted_params} params.")
286
+
287
+ # params
288
+ # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
289
+ # out-of-core computing solution
290
+ total_numel = 0
291
+ total_params = 0
292
+ for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
293
+ offset = 0
294
+ avail_numel = full_single_fp32_vector.numel()
295
+ for name, shape in shapes.items():
296
+
297
+ unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
298
+ total_numel += unpartitioned_numel
299
+ total_params += 1
300
+
301
+ if debug:
302
+ print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
303
+ state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
304
+ offset += unpartitioned_numel
305
+
306
+ # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
307
+ # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
308
+ # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
309
+ # live optimizer object, so we are checking that the numbers are within the right range
310
+ align_to = 2 * world_size
311
+
312
+ def zero2_align(x):
313
+ return align_to * math.ceil(x / align_to)
314
+
315
+ if debug:
316
+ print(f"original offset={offset}, avail_numel={avail_numel}")
317
+
318
+ offset = zero2_align(offset)
319
+ avail_numel = zero2_align(avail_numel)
320
+
321
+ if debug:
322
+ print(f"aligned offset={offset}, avail_numel={avail_numel}")
323
+
324
+ # Sanity check
325
+ if offset != avail_numel:
326
+ raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
327
+
328
+ print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
329
+
330
+
331
+ def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
332
+ exclude_frozen_parameters):
333
+ state_dict = OrderedDict()
334
+
335
+ # buffers
336
+ buffers = zero_model_states[0].buffers
337
+ state_dict.update(buffers)
338
+ if debug:
339
+ print(f"added {len(buffers)} buffers")
340
+
341
+ if not exclude_frozen_parameters:
342
+ _zero2_merge_frozen_params(state_dict, zero_model_states)
343
+
344
+ _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
345
+
346
+ # recover shared parameters
347
+ for pair in zero_model_states[0].shared_params:
348
+ if pair[1] in state_dict:
349
+ state_dict[pair[0]] = state_dict[pair[1]]
350
+
351
+ return state_dict
352
+
353
+
354
+ def zero3_partitioned_param_info(unpartitioned_numel, world_size):
355
+ remainder = unpartitioned_numel % world_size
356
+ padding_numel = (world_size - remainder) if remainder else 0
357
+ partitioned_numel = math.ceil(unpartitioned_numel / world_size)
358
+ return partitioned_numel, padding_numel
359
+
360
+
361
+ def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
362
+ if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
363
+ return
364
+
365
+ if debug:
366
+ for i in range(world_size):
367
+ num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
368
+ print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
369
+
370
+ frozen_param_shapes = zero_model_states[0].frozen_param_shapes
371
+ wanted_params = len(frozen_param_shapes)
372
+ wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
373
+ avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
374
+ print(f'Frozen params: Have {avail_numel} numels to process.')
375
+ print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
376
+
377
+ total_params = 0
378
+ total_numel = 0
379
+ for name, shape in zero_model_states[0].frozen_param_shapes.items():
380
+ total_params += 1
381
+ unpartitioned_numel = shape.numel()
382
+ total_numel += unpartitioned_numel
383
+
384
+ param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
385
+ state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
386
+
387
+ partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
388
+
389
+ if debug:
390
+ print(
391
+ f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
392
+ )
393
+
394
+ print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
395
+
396
+
397
+ def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
398
+ param_shapes = zero_model_states[0].param_shapes
399
+ avail_numel = fp32_flat_groups[0].numel() * world_size
400
+ # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
401
+ # param, re-consolidating each param, while dealing with padding if any
402
+
403
+ # merge list of dicts, preserving order
404
+ param_shapes = {k: v for d in param_shapes for k, v in d.items()}
405
+
406
+ if debug:
407
+ for i in range(world_size):
408
+ print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
409
+
410
+ wanted_params = len(param_shapes)
411
+ wanted_numel = sum(shape.numel() for shape in param_shapes.values())
412
+ # not asserting if there is a mismatch due to possible padding
413
+ avail_numel = fp32_flat_groups[0].numel() * world_size
414
+ print(f"Trainable params: Have {avail_numel} numels to process.")
415
+ print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
416
+
417
+ # params
418
+ # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
419
+ # out-of-core computing solution
420
+ offset = 0
421
+ total_numel = 0
422
+ total_params = 0
423
+ for name, shape in param_shapes.items():
424
+
425
+ unpartitioned_numel = shape.numel()
426
+ total_numel += unpartitioned_numel
427
+ total_params += 1
428
+
429
+ partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
430
+
431
+ if debug:
432
+ print(
433
+ f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
434
+ )
435
+
436
+ # XXX: memory usage doubles here
437
+ state_dict[name] = torch.cat(
438
+ tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
439
+ 0).narrow(0, 0, unpartitioned_numel).view(shape)
440
+ offset += partitioned_numel
441
+
442
+ offset *= world_size
443
+
444
+ # Sanity check
445
+ if offset != avail_numel:
446
+ raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
447
+
448
+ print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
449
+
450
+
451
+ def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
452
+ exclude_frozen_parameters):
453
+ state_dict = OrderedDict()
454
+
455
+ # buffers
456
+ buffers = zero_model_states[0].buffers
457
+ state_dict.update(buffers)
458
+ if debug:
459
+ print(f"added {len(buffers)} buffers")
460
+
461
+ if not exclude_frozen_parameters:
462
+ _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
463
+
464
+ _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
465
+
466
+ # recover shared parameters
467
+ for pair in zero_model_states[0].shared_params:
468
+ if pair[1] in state_dict:
469
+ state_dict[pair[0]] = state_dict[pair[1]]
470
+
471
+ return state_dict
472
+
473
+
474
+ def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
475
+ """
476
+ Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
477
+ ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
478
+ via a model hub.
479
+
480
+ Args:
481
+ - ``checkpoint_dir``: path to the desired checkpoint folder
482
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
483
+ - ``exclude_frozen_parameters``: exclude frozen parameters
484
+
485
+ Returns:
486
+ - pytorch ``state_dict``
487
+
488
+ Note: this approach may not work if your application doesn't have sufficient free CPU memory and
489
+ you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
490
+ the checkpoint.
491
+
492
+ A typical usage might be ::
493
+
494
+ from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
495
+ # do the training and checkpoint saving
496
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
497
+ model = model.cpu() # move to cpu
498
+ model.load_state_dict(state_dict)
499
+ # submit to model hub or save the model to share with others
500
+
501
+ In this example the ``model`` will no longer be usable in the deepspeed context of the same
502
+ application. i.e. you will need to re-initialize the deepspeed engine, since
503
+ ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
504
+
505
+ If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
506
+
507
+ """
508
+ if tag is None:
509
+ latest_path = os.path.join(checkpoint_dir, 'latest')
510
+ if os.path.isfile(latest_path):
511
+ with open(latest_path, 'r') as fd:
512
+ tag = fd.read().strip()
513
+ else:
514
+ raise ValueError(f"Unable to find 'latest' file at {latest_path}")
515
+
516
+ ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
517
+
518
+ if not os.path.isdir(ds_checkpoint_dir):
519
+ raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
520
+
521
+ return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
522
+
523
+
524
+ def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None, exclude_frozen_parameters=False):
525
+ """
526
+ Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
527
+ loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
528
+
529
+ Args:
530
+ - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
531
+ - ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
532
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
533
+ - ``exclude_frozen_parameters``: exclude frozen parameters
534
+ """
535
+
536
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
537
+ print(f"Saving fp32 state dict to {output_file}")
538
+ torch.save(state_dict, output_file)
539
+
540
+
541
+ def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
542
+ """
543
+ 1. Put the provided model to cpu
544
+ 2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
545
+ 3. Load it into the provided model
546
+
547
+ Args:
548
+ - ``model``: the model object to update
549
+ - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
550
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
551
+
552
+ Returns:
553
+ - ``model`: modified model
554
+
555
+ Make sure you have plenty of CPU memory available before you call this function. If you don't
556
+ have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
557
+ conveniently placed for you in the checkpoint folder.
558
+
559
+ A typical usage might be ::
560
+
561
+ from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
562
+ model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
563
+ # submit to model hub or save the model to share with others
564
+
565
+ Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
566
+ of the same application. i.e. you will need to re-initialize the deepspeed engine, since
567
+ ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
568
+
569
+ """
570
+ logger.info(f"Extracting fp32 weights")
571
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
572
+
573
+ logger.info(f"Overwriting model with fp32 weights")
574
+ model = model.cpu()
575
+ model.load_state_dict(state_dict, strict=False)
576
+
577
+ return model
578
+
579
+
580
+ if __name__ == "__main__":
581
+
582
+ parser = argparse.ArgumentParser()
583
+ parser.add_argument("checkpoint_dir",
584
+ type=str,
585
+ help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
586
+ parser.add_argument(
587
+ "output_file",
588
+ type=str,
589
+ help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
590
+ parser.add_argument("-t",
591
+ "--tag",
592
+ type=str,
593
+ default=None,
594
+ help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
595
+ parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
596
+ parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
597
+ args = parser.parse_args()
598
+
599
+ debug = args.debug
600
+
601
+ convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
602
+ args.output_file,
603
+ tag=args.tag,
604
+ exclude_frozen_parameters=args.exclude_frozen_parameters)