Hugging Face's logo

Edens-Gate
/
Adventure-CKPTS-V2-R1

Safetensors
llama
Model card Files
xet
Community
Delta-Vector commited on
Commit
4e3d057
·
verified ·
1 Parent(s): 377c3ec

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 +5 -0
  2. adapter_config.json +39 -0
  3. adapter_model.safetensors +3 -0
  4. checkpoint-300/README.md +202 -0
  5. checkpoint-300/adapter_config.json +39 -0
  6. checkpoint-300/adapter_model.safetensors +3 -0
  7. checkpoint-300/latest +1 -0
  8. checkpoint-300/rng_state_0.pth +3 -0
  9. checkpoint-300/rng_state_1.pth +3 -0
  10. checkpoint-300/rng_state_2.pth +3 -0
  11. checkpoint-300/rng_state_3.pth +3 -0
  12. checkpoint-300/scheduler.pt +3 -0
  13. checkpoint-300/special_tokens_map.json +23 -0
  14. checkpoint-300/tokenizer.json +3 -0
  15. checkpoint-300/tokenizer_config.json +2064 -0
  16. checkpoint-300/trainer_state.json +2222 -0
  17. checkpoint-300/training_args.bin +3 -0
  18. checkpoint-300/zero_to_fp32.py +760 -0
  19. checkpoint-360/README.md +202 -0
  20. checkpoint-360/adapter_config.json +39 -0
  21. checkpoint-360/adapter_model.safetensors +3 -0
  22. checkpoint-360/latest +1 -0
  23. checkpoint-360/rng_state_0.pth +3 -0
  24. checkpoint-360/rng_state_1.pth +3 -0
  25. checkpoint-360/rng_state_2.pth +3 -0
  26. checkpoint-360/rng_state_3.pth +3 -0
  27. checkpoint-360/scheduler.pt +3 -0
  28. checkpoint-360/special_tokens_map.json +23 -0
  29. checkpoint-360/tokenizer.json +3 -0
  30. checkpoint-360/tokenizer_config.json +2064 -0
  31. checkpoint-360/trainer_state.json +2658 -0
  32. checkpoint-360/training_args.bin +3 -0
  33. checkpoint-360/zero_to_fp32.py +760 -0
  34. checkpoint-420/README.md +202 -0
  35. checkpoint-420/adapter_config.json +39 -0
  36. checkpoint-420/adapter_model.safetensors +3 -0
  37. checkpoint-420/latest +1 -0
  38. checkpoint-420/rng_state_0.pth +3 -0
  39. checkpoint-420/rng_state_1.pth +3 -0
  40. checkpoint-420/rng_state_2.pth +3 -0
  41. checkpoint-420/rng_state_3.pth +3 -0
  42. checkpoint-420/scheduler.pt +3 -0
  43. checkpoint-420/special_tokens_map.json +23 -0
  44. checkpoint-420/tokenizer.json +3 -0
  45. checkpoint-420/tokenizer_config.json +2064 -0
  46. checkpoint-420/trainer_state.json +3094 -0
  47. checkpoint-420/training_args.bin +3 -0
  48. checkpoint-420/zero_to_fp32.py +760 -0
  49. checkpoint-480/adapter_config.json +39 -0
  50. checkpoint-480/adapter_model.safetensors +3 -0
.gitattributes CHANGED
@@ -33,3 +33,8 @@ 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-300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint-360/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ checkpoint-420/tokenizer.json filter=lfs diff=lfs merge=lfs -text
39
+ checkpoint-480/tokenizer.json filter=lfs diff=lfs merge=lfs -text
40
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "NewEden/Hamanasu-KTO-V2",
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": 16,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 128,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "gate_proj",
28
+ "o_proj",
29
+ "q_proj",
30
+ "k_proj",
31
+ "down_proj",
32
+ "up_proj",
33
+ "v_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": true
39
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f43dab069cfdcacbd2443671997ce7738bb6dc3830c63fa9d0e4d28a5903ffc
3
+ size 486600536
checkpoint-300/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: NewEden/Hamanasu-KTO-V2
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-300/adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "NewEden/Hamanasu-KTO-V2",
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": 16,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 128,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "gate_proj",
28
+ "o_proj",
29
+ "q_proj",
30
+ "k_proj",
31
+ "down_proj",
32
+ "up_proj",
33
+ "v_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": true
39
+ }
checkpoint-300/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc93317df87d24dbc751827fb8b7261f1eb6df3cf31124032e490d3d6a2fff61
3
+ size 486600536
checkpoint-300/latest ADDED
@@ -0,0 +1 @@
 
 
1
+ global_step300
checkpoint-300/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:080b6d5dd016eedd242f1c87f1c49f6194cbf61dc02b1e8482849da2ffc7bc1d
3
+ size 15024
checkpoint-300/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b038dedf6c8088f62157bca21d8a81ddc3cf88995a4a31cdc0ce765b8a8c533
3
+ size 15024
checkpoint-300/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bc5c7fa0ff819fadae8b2511d96c19201285725b85fa37843d322b529d01cc8
3
+ size 15024
checkpoint-300/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c75def22398a44a621a99bc32c2853940c7f21955a8423605b2ef4b73bb5b85
3
+ size 15024
checkpoint-300/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:840c5d110a77253c19ab9743baad88cf5330aef39fa9b184a3da25d97a87b15d
3
+ size 1064
checkpoint-300/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": "<|im_end|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|finetune_right_pad_id|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
checkpoint-300/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:907a7b3b13afcc9d481433f17277a6dd7cf852c6185262597f1a849d2ebeaa45
3
+ size 17209884
checkpoint-300/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": "<|im_start|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|im_end|>",
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": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|im_end|>",
2056
+ "extra_special_tokens": {},
2057
+ "model_input_names": [
2058
+ "input_ids",
2059
+ "attention_mask"
2060
+ ],
2061
+ "model_max_length": 131072,
2062
+ "pad_token": "<|finetune_right_pad_id|>",
2063
+ "tokenizer_class": "PreTrainedTokenizer"
2064
+ }
checkpoint-300/trainer_state.json ADDED
@@ -0,0 +1,2222 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.5,
6
+ "eval_steps": 30,
7
+ "global_step": 300,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.008333333333333333,
14
+ "grad_norm": 0.9462232657835241,
15
+ "learning_rate": 8.142857142857143e-07,
16
+ "loss": 2.5443,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.008333333333333333,
21
+ "eval_loss": 2.5896365642547607,
22
+ "eval_runtime": 96.0059,
23
+ "eval_samples_per_second": 4.271,
24
+ "eval_steps_per_second": 0.271,
25
+ "step": 1
26
+ },
27
+ {
28
+ "epoch": 0.016666666666666666,
29
+ "grad_norm": 0.9597143397960513,
30
+ "learning_rate": 1.6285714285714286e-06,
31
+ "loss": 2.5524,
32
+ "step": 2
33
+ },
34
+ {
35
+ "epoch": 0.025,
36
+ "grad_norm": 0.9246258453027174,
37
+ "learning_rate": 2.442857142857143e-06,
38
+ "loss": 2.5411,
39
+ "step": 3
40
+ },
41
+ {
42
+ "epoch": 0.03333333333333333,
43
+ "grad_norm": 0.9822285829186661,
44
+ "learning_rate": 3.2571428571428572e-06,
45
+ "loss": 2.5518,
46
+ "step": 4
47
+ },
48
+ {
49
+ "epoch": 0.041666666666666664,
50
+ "grad_norm": 0.9044329068814566,
51
+ "learning_rate": 4.071428571428572e-06,
52
+ "loss": 2.4922,
53
+ "step": 5
54
+ },
55
+ {
56
+ "epoch": 0.05,
57
+ "grad_norm": 0.9131300887744053,
58
+ "learning_rate": 4.885714285714286e-06,
59
+ "loss": 2.5713,
60
+ "step": 6
61
+ },
62
+ {
63
+ "epoch": 0.058333333333333334,
64
+ "grad_norm": 0.8336298309675122,
65
+ "learning_rate": 5.7000000000000005e-06,
66
+ "loss": 2.4959,
67
+ "step": 7
68
+ },
69
+ {
70
+ "epoch": 0.06666666666666667,
71
+ "grad_norm": 0.810775409605909,
72
+ "learning_rate": 6.5142857142857145e-06,
73
+ "loss": 2.4943,
74
+ "step": 8
75
+ },
76
+ {
77
+ "epoch": 0.075,
78
+ "grad_norm": 0.6993505055921954,
79
+ "learning_rate": 7.3285714285714285e-06,
80
+ "loss": 2.5022,
81
+ "step": 9
82
+ },
83
+ {
84
+ "epoch": 0.08333333333333333,
85
+ "grad_norm": 0.5909140859664664,
86
+ "learning_rate": 8.142857142857143e-06,
87
+ "loss": 2.468,
88
+ "step": 10
89
+ },
90
+ {
91
+ "epoch": 0.09166666666666666,
92
+ "grad_norm": 0.5464791893738283,
93
+ "learning_rate": 8.957142857142857e-06,
94
+ "loss": 2.5203,
95
+ "step": 11
96
+ },
97
+ {
98
+ "epoch": 0.1,
99
+ "grad_norm": 0.41153668995149084,
100
+ "learning_rate": 9.771428571428571e-06,
101
+ "loss": 2.4912,
102
+ "step": 12
103
+ },
104
+ {
105
+ "epoch": 0.10833333333333334,
106
+ "grad_norm": 0.35433353277028035,
107
+ "learning_rate": 1.0585714285714287e-05,
108
+ "loss": 2.4467,
109
+ "step": 13
110
+ },
111
+ {
112
+ "epoch": 0.11666666666666667,
113
+ "grad_norm": 0.27579908222756766,
114
+ "learning_rate": 1.1400000000000001e-05,
115
+ "loss": 2.4599,
116
+ "step": 14
117
+ },
118
+ {
119
+ "epoch": 0.125,
120
+ "grad_norm": 0.22636758420678307,
121
+ "learning_rate": 1.2214285714285715e-05,
122
+ "loss": 2.4357,
123
+ "step": 15
124
+ },
125
+ {
126
+ "epoch": 0.13333333333333333,
127
+ "grad_norm": 0.22309908436920517,
128
+ "learning_rate": 1.3028571428571429e-05,
129
+ "loss": 2.368,
130
+ "step": 16
131
+ },
132
+ {
133
+ "epoch": 0.14166666666666666,
134
+ "grad_norm": 0.2384290311446137,
135
+ "learning_rate": 1.3842857142857143e-05,
136
+ "loss": 2.4054,
137
+ "step": 17
138
+ },
139
+ {
140
+ "epoch": 0.15,
141
+ "grad_norm": 0.2279055472006466,
142
+ "learning_rate": 1.4657142857142857e-05,
143
+ "loss": 2.4162,
144
+ "step": 18
145
+ },
146
+ {
147
+ "epoch": 0.15833333333333333,
148
+ "grad_norm": 0.24659885813398136,
149
+ "learning_rate": 1.547142857142857e-05,
150
+ "loss": 2.4109,
151
+ "step": 19
152
+ },
153
+ {
154
+ "epoch": 0.16666666666666666,
155
+ "grad_norm": 0.21920560481126147,
156
+ "learning_rate": 1.6285714285714287e-05,
157
+ "loss": 2.4344,
158
+ "step": 20
159
+ },
160
+ {
161
+ "epoch": 0.175,
162
+ "grad_norm": 0.21340860355678012,
163
+ "learning_rate": 1.71e-05,
164
+ "loss": 2.4532,
165
+ "step": 21
166
+ },
167
+ {
168
+ "epoch": 0.18333333333333332,
169
+ "grad_norm": 0.1775246176788835,
170
+ "learning_rate": 1.7914285714285715e-05,
171
+ "loss": 2.4398,
172
+ "step": 22
173
+ },
174
+ {
175
+ "epoch": 0.19166666666666668,
176
+ "grad_norm": 0.15469100364725502,
177
+ "learning_rate": 1.872857142857143e-05,
178
+ "loss": 2.4275,
179
+ "step": 23
180
+ },
181
+ {
182
+ "epoch": 0.2,
183
+ "grad_norm": 0.1261136620302219,
184
+ "learning_rate": 1.9542857142857143e-05,
185
+ "loss": 2.3855,
186
+ "step": 24
187
+ },
188
+ {
189
+ "epoch": 0.20833333333333334,
190
+ "grad_norm": 0.1251566381945981,
191
+ "learning_rate": 2.0357142857142858e-05,
192
+ "loss": 2.4008,
193
+ "step": 25
194
+ },
195
+ {
196
+ "epoch": 0.21666666666666667,
197
+ "grad_norm": 0.12280228065778742,
198
+ "learning_rate": 2.1171428571428574e-05,
199
+ "loss": 2.4086,
200
+ "step": 26
201
+ },
202
+ {
203
+ "epoch": 0.225,
204
+ "grad_norm": 0.1362748806421765,
205
+ "learning_rate": 2.1985714285714286e-05,
206
+ "loss": 2.3642,
207
+ "step": 27
208
+ },
209
+ {
210
+ "epoch": 0.23333333333333334,
211
+ "grad_norm": 0.12370426656542512,
212
+ "learning_rate": 2.2800000000000002e-05,
213
+ "loss": 2.4168,
214
+ "step": 28
215
+ },
216
+ {
217
+ "epoch": 0.24166666666666667,
218
+ "grad_norm": 0.12077140199925576,
219
+ "learning_rate": 2.3614285714285718e-05,
220
+ "loss": 2.3502,
221
+ "step": 29
222
+ },
223
+ {
224
+ "epoch": 0.25,
225
+ "grad_norm": 0.10854652278245232,
226
+ "learning_rate": 2.442857142857143e-05,
227
+ "loss": 2.323,
228
+ "step": 30
229
+ },
230
+ {
231
+ "epoch": 0.25,
232
+ "eval_loss": 2.4455511569976807,
233
+ "eval_runtime": 82.5732,
234
+ "eval_samples_per_second": 4.965,
235
+ "eval_steps_per_second": 0.315,
236
+ "step": 30
237
+ },
238
+ {
239
+ "epoch": 0.25833333333333336,
240
+ "grad_norm": 0.10286886191993252,
241
+ "learning_rate": 2.5242857142857142e-05,
242
+ "loss": 2.4007,
243
+ "step": 31
244
+ },
245
+ {
246
+ "epoch": 0.26666666666666666,
247
+ "grad_norm": 0.09687340891245565,
248
+ "learning_rate": 2.6057142857142858e-05,
249
+ "loss": 2.4088,
250
+ "step": 32
251
+ },
252
+ {
253
+ "epoch": 0.275,
254
+ "grad_norm": 0.09653492248714694,
255
+ "learning_rate": 2.6871428571428574e-05,
256
+ "loss": 2.3906,
257
+ "step": 33
258
+ },
259
+ {
260
+ "epoch": 0.2833333333333333,
261
+ "grad_norm": 0.09022900019263645,
262
+ "learning_rate": 2.7685714285714286e-05,
263
+ "loss": 2.4065,
264
+ "step": 34
265
+ },
266
+ {
267
+ "epoch": 0.2916666666666667,
268
+ "grad_norm": 0.0912409242342349,
269
+ "learning_rate": 2.85e-05,
270
+ "loss": 2.3699,
271
+ "step": 35
272
+ },
273
+ {
274
+ "epoch": 0.3,
275
+ "grad_norm": 0.09592020125185927,
276
+ "learning_rate": 2.8499644890093217e-05,
277
+ "loss": 2.3587,
278
+ "step": 36
279
+ },
280
+ {
281
+ "epoch": 0.30833333333333335,
282
+ "grad_norm": 0.0907084429462166,
283
+ "learning_rate": 2.8498579578071537e-05,
284
+ "loss": 2.4259,
285
+ "step": 37
286
+ },
287
+ {
288
+ "epoch": 0.31666666666666665,
289
+ "grad_norm": 0.09390099422567517,
290
+ "learning_rate": 2.8496804117030106e-05,
291
+ "loss": 2.3232,
292
+ "step": 38
293
+ },
294
+ {
295
+ "epoch": 0.325,
296
+ "grad_norm": 0.08704027284958313,
297
+ "learning_rate": 2.849431859545787e-05,
298
+ "loss": 2.4027,
299
+ "step": 39
300
+ },
301
+ {
302
+ "epoch": 0.3333333333333333,
303
+ "grad_norm": 0.08787482564111378,
304
+ "learning_rate": 2.849112313723319e-05,
305
+ "loss": 2.3827,
306
+ "step": 40
307
+ },
308
+ {
309
+ "epoch": 0.3416666666666667,
310
+ "grad_norm": 0.08422520058818864,
311
+ "learning_rate": 2.8487217901617672e-05,
312
+ "loss": 2.353,
313
+ "step": 41
314
+ },
315
+ {
316
+ "epoch": 0.35,
317
+ "grad_norm": 0.07979320980153469,
318
+ "learning_rate": 2.84826030832482e-05,
319
+ "loss": 2.3519,
320
+ "step": 42
321
+ },
322
+ {
323
+ "epoch": 0.35833333333333334,
324
+ "grad_norm": 0.07814774416810645,
325
+ "learning_rate": 2.8477278912127266e-05,
326
+ "loss": 2.3708,
327
+ "step": 43
328
+ },
329
+ {
330
+ "epoch": 0.36666666666666664,
331
+ "grad_norm": 0.07237049854036091,
332
+ "learning_rate": 2.847124565361149e-05,
333
+ "loss": 2.388,
334
+ "step": 44
335
+ },
336
+ {
337
+ "epoch": 0.375,
338
+ "grad_norm": 0.07354258492789081,
339
+ "learning_rate": 2.8464503608398385e-05,
340
+ "loss": 2.3586,
341
+ "step": 45
342
+ },
343
+ {
344
+ "epoch": 0.38333333333333336,
345
+ "grad_norm": 0.0771281784161838,
346
+ "learning_rate": 2.845705311251141e-05,
347
+ "loss": 2.3993,
348
+ "step": 46
349
+ },
350
+ {
351
+ "epoch": 0.39166666666666666,
352
+ "grad_norm": 0.0763264062020341,
353
+ "learning_rate": 2.844889453728318e-05,
354
+ "loss": 2.3838,
355
+ "step": 47
356
+ },
357
+ {
358
+ "epoch": 0.4,
359
+ "grad_norm": 0.07082143620733677,
360
+ "learning_rate": 2.8440028289336977e-05,
361
+ "loss": 2.3628,
362
+ "step": 48
363
+ },
364
+ {
365
+ "epoch": 0.4083333333333333,
366
+ "grad_norm": 0.0715578975320661,
367
+ "learning_rate": 2.8430454810566477e-05,
368
+ "loss": 2.361,
369
+ "step": 49
370
+ },
371
+ {
372
+ "epoch": 0.4166666666666667,
373
+ "grad_norm": 0.06881630985450242,
374
+ "learning_rate": 2.8420174578113747e-05,
375
+ "loss": 2.4392,
376
+ "step": 50
377
+ },
378
+ {
379
+ "epoch": 0.425,
380
+ "grad_norm": 0.0689279893077156,
381
+ "learning_rate": 2.8409188104345426e-05,
382
+ "loss": 2.3519,
383
+ "step": 51
384
+ },
385
+ {
386
+ "epoch": 0.43333333333333335,
387
+ "grad_norm": 0.07069081407018309,
388
+ "learning_rate": 2.8397495936827232e-05,
389
+ "loss": 2.3981,
390
+ "step": 52
391
+ },
392
+ {
393
+ "epoch": 0.44166666666666665,
394
+ "grad_norm": 0.07092917277421104,
395
+ "learning_rate": 2.8385098658296637e-05,
396
+ "loss": 2.355,
397
+ "step": 53
398
+ },
399
+ {
400
+ "epoch": 0.45,
401
+ "grad_norm": 0.0703607034709259,
402
+ "learning_rate": 2.8371996886633843e-05,
403
+ "loss": 2.3793,
404
+ "step": 54
405
+ },
406
+ {
407
+ "epoch": 0.4583333333333333,
408
+ "grad_norm": 0.07124199690967324,
409
+ "learning_rate": 2.8358191274830974e-05,
410
+ "loss": 2.4275,
411
+ "step": 55
412
+ },
413
+ {
414
+ "epoch": 0.4666666666666667,
415
+ "grad_norm": 0.07099804346309355,
416
+ "learning_rate": 2.8343682510959552e-05,
417
+ "loss": 2.3323,
418
+ "step": 56
419
+ },
420
+ {
421
+ "epoch": 0.475,
422
+ "grad_norm": 0.06967632308939245,
423
+ "learning_rate": 2.8328471318136165e-05,
424
+ "loss": 2.3883,
425
+ "step": 57
426
+ },
427
+ {
428
+ "epoch": 0.48333333333333334,
429
+ "grad_norm": 0.07156300179553134,
430
+ "learning_rate": 2.831255845448647e-05,
431
+ "loss": 2.3298,
432
+ "step": 58
433
+ },
434
+ {
435
+ "epoch": 0.49166666666666664,
436
+ "grad_norm": 0.0704201532980033,
437
+ "learning_rate": 2.8295944713107387e-05,
438
+ "loss": 2.331,
439
+ "step": 59
440
+ },
441
+ {
442
+ "epoch": 0.5,
443
+ "grad_norm": 0.06794782460291071,
444
+ "learning_rate": 2.8278630922027563e-05,
445
+ "loss": 2.3776,
446
+ "step": 60
447
+ },
448
+ {
449
+ "epoch": 0.5,
450
+ "eval_loss": 2.4216628074645996,
451
+ "eval_runtime": 82.3879,
452
+ "eval_samples_per_second": 4.976,
453
+ "eval_steps_per_second": 0.316,
454
+ "step": 60
455
+ },
456
+ {
457
+ "epoch": 0.5083333333333333,
458
+ "grad_norm": 0.07045949082426937,
459
+ "learning_rate": 2.8260617944166123e-05,
460
+ "loss": 2.3319,
461
+ "step": 61
462
+ },
463
+ {
464
+ "epoch": 0.5166666666666667,
465
+ "grad_norm": 0.0702234192794877,
466
+ "learning_rate": 2.824190667728965e-05,
467
+ "loss": 2.3647,
468
+ "step": 62
469
+ },
470
+ {
471
+ "epoch": 0.525,
472
+ "grad_norm": 0.06946814214632402,
473
+ "learning_rate": 2.8222498053967434e-05,
474
+ "loss": 2.3967,
475
+ "step": 63
476
+ },
477
+ {
478
+ "epoch": 0.5333333333333333,
479
+ "grad_norm": 0.06563265580127577,
480
+ "learning_rate": 2.8202393041525005e-05,
481
+ "loss": 2.3863,
482
+ "step": 64
483
+ },
484
+ {
485
+ "epoch": 0.5416666666666666,
486
+ "grad_norm": 0.0723770670150652,
487
+ "learning_rate": 2.8181592641995933e-05,
488
+ "loss": 2.3823,
489
+ "step": 65
490
+ },
491
+ {
492
+ "epoch": 0.55,
493
+ "grad_norm": 0.06870429029917037,
494
+ "learning_rate": 2.8160097892071847e-05,
495
+ "loss": 2.3241,
496
+ "step": 66
497
+ },
498
+ {
499
+ "epoch": 0.5583333333333333,
500
+ "grad_norm": 0.08615444480664787,
501
+ "learning_rate": 2.8137909863050806e-05,
502
+ "loss": 2.3504,
503
+ "step": 67
504
+ },
505
+ {
506
+ "epoch": 0.5666666666666667,
507
+ "grad_norm": 0.06980417460436542,
508
+ "learning_rate": 2.8115029660783887e-05,
509
+ "loss": 2.3762,
510
+ "step": 68
511
+ },
512
+ {
513
+ "epoch": 0.575,
514
+ "grad_norm": 0.0691283200064781,
515
+ "learning_rate": 2.809145842562007e-05,
516
+ "loss": 2.3202,
517
+ "step": 69
518
+ },
519
+ {
520
+ "epoch": 0.5833333333333334,
521
+ "grad_norm": 0.06434433998677834,
522
+ "learning_rate": 2.8067197332349406e-05,
523
+ "loss": 2.4117,
524
+ "step": 70
525
+ },
526
+ {
527
+ "epoch": 0.5916666666666667,
528
+ "grad_norm": 0.06712521054811822,
529
+ "learning_rate": 2.8042247590144472e-05,
530
+ "loss": 2.4234,
531
+ "step": 71
532
+ },
533
+ {
534
+ "epoch": 0.6,
535
+ "grad_norm": 0.07781170630767965,
536
+ "learning_rate": 2.8016610442500087e-05,
537
+ "loss": 2.3614,
538
+ "step": 72
539
+ },
540
+ {
541
+ "epoch": 0.6083333333333333,
542
+ "grad_norm": 0.07179449259884696,
543
+ "learning_rate": 2.7990287167171357e-05,
544
+ "loss": 2.327,
545
+ "step": 73
546
+ },
547
+ {
548
+ "epoch": 0.6166666666666667,
549
+ "grad_norm": 0.0666012429917219,
550
+ "learning_rate": 2.7963279076109976e-05,
551
+ "loss": 2.3606,
552
+ "step": 74
553
+ },
554
+ {
555
+ "epoch": 0.625,
556
+ "grad_norm": 0.07042352420672252,
557
+ "learning_rate": 2.7935587515398855e-05,
558
+ "loss": 2.387,
559
+ "step": 75
560
+ },
561
+ {
562
+ "epoch": 0.6333333333333333,
563
+ "grad_norm": 0.07141219809062525,
564
+ "learning_rate": 2.7907213865185014e-05,
565
+ "loss": 2.3975,
566
+ "step": 76
567
+ },
568
+ {
569
+ "epoch": 0.6416666666666667,
570
+ "grad_norm": 0.07530038535140655,
571
+ "learning_rate": 2.787815953961081e-05,
572
+ "loss": 2.3975,
573
+ "step": 77
574
+ },
575
+ {
576
+ "epoch": 0.65,
577
+ "grad_norm": 0.06873021297298251,
578
+ "learning_rate": 2.784842598674345e-05,
579
+ "loss": 2.3724,
580
+ "step": 78
581
+ },
582
+ {
583
+ "epoch": 0.6583333333333333,
584
+ "grad_norm": 0.06853494667979494,
585
+ "learning_rate": 2.781801468850282e-05,
586
+ "loss": 2.3994,
587
+ "step": 79
588
+ },
589
+ {
590
+ "epoch": 0.6666666666666666,
591
+ "grad_norm": 0.07164446612343163,
592
+ "learning_rate": 2.778692716058762e-05,
593
+ "loss": 2.3448,
594
+ "step": 80
595
+ },
596
+ {
597
+ "epoch": 0.675,
598
+ "grad_norm": 0.07112624750325054,
599
+ "learning_rate": 2.7755164952399844e-05,
600
+ "loss": 2.2984,
601
+ "step": 81
602
+ },
603
+ {
604
+ "epoch": 0.6833333333333333,
605
+ "grad_norm": 0.07679055297227524,
606
+ "learning_rate": 2.7722729646967527e-05,
607
+ "loss": 2.3699,
608
+ "step": 82
609
+ },
610
+ {
611
+ "epoch": 0.6916666666666667,
612
+ "grad_norm": 0.07270378630883641,
613
+ "learning_rate": 2.768962286086587e-05,
614
+ "loss": 2.3436,
615
+ "step": 83
616
+ },
617
+ {
618
+ "epoch": 0.7,
619
+ "grad_norm": 0.06869524209312625,
620
+ "learning_rate": 2.7655846244136654e-05,
621
+ "loss": 2.3856,
622
+ "step": 84
623
+ },
624
+ {
625
+ "epoch": 0.7083333333333334,
626
+ "grad_norm": 0.07006104211903366,
627
+ "learning_rate": 2.762140148020602e-05,
628
+ "loss": 2.3852,
629
+ "step": 85
630
+ },
631
+ {
632
+ "epoch": 0.7166666666666667,
633
+ "grad_norm": 0.07264285304887648,
634
+ "learning_rate": 2.758629028580055e-05,
635
+ "loss": 2.3834,
636
+ "step": 86
637
+ },
638
+ {
639
+ "epoch": 0.725,
640
+ "grad_norm": 0.07253530482477301,
641
+ "learning_rate": 2.7550514410861718e-05,
642
+ "loss": 2.3573,
643
+ "step": 87
644
+ },
645
+ {
646
+ "epoch": 0.7333333333333333,
647
+ "grad_norm": 0.07265955522289944,
648
+ "learning_rate": 2.751407563845866e-05,
649
+ "loss": 2.3163,
650
+ "step": 88
651
+ },
652
+ {
653
+ "epoch": 0.7416666666666667,
654
+ "grad_norm": 0.07374626234739601,
655
+ "learning_rate": 2.747697578469931e-05,
656
+ "loss": 2.3851,
657
+ "step": 89
658
+ },
659
+ {
660
+ "epoch": 0.75,
661
+ "grad_norm": 0.07255481420091238,
662
+ "learning_rate": 2.7439216698639904e-05,
663
+ "loss": 2.3345,
664
+ "step": 90
665
+ },
666
+ {
667
+ "epoch": 0.75,
668
+ "eval_loss": 2.4115521907806396,
669
+ "eval_runtime": 82.0248,
670
+ "eval_samples_per_second": 4.998,
671
+ "eval_steps_per_second": 0.317,
672
+ "step": 90
673
+ },
674
+ {
675
+ "epoch": 0.7583333333333333,
676
+ "grad_norm": 0.06817548300510701,
677
+ "learning_rate": 2.7400800262192788e-05,
678
+ "loss": 2.3449,
679
+ "step": 91
680
+ },
681
+ {
682
+ "epoch": 0.7666666666666667,
683
+ "grad_norm": 0.07336990573663302,
684
+ "learning_rate": 2.7361728390032657e-05,
685
+ "loss": 2.3448,
686
+ "step": 92
687
+ },
688
+ {
689
+ "epoch": 0.775,
690
+ "grad_norm": 0.07822885886131264,
691
+ "learning_rate": 2.732200302950111e-05,
692
+ "loss": 2.3217,
693
+ "step": 93
694
+ },
695
+ {
696
+ "epoch": 0.7833333333333333,
697
+ "grad_norm": 0.07296512071361201,
698
+ "learning_rate": 2.728162616050959e-05,
699
+ "loss": 2.3329,
700
+ "step": 94
701
+ },
702
+ {
703
+ "epoch": 0.7916666666666666,
704
+ "grad_norm": 0.07367928865175823,
705
+ "learning_rate": 2.724059979544072e-05,
706
+ "loss": 2.3208,
707
+ "step": 95
708
+ },
709
+ {
710
+ "epoch": 0.8,
711
+ "grad_norm": 0.07504139519989858,
712
+ "learning_rate": 2.719892597904801e-05,
713
+ "loss": 2.3483,
714
+ "step": 96
715
+ },
716
+ {
717
+ "epoch": 0.8083333333333333,
718
+ "grad_norm": 0.06790757702451031,
719
+ "learning_rate": 2.7156606788353906e-05,
720
+ "loss": 2.4128,
721
+ "step": 97
722
+ },
723
+ {
724
+ "epoch": 0.8166666666666667,
725
+ "grad_norm": 0.07011160737870108,
726
+ "learning_rate": 2.7113644332546336e-05,
727
+ "loss": 2.3832,
728
+ "step": 98
729
+ },
730
+ {
731
+ "epoch": 0.825,
732
+ "grad_norm": 0.08077329808935288,
733
+ "learning_rate": 2.707004075287352e-05,
734
+ "loss": 2.3308,
735
+ "step": 99
736
+ },
737
+ {
738
+ "epoch": 0.8333333333333334,
739
+ "grad_norm": 0.0719496280235162,
740
+ "learning_rate": 2.7025798222537306e-05,
741
+ "loss": 2.3254,
742
+ "step": 100
743
+ },
744
+ {
745
+ "epoch": 0.8416666666666667,
746
+ "grad_norm": 0.07275409855582728,
747
+ "learning_rate": 2.698091894658483e-05,
748
+ "loss": 2.3967,
749
+ "step": 101
750
+ },
751
+ {
752
+ "epoch": 0.85,
753
+ "grad_norm": 0.07201531734077336,
754
+ "learning_rate": 2.693540516179861e-05,
755
+ "loss": 2.3346,
756
+ "step": 102
757
+ },
758
+ {
759
+ "epoch": 0.8583333333333333,
760
+ "grad_norm": 0.0765467775604243,
761
+ "learning_rate": 2.6889259136585094e-05,
762
+ "loss": 2.3336,
763
+ "step": 103
764
+ },
765
+ {
766
+ "epoch": 0.8666666666666667,
767
+ "grad_norm": 0.077223728318478,
768
+ "learning_rate": 2.6842483170861568e-05,
769
+ "loss": 2.3313,
770
+ "step": 104
771
+ },
772
+ {
773
+ "epoch": 0.875,
774
+ "grad_norm": 0.07639332869289207,
775
+ "learning_rate": 2.6795079595941553e-05,
776
+ "loss": 2.4008,
777
+ "step": 105
778
+ },
779
+ {
780
+ "epoch": 0.8833333333333333,
781
+ "grad_norm": 0.07440505813328589,
782
+ "learning_rate": 2.6747050774418605e-05,
783
+ "loss": 2.3425,
784
+ "step": 106
785
+ },
786
+ {
787
+ "epoch": 0.8916666666666667,
788
+ "grad_norm": 0.06937810484842656,
789
+ "learning_rate": 2.6698399100048556e-05,
790
+ "loss": 2.3349,
791
+ "step": 107
792
+ },
793
+ {
794
+ "epoch": 0.9,
795
+ "grad_norm": 0.07336400555418392,
796
+ "learning_rate": 2.6649126997630225e-05,
797
+ "loss": 2.3792,
798
+ "step": 108
799
+ },
800
+ {
801
+ "epoch": 0.9083333333333333,
802
+ "grad_norm": 0.07442564570941794,
803
+ "learning_rate": 2.6599236922884547e-05,
804
+ "loss": 2.3683,
805
+ "step": 109
806
+ },
807
+ {
808
+ "epoch": 0.9166666666666666,
809
+ "grad_norm": 0.07470689463768693,
810
+ "learning_rate": 2.65487313623322e-05,
811
+ "loss": 2.3036,
812
+ "step": 110
813
+ },
814
+ {
815
+ "epoch": 0.925,
816
+ "grad_norm": 0.07096997017300663,
817
+ "learning_rate": 2.649761283316966e-05,
818
+ "loss": 2.3682,
819
+ "step": 111
820
+ },
821
+ {
822
+ "epoch": 0.9333333333333333,
823
+ "grad_norm": 0.07511821034386772,
824
+ "learning_rate": 2.6445883883143744e-05,
825
+ "loss": 2.3346,
826
+ "step": 112
827
+ },
828
+ {
829
+ "epoch": 0.9416666666666667,
830
+ "grad_norm": 0.07057540374817312,
831
+ "learning_rate": 2.639354709042466e-05,
832
+ "loss": 2.3502,
833
+ "step": 113
834
+ },
835
+ {
836
+ "epoch": 0.95,
837
+ "grad_norm": 0.07300364605060353,
838
+ "learning_rate": 2.6340605063477456e-05,
839
+ "loss": 2.3711,
840
+ "step": 114
841
+ },
842
+ {
843
+ "epoch": 0.9583333333333334,
844
+ "grad_norm": 0.06925480258849577,
845
+ "learning_rate": 2.628706044093207e-05,
846
+ "loss": 2.3816,
847
+ "step": 115
848
+ },
849
+ {
850
+ "epoch": 0.9666666666666667,
851
+ "grad_norm": 0.0705107307569524,
852
+ "learning_rate": 2.623291589145179e-05,
853
+ "loss": 2.2958,
854
+ "step": 116
855
+ },
856
+ {
857
+ "epoch": 0.975,
858
+ "grad_norm": 0.07331112076487026,
859
+ "learning_rate": 2.6178174113600252e-05,
860
+ "loss": 2.3279,
861
+ "step": 117
862
+ },
863
+ {
864
+ "epoch": 0.9833333333333333,
865
+ "grad_norm": 0.06780655482074792,
866
+ "learning_rate": 2.612283783570695e-05,
867
+ "loss": 2.4117,
868
+ "step": 118
869
+ },
870
+ {
871
+ "epoch": 0.9916666666666667,
872
+ "grad_norm": 0.07485055181125701,
873
+ "learning_rate": 2.606690981573125e-05,
874
+ "loss": 2.303,
875
+ "step": 119
876
+ },
877
+ {
878
+ "epoch": 1.0,
879
+ "grad_norm": 0.07276467760742707,
880
+ "learning_rate": 2.6010392841124932e-05,
881
+ "loss": 2.3608,
882
+ "step": 120
883
+ },
884
+ {
885
+ "epoch": 1.0,
886
+ "eval_loss": 2.4049572944641113,
887
+ "eval_runtime": 82.3343,
888
+ "eval_samples_per_second": 4.98,
889
+ "eval_steps_per_second": 0.316,
890
+ "step": 120
891
+ },
892
+ {
893
+ "epoch": 1.0083333333333333,
894
+ "grad_norm": 0.07548790321925977,
895
+ "learning_rate": 2.5953289728693274e-05,
896
+ "loss": 2.3185,
897
+ "step": 121
898
+ },
899
+ {
900
+ "epoch": 1.0166666666666666,
901
+ "grad_norm": 0.0730570698984131,
902
+ "learning_rate": 2.5895603324454647e-05,
903
+ "loss": 2.2877,
904
+ "step": 122
905
+ },
906
+ {
907
+ "epoch": 1.025,
908
+ "grad_norm": 0.07345139782586493,
909
+ "learning_rate": 2.5837336503498694e-05,
910
+ "loss": 2.2836,
911
+ "step": 123
912
+ },
913
+ {
914
+ "epoch": 1.0333333333333334,
915
+ "grad_norm": 0.07299378924326991,
916
+ "learning_rate": 2.5778492169843003e-05,
917
+ "loss": 2.3436,
918
+ "step": 124
919
+ },
920
+ {
921
+ "epoch": 1.0416666666666667,
922
+ "grad_norm": 0.07154250149880004,
923
+ "learning_rate": 2.5719073256288394e-05,
924
+ "loss": 2.3822,
925
+ "step": 125
926
+ },
927
+ {
928
+ "epoch": 1.05,
929
+ "grad_norm": 0.0720748804004234,
930
+ "learning_rate": 2.565908272427274e-05,
931
+ "loss": 2.2708,
932
+ "step": 126
933
+ },
934
+ {
935
+ "epoch": 1.0583333333333333,
936
+ "grad_norm": 0.07269892036621302,
937
+ "learning_rate": 2.5598523563723373e-05,
938
+ "loss": 2.3377,
939
+ "step": 127
940
+ },
941
+ {
942
+ "epoch": 1.0666666666666667,
943
+ "grad_norm": 0.0756770863265576,
944
+ "learning_rate": 2.5537398792908062e-05,
945
+ "loss": 2.352,
946
+ "step": 128
947
+ },
948
+ {
949
+ "epoch": 1.075,
950
+ "grad_norm": 0.07397323539112335,
951
+ "learning_rate": 2.547571145828459e-05,
952
+ "loss": 2.3643,
953
+ "step": 129
954
+ },
955
+ {
956
+ "epoch": 1.0833333333333333,
957
+ "grad_norm": 0.07438211371538549,
958
+ "learning_rate": 2.54134646343489e-05,
959
+ "loss": 2.3387,
960
+ "step": 130
961
+ },
962
+ {
963
+ "epoch": 1.0916666666666666,
964
+ "grad_norm": 0.07094248712059498,
965
+ "learning_rate": 2.5350661423481885e-05,
966
+ "loss": 2.3221,
967
+ "step": 131
968
+ },
969
+ {
970
+ "epoch": 1.1,
971
+ "grad_norm": 0.0771622686218861,
972
+ "learning_rate": 2.5287304955794754e-05,
973
+ "loss": 2.3183,
974
+ "step": 132
975
+ },
976
+ {
977
+ "epoch": 1.1083333333333334,
978
+ "grad_norm": 0.07495056480159959,
979
+ "learning_rate": 2.5223398388973028e-05,
980
+ "loss": 2.3697,
981
+ "step": 133
982
+ },
983
+ {
984
+ "epoch": 1.1166666666666667,
985
+ "grad_norm": 0.07629199954207538,
986
+ "learning_rate": 2.515894490811916e-05,
987
+ "loss": 2.3529,
988
+ "step": 134
989
+ },
990
+ {
991
+ "epoch": 1.125,
992
+ "grad_norm": 0.0762534542729489,
993
+ "learning_rate": 2.5093947725593792e-05,
994
+ "loss": 2.3208,
995
+ "step": 135
996
+ },
997
+ {
998
+ "epoch": 1.1333333333333333,
999
+ "grad_norm": 0.07587427933984144,
1000
+ "learning_rate": 2.502841008085565e-05,
1001
+ "loss": 2.3448,
1002
+ "step": 136
1003
+ },
1004
+ {
1005
+ "epoch": 1.1416666666666666,
1006
+ "grad_norm": 0.07490456619530689,
1007
+ "learning_rate": 2.49623352403001e-05,
1008
+ "loss": 2.3435,
1009
+ "step": 137
1010
+ },
1011
+ {
1012
+ "epoch": 1.15,
1013
+ "grad_norm": 0.0744781797534131,
1014
+ "learning_rate": 2.4895726497096315e-05,
1015
+ "loss": 2.4,
1016
+ "step": 138
1017
+ },
1018
+ {
1019
+ "epoch": 1.1583333333333332,
1020
+ "grad_norm": 0.07464944817741491,
1021
+ "learning_rate": 2.482858717102319e-05,
1022
+ "loss": 2.318,
1023
+ "step": 139
1024
+ },
1025
+ {
1026
+ "epoch": 1.1666666666666667,
1027
+ "grad_norm": 0.07309033869975678,
1028
+ "learning_rate": 2.4760920608303867e-05,
1029
+ "loss": 2.2891,
1030
+ "step": 140
1031
+ },
1032
+ {
1033
+ "epoch": 1.175,
1034
+ "grad_norm": 0.07284517336177344,
1035
+ "learning_rate": 2.469273018143894e-05,
1036
+ "loss": 2.3051,
1037
+ "step": 141
1038
+ },
1039
+ {
1040
+ "epoch": 1.1833333333333333,
1041
+ "grad_norm": 0.07652064520411771,
1042
+ "learning_rate": 2.462401928903839e-05,
1043
+ "loss": 2.3555,
1044
+ "step": 142
1045
+ },
1046
+ {
1047
+ "epoch": 1.1916666666666667,
1048
+ "grad_norm": 0.07701974074136966,
1049
+ "learning_rate": 2.45547913556522e-05,
1050
+ "loss": 2.3015,
1051
+ "step": 143
1052
+ },
1053
+ {
1054
+ "epoch": 1.2,
1055
+ "grad_norm": 0.08108352272511765,
1056
+ "learning_rate": 2.448504983159966e-05,
1057
+ "loss": 2.3221,
1058
+ "step": 144
1059
+ },
1060
+ {
1061
+ "epoch": 1.2083333333333333,
1062
+ "grad_norm": 0.07752288456105606,
1063
+ "learning_rate": 2.441479819279742e-05,
1064
+ "loss": 2.3684,
1065
+ "step": 145
1066
+ },
1067
+ {
1068
+ "epoch": 1.2166666666666668,
1069
+ "grad_norm": 0.07881711814524053,
1070
+ "learning_rate": 2.4344039940586235e-05,
1071
+ "loss": 2.3011,
1072
+ "step": 146
1073
+ },
1074
+ {
1075
+ "epoch": 1.225,
1076
+ "grad_norm": 0.07757542042787384,
1077
+ "learning_rate": 2.4272778601556472e-05,
1078
+ "loss": 2.3509,
1079
+ "step": 147
1080
+ },
1081
+ {
1082
+ "epoch": 1.2333333333333334,
1083
+ "grad_norm": 0.07228965364348439,
1084
+ "learning_rate": 2.4201017727372336e-05,
1085
+ "loss": 2.3801,
1086
+ "step": 148
1087
+ },
1088
+ {
1089
+ "epoch": 1.2416666666666667,
1090
+ "grad_norm": 0.07389812003829682,
1091
+ "learning_rate": 2.4128760894594853e-05,
1092
+ "loss": 2.3359,
1093
+ "step": 149
1094
+ },
1095
+ {
1096
+ "epoch": 1.25,
1097
+ "grad_norm": 0.08146218033856112,
1098
+ "learning_rate": 2.4056011704503633e-05,
1099
+ "loss": 2.3096,
1100
+ "step": 150
1101
+ },
1102
+ {
1103
+ "epoch": 1.25,
1104
+ "eval_loss": 2.400259494781494,
1105
+ "eval_runtime": 81.604,
1106
+ "eval_samples_per_second": 5.024,
1107
+ "eval_steps_per_second": 0.319,
1108
+ "step": 150
1109
+ },
1110
+ {
1111
+ "epoch": 1.2583333333333333,
1112
+ "grad_norm": 0.07407260421175128,
1113
+ "learning_rate": 2.3982773782917347e-05,
1114
+ "loss": 2.3418,
1115
+ "step": 151
1116
+ },
1117
+ {
1118
+ "epoch": 1.2666666666666666,
1119
+ "grad_norm": 0.07827237096687646,
1120
+ "learning_rate": 2.390905078001306e-05,
1121
+ "loss": 2.2778,
1122
+ "step": 152
1123
+ },
1124
+ {
1125
+ "epoch": 1.275,
1126
+ "grad_norm": 0.07699758244967876,
1127
+ "learning_rate": 2.383484637014426e-05,
1128
+ "loss": 2.3245,
1129
+ "step": 153
1130
+ },
1131
+ {
1132
+ "epoch": 1.2833333333333332,
1133
+ "grad_norm": 0.07805943021524937,
1134
+ "learning_rate": 2.3760164251657773e-05,
1135
+ "loss": 2.3782,
1136
+ "step": 154
1137
+ },
1138
+ {
1139
+ "epoch": 1.2916666666666667,
1140
+ "grad_norm": 0.0741687347632035,
1141
+ "learning_rate": 2.368500814670941e-05,
1142
+ "loss": 2.3765,
1143
+ "step": 155
1144
+ },
1145
+ {
1146
+ "epoch": 1.3,
1147
+ "grad_norm": 0.07696079818166807,
1148
+ "learning_rate": 2.3609381801078448e-05,
1149
+ "loss": 2.3958,
1150
+ "step": 156
1151
+ },
1152
+ {
1153
+ "epoch": 1.3083333333333333,
1154
+ "grad_norm": 0.08864860865623735,
1155
+ "learning_rate": 2.3533288983980964e-05,
1156
+ "loss": 2.3482,
1157
+ "step": 157
1158
+ },
1159
+ {
1160
+ "epoch": 1.3166666666666667,
1161
+ "grad_norm": 0.07676755572584443,
1162
+ "learning_rate": 2.3456733487881978e-05,
1163
+ "loss": 2.3511,
1164
+ "step": 158
1165
+ },
1166
+ {
1167
+ "epoch": 1.325,
1168
+ "grad_norm": 0.07754541163995884,
1169
+ "learning_rate": 2.337971912830641e-05,
1170
+ "loss": 2.3754,
1171
+ "step": 159
1172
+ },
1173
+ {
1174
+ "epoch": 1.3333333333333333,
1175
+ "grad_norm": 0.08430746433268149,
1176
+ "learning_rate": 2.3302249743648926e-05,
1177
+ "loss": 2.4063,
1178
+ "step": 160
1179
+ },
1180
+ {
1181
+ "epoch": 1.3416666666666668,
1182
+ "grad_norm": 0.08113759941899056,
1183
+ "learning_rate": 2.322432919498265e-05,
1184
+ "loss": 2.3352,
1185
+ "step": 161
1186
+ },
1187
+ {
1188
+ "epoch": 1.35,
1189
+ "grad_norm": 0.08147516272984133,
1190
+ "learning_rate": 2.3145961365866708e-05,
1191
+ "loss": 2.3119,
1192
+ "step": 162
1193
+ },
1194
+ {
1195
+ "epoch": 1.3583333333333334,
1196
+ "grad_norm": 0.07749688842544009,
1197
+ "learning_rate": 2.3067150162152675e-05,
1198
+ "loss": 2.3547,
1199
+ "step": 163
1200
+ },
1201
+ {
1202
+ "epoch": 1.3666666666666667,
1203
+ "grad_norm": 0.08640326754187048,
1204
+ "learning_rate": 2.298789951178992e-05,
1205
+ "loss": 2.3389,
1206
+ "step": 164
1207
+ },
1208
+ {
1209
+ "epoch": 1.375,
1210
+ "grad_norm": 0.0795137333109577,
1211
+ "learning_rate": 2.2908213364629812e-05,
1212
+ "loss": 2.3778,
1213
+ "step": 165
1214
+ },
1215
+ {
1216
+ "epoch": 1.3833333333333333,
1217
+ "grad_norm": 0.07739334763959965,
1218
+ "learning_rate": 2.2828095692228886e-05,
1219
+ "loss": 2.3658,
1220
+ "step": 166
1221
+ },
1222
+ {
1223
+ "epoch": 1.3916666666666666,
1224
+ "grad_norm": 0.07783031237693959,
1225
+ "learning_rate": 2.2747550487650887e-05,
1226
+ "loss": 2.3575,
1227
+ "step": 167
1228
+ },
1229
+ {
1230
+ "epoch": 1.4,
1231
+ "grad_norm": 0.07682655233706284,
1232
+ "learning_rate": 2.2666581765267758e-05,
1233
+ "loss": 2.2825,
1234
+ "step": 168
1235
+ },
1236
+ {
1237
+ "epoch": 1.4083333333333332,
1238
+ "grad_norm": 0.08359081032268273,
1239
+ "learning_rate": 2.2585193560559563e-05,
1240
+ "loss": 2.261,
1241
+ "step": 169
1242
+ },
1243
+ {
1244
+ "epoch": 1.4166666666666667,
1245
+ "grad_norm": 0.0826940676306091,
1246
+ "learning_rate": 2.250338992991335e-05,
1247
+ "loss": 2.3069,
1248
+ "step": 170
1249
+ },
1250
+ {
1251
+ "epoch": 1.425,
1252
+ "grad_norm": 0.08462619097403327,
1253
+ "learning_rate": 2.2421174950421017e-05,
1254
+ "loss": 2.2864,
1255
+ "step": 171
1256
+ },
1257
+ {
1258
+ "epoch": 1.4333333333333333,
1259
+ "grad_norm": 0.07990029642375193,
1260
+ "learning_rate": 2.233855271967606e-05,
1261
+ "loss": 2.3033,
1262
+ "step": 172
1263
+ },
1264
+ {
1265
+ "epoch": 1.4416666666666667,
1266
+ "grad_norm": 0.08051779058857793,
1267
+ "learning_rate": 2.2255527355569372e-05,
1268
+ "loss": 2.3166,
1269
+ "step": 173
1270
+ },
1271
+ {
1272
+ "epoch": 1.45,
1273
+ "grad_norm": 0.08604667339713809,
1274
+ "learning_rate": 2.217210299608402e-05,
1275
+ "loss": 2.387,
1276
+ "step": 174
1277
+ },
1278
+ {
1279
+ "epoch": 1.4583333333333333,
1280
+ "grad_norm": 0.07829742536277012,
1281
+ "learning_rate": 2.208828379908899e-05,
1282
+ "loss": 2.311,
1283
+ "step": 175
1284
+ },
1285
+ {
1286
+ "epoch": 1.4666666666666668,
1287
+ "grad_norm": 0.07850219342360719,
1288
+ "learning_rate": 2.200407394213196e-05,
1289
+ "loss": 2.3384,
1290
+ "step": 176
1291
+ },
1292
+ {
1293
+ "epoch": 1.475,
1294
+ "grad_norm": 0.08531707041033702,
1295
+ "learning_rate": 2.19194776222311e-05,
1296
+ "loss": 2.3107,
1297
+ "step": 177
1298
+ },
1299
+ {
1300
+ "epoch": 1.4833333333333334,
1301
+ "grad_norm": 0.07652853009760147,
1302
+ "learning_rate": 2.183449905566589e-05,
1303
+ "loss": 2.3494,
1304
+ "step": 178
1305
+ },
1306
+ {
1307
+ "epoch": 1.4916666666666667,
1308
+ "grad_norm": 0.0797336095546633,
1309
+ "learning_rate": 2.1749142477766972e-05,
1310
+ "loss": 2.3291,
1311
+ "step": 179
1312
+ },
1313
+ {
1314
+ "epoch": 1.5,
1315
+ "grad_norm": 0.08700079540422817,
1316
+ "learning_rate": 2.166341214270507e-05,
1317
+ "loss": 2.3132,
1318
+ "step": 180
1319
+ },
1320
+ {
1321
+ "epoch": 1.5,
1322
+ "eval_loss": 2.3966128826141357,
1323
+ "eval_runtime": 83.184,
1324
+ "eval_samples_per_second": 4.929,
1325
+ "eval_steps_per_second": 0.313,
1326
+ "step": 180
1327
+ },
1328
+ {
1329
+ "epoch": 1.5083333333333333,
1330
+ "grad_norm": 0.07925581040107615,
1331
+ "learning_rate": 2.157731232327897e-05,
1332
+ "loss": 2.3578,
1333
+ "step": 181
1334
+ },
1335
+ {
1336
+ "epoch": 1.5166666666666666,
1337
+ "grad_norm": 0.07873086864048841,
1338
+ "learning_rate": 2.1490847310702544e-05,
1339
+ "loss": 2.3229,
1340
+ "step": 182
1341
+ },
1342
+ {
1343
+ "epoch": 1.525,
1344
+ "grad_norm": 0.07775316849537767,
1345
+ "learning_rate": 2.1404021414390874e-05,
1346
+ "loss": 2.3756,
1347
+ "step": 183
1348
+ },
1349
+ {
1350
+ "epoch": 1.5333333333333332,
1351
+ "grad_norm": 0.07949428482523528,
1352
+ "learning_rate": 2.1316838961745518e-05,
1353
+ "loss": 2.3535,
1354
+ "step": 184
1355
+ },
1356
+ {
1357
+ "epoch": 1.5416666666666665,
1358
+ "grad_norm": 0.08423278187074197,
1359
+ "learning_rate": 2.1229304297938755e-05,
1360
+ "loss": 2.3517,
1361
+ "step": 185
1362
+ },
1363
+ {
1364
+ "epoch": 1.55,
1365
+ "grad_norm": 0.07930583119038707,
1366
+ "learning_rate": 2.1141421785697097e-05,
1367
+ "loss": 2.3929,
1368
+ "step": 186
1369
+ },
1370
+ {
1371
+ "epoch": 1.5583333333333333,
1372
+ "grad_norm": 0.07736840323261199,
1373
+ "learning_rate": 2.1053195805083803e-05,
1374
+ "loss": 2.3194,
1375
+ "step": 187
1376
+ },
1377
+ {
1378
+ "epoch": 1.5666666666666667,
1379
+ "grad_norm": 0.08306421066524537,
1380
+ "learning_rate": 2.0964630753280584e-05,
1381
+ "loss": 2.3131,
1382
+ "step": 188
1383
+ },
1384
+ {
1385
+ "epoch": 1.575,
1386
+ "grad_norm": 0.0805185815818936,
1387
+ "learning_rate": 2.0875731044368472e-05,
1388
+ "loss": 2.3238,
1389
+ "step": 189
1390
+ },
1391
+ {
1392
+ "epoch": 1.5833333333333335,
1393
+ "grad_norm": 0.07729948838070921,
1394
+ "learning_rate": 2.078650110910779e-05,
1395
+ "loss": 2.3279,
1396
+ "step": 190
1397
+ },
1398
+ {
1399
+ "epoch": 1.5916666666666668,
1400
+ "grad_norm": 0.08053951644296133,
1401
+ "learning_rate": 2.0696945394717355e-05,
1402
+ "loss": 2.3343,
1403
+ "step": 191
1404
+ },
1405
+ {
1406
+ "epoch": 1.6,
1407
+ "grad_norm": 0.08184664333069269,
1408
+ "learning_rate": 2.0607068364652783e-05,
1409
+ "loss": 2.3441,
1410
+ "step": 192
1411
+ },
1412
+ {
1413
+ "epoch": 1.6083333333333334,
1414
+ "grad_norm": 0.07894699650259683,
1415
+ "learning_rate": 2.051687449838409e-05,
1416
+ "loss": 2.3384,
1417
+ "step": 193
1418
+ },
1419
+ {
1420
+ "epoch": 1.6166666666666667,
1421
+ "grad_norm": 0.08288692832517489,
1422
+ "learning_rate": 2.042636829117239e-05,
1423
+ "loss": 2.3219,
1424
+ "step": 194
1425
+ },
1426
+ {
1427
+ "epoch": 1.625,
1428
+ "grad_norm": 0.09061769591669266,
1429
+ "learning_rate": 2.033555425384586e-05,
1430
+ "loss": 2.3168,
1431
+ "step": 195
1432
+ },
1433
+ {
1434
+ "epoch": 1.6333333333333333,
1435
+ "grad_norm": 0.07607427061534017,
1436
+ "learning_rate": 2.0244436912574938e-05,
1437
+ "loss": 2.3592,
1438
+ "step": 196
1439
+ },
1440
+ {
1441
+ "epoch": 1.6416666666666666,
1442
+ "grad_norm": 0.08827457673533141,
1443
+ "learning_rate": 2.0153020808646715e-05,
1444
+ "loss": 2.3177,
1445
+ "step": 197
1446
+ },
1447
+ {
1448
+ "epoch": 1.65,
1449
+ "grad_norm": 0.0757688204165182,
1450
+ "learning_rate": 2.0061310498238618e-05,
1451
+ "loss": 2.2366,
1452
+ "step": 198
1453
+ },
1454
+ {
1455
+ "epoch": 1.6583333333333332,
1456
+ "grad_norm": 0.07815852114026649,
1457
+ "learning_rate": 1.996931055219132e-05,
1458
+ "loss": 2.3161,
1459
+ "step": 199
1460
+ },
1461
+ {
1462
+ "epoch": 1.6666666666666665,
1463
+ "grad_norm": 0.08058901889279678,
1464
+ "learning_rate": 1.9877025555780927e-05,
1465
+ "loss": 2.3749,
1466
+ "step": 200
1467
+ },
1468
+ {
1469
+ "epoch": 1.675,
1470
+ "grad_norm": 0.07708027281441528,
1471
+ "learning_rate": 1.978446010849045e-05,
1472
+ "loss": 2.2854,
1473
+ "step": 201
1474
+ },
1475
+ {
1476
+ "epoch": 1.6833333333333333,
1477
+ "grad_norm": 0.08312283019758401,
1478
+ "learning_rate": 1.969161882378058e-05,
1479
+ "loss": 2.3524,
1480
+ "step": 202
1481
+ },
1482
+ {
1483
+ "epoch": 1.6916666666666667,
1484
+ "grad_norm": 0.07784046601849169,
1485
+ "learning_rate": 1.9598506328859717e-05,
1486
+ "loss": 2.3418,
1487
+ "step": 203
1488
+ },
1489
+ {
1490
+ "epoch": 1.7,
1491
+ "grad_norm": 0.07906237498578873,
1492
+ "learning_rate": 1.95051272644534e-05,
1493
+ "loss": 2.3514,
1494
+ "step": 204
1495
+ },
1496
+ {
1497
+ "epoch": 1.7083333333333335,
1498
+ "grad_norm": 0.08323464269988524,
1499
+ "learning_rate": 1.9411486284572977e-05,
1500
+ "loss": 2.3133,
1501
+ "step": 205
1502
+ },
1503
+ {
1504
+ "epoch": 1.7166666666666668,
1505
+ "grad_norm": 0.08153670371604982,
1506
+ "learning_rate": 1.931758805628366e-05,
1507
+ "loss": 2.3388,
1508
+ "step": 206
1509
+ },
1510
+ {
1511
+ "epoch": 1.725,
1512
+ "grad_norm": 0.08152589045596419,
1513
+ "learning_rate": 1.9223437259471912e-05,
1514
+ "loss": 2.3309,
1515
+ "step": 207
1516
+ },
1517
+ {
1518
+ "epoch": 1.7333333333333334,
1519
+ "grad_norm": 0.08382345786042532,
1520
+ "learning_rate": 1.9129038586612224e-05,
1521
+ "loss": 2.3282,
1522
+ "step": 208
1523
+ },
1524
+ {
1525
+ "epoch": 1.7416666666666667,
1526
+ "grad_norm": 0.0835609429134592,
1527
+ "learning_rate": 1.903439674253321e-05,
1528
+ "loss": 2.3567,
1529
+ "step": 209
1530
+ },
1531
+ {
1532
+ "epoch": 1.75,
1533
+ "grad_norm": 0.08252984125014622,
1534
+ "learning_rate": 1.8939516444183143e-05,
1535
+ "loss": 2.3352,
1536
+ "step": 210
1537
+ },
1538
+ {
1539
+ "epoch": 1.75,
1540
+ "eval_loss": 2.3933684825897217,
1541
+ "eval_runtime": 83.3063,
1542
+ "eval_samples_per_second": 4.922,
1543
+ "eval_steps_per_second": 0.312,
1544
+ "step": 210
1545
+ },
1546
+ {
1547
+ "epoch": 1.7583333333333333,
1548
+ "grad_norm": 0.0815481053340795,
1549
+ "learning_rate": 1.884440242039485e-05,
1550
+ "loss": 2.3262,
1551
+ "step": 211
1552
+ },
1553
+ {
1554
+ "epoch": 1.7666666666666666,
1555
+ "grad_norm": 0.08258761118218041,
1556
+ "learning_rate": 1.8749059411650034e-05,
1557
+ "loss": 2.3396,
1558
+ "step": 212
1559
+ },
1560
+ {
1561
+ "epoch": 1.775,
1562
+ "grad_norm": 0.0884999967331726,
1563
+ "learning_rate": 1.8653492169843003e-05,
1564
+ "loss": 2.3176,
1565
+ "step": 213
1566
+ },
1567
+ {
1568
+ "epoch": 1.7833333333333332,
1569
+ "grad_norm": 0.0824785010834098,
1570
+ "learning_rate": 1.8557705458043838e-05,
1571
+ "loss": 2.3272,
1572
+ "step": 214
1573
+ },
1574
+ {
1575
+ "epoch": 1.7916666666666665,
1576
+ "grad_norm": 0.08727167025374602,
1577
+ "learning_rate": 1.8461704050261e-05,
1578
+ "loss": 2.2298,
1579
+ "step": 215
1580
+ },
1581
+ {
1582
+ "epoch": 1.8,
1583
+ "grad_norm": 0.0768016904891171,
1584
+ "learning_rate": 1.8365492731203398e-05,
1585
+ "loss": 2.3554,
1586
+ "step": 216
1587
+ },
1588
+ {
1589
+ "epoch": 1.8083333333333333,
1590
+ "grad_norm": 0.07709533586121158,
1591
+ "learning_rate": 1.8269076296041917e-05,
1592
+ "loss": 2.3702,
1593
+ "step": 217
1594
+ },
1595
+ {
1596
+ "epoch": 1.8166666666666667,
1597
+ "grad_norm": 0.0806446736093232,
1598
+ "learning_rate": 1.8172459550170424e-05,
1599
+ "loss": 2.3585,
1600
+ "step": 218
1601
+ },
1602
+ {
1603
+ "epoch": 1.825,
1604
+ "grad_norm": 0.07523532523458193,
1605
+ "learning_rate": 1.8075647308966268e-05,
1606
+ "loss": 2.3609,
1607
+ "step": 219
1608
+ },
1609
+ {
1610
+ "epoch": 1.8333333333333335,
1611
+ "grad_norm": 0.07497201271988578,
1612
+ "learning_rate": 1.797864439755028e-05,
1613
+ "loss": 2.3755,
1614
+ "step": 220
1615
+ },
1616
+ {
1617
+ "epoch": 1.8416666666666668,
1618
+ "grad_norm": 0.08249074177996166,
1619
+ "learning_rate": 1.7881455650546303e-05,
1620
+ "loss": 2.372,
1621
+ "step": 221
1622
+ },
1623
+ {
1624
+ "epoch": 1.85,
1625
+ "grad_norm": 0.0780160636961897,
1626
+ "learning_rate": 1.7784085911840214e-05,
1627
+ "loss": 2.3823,
1628
+ "step": 222
1629
+ },
1630
+ {
1631
+ "epoch": 1.8583333333333334,
1632
+ "grad_norm": 0.08148680526536918,
1633
+ "learning_rate": 1.7686540034338513e-05,
1634
+ "loss": 2.3314,
1635
+ "step": 223
1636
+ },
1637
+ {
1638
+ "epoch": 1.8666666666666667,
1639
+ "grad_norm": 0.0795864595636552,
1640
+ "learning_rate": 1.758882287972646e-05,
1641
+ "loss": 2.2853,
1642
+ "step": 224
1643
+ },
1644
+ {
1645
+ "epoch": 1.875,
1646
+ "grad_norm": 0.08198344669246531,
1647
+ "learning_rate": 1.749093931822577e-05,
1648
+ "loss": 2.3605,
1649
+ "step": 225
1650
+ },
1651
+ {
1652
+ "epoch": 1.8833333333333333,
1653
+ "grad_norm": 0.08138145213474299,
1654
+ "learning_rate": 1.739289422835185e-05,
1655
+ "loss": 2.2721,
1656
+ "step": 226
1657
+ },
1658
+ {
1659
+ "epoch": 1.8916666666666666,
1660
+ "grad_norm": 0.08306015511124677,
1661
+ "learning_rate": 1.7294692496670715e-05,
1662
+ "loss": 2.2889,
1663
+ "step": 227
1664
+ },
1665
+ {
1666
+ "epoch": 1.9,
1667
+ "grad_norm": 0.07478727556401082,
1668
+ "learning_rate": 1.7196339017555378e-05,
1669
+ "loss": 2.3416,
1670
+ "step": 228
1671
+ },
1672
+ {
1673
+ "epoch": 1.9083333333333332,
1674
+ "grad_norm": 0.08858459574829487,
1675
+ "learning_rate": 1.709783869294196e-05,
1676
+ "loss": 2.3081,
1677
+ "step": 229
1678
+ },
1679
+ {
1680
+ "epoch": 1.9166666666666665,
1681
+ "grad_norm": 0.08175368181940743,
1682
+ "learning_rate": 1.699919643208533e-05,
1683
+ "loss": 2.3304,
1684
+ "step": 230
1685
+ },
1686
+ {
1687
+ "epoch": 1.925,
1688
+ "grad_norm": 0.07630479738636474,
1689
+ "learning_rate": 1.6900417151314503e-05,
1690
+ "loss": 2.3454,
1691
+ "step": 231
1692
+ },
1693
+ {
1694
+ "epoch": 1.9333333333333333,
1695
+ "grad_norm": 0.07687273996639293,
1696
+ "learning_rate": 1.6801505773787527e-05,
1697
+ "loss": 2.3901,
1698
+ "step": 232
1699
+ },
1700
+ {
1701
+ "epoch": 1.9416666666666667,
1702
+ "grad_norm": 0.08600269874202937,
1703
+ "learning_rate": 1.670246722924616e-05,
1704
+ "loss": 2.3081,
1705
+ "step": 233
1706
+ },
1707
+ {
1708
+ "epoch": 1.95,
1709
+ "grad_norm": 0.07737694968965858,
1710
+ "learning_rate": 1.660330645377018e-05,
1711
+ "loss": 2.3643,
1712
+ "step": 234
1713
+ },
1714
+ {
1715
+ "epoch": 1.9583333333333335,
1716
+ "grad_norm": 0.08165758061569027,
1717
+ "learning_rate": 1.6504028389531333e-05,
1718
+ "loss": 2.355,
1719
+ "step": 235
1720
+ },
1721
+ {
1722
+ "epoch": 1.9666666666666668,
1723
+ "grad_norm": 0.08264378429137093,
1724
+ "learning_rate": 1.640463798454704e-05,
1725
+ "loss": 2.3219,
1726
+ "step": 236
1727
+ },
1728
+ {
1729
+ "epoch": 1.975,
1730
+ "grad_norm": 0.0858368818345628,
1731
+ "learning_rate": 1.6305140192433787e-05,
1732
+ "loss": 2.3329,
1733
+ "step": 237
1734
+ },
1735
+ {
1736
+ "epoch": 1.9833333333333334,
1737
+ "grad_norm": 0.07616999163161729,
1738
+ "learning_rate": 1.620553997216023e-05,
1739
+ "loss": 2.3523,
1740
+ "step": 238
1741
+ },
1742
+ {
1743
+ "epoch": 1.9916666666666667,
1744
+ "grad_norm": 0.08241527325980988,
1745
+ "learning_rate": 1.6105842287800046e-05,
1746
+ "loss": 2.2982,
1747
+ "step": 239
1748
+ },
1749
+ {
1750
+ "epoch": 2.0,
1751
+ "grad_norm": 0.08007891750583127,
1752
+ "learning_rate": 1.600605210828451e-05,
1753
+ "loss": 2.2785,
1754
+ "step": 240
1755
+ },
1756
+ {
1757
+ "epoch": 2.0,
1758
+ "eval_loss": 2.3910558223724365,
1759
+ "eval_runtime": 83.4904,
1760
+ "eval_samples_per_second": 4.911,
1761
+ "eval_steps_per_second": 0.311,
1762
+ "step": 240
1763
+ },
1764
+ {
1765
+ "epoch": 2.0083333333333333,
1766
+ "grad_norm": 0.08108687194604622,
1767
+ "learning_rate": 1.5906174407154883e-05,
1768
+ "loss": 2.3367,
1769
+ "step": 241
1770
+ },
1771
+ {
1772
+ "epoch": 2.0166666666666666,
1773
+ "grad_norm": 0.0806511417182259,
1774
+ "learning_rate": 1.5806214162314463e-05,
1775
+ "loss": 2.3011,
1776
+ "step": 242
1777
+ },
1778
+ {
1779
+ "epoch": 2.025,
1780
+ "grad_norm": 0.08264392219751603,
1781
+ "learning_rate": 1.5706176355780556e-05,
1782
+ "loss": 2.3036,
1783
+ "step": 243
1784
+ },
1785
+ {
1786
+ "epoch": 2.033333333333333,
1787
+ "grad_norm": 0.07958409681135217,
1788
+ "learning_rate": 1.5606065973436132e-05,
1789
+ "loss": 2.3056,
1790
+ "step": 244
1791
+ },
1792
+ {
1793
+ "epoch": 2.0416666666666665,
1794
+ "grad_norm": 0.07856642651007223,
1795
+ "learning_rate": 1.550588800478133e-05,
1796
+ "loss": 2.3692,
1797
+ "step": 245
1798
+ },
1799
+ {
1800
+ "epoch": 2.05,
1801
+ "grad_norm": 0.08350216798892127,
1802
+ "learning_rate": 1.5405647442684794e-05,
1803
+ "loss": 2.2697,
1804
+ "step": 246
1805
+ },
1806
+ {
1807
+ "epoch": 2.058333333333333,
1808
+ "grad_norm": 0.08390645284684875,
1809
+ "learning_rate": 1.530534928313484e-05,
1810
+ "loss": 2.2425,
1811
+ "step": 247
1812
+ },
1813
+ {
1814
+ "epoch": 2.066666666666667,
1815
+ "grad_norm": 0.07883358190907572,
1816
+ "learning_rate": 1.5204998524990423e-05,
1817
+ "loss": 2.3281,
1818
+ "step": 248
1819
+ },
1820
+ {
1821
+ "epoch": 2.075,
1822
+ "grad_norm": 0.07994560560782488,
1823
+ "learning_rate": 1.5104600169732015e-05,
1824
+ "loss": 2.3285,
1825
+ "step": 249
1826
+ },
1827
+ {
1828
+ "epoch": 2.0833333333333335,
1829
+ "grad_norm": 0.08345016891314849,
1830
+ "learning_rate": 1.5004159221212325e-05,
1831
+ "loss": 2.3252,
1832
+ "step": 250
1833
+ },
1834
+ {
1835
+ "epoch": 2.091666666666667,
1836
+ "grad_norm": 0.0767244585605165,
1837
+ "learning_rate": 1.490368068540692e-05,
1838
+ "loss": 2.3176,
1839
+ "step": 251
1840
+ },
1841
+ {
1842
+ "epoch": 2.1,
1843
+ "grad_norm": 0.07853322933102938,
1844
+ "learning_rate": 1.4803169570164703e-05,
1845
+ "loss": 2.286,
1846
+ "step": 252
1847
+ },
1848
+ {
1849
+ "epoch": 2.1083333333333334,
1850
+ "grad_norm": 0.07885223855237164,
1851
+ "learning_rate": 1.4702630884958345e-05,
1852
+ "loss": 2.3293,
1853
+ "step": 253
1854
+ },
1855
+ {
1856
+ "epoch": 2.1166666666666667,
1857
+ "grad_norm": 0.07786083611140765,
1858
+ "learning_rate": 1.4602069640634605e-05,
1859
+ "loss": 2.3241,
1860
+ "step": 254
1861
+ },
1862
+ {
1863
+ "epoch": 2.125,
1864
+ "grad_norm": 0.07961379829842732,
1865
+ "learning_rate": 1.4501490849164585e-05,
1866
+ "loss": 2.3218,
1867
+ "step": 255
1868
+ },
1869
+ {
1870
+ "epoch": 2.1333333333333333,
1871
+ "grad_norm": 0.0812119479291348,
1872
+ "learning_rate": 1.4400899523393928e-05,
1873
+ "loss": 2.3101,
1874
+ "step": 256
1875
+ },
1876
+ {
1877
+ "epoch": 2.1416666666666666,
1878
+ "grad_norm": 0.07820228956836967,
1879
+ "learning_rate": 1.4300300676793e-05,
1880
+ "loss": 2.3105,
1881
+ "step": 257
1882
+ },
1883
+ {
1884
+ "epoch": 2.15,
1885
+ "grad_norm": 0.0787354321940814,
1886
+ "learning_rate": 1.4199699323207e-05,
1887
+ "loss": 2.2921,
1888
+ "step": 258
1889
+ },
1890
+ {
1891
+ "epoch": 2.158333333333333,
1892
+ "grad_norm": 0.0821168083039209,
1893
+ "learning_rate": 1.4099100476606071e-05,
1894
+ "loss": 2.3449,
1895
+ "step": 259
1896
+ },
1897
+ {
1898
+ "epoch": 2.1666666666666665,
1899
+ "grad_norm": 0.08227570212622978,
1900
+ "learning_rate": 1.3998509150835417e-05,
1901
+ "loss": 2.2804,
1902
+ "step": 260
1903
+ },
1904
+ {
1905
+ "epoch": 2.175,
1906
+ "grad_norm": 0.07956552166316343,
1907
+ "learning_rate": 1.3897930359365397e-05,
1908
+ "loss": 2.2798,
1909
+ "step": 261
1910
+ },
1911
+ {
1912
+ "epoch": 2.183333333333333,
1913
+ "grad_norm": 0.08355971196343313,
1914
+ "learning_rate": 1.3797369115041656e-05,
1915
+ "loss": 2.3121,
1916
+ "step": 262
1917
+ },
1918
+ {
1919
+ "epoch": 2.191666666666667,
1920
+ "grad_norm": 0.07664615523847712,
1921
+ "learning_rate": 1.3696830429835303e-05,
1922
+ "loss": 2.3511,
1923
+ "step": 263
1924
+ },
1925
+ {
1926
+ "epoch": 2.2,
1927
+ "grad_norm": 0.07875754809310784,
1928
+ "learning_rate": 1.3596319314593088e-05,
1929
+ "loss": 2.276,
1930
+ "step": 264
1931
+ },
1932
+ {
1933
+ "epoch": 2.2083333333333335,
1934
+ "grad_norm": 0.07805417721469433,
1935
+ "learning_rate": 1.3495840778787675e-05,
1936
+ "loss": 2.3156,
1937
+ "step": 265
1938
+ },
1939
+ {
1940
+ "epoch": 2.216666666666667,
1941
+ "grad_norm": 0.08500867883177173,
1942
+ "learning_rate": 1.339539983026799e-05,
1943
+ "loss": 2.3304,
1944
+ "step": 266
1945
+ },
1946
+ {
1947
+ "epoch": 2.225,
1948
+ "grad_norm": 0.08575986404103182,
1949
+ "learning_rate": 1.3295001475009578e-05,
1950
+ "loss": 2.3171,
1951
+ "step": 267
1952
+ },
1953
+ {
1954
+ "epoch": 2.2333333333333334,
1955
+ "grad_norm": 0.0796424885760881,
1956
+ "learning_rate": 1.3194650716865163e-05,
1957
+ "loss": 2.3488,
1958
+ "step": 268
1959
+ },
1960
+ {
1961
+ "epoch": 2.2416666666666667,
1962
+ "grad_norm": 0.07791982790558008,
1963
+ "learning_rate": 1.3094352557315207e-05,
1964
+ "loss": 2.3806,
1965
+ "step": 269
1966
+ },
1967
+ {
1968
+ "epoch": 2.25,
1969
+ "grad_norm": 0.0840055290628465,
1970
+ "learning_rate": 1.299411199521868e-05,
1971
+ "loss": 2.3277,
1972
+ "step": 270
1973
+ },
1974
+ {
1975
+ "epoch": 2.25,
1976
+ "eval_loss": 2.3895957469940186,
1977
+ "eval_runtime": 83.1157,
1978
+ "eval_samples_per_second": 4.933,
1979
+ "eval_steps_per_second": 0.313,
1980
+ "step": 270
1981
+ },
1982
+ {
1983
+ "epoch": 2.2583333333333333,
1984
+ "grad_norm": 0.07770712903979533,
1985
+ "learning_rate": 1.2893934026563873e-05,
1986
+ "loss": 2.2666,
1987
+ "step": 271
1988
+ },
1989
+ {
1990
+ "epoch": 2.2666666666666666,
1991
+ "grad_norm": 0.07846164594226922,
1992
+ "learning_rate": 1.2793823644219445e-05,
1993
+ "loss": 2.2855,
1994
+ "step": 272
1995
+ },
1996
+ {
1997
+ "epoch": 2.275,
1998
+ "grad_norm": 0.08498339693180243,
1999
+ "learning_rate": 1.269378583768554e-05,
2000
+ "loss": 2.2733,
2001
+ "step": 273
2002
+ },
2003
+ {
2004
+ "epoch": 2.283333333333333,
2005
+ "grad_norm": 0.07834222258922019,
2006
+ "learning_rate": 1.2593825592845122e-05,
2007
+ "loss": 2.3193,
2008
+ "step": 274
2009
+ },
2010
+ {
2011
+ "epoch": 2.2916666666666665,
2012
+ "grad_norm": 0.08132580954052983,
2013
+ "learning_rate": 1.2493947891715491e-05,
2014
+ "loss": 2.3085,
2015
+ "step": 275
2016
+ },
2017
+ {
2018
+ "epoch": 2.3,
2019
+ "grad_norm": 0.07883697009265064,
2020
+ "learning_rate": 1.239415771219996e-05,
2021
+ "loss": 2.3545,
2022
+ "step": 276
2023
+ },
2024
+ {
2025
+ "epoch": 2.3083333333333336,
2026
+ "grad_norm": 0.08023901828387182,
2027
+ "learning_rate": 1.2294460027839779e-05,
2028
+ "loss": 2.3489,
2029
+ "step": 277
2030
+ },
2031
+ {
2032
+ "epoch": 2.3166666666666664,
2033
+ "grad_norm": 0.08930364086676225,
2034
+ "learning_rate": 1.2194859807566216e-05,
2035
+ "loss": 2.2591,
2036
+ "step": 278
2037
+ },
2038
+ {
2039
+ "epoch": 2.325,
2040
+ "grad_norm": 0.08343332964333285,
2041
+ "learning_rate": 1.2095362015452961e-05,
2042
+ "loss": 2.3404,
2043
+ "step": 279
2044
+ },
2045
+ {
2046
+ "epoch": 2.3333333333333335,
2047
+ "grad_norm": 0.08292455976075656,
2048
+ "learning_rate": 1.199597161046867e-05,
2049
+ "loss": 2.3028,
2050
+ "step": 280
2051
+ },
2052
+ {
2053
+ "epoch": 2.341666666666667,
2054
+ "grad_norm": 0.08627078651851632,
2055
+ "learning_rate": 1.189669354622982e-05,
2056
+ "loss": 2.343,
2057
+ "step": 281
2058
+ },
2059
+ {
2060
+ "epoch": 2.35,
2061
+ "grad_norm": 0.08202097516344958,
2062
+ "learning_rate": 1.1797532770753842e-05,
2063
+ "loss": 2.326,
2064
+ "step": 282
2065
+ },
2066
+ {
2067
+ "epoch": 2.3583333333333334,
2068
+ "grad_norm": 0.08362611496815728,
2069
+ "learning_rate": 1.169849422621248e-05,
2070
+ "loss": 2.3035,
2071
+ "step": 283
2072
+ },
2073
+ {
2074
+ "epoch": 2.3666666666666667,
2075
+ "grad_norm": 0.08888611458113292,
2076
+ "learning_rate": 1.1599582848685506e-05,
2077
+ "loss": 2.2812,
2078
+ "step": 284
2079
+ },
2080
+ {
2081
+ "epoch": 2.375,
2082
+ "grad_norm": 0.08217261091117088,
2083
+ "learning_rate": 1.1500803567914671e-05,
2084
+ "loss": 2.3378,
2085
+ "step": 285
2086
+ },
2087
+ {
2088
+ "epoch": 2.3833333333333333,
2089
+ "grad_norm": 0.07985728135451624,
2090
+ "learning_rate": 1.1402161307058047e-05,
2091
+ "loss": 2.3522,
2092
+ "step": 286
2093
+ },
2094
+ {
2095
+ "epoch": 2.3916666666666666,
2096
+ "grad_norm": 0.08014525439116486,
2097
+ "learning_rate": 1.1303660982444624e-05,
2098
+ "loss": 2.2256,
2099
+ "step": 287
2100
+ },
2101
+ {
2102
+ "epoch": 2.4,
2103
+ "grad_norm": 0.08787593050595495,
2104
+ "learning_rate": 1.1205307503329286e-05,
2105
+ "loss": 2.2974,
2106
+ "step": 288
2107
+ },
2108
+ {
2109
+ "epoch": 2.408333333333333,
2110
+ "grad_norm": 0.08195162040998395,
2111
+ "learning_rate": 1.1107105771648151e-05,
2112
+ "loss": 2.353,
2113
+ "step": 289
2114
+ },
2115
+ {
2116
+ "epoch": 2.4166666666666665,
2117
+ "grad_norm": 0.08267743479386988,
2118
+ "learning_rate": 1.1009060681774236e-05,
2119
+ "loss": 2.3274,
2120
+ "step": 290
2121
+ },
2122
+ {
2123
+ "epoch": 2.425,
2124
+ "grad_norm": 0.08798947281948663,
2125
+ "learning_rate": 1.0911177120273537e-05,
2126
+ "loss": 2.3404,
2127
+ "step": 291
2128
+ },
2129
+ {
2130
+ "epoch": 2.4333333333333336,
2131
+ "grad_norm": 0.08828111892887862,
2132
+ "learning_rate": 1.0813459965661489e-05,
2133
+ "loss": 2.3348,
2134
+ "step": 292
2135
+ },
2136
+ {
2137
+ "epoch": 2.4416666666666664,
2138
+ "grad_norm": 0.08102528742267785,
2139
+ "learning_rate": 1.0715914088159789e-05,
2140
+ "loss": 2.2863,
2141
+ "step": 293
2142
+ },
2143
+ {
2144
+ "epoch": 2.45,
2145
+ "grad_norm": 0.0866645702075036,
2146
+ "learning_rate": 1.06185443494537e-05,
2147
+ "loss": 2.3357,
2148
+ "step": 294
2149
+ },
2150
+ {
2151
+ "epoch": 2.4583333333333335,
2152
+ "grad_norm": 0.08290121294865929,
2153
+ "learning_rate": 1.0521355602449723e-05,
2154
+ "loss": 2.3537,
2155
+ "step": 295
2156
+ },
2157
+ {
2158
+ "epoch": 2.466666666666667,
2159
+ "grad_norm": 0.08332374744178081,
2160
+ "learning_rate": 1.042435269103374e-05,
2161
+ "loss": 2.3554,
2162
+ "step": 296
2163
+ },
2164
+ {
2165
+ "epoch": 2.475,
2166
+ "grad_norm": 0.08367195510948358,
2167
+ "learning_rate": 1.0327540449829583e-05,
2168
+ "loss": 2.3384,
2169
+ "step": 297
2170
+ },
2171
+ {
2172
+ "epoch": 2.4833333333333334,
2173
+ "grad_norm": 0.08673119537467149,
2174
+ "learning_rate": 1.0230923703958083e-05,
2175
+ "loss": 2.2725,
2176
+ "step": 298
2177
+ },
2178
+ {
2179
+ "epoch": 2.4916666666666667,
2180
+ "grad_norm": 0.08235186060858125,
2181
+ "learning_rate": 1.0134507268796605e-05,
2182
+ "loss": 2.328,
2183
+ "step": 299
2184
+ },
2185
+ {
2186
+ "epoch": 2.5,
2187
+ "grad_norm": 0.08408079009588813,
2188
+ "learning_rate": 1.0038295949739004e-05,
2189
+ "loss": 2.3403,
2190
+ "step": 300
2191
+ },
2192
+ {
2193
+ "epoch": 2.5,
2194
+ "eval_loss": 2.3881967067718506,
2195
+ "eval_runtime": 82.1489,
2196
+ "eval_samples_per_second": 4.991,
2197
+ "eval_steps_per_second": 0.316,
2198
+ "step": 300
2199
+ }
2200
+ ],
2201
+ "logging_steps": 1,
2202
+ "max_steps": 480,
2203
+ "num_input_tokens_seen": 0,
2204
+ "num_train_epochs": 4,
2205
+ "save_steps": 60,
2206
+ "stateful_callbacks": {
2207
+ "TrainerControl": {
2208
+ "args": {
2209
+ "should_epoch_stop": false,
2210
+ "should_evaluate": false,
2211
+ "should_log": false,
2212
+ "should_save": true,
2213
+ "should_training_stop": false
2214
+ },
2215
+ "attributes": {}
2216
+ }
2217
+ },
2218
+ "total_flos": 3.7220359996440576e+17,
2219
+ "train_batch_size": 4,
2220
+ "trial_name": null,
2221
+ "trial_params": null
2222
+ }
checkpoint-300/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0950ae128e4d4958ddb8a58739e4390730bca7076e922a94736a9f4ca7c6f0f1
3
+ size 8504
checkpoint-300/zero_to_fp32.py ADDED
@@ -0,0 +1,760 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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:
14
+ # python zero_to_fp32.py . output_dir/
15
+ # or
16
+ # python zero_to_fp32.py . output_dir/ --safe_serialization
17
+
18
+ import argparse
19
+ import torch
20
+ import glob
21
+ import math
22
+ import os
23
+ import re
24
+ import gc
25
+ import json
26
+ import numpy as np
27
+ from tqdm import tqdm
28
+ from collections import OrderedDict
29
+ from dataclasses import dataclass
30
+
31
+ # while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
32
+ # DeepSpeed data structures it has to be available in the current python environment.
33
+ from deepspeed.utils import logger
34
+ from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
35
+ FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
36
+ FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
37
+
38
+
39
+ @dataclass
40
+ class zero_model_state:
41
+ buffers: dict()
42
+ param_shapes: dict()
43
+ shared_params: list
44
+ ds_version: int
45
+ frozen_param_shapes: dict()
46
+ frozen_param_fragments: dict()
47
+
48
+
49
+ debug = 0
50
+
51
+ # load to cpu
52
+ device = torch.device('cpu')
53
+
54
+
55
+ def atoi(text):
56
+ return int(text) if text.isdigit() else text
57
+
58
+
59
+ def natural_keys(text):
60
+ '''
61
+ alist.sort(key=natural_keys) sorts in human order
62
+ http://nedbatchelder.com/blog/200712/human_sorting.html
63
+ (See Toothy's implementation in the comments)
64
+ '''
65
+ return [atoi(c) for c in re.split(r'(\d+)', text)]
66
+
67
+
68
+ def get_model_state_file(checkpoint_dir, zero_stage):
69
+ if not os.path.isdir(checkpoint_dir):
70
+ raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
71
+
72
+ # there should be only one file
73
+ if zero_stage <= 2:
74
+ file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
75
+ elif zero_stage == 3:
76
+ file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
77
+
78
+ if not os.path.exists(file):
79
+ raise FileNotFoundError(f"can't find model states file at '{file}'")
80
+
81
+ return file
82
+
83
+
84
+ def get_checkpoint_files(checkpoint_dir, glob_pattern):
85
+ # XXX: need to test that this simple glob rule works for multi-node setup too
86
+ ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
87
+
88
+ if len(ckpt_files) == 0:
89
+ raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
90
+
91
+ return ckpt_files
92
+
93
+
94
+ def get_optim_files(checkpoint_dir):
95
+ return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
96
+
97
+
98
+ def get_model_state_files(checkpoint_dir):
99
+ return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
100
+
101
+
102
+ def parse_model_states(files):
103
+ zero_model_states = []
104
+ for file in files:
105
+ state_dict = torch.load(file, map_location=device, weights_only=False)
106
+
107
+ if BUFFER_NAMES not in state_dict:
108
+ raise ValueError(f"{file} is not a model state checkpoint")
109
+ buffer_names = state_dict[BUFFER_NAMES]
110
+ if debug:
111
+ print("Found buffers:", buffer_names)
112
+
113
+ # recover just the buffers while restoring them to fp32 if they were saved in fp16
114
+ buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
115
+ param_shapes = state_dict[PARAM_SHAPES]
116
+
117
+ # collect parameters that are included in param_shapes
118
+ param_names = []
119
+ for s in param_shapes:
120
+ for name in s.keys():
121
+ param_names.append(name)
122
+
123
+ # update with frozen parameters
124
+ frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
125
+ if frozen_param_shapes is not None:
126
+ if debug:
127
+ print(f"Found frozen_param_shapes: {frozen_param_shapes}")
128
+ param_names += list(frozen_param_shapes.keys())
129
+
130
+ # handle shared params
131
+ shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
132
+
133
+ ds_version = state_dict.get(DS_VERSION, None)
134
+
135
+ frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
136
+
137
+ z_model_state = zero_model_state(buffers=buffers,
138
+ param_shapes=param_shapes,
139
+ shared_params=shared_params,
140
+ ds_version=ds_version,
141
+ frozen_param_shapes=frozen_param_shapes,
142
+ frozen_param_fragments=frozen_param_fragments)
143
+ zero_model_states.append(z_model_state)
144
+
145
+ return zero_model_states
146
+
147
+
148
+ def parse_optim_states(files, ds_checkpoint_dir):
149
+ total_files = len(files)
150
+ state_dicts = []
151
+ for f in tqdm(files, desc='Loading checkpoint shards'):
152
+ state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
153
+ # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
154
+ # and also handle the case where it was already removed by another helper script
155
+ state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
156
+ state_dicts.append(state_dict)
157
+
158
+ if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
159
+ raise ValueError(f"{files[0]} is not a zero checkpoint")
160
+ zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
161
+ world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
162
+
163
+ # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
164
+ # parameters can be different from data parallelism for non-expert parameters. So we can just
165
+ # use the max of the partition_count to get the dp world_size.
166
+
167
+ if type(world_size) is list:
168
+ world_size = max(world_size)
169
+
170
+ if world_size != total_files:
171
+ raise ValueError(
172
+ f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
173
+ "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
174
+ )
175
+
176
+ # the groups are named differently in each stage
177
+ if zero_stage <= 2:
178
+ fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
179
+ elif zero_stage == 3:
180
+ fp32_groups_key = FP32_FLAT_GROUPS
181
+ else:
182
+ raise ValueError(f"unknown zero stage {zero_stage}")
183
+
184
+ fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
185
+ return zero_stage, world_size, fp32_flat_groups
186
+
187
+
188
+ def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
189
+ """
190
+ Returns fp32 state_dict reconstructed from ds checkpoint
191
+
192
+ Args:
193
+ - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
194
+
195
+ """
196
+ print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
197
+
198
+ optim_files = get_optim_files(ds_checkpoint_dir)
199
+ zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
200
+ print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
201
+
202
+ model_files = get_model_state_files(ds_checkpoint_dir)
203
+
204
+ zero_model_states = parse_model_states(model_files)
205
+ print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
206
+
207
+ if zero_stage <= 2:
208
+ return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
209
+ exclude_frozen_parameters)
210
+ elif zero_stage == 3:
211
+ return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
212
+ exclude_frozen_parameters)
213
+
214
+
215
+ def _zero2_merge_frozen_params(state_dict, zero_model_states):
216
+ if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
217
+ return
218
+
219
+ frozen_param_shapes = zero_model_states[0].frozen_param_shapes
220
+ frozen_param_fragments = zero_model_states[0].frozen_param_fragments
221
+
222
+ if debug:
223
+ num_elem = sum(s.numel() for s in frozen_param_shapes.values())
224
+ print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
225
+
226
+ wanted_params = len(frozen_param_shapes)
227
+ wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
228
+ avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
229
+ print(f'Frozen params: Have {avail_numel} numels to process.')
230
+ print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
231
+
232
+ total_params = 0
233
+ total_numel = 0
234
+ for name, shape in frozen_param_shapes.items():
235
+ total_params += 1
236
+ unpartitioned_numel = shape.numel()
237
+ total_numel += unpartitioned_numel
238
+
239
+ state_dict[name] = frozen_param_fragments[name]
240
+
241
+ if debug:
242
+ print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
243
+
244
+ print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
245
+
246
+
247
+ def _has_callable(obj, fn):
248
+ attr = getattr(obj, fn, None)
249
+ return callable(attr)
250
+
251
+
252
+ def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
253
+ param_shapes = zero_model_states[0].param_shapes
254
+
255
+ # Reconstruction protocol:
256
+ #
257
+ # XXX: document this
258
+
259
+ if debug:
260
+ for i in range(world_size):
261
+ for j in range(len(fp32_flat_groups[0])):
262
+ print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
263
+
264
+ # XXX: memory usage doubles here (zero2)
265
+ num_param_groups = len(fp32_flat_groups[0])
266
+ merged_single_partition_of_fp32_groups = []
267
+ for i in range(num_param_groups):
268
+ merged_partitions = [sd[i] for sd in fp32_flat_groups]
269
+ full_single_fp32_vector = torch.cat(merged_partitions, 0)
270
+ merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
271
+ avail_numel = sum(
272
+ [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
273
+
274
+ if debug:
275
+ wanted_params = sum([len(shapes) for shapes in param_shapes])
276
+ wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
277
+ # not asserting if there is a mismatch due to possible padding
278
+ print(f"Have {avail_numel} numels to process.")
279
+ print(f"Need {wanted_numel} numels in {wanted_params} params.")
280
+
281
+ # params
282
+ # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
283
+ # out-of-core computing solution
284
+ total_numel = 0
285
+ total_params = 0
286
+ for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
287
+ offset = 0
288
+ avail_numel = full_single_fp32_vector.numel()
289
+ for name, shape in shapes.items():
290
+
291
+ unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
292
+ total_numel += unpartitioned_numel
293
+ total_params += 1
294
+
295
+ if debug:
296
+ print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
297
+ state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
298
+ offset += unpartitioned_numel
299
+
300
+ # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
301
+ # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
302
+ # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
303
+ # live optimizer object, so we are checking that the numbers are within the right range
304
+ align_to = 2 * world_size
305
+
306
+ def zero2_align(x):
307
+ return align_to * math.ceil(x / align_to)
308
+
309
+ if debug:
310
+ print(f"original offset={offset}, avail_numel={avail_numel}")
311
+
312
+ offset = zero2_align(offset)
313
+ avail_numel = zero2_align(avail_numel)
314
+
315
+ if debug:
316
+ print(f"aligned offset={offset}, avail_numel={avail_numel}")
317
+
318
+ # Sanity check
319
+ if offset != avail_numel:
320
+ raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
321
+
322
+ print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
323
+
324
+
325
+ def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
326
+ exclude_frozen_parameters):
327
+ state_dict = OrderedDict()
328
+
329
+ # buffers
330
+ buffers = zero_model_states[0].buffers
331
+ state_dict.update(buffers)
332
+ if debug:
333
+ print(f"added {len(buffers)} buffers")
334
+
335
+ if not exclude_frozen_parameters:
336
+ _zero2_merge_frozen_params(state_dict, zero_model_states)
337
+
338
+ _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
339
+
340
+ # recover shared parameters
341
+ for pair in zero_model_states[0].shared_params:
342
+ if pair[1] in state_dict:
343
+ state_dict[pair[0]] = state_dict[pair[1]]
344
+
345
+ return state_dict
346
+
347
+
348
+ def zero3_partitioned_param_info(unpartitioned_numel, world_size):
349
+ remainder = unpartitioned_numel % world_size
350
+ padding_numel = (world_size - remainder) if remainder else 0
351
+ partitioned_numel = math.ceil(unpartitioned_numel / world_size)
352
+ return partitioned_numel, padding_numel
353
+
354
+
355
+ def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
356
+ if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
357
+ return
358
+
359
+ if debug:
360
+ for i in range(world_size):
361
+ num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
362
+ print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
363
+
364
+ frozen_param_shapes = zero_model_states[0].frozen_param_shapes
365
+ wanted_params = len(frozen_param_shapes)
366
+ wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
367
+ avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
368
+ print(f'Frozen params: Have {avail_numel} numels to process.')
369
+ print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
370
+
371
+ total_params = 0
372
+ total_numel = 0
373
+ for name, shape in zero_model_states[0].frozen_param_shapes.items():
374
+ total_params += 1
375
+ unpartitioned_numel = shape.numel()
376
+ total_numel += unpartitioned_numel
377
+
378
+ param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
379
+ state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
380
+
381
+ partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
382
+
383
+ if debug:
384
+ print(
385
+ f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
386
+ )
387
+
388
+ print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
389
+
390
+
391
+ class GatheredTensor:
392
+ """
393
+ A pseudo tensor that collects partitioned weights.
394
+ It is more memory efficient when there are multiple groups.
395
+ """
396
+
397
+ def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
398
+ self.flat_groups = flat_groups
399
+ self.flat_groups_offset = flat_groups_offset
400
+ self.offset = offset
401
+ self.partitioned_numel = partitioned_numel
402
+ self.shape = shape
403
+ self.dtype = self.flat_groups[0][0].dtype
404
+
405
+ def contiguous(self):
406
+ """
407
+ Merge partitioned weights from flat_groups into a single tensor.
408
+ """
409
+ end_idx = self.offset + self.partitioned_numel
410
+ world_size = len(self.flat_groups)
411
+ pad_flat_param_chunks = []
412
+
413
+ for rank_i in range(world_size):
414
+ # for each rank, we need to collect weights from related group/groups
415
+ flat_groups_at_rank_i = self.flat_groups[rank_i]
416
+ start_group_id = None
417
+ end_group_id = None
418
+ for group_id in range(len(self.flat_groups_offset)):
419
+ if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
420
+ start_group_id = group_id
421
+ if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
422
+ end_group_id = group_id
423
+ break
424
+ # collect weights from related group/groups
425
+ for group_id in range(start_group_id, end_group_id + 1):
426
+ flat_tensor = flat_groups_at_rank_i[group_id]
427
+ start_offset = self.offset - self.flat_groups_offset[group_id]
428
+ end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
429
+ pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
430
+
431
+ # collect weights from all ranks
432
+ pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
433
+ param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
434
+ return param
435
+
436
+
437
+ def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
438
+ param_shapes = zero_model_states[0].param_shapes
439
+ avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size
440
+
441
+ # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
442
+ # param, re-consolidating each param, while dealing with padding if any
443
+
444
+ # merge list of dicts, preserving order
445
+ param_shapes = {k: v for d in param_shapes for k, v in d.items()}
446
+
447
+ if debug:
448
+ for i in range(world_size):
449
+ print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
450
+
451
+ wanted_params = len(param_shapes)
452
+ wanted_numel = sum(shape.numel() for shape in param_shapes.values())
453
+ # not asserting if there is a mismatch due to possible padding
454
+ avail_numel = fp32_flat_groups[0].numel() * world_size
455
+ print(f"Trainable params: Have {avail_numel} numels to process.")
456
+ print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
457
+
458
+ # params
459
+ # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
460
+ # out-of-core computing solution
461
+ offset = 0
462
+ total_numel = 0
463
+ total_params = 0
464
+ flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
465
+ for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
466
+ unpartitioned_numel = shape.numel()
467
+ total_numel += unpartitioned_numel
468
+ total_params += 1
469
+ partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
470
+
471
+ if debug:
472
+ print(
473
+ f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
474
+ )
475
+
476
+ # memory efficient tensor
477
+ tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
478
+ state_dict[name] = tensor
479
+ offset += partitioned_numel
480
+
481
+ offset *= world_size
482
+
483
+ # Sanity check
484
+ if offset != avail_numel:
485
+ raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
486
+
487
+ print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
488
+
489
+
490
+ def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
491
+ exclude_frozen_parameters):
492
+ state_dict = OrderedDict()
493
+
494
+ # buffers
495
+ buffers = zero_model_states[0].buffers
496
+ state_dict.update(buffers)
497
+ if debug:
498
+ print(f"added {len(buffers)} buffers")
499
+
500
+ if not exclude_frozen_parameters:
501
+ _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
502
+
503
+ _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
504
+
505
+ # recover shared parameters
506
+ for pair in zero_model_states[0].shared_params:
507
+ if pair[1] in state_dict:
508
+ state_dict[pair[0]] = state_dict[pair[1]]
509
+
510
+ return state_dict
511
+
512
+
513
+ def to_torch_tensor(state_dict, return_empty_tensor=False):
514
+ """
515
+ Convert state_dict of GatheredTensor to torch tensor
516
+ """
517
+ torch_state_dict = {}
518
+ converted_tensors = {}
519
+ for name, tensor in state_dict.items():
520
+ tensor_id = id(tensor)
521
+ if tensor_id in converted_tensors: # shared tensors
522
+ shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
523
+ torch_state_dict[name] = shared_tensor
524
+ else:
525
+ converted_tensors[tensor_id] = name
526
+ if return_empty_tensor:
527
+ torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
528
+ else:
529
+ torch_state_dict[name] = tensor.contiguous()
530
+ return torch_state_dict
531
+
532
+
533
+ def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
534
+ tag=None,
535
+ exclude_frozen_parameters=False,
536
+ lazy_mode=False):
537
+ """
538
+ Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
539
+ ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
540
+ via a model hub.
541
+
542
+ Args:
543
+ - ``checkpoint_dir``: path to the desired checkpoint folder
544
+ - ``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``
545
+ - ``exclude_frozen_parameters``: exclude frozen parameters
546
+ - ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
547
+ Convert the pesduo tensor to torch tensor by ``.contiguous()``
548
+
549
+ Returns:
550
+ - pytorch ``state_dict``
551
+
552
+ A typical usage might be ::
553
+
554
+ from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
555
+ # do the training and checkpoint saving
556
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
557
+ model = model.cpu() # move to cpu
558
+ model.load_state_dict(state_dict)
559
+ # submit to model hub or save the model to share with others
560
+
561
+ In this example the ``model`` will no longer be usable in the deepspeed context of the same
562
+ application. i.e. you will need to re-initialize the deepspeed engine, since
563
+ ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
564
+
565
+ If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
566
+
567
+ Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
568
+ You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
569
+ the checkpoint. Or you can load state_dict in lazy mode ::
570
+
571
+ from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
572
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
573
+ for name, lazy_tensor in state_dict.item():
574
+ tensor = lazy_tensor.contiguous() # to cpu
575
+ print(name, tensor)
576
+ # del tensor to release memory if it no longer in use
577
+ """
578
+ if tag is None:
579
+ latest_path = os.path.join(checkpoint_dir, 'latest')
580
+ if os.path.isfile(latest_path):
581
+ with open(latest_path, 'r') as fd:
582
+ tag = fd.read().strip()
583
+ else:
584
+ raise ValueError(f"Unable to find 'latest' file at {latest_path}")
585
+
586
+ ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
587
+
588
+ if not os.path.isdir(ds_checkpoint_dir):
589
+ raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
590
+
591
+ state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
592
+ if lazy_mode:
593
+ return state_dict
594
+ else:
595
+ return to_torch_tensor(state_dict)
596
+
597
+
598
+ def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
599
+ output_dir,
600
+ max_shard_size="5GB",
601
+ safe_serialization=False,
602
+ tag=None,
603
+ exclude_frozen_parameters=False):
604
+ """
605
+ Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
606
+ loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
607
+
608
+ Args:
609
+ - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
610
+ - ``output_dir``: directory to the pytorch fp32 state_dict output files
611
+ - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
612
+ - ``safe_serialization``: whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
613
+ - ``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``
614
+ - ``exclude_frozen_parameters``: exclude frozen parameters
615
+ """
616
+
617
+ # Dependency pre-check
618
+ if safe_serialization:
619
+ try:
620
+ from safetensors.torch import save_file
621
+ except ImportError:
622
+ print('If you want to use `safe_serialization`, please `pip install safetensors`')
623
+ raise
624
+ if max_shard_size is not None:
625
+ try:
626
+ from huggingface_hub import split_torch_state_dict_into_shards
627
+ except ImportError:
628
+ print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
629
+ raise
630
+
631
+ # Convert zero checkpoint to state_dict
632
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
633
+ tag,
634
+ exclude_frozen_parameters,
635
+ lazy_mode=True)
636
+
637
+ # Shard the model if it is too big.
638
+ weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
639
+ if max_shard_size is not None:
640
+ filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
641
+ # an memory-efficient approach for sharding
642
+ empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
643
+ state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
644
+ filename_pattern=filename_pattern,
645
+ max_shard_size=max_shard_size)
646
+ else:
647
+ from collections import namedtuple
648
+ StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
649
+ state_dict_split = StateDictSplit(is_sharded=False,
650
+ filename_to_tensors={weights_name: list(state_dict.keys())})
651
+
652
+ # Save the model by shard
653
+ os.makedirs(output_dir, exist_ok=True)
654
+ filename_to_tensors = state_dict_split.filename_to_tensors.items()
655
+ for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
656
+ shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
657
+ shard_state_dict = to_torch_tensor(shard_state_dict)
658
+ output_path = os.path.join(output_dir, shard_file)
659
+ if safe_serialization:
660
+ save_file(shard_state_dict, output_path, metadata={"format": "pt"})
661
+ else:
662
+ torch.save(shard_state_dict, output_path)
663
+ # release the memory of current shard
664
+ for tensor_name in list(shard_state_dict.keys()):
665
+ del state_dict[tensor_name]
666
+ del shard_state_dict[tensor_name]
667
+ del shard_state_dict
668
+ gc.collect()
669
+
670
+ # Save index if sharded
671
+ if state_dict_split.is_sharded:
672
+ index = {
673
+ "metadata": state_dict_split.metadata,
674
+ "weight_map": state_dict_split.tensor_to_filename,
675
+ }
676
+ save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
677
+ save_index_file = os.path.join(output_dir, save_index_file)
678
+ with open(save_index_file, "w", encoding="utf-8") as f:
679
+ content = json.dumps(index, indent=2, sort_keys=True) + "\n"
680
+ f.write(content)
681
+
682
+
683
+ def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
684
+ """
685
+ 1. Put the provided model to cpu
686
+ 2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
687
+ 3. Load it into the provided model
688
+
689
+ Args:
690
+ - ``model``: the model object to update
691
+ - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
692
+ - ``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``
693
+
694
+ Returns:
695
+ - ``model`: modified model
696
+
697
+ Make sure you have plenty of CPU memory available before you call this function. If you don't
698
+ have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
699
+ conveniently placed for you in the checkpoint folder.
700
+
701
+ A typical usage might be ::
702
+
703
+ from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
704
+ model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
705
+ # submit to model hub or save the model to share with others
706
+
707
+ Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
708
+ of the same application. i.e. you will need to re-initialize the deepspeed engine, since
709
+ ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
710
+
711
+ """
712
+ logger.info(f"Extracting fp32 weights")
713
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
714
+
715
+ logger.info(f"Overwriting model with fp32 weights")
716
+ model = model.cpu()
717
+ model.load_state_dict(state_dict, strict=False)
718
+
719
+ return model
720
+
721
+
722
+ if __name__ == "__main__":
723
+ parser = argparse.ArgumentParser()
724
+ parser.add_argument("checkpoint_dir",
725
+ type=str,
726
+ help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
727
+ parser.add_argument("output_dir",
728
+ type=str,
729
+ help="directory to the pytorch fp32 state_dict output files"
730
+ "(e.g. path/checkpoint-12-output/)")
731
+ parser.add_argument(
732
+ "--max_shard_size",
733
+ type=str,
734
+ default="5GB",
735
+ help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
736
+ "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
737
+ "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
738
+ "without CPU OOM issues.")
739
+ parser.add_argument(
740
+ "--safe_serialization",
741
+ default=False,
742
+ action='store_true',
743
+ help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
744
+ parser.add_argument("-t",
745
+ "--tag",
746
+ type=str,
747
+ default=None,
748
+ help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
749
+ parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
750
+ parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
751
+ args = parser.parse_args()
752
+
753
+ debug = args.debug
754
+
755
+ convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
756
+ args.output_dir,
757
+ max_shard_size=args.max_shard_size,
758
+ safe_serialization=args.safe_serialization,
759
+ tag=args.tag,
760
+ exclude_frozen_parameters=args.exclude_frozen_parameters)
checkpoint-360/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: NewEden/Hamanasu-KTO-V2
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-360/adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "NewEden/Hamanasu-KTO-V2",
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": 16,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 128,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "gate_proj",
28
+ "o_proj",
29
+ "q_proj",
30
+ "k_proj",
31
+ "down_proj",
32
+ "up_proj",
33
+ "v_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": true
39
+ }
checkpoint-360/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49824f024f3dcb88857e84ac57519e0e800ee74f51f671d8a845e8316d023b98
3
+ size 486600536
checkpoint-360/latest ADDED
@@ -0,0 +1 @@
 
 
1
+ global_step360
checkpoint-360/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc27c0ec5192565247549b2b990df01444d0ae2c5e4ef88a04caa8ea3511f368
3
+ size 15024
checkpoint-360/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ebba24edc22a78099e68ae948789a5f3988d99d2837dc3bf4cb3d90aa25b72c
3
+ size 15024
checkpoint-360/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2529034b653929c4c29ceb0c5a2f3f64cad1f7ba74055b08e6c45150153eefb2
3
+ size 15024
checkpoint-360/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ba98362b76d76c3c8eea947d797b259757fc17dfc963b81f3420b8ff1d7eb7e
3
+ size 15024
checkpoint-360/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a16947658fa0da4dd9926fd82031ac7020c56660a3149c81269647590342e23
3
+ size 1064
checkpoint-360/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": "<|im_end|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|finetune_right_pad_id|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
checkpoint-360/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:907a7b3b13afcc9d481433f17277a6dd7cf852c6185262597f1a849d2ebeaa45
3
+ size 17209884
checkpoint-360/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": "<|im_start|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|im_end|>",
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": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|im_end|>",
2056
+ "extra_special_tokens": {},
2057
+ "model_input_names": [
2058
+ "input_ids",
2059
+ "attention_mask"
2060
+ ],
2061
+ "model_max_length": 131072,
2062
+ "pad_token": "<|finetune_right_pad_id|>",
2063
+ "tokenizer_class": "PreTrainedTokenizer"
2064
+ }
checkpoint-360/trainer_state.json ADDED
@@ -0,0 +1,2658 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
+ "eval_steps": 30,
7
+ "global_step": 360,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.008333333333333333,
14
+ "grad_norm": 0.9462232657835241,
15
+ "learning_rate": 8.142857142857143e-07,
16
+ "loss": 2.5443,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.008333333333333333,
21
+ "eval_loss": 2.5896365642547607,
22
+ "eval_runtime": 96.0059,
23
+ "eval_samples_per_second": 4.271,
24
+ "eval_steps_per_second": 0.271,
25
+ "step": 1
26
+ },
27
+ {
28
+ "epoch": 0.016666666666666666,
29
+ "grad_norm": 0.9597143397960513,
30
+ "learning_rate": 1.6285714285714286e-06,
31
+ "loss": 2.5524,
32
+ "step": 2
33
+ },
34
+ {
35
+ "epoch": 0.025,
36
+ "grad_norm": 0.9246258453027174,
37
+ "learning_rate": 2.442857142857143e-06,
38
+ "loss": 2.5411,
39
+ "step": 3
40
+ },
41
+ {
42
+ "epoch": 0.03333333333333333,
43
+ "grad_norm": 0.9822285829186661,
44
+ "learning_rate": 3.2571428571428572e-06,
45
+ "loss": 2.5518,
46
+ "step": 4
47
+ },
48
+ {
49
+ "epoch": 0.041666666666666664,
50
+ "grad_norm": 0.9044329068814566,
51
+ "learning_rate": 4.071428571428572e-06,
52
+ "loss": 2.4922,
53
+ "step": 5
54
+ },
55
+ {
56
+ "epoch": 0.05,
57
+ "grad_norm": 0.9131300887744053,
58
+ "learning_rate": 4.885714285714286e-06,
59
+ "loss": 2.5713,
60
+ "step": 6
61
+ },
62
+ {
63
+ "epoch": 0.058333333333333334,
64
+ "grad_norm": 0.8336298309675122,
65
+ "learning_rate": 5.7000000000000005e-06,
66
+ "loss": 2.4959,
67
+ "step": 7
68
+ },
69
+ {
70
+ "epoch": 0.06666666666666667,
71
+ "grad_norm": 0.810775409605909,
72
+ "learning_rate": 6.5142857142857145e-06,
73
+ "loss": 2.4943,
74
+ "step": 8
75
+ },
76
+ {
77
+ "epoch": 0.075,
78
+ "grad_norm": 0.6993505055921954,
79
+ "learning_rate": 7.3285714285714285e-06,
80
+ "loss": 2.5022,
81
+ "step": 9
82
+ },
83
+ {
84
+ "epoch": 0.08333333333333333,
85
+ "grad_norm": 0.5909140859664664,
86
+ "learning_rate": 8.142857142857143e-06,
87
+ "loss": 2.468,
88
+ "step": 10
89
+ },
90
+ {
91
+ "epoch": 0.09166666666666666,
92
+ "grad_norm": 0.5464791893738283,
93
+ "learning_rate": 8.957142857142857e-06,
94
+ "loss": 2.5203,
95
+ "step": 11
96
+ },
97
+ {
98
+ "epoch": 0.1,
99
+ "grad_norm": 0.41153668995149084,
100
+ "learning_rate": 9.771428571428571e-06,
101
+ "loss": 2.4912,
102
+ "step": 12
103
+ },
104
+ {
105
+ "epoch": 0.10833333333333334,
106
+ "grad_norm": 0.35433353277028035,
107
+ "learning_rate": 1.0585714285714287e-05,
108
+ "loss": 2.4467,
109
+ "step": 13
110
+ },
111
+ {
112
+ "epoch": 0.11666666666666667,
113
+ "grad_norm": 0.27579908222756766,
114
+ "learning_rate": 1.1400000000000001e-05,
115
+ "loss": 2.4599,
116
+ "step": 14
117
+ },
118
+ {
119
+ "epoch": 0.125,
120
+ "grad_norm": 0.22636758420678307,
121
+ "learning_rate": 1.2214285714285715e-05,
122
+ "loss": 2.4357,
123
+ "step": 15
124
+ },
125
+ {
126
+ "epoch": 0.13333333333333333,
127
+ "grad_norm": 0.22309908436920517,
128
+ "learning_rate": 1.3028571428571429e-05,
129
+ "loss": 2.368,
130
+ "step": 16
131
+ },
132
+ {
133
+ "epoch": 0.14166666666666666,
134
+ "grad_norm": 0.2384290311446137,
135
+ "learning_rate": 1.3842857142857143e-05,
136
+ "loss": 2.4054,
137
+ "step": 17
138
+ },
139
+ {
140
+ "epoch": 0.15,
141
+ "grad_norm": 0.2279055472006466,
142
+ "learning_rate": 1.4657142857142857e-05,
143
+ "loss": 2.4162,
144
+ "step": 18
145
+ },
146
+ {
147
+ "epoch": 0.15833333333333333,
148
+ "grad_norm": 0.24659885813398136,
149
+ "learning_rate": 1.547142857142857e-05,
150
+ "loss": 2.4109,
151
+ "step": 19
152
+ },
153
+ {
154
+ "epoch": 0.16666666666666666,
155
+ "grad_norm": 0.21920560481126147,
156
+ "learning_rate": 1.6285714285714287e-05,
157
+ "loss": 2.4344,
158
+ "step": 20
159
+ },
160
+ {
161
+ "epoch": 0.175,
162
+ "grad_norm": 0.21340860355678012,
163
+ "learning_rate": 1.71e-05,
164
+ "loss": 2.4532,
165
+ "step": 21
166
+ },
167
+ {
168
+ "epoch": 0.18333333333333332,
169
+ "grad_norm": 0.1775246176788835,
170
+ "learning_rate": 1.7914285714285715e-05,
171
+ "loss": 2.4398,
172
+ "step": 22
173
+ },
174
+ {
175
+ "epoch": 0.19166666666666668,
176
+ "grad_norm": 0.15469100364725502,
177
+ "learning_rate": 1.872857142857143e-05,
178
+ "loss": 2.4275,
179
+ "step": 23
180
+ },
181
+ {
182
+ "epoch": 0.2,
183
+ "grad_norm": 0.1261136620302219,
184
+ "learning_rate": 1.9542857142857143e-05,
185
+ "loss": 2.3855,
186
+ "step": 24
187
+ },
188
+ {
189
+ "epoch": 0.20833333333333334,
190
+ "grad_norm": 0.1251566381945981,
191
+ "learning_rate": 2.0357142857142858e-05,
192
+ "loss": 2.4008,
193
+ "step": 25
194
+ },
195
+ {
196
+ "epoch": 0.21666666666666667,
197
+ "grad_norm": 0.12280228065778742,
198
+ "learning_rate": 2.1171428571428574e-05,
199
+ "loss": 2.4086,
200
+ "step": 26
201
+ },
202
+ {
203
+ "epoch": 0.225,
204
+ "grad_norm": 0.1362748806421765,
205
+ "learning_rate": 2.1985714285714286e-05,
206
+ "loss": 2.3642,
207
+ "step": 27
208
+ },
209
+ {
210
+ "epoch": 0.23333333333333334,
211
+ "grad_norm": 0.12370426656542512,
212
+ "learning_rate": 2.2800000000000002e-05,
213
+ "loss": 2.4168,
214
+ "step": 28
215
+ },
216
+ {
217
+ "epoch": 0.24166666666666667,
218
+ "grad_norm": 0.12077140199925576,
219
+ "learning_rate": 2.3614285714285718e-05,
220
+ "loss": 2.3502,
221
+ "step": 29
222
+ },
223
+ {
224
+ "epoch": 0.25,
225
+ "grad_norm": 0.10854652278245232,
226
+ "learning_rate": 2.442857142857143e-05,
227
+ "loss": 2.323,
228
+ "step": 30
229
+ },
230
+ {
231
+ "epoch": 0.25,
232
+ "eval_loss": 2.4455511569976807,
233
+ "eval_runtime": 82.5732,
234
+ "eval_samples_per_second": 4.965,
235
+ "eval_steps_per_second": 0.315,
236
+ "step": 30
237
+ },
238
+ {
239
+ "epoch": 0.25833333333333336,
240
+ "grad_norm": 0.10286886191993252,
241
+ "learning_rate": 2.5242857142857142e-05,
242
+ "loss": 2.4007,
243
+ "step": 31
244
+ },
245
+ {
246
+ "epoch": 0.26666666666666666,
247
+ "grad_norm": 0.09687340891245565,
248
+ "learning_rate": 2.6057142857142858e-05,
249
+ "loss": 2.4088,
250
+ "step": 32
251
+ },
252
+ {
253
+ "epoch": 0.275,
254
+ "grad_norm": 0.09653492248714694,
255
+ "learning_rate": 2.6871428571428574e-05,
256
+ "loss": 2.3906,
257
+ "step": 33
258
+ },
259
+ {
260
+ "epoch": 0.2833333333333333,
261
+ "grad_norm": 0.09022900019263645,
262
+ "learning_rate": 2.7685714285714286e-05,
263
+ "loss": 2.4065,
264
+ "step": 34
265
+ },
266
+ {
267
+ "epoch": 0.2916666666666667,
268
+ "grad_norm": 0.0912409242342349,
269
+ "learning_rate": 2.85e-05,
270
+ "loss": 2.3699,
271
+ "step": 35
272
+ },
273
+ {
274
+ "epoch": 0.3,
275
+ "grad_norm": 0.09592020125185927,
276
+ "learning_rate": 2.8499644890093217e-05,
277
+ "loss": 2.3587,
278
+ "step": 36
279
+ },
280
+ {
281
+ "epoch": 0.30833333333333335,
282
+ "grad_norm": 0.0907084429462166,
283
+ "learning_rate": 2.8498579578071537e-05,
284
+ "loss": 2.4259,
285
+ "step": 37
286
+ },
287
+ {
288
+ "epoch": 0.31666666666666665,
289
+ "grad_norm": 0.09390099422567517,
290
+ "learning_rate": 2.8496804117030106e-05,
291
+ "loss": 2.3232,
292
+ "step": 38
293
+ },
294
+ {
295
+ "epoch": 0.325,
296
+ "grad_norm": 0.08704027284958313,
297
+ "learning_rate": 2.849431859545787e-05,
298
+ "loss": 2.4027,
299
+ "step": 39
300
+ },
301
+ {
302
+ "epoch": 0.3333333333333333,
303
+ "grad_norm": 0.08787482564111378,
304
+ "learning_rate": 2.849112313723319e-05,
305
+ "loss": 2.3827,
306
+ "step": 40
307
+ },
308
+ {
309
+ "epoch": 0.3416666666666667,
310
+ "grad_norm": 0.08422520058818864,
311
+ "learning_rate": 2.8487217901617672e-05,
312
+ "loss": 2.353,
313
+ "step": 41
314
+ },
315
+ {
316
+ "epoch": 0.35,
317
+ "grad_norm": 0.07979320980153469,
318
+ "learning_rate": 2.84826030832482e-05,
319
+ "loss": 2.3519,
320
+ "step": 42
321
+ },
322
+ {
323
+ "epoch": 0.35833333333333334,
324
+ "grad_norm": 0.07814774416810645,
325
+ "learning_rate": 2.8477278912127266e-05,
326
+ "loss": 2.3708,
327
+ "step": 43
328
+ },
329
+ {
330
+ "epoch": 0.36666666666666664,
331
+ "grad_norm": 0.07237049854036091,
332
+ "learning_rate": 2.847124565361149e-05,
333
+ "loss": 2.388,
334
+ "step": 44
335
+ },
336
+ {
337
+ "epoch": 0.375,
338
+ "grad_norm": 0.07354258492789081,
339
+ "learning_rate": 2.8464503608398385e-05,
340
+ "loss": 2.3586,
341
+ "step": 45
342
+ },
343
+ {
344
+ "epoch": 0.38333333333333336,
345
+ "grad_norm": 0.0771281784161838,
346
+ "learning_rate": 2.845705311251141e-05,
347
+ "loss": 2.3993,
348
+ "step": 46
349
+ },
350
+ {
351
+ "epoch": 0.39166666666666666,
352
+ "grad_norm": 0.0763264062020341,
353
+ "learning_rate": 2.844889453728318e-05,
354
+ "loss": 2.3838,
355
+ "step": 47
356
+ },
357
+ {
358
+ "epoch": 0.4,
359
+ "grad_norm": 0.07082143620733677,
360
+ "learning_rate": 2.8440028289336977e-05,
361
+ "loss": 2.3628,
362
+ "step": 48
363
+ },
364
+ {
365
+ "epoch": 0.4083333333333333,
366
+ "grad_norm": 0.0715578975320661,
367
+ "learning_rate": 2.8430454810566477e-05,
368
+ "loss": 2.361,
369
+ "step": 49
370
+ },
371
+ {
372
+ "epoch": 0.4166666666666667,
373
+ "grad_norm": 0.06881630985450242,
374
+ "learning_rate": 2.8420174578113747e-05,
375
+ "loss": 2.4392,
376
+ "step": 50
377
+ },
378
+ {
379
+ "epoch": 0.425,
380
+ "grad_norm": 0.0689279893077156,
381
+ "learning_rate": 2.8409188104345426e-05,
382
+ "loss": 2.3519,
383
+ "step": 51
384
+ },
385
+ {
386
+ "epoch": 0.43333333333333335,
387
+ "grad_norm": 0.07069081407018309,
388
+ "learning_rate": 2.8397495936827232e-05,
389
+ "loss": 2.3981,
390
+ "step": 52
391
+ },
392
+ {
393
+ "epoch": 0.44166666666666665,
394
+ "grad_norm": 0.07092917277421104,
395
+ "learning_rate": 2.8385098658296637e-05,
396
+ "loss": 2.355,
397
+ "step": 53
398
+ },
399
+ {
400
+ "epoch": 0.45,
401
+ "grad_norm": 0.0703607034709259,
402
+ "learning_rate": 2.8371996886633843e-05,
403
+ "loss": 2.3793,
404
+ "step": 54
405
+ },
406
+ {
407
+ "epoch": 0.4583333333333333,
408
+ "grad_norm": 0.07124199690967324,
409
+ "learning_rate": 2.8358191274830974e-05,
410
+ "loss": 2.4275,
411
+ "step": 55
412
+ },
413
+ {
414
+ "epoch": 0.4666666666666667,
415
+ "grad_norm": 0.07099804346309355,
416
+ "learning_rate": 2.8343682510959552e-05,
417
+ "loss": 2.3323,
418
+ "step": 56
419
+ },
420
+ {
421
+ "epoch": 0.475,
422
+ "grad_norm": 0.06967632308939245,
423
+ "learning_rate": 2.8328471318136165e-05,
424
+ "loss": 2.3883,
425
+ "step": 57
426
+ },
427
+ {
428
+ "epoch": 0.48333333333333334,
429
+ "grad_norm": 0.07156300179553134,
430
+ "learning_rate": 2.831255845448647e-05,
431
+ "loss": 2.3298,
432
+ "step": 58
433
+ },
434
+ {
435
+ "epoch": 0.49166666666666664,
436
+ "grad_norm": 0.0704201532980033,
437
+ "learning_rate": 2.8295944713107387e-05,
438
+ "loss": 2.331,
439
+ "step": 59
440
+ },
441
+ {
442
+ "epoch": 0.5,
443
+ "grad_norm": 0.06794782460291071,
444
+ "learning_rate": 2.8278630922027563e-05,
445
+ "loss": 2.3776,
446
+ "step": 60
447
+ },
448
+ {
449
+ "epoch": 0.5,
450
+ "eval_loss": 2.4216628074645996,
451
+ "eval_runtime": 82.3879,
452
+ "eval_samples_per_second": 4.976,
453
+ "eval_steps_per_second": 0.316,
454
+ "step": 60
455
+ },
456
+ {
457
+ "epoch": 0.5083333333333333,
458
+ "grad_norm": 0.07045949082426937,
459
+ "learning_rate": 2.8260617944166123e-05,
460
+ "loss": 2.3319,
461
+ "step": 61
462
+ },
463
+ {
464
+ "epoch": 0.5166666666666667,
465
+ "grad_norm": 0.0702234192794877,
466
+ "learning_rate": 2.824190667728965e-05,
467
+ "loss": 2.3647,
468
+ "step": 62
469
+ },
470
+ {
471
+ "epoch": 0.525,
472
+ "grad_norm": 0.06946814214632402,
473
+ "learning_rate": 2.8222498053967434e-05,
474
+ "loss": 2.3967,
475
+ "step": 63
476
+ },
477
+ {
478
+ "epoch": 0.5333333333333333,
479
+ "grad_norm": 0.06563265580127577,
480
+ "learning_rate": 2.8202393041525005e-05,
481
+ "loss": 2.3863,
482
+ "step": 64
483
+ },
484
+ {
485
+ "epoch": 0.5416666666666666,
486
+ "grad_norm": 0.0723770670150652,
487
+ "learning_rate": 2.8181592641995933e-05,
488
+ "loss": 2.3823,
489
+ "step": 65
490
+ },
491
+ {
492
+ "epoch": 0.55,
493
+ "grad_norm": 0.06870429029917037,
494
+ "learning_rate": 2.8160097892071847e-05,
495
+ "loss": 2.3241,
496
+ "step": 66
497
+ },
498
+ {
499
+ "epoch": 0.5583333333333333,
500
+ "grad_norm": 0.08615444480664787,
501
+ "learning_rate": 2.8137909863050806e-05,
502
+ "loss": 2.3504,
503
+ "step": 67
504
+ },
505
+ {
506
+ "epoch": 0.5666666666666667,
507
+ "grad_norm": 0.06980417460436542,
508
+ "learning_rate": 2.8115029660783887e-05,
509
+ "loss": 2.3762,
510
+ "step": 68
511
+ },
512
+ {
513
+ "epoch": 0.575,
514
+ "grad_norm": 0.0691283200064781,
515
+ "learning_rate": 2.809145842562007e-05,
516
+ "loss": 2.3202,
517
+ "step": 69
518
+ },
519
+ {
520
+ "epoch": 0.5833333333333334,
521
+ "grad_norm": 0.06434433998677834,
522
+ "learning_rate": 2.8067197332349406e-05,
523
+ "loss": 2.4117,
524
+ "step": 70
525
+ },
526
+ {
527
+ "epoch": 0.5916666666666667,
528
+ "grad_norm": 0.06712521054811822,
529
+ "learning_rate": 2.8042247590144472e-05,
530
+ "loss": 2.4234,
531
+ "step": 71
532
+ },
533
+ {
534
+ "epoch": 0.6,
535
+ "grad_norm": 0.07781170630767965,
536
+ "learning_rate": 2.8016610442500087e-05,
537
+ "loss": 2.3614,
538
+ "step": 72
539
+ },
540
+ {
541
+ "epoch": 0.6083333333333333,
542
+ "grad_norm": 0.07179449259884696,
543
+ "learning_rate": 2.7990287167171357e-05,
544
+ "loss": 2.327,
545
+ "step": 73
546
+ },
547
+ {
548
+ "epoch": 0.6166666666666667,
549
+ "grad_norm": 0.0666012429917219,
550
+ "learning_rate": 2.7963279076109976e-05,
551
+ "loss": 2.3606,
552
+ "step": 74
553
+ },
554
+ {
555
+ "epoch": 0.625,
556
+ "grad_norm": 0.07042352420672252,
557
+ "learning_rate": 2.7935587515398855e-05,
558
+ "loss": 2.387,
559
+ "step": 75
560
+ },
561
+ {
562
+ "epoch": 0.6333333333333333,
563
+ "grad_norm": 0.07141219809062525,
564
+ "learning_rate": 2.7907213865185014e-05,
565
+ "loss": 2.3975,
566
+ "step": 76
567
+ },
568
+ {
569
+ "epoch": 0.6416666666666667,
570
+ "grad_norm": 0.07530038535140655,
571
+ "learning_rate": 2.787815953961081e-05,
572
+ "loss": 2.3975,
573
+ "step": 77
574
+ },
575
+ {
576
+ "epoch": 0.65,
577
+ "grad_norm": 0.06873021297298251,
578
+ "learning_rate": 2.784842598674345e-05,
579
+ "loss": 2.3724,
580
+ "step": 78
581
+ },
582
+ {
583
+ "epoch": 0.6583333333333333,
584
+ "grad_norm": 0.06853494667979494,
585
+ "learning_rate": 2.781801468850282e-05,
586
+ "loss": 2.3994,
587
+ "step": 79
588
+ },
589
+ {
590
+ "epoch": 0.6666666666666666,
591
+ "grad_norm": 0.07164446612343163,
592
+ "learning_rate": 2.778692716058762e-05,
593
+ "loss": 2.3448,
594
+ "step": 80
595
+ },
596
+ {
597
+ "epoch": 0.675,
598
+ "grad_norm": 0.07112624750325054,
599
+ "learning_rate": 2.7755164952399844e-05,
600
+ "loss": 2.2984,
601
+ "step": 81
602
+ },
603
+ {
604
+ "epoch": 0.6833333333333333,
605
+ "grad_norm": 0.07679055297227524,
606
+ "learning_rate": 2.7722729646967527e-05,
607
+ "loss": 2.3699,
608
+ "step": 82
609
+ },
610
+ {
611
+ "epoch": 0.6916666666666667,
612
+ "grad_norm": 0.07270378630883641,
613
+ "learning_rate": 2.768962286086587e-05,
614
+ "loss": 2.3436,
615
+ "step": 83
616
+ },
617
+ {
618
+ "epoch": 0.7,
619
+ "grad_norm": 0.06869524209312625,
620
+ "learning_rate": 2.7655846244136654e-05,
621
+ "loss": 2.3856,
622
+ "step": 84
623
+ },
624
+ {
625
+ "epoch": 0.7083333333333334,
626
+ "grad_norm": 0.07006104211903366,
627
+ "learning_rate": 2.762140148020602e-05,
628
+ "loss": 2.3852,
629
+ "step": 85
630
+ },
631
+ {
632
+ "epoch": 0.7166666666666667,
633
+ "grad_norm": 0.07264285304887648,
634
+ "learning_rate": 2.758629028580055e-05,
635
+ "loss": 2.3834,
636
+ "step": 86
637
+ },
638
+ {
639
+ "epoch": 0.725,
640
+ "grad_norm": 0.07253530482477301,
641
+ "learning_rate": 2.7550514410861718e-05,
642
+ "loss": 2.3573,
643
+ "step": 87
644
+ },
645
+ {
646
+ "epoch": 0.7333333333333333,
647
+ "grad_norm": 0.07265955522289944,
648
+ "learning_rate": 2.751407563845866e-05,
649
+ "loss": 2.3163,
650
+ "step": 88
651
+ },
652
+ {
653
+ "epoch": 0.7416666666666667,
654
+ "grad_norm": 0.07374626234739601,
655
+ "learning_rate": 2.747697578469931e-05,
656
+ "loss": 2.3851,
657
+ "step": 89
658
+ },
659
+ {
660
+ "epoch": 0.75,
661
+ "grad_norm": 0.07255481420091238,
662
+ "learning_rate": 2.7439216698639904e-05,
663
+ "loss": 2.3345,
664
+ "step": 90
665
+ },
666
+ {
667
+ "epoch": 0.75,
668
+ "eval_loss": 2.4115521907806396,
669
+ "eval_runtime": 82.0248,
670
+ "eval_samples_per_second": 4.998,
671
+ "eval_steps_per_second": 0.317,
672
+ "step": 90
673
+ },
674
+ {
675
+ "epoch": 0.7583333333333333,
676
+ "grad_norm": 0.06817548300510701,
677
+ "learning_rate": 2.7400800262192788e-05,
678
+ "loss": 2.3449,
679
+ "step": 91
680
+ },
681
+ {
682
+ "epoch": 0.7666666666666667,
683
+ "grad_norm": 0.07336990573663302,
684
+ "learning_rate": 2.7361728390032657e-05,
685
+ "loss": 2.3448,
686
+ "step": 92
687
+ },
688
+ {
689
+ "epoch": 0.775,
690
+ "grad_norm": 0.07822885886131264,
691
+ "learning_rate": 2.732200302950111e-05,
692
+ "loss": 2.3217,
693
+ "step": 93
694
+ },
695
+ {
696
+ "epoch": 0.7833333333333333,
697
+ "grad_norm": 0.07296512071361201,
698
+ "learning_rate": 2.728162616050959e-05,
699
+ "loss": 2.3329,
700
+ "step": 94
701
+ },
702
+ {
703
+ "epoch": 0.7916666666666666,
704
+ "grad_norm": 0.07367928865175823,
705
+ "learning_rate": 2.724059979544072e-05,
706
+ "loss": 2.3208,
707
+ "step": 95
708
+ },
709
+ {
710
+ "epoch": 0.8,
711
+ "grad_norm": 0.07504139519989858,
712
+ "learning_rate": 2.719892597904801e-05,
713
+ "loss": 2.3483,
714
+ "step": 96
715
+ },
716
+ {
717
+ "epoch": 0.8083333333333333,
718
+ "grad_norm": 0.06790757702451031,
719
+ "learning_rate": 2.7156606788353906e-05,
720
+ "loss": 2.4128,
721
+ "step": 97
722
+ },
723
+ {
724
+ "epoch": 0.8166666666666667,
725
+ "grad_norm": 0.07011160737870108,
726
+ "learning_rate": 2.7113644332546336e-05,
727
+ "loss": 2.3832,
728
+ "step": 98
729
+ },
730
+ {
731
+ "epoch": 0.825,
732
+ "grad_norm": 0.08077329808935288,
733
+ "learning_rate": 2.707004075287352e-05,
734
+ "loss": 2.3308,
735
+ "step": 99
736
+ },
737
+ {
738
+ "epoch": 0.8333333333333334,
739
+ "grad_norm": 0.0719496280235162,
740
+ "learning_rate": 2.7025798222537306e-05,
741
+ "loss": 2.3254,
742
+ "step": 100
743
+ },
744
+ {
745
+ "epoch": 0.8416666666666667,
746
+ "grad_norm": 0.07275409855582728,
747
+ "learning_rate": 2.698091894658483e-05,
748
+ "loss": 2.3967,
749
+ "step": 101
750
+ },
751
+ {
752
+ "epoch": 0.85,
753
+ "grad_norm": 0.07201531734077336,
754
+ "learning_rate": 2.693540516179861e-05,
755
+ "loss": 2.3346,
756
+ "step": 102
757
+ },
758
+ {
759
+ "epoch": 0.8583333333333333,
760
+ "grad_norm": 0.0765467775604243,
761
+ "learning_rate": 2.6889259136585094e-05,
762
+ "loss": 2.3336,
763
+ "step": 103
764
+ },
765
+ {
766
+ "epoch": 0.8666666666666667,
767
+ "grad_norm": 0.077223728318478,
768
+ "learning_rate": 2.6842483170861568e-05,
769
+ "loss": 2.3313,
770
+ "step": 104
771
+ },
772
+ {
773
+ "epoch": 0.875,
774
+ "grad_norm": 0.07639332869289207,
775
+ "learning_rate": 2.6795079595941553e-05,
776
+ "loss": 2.4008,
777
+ "step": 105
778
+ },
779
+ {
780
+ "epoch": 0.8833333333333333,
781
+ "grad_norm": 0.07440505813328589,
782
+ "learning_rate": 2.6747050774418605e-05,
783
+ "loss": 2.3425,
784
+ "step": 106
785
+ },
786
+ {
787
+ "epoch": 0.8916666666666667,
788
+ "grad_norm": 0.06937810484842656,
789
+ "learning_rate": 2.6698399100048556e-05,
790
+ "loss": 2.3349,
791
+ "step": 107
792
+ },
793
+ {
794
+ "epoch": 0.9,
795
+ "grad_norm": 0.07336400555418392,
796
+ "learning_rate": 2.6649126997630225e-05,
797
+ "loss": 2.3792,
798
+ "step": 108
799
+ },
800
+ {
801
+ "epoch": 0.9083333333333333,
802
+ "grad_norm": 0.07442564570941794,
803
+ "learning_rate": 2.6599236922884547e-05,
804
+ "loss": 2.3683,
805
+ "step": 109
806
+ },
807
+ {
808
+ "epoch": 0.9166666666666666,
809
+ "grad_norm": 0.07470689463768693,
810
+ "learning_rate": 2.65487313623322e-05,
811
+ "loss": 2.3036,
812
+ "step": 110
813
+ },
814
+ {
815
+ "epoch": 0.925,
816
+ "grad_norm": 0.07096997017300663,
817
+ "learning_rate": 2.649761283316966e-05,
818
+ "loss": 2.3682,
819
+ "step": 111
820
+ },
821
+ {
822
+ "epoch": 0.9333333333333333,
823
+ "grad_norm": 0.07511821034386772,
824
+ "learning_rate": 2.6445883883143744e-05,
825
+ "loss": 2.3346,
826
+ "step": 112
827
+ },
828
+ {
829
+ "epoch": 0.9416666666666667,
830
+ "grad_norm": 0.07057540374817312,
831
+ "learning_rate": 2.639354709042466e-05,
832
+ "loss": 2.3502,
833
+ "step": 113
834
+ },
835
+ {
836
+ "epoch": 0.95,
837
+ "grad_norm": 0.07300364605060353,
838
+ "learning_rate": 2.6340605063477456e-05,
839
+ "loss": 2.3711,
840
+ "step": 114
841
+ },
842
+ {
843
+ "epoch": 0.9583333333333334,
844
+ "grad_norm": 0.06925480258849577,
845
+ "learning_rate": 2.628706044093207e-05,
846
+ "loss": 2.3816,
847
+ "step": 115
848
+ },
849
+ {
850
+ "epoch": 0.9666666666666667,
851
+ "grad_norm": 0.0705107307569524,
852
+ "learning_rate": 2.623291589145179e-05,
853
+ "loss": 2.2958,
854
+ "step": 116
855
+ },
856
+ {
857
+ "epoch": 0.975,
858
+ "grad_norm": 0.07331112076487026,
859
+ "learning_rate": 2.6178174113600252e-05,
860
+ "loss": 2.3279,
861
+ "step": 117
862
+ },
863
+ {
864
+ "epoch": 0.9833333333333333,
865
+ "grad_norm": 0.06780655482074792,
866
+ "learning_rate": 2.612283783570695e-05,
867
+ "loss": 2.4117,
868
+ "step": 118
869
+ },
870
+ {
871
+ "epoch": 0.9916666666666667,
872
+ "grad_norm": 0.07485055181125701,
873
+ "learning_rate": 2.606690981573125e-05,
874
+ "loss": 2.303,
875
+ "step": 119
876
+ },
877
+ {
878
+ "epoch": 1.0,
879
+ "grad_norm": 0.07276467760742707,
880
+ "learning_rate": 2.6010392841124932e-05,
881
+ "loss": 2.3608,
882
+ "step": 120
883
+ },
884
+ {
885
+ "epoch": 1.0,
886
+ "eval_loss": 2.4049572944641113,
887
+ "eval_runtime": 82.3343,
888
+ "eval_samples_per_second": 4.98,
889
+ "eval_steps_per_second": 0.316,
890
+ "step": 120
891
+ },
892
+ {
893
+ "epoch": 1.0083333333333333,
894
+ "grad_norm": 0.07548790321925977,
895
+ "learning_rate": 2.5953289728693274e-05,
896
+ "loss": 2.3185,
897
+ "step": 121
898
+ },
899
+ {
900
+ "epoch": 1.0166666666666666,
901
+ "grad_norm": 0.0730570698984131,
902
+ "learning_rate": 2.5895603324454647e-05,
903
+ "loss": 2.2877,
904
+ "step": 122
905
+ },
906
+ {
907
+ "epoch": 1.025,
908
+ "grad_norm": 0.07345139782586493,
909
+ "learning_rate": 2.5837336503498694e-05,
910
+ "loss": 2.2836,
911
+ "step": 123
912
+ },
913
+ {
914
+ "epoch": 1.0333333333333334,
915
+ "grad_norm": 0.07299378924326991,
916
+ "learning_rate": 2.5778492169843003e-05,
917
+ "loss": 2.3436,
918
+ "step": 124
919
+ },
920
+ {
921
+ "epoch": 1.0416666666666667,
922
+ "grad_norm": 0.07154250149880004,
923
+ "learning_rate": 2.5719073256288394e-05,
924
+ "loss": 2.3822,
925
+ "step": 125
926
+ },
927
+ {
928
+ "epoch": 1.05,
929
+ "grad_norm": 0.0720748804004234,
930
+ "learning_rate": 2.565908272427274e-05,
931
+ "loss": 2.2708,
932
+ "step": 126
933
+ },
934
+ {
935
+ "epoch": 1.0583333333333333,
936
+ "grad_norm": 0.07269892036621302,
937
+ "learning_rate": 2.5598523563723373e-05,
938
+ "loss": 2.3377,
939
+ "step": 127
940
+ },
941
+ {
942
+ "epoch": 1.0666666666666667,
943
+ "grad_norm": 0.0756770863265576,
944
+ "learning_rate": 2.5537398792908062e-05,
945
+ "loss": 2.352,
946
+ "step": 128
947
+ },
948
+ {
949
+ "epoch": 1.075,
950
+ "grad_norm": 0.07397323539112335,
951
+ "learning_rate": 2.547571145828459e-05,
952
+ "loss": 2.3643,
953
+ "step": 129
954
+ },
955
+ {
956
+ "epoch": 1.0833333333333333,
957
+ "grad_norm": 0.07438211371538549,
958
+ "learning_rate": 2.54134646343489e-05,
959
+ "loss": 2.3387,
960
+ "step": 130
961
+ },
962
+ {
963
+ "epoch": 1.0916666666666666,
964
+ "grad_norm": 0.07094248712059498,
965
+ "learning_rate": 2.5350661423481885e-05,
966
+ "loss": 2.3221,
967
+ "step": 131
968
+ },
969
+ {
970
+ "epoch": 1.1,
971
+ "grad_norm": 0.0771622686218861,
972
+ "learning_rate": 2.5287304955794754e-05,
973
+ "loss": 2.3183,
974
+ "step": 132
975
+ },
976
+ {
977
+ "epoch": 1.1083333333333334,
978
+ "grad_norm": 0.07495056480159959,
979
+ "learning_rate": 2.5223398388973028e-05,
980
+ "loss": 2.3697,
981
+ "step": 133
982
+ },
983
+ {
984
+ "epoch": 1.1166666666666667,
985
+ "grad_norm": 0.07629199954207538,
986
+ "learning_rate": 2.515894490811916e-05,
987
+ "loss": 2.3529,
988
+ "step": 134
989
+ },
990
+ {
991
+ "epoch": 1.125,
992
+ "grad_norm": 0.0762534542729489,
993
+ "learning_rate": 2.5093947725593792e-05,
994
+ "loss": 2.3208,
995
+ "step": 135
996
+ },
997
+ {
998
+ "epoch": 1.1333333333333333,
999
+ "grad_norm": 0.07587427933984144,
1000
+ "learning_rate": 2.502841008085565e-05,
1001
+ "loss": 2.3448,
1002
+ "step": 136
1003
+ },
1004
+ {
1005
+ "epoch": 1.1416666666666666,
1006
+ "grad_norm": 0.07490456619530689,
1007
+ "learning_rate": 2.49623352403001e-05,
1008
+ "loss": 2.3435,
1009
+ "step": 137
1010
+ },
1011
+ {
1012
+ "epoch": 1.15,
1013
+ "grad_norm": 0.0744781797534131,
1014
+ "learning_rate": 2.4895726497096315e-05,
1015
+ "loss": 2.4,
1016
+ "step": 138
1017
+ },
1018
+ {
1019
+ "epoch": 1.1583333333333332,
1020
+ "grad_norm": 0.07464944817741491,
1021
+ "learning_rate": 2.482858717102319e-05,
1022
+ "loss": 2.318,
1023
+ "step": 139
1024
+ },
1025
+ {
1026
+ "epoch": 1.1666666666666667,
1027
+ "grad_norm": 0.07309033869975678,
1028
+ "learning_rate": 2.4760920608303867e-05,
1029
+ "loss": 2.2891,
1030
+ "step": 140
1031
+ },
1032
+ {
1033
+ "epoch": 1.175,
1034
+ "grad_norm": 0.07284517336177344,
1035
+ "learning_rate": 2.469273018143894e-05,
1036
+ "loss": 2.3051,
1037
+ "step": 141
1038
+ },
1039
+ {
1040
+ "epoch": 1.1833333333333333,
1041
+ "grad_norm": 0.07652064520411771,
1042
+ "learning_rate": 2.462401928903839e-05,
1043
+ "loss": 2.3555,
1044
+ "step": 142
1045
+ },
1046
+ {
1047
+ "epoch": 1.1916666666666667,
1048
+ "grad_norm": 0.07701974074136966,
1049
+ "learning_rate": 2.45547913556522e-05,
1050
+ "loss": 2.3015,
1051
+ "step": 143
1052
+ },
1053
+ {
1054
+ "epoch": 1.2,
1055
+ "grad_norm": 0.08108352272511765,
1056
+ "learning_rate": 2.448504983159966e-05,
1057
+ "loss": 2.3221,
1058
+ "step": 144
1059
+ },
1060
+ {
1061
+ "epoch": 1.2083333333333333,
1062
+ "grad_norm": 0.07752288456105606,
1063
+ "learning_rate": 2.441479819279742e-05,
1064
+ "loss": 2.3684,
1065
+ "step": 145
1066
+ },
1067
+ {
1068
+ "epoch": 1.2166666666666668,
1069
+ "grad_norm": 0.07881711814524053,
1070
+ "learning_rate": 2.4344039940586235e-05,
1071
+ "loss": 2.3011,
1072
+ "step": 146
1073
+ },
1074
+ {
1075
+ "epoch": 1.225,
1076
+ "grad_norm": 0.07757542042787384,
1077
+ "learning_rate": 2.4272778601556472e-05,
1078
+ "loss": 2.3509,
1079
+ "step": 147
1080
+ },
1081
+ {
1082
+ "epoch": 1.2333333333333334,
1083
+ "grad_norm": 0.07228965364348439,
1084
+ "learning_rate": 2.4201017727372336e-05,
1085
+ "loss": 2.3801,
1086
+ "step": 148
1087
+ },
1088
+ {
1089
+ "epoch": 1.2416666666666667,
1090
+ "grad_norm": 0.07389812003829682,
1091
+ "learning_rate": 2.4128760894594853e-05,
1092
+ "loss": 2.3359,
1093
+ "step": 149
1094
+ },
1095
+ {
1096
+ "epoch": 1.25,
1097
+ "grad_norm": 0.08146218033856112,
1098
+ "learning_rate": 2.4056011704503633e-05,
1099
+ "loss": 2.3096,
1100
+ "step": 150
1101
+ },
1102
+ {
1103
+ "epoch": 1.25,
1104
+ "eval_loss": 2.400259494781494,
1105
+ "eval_runtime": 81.604,
1106
+ "eval_samples_per_second": 5.024,
1107
+ "eval_steps_per_second": 0.319,
1108
+ "step": 150
1109
+ },
1110
+ {
1111
+ "epoch": 1.2583333333333333,
1112
+ "grad_norm": 0.07407260421175128,
1113
+ "learning_rate": 2.3982773782917347e-05,
1114
+ "loss": 2.3418,
1115
+ "step": 151
1116
+ },
1117
+ {
1118
+ "epoch": 1.2666666666666666,
1119
+ "grad_norm": 0.07827237096687646,
1120
+ "learning_rate": 2.390905078001306e-05,
1121
+ "loss": 2.2778,
1122
+ "step": 152
1123
+ },
1124
+ {
1125
+ "epoch": 1.275,
1126
+ "grad_norm": 0.07699758244967876,
1127
+ "learning_rate": 2.383484637014426e-05,
1128
+ "loss": 2.3245,
1129
+ "step": 153
1130
+ },
1131
+ {
1132
+ "epoch": 1.2833333333333332,
1133
+ "grad_norm": 0.07805943021524937,
1134
+ "learning_rate": 2.3760164251657773e-05,
1135
+ "loss": 2.3782,
1136
+ "step": 154
1137
+ },
1138
+ {
1139
+ "epoch": 1.2916666666666667,
1140
+ "grad_norm": 0.0741687347632035,
1141
+ "learning_rate": 2.368500814670941e-05,
1142
+ "loss": 2.3765,
1143
+ "step": 155
1144
+ },
1145
+ {
1146
+ "epoch": 1.3,
1147
+ "grad_norm": 0.07696079818166807,
1148
+ "learning_rate": 2.3609381801078448e-05,
1149
+ "loss": 2.3958,
1150
+ "step": 156
1151
+ },
1152
+ {
1153
+ "epoch": 1.3083333333333333,
1154
+ "grad_norm": 0.08864860865623735,
1155
+ "learning_rate": 2.3533288983980964e-05,
1156
+ "loss": 2.3482,
1157
+ "step": 157
1158
+ },
1159
+ {
1160
+ "epoch": 1.3166666666666667,
1161
+ "grad_norm": 0.07676755572584443,
1162
+ "learning_rate": 2.3456733487881978e-05,
1163
+ "loss": 2.3511,
1164
+ "step": 158
1165
+ },
1166
+ {
1167
+ "epoch": 1.325,
1168
+ "grad_norm": 0.07754541163995884,
1169
+ "learning_rate": 2.337971912830641e-05,
1170
+ "loss": 2.3754,
1171
+ "step": 159
1172
+ },
1173
+ {
1174
+ "epoch": 1.3333333333333333,
1175
+ "grad_norm": 0.08430746433268149,
1176
+ "learning_rate": 2.3302249743648926e-05,
1177
+ "loss": 2.4063,
1178
+ "step": 160
1179
+ },
1180
+ {
1181
+ "epoch": 1.3416666666666668,
1182
+ "grad_norm": 0.08113759941899056,
1183
+ "learning_rate": 2.322432919498265e-05,
1184
+ "loss": 2.3352,
1185
+ "step": 161
1186
+ },
1187
+ {
1188
+ "epoch": 1.35,
1189
+ "grad_norm": 0.08147516272984133,
1190
+ "learning_rate": 2.3145961365866708e-05,
1191
+ "loss": 2.3119,
1192
+ "step": 162
1193
+ },
1194
+ {
1195
+ "epoch": 1.3583333333333334,
1196
+ "grad_norm": 0.07749688842544009,
1197
+ "learning_rate": 2.3067150162152675e-05,
1198
+ "loss": 2.3547,
1199
+ "step": 163
1200
+ },
1201
+ {
1202
+ "epoch": 1.3666666666666667,
1203
+ "grad_norm": 0.08640326754187048,
1204
+ "learning_rate": 2.298789951178992e-05,
1205
+ "loss": 2.3389,
1206
+ "step": 164
1207
+ },
1208
+ {
1209
+ "epoch": 1.375,
1210
+ "grad_norm": 0.0795137333109577,
1211
+ "learning_rate": 2.2908213364629812e-05,
1212
+ "loss": 2.3778,
1213
+ "step": 165
1214
+ },
1215
+ {
1216
+ "epoch": 1.3833333333333333,
1217
+ "grad_norm": 0.07739334763959965,
1218
+ "learning_rate": 2.2828095692228886e-05,
1219
+ "loss": 2.3658,
1220
+ "step": 166
1221
+ },
1222
+ {
1223
+ "epoch": 1.3916666666666666,
1224
+ "grad_norm": 0.07783031237693959,
1225
+ "learning_rate": 2.2747550487650887e-05,
1226
+ "loss": 2.3575,
1227
+ "step": 167
1228
+ },
1229
+ {
1230
+ "epoch": 1.4,
1231
+ "grad_norm": 0.07682655233706284,
1232
+ "learning_rate": 2.2666581765267758e-05,
1233
+ "loss": 2.2825,
1234
+ "step": 168
1235
+ },
1236
+ {
1237
+ "epoch": 1.4083333333333332,
1238
+ "grad_norm": 0.08359081032268273,
1239
+ "learning_rate": 2.2585193560559563e-05,
1240
+ "loss": 2.261,
1241
+ "step": 169
1242
+ },
1243
+ {
1244
+ "epoch": 1.4166666666666667,
1245
+ "grad_norm": 0.0826940676306091,
1246
+ "learning_rate": 2.250338992991335e-05,
1247
+ "loss": 2.3069,
1248
+ "step": 170
1249
+ },
1250
+ {
1251
+ "epoch": 1.425,
1252
+ "grad_norm": 0.08462619097403327,
1253
+ "learning_rate": 2.2421174950421017e-05,
1254
+ "loss": 2.2864,
1255
+ "step": 171
1256
+ },
1257
+ {
1258
+ "epoch": 1.4333333333333333,
1259
+ "grad_norm": 0.07990029642375193,
1260
+ "learning_rate": 2.233855271967606e-05,
1261
+ "loss": 2.3033,
1262
+ "step": 172
1263
+ },
1264
+ {
1265
+ "epoch": 1.4416666666666667,
1266
+ "grad_norm": 0.08051779058857793,
1267
+ "learning_rate": 2.2255527355569372e-05,
1268
+ "loss": 2.3166,
1269
+ "step": 173
1270
+ },
1271
+ {
1272
+ "epoch": 1.45,
1273
+ "grad_norm": 0.08604667339713809,
1274
+ "learning_rate": 2.217210299608402e-05,
1275
+ "loss": 2.387,
1276
+ "step": 174
1277
+ },
1278
+ {
1279
+ "epoch": 1.4583333333333333,
1280
+ "grad_norm": 0.07829742536277012,
1281
+ "learning_rate": 2.208828379908899e-05,
1282
+ "loss": 2.311,
1283
+ "step": 175
1284
+ },
1285
+ {
1286
+ "epoch": 1.4666666666666668,
1287
+ "grad_norm": 0.07850219342360719,
1288
+ "learning_rate": 2.200407394213196e-05,
1289
+ "loss": 2.3384,
1290
+ "step": 176
1291
+ },
1292
+ {
1293
+ "epoch": 1.475,
1294
+ "grad_norm": 0.08531707041033702,
1295
+ "learning_rate": 2.19194776222311e-05,
1296
+ "loss": 2.3107,
1297
+ "step": 177
1298
+ },
1299
+ {
1300
+ "epoch": 1.4833333333333334,
1301
+ "grad_norm": 0.07652853009760147,
1302
+ "learning_rate": 2.183449905566589e-05,
1303
+ "loss": 2.3494,
1304
+ "step": 178
1305
+ },
1306
+ {
1307
+ "epoch": 1.4916666666666667,
1308
+ "grad_norm": 0.0797336095546633,
1309
+ "learning_rate": 2.1749142477766972e-05,
1310
+ "loss": 2.3291,
1311
+ "step": 179
1312
+ },
1313
+ {
1314
+ "epoch": 1.5,
1315
+ "grad_norm": 0.08700079540422817,
1316
+ "learning_rate": 2.166341214270507e-05,
1317
+ "loss": 2.3132,
1318
+ "step": 180
1319
+ },
1320
+ {
1321
+ "epoch": 1.5,
1322
+ "eval_loss": 2.3966128826141357,
1323
+ "eval_runtime": 83.184,
1324
+ "eval_samples_per_second": 4.929,
1325
+ "eval_steps_per_second": 0.313,
1326
+ "step": 180
1327
+ },
1328
+ {
1329
+ "epoch": 1.5083333333333333,
1330
+ "grad_norm": 0.07925581040107615,
1331
+ "learning_rate": 2.157731232327897e-05,
1332
+ "loss": 2.3578,
1333
+ "step": 181
1334
+ },
1335
+ {
1336
+ "epoch": 1.5166666666666666,
1337
+ "grad_norm": 0.07873086864048841,
1338
+ "learning_rate": 2.1490847310702544e-05,
1339
+ "loss": 2.3229,
1340
+ "step": 182
1341
+ },
1342
+ {
1343
+ "epoch": 1.525,
1344
+ "grad_norm": 0.07775316849537767,
1345
+ "learning_rate": 2.1404021414390874e-05,
1346
+ "loss": 2.3756,
1347
+ "step": 183
1348
+ },
1349
+ {
1350
+ "epoch": 1.5333333333333332,
1351
+ "grad_norm": 0.07949428482523528,
1352
+ "learning_rate": 2.1316838961745518e-05,
1353
+ "loss": 2.3535,
1354
+ "step": 184
1355
+ },
1356
+ {
1357
+ "epoch": 1.5416666666666665,
1358
+ "grad_norm": 0.08423278187074197,
1359
+ "learning_rate": 2.1229304297938755e-05,
1360
+ "loss": 2.3517,
1361
+ "step": 185
1362
+ },
1363
+ {
1364
+ "epoch": 1.55,
1365
+ "grad_norm": 0.07930583119038707,
1366
+ "learning_rate": 2.1141421785697097e-05,
1367
+ "loss": 2.3929,
1368
+ "step": 186
1369
+ },
1370
+ {
1371
+ "epoch": 1.5583333333333333,
1372
+ "grad_norm": 0.07736840323261199,
1373
+ "learning_rate": 2.1053195805083803e-05,
1374
+ "loss": 2.3194,
1375
+ "step": 187
1376
+ },
1377
+ {
1378
+ "epoch": 1.5666666666666667,
1379
+ "grad_norm": 0.08306421066524537,
1380
+ "learning_rate": 2.0964630753280584e-05,
1381
+ "loss": 2.3131,
1382
+ "step": 188
1383
+ },
1384
+ {
1385
+ "epoch": 1.575,
1386
+ "grad_norm": 0.0805185815818936,
1387
+ "learning_rate": 2.0875731044368472e-05,
1388
+ "loss": 2.3238,
1389
+ "step": 189
1390
+ },
1391
+ {
1392
+ "epoch": 1.5833333333333335,
1393
+ "grad_norm": 0.07729948838070921,
1394
+ "learning_rate": 2.078650110910779e-05,
1395
+ "loss": 2.3279,
1396
+ "step": 190
1397
+ },
1398
+ {
1399
+ "epoch": 1.5916666666666668,
1400
+ "grad_norm": 0.08053951644296133,
1401
+ "learning_rate": 2.0696945394717355e-05,
1402
+ "loss": 2.3343,
1403
+ "step": 191
1404
+ },
1405
+ {
1406
+ "epoch": 1.6,
1407
+ "grad_norm": 0.08184664333069269,
1408
+ "learning_rate": 2.0607068364652783e-05,
1409
+ "loss": 2.3441,
1410
+ "step": 192
1411
+ },
1412
+ {
1413
+ "epoch": 1.6083333333333334,
1414
+ "grad_norm": 0.07894699650259683,
1415
+ "learning_rate": 2.051687449838409e-05,
1416
+ "loss": 2.3384,
1417
+ "step": 193
1418
+ },
1419
+ {
1420
+ "epoch": 1.6166666666666667,
1421
+ "grad_norm": 0.08288692832517489,
1422
+ "learning_rate": 2.042636829117239e-05,
1423
+ "loss": 2.3219,
1424
+ "step": 194
1425
+ },
1426
+ {
1427
+ "epoch": 1.625,
1428
+ "grad_norm": 0.09061769591669266,
1429
+ "learning_rate": 2.033555425384586e-05,
1430
+ "loss": 2.3168,
1431
+ "step": 195
1432
+ },
1433
+ {
1434
+ "epoch": 1.6333333333333333,
1435
+ "grad_norm": 0.07607427061534017,
1436
+ "learning_rate": 2.0244436912574938e-05,
1437
+ "loss": 2.3592,
1438
+ "step": 196
1439
+ },
1440
+ {
1441
+ "epoch": 1.6416666666666666,
1442
+ "grad_norm": 0.08827457673533141,
1443
+ "learning_rate": 2.0153020808646715e-05,
1444
+ "loss": 2.3177,
1445
+ "step": 197
1446
+ },
1447
+ {
1448
+ "epoch": 1.65,
1449
+ "grad_norm": 0.0757688204165182,
1450
+ "learning_rate": 2.0061310498238618e-05,
1451
+ "loss": 2.2366,
1452
+ "step": 198
1453
+ },
1454
+ {
1455
+ "epoch": 1.6583333333333332,
1456
+ "grad_norm": 0.07815852114026649,
1457
+ "learning_rate": 1.996931055219132e-05,
1458
+ "loss": 2.3161,
1459
+ "step": 199
1460
+ },
1461
+ {
1462
+ "epoch": 1.6666666666666665,
1463
+ "grad_norm": 0.08058901889279678,
1464
+ "learning_rate": 1.9877025555780927e-05,
1465
+ "loss": 2.3749,
1466
+ "step": 200
1467
+ },
1468
+ {
1469
+ "epoch": 1.675,
1470
+ "grad_norm": 0.07708027281441528,
1471
+ "learning_rate": 1.978446010849045e-05,
1472
+ "loss": 2.2854,
1473
+ "step": 201
1474
+ },
1475
+ {
1476
+ "epoch": 1.6833333333333333,
1477
+ "grad_norm": 0.08312283019758401,
1478
+ "learning_rate": 1.969161882378058e-05,
1479
+ "loss": 2.3524,
1480
+ "step": 202
1481
+ },
1482
+ {
1483
+ "epoch": 1.6916666666666667,
1484
+ "grad_norm": 0.07784046601849169,
1485
+ "learning_rate": 1.9598506328859717e-05,
1486
+ "loss": 2.3418,
1487
+ "step": 203
1488
+ },
1489
+ {
1490
+ "epoch": 1.7,
1491
+ "grad_norm": 0.07906237498578873,
1492
+ "learning_rate": 1.95051272644534e-05,
1493
+ "loss": 2.3514,
1494
+ "step": 204
1495
+ },
1496
+ {
1497
+ "epoch": 1.7083333333333335,
1498
+ "grad_norm": 0.08323464269988524,
1499
+ "learning_rate": 1.9411486284572977e-05,
1500
+ "loss": 2.3133,
1501
+ "step": 205
1502
+ },
1503
+ {
1504
+ "epoch": 1.7166666666666668,
1505
+ "grad_norm": 0.08153670371604982,
1506
+ "learning_rate": 1.931758805628366e-05,
1507
+ "loss": 2.3388,
1508
+ "step": 206
1509
+ },
1510
+ {
1511
+ "epoch": 1.725,
1512
+ "grad_norm": 0.08152589045596419,
1513
+ "learning_rate": 1.9223437259471912e-05,
1514
+ "loss": 2.3309,
1515
+ "step": 207
1516
+ },
1517
+ {
1518
+ "epoch": 1.7333333333333334,
1519
+ "grad_norm": 0.08382345786042532,
1520
+ "learning_rate": 1.9129038586612224e-05,
1521
+ "loss": 2.3282,
1522
+ "step": 208
1523
+ },
1524
+ {
1525
+ "epoch": 1.7416666666666667,
1526
+ "grad_norm": 0.0835609429134592,
1527
+ "learning_rate": 1.903439674253321e-05,
1528
+ "loss": 2.3567,
1529
+ "step": 209
1530
+ },
1531
+ {
1532
+ "epoch": 1.75,
1533
+ "grad_norm": 0.08252984125014622,
1534
+ "learning_rate": 1.8939516444183143e-05,
1535
+ "loss": 2.3352,
1536
+ "step": 210
1537
+ },
1538
+ {
1539
+ "epoch": 1.75,
1540
+ "eval_loss": 2.3933684825897217,
1541
+ "eval_runtime": 83.3063,
1542
+ "eval_samples_per_second": 4.922,
1543
+ "eval_steps_per_second": 0.312,
1544
+ "step": 210
1545
+ },
1546
+ {
1547
+ "epoch": 1.7583333333333333,
1548
+ "grad_norm": 0.0815481053340795,
1549
+ "learning_rate": 1.884440242039485e-05,
1550
+ "loss": 2.3262,
1551
+ "step": 211
1552
+ },
1553
+ {
1554
+ "epoch": 1.7666666666666666,
1555
+ "grad_norm": 0.08258761118218041,
1556
+ "learning_rate": 1.8749059411650034e-05,
1557
+ "loss": 2.3396,
1558
+ "step": 212
1559
+ },
1560
+ {
1561
+ "epoch": 1.775,
1562
+ "grad_norm": 0.0884999967331726,
1563
+ "learning_rate": 1.8653492169843003e-05,
1564
+ "loss": 2.3176,
1565
+ "step": 213
1566
+ },
1567
+ {
1568
+ "epoch": 1.7833333333333332,
1569
+ "grad_norm": 0.0824785010834098,
1570
+ "learning_rate": 1.8557705458043838e-05,
1571
+ "loss": 2.3272,
1572
+ "step": 214
1573
+ },
1574
+ {
1575
+ "epoch": 1.7916666666666665,
1576
+ "grad_norm": 0.08727167025374602,
1577
+ "learning_rate": 1.8461704050261e-05,
1578
+ "loss": 2.2298,
1579
+ "step": 215
1580
+ },
1581
+ {
1582
+ "epoch": 1.8,
1583
+ "grad_norm": 0.0768016904891171,
1584
+ "learning_rate": 1.8365492731203398e-05,
1585
+ "loss": 2.3554,
1586
+ "step": 216
1587
+ },
1588
+ {
1589
+ "epoch": 1.8083333333333333,
1590
+ "grad_norm": 0.07709533586121158,
1591
+ "learning_rate": 1.8269076296041917e-05,
1592
+ "loss": 2.3702,
1593
+ "step": 217
1594
+ },
1595
+ {
1596
+ "epoch": 1.8166666666666667,
1597
+ "grad_norm": 0.0806446736093232,
1598
+ "learning_rate": 1.8172459550170424e-05,
1599
+ "loss": 2.3585,
1600
+ "step": 218
1601
+ },
1602
+ {
1603
+ "epoch": 1.825,
1604
+ "grad_norm": 0.07523532523458193,
1605
+ "learning_rate": 1.8075647308966268e-05,
1606
+ "loss": 2.3609,
1607
+ "step": 219
1608
+ },
1609
+ {
1610
+ "epoch": 1.8333333333333335,
1611
+ "grad_norm": 0.07497201271988578,
1612
+ "learning_rate": 1.797864439755028e-05,
1613
+ "loss": 2.3755,
1614
+ "step": 220
1615
+ },
1616
+ {
1617
+ "epoch": 1.8416666666666668,
1618
+ "grad_norm": 0.08249074177996166,
1619
+ "learning_rate": 1.7881455650546303e-05,
1620
+ "loss": 2.372,
1621
+ "step": 221
1622
+ },
1623
+ {
1624
+ "epoch": 1.85,
1625
+ "grad_norm": 0.0780160636961897,
1626
+ "learning_rate": 1.7784085911840214e-05,
1627
+ "loss": 2.3823,
1628
+ "step": 222
1629
+ },
1630
+ {
1631
+ "epoch": 1.8583333333333334,
1632
+ "grad_norm": 0.08148680526536918,
1633
+ "learning_rate": 1.7686540034338513e-05,
1634
+ "loss": 2.3314,
1635
+ "step": 223
1636
+ },
1637
+ {
1638
+ "epoch": 1.8666666666666667,
1639
+ "grad_norm": 0.0795864595636552,
1640
+ "learning_rate": 1.758882287972646e-05,
1641
+ "loss": 2.2853,
1642
+ "step": 224
1643
+ },
1644
+ {
1645
+ "epoch": 1.875,
1646
+ "grad_norm": 0.08198344669246531,
1647
+ "learning_rate": 1.749093931822577e-05,
1648
+ "loss": 2.3605,
1649
+ "step": 225
1650
+ },
1651
+ {
1652
+ "epoch": 1.8833333333333333,
1653
+ "grad_norm": 0.08138145213474299,
1654
+ "learning_rate": 1.739289422835185e-05,
1655
+ "loss": 2.2721,
1656
+ "step": 226
1657
+ },
1658
+ {
1659
+ "epoch": 1.8916666666666666,
1660
+ "grad_norm": 0.08306015511124677,
1661
+ "learning_rate": 1.7294692496670715e-05,
1662
+ "loss": 2.2889,
1663
+ "step": 227
1664
+ },
1665
+ {
1666
+ "epoch": 1.9,
1667
+ "grad_norm": 0.07478727556401082,
1668
+ "learning_rate": 1.7196339017555378e-05,
1669
+ "loss": 2.3416,
1670
+ "step": 228
1671
+ },
1672
+ {
1673
+ "epoch": 1.9083333333333332,
1674
+ "grad_norm": 0.08858459574829487,
1675
+ "learning_rate": 1.709783869294196e-05,
1676
+ "loss": 2.3081,
1677
+ "step": 229
1678
+ },
1679
+ {
1680
+ "epoch": 1.9166666666666665,
1681
+ "grad_norm": 0.08175368181940743,
1682
+ "learning_rate": 1.699919643208533e-05,
1683
+ "loss": 2.3304,
1684
+ "step": 230
1685
+ },
1686
+ {
1687
+ "epoch": 1.925,
1688
+ "grad_norm": 0.07630479738636474,
1689
+ "learning_rate": 1.6900417151314503e-05,
1690
+ "loss": 2.3454,
1691
+ "step": 231
1692
+ },
1693
+ {
1694
+ "epoch": 1.9333333333333333,
1695
+ "grad_norm": 0.07687273996639293,
1696
+ "learning_rate": 1.6801505773787527e-05,
1697
+ "loss": 2.3901,
1698
+ "step": 232
1699
+ },
1700
+ {
1701
+ "epoch": 1.9416666666666667,
1702
+ "grad_norm": 0.08600269874202937,
1703
+ "learning_rate": 1.670246722924616e-05,
1704
+ "loss": 2.3081,
1705
+ "step": 233
1706
+ },
1707
+ {
1708
+ "epoch": 1.95,
1709
+ "grad_norm": 0.07737694968965858,
1710
+ "learning_rate": 1.660330645377018e-05,
1711
+ "loss": 2.3643,
1712
+ "step": 234
1713
+ },
1714
+ {
1715
+ "epoch": 1.9583333333333335,
1716
+ "grad_norm": 0.08165758061569027,
1717
+ "learning_rate": 1.6504028389531333e-05,
1718
+ "loss": 2.355,
1719
+ "step": 235
1720
+ },
1721
+ {
1722
+ "epoch": 1.9666666666666668,
1723
+ "grad_norm": 0.08264378429137093,
1724
+ "learning_rate": 1.640463798454704e-05,
1725
+ "loss": 2.3219,
1726
+ "step": 236
1727
+ },
1728
+ {
1729
+ "epoch": 1.975,
1730
+ "grad_norm": 0.0858368818345628,
1731
+ "learning_rate": 1.6305140192433787e-05,
1732
+ "loss": 2.3329,
1733
+ "step": 237
1734
+ },
1735
+ {
1736
+ "epoch": 1.9833333333333334,
1737
+ "grad_norm": 0.07616999163161729,
1738
+ "learning_rate": 1.620553997216023e-05,
1739
+ "loss": 2.3523,
1740
+ "step": 238
1741
+ },
1742
+ {
1743
+ "epoch": 1.9916666666666667,
1744
+ "grad_norm": 0.08241527325980988,
1745
+ "learning_rate": 1.6105842287800046e-05,
1746
+ "loss": 2.2982,
1747
+ "step": 239
1748
+ },
1749
+ {
1750
+ "epoch": 2.0,
1751
+ "grad_norm": 0.08007891750583127,
1752
+ "learning_rate": 1.600605210828451e-05,
1753
+ "loss": 2.2785,
1754
+ "step": 240
1755
+ },
1756
+ {
1757
+ "epoch": 2.0,
1758
+ "eval_loss": 2.3910558223724365,
1759
+ "eval_runtime": 83.4904,
1760
+ "eval_samples_per_second": 4.911,
1761
+ "eval_steps_per_second": 0.311,
1762
+ "step": 240
1763
+ },
1764
+ {
1765
+ "epoch": 2.0083333333333333,
1766
+ "grad_norm": 0.08108687194604622,
1767
+ "learning_rate": 1.5906174407154883e-05,
1768
+ "loss": 2.3367,
1769
+ "step": 241
1770
+ },
1771
+ {
1772
+ "epoch": 2.0166666666666666,
1773
+ "grad_norm": 0.0806511417182259,
1774
+ "learning_rate": 1.5806214162314463e-05,
1775
+ "loss": 2.3011,
1776
+ "step": 242
1777
+ },
1778
+ {
1779
+ "epoch": 2.025,
1780
+ "grad_norm": 0.08264392219751603,
1781
+ "learning_rate": 1.5706176355780556e-05,
1782
+ "loss": 2.3036,
1783
+ "step": 243
1784
+ },
1785
+ {
1786
+ "epoch": 2.033333333333333,
1787
+ "grad_norm": 0.07958409681135217,
1788
+ "learning_rate": 1.5606065973436132e-05,
1789
+ "loss": 2.3056,
1790
+ "step": 244
1791
+ },
1792
+ {
1793
+ "epoch": 2.0416666666666665,
1794
+ "grad_norm": 0.07856642651007223,
1795
+ "learning_rate": 1.550588800478133e-05,
1796
+ "loss": 2.3692,
1797
+ "step": 245
1798
+ },
1799
+ {
1800
+ "epoch": 2.05,
1801
+ "grad_norm": 0.08350216798892127,
1802
+ "learning_rate": 1.5405647442684794e-05,
1803
+ "loss": 2.2697,
1804
+ "step": 246
1805
+ },
1806
+ {
1807
+ "epoch": 2.058333333333333,
1808
+ "grad_norm": 0.08390645284684875,
1809
+ "learning_rate": 1.530534928313484e-05,
1810
+ "loss": 2.2425,
1811
+ "step": 247
1812
+ },
1813
+ {
1814
+ "epoch": 2.066666666666667,
1815
+ "grad_norm": 0.07883358190907572,
1816
+ "learning_rate": 1.5204998524990423e-05,
1817
+ "loss": 2.3281,
1818
+ "step": 248
1819
+ },
1820
+ {
1821
+ "epoch": 2.075,
1822
+ "grad_norm": 0.07994560560782488,
1823
+ "learning_rate": 1.5104600169732015e-05,
1824
+ "loss": 2.3285,
1825
+ "step": 249
1826
+ },
1827
+ {
1828
+ "epoch": 2.0833333333333335,
1829
+ "grad_norm": 0.08345016891314849,
1830
+ "learning_rate": 1.5004159221212325e-05,
1831
+ "loss": 2.3252,
1832
+ "step": 250
1833
+ },
1834
+ {
1835
+ "epoch": 2.091666666666667,
1836
+ "grad_norm": 0.0767244585605165,
1837
+ "learning_rate": 1.490368068540692e-05,
1838
+ "loss": 2.3176,
1839
+ "step": 251
1840
+ },
1841
+ {
1842
+ "epoch": 2.1,
1843
+ "grad_norm": 0.07853322933102938,
1844
+ "learning_rate": 1.4803169570164703e-05,
1845
+ "loss": 2.286,
1846
+ "step": 252
1847
+ },
1848
+ {
1849
+ "epoch": 2.1083333333333334,
1850
+ "grad_norm": 0.07885223855237164,
1851
+ "learning_rate": 1.4702630884958345e-05,
1852
+ "loss": 2.3293,
1853
+ "step": 253
1854
+ },
1855
+ {
1856
+ "epoch": 2.1166666666666667,
1857
+ "grad_norm": 0.07786083611140765,
1858
+ "learning_rate": 1.4602069640634605e-05,
1859
+ "loss": 2.3241,
1860
+ "step": 254
1861
+ },
1862
+ {
1863
+ "epoch": 2.125,
1864
+ "grad_norm": 0.07961379829842732,
1865
+ "learning_rate": 1.4501490849164585e-05,
1866
+ "loss": 2.3218,
1867
+ "step": 255
1868
+ },
1869
+ {
1870
+ "epoch": 2.1333333333333333,
1871
+ "grad_norm": 0.0812119479291348,
1872
+ "learning_rate": 1.4400899523393928e-05,
1873
+ "loss": 2.3101,
1874
+ "step": 256
1875
+ },
1876
+ {
1877
+ "epoch": 2.1416666666666666,
1878
+ "grad_norm": 0.07820228956836967,
1879
+ "learning_rate": 1.4300300676793e-05,
1880
+ "loss": 2.3105,
1881
+ "step": 257
1882
+ },
1883
+ {
1884
+ "epoch": 2.15,
1885
+ "grad_norm": 0.0787354321940814,
1886
+ "learning_rate": 1.4199699323207e-05,
1887
+ "loss": 2.2921,
1888
+ "step": 258
1889
+ },
1890
+ {
1891
+ "epoch": 2.158333333333333,
1892
+ "grad_norm": 0.0821168083039209,
1893
+ "learning_rate": 1.4099100476606071e-05,
1894
+ "loss": 2.3449,
1895
+ "step": 259
1896
+ },
1897
+ {
1898
+ "epoch": 2.1666666666666665,
1899
+ "grad_norm": 0.08227570212622978,
1900
+ "learning_rate": 1.3998509150835417e-05,
1901
+ "loss": 2.2804,
1902
+ "step": 260
1903
+ },
1904
+ {
1905
+ "epoch": 2.175,
1906
+ "grad_norm": 0.07956552166316343,
1907
+ "learning_rate": 1.3897930359365397e-05,
1908
+ "loss": 2.2798,
1909
+ "step": 261
1910
+ },
1911
+ {
1912
+ "epoch": 2.183333333333333,
1913
+ "grad_norm": 0.08355971196343313,
1914
+ "learning_rate": 1.3797369115041656e-05,
1915
+ "loss": 2.3121,
1916
+ "step": 262
1917
+ },
1918
+ {
1919
+ "epoch": 2.191666666666667,
1920
+ "grad_norm": 0.07664615523847712,
1921
+ "learning_rate": 1.3696830429835303e-05,
1922
+ "loss": 2.3511,
1923
+ "step": 263
1924
+ },
1925
+ {
1926
+ "epoch": 2.2,
1927
+ "grad_norm": 0.07875754809310784,
1928
+ "learning_rate": 1.3596319314593088e-05,
1929
+ "loss": 2.276,
1930
+ "step": 264
1931
+ },
1932
+ {
1933
+ "epoch": 2.2083333333333335,
1934
+ "grad_norm": 0.07805417721469433,
1935
+ "learning_rate": 1.3495840778787675e-05,
1936
+ "loss": 2.3156,
1937
+ "step": 265
1938
+ },
1939
+ {
1940
+ "epoch": 2.216666666666667,
1941
+ "grad_norm": 0.08500867883177173,
1942
+ "learning_rate": 1.339539983026799e-05,
1943
+ "loss": 2.3304,
1944
+ "step": 266
1945
+ },
1946
+ {
1947
+ "epoch": 2.225,
1948
+ "grad_norm": 0.08575986404103182,
1949
+ "learning_rate": 1.3295001475009578e-05,
1950
+ "loss": 2.3171,
1951
+ "step": 267
1952
+ },
1953
+ {
1954
+ "epoch": 2.2333333333333334,
1955
+ "grad_norm": 0.0796424885760881,
1956
+ "learning_rate": 1.3194650716865163e-05,
1957
+ "loss": 2.3488,
1958
+ "step": 268
1959
+ },
1960
+ {
1961
+ "epoch": 2.2416666666666667,
1962
+ "grad_norm": 0.07791982790558008,
1963
+ "learning_rate": 1.3094352557315207e-05,
1964
+ "loss": 2.3806,
1965
+ "step": 269
1966
+ },
1967
+ {
1968
+ "epoch": 2.25,
1969
+ "grad_norm": 0.0840055290628465,
1970
+ "learning_rate": 1.299411199521868e-05,
1971
+ "loss": 2.3277,
1972
+ "step": 270
1973
+ },
1974
+ {
1975
+ "epoch": 2.25,
1976
+ "eval_loss": 2.3895957469940186,
1977
+ "eval_runtime": 83.1157,
1978
+ "eval_samples_per_second": 4.933,
1979
+ "eval_steps_per_second": 0.313,
1980
+ "step": 270
1981
+ },
1982
+ {
1983
+ "epoch": 2.2583333333333333,
1984
+ "grad_norm": 0.07770712903979533,
1985
+ "learning_rate": 1.2893934026563873e-05,
1986
+ "loss": 2.2666,
1987
+ "step": 271
1988
+ },
1989
+ {
1990
+ "epoch": 2.2666666666666666,
1991
+ "grad_norm": 0.07846164594226922,
1992
+ "learning_rate": 1.2793823644219445e-05,
1993
+ "loss": 2.2855,
1994
+ "step": 272
1995
+ },
1996
+ {
1997
+ "epoch": 2.275,
1998
+ "grad_norm": 0.08498339693180243,
1999
+ "learning_rate": 1.269378583768554e-05,
2000
+ "loss": 2.2733,
2001
+ "step": 273
2002
+ },
2003
+ {
2004
+ "epoch": 2.283333333333333,
2005
+ "grad_norm": 0.07834222258922019,
2006
+ "learning_rate": 1.2593825592845122e-05,
2007
+ "loss": 2.3193,
2008
+ "step": 274
2009
+ },
2010
+ {
2011
+ "epoch": 2.2916666666666665,
2012
+ "grad_norm": 0.08132580954052983,
2013
+ "learning_rate": 1.2493947891715491e-05,
2014
+ "loss": 2.3085,
2015
+ "step": 275
2016
+ },
2017
+ {
2018
+ "epoch": 2.3,
2019
+ "grad_norm": 0.07883697009265064,
2020
+ "learning_rate": 1.239415771219996e-05,
2021
+ "loss": 2.3545,
2022
+ "step": 276
2023
+ },
2024
+ {
2025
+ "epoch": 2.3083333333333336,
2026
+ "grad_norm": 0.08023901828387182,
2027
+ "learning_rate": 1.2294460027839779e-05,
2028
+ "loss": 2.3489,
2029
+ "step": 277
2030
+ },
2031
+ {
2032
+ "epoch": 2.3166666666666664,
2033
+ "grad_norm": 0.08930364086676225,
2034
+ "learning_rate": 1.2194859807566216e-05,
2035
+ "loss": 2.2591,
2036
+ "step": 278
2037
+ },
2038
+ {
2039
+ "epoch": 2.325,
2040
+ "grad_norm": 0.08343332964333285,
2041
+ "learning_rate": 1.2095362015452961e-05,
2042
+ "loss": 2.3404,
2043
+ "step": 279
2044
+ },
2045
+ {
2046
+ "epoch": 2.3333333333333335,
2047
+ "grad_norm": 0.08292455976075656,
2048
+ "learning_rate": 1.199597161046867e-05,
2049
+ "loss": 2.3028,
2050
+ "step": 280
2051
+ },
2052
+ {
2053
+ "epoch": 2.341666666666667,
2054
+ "grad_norm": 0.08627078651851632,
2055
+ "learning_rate": 1.189669354622982e-05,
2056
+ "loss": 2.343,
2057
+ "step": 281
2058
+ },
2059
+ {
2060
+ "epoch": 2.35,
2061
+ "grad_norm": 0.08202097516344958,
2062
+ "learning_rate": 1.1797532770753842e-05,
2063
+ "loss": 2.326,
2064
+ "step": 282
2065
+ },
2066
+ {
2067
+ "epoch": 2.3583333333333334,
2068
+ "grad_norm": 0.08362611496815728,
2069
+ "learning_rate": 1.169849422621248e-05,
2070
+ "loss": 2.3035,
2071
+ "step": 283
2072
+ },
2073
+ {
2074
+ "epoch": 2.3666666666666667,
2075
+ "grad_norm": 0.08888611458113292,
2076
+ "learning_rate": 1.1599582848685506e-05,
2077
+ "loss": 2.2812,
2078
+ "step": 284
2079
+ },
2080
+ {
2081
+ "epoch": 2.375,
2082
+ "grad_norm": 0.08217261091117088,
2083
+ "learning_rate": 1.1500803567914671e-05,
2084
+ "loss": 2.3378,
2085
+ "step": 285
2086
+ },
2087
+ {
2088
+ "epoch": 2.3833333333333333,
2089
+ "grad_norm": 0.07985728135451624,
2090
+ "learning_rate": 1.1402161307058047e-05,
2091
+ "loss": 2.3522,
2092
+ "step": 286
2093
+ },
2094
+ {
2095
+ "epoch": 2.3916666666666666,
2096
+ "grad_norm": 0.08014525439116486,
2097
+ "learning_rate": 1.1303660982444624e-05,
2098
+ "loss": 2.2256,
2099
+ "step": 287
2100
+ },
2101
+ {
2102
+ "epoch": 2.4,
2103
+ "grad_norm": 0.08787593050595495,
2104
+ "learning_rate": 1.1205307503329286e-05,
2105
+ "loss": 2.2974,
2106
+ "step": 288
2107
+ },
2108
+ {
2109
+ "epoch": 2.408333333333333,
2110
+ "grad_norm": 0.08195162040998395,
2111
+ "learning_rate": 1.1107105771648151e-05,
2112
+ "loss": 2.353,
2113
+ "step": 289
2114
+ },
2115
+ {
2116
+ "epoch": 2.4166666666666665,
2117
+ "grad_norm": 0.08267743479386988,
2118
+ "learning_rate": 1.1009060681774236e-05,
2119
+ "loss": 2.3274,
2120
+ "step": 290
2121
+ },
2122
+ {
2123
+ "epoch": 2.425,
2124
+ "grad_norm": 0.08798947281948663,
2125
+ "learning_rate": 1.0911177120273537e-05,
2126
+ "loss": 2.3404,
2127
+ "step": 291
2128
+ },
2129
+ {
2130
+ "epoch": 2.4333333333333336,
2131
+ "grad_norm": 0.08828111892887862,
2132
+ "learning_rate": 1.0813459965661489e-05,
2133
+ "loss": 2.3348,
2134
+ "step": 292
2135
+ },
2136
+ {
2137
+ "epoch": 2.4416666666666664,
2138
+ "grad_norm": 0.08102528742267785,
2139
+ "learning_rate": 1.0715914088159789e-05,
2140
+ "loss": 2.2863,
2141
+ "step": 293
2142
+ },
2143
+ {
2144
+ "epoch": 2.45,
2145
+ "grad_norm": 0.0866645702075036,
2146
+ "learning_rate": 1.06185443494537e-05,
2147
+ "loss": 2.3357,
2148
+ "step": 294
2149
+ },
2150
+ {
2151
+ "epoch": 2.4583333333333335,
2152
+ "grad_norm": 0.08290121294865929,
2153
+ "learning_rate": 1.0521355602449723e-05,
2154
+ "loss": 2.3537,
2155
+ "step": 295
2156
+ },
2157
+ {
2158
+ "epoch": 2.466666666666667,
2159
+ "grad_norm": 0.08332374744178081,
2160
+ "learning_rate": 1.042435269103374e-05,
2161
+ "loss": 2.3554,
2162
+ "step": 296
2163
+ },
2164
+ {
2165
+ "epoch": 2.475,
2166
+ "grad_norm": 0.08367195510948358,
2167
+ "learning_rate": 1.0327540449829583e-05,
2168
+ "loss": 2.3384,
2169
+ "step": 297
2170
+ },
2171
+ {
2172
+ "epoch": 2.4833333333333334,
2173
+ "grad_norm": 0.08673119537467149,
2174
+ "learning_rate": 1.0230923703958083e-05,
2175
+ "loss": 2.2725,
2176
+ "step": 298
2177
+ },
2178
+ {
2179
+ "epoch": 2.4916666666666667,
2180
+ "grad_norm": 0.08235186060858125,
2181
+ "learning_rate": 1.0134507268796605e-05,
2182
+ "loss": 2.328,
2183
+ "step": 299
2184
+ },
2185
+ {
2186
+ "epoch": 2.5,
2187
+ "grad_norm": 0.08408079009588813,
2188
+ "learning_rate": 1.0038295949739004e-05,
2189
+ "loss": 2.3403,
2190
+ "step": 300
2191
+ },
2192
+ {
2193
+ "epoch": 2.5,
2194
+ "eval_loss": 2.3881967067718506,
2195
+ "eval_runtime": 82.1489,
2196
+ "eval_samples_per_second": 4.991,
2197
+ "eval_steps_per_second": 0.316,
2198
+ "step": 300
2199
+ },
2200
+ {
2201
+ "epoch": 2.5083333333333333,
2202
+ "grad_norm": 0.07909547450093556,
2203
+ "learning_rate": 9.942294541956169e-06,
2204
+ "loss": 2.3357,
2205
+ "step": 301
2206
+ },
2207
+ {
2208
+ "epoch": 2.5166666666666666,
2209
+ "grad_norm": 0.08766753125589274,
2210
+ "learning_rate": 9.846507830157e-06,
2211
+ "loss": 2.2503,
2212
+ "step": 302
2213
+ },
2214
+ {
2215
+ "epoch": 2.525,
2216
+ "grad_norm": 0.07987208695801865,
2217
+ "learning_rate": 9.75094058834997e-06,
2218
+ "loss": 2.3168,
2219
+ "step": 303
2220
+ },
2221
+ {
2222
+ "epoch": 2.533333333333333,
2223
+ "grad_norm": 0.08537107163629042,
2224
+ "learning_rate": 9.655597579605152e-06,
2225
+ "loss": 2.3036,
2226
+ "step": 304
2227
+ },
2228
+ {
2229
+ "epoch": 2.5416666666666665,
2230
+ "grad_norm": 0.08251527677113132,
2231
+ "learning_rate": 9.560483555816858e-06,
2232
+ "loss": 2.3419,
2233
+ "step": 305
2234
+ },
2235
+ {
2236
+ "epoch": 2.55,
2237
+ "grad_norm": 0.08523777732696665,
2238
+ "learning_rate": 9.465603257466792e-06,
2239
+ "loss": 2.3449,
2240
+ "step": 306
2241
+ },
2242
+ {
2243
+ "epoch": 2.5583333333333336,
2244
+ "grad_norm": 0.0848931418707024,
2245
+ "learning_rate": 9.370961413387778e-06,
2246
+ "loss": 2.2844,
2247
+ "step": 307
2248
+ },
2249
+ {
2250
+ "epoch": 2.5666666666666664,
2251
+ "grad_norm": 0.08156484852737556,
2252
+ "learning_rate": 9.27656274052809e-06,
2253
+ "loss": 2.3485,
2254
+ "step": 308
2255
+ },
2256
+ {
2257
+ "epoch": 2.575,
2258
+ "grad_norm": 0.08185057405642468,
2259
+ "learning_rate": 9.182411943716344e-06,
2260
+ "loss": 2.3748,
2261
+ "step": 309
2262
+ },
2263
+ {
2264
+ "epoch": 2.5833333333333335,
2265
+ "grad_norm": 0.08210521440208327,
2266
+ "learning_rate": 9.088513715427028e-06,
2267
+ "loss": 2.376,
2268
+ "step": 310
2269
+ },
2270
+ {
2271
+ "epoch": 2.591666666666667,
2272
+ "grad_norm": 0.08030540134328207,
2273
+ "learning_rate": 8.9948727355466e-06,
2274
+ "loss": 2.3196,
2275
+ "step": 311
2276
+ },
2277
+ {
2278
+ "epoch": 2.6,
2279
+ "grad_norm": 0.08216024303479584,
2280
+ "learning_rate": 8.901493671140283e-06,
2281
+ "loss": 2.3534,
2282
+ "step": 312
2283
+ },
2284
+ {
2285
+ "epoch": 2.6083333333333334,
2286
+ "grad_norm": 0.08105902557687622,
2287
+ "learning_rate": 8.808381176219426e-06,
2288
+ "loss": 2.2729,
2289
+ "step": 313
2290
+ },
2291
+ {
2292
+ "epoch": 2.6166666666666667,
2293
+ "grad_norm": 0.08410998796525411,
2294
+ "learning_rate": 8.71553989150955e-06,
2295
+ "loss": 2.3596,
2296
+ "step": 314
2297
+ },
2298
+ {
2299
+ "epoch": 2.625,
2300
+ "grad_norm": 0.08582437979635364,
2301
+ "learning_rate": 8.622974444219076e-06,
2302
+ "loss": 2.3063,
2303
+ "step": 315
2304
+ },
2305
+ {
2306
+ "epoch": 2.6333333333333333,
2307
+ "grad_norm": 0.08419960708603666,
2308
+ "learning_rate": 8.530689447808683e-06,
2309
+ "loss": 2.3468,
2310
+ "step": 316
2311
+ },
2312
+ {
2313
+ "epoch": 2.6416666666666666,
2314
+ "grad_norm": 0.08532017727647645,
2315
+ "learning_rate": 8.438689501761387e-06,
2316
+ "loss": 2.3378,
2317
+ "step": 317
2318
+ },
2319
+ {
2320
+ "epoch": 2.65,
2321
+ "grad_norm": 0.08544492639100988,
2322
+ "learning_rate": 8.346979191353288e-06,
2323
+ "loss": 2.2872,
2324
+ "step": 318
2325
+ },
2326
+ {
2327
+ "epoch": 2.658333333333333,
2328
+ "grad_norm": 0.0825611786693761,
2329
+ "learning_rate": 8.255563087425069e-06,
2330
+ "loss": 2.3037,
2331
+ "step": 319
2332
+ },
2333
+ {
2334
+ "epoch": 2.6666666666666665,
2335
+ "grad_norm": 0.07923900030264817,
2336
+ "learning_rate": 8.164445746154141e-06,
2337
+ "loss": 2.2746,
2338
+ "step": 320
2339
+ },
2340
+ {
2341
+ "epoch": 2.675,
2342
+ "grad_norm": 0.0805988851220756,
2343
+ "learning_rate": 8.073631708827614e-06,
2344
+ "loss": 2.3116,
2345
+ "step": 321
2346
+ },
2347
+ {
2348
+ "epoch": 2.6833333333333336,
2349
+ "grad_norm": 0.07902450485255898,
2350
+ "learning_rate": 7.983125501615913e-06,
2351
+ "loss": 2.3253,
2352
+ "step": 322
2353
+ },
2354
+ {
2355
+ "epoch": 2.6916666666666664,
2356
+ "grad_norm": 0.08586994856844313,
2357
+ "learning_rate": 7.892931635347223e-06,
2358
+ "loss": 2.3636,
2359
+ "step": 323
2360
+ },
2361
+ {
2362
+ "epoch": 2.7,
2363
+ "grad_norm": 0.08029033935205021,
2364
+ "learning_rate": 7.803054605282652e-06,
2365
+ "loss": 2.3023,
2366
+ "step": 324
2367
+ },
2368
+ {
2369
+ "epoch": 2.7083333333333335,
2370
+ "grad_norm": 0.08041087816983067,
2371
+ "learning_rate": 7.713498890892208e-06,
2372
+ "loss": 2.3629,
2373
+ "step": 325
2374
+ },
2375
+ {
2376
+ "epoch": 2.716666666666667,
2377
+ "grad_norm": 0.08451031313730265,
2378
+ "learning_rate": 7.624268955631531e-06,
2379
+ "loss": 2.2625,
2380
+ "step": 326
2381
+ },
2382
+ {
2383
+ "epoch": 2.725,
2384
+ "grad_norm": 0.07898217475608488,
2385
+ "learning_rate": 7.53536924671942e-06,
2386
+ "loss": 2.3106,
2387
+ "step": 327
2388
+ },
2389
+ {
2390
+ "epoch": 2.7333333333333334,
2391
+ "grad_norm": 0.08283676255780481,
2392
+ "learning_rate": 7.446804194916206e-06,
2393
+ "loss": 2.3576,
2394
+ "step": 328
2395
+ },
2396
+ {
2397
+ "epoch": 2.7416666666666667,
2398
+ "grad_norm": 0.08212231805524588,
2399
+ "learning_rate": 7.358578214302908e-06,
2400
+ "loss": 2.2791,
2401
+ "step": 329
2402
+ },
2403
+ {
2404
+ "epoch": 2.75,
2405
+ "grad_norm": 0.08251122557980495,
2406
+ "learning_rate": 7.270695702061248e-06,
2407
+ "loss": 2.3553,
2408
+ "step": 330
2409
+ },
2410
+ {
2411
+ "epoch": 2.75,
2412
+ "eval_loss": 2.387129783630371,
2413
+ "eval_runtime": 81.7826,
2414
+ "eval_samples_per_second": 5.013,
2415
+ "eval_steps_per_second": 0.318,
2416
+ "step": 330
2417
+ },
2418
+ {
2419
+ "epoch": 2.7583333333333333,
2420
+ "grad_norm": 0.08008513950564178,
2421
+ "learning_rate": 7.1831610382544856e-06,
2422
+ "loss": 2.2737,
2423
+ "step": 331
2424
+ },
2425
+ {
2426
+ "epoch": 2.7666666666666666,
2427
+ "grad_norm": 0.08378397772580942,
2428
+ "learning_rate": 7.095978585609125e-06,
2429
+ "loss": 2.362,
2430
+ "step": 332
2431
+ },
2432
+ {
2433
+ "epoch": 2.775,
2434
+ "grad_norm": 0.08519607549475229,
2435
+ "learning_rate": 7.009152689297463e-06,
2436
+ "loss": 2.2601,
2437
+ "step": 333
2438
+ },
2439
+ {
2440
+ "epoch": 2.783333333333333,
2441
+ "grad_norm": 0.08038464346170233,
2442
+ "learning_rate": 6.9226876767210355e-06,
2443
+ "loss": 2.3434,
2444
+ "step": 334
2445
+ },
2446
+ {
2447
+ "epoch": 2.7916666666666665,
2448
+ "grad_norm": 0.08107258257971683,
2449
+ "learning_rate": 6.83658785729493e-06,
2450
+ "loss": 2.2608,
2451
+ "step": 335
2452
+ },
2453
+ {
2454
+ "epoch": 2.8,
2455
+ "grad_norm": 0.0801095446046233,
2456
+ "learning_rate": 6.750857522233032e-06,
2457
+ "loss": 2.3562,
2458
+ "step": 336
2459
+ },
2460
+ {
2461
+ "epoch": 2.8083333333333336,
2462
+ "grad_norm": 0.08032953635285699,
2463
+ "learning_rate": 6.665500944334116e-06,
2464
+ "loss": 2.3473,
2465
+ "step": 337
2466
+ },
2467
+ {
2468
+ "epoch": 2.8166666666666664,
2469
+ "grad_norm": 0.08165787890975398,
2470
+ "learning_rate": 6.580522377768902e-06,
2471
+ "loss": 2.3662,
2472
+ "step": 338
2473
+ },
2474
+ {
2475
+ "epoch": 2.825,
2476
+ "grad_norm": 0.08186138228862638,
2477
+ "learning_rate": 6.495926057868045e-06,
2478
+ "loss": 2.3611,
2479
+ "step": 339
2480
+ },
2481
+ {
2482
+ "epoch": 2.8333333333333335,
2483
+ "grad_norm": 0.08409693406516083,
2484
+ "learning_rate": 6.4117162009110105e-06,
2485
+ "loss": 2.3014,
2486
+ "step": 340
2487
+ },
2488
+ {
2489
+ "epoch": 2.841666666666667,
2490
+ "grad_norm": 0.08426043237254878,
2491
+ "learning_rate": 6.327897003915982e-06,
2492
+ "loss": 2.3556,
2493
+ "step": 341
2494
+ },
2495
+ {
2496
+ "epoch": 2.85,
2497
+ "grad_norm": 0.07860767709618154,
2498
+ "learning_rate": 6.244472644430632e-06,
2499
+ "loss": 2.3986,
2500
+ "step": 342
2501
+ },
2502
+ {
2503
+ "epoch": 2.8583333333333334,
2504
+ "grad_norm": 0.07913910815896576,
2505
+ "learning_rate": 6.161447280323948e-06,
2506
+ "loss": 2.3041,
2507
+ "step": 343
2508
+ },
2509
+ {
2510
+ "epoch": 2.8666666666666667,
2511
+ "grad_norm": 0.0834686817566552,
2512
+ "learning_rate": 6.078825049578985e-06,
2513
+ "loss": 2.2694,
2514
+ "step": 344
2515
+ },
2516
+ {
2517
+ "epoch": 2.875,
2518
+ "grad_norm": 0.09464173421182612,
2519
+ "learning_rate": 5.996610070086646e-06,
2520
+ "loss": 2.3291,
2521
+ "step": 345
2522
+ },
2523
+ {
2524
+ "epoch": 2.8833333333333333,
2525
+ "grad_norm": 0.08924525286993587,
2526
+ "learning_rate": 5.914806439440443e-06,
2527
+ "loss": 2.2425,
2528
+ "step": 346
2529
+ },
2530
+ {
2531
+ "epoch": 2.8916666666666666,
2532
+ "grad_norm": 0.07984144031222275,
2533
+ "learning_rate": 5.833418234732248e-06,
2534
+ "loss": 2.3212,
2535
+ "step": 347
2536
+ },
2537
+ {
2538
+ "epoch": 2.9,
2539
+ "grad_norm": 0.08119999485058818,
2540
+ "learning_rate": 5.752449512349119e-06,
2541
+ "loss": 2.3043,
2542
+ "step": 348
2543
+ },
2544
+ {
2545
+ "epoch": 2.908333333333333,
2546
+ "grad_norm": 0.08130268904604636,
2547
+ "learning_rate": 5.671904307771115e-06,
2548
+ "loss": 2.3431,
2549
+ "step": 349
2550
+ },
2551
+ {
2552
+ "epoch": 2.9166666666666665,
2553
+ "grad_norm": 0.0886368269447557,
2554
+ "learning_rate": 5.591786635370193e-06,
2555
+ "loss": 2.2584,
2556
+ "step": 350
2557
+ },
2558
+ {
2559
+ "epoch": 2.925,
2560
+ "grad_norm": 0.08449560278602129,
2561
+ "learning_rate": 5.5121004882100805e-06,
2562
+ "loss": 2.2614,
2563
+ "step": 351
2564
+ },
2565
+ {
2566
+ "epoch": 2.9333333333333336,
2567
+ "grad_norm": 0.0877133422168611,
2568
+ "learning_rate": 5.4328498378473245e-06,
2569
+ "loss": 2.3467,
2570
+ "step": 352
2571
+ },
2572
+ {
2573
+ "epoch": 2.9416666666666664,
2574
+ "grad_norm": 0.0829503072213313,
2575
+ "learning_rate": 5.354038634133295e-06,
2576
+ "loss": 2.2975,
2577
+ "step": 353
2578
+ },
2579
+ {
2580
+ "epoch": 2.95,
2581
+ "grad_norm": 0.08436627929472401,
2582
+ "learning_rate": 5.27567080501735e-06,
2583
+ "loss": 2.3115,
2584
+ "step": 354
2585
+ },
2586
+ {
2587
+ "epoch": 2.9583333333333335,
2588
+ "grad_norm": 0.08048623155801396,
2589
+ "learning_rate": 5.197750256351076e-06,
2590
+ "loss": 2.2584,
2591
+ "step": 355
2592
+ },
2593
+ {
2594
+ "epoch": 2.966666666666667,
2595
+ "grad_norm": 0.08109596859654204,
2596
+ "learning_rate": 5.120280871693596e-06,
2597
+ "loss": 2.3677,
2598
+ "step": 356
2599
+ },
2600
+ {
2601
+ "epoch": 2.975,
2602
+ "grad_norm": 0.081013576151029,
2603
+ "learning_rate": 5.0432665121180266e-06,
2604
+ "loss": 2.3585,
2605
+ "step": 357
2606
+ },
2607
+ {
2608
+ "epoch": 2.9833333333333334,
2609
+ "grad_norm": 0.08546479543984016,
2610
+ "learning_rate": 4.966711016019037e-06,
2611
+ "loss": 2.303,
2612
+ "step": 358
2613
+ },
2614
+ {
2615
+ "epoch": 2.9916666666666667,
2616
+ "grad_norm": 0.08245660024002954,
2617
+ "learning_rate": 4.890618198921555e-06,
2618
+ "loss": 2.3149,
2619
+ "step": 359
2620
+ },
2621
+ {
2622
+ "epoch": 3.0,
2623
+ "grad_norm": 0.08512068224524219,
2624
+ "learning_rate": 4.814991853290595e-06,
2625
+ "loss": 2.2894,
2626
+ "step": 360
2627
+ },
2628
+ {
2629
+ "epoch": 3.0,
2630
+ "eval_loss": 2.386331081390381,
2631
+ "eval_runtime": 82.119,
2632
+ "eval_samples_per_second": 4.993,
2633
+ "eval_steps_per_second": 0.317,
2634
+ "step": 360
2635
+ }
2636
+ ],
2637
+ "logging_steps": 1,
2638
+ "max_steps": 480,
2639
+ "num_input_tokens_seen": 0,
2640
+ "num_train_epochs": 4,
2641
+ "save_steps": 60,
2642
+ "stateful_callbacks": {
2643
+ "TrainerControl": {
2644
+ "args": {
2645
+ "should_epoch_stop": false,
2646
+ "should_evaluate": false,
2647
+ "should_log": false,
2648
+ "should_save": true,
2649
+ "should_training_stop": false
2650
+ },
2651
+ "attributes": {}
2652
+ }
2653
+ },
2654
+ "total_flos": 4.466444455850803e+17,
2655
+ "train_batch_size": 4,
2656
+ "trial_name": null,
2657
+ "trial_params": null
2658
+ }
checkpoint-360/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0950ae128e4d4958ddb8a58739e4390730bca7076e922a94736a9f4ca7c6f0f1
3
+ size 8504
checkpoint-360/zero_to_fp32.py ADDED
@@ -0,0 +1,760 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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:
14
+ # python zero_to_fp32.py . output_dir/
15
+ # or
16
+ # python zero_to_fp32.py . output_dir/ --safe_serialization
17
+
18
+ import argparse
19
+ import torch
20
+ import glob
21
+ import math
22
+ import os
23
+ import re
24
+ import gc
25
+ import json
26
+ import numpy as np
27
+ from tqdm import tqdm
28
+ from collections import OrderedDict
29
+ from dataclasses import dataclass
30
+
31
+ # while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
32
+ # DeepSpeed data structures it has to be available in the current python environment.
33
+ from deepspeed.utils import logger
34
+ from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
35
+ FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
36
+ FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
37
+
38
+
39
+ @dataclass
40
+ class zero_model_state:
41
+ buffers: dict()
42
+ param_shapes: dict()
43
+ shared_params: list
44
+ ds_version: int
45
+ frozen_param_shapes: dict()
46
+ frozen_param_fragments: dict()
47
+
48
+
49
+ debug = 0
50
+
51
+ # load to cpu
52
+ device = torch.device('cpu')
53
+
54
+
55
+ def atoi(text):
56
+ return int(text) if text.isdigit() else text
57
+
58
+
59
+ def natural_keys(text):
60
+ '''
61
+ alist.sort(key=natural_keys) sorts in human order
62
+ http://nedbatchelder.com/blog/200712/human_sorting.html
63
+ (See Toothy's implementation in the comments)
64
+ '''
65
+ return [atoi(c) for c in re.split(r'(\d+)', text)]
66
+
67
+
68
+ def get_model_state_file(checkpoint_dir, zero_stage):
69
+ if not os.path.isdir(checkpoint_dir):
70
+ raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
71
+
72
+ # there should be only one file
73
+ if zero_stage <= 2:
74
+ file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
75
+ elif zero_stage == 3:
76
+ file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
77
+
78
+ if not os.path.exists(file):
79
+ raise FileNotFoundError(f"can't find model states file at '{file}'")
80
+
81
+ return file
82
+
83
+
84
+ def get_checkpoint_files(checkpoint_dir, glob_pattern):
85
+ # XXX: need to test that this simple glob rule works for multi-node setup too
86
+ ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
87
+
88
+ if len(ckpt_files) == 0:
89
+ raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
90
+
91
+ return ckpt_files
92
+
93
+
94
+ def get_optim_files(checkpoint_dir):
95
+ return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
96
+
97
+
98
+ def get_model_state_files(checkpoint_dir):
99
+ return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
100
+
101
+
102
+ def parse_model_states(files):
103
+ zero_model_states = []
104
+ for file in files:
105
+ state_dict = torch.load(file, map_location=device, weights_only=False)
106
+
107
+ if BUFFER_NAMES not in state_dict:
108
+ raise ValueError(f"{file} is not a model state checkpoint")
109
+ buffer_names = state_dict[BUFFER_NAMES]
110
+ if debug:
111
+ print("Found buffers:", buffer_names)
112
+
113
+ # recover just the buffers while restoring them to fp32 if they were saved in fp16
114
+ buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
115
+ param_shapes = state_dict[PARAM_SHAPES]
116
+
117
+ # collect parameters that are included in param_shapes
118
+ param_names = []
119
+ for s in param_shapes:
120
+ for name in s.keys():
121
+ param_names.append(name)
122
+
123
+ # update with frozen parameters
124
+ frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
125
+ if frozen_param_shapes is not None:
126
+ if debug:
127
+ print(f"Found frozen_param_shapes: {frozen_param_shapes}")
128
+ param_names += list(frozen_param_shapes.keys())
129
+
130
+ # handle shared params
131
+ shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
132
+
133
+ ds_version = state_dict.get(DS_VERSION, None)
134
+
135
+ frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
136
+
137
+ z_model_state = zero_model_state(buffers=buffers,
138
+ param_shapes=param_shapes,
139
+ shared_params=shared_params,
140
+ ds_version=ds_version,
141
+ frozen_param_shapes=frozen_param_shapes,
142
+ frozen_param_fragments=frozen_param_fragments)
143
+ zero_model_states.append(z_model_state)
144
+
145
+ return zero_model_states
146
+
147
+
148
+ def parse_optim_states(files, ds_checkpoint_dir):
149
+ total_files = len(files)
150
+ state_dicts = []
151
+ for f in tqdm(files, desc='Loading checkpoint shards'):
152
+ state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
153
+ # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
154
+ # and also handle the case where it was already removed by another helper script
155
+ state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
156
+ state_dicts.append(state_dict)
157
+
158
+ if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
159
+ raise ValueError(f"{files[0]} is not a zero checkpoint")
160
+ zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
161
+ world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
162
+
163
+ # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
164
+ # parameters can be different from data parallelism for non-expert parameters. So we can just
165
+ # use the max of the partition_count to get the dp world_size.
166
+
167
+ if type(world_size) is list:
168
+ world_size = max(world_size)
169
+
170
+ if world_size != total_files:
171
+ raise ValueError(
172
+ f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
173
+ "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
174
+ )
175
+
176
+ # the groups are named differently in each stage
177
+ if zero_stage <= 2:
178
+ fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
179
+ elif zero_stage == 3:
180
+ fp32_groups_key = FP32_FLAT_GROUPS
181
+ else:
182
+ raise ValueError(f"unknown zero stage {zero_stage}")
183
+
184
+ fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
185
+ return zero_stage, world_size, fp32_flat_groups
186
+
187
+
188
+ def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
189
+ """
190
+ Returns fp32 state_dict reconstructed from ds checkpoint
191
+
192
+ Args:
193
+ - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
194
+
195
+ """
196
+ print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
197
+
198
+ optim_files = get_optim_files(ds_checkpoint_dir)
199
+ zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
200
+ print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
201
+
202
+ model_files = get_model_state_files(ds_checkpoint_dir)
203
+
204
+ zero_model_states = parse_model_states(model_files)
205
+ print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
206
+
207
+ if zero_stage <= 2:
208
+ return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
209
+ exclude_frozen_parameters)
210
+ elif zero_stage == 3:
211
+ return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
212
+ exclude_frozen_parameters)
213
+
214
+
215
+ def _zero2_merge_frozen_params(state_dict, zero_model_states):
216
+ if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
217
+ return
218
+
219
+ frozen_param_shapes = zero_model_states[0].frozen_param_shapes
220
+ frozen_param_fragments = zero_model_states[0].frozen_param_fragments
221
+
222
+ if debug:
223
+ num_elem = sum(s.numel() for s in frozen_param_shapes.values())
224
+ print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
225
+
226
+ wanted_params = len(frozen_param_shapes)
227
+ wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
228
+ avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
229
+ print(f'Frozen params: Have {avail_numel} numels to process.')
230
+ print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
231
+
232
+ total_params = 0
233
+ total_numel = 0
234
+ for name, shape in frozen_param_shapes.items():
235
+ total_params += 1
236
+ unpartitioned_numel = shape.numel()
237
+ total_numel += unpartitioned_numel
238
+
239
+ state_dict[name] = frozen_param_fragments[name]
240
+
241
+ if debug:
242
+ print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
243
+
244
+ print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
245
+
246
+
247
+ def _has_callable(obj, fn):
248
+ attr = getattr(obj, fn, None)
249
+ return callable(attr)
250
+
251
+
252
+ def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
253
+ param_shapes = zero_model_states[0].param_shapes
254
+
255
+ # Reconstruction protocol:
256
+ #
257
+ # XXX: document this
258
+
259
+ if debug:
260
+ for i in range(world_size):
261
+ for j in range(len(fp32_flat_groups[0])):
262
+ print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
263
+
264
+ # XXX: memory usage doubles here (zero2)
265
+ num_param_groups = len(fp32_flat_groups[0])
266
+ merged_single_partition_of_fp32_groups = []
267
+ for i in range(num_param_groups):
268
+ merged_partitions = [sd[i] for sd in fp32_flat_groups]
269
+ full_single_fp32_vector = torch.cat(merged_partitions, 0)
270
+ merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
271
+ avail_numel = sum(
272
+ [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
273
+
274
+ if debug:
275
+ wanted_params = sum([len(shapes) for shapes in param_shapes])
276
+ wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
277
+ # not asserting if there is a mismatch due to possible padding
278
+ print(f"Have {avail_numel} numels to process.")
279
+ print(f"Need {wanted_numel} numels in {wanted_params} params.")
280
+
281
+ # params
282
+ # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
283
+ # out-of-core computing solution
284
+ total_numel = 0
285
+ total_params = 0
286
+ for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
287
+ offset = 0
288
+ avail_numel = full_single_fp32_vector.numel()
289
+ for name, shape in shapes.items():
290
+
291
+ unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
292
+ total_numel += unpartitioned_numel
293
+ total_params += 1
294
+
295
+ if debug:
296
+ print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
297
+ state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
298
+ offset += unpartitioned_numel
299
+
300
+ # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
301
+ # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
302
+ # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
303
+ # live optimizer object, so we are checking that the numbers are within the right range
304
+ align_to = 2 * world_size
305
+
306
+ def zero2_align(x):
307
+ return align_to * math.ceil(x / align_to)
308
+
309
+ if debug:
310
+ print(f"original offset={offset}, avail_numel={avail_numel}")
311
+
312
+ offset = zero2_align(offset)
313
+ avail_numel = zero2_align(avail_numel)
314
+
315
+ if debug:
316
+ print(f"aligned offset={offset}, avail_numel={avail_numel}")
317
+
318
+ # Sanity check
319
+ if offset != avail_numel:
320
+ raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
321
+
322
+ print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
323
+
324
+
325
+ def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
326
+ exclude_frozen_parameters):
327
+ state_dict = OrderedDict()
328
+
329
+ # buffers
330
+ buffers = zero_model_states[0].buffers
331
+ state_dict.update(buffers)
332
+ if debug:
333
+ print(f"added {len(buffers)} buffers")
334
+
335
+ if not exclude_frozen_parameters:
336
+ _zero2_merge_frozen_params(state_dict, zero_model_states)
337
+
338
+ _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
339
+
340
+ # recover shared parameters
341
+ for pair in zero_model_states[0].shared_params:
342
+ if pair[1] in state_dict:
343
+ state_dict[pair[0]] = state_dict[pair[1]]
344
+
345
+ return state_dict
346
+
347
+
348
+ def zero3_partitioned_param_info(unpartitioned_numel, world_size):
349
+ remainder = unpartitioned_numel % world_size
350
+ padding_numel = (world_size - remainder) if remainder else 0
351
+ partitioned_numel = math.ceil(unpartitioned_numel / world_size)
352
+ return partitioned_numel, padding_numel
353
+
354
+
355
+ def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
356
+ if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
357
+ return
358
+
359
+ if debug:
360
+ for i in range(world_size):
361
+ num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
362
+ print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
363
+
364
+ frozen_param_shapes = zero_model_states[0].frozen_param_shapes
365
+ wanted_params = len(frozen_param_shapes)
366
+ wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
367
+ avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
368
+ print(f'Frozen params: Have {avail_numel} numels to process.')
369
+ print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
370
+
371
+ total_params = 0
372
+ total_numel = 0
373
+ for name, shape in zero_model_states[0].frozen_param_shapes.items():
374
+ total_params += 1
375
+ unpartitioned_numel = shape.numel()
376
+ total_numel += unpartitioned_numel
377
+
378
+ param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
379
+ state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
380
+
381
+ partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
382
+
383
+ if debug:
384
+ print(
385
+ f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
386
+ )
387
+
388
+ print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
389
+
390
+
391
+ class GatheredTensor:
392
+ """
393
+ A pseudo tensor that collects partitioned weights.
394
+ It is more memory efficient when there are multiple groups.
395
+ """
396
+
397
+ def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
398
+ self.flat_groups = flat_groups
399
+ self.flat_groups_offset = flat_groups_offset
400
+ self.offset = offset
401
+ self.partitioned_numel = partitioned_numel
402
+ self.shape = shape
403
+ self.dtype = self.flat_groups[0][0].dtype
404
+
405
+ def contiguous(self):
406
+ """
407
+ Merge partitioned weights from flat_groups into a single tensor.
408
+ """
409
+ end_idx = self.offset + self.partitioned_numel
410
+ world_size = len(self.flat_groups)
411
+ pad_flat_param_chunks = []
412
+
413
+ for rank_i in range(world_size):
414
+ # for each rank, we need to collect weights from related group/groups
415
+ flat_groups_at_rank_i = self.flat_groups[rank_i]
416
+ start_group_id = None
417
+ end_group_id = None
418
+ for group_id in range(len(self.flat_groups_offset)):
419
+ if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
420
+ start_group_id = group_id
421
+ if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
422
+ end_group_id = group_id
423
+ break
424
+ # collect weights from related group/groups
425
+ for group_id in range(start_group_id, end_group_id + 1):
426
+ flat_tensor = flat_groups_at_rank_i[group_id]
427
+ start_offset = self.offset - self.flat_groups_offset[group_id]
428
+ end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
429
+ pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
430
+
431
+ # collect weights from all ranks
432
+ pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
433
+ param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
434
+ return param
435
+
436
+
437
+ def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
438
+ param_shapes = zero_model_states[0].param_shapes
439
+ avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size
440
+
441
+ # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
442
+ # param, re-consolidating each param, while dealing with padding if any
443
+
444
+ # merge list of dicts, preserving order
445
+ param_shapes = {k: v for d in param_shapes for k, v in d.items()}
446
+
447
+ if debug:
448
+ for i in range(world_size):
449
+ print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
450
+
451
+ wanted_params = len(param_shapes)
452
+ wanted_numel = sum(shape.numel() for shape in param_shapes.values())
453
+ # not asserting if there is a mismatch due to possible padding
454
+ avail_numel = fp32_flat_groups[0].numel() * world_size
455
+ print(f"Trainable params: Have {avail_numel} numels to process.")
456
+ print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
457
+
458
+ # params
459
+ # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
460
+ # out-of-core computing solution
461
+ offset = 0
462
+ total_numel = 0
463
+ total_params = 0
464
+ flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
465
+ for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
466
+ unpartitioned_numel = shape.numel()
467
+ total_numel += unpartitioned_numel
468
+ total_params += 1
469
+ partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
470
+
471
+ if debug:
472
+ print(
473
+ f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
474
+ )
475
+
476
+ # memory efficient tensor
477
+ tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
478
+ state_dict[name] = tensor
479
+ offset += partitioned_numel
480
+
481
+ offset *= world_size
482
+
483
+ # Sanity check
484
+ if offset != avail_numel:
485
+ raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
486
+
487
+ print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
488
+
489
+
490
+ def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
491
+ exclude_frozen_parameters):
492
+ state_dict = OrderedDict()
493
+
494
+ # buffers
495
+ buffers = zero_model_states[0].buffers
496
+ state_dict.update(buffers)
497
+ if debug:
498
+ print(f"added {len(buffers)} buffers")
499
+
500
+ if not exclude_frozen_parameters:
501
+ _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
502
+
503
+ _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
504
+
505
+ # recover shared parameters
506
+ for pair in zero_model_states[0].shared_params:
507
+ if pair[1] in state_dict:
508
+ state_dict[pair[0]] = state_dict[pair[1]]
509
+
510
+ return state_dict
511
+
512
+
513
+ def to_torch_tensor(state_dict, return_empty_tensor=False):
514
+ """
515
+ Convert state_dict of GatheredTensor to torch tensor
516
+ """
517
+ torch_state_dict = {}
518
+ converted_tensors = {}
519
+ for name, tensor in state_dict.items():
520
+ tensor_id = id(tensor)
521
+ if tensor_id in converted_tensors: # shared tensors
522
+ shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
523
+ torch_state_dict[name] = shared_tensor
524
+ else:
525
+ converted_tensors[tensor_id] = name
526
+ if return_empty_tensor:
527
+ torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
528
+ else:
529
+ torch_state_dict[name] = tensor.contiguous()
530
+ return torch_state_dict
531
+
532
+
533
+ def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
534
+ tag=None,
535
+ exclude_frozen_parameters=False,
536
+ lazy_mode=False):
537
+ """
538
+ Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
539
+ ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
540
+ via a model hub.
541
+
542
+ Args:
543
+ - ``checkpoint_dir``: path to the desired checkpoint folder
544
+ - ``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``
545
+ - ``exclude_frozen_parameters``: exclude frozen parameters
546
+ - ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
547
+ Convert the pesduo tensor to torch tensor by ``.contiguous()``
548
+
549
+ Returns:
550
+ - pytorch ``state_dict``
551
+
552
+ A typical usage might be ::
553
+
554
+ from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
555
+ # do the training and checkpoint saving
556
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
557
+ model = model.cpu() # move to cpu
558
+ model.load_state_dict(state_dict)
559
+ # submit to model hub or save the model to share with others
560
+
561
+ In this example the ``model`` will no longer be usable in the deepspeed context of the same
562
+ application. i.e. you will need to re-initialize the deepspeed engine, since
563
+ ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
564
+
565
+ If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
566
+
567
+ Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
568
+ You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
569
+ the checkpoint. Or you can load state_dict in lazy mode ::
570
+
571
+ from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
572
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
573
+ for name, lazy_tensor in state_dict.item():
574
+ tensor = lazy_tensor.contiguous() # to cpu
575
+ print(name, tensor)
576
+ # del tensor to release memory if it no longer in use
577
+ """
578
+ if tag is None:
579
+ latest_path = os.path.join(checkpoint_dir, 'latest')
580
+ if os.path.isfile(latest_path):
581
+ with open(latest_path, 'r') as fd:
582
+ tag = fd.read().strip()
583
+ else:
584
+ raise ValueError(f"Unable to find 'latest' file at {latest_path}")
585
+
586
+ ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
587
+
588
+ if not os.path.isdir(ds_checkpoint_dir):
589
+ raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
590
+
591
+ state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
592
+ if lazy_mode:
593
+ return state_dict
594
+ else:
595
+ return to_torch_tensor(state_dict)
596
+
597
+
598
+ def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
599
+ output_dir,
600
+ max_shard_size="5GB",
601
+ safe_serialization=False,
602
+ tag=None,
603
+ exclude_frozen_parameters=False):
604
+ """
605
+ Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
606
+ loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
607
+
608
+ Args:
609
+ - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
610
+ - ``output_dir``: directory to the pytorch fp32 state_dict output files
611
+ - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
612
+ - ``safe_serialization``: whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
613
+ - ``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``
614
+ - ``exclude_frozen_parameters``: exclude frozen parameters
615
+ """
616
+
617
+ # Dependency pre-check
618
+ if safe_serialization:
619
+ try:
620
+ from safetensors.torch import save_file
621
+ except ImportError:
622
+ print('If you want to use `safe_serialization`, please `pip install safetensors`')
623
+ raise
624
+ if max_shard_size is not None:
625
+ try:
626
+ from huggingface_hub import split_torch_state_dict_into_shards
627
+ except ImportError:
628
+ print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
629
+ raise
630
+
631
+ # Convert zero checkpoint to state_dict
632
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
633
+ tag,
634
+ exclude_frozen_parameters,
635
+ lazy_mode=True)
636
+
637
+ # Shard the model if it is too big.
638
+ weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
639
+ if max_shard_size is not None:
640
+ filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
641
+ # an memory-efficient approach for sharding
642
+ empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
643
+ state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
644
+ filename_pattern=filename_pattern,
645
+ max_shard_size=max_shard_size)
646
+ else:
647
+ from collections import namedtuple
648
+ StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
649
+ state_dict_split = StateDictSplit(is_sharded=False,
650
+ filename_to_tensors={weights_name: list(state_dict.keys())})
651
+
652
+ # Save the model by shard
653
+ os.makedirs(output_dir, exist_ok=True)
654
+ filename_to_tensors = state_dict_split.filename_to_tensors.items()
655
+ for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
656
+ shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
657
+ shard_state_dict = to_torch_tensor(shard_state_dict)
658
+ output_path = os.path.join(output_dir, shard_file)
659
+ if safe_serialization:
660
+ save_file(shard_state_dict, output_path, metadata={"format": "pt"})
661
+ else:
662
+ torch.save(shard_state_dict, output_path)
663
+ # release the memory of current shard
664
+ for tensor_name in list(shard_state_dict.keys()):
665
+ del state_dict[tensor_name]
666
+ del shard_state_dict[tensor_name]
667
+ del shard_state_dict
668
+ gc.collect()
669
+
670
+ # Save index if sharded
671
+ if state_dict_split.is_sharded:
672
+ index = {
673
+ "metadata": state_dict_split.metadata,
674
+ "weight_map": state_dict_split.tensor_to_filename,
675
+ }
676
+ save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
677
+ save_index_file = os.path.join(output_dir, save_index_file)
678
+ with open(save_index_file, "w", encoding="utf-8") as f:
679
+ content = json.dumps(index, indent=2, sort_keys=True) + "\n"
680
+ f.write(content)
681
+
682
+
683
+ def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
684
+ """
685
+ 1. Put the provided model to cpu
686
+ 2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
687
+ 3. Load it into the provided model
688
+
689
+ Args:
690
+ - ``model``: the model object to update
691
+ - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
692
+ - ``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``
693
+
694
+ Returns:
695
+ - ``model`: modified model
696
+
697
+ Make sure you have plenty of CPU memory available before you call this function. If you don't
698
+ have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
699
+ conveniently placed for you in the checkpoint folder.
700
+
701
+ A typical usage might be ::
702
+
703
+ from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
704
+ model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
705
+ # submit to model hub or save the model to share with others
706
+
707
+ Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
708
+ of the same application. i.e. you will need to re-initialize the deepspeed engine, since
709
+ ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
710
+
711
+ """
712
+ logger.info(f"Extracting fp32 weights")
713
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
714
+
715
+ logger.info(f"Overwriting model with fp32 weights")
716
+ model = model.cpu()
717
+ model.load_state_dict(state_dict, strict=False)
718
+
719
+ return model
720
+
721
+
722
+ if __name__ == "__main__":
723
+ parser = argparse.ArgumentParser()
724
+ parser.add_argument("checkpoint_dir",
725
+ type=str,
726
+ help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
727
+ parser.add_argument("output_dir",
728
+ type=str,
729
+ help="directory to the pytorch fp32 state_dict output files"
730
+ "(e.g. path/checkpoint-12-output/)")
731
+ parser.add_argument(
732
+ "--max_shard_size",
733
+ type=str,
734
+ default="5GB",
735
+ help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
736
+ "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
737
+ "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
738
+ "without CPU OOM issues.")
739
+ parser.add_argument(
740
+ "--safe_serialization",
741
+ default=False,
742
+ action='store_true',
743
+ help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
744
+ parser.add_argument("-t",
745
+ "--tag",
746
+ type=str,
747
+ default=None,
748
+ help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
749
+ parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
750
+ parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
751
+ args = parser.parse_args()
752
+
753
+ debug = args.debug
754
+
755
+ convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
756
+ args.output_dir,
757
+ max_shard_size=args.max_shard_size,
758
+ safe_serialization=args.safe_serialization,
759
+ tag=args.tag,
760
+ exclude_frozen_parameters=args.exclude_frozen_parameters)
checkpoint-420/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: NewEden/Hamanasu-KTO-V2
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-420/adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "NewEden/Hamanasu-KTO-V2",
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": 16,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 128,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "gate_proj",
28
+ "o_proj",
29
+ "q_proj",
30
+ "k_proj",
31
+ "down_proj",
32
+ "up_proj",
33
+ "v_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": true
39
+ }
checkpoint-420/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95fa37d9c7ab3421ae2b662d0f902689ce2e64e92c4348d941a055be12681c8a
3
+ size 486600536
checkpoint-420/latest ADDED
@@ -0,0 +1 @@
 
 
1
+ global_step420
checkpoint-420/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:265918a61a0314e0f11594fea15cc94488f89132a5b6d694ae26646aa63079ad
3
+ size 15024
checkpoint-420/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d93e2c7fb83e3faca8947c112fc00f12cfb3e73be0f55d679b281e23123db3ae
3
+ size 15024
checkpoint-420/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2df3dbab1a7618f30312de2972ec44d4066f88f75cf720b898007432e17a2a96
3
+ size 15024
checkpoint-420/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50c49799083d1c2eee8103a3275b06480830c78ca81702f633d79806fac560f3
3
+ size 15024
checkpoint-420/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7749be1c411bb72e5642b76dd4a581519272a010b19e8263d24eb1b38a5c7eec
3
+ size 1064
checkpoint-420/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": "<|im_end|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|finetune_right_pad_id|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
checkpoint-420/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:907a7b3b13afcc9d481433f17277a6dd7cf852c6185262597f1a849d2ebeaa45
3
+ size 17209884
checkpoint-420/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": "<|im_start|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|im_end|>",
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": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|im_end|>",
2056
+ "extra_special_tokens": {},
2057
+ "model_input_names": [
2058
+ "input_ids",
2059
+ "attention_mask"
2060
+ ],
2061
+ "model_max_length": 131072,
2062
+ "pad_token": "<|finetune_right_pad_id|>",
2063
+ "tokenizer_class": "PreTrainedTokenizer"
2064
+ }
checkpoint-420/trainer_state.json ADDED
@@ -0,0 +1,3094 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.5,
6
+ "eval_steps": 30,
7
+ "global_step": 420,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.008333333333333333,
14
+ "grad_norm": 0.9462232657835241,
15
+ "learning_rate": 8.142857142857143e-07,
16
+ "loss": 2.5443,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.008333333333333333,
21
+ "eval_loss": 2.5896365642547607,
22
+ "eval_runtime": 96.0059,
23
+ "eval_samples_per_second": 4.271,
24
+ "eval_steps_per_second": 0.271,
25
+ "step": 1
26
+ },
27
+ {
28
+ "epoch": 0.016666666666666666,
29
+ "grad_norm": 0.9597143397960513,
30
+ "learning_rate": 1.6285714285714286e-06,
31
+ "loss": 2.5524,
32
+ "step": 2
33
+ },
34
+ {
35
+ "epoch": 0.025,
36
+ "grad_norm": 0.9246258453027174,
37
+ "learning_rate": 2.442857142857143e-06,
38
+ "loss": 2.5411,
39
+ "step": 3
40
+ },
41
+ {
42
+ "epoch": 0.03333333333333333,
43
+ "grad_norm": 0.9822285829186661,
44
+ "learning_rate": 3.2571428571428572e-06,
45
+ "loss": 2.5518,
46
+ "step": 4
47
+ },
48
+ {
49
+ "epoch": 0.041666666666666664,
50
+ "grad_norm": 0.9044329068814566,
51
+ "learning_rate": 4.071428571428572e-06,
52
+ "loss": 2.4922,
53
+ "step": 5
54
+ },
55
+ {
56
+ "epoch": 0.05,
57
+ "grad_norm": 0.9131300887744053,
58
+ "learning_rate": 4.885714285714286e-06,
59
+ "loss": 2.5713,
60
+ "step": 6
61
+ },
62
+ {
63
+ "epoch": 0.058333333333333334,
64
+ "grad_norm": 0.8336298309675122,
65
+ "learning_rate": 5.7000000000000005e-06,
66
+ "loss": 2.4959,
67
+ "step": 7
68
+ },
69
+ {
70
+ "epoch": 0.06666666666666667,
71
+ "grad_norm": 0.810775409605909,
72
+ "learning_rate": 6.5142857142857145e-06,
73
+ "loss": 2.4943,
74
+ "step": 8
75
+ },
76
+ {
77
+ "epoch": 0.075,
78
+ "grad_norm": 0.6993505055921954,
79
+ "learning_rate": 7.3285714285714285e-06,
80
+ "loss": 2.5022,
81
+ "step": 9
82
+ },
83
+ {
84
+ "epoch": 0.08333333333333333,
85
+ "grad_norm": 0.5909140859664664,
86
+ "learning_rate": 8.142857142857143e-06,
87
+ "loss": 2.468,
88
+ "step": 10
89
+ },
90
+ {
91
+ "epoch": 0.09166666666666666,
92
+ "grad_norm": 0.5464791893738283,
93
+ "learning_rate": 8.957142857142857e-06,
94
+ "loss": 2.5203,
95
+ "step": 11
96
+ },
97
+ {
98
+ "epoch": 0.1,
99
+ "grad_norm": 0.41153668995149084,
100
+ "learning_rate": 9.771428571428571e-06,
101
+ "loss": 2.4912,
102
+ "step": 12
103
+ },
104
+ {
105
+ "epoch": 0.10833333333333334,
106
+ "grad_norm": 0.35433353277028035,
107
+ "learning_rate": 1.0585714285714287e-05,
108
+ "loss": 2.4467,
109
+ "step": 13
110
+ },
111
+ {
112
+ "epoch": 0.11666666666666667,
113
+ "grad_norm": 0.27579908222756766,
114
+ "learning_rate": 1.1400000000000001e-05,
115
+ "loss": 2.4599,
116
+ "step": 14
117
+ },
118
+ {
119
+ "epoch": 0.125,
120
+ "grad_norm": 0.22636758420678307,
121
+ "learning_rate": 1.2214285714285715e-05,
122
+ "loss": 2.4357,
123
+ "step": 15
124
+ },
125
+ {
126
+ "epoch": 0.13333333333333333,
127
+ "grad_norm": 0.22309908436920517,
128
+ "learning_rate": 1.3028571428571429e-05,
129
+ "loss": 2.368,
130
+ "step": 16
131
+ },
132
+ {
133
+ "epoch": 0.14166666666666666,
134
+ "grad_norm": 0.2384290311446137,
135
+ "learning_rate": 1.3842857142857143e-05,
136
+ "loss": 2.4054,
137
+ "step": 17
138
+ },
139
+ {
140
+ "epoch": 0.15,
141
+ "grad_norm": 0.2279055472006466,
142
+ "learning_rate": 1.4657142857142857e-05,
143
+ "loss": 2.4162,
144
+ "step": 18
145
+ },
146
+ {
147
+ "epoch": 0.15833333333333333,
148
+ "grad_norm": 0.24659885813398136,
149
+ "learning_rate": 1.547142857142857e-05,
150
+ "loss": 2.4109,
151
+ "step": 19
152
+ },
153
+ {
154
+ "epoch": 0.16666666666666666,
155
+ "grad_norm": 0.21920560481126147,
156
+ "learning_rate": 1.6285714285714287e-05,
157
+ "loss": 2.4344,
158
+ "step": 20
159
+ },
160
+ {
161
+ "epoch": 0.175,
162
+ "grad_norm": 0.21340860355678012,
163
+ "learning_rate": 1.71e-05,
164
+ "loss": 2.4532,
165
+ "step": 21
166
+ },
167
+ {
168
+ "epoch": 0.18333333333333332,
169
+ "grad_norm": 0.1775246176788835,
170
+ "learning_rate": 1.7914285714285715e-05,
171
+ "loss": 2.4398,
172
+ "step": 22
173
+ },
174
+ {
175
+ "epoch": 0.19166666666666668,
176
+ "grad_norm": 0.15469100364725502,
177
+ "learning_rate": 1.872857142857143e-05,
178
+ "loss": 2.4275,
179
+ "step": 23
180
+ },
181
+ {
182
+ "epoch": 0.2,
183
+ "grad_norm": 0.1261136620302219,
184
+ "learning_rate": 1.9542857142857143e-05,
185
+ "loss": 2.3855,
186
+ "step": 24
187
+ },
188
+ {
189
+ "epoch": 0.20833333333333334,
190
+ "grad_norm": 0.1251566381945981,
191
+ "learning_rate": 2.0357142857142858e-05,
192
+ "loss": 2.4008,
193
+ "step": 25
194
+ },
195
+ {
196
+ "epoch": 0.21666666666666667,
197
+ "grad_norm": 0.12280228065778742,
198
+ "learning_rate": 2.1171428571428574e-05,
199
+ "loss": 2.4086,
200
+ "step": 26
201
+ },
202
+ {
203
+ "epoch": 0.225,
204
+ "grad_norm": 0.1362748806421765,
205
+ "learning_rate": 2.1985714285714286e-05,
206
+ "loss": 2.3642,
207
+ "step": 27
208
+ },
209
+ {
210
+ "epoch": 0.23333333333333334,
211
+ "grad_norm": 0.12370426656542512,
212
+ "learning_rate": 2.2800000000000002e-05,
213
+ "loss": 2.4168,
214
+ "step": 28
215
+ },
216
+ {
217
+ "epoch": 0.24166666666666667,
218
+ "grad_norm": 0.12077140199925576,
219
+ "learning_rate": 2.3614285714285718e-05,
220
+ "loss": 2.3502,
221
+ "step": 29
222
+ },
223
+ {
224
+ "epoch": 0.25,
225
+ "grad_norm": 0.10854652278245232,
226
+ "learning_rate": 2.442857142857143e-05,
227
+ "loss": 2.323,
228
+ "step": 30
229
+ },
230
+ {
231
+ "epoch": 0.25,
232
+ "eval_loss": 2.4455511569976807,
233
+ "eval_runtime": 82.5732,
234
+ "eval_samples_per_second": 4.965,
235
+ "eval_steps_per_second": 0.315,
236
+ "step": 30
237
+ },
238
+ {
239
+ "epoch": 0.25833333333333336,
240
+ "grad_norm": 0.10286886191993252,
241
+ "learning_rate": 2.5242857142857142e-05,
242
+ "loss": 2.4007,
243
+ "step": 31
244
+ },
245
+ {
246
+ "epoch": 0.26666666666666666,
247
+ "grad_norm": 0.09687340891245565,
248
+ "learning_rate": 2.6057142857142858e-05,
249
+ "loss": 2.4088,
250
+ "step": 32
251
+ },
252
+ {
253
+ "epoch": 0.275,
254
+ "grad_norm": 0.09653492248714694,
255
+ "learning_rate": 2.6871428571428574e-05,
256
+ "loss": 2.3906,
257
+ "step": 33
258
+ },
259
+ {
260
+ "epoch": 0.2833333333333333,
261
+ "grad_norm": 0.09022900019263645,
262
+ "learning_rate": 2.7685714285714286e-05,
263
+ "loss": 2.4065,
264
+ "step": 34
265
+ },
266
+ {
267
+ "epoch": 0.2916666666666667,
268
+ "grad_norm": 0.0912409242342349,
269
+ "learning_rate": 2.85e-05,
270
+ "loss": 2.3699,
271
+ "step": 35
272
+ },
273
+ {
274
+ "epoch": 0.3,
275
+ "grad_norm": 0.09592020125185927,
276
+ "learning_rate": 2.8499644890093217e-05,
277
+ "loss": 2.3587,
278
+ "step": 36
279
+ },
280
+ {
281
+ "epoch": 0.30833333333333335,
282
+ "grad_norm": 0.0907084429462166,
283
+ "learning_rate": 2.8498579578071537e-05,
284
+ "loss": 2.4259,
285
+ "step": 37
286
+ },
287
+ {
288
+ "epoch": 0.31666666666666665,
289
+ "grad_norm": 0.09390099422567517,
290
+ "learning_rate": 2.8496804117030106e-05,
291
+ "loss": 2.3232,
292
+ "step": 38
293
+ },
294
+ {
295
+ "epoch": 0.325,
296
+ "grad_norm": 0.08704027284958313,
297
+ "learning_rate": 2.849431859545787e-05,
298
+ "loss": 2.4027,
299
+ "step": 39
300
+ },
301
+ {
302
+ "epoch": 0.3333333333333333,
303
+ "grad_norm": 0.08787482564111378,
304
+ "learning_rate": 2.849112313723319e-05,
305
+ "loss": 2.3827,
306
+ "step": 40
307
+ },
308
+ {
309
+ "epoch": 0.3416666666666667,
310
+ "grad_norm": 0.08422520058818864,
311
+ "learning_rate": 2.8487217901617672e-05,
312
+ "loss": 2.353,
313
+ "step": 41
314
+ },
315
+ {
316
+ "epoch": 0.35,
317
+ "grad_norm": 0.07979320980153469,
318
+ "learning_rate": 2.84826030832482e-05,
319
+ "loss": 2.3519,
320
+ "step": 42
321
+ },
322
+ {
323
+ "epoch": 0.35833333333333334,
324
+ "grad_norm": 0.07814774416810645,
325
+ "learning_rate": 2.8477278912127266e-05,
326
+ "loss": 2.3708,
327
+ "step": 43
328
+ },
329
+ {
330
+ "epoch": 0.36666666666666664,
331
+ "grad_norm": 0.07237049854036091,
332
+ "learning_rate": 2.847124565361149e-05,
333
+ "loss": 2.388,
334
+ "step": 44
335
+ },
336
+ {
337
+ "epoch": 0.375,
338
+ "grad_norm": 0.07354258492789081,
339
+ "learning_rate": 2.8464503608398385e-05,
340
+ "loss": 2.3586,
341
+ "step": 45
342
+ },
343
+ {
344
+ "epoch": 0.38333333333333336,
345
+ "grad_norm": 0.0771281784161838,
346
+ "learning_rate": 2.845705311251141e-05,
347
+ "loss": 2.3993,
348
+ "step": 46
349
+ },
350
+ {
351
+ "epoch": 0.39166666666666666,
352
+ "grad_norm": 0.0763264062020341,
353
+ "learning_rate": 2.844889453728318e-05,
354
+ "loss": 2.3838,
355
+ "step": 47
356
+ },
357
+ {
358
+ "epoch": 0.4,
359
+ "grad_norm": 0.07082143620733677,
360
+ "learning_rate": 2.8440028289336977e-05,
361
+ "loss": 2.3628,
362
+ "step": 48
363
+ },
364
+ {
365
+ "epoch": 0.4083333333333333,
366
+ "grad_norm": 0.0715578975320661,
367
+ "learning_rate": 2.8430454810566477e-05,
368
+ "loss": 2.361,
369
+ "step": 49
370
+ },
371
+ {
372
+ "epoch": 0.4166666666666667,
373
+ "grad_norm": 0.06881630985450242,
374
+ "learning_rate": 2.8420174578113747e-05,
375
+ "loss": 2.4392,
376
+ "step": 50
377
+ },
378
+ {
379
+ "epoch": 0.425,
380
+ "grad_norm": 0.0689279893077156,
381
+ "learning_rate": 2.8409188104345426e-05,
382
+ "loss": 2.3519,
383
+ "step": 51
384
+ },
385
+ {
386
+ "epoch": 0.43333333333333335,
387
+ "grad_norm": 0.07069081407018309,
388
+ "learning_rate": 2.8397495936827232e-05,
389
+ "loss": 2.3981,
390
+ "step": 52
391
+ },
392
+ {
393
+ "epoch": 0.44166666666666665,
394
+ "grad_norm": 0.07092917277421104,
395
+ "learning_rate": 2.8385098658296637e-05,
396
+ "loss": 2.355,
397
+ "step": 53
398
+ },
399
+ {
400
+ "epoch": 0.45,
401
+ "grad_norm": 0.0703607034709259,
402
+ "learning_rate": 2.8371996886633843e-05,
403
+ "loss": 2.3793,
404
+ "step": 54
405
+ },
406
+ {
407
+ "epoch": 0.4583333333333333,
408
+ "grad_norm": 0.07124199690967324,
409
+ "learning_rate": 2.8358191274830974e-05,
410
+ "loss": 2.4275,
411
+ "step": 55
412
+ },
413
+ {
414
+ "epoch": 0.4666666666666667,
415
+ "grad_norm": 0.07099804346309355,
416
+ "learning_rate": 2.8343682510959552e-05,
417
+ "loss": 2.3323,
418
+ "step": 56
419
+ },
420
+ {
421
+ "epoch": 0.475,
422
+ "grad_norm": 0.06967632308939245,
423
+ "learning_rate": 2.8328471318136165e-05,
424
+ "loss": 2.3883,
425
+ "step": 57
426
+ },
427
+ {
428
+ "epoch": 0.48333333333333334,
429
+ "grad_norm": 0.07156300179553134,
430
+ "learning_rate": 2.831255845448647e-05,
431
+ "loss": 2.3298,
432
+ "step": 58
433
+ },
434
+ {
435
+ "epoch": 0.49166666666666664,
436
+ "grad_norm": 0.0704201532980033,
437
+ "learning_rate": 2.8295944713107387e-05,
438
+ "loss": 2.331,
439
+ "step": 59
440
+ },
441
+ {
442
+ "epoch": 0.5,
443
+ "grad_norm": 0.06794782460291071,
444
+ "learning_rate": 2.8278630922027563e-05,
445
+ "loss": 2.3776,
446
+ "step": 60
447
+ },
448
+ {
449
+ "epoch": 0.5,
450
+ "eval_loss": 2.4216628074645996,
451
+ "eval_runtime": 82.3879,
452
+ "eval_samples_per_second": 4.976,
453
+ "eval_steps_per_second": 0.316,
454
+ "step": 60
455
+ },
456
+ {
457
+ "epoch": 0.5083333333333333,
458
+ "grad_norm": 0.07045949082426937,
459
+ "learning_rate": 2.8260617944166123e-05,
460
+ "loss": 2.3319,
461
+ "step": 61
462
+ },
463
+ {
464
+ "epoch": 0.5166666666666667,
465
+ "grad_norm": 0.0702234192794877,
466
+ "learning_rate": 2.824190667728965e-05,
467
+ "loss": 2.3647,
468
+ "step": 62
469
+ },
470
+ {
471
+ "epoch": 0.525,
472
+ "grad_norm": 0.06946814214632402,
473
+ "learning_rate": 2.8222498053967434e-05,
474
+ "loss": 2.3967,
475
+ "step": 63
476
+ },
477
+ {
478
+ "epoch": 0.5333333333333333,
479
+ "grad_norm": 0.06563265580127577,
480
+ "learning_rate": 2.8202393041525005e-05,
481
+ "loss": 2.3863,
482
+ "step": 64
483
+ },
484
+ {
485
+ "epoch": 0.5416666666666666,
486
+ "grad_norm": 0.0723770670150652,
487
+ "learning_rate": 2.8181592641995933e-05,
488
+ "loss": 2.3823,
489
+ "step": 65
490
+ },
491
+ {
492
+ "epoch": 0.55,
493
+ "grad_norm": 0.06870429029917037,
494
+ "learning_rate": 2.8160097892071847e-05,
495
+ "loss": 2.3241,
496
+ "step": 66
497
+ },
498
+ {
499
+ "epoch": 0.5583333333333333,
500
+ "grad_norm": 0.08615444480664787,
501
+ "learning_rate": 2.8137909863050806e-05,
502
+ "loss": 2.3504,
503
+ "step": 67
504
+ },
505
+ {
506
+ "epoch": 0.5666666666666667,
507
+ "grad_norm": 0.06980417460436542,
508
+ "learning_rate": 2.8115029660783887e-05,
509
+ "loss": 2.3762,
510
+ "step": 68
511
+ },
512
+ {
513
+ "epoch": 0.575,
514
+ "grad_norm": 0.0691283200064781,
515
+ "learning_rate": 2.809145842562007e-05,
516
+ "loss": 2.3202,
517
+ "step": 69
518
+ },
519
+ {
520
+ "epoch": 0.5833333333333334,
521
+ "grad_norm": 0.06434433998677834,
522
+ "learning_rate": 2.8067197332349406e-05,
523
+ "loss": 2.4117,
524
+ "step": 70
525
+ },
526
+ {
527
+ "epoch": 0.5916666666666667,
528
+ "grad_norm": 0.06712521054811822,
529
+ "learning_rate": 2.8042247590144472e-05,
530
+ "loss": 2.4234,
531
+ "step": 71
532
+ },
533
+ {
534
+ "epoch": 0.6,
535
+ "grad_norm": 0.07781170630767965,
536
+ "learning_rate": 2.8016610442500087e-05,
537
+ "loss": 2.3614,
538
+ "step": 72
539
+ },
540
+ {
541
+ "epoch": 0.6083333333333333,
542
+ "grad_norm": 0.07179449259884696,
543
+ "learning_rate": 2.7990287167171357e-05,
544
+ "loss": 2.327,
545
+ "step": 73
546
+ },
547
+ {
548
+ "epoch": 0.6166666666666667,
549
+ "grad_norm": 0.0666012429917219,
550
+ "learning_rate": 2.7963279076109976e-05,
551
+ "loss": 2.3606,
552
+ "step": 74
553
+ },
554
+ {
555
+ "epoch": 0.625,
556
+ "grad_norm": 0.07042352420672252,
557
+ "learning_rate": 2.7935587515398855e-05,
558
+ "loss": 2.387,
559
+ "step": 75
560
+ },
561
+ {
562
+ "epoch": 0.6333333333333333,
563
+ "grad_norm": 0.07141219809062525,
564
+ "learning_rate": 2.7907213865185014e-05,
565
+ "loss": 2.3975,
566
+ "step": 76
567
+ },
568
+ {
569
+ "epoch": 0.6416666666666667,
570
+ "grad_norm": 0.07530038535140655,
571
+ "learning_rate": 2.787815953961081e-05,
572
+ "loss": 2.3975,
573
+ "step": 77
574
+ },
575
+ {
576
+ "epoch": 0.65,
577
+ "grad_norm": 0.06873021297298251,
578
+ "learning_rate": 2.784842598674345e-05,
579
+ "loss": 2.3724,
580
+ "step": 78
581
+ },
582
+ {
583
+ "epoch": 0.6583333333333333,
584
+ "grad_norm": 0.06853494667979494,
585
+ "learning_rate": 2.781801468850282e-05,
586
+ "loss": 2.3994,
587
+ "step": 79
588
+ },
589
+ {
590
+ "epoch": 0.6666666666666666,
591
+ "grad_norm": 0.07164446612343163,
592
+ "learning_rate": 2.778692716058762e-05,
593
+ "loss": 2.3448,
594
+ "step": 80
595
+ },
596
+ {
597
+ "epoch": 0.675,
598
+ "grad_norm": 0.07112624750325054,
599
+ "learning_rate": 2.7755164952399844e-05,
600
+ "loss": 2.2984,
601
+ "step": 81
602
+ },
603
+ {
604
+ "epoch": 0.6833333333333333,
605
+ "grad_norm": 0.07679055297227524,
606
+ "learning_rate": 2.7722729646967527e-05,
607
+ "loss": 2.3699,
608
+ "step": 82
609
+ },
610
+ {
611
+ "epoch": 0.6916666666666667,
612
+ "grad_norm": 0.07270378630883641,
613
+ "learning_rate": 2.768962286086587e-05,
614
+ "loss": 2.3436,
615
+ "step": 83
616
+ },
617
+ {
618
+ "epoch": 0.7,
619
+ "grad_norm": 0.06869524209312625,
620
+ "learning_rate": 2.7655846244136654e-05,
621
+ "loss": 2.3856,
622
+ "step": 84
623
+ },
624
+ {
625
+ "epoch": 0.7083333333333334,
626
+ "grad_norm": 0.07006104211903366,
627
+ "learning_rate": 2.762140148020602e-05,
628
+ "loss": 2.3852,
629
+ "step": 85
630
+ },
631
+ {
632
+ "epoch": 0.7166666666666667,
633
+ "grad_norm": 0.07264285304887648,
634
+ "learning_rate": 2.758629028580055e-05,
635
+ "loss": 2.3834,
636
+ "step": 86
637
+ },
638
+ {
639
+ "epoch": 0.725,
640
+ "grad_norm": 0.07253530482477301,
641
+ "learning_rate": 2.7550514410861718e-05,
642
+ "loss": 2.3573,
643
+ "step": 87
644
+ },
645
+ {
646
+ "epoch": 0.7333333333333333,
647
+ "grad_norm": 0.07265955522289944,
648
+ "learning_rate": 2.751407563845866e-05,
649
+ "loss": 2.3163,
650
+ "step": 88
651
+ },
652
+ {
653
+ "epoch": 0.7416666666666667,
654
+ "grad_norm": 0.07374626234739601,
655
+ "learning_rate": 2.747697578469931e-05,
656
+ "loss": 2.3851,
657
+ "step": 89
658
+ },
659
+ {
660
+ "epoch": 0.75,
661
+ "grad_norm": 0.07255481420091238,
662
+ "learning_rate": 2.7439216698639904e-05,
663
+ "loss": 2.3345,
664
+ "step": 90
665
+ },
666
+ {
667
+ "epoch": 0.75,
668
+ "eval_loss": 2.4115521907806396,
669
+ "eval_runtime": 82.0248,
670
+ "eval_samples_per_second": 4.998,
671
+ "eval_steps_per_second": 0.317,
672
+ "step": 90
673
+ },
674
+ {
675
+ "epoch": 0.7583333333333333,
676
+ "grad_norm": 0.06817548300510701,
677
+ "learning_rate": 2.7400800262192788e-05,
678
+ "loss": 2.3449,
679
+ "step": 91
680
+ },
681
+ {
682
+ "epoch": 0.7666666666666667,
683
+ "grad_norm": 0.07336990573663302,
684
+ "learning_rate": 2.7361728390032657e-05,
685
+ "loss": 2.3448,
686
+ "step": 92
687
+ },
688
+ {
689
+ "epoch": 0.775,
690
+ "grad_norm": 0.07822885886131264,
691
+ "learning_rate": 2.732200302950111e-05,
692
+ "loss": 2.3217,
693
+ "step": 93
694
+ },
695
+ {
696
+ "epoch": 0.7833333333333333,
697
+ "grad_norm": 0.07296512071361201,
698
+ "learning_rate": 2.728162616050959e-05,
699
+ "loss": 2.3329,
700
+ "step": 94
701
+ },
702
+ {
703
+ "epoch": 0.7916666666666666,
704
+ "grad_norm": 0.07367928865175823,
705
+ "learning_rate": 2.724059979544072e-05,
706
+ "loss": 2.3208,
707
+ "step": 95
708
+ },
709
+ {
710
+ "epoch": 0.8,
711
+ "grad_norm": 0.07504139519989858,
712
+ "learning_rate": 2.719892597904801e-05,
713
+ "loss": 2.3483,
714
+ "step": 96
715
+ },
716
+ {
717
+ "epoch": 0.8083333333333333,
718
+ "grad_norm": 0.06790757702451031,
719
+ "learning_rate": 2.7156606788353906e-05,
720
+ "loss": 2.4128,
721
+ "step": 97
722
+ },
723
+ {
724
+ "epoch": 0.8166666666666667,
725
+ "grad_norm": 0.07011160737870108,
726
+ "learning_rate": 2.7113644332546336e-05,
727
+ "loss": 2.3832,
728
+ "step": 98
729
+ },
730
+ {
731
+ "epoch": 0.825,
732
+ "grad_norm": 0.08077329808935288,
733
+ "learning_rate": 2.707004075287352e-05,
734
+ "loss": 2.3308,
735
+ "step": 99
736
+ },
737
+ {
738
+ "epoch": 0.8333333333333334,
739
+ "grad_norm": 0.0719496280235162,
740
+ "learning_rate": 2.7025798222537306e-05,
741
+ "loss": 2.3254,
742
+ "step": 100
743
+ },
744
+ {
745
+ "epoch": 0.8416666666666667,
746
+ "grad_norm": 0.07275409855582728,
747
+ "learning_rate": 2.698091894658483e-05,
748
+ "loss": 2.3967,
749
+ "step": 101
750
+ },
751
+ {
752
+ "epoch": 0.85,
753
+ "grad_norm": 0.07201531734077336,
754
+ "learning_rate": 2.693540516179861e-05,
755
+ "loss": 2.3346,
756
+ "step": 102
757
+ },
758
+ {
759
+ "epoch": 0.8583333333333333,
760
+ "grad_norm": 0.0765467775604243,
761
+ "learning_rate": 2.6889259136585094e-05,
762
+ "loss": 2.3336,
763
+ "step": 103
764
+ },
765
+ {
766
+ "epoch": 0.8666666666666667,
767
+ "grad_norm": 0.077223728318478,
768
+ "learning_rate": 2.6842483170861568e-05,
769
+ "loss": 2.3313,
770
+ "step": 104
771
+ },
772
+ {
773
+ "epoch": 0.875,
774
+ "grad_norm": 0.07639332869289207,
775
+ "learning_rate": 2.6795079595941553e-05,
776
+ "loss": 2.4008,
777
+ "step": 105
778
+ },
779
+ {
780
+ "epoch": 0.8833333333333333,
781
+ "grad_norm": 0.07440505813328589,
782
+ "learning_rate": 2.6747050774418605e-05,
783
+ "loss": 2.3425,
784
+ "step": 106
785
+ },
786
+ {
787
+ "epoch": 0.8916666666666667,
788
+ "grad_norm": 0.06937810484842656,
789
+ "learning_rate": 2.6698399100048556e-05,
790
+ "loss": 2.3349,
791
+ "step": 107
792
+ },
793
+ {
794
+ "epoch": 0.9,
795
+ "grad_norm": 0.07336400555418392,
796
+ "learning_rate": 2.6649126997630225e-05,
797
+ "loss": 2.3792,
798
+ "step": 108
799
+ },
800
+ {
801
+ "epoch": 0.9083333333333333,
802
+ "grad_norm": 0.07442564570941794,
803
+ "learning_rate": 2.6599236922884547e-05,
804
+ "loss": 2.3683,
805
+ "step": 109
806
+ },
807
+ {
808
+ "epoch": 0.9166666666666666,
809
+ "grad_norm": 0.07470689463768693,
810
+ "learning_rate": 2.65487313623322e-05,
811
+ "loss": 2.3036,
812
+ "step": 110
813
+ },
814
+ {
815
+ "epoch": 0.925,
816
+ "grad_norm": 0.07096997017300663,
817
+ "learning_rate": 2.649761283316966e-05,
818
+ "loss": 2.3682,
819
+ "step": 111
820
+ },
821
+ {
822
+ "epoch": 0.9333333333333333,
823
+ "grad_norm": 0.07511821034386772,
824
+ "learning_rate": 2.6445883883143744e-05,
825
+ "loss": 2.3346,
826
+ "step": 112
827
+ },
828
+ {
829
+ "epoch": 0.9416666666666667,
830
+ "grad_norm": 0.07057540374817312,
831
+ "learning_rate": 2.639354709042466e-05,
832
+ "loss": 2.3502,
833
+ "step": 113
834
+ },
835
+ {
836
+ "epoch": 0.95,
837
+ "grad_norm": 0.07300364605060353,
838
+ "learning_rate": 2.6340605063477456e-05,
839
+ "loss": 2.3711,
840
+ "step": 114
841
+ },
842
+ {
843
+ "epoch": 0.9583333333333334,
844
+ "grad_norm": 0.06925480258849577,
845
+ "learning_rate": 2.628706044093207e-05,
846
+ "loss": 2.3816,
847
+ "step": 115
848
+ },
849
+ {
850
+ "epoch": 0.9666666666666667,
851
+ "grad_norm": 0.0705107307569524,
852
+ "learning_rate": 2.623291589145179e-05,
853
+ "loss": 2.2958,
854
+ "step": 116
855
+ },
856
+ {
857
+ "epoch": 0.975,
858
+ "grad_norm": 0.07331112076487026,
859
+ "learning_rate": 2.6178174113600252e-05,
860
+ "loss": 2.3279,
861
+ "step": 117
862
+ },
863
+ {
864
+ "epoch": 0.9833333333333333,
865
+ "grad_norm": 0.06780655482074792,
866
+ "learning_rate": 2.612283783570695e-05,
867
+ "loss": 2.4117,
868
+ "step": 118
869
+ },
870
+ {
871
+ "epoch": 0.9916666666666667,
872
+ "grad_norm": 0.07485055181125701,
873
+ "learning_rate": 2.606690981573125e-05,
874
+ "loss": 2.303,
875
+ "step": 119
876
+ },
877
+ {
878
+ "epoch": 1.0,
879
+ "grad_norm": 0.07276467760742707,
880
+ "learning_rate": 2.6010392841124932e-05,
881
+ "loss": 2.3608,
882
+ "step": 120
883
+ },
884
+ {
885
+ "epoch": 1.0,
886
+ "eval_loss": 2.4049572944641113,
887
+ "eval_runtime": 82.3343,
888
+ "eval_samples_per_second": 4.98,
889
+ "eval_steps_per_second": 0.316,
890
+ "step": 120
891
+ },
892
+ {
893
+ "epoch": 1.0083333333333333,
894
+ "grad_norm": 0.07548790321925977,
895
+ "learning_rate": 2.5953289728693274e-05,
896
+ "loss": 2.3185,
897
+ "step": 121
898
+ },
899
+ {
900
+ "epoch": 1.0166666666666666,
901
+ "grad_norm": 0.0730570698984131,
902
+ "learning_rate": 2.5895603324454647e-05,
903
+ "loss": 2.2877,
904
+ "step": 122
905
+ },
906
+ {
907
+ "epoch": 1.025,
908
+ "grad_norm": 0.07345139782586493,
909
+ "learning_rate": 2.5837336503498694e-05,
910
+ "loss": 2.2836,
911
+ "step": 123
912
+ },
913
+ {
914
+ "epoch": 1.0333333333333334,
915
+ "grad_norm": 0.07299378924326991,
916
+ "learning_rate": 2.5778492169843003e-05,
917
+ "loss": 2.3436,
918
+ "step": 124
919
+ },
920
+ {
921
+ "epoch": 1.0416666666666667,
922
+ "grad_norm": 0.07154250149880004,
923
+ "learning_rate": 2.5719073256288394e-05,
924
+ "loss": 2.3822,
925
+ "step": 125
926
+ },
927
+ {
928
+ "epoch": 1.05,
929
+ "grad_norm": 0.0720748804004234,
930
+ "learning_rate": 2.565908272427274e-05,
931
+ "loss": 2.2708,
932
+ "step": 126
933
+ },
934
+ {
935
+ "epoch": 1.0583333333333333,
936
+ "grad_norm": 0.07269892036621302,
937
+ "learning_rate": 2.5598523563723373e-05,
938
+ "loss": 2.3377,
939
+ "step": 127
940
+ },
941
+ {
942
+ "epoch": 1.0666666666666667,
943
+ "grad_norm": 0.0756770863265576,
944
+ "learning_rate": 2.5537398792908062e-05,
945
+ "loss": 2.352,
946
+ "step": 128
947
+ },
948
+ {
949
+ "epoch": 1.075,
950
+ "grad_norm": 0.07397323539112335,
951
+ "learning_rate": 2.547571145828459e-05,
952
+ "loss": 2.3643,
953
+ "step": 129
954
+ },
955
+ {
956
+ "epoch": 1.0833333333333333,
957
+ "grad_norm": 0.07438211371538549,
958
+ "learning_rate": 2.54134646343489e-05,
959
+ "loss": 2.3387,
960
+ "step": 130
961
+ },
962
+ {
963
+ "epoch": 1.0916666666666666,
964
+ "grad_norm": 0.07094248712059498,
965
+ "learning_rate": 2.5350661423481885e-05,
966
+ "loss": 2.3221,
967
+ "step": 131
968
+ },
969
+ {
970
+ "epoch": 1.1,
971
+ "grad_norm": 0.0771622686218861,
972
+ "learning_rate": 2.5287304955794754e-05,
973
+ "loss": 2.3183,
974
+ "step": 132
975
+ },
976
+ {
977
+ "epoch": 1.1083333333333334,
978
+ "grad_norm": 0.07495056480159959,
979
+ "learning_rate": 2.5223398388973028e-05,
980
+ "loss": 2.3697,
981
+ "step": 133
982
+ },
983
+ {
984
+ "epoch": 1.1166666666666667,
985
+ "grad_norm": 0.07629199954207538,
986
+ "learning_rate": 2.515894490811916e-05,
987
+ "loss": 2.3529,
988
+ "step": 134
989
+ },
990
+ {
991
+ "epoch": 1.125,
992
+ "grad_norm": 0.0762534542729489,
993
+ "learning_rate": 2.5093947725593792e-05,
994
+ "loss": 2.3208,
995
+ "step": 135
996
+ },
997
+ {
998
+ "epoch": 1.1333333333333333,
999
+ "grad_norm": 0.07587427933984144,
1000
+ "learning_rate": 2.502841008085565e-05,
1001
+ "loss": 2.3448,
1002
+ "step": 136
1003
+ },
1004
+ {
1005
+ "epoch": 1.1416666666666666,
1006
+ "grad_norm": 0.07490456619530689,
1007
+ "learning_rate": 2.49623352403001e-05,
1008
+ "loss": 2.3435,
1009
+ "step": 137
1010
+ },
1011
+ {
1012
+ "epoch": 1.15,
1013
+ "grad_norm": 0.0744781797534131,
1014
+ "learning_rate": 2.4895726497096315e-05,
1015
+ "loss": 2.4,
1016
+ "step": 138
1017
+ },
1018
+ {
1019
+ "epoch": 1.1583333333333332,
1020
+ "grad_norm": 0.07464944817741491,
1021
+ "learning_rate": 2.482858717102319e-05,
1022
+ "loss": 2.318,
1023
+ "step": 139
1024
+ },
1025
+ {
1026
+ "epoch": 1.1666666666666667,
1027
+ "grad_norm": 0.07309033869975678,
1028
+ "learning_rate": 2.4760920608303867e-05,
1029
+ "loss": 2.2891,
1030
+ "step": 140
1031
+ },
1032
+ {
1033
+ "epoch": 1.175,
1034
+ "grad_norm": 0.07284517336177344,
1035
+ "learning_rate": 2.469273018143894e-05,
1036
+ "loss": 2.3051,
1037
+ "step": 141
1038
+ },
1039
+ {
1040
+ "epoch": 1.1833333333333333,
1041
+ "grad_norm": 0.07652064520411771,
1042
+ "learning_rate": 2.462401928903839e-05,
1043
+ "loss": 2.3555,
1044
+ "step": 142
1045
+ },
1046
+ {
1047
+ "epoch": 1.1916666666666667,
1048
+ "grad_norm": 0.07701974074136966,
1049
+ "learning_rate": 2.45547913556522e-05,
1050
+ "loss": 2.3015,
1051
+ "step": 143
1052
+ },
1053
+ {
1054
+ "epoch": 1.2,
1055
+ "grad_norm": 0.08108352272511765,
1056
+ "learning_rate": 2.448504983159966e-05,
1057
+ "loss": 2.3221,
1058
+ "step": 144
1059
+ },
1060
+ {
1061
+ "epoch": 1.2083333333333333,
1062
+ "grad_norm": 0.07752288456105606,
1063
+ "learning_rate": 2.441479819279742e-05,
1064
+ "loss": 2.3684,
1065
+ "step": 145
1066
+ },
1067
+ {
1068
+ "epoch": 1.2166666666666668,
1069
+ "grad_norm": 0.07881711814524053,
1070
+ "learning_rate": 2.4344039940586235e-05,
1071
+ "loss": 2.3011,
1072
+ "step": 146
1073
+ },
1074
+ {
1075
+ "epoch": 1.225,
1076
+ "grad_norm": 0.07757542042787384,
1077
+ "learning_rate": 2.4272778601556472e-05,
1078
+ "loss": 2.3509,
1079
+ "step": 147
1080
+ },
1081
+ {
1082
+ "epoch": 1.2333333333333334,
1083
+ "grad_norm": 0.07228965364348439,
1084
+ "learning_rate": 2.4201017727372336e-05,
1085
+ "loss": 2.3801,
1086
+ "step": 148
1087
+ },
1088
+ {
1089
+ "epoch": 1.2416666666666667,
1090
+ "grad_norm": 0.07389812003829682,
1091
+ "learning_rate": 2.4128760894594853e-05,
1092
+ "loss": 2.3359,
1093
+ "step": 149
1094
+ },
1095
+ {
1096
+ "epoch": 1.25,
1097
+ "grad_norm": 0.08146218033856112,
1098
+ "learning_rate": 2.4056011704503633e-05,
1099
+ "loss": 2.3096,
1100
+ "step": 150
1101
+ },
1102
+ {
1103
+ "epoch": 1.25,
1104
+ "eval_loss": 2.400259494781494,
1105
+ "eval_runtime": 81.604,
1106
+ "eval_samples_per_second": 5.024,
1107
+ "eval_steps_per_second": 0.319,
1108
+ "step": 150
1109
+ },
1110
+ {
1111
+ "epoch": 1.2583333333333333,
1112
+ "grad_norm": 0.07407260421175128,
1113
+ "learning_rate": 2.3982773782917347e-05,
1114
+ "loss": 2.3418,
1115
+ "step": 151
1116
+ },
1117
+ {
1118
+ "epoch": 1.2666666666666666,
1119
+ "grad_norm": 0.07827237096687646,
1120
+ "learning_rate": 2.390905078001306e-05,
1121
+ "loss": 2.2778,
1122
+ "step": 152
1123
+ },
1124
+ {
1125
+ "epoch": 1.275,
1126
+ "grad_norm": 0.07699758244967876,
1127
+ "learning_rate": 2.383484637014426e-05,
1128
+ "loss": 2.3245,
1129
+ "step": 153
1130
+ },
1131
+ {
1132
+ "epoch": 1.2833333333333332,
1133
+ "grad_norm": 0.07805943021524937,
1134
+ "learning_rate": 2.3760164251657773e-05,
1135
+ "loss": 2.3782,
1136
+ "step": 154
1137
+ },
1138
+ {
1139
+ "epoch": 1.2916666666666667,
1140
+ "grad_norm": 0.0741687347632035,
1141
+ "learning_rate": 2.368500814670941e-05,
1142
+ "loss": 2.3765,
1143
+ "step": 155
1144
+ },
1145
+ {
1146
+ "epoch": 1.3,
1147
+ "grad_norm": 0.07696079818166807,
1148
+ "learning_rate": 2.3609381801078448e-05,
1149
+ "loss": 2.3958,
1150
+ "step": 156
1151
+ },
1152
+ {
1153
+ "epoch": 1.3083333333333333,
1154
+ "grad_norm": 0.08864860865623735,
1155
+ "learning_rate": 2.3533288983980964e-05,
1156
+ "loss": 2.3482,
1157
+ "step": 157
1158
+ },
1159
+ {
1160
+ "epoch": 1.3166666666666667,
1161
+ "grad_norm": 0.07676755572584443,
1162
+ "learning_rate": 2.3456733487881978e-05,
1163
+ "loss": 2.3511,
1164
+ "step": 158
1165
+ },
1166
+ {
1167
+ "epoch": 1.325,
1168
+ "grad_norm": 0.07754541163995884,
1169
+ "learning_rate": 2.337971912830641e-05,
1170
+ "loss": 2.3754,
1171
+ "step": 159
1172
+ },
1173
+ {
1174
+ "epoch": 1.3333333333333333,
1175
+ "grad_norm": 0.08430746433268149,
1176
+ "learning_rate": 2.3302249743648926e-05,
1177
+ "loss": 2.4063,
1178
+ "step": 160
1179
+ },
1180
+ {
1181
+ "epoch": 1.3416666666666668,
1182
+ "grad_norm": 0.08113759941899056,
1183
+ "learning_rate": 2.322432919498265e-05,
1184
+ "loss": 2.3352,
1185
+ "step": 161
1186
+ },
1187
+ {
1188
+ "epoch": 1.35,
1189
+ "grad_norm": 0.08147516272984133,
1190
+ "learning_rate": 2.3145961365866708e-05,
1191
+ "loss": 2.3119,
1192
+ "step": 162
1193
+ },
1194
+ {
1195
+ "epoch": 1.3583333333333334,
1196
+ "grad_norm": 0.07749688842544009,
1197
+ "learning_rate": 2.3067150162152675e-05,
1198
+ "loss": 2.3547,
1199
+ "step": 163
1200
+ },
1201
+ {
1202
+ "epoch": 1.3666666666666667,
1203
+ "grad_norm": 0.08640326754187048,
1204
+ "learning_rate": 2.298789951178992e-05,
1205
+ "loss": 2.3389,
1206
+ "step": 164
1207
+ },
1208
+ {
1209
+ "epoch": 1.375,
1210
+ "grad_norm": 0.0795137333109577,
1211
+ "learning_rate": 2.2908213364629812e-05,
1212
+ "loss": 2.3778,
1213
+ "step": 165
1214
+ },
1215
+ {
1216
+ "epoch": 1.3833333333333333,
1217
+ "grad_norm": 0.07739334763959965,
1218
+ "learning_rate": 2.2828095692228886e-05,
1219
+ "loss": 2.3658,
1220
+ "step": 166
1221
+ },
1222
+ {
1223
+ "epoch": 1.3916666666666666,
1224
+ "grad_norm": 0.07783031237693959,
1225
+ "learning_rate": 2.2747550487650887e-05,
1226
+ "loss": 2.3575,
1227
+ "step": 167
1228
+ },
1229
+ {
1230
+ "epoch": 1.4,
1231
+ "grad_norm": 0.07682655233706284,
1232
+ "learning_rate": 2.2666581765267758e-05,
1233
+ "loss": 2.2825,
1234
+ "step": 168
1235
+ },
1236
+ {
1237
+ "epoch": 1.4083333333333332,
1238
+ "grad_norm": 0.08359081032268273,
1239
+ "learning_rate": 2.2585193560559563e-05,
1240
+ "loss": 2.261,
1241
+ "step": 169
1242
+ },
1243
+ {
1244
+ "epoch": 1.4166666666666667,
1245
+ "grad_norm": 0.0826940676306091,
1246
+ "learning_rate": 2.250338992991335e-05,
1247
+ "loss": 2.3069,
1248
+ "step": 170
1249
+ },
1250
+ {
1251
+ "epoch": 1.425,
1252
+ "grad_norm": 0.08462619097403327,
1253
+ "learning_rate": 2.2421174950421017e-05,
1254
+ "loss": 2.2864,
1255
+ "step": 171
1256
+ },
1257
+ {
1258
+ "epoch": 1.4333333333333333,
1259
+ "grad_norm": 0.07990029642375193,
1260
+ "learning_rate": 2.233855271967606e-05,
1261
+ "loss": 2.3033,
1262
+ "step": 172
1263
+ },
1264
+ {
1265
+ "epoch": 1.4416666666666667,
1266
+ "grad_norm": 0.08051779058857793,
1267
+ "learning_rate": 2.2255527355569372e-05,
1268
+ "loss": 2.3166,
1269
+ "step": 173
1270
+ },
1271
+ {
1272
+ "epoch": 1.45,
1273
+ "grad_norm": 0.08604667339713809,
1274
+ "learning_rate": 2.217210299608402e-05,
1275
+ "loss": 2.387,
1276
+ "step": 174
1277
+ },
1278
+ {
1279
+ "epoch": 1.4583333333333333,
1280
+ "grad_norm": 0.07829742536277012,
1281
+ "learning_rate": 2.208828379908899e-05,
1282
+ "loss": 2.311,
1283
+ "step": 175
1284
+ },
1285
+ {
1286
+ "epoch": 1.4666666666666668,
1287
+ "grad_norm": 0.07850219342360719,
1288
+ "learning_rate": 2.200407394213196e-05,
1289
+ "loss": 2.3384,
1290
+ "step": 176
1291
+ },
1292
+ {
1293
+ "epoch": 1.475,
1294
+ "grad_norm": 0.08531707041033702,
1295
+ "learning_rate": 2.19194776222311e-05,
1296
+ "loss": 2.3107,
1297
+ "step": 177
1298
+ },
1299
+ {
1300
+ "epoch": 1.4833333333333334,
1301
+ "grad_norm": 0.07652853009760147,
1302
+ "learning_rate": 2.183449905566589e-05,
1303
+ "loss": 2.3494,
1304
+ "step": 178
1305
+ },
1306
+ {
1307
+ "epoch": 1.4916666666666667,
1308
+ "grad_norm": 0.0797336095546633,
1309
+ "learning_rate": 2.1749142477766972e-05,
1310
+ "loss": 2.3291,
1311
+ "step": 179
1312
+ },
1313
+ {
1314
+ "epoch": 1.5,
1315
+ "grad_norm": 0.08700079540422817,
1316
+ "learning_rate": 2.166341214270507e-05,
1317
+ "loss": 2.3132,
1318
+ "step": 180
1319
+ },
1320
+ {
1321
+ "epoch": 1.5,
1322
+ "eval_loss": 2.3966128826141357,
1323
+ "eval_runtime": 83.184,
1324
+ "eval_samples_per_second": 4.929,
1325
+ "eval_steps_per_second": 0.313,
1326
+ "step": 180
1327
+ },
1328
+ {
1329
+ "epoch": 1.5083333333333333,
1330
+ "grad_norm": 0.07925581040107615,
1331
+ "learning_rate": 2.157731232327897e-05,
1332
+ "loss": 2.3578,
1333
+ "step": 181
1334
+ },
1335
+ {
1336
+ "epoch": 1.5166666666666666,
1337
+ "grad_norm": 0.07873086864048841,
1338
+ "learning_rate": 2.1490847310702544e-05,
1339
+ "loss": 2.3229,
1340
+ "step": 182
1341
+ },
1342
+ {
1343
+ "epoch": 1.525,
1344
+ "grad_norm": 0.07775316849537767,
1345
+ "learning_rate": 2.1404021414390874e-05,
1346
+ "loss": 2.3756,
1347
+ "step": 183
1348
+ },
1349
+ {
1350
+ "epoch": 1.5333333333333332,
1351
+ "grad_norm": 0.07949428482523528,
1352
+ "learning_rate": 2.1316838961745518e-05,
1353
+ "loss": 2.3535,
1354
+ "step": 184
1355
+ },
1356
+ {
1357
+ "epoch": 1.5416666666666665,
1358
+ "grad_norm": 0.08423278187074197,
1359
+ "learning_rate": 2.1229304297938755e-05,
1360
+ "loss": 2.3517,
1361
+ "step": 185
1362
+ },
1363
+ {
1364
+ "epoch": 1.55,
1365
+ "grad_norm": 0.07930583119038707,
1366
+ "learning_rate": 2.1141421785697097e-05,
1367
+ "loss": 2.3929,
1368
+ "step": 186
1369
+ },
1370
+ {
1371
+ "epoch": 1.5583333333333333,
1372
+ "grad_norm": 0.07736840323261199,
1373
+ "learning_rate": 2.1053195805083803e-05,
1374
+ "loss": 2.3194,
1375
+ "step": 187
1376
+ },
1377
+ {
1378
+ "epoch": 1.5666666666666667,
1379
+ "grad_norm": 0.08306421066524537,
1380
+ "learning_rate": 2.0964630753280584e-05,
1381
+ "loss": 2.3131,
1382
+ "step": 188
1383
+ },
1384
+ {
1385
+ "epoch": 1.575,
1386
+ "grad_norm": 0.0805185815818936,
1387
+ "learning_rate": 2.0875731044368472e-05,
1388
+ "loss": 2.3238,
1389
+ "step": 189
1390
+ },
1391
+ {
1392
+ "epoch": 1.5833333333333335,
1393
+ "grad_norm": 0.07729948838070921,
1394
+ "learning_rate": 2.078650110910779e-05,
1395
+ "loss": 2.3279,
1396
+ "step": 190
1397
+ },
1398
+ {
1399
+ "epoch": 1.5916666666666668,
1400
+ "grad_norm": 0.08053951644296133,
1401
+ "learning_rate": 2.0696945394717355e-05,
1402
+ "loss": 2.3343,
1403
+ "step": 191
1404
+ },
1405
+ {
1406
+ "epoch": 1.6,
1407
+ "grad_norm": 0.08184664333069269,
1408
+ "learning_rate": 2.0607068364652783e-05,
1409
+ "loss": 2.3441,
1410
+ "step": 192
1411
+ },
1412
+ {
1413
+ "epoch": 1.6083333333333334,
1414
+ "grad_norm": 0.07894699650259683,
1415
+ "learning_rate": 2.051687449838409e-05,
1416
+ "loss": 2.3384,
1417
+ "step": 193
1418
+ },
1419
+ {
1420
+ "epoch": 1.6166666666666667,
1421
+ "grad_norm": 0.08288692832517489,
1422
+ "learning_rate": 2.042636829117239e-05,
1423
+ "loss": 2.3219,
1424
+ "step": 194
1425
+ },
1426
+ {
1427
+ "epoch": 1.625,
1428
+ "grad_norm": 0.09061769591669266,
1429
+ "learning_rate": 2.033555425384586e-05,
1430
+ "loss": 2.3168,
1431
+ "step": 195
1432
+ },
1433
+ {
1434
+ "epoch": 1.6333333333333333,
1435
+ "grad_norm": 0.07607427061534017,
1436
+ "learning_rate": 2.0244436912574938e-05,
1437
+ "loss": 2.3592,
1438
+ "step": 196
1439
+ },
1440
+ {
1441
+ "epoch": 1.6416666666666666,
1442
+ "grad_norm": 0.08827457673533141,
1443
+ "learning_rate": 2.0153020808646715e-05,
1444
+ "loss": 2.3177,
1445
+ "step": 197
1446
+ },
1447
+ {
1448
+ "epoch": 1.65,
1449
+ "grad_norm": 0.0757688204165182,
1450
+ "learning_rate": 2.0061310498238618e-05,
1451
+ "loss": 2.2366,
1452
+ "step": 198
1453
+ },
1454
+ {
1455
+ "epoch": 1.6583333333333332,
1456
+ "grad_norm": 0.07815852114026649,
1457
+ "learning_rate": 1.996931055219132e-05,
1458
+ "loss": 2.3161,
1459
+ "step": 199
1460
+ },
1461
+ {
1462
+ "epoch": 1.6666666666666665,
1463
+ "grad_norm": 0.08058901889279678,
1464
+ "learning_rate": 1.9877025555780927e-05,
1465
+ "loss": 2.3749,
1466
+ "step": 200
1467
+ },
1468
+ {
1469
+ "epoch": 1.675,
1470
+ "grad_norm": 0.07708027281441528,
1471
+ "learning_rate": 1.978446010849045e-05,
1472
+ "loss": 2.2854,
1473
+ "step": 201
1474
+ },
1475
+ {
1476
+ "epoch": 1.6833333333333333,
1477
+ "grad_norm": 0.08312283019758401,
1478
+ "learning_rate": 1.969161882378058e-05,
1479
+ "loss": 2.3524,
1480
+ "step": 202
1481
+ },
1482
+ {
1483
+ "epoch": 1.6916666666666667,
1484
+ "grad_norm": 0.07784046601849169,
1485
+ "learning_rate": 1.9598506328859717e-05,
1486
+ "loss": 2.3418,
1487
+ "step": 203
1488
+ },
1489
+ {
1490
+ "epoch": 1.7,
1491
+ "grad_norm": 0.07906237498578873,
1492
+ "learning_rate": 1.95051272644534e-05,
1493
+ "loss": 2.3514,
1494
+ "step": 204
1495
+ },
1496
+ {
1497
+ "epoch": 1.7083333333333335,
1498
+ "grad_norm": 0.08323464269988524,
1499
+ "learning_rate": 1.9411486284572977e-05,
1500
+ "loss": 2.3133,
1501
+ "step": 205
1502
+ },
1503
+ {
1504
+ "epoch": 1.7166666666666668,
1505
+ "grad_norm": 0.08153670371604982,
1506
+ "learning_rate": 1.931758805628366e-05,
1507
+ "loss": 2.3388,
1508
+ "step": 206
1509
+ },
1510
+ {
1511
+ "epoch": 1.725,
1512
+ "grad_norm": 0.08152589045596419,
1513
+ "learning_rate": 1.9223437259471912e-05,
1514
+ "loss": 2.3309,
1515
+ "step": 207
1516
+ },
1517
+ {
1518
+ "epoch": 1.7333333333333334,
1519
+ "grad_norm": 0.08382345786042532,
1520
+ "learning_rate": 1.9129038586612224e-05,
1521
+ "loss": 2.3282,
1522
+ "step": 208
1523
+ },
1524
+ {
1525
+ "epoch": 1.7416666666666667,
1526
+ "grad_norm": 0.0835609429134592,
1527
+ "learning_rate": 1.903439674253321e-05,
1528
+ "loss": 2.3567,
1529
+ "step": 209
1530
+ },
1531
+ {
1532
+ "epoch": 1.75,
1533
+ "grad_norm": 0.08252984125014622,
1534
+ "learning_rate": 1.8939516444183143e-05,
1535
+ "loss": 2.3352,
1536
+ "step": 210
1537
+ },
1538
+ {
1539
+ "epoch": 1.75,
1540
+ "eval_loss": 2.3933684825897217,
1541
+ "eval_runtime": 83.3063,
1542
+ "eval_samples_per_second": 4.922,
1543
+ "eval_steps_per_second": 0.312,
1544
+ "step": 210
1545
+ },
1546
+ {
1547
+ "epoch": 1.7583333333333333,
1548
+ "grad_norm": 0.0815481053340795,
1549
+ "learning_rate": 1.884440242039485e-05,
1550
+ "loss": 2.3262,
1551
+ "step": 211
1552
+ },
1553
+ {
1554
+ "epoch": 1.7666666666666666,
1555
+ "grad_norm": 0.08258761118218041,
1556
+ "learning_rate": 1.8749059411650034e-05,
1557
+ "loss": 2.3396,
1558
+ "step": 212
1559
+ },
1560
+ {
1561
+ "epoch": 1.775,
1562
+ "grad_norm": 0.0884999967331726,
1563
+ "learning_rate": 1.8653492169843003e-05,
1564
+ "loss": 2.3176,
1565
+ "step": 213
1566
+ },
1567
+ {
1568
+ "epoch": 1.7833333333333332,
1569
+ "grad_norm": 0.0824785010834098,
1570
+ "learning_rate": 1.8557705458043838e-05,
1571
+ "loss": 2.3272,
1572
+ "step": 214
1573
+ },
1574
+ {
1575
+ "epoch": 1.7916666666666665,
1576
+ "grad_norm": 0.08727167025374602,
1577
+ "learning_rate": 1.8461704050261e-05,
1578
+ "loss": 2.2298,
1579
+ "step": 215
1580
+ },
1581
+ {
1582
+ "epoch": 1.8,
1583
+ "grad_norm": 0.0768016904891171,
1584
+ "learning_rate": 1.8365492731203398e-05,
1585
+ "loss": 2.3554,
1586
+ "step": 216
1587
+ },
1588
+ {
1589
+ "epoch": 1.8083333333333333,
1590
+ "grad_norm": 0.07709533586121158,
1591
+ "learning_rate": 1.8269076296041917e-05,
1592
+ "loss": 2.3702,
1593
+ "step": 217
1594
+ },
1595
+ {
1596
+ "epoch": 1.8166666666666667,
1597
+ "grad_norm": 0.0806446736093232,
1598
+ "learning_rate": 1.8172459550170424e-05,
1599
+ "loss": 2.3585,
1600
+ "step": 218
1601
+ },
1602
+ {
1603
+ "epoch": 1.825,
1604
+ "grad_norm": 0.07523532523458193,
1605
+ "learning_rate": 1.8075647308966268e-05,
1606
+ "loss": 2.3609,
1607
+ "step": 219
1608
+ },
1609
+ {
1610
+ "epoch": 1.8333333333333335,
1611
+ "grad_norm": 0.07497201271988578,
1612
+ "learning_rate": 1.797864439755028e-05,
1613
+ "loss": 2.3755,
1614
+ "step": 220
1615
+ },
1616
+ {
1617
+ "epoch": 1.8416666666666668,
1618
+ "grad_norm": 0.08249074177996166,
1619
+ "learning_rate": 1.7881455650546303e-05,
1620
+ "loss": 2.372,
1621
+ "step": 221
1622
+ },
1623
+ {
1624
+ "epoch": 1.85,
1625
+ "grad_norm": 0.0780160636961897,
1626
+ "learning_rate": 1.7784085911840214e-05,
1627
+ "loss": 2.3823,
1628
+ "step": 222
1629
+ },
1630
+ {
1631
+ "epoch": 1.8583333333333334,
1632
+ "grad_norm": 0.08148680526536918,
1633
+ "learning_rate": 1.7686540034338513e-05,
1634
+ "loss": 2.3314,
1635
+ "step": 223
1636
+ },
1637
+ {
1638
+ "epoch": 1.8666666666666667,
1639
+ "grad_norm": 0.0795864595636552,
1640
+ "learning_rate": 1.758882287972646e-05,
1641
+ "loss": 2.2853,
1642
+ "step": 224
1643
+ },
1644
+ {
1645
+ "epoch": 1.875,
1646
+ "grad_norm": 0.08198344669246531,
1647
+ "learning_rate": 1.749093931822577e-05,
1648
+ "loss": 2.3605,
1649
+ "step": 225
1650
+ },
1651
+ {
1652
+ "epoch": 1.8833333333333333,
1653
+ "grad_norm": 0.08138145213474299,
1654
+ "learning_rate": 1.739289422835185e-05,
1655
+ "loss": 2.2721,
1656
+ "step": 226
1657
+ },
1658
+ {
1659
+ "epoch": 1.8916666666666666,
1660
+ "grad_norm": 0.08306015511124677,
1661
+ "learning_rate": 1.7294692496670715e-05,
1662
+ "loss": 2.2889,
1663
+ "step": 227
1664
+ },
1665
+ {
1666
+ "epoch": 1.9,
1667
+ "grad_norm": 0.07478727556401082,
1668
+ "learning_rate": 1.7196339017555378e-05,
1669
+ "loss": 2.3416,
1670
+ "step": 228
1671
+ },
1672
+ {
1673
+ "epoch": 1.9083333333333332,
1674
+ "grad_norm": 0.08858459574829487,
1675
+ "learning_rate": 1.709783869294196e-05,
1676
+ "loss": 2.3081,
1677
+ "step": 229
1678
+ },
1679
+ {
1680
+ "epoch": 1.9166666666666665,
1681
+ "grad_norm": 0.08175368181940743,
1682
+ "learning_rate": 1.699919643208533e-05,
1683
+ "loss": 2.3304,
1684
+ "step": 230
1685
+ },
1686
+ {
1687
+ "epoch": 1.925,
1688
+ "grad_norm": 0.07630479738636474,
1689
+ "learning_rate": 1.6900417151314503e-05,
1690
+ "loss": 2.3454,
1691
+ "step": 231
1692
+ },
1693
+ {
1694
+ "epoch": 1.9333333333333333,
1695
+ "grad_norm": 0.07687273996639293,
1696
+ "learning_rate": 1.6801505773787527e-05,
1697
+ "loss": 2.3901,
1698
+ "step": 232
1699
+ },
1700
+ {
1701
+ "epoch": 1.9416666666666667,
1702
+ "grad_norm": 0.08600269874202937,
1703
+ "learning_rate": 1.670246722924616e-05,
1704
+ "loss": 2.3081,
1705
+ "step": 233
1706
+ },
1707
+ {
1708
+ "epoch": 1.95,
1709
+ "grad_norm": 0.07737694968965858,
1710
+ "learning_rate": 1.660330645377018e-05,
1711
+ "loss": 2.3643,
1712
+ "step": 234
1713
+ },
1714
+ {
1715
+ "epoch": 1.9583333333333335,
1716
+ "grad_norm": 0.08165758061569027,
1717
+ "learning_rate": 1.6504028389531333e-05,
1718
+ "loss": 2.355,
1719
+ "step": 235
1720
+ },
1721
+ {
1722
+ "epoch": 1.9666666666666668,
1723
+ "grad_norm": 0.08264378429137093,
1724
+ "learning_rate": 1.640463798454704e-05,
1725
+ "loss": 2.3219,
1726
+ "step": 236
1727
+ },
1728
+ {
1729
+ "epoch": 1.975,
1730
+ "grad_norm": 0.0858368818345628,
1731
+ "learning_rate": 1.6305140192433787e-05,
1732
+ "loss": 2.3329,
1733
+ "step": 237
1734
+ },
1735
+ {
1736
+ "epoch": 1.9833333333333334,
1737
+ "grad_norm": 0.07616999163161729,
1738
+ "learning_rate": 1.620553997216023e-05,
1739
+ "loss": 2.3523,
1740
+ "step": 238
1741
+ },
1742
+ {
1743
+ "epoch": 1.9916666666666667,
1744
+ "grad_norm": 0.08241527325980988,
1745
+ "learning_rate": 1.6105842287800046e-05,
1746
+ "loss": 2.2982,
1747
+ "step": 239
1748
+ },
1749
+ {
1750
+ "epoch": 2.0,
1751
+ "grad_norm": 0.08007891750583127,
1752
+ "learning_rate": 1.600605210828451e-05,
1753
+ "loss": 2.2785,
1754
+ "step": 240
1755
+ },
1756
+ {
1757
+ "epoch": 2.0,
1758
+ "eval_loss": 2.3910558223724365,
1759
+ "eval_runtime": 83.4904,
1760
+ "eval_samples_per_second": 4.911,
1761
+ "eval_steps_per_second": 0.311,
1762
+ "step": 240
1763
+ },
1764
+ {
1765
+ "epoch": 2.0083333333333333,
1766
+ "grad_norm": 0.08108687194604622,
1767
+ "learning_rate": 1.5906174407154883e-05,
1768
+ "loss": 2.3367,
1769
+ "step": 241
1770
+ },
1771
+ {
1772
+ "epoch": 2.0166666666666666,
1773
+ "grad_norm": 0.0806511417182259,
1774
+ "learning_rate": 1.5806214162314463e-05,
1775
+ "loss": 2.3011,
1776
+ "step": 242
1777
+ },
1778
+ {
1779
+ "epoch": 2.025,
1780
+ "grad_norm": 0.08264392219751603,
1781
+ "learning_rate": 1.5706176355780556e-05,
1782
+ "loss": 2.3036,
1783
+ "step": 243
1784
+ },
1785
+ {
1786
+ "epoch": 2.033333333333333,
1787
+ "grad_norm": 0.07958409681135217,
1788
+ "learning_rate": 1.5606065973436132e-05,
1789
+ "loss": 2.3056,
1790
+ "step": 244
1791
+ },
1792
+ {
1793
+ "epoch": 2.0416666666666665,
1794
+ "grad_norm": 0.07856642651007223,
1795
+ "learning_rate": 1.550588800478133e-05,
1796
+ "loss": 2.3692,
1797
+ "step": 245
1798
+ },
1799
+ {
1800
+ "epoch": 2.05,
1801
+ "grad_norm": 0.08350216798892127,
1802
+ "learning_rate": 1.5405647442684794e-05,
1803
+ "loss": 2.2697,
1804
+ "step": 246
1805
+ },
1806
+ {
1807
+ "epoch": 2.058333333333333,
1808
+ "grad_norm": 0.08390645284684875,
1809
+ "learning_rate": 1.530534928313484e-05,
1810
+ "loss": 2.2425,
1811
+ "step": 247
1812
+ },
1813
+ {
1814
+ "epoch": 2.066666666666667,
1815
+ "grad_norm": 0.07883358190907572,
1816
+ "learning_rate": 1.5204998524990423e-05,
1817
+ "loss": 2.3281,
1818
+ "step": 248
1819
+ },
1820
+ {
1821
+ "epoch": 2.075,
1822
+ "grad_norm": 0.07994560560782488,
1823
+ "learning_rate": 1.5104600169732015e-05,
1824
+ "loss": 2.3285,
1825
+ "step": 249
1826
+ },
1827
+ {
1828
+ "epoch": 2.0833333333333335,
1829
+ "grad_norm": 0.08345016891314849,
1830
+ "learning_rate": 1.5004159221212325e-05,
1831
+ "loss": 2.3252,
1832
+ "step": 250
1833
+ },
1834
+ {
1835
+ "epoch": 2.091666666666667,
1836
+ "grad_norm": 0.0767244585605165,
1837
+ "learning_rate": 1.490368068540692e-05,
1838
+ "loss": 2.3176,
1839
+ "step": 251
1840
+ },
1841
+ {
1842
+ "epoch": 2.1,
1843
+ "grad_norm": 0.07853322933102938,
1844
+ "learning_rate": 1.4803169570164703e-05,
1845
+ "loss": 2.286,
1846
+ "step": 252
1847
+ },
1848
+ {
1849
+ "epoch": 2.1083333333333334,
1850
+ "grad_norm": 0.07885223855237164,
1851
+ "learning_rate": 1.4702630884958345e-05,
1852
+ "loss": 2.3293,
1853
+ "step": 253
1854
+ },
1855
+ {
1856
+ "epoch": 2.1166666666666667,
1857
+ "grad_norm": 0.07786083611140765,
1858
+ "learning_rate": 1.4602069640634605e-05,
1859
+ "loss": 2.3241,
1860
+ "step": 254
1861
+ },
1862
+ {
1863
+ "epoch": 2.125,
1864
+ "grad_norm": 0.07961379829842732,
1865
+ "learning_rate": 1.4501490849164585e-05,
1866
+ "loss": 2.3218,
1867
+ "step": 255
1868
+ },
1869
+ {
1870
+ "epoch": 2.1333333333333333,
1871
+ "grad_norm": 0.0812119479291348,
1872
+ "learning_rate": 1.4400899523393928e-05,
1873
+ "loss": 2.3101,
1874
+ "step": 256
1875
+ },
1876
+ {
1877
+ "epoch": 2.1416666666666666,
1878
+ "grad_norm": 0.07820228956836967,
1879
+ "learning_rate": 1.4300300676793e-05,
1880
+ "loss": 2.3105,
1881
+ "step": 257
1882
+ },
1883
+ {
1884
+ "epoch": 2.15,
1885
+ "grad_norm": 0.0787354321940814,
1886
+ "learning_rate": 1.4199699323207e-05,
1887
+ "loss": 2.2921,
1888
+ "step": 258
1889
+ },
1890
+ {
1891
+ "epoch": 2.158333333333333,
1892
+ "grad_norm": 0.0821168083039209,
1893
+ "learning_rate": 1.4099100476606071e-05,
1894
+ "loss": 2.3449,
1895
+ "step": 259
1896
+ },
1897
+ {
1898
+ "epoch": 2.1666666666666665,
1899
+ "grad_norm": 0.08227570212622978,
1900
+ "learning_rate": 1.3998509150835417e-05,
1901
+ "loss": 2.2804,
1902
+ "step": 260
1903
+ },
1904
+ {
1905
+ "epoch": 2.175,
1906
+ "grad_norm": 0.07956552166316343,
1907
+ "learning_rate": 1.3897930359365397e-05,
1908
+ "loss": 2.2798,
1909
+ "step": 261
1910
+ },
1911
+ {
1912
+ "epoch": 2.183333333333333,
1913
+ "grad_norm": 0.08355971196343313,
1914
+ "learning_rate": 1.3797369115041656e-05,
1915
+ "loss": 2.3121,
1916
+ "step": 262
1917
+ },
1918
+ {
1919
+ "epoch": 2.191666666666667,
1920
+ "grad_norm": 0.07664615523847712,
1921
+ "learning_rate": 1.3696830429835303e-05,
1922
+ "loss": 2.3511,
1923
+ "step": 263
1924
+ },
1925
+ {
1926
+ "epoch": 2.2,
1927
+ "grad_norm": 0.07875754809310784,
1928
+ "learning_rate": 1.3596319314593088e-05,
1929
+ "loss": 2.276,
1930
+ "step": 264
1931
+ },
1932
+ {
1933
+ "epoch": 2.2083333333333335,
1934
+ "grad_norm": 0.07805417721469433,
1935
+ "learning_rate": 1.3495840778787675e-05,
1936
+ "loss": 2.3156,
1937
+ "step": 265
1938
+ },
1939
+ {
1940
+ "epoch": 2.216666666666667,
1941
+ "grad_norm": 0.08500867883177173,
1942
+ "learning_rate": 1.339539983026799e-05,
1943
+ "loss": 2.3304,
1944
+ "step": 266
1945
+ },
1946
+ {
1947
+ "epoch": 2.225,
1948
+ "grad_norm": 0.08575986404103182,
1949
+ "learning_rate": 1.3295001475009578e-05,
1950
+ "loss": 2.3171,
1951
+ "step": 267
1952
+ },
1953
+ {
1954
+ "epoch": 2.2333333333333334,
1955
+ "grad_norm": 0.0796424885760881,
1956
+ "learning_rate": 1.3194650716865163e-05,
1957
+ "loss": 2.3488,
1958
+ "step": 268
1959
+ },
1960
+ {
1961
+ "epoch": 2.2416666666666667,
1962
+ "grad_norm": 0.07791982790558008,
1963
+ "learning_rate": 1.3094352557315207e-05,
1964
+ "loss": 2.3806,
1965
+ "step": 269
1966
+ },
1967
+ {
1968
+ "epoch": 2.25,
1969
+ "grad_norm": 0.0840055290628465,
1970
+ "learning_rate": 1.299411199521868e-05,
1971
+ "loss": 2.3277,
1972
+ "step": 270
1973
+ },
1974
+ {
1975
+ "epoch": 2.25,
1976
+ "eval_loss": 2.3895957469940186,
1977
+ "eval_runtime": 83.1157,
1978
+ "eval_samples_per_second": 4.933,
1979
+ "eval_steps_per_second": 0.313,
1980
+ "step": 270
1981
+ },
1982
+ {
1983
+ "epoch": 2.2583333333333333,
1984
+ "grad_norm": 0.07770712903979533,
1985
+ "learning_rate": 1.2893934026563873e-05,
1986
+ "loss": 2.2666,
1987
+ "step": 271
1988
+ },
1989
+ {
1990
+ "epoch": 2.2666666666666666,
1991
+ "grad_norm": 0.07846164594226922,
1992
+ "learning_rate": 1.2793823644219445e-05,
1993
+ "loss": 2.2855,
1994
+ "step": 272
1995
+ },
1996
+ {
1997
+ "epoch": 2.275,
1998
+ "grad_norm": 0.08498339693180243,
1999
+ "learning_rate": 1.269378583768554e-05,
2000
+ "loss": 2.2733,
2001
+ "step": 273
2002
+ },
2003
+ {
2004
+ "epoch": 2.283333333333333,
2005
+ "grad_norm": 0.07834222258922019,
2006
+ "learning_rate": 1.2593825592845122e-05,
2007
+ "loss": 2.3193,
2008
+ "step": 274
2009
+ },
2010
+ {
2011
+ "epoch": 2.2916666666666665,
2012
+ "grad_norm": 0.08132580954052983,
2013
+ "learning_rate": 1.2493947891715491e-05,
2014
+ "loss": 2.3085,
2015
+ "step": 275
2016
+ },
2017
+ {
2018
+ "epoch": 2.3,
2019
+ "grad_norm": 0.07883697009265064,
2020
+ "learning_rate": 1.239415771219996e-05,
2021
+ "loss": 2.3545,
2022
+ "step": 276
2023
+ },
2024
+ {
2025
+ "epoch": 2.3083333333333336,
2026
+ "grad_norm": 0.08023901828387182,
2027
+ "learning_rate": 1.2294460027839779e-05,
2028
+ "loss": 2.3489,
2029
+ "step": 277
2030
+ },
2031
+ {
2032
+ "epoch": 2.3166666666666664,
2033
+ "grad_norm": 0.08930364086676225,
2034
+ "learning_rate": 1.2194859807566216e-05,
2035
+ "loss": 2.2591,
2036
+ "step": 278
2037
+ },
2038
+ {
2039
+ "epoch": 2.325,
2040
+ "grad_norm": 0.08343332964333285,
2041
+ "learning_rate": 1.2095362015452961e-05,
2042
+ "loss": 2.3404,
2043
+ "step": 279
2044
+ },
2045
+ {
2046
+ "epoch": 2.3333333333333335,
2047
+ "grad_norm": 0.08292455976075656,
2048
+ "learning_rate": 1.199597161046867e-05,
2049
+ "loss": 2.3028,
2050
+ "step": 280
2051
+ },
2052
+ {
2053
+ "epoch": 2.341666666666667,
2054
+ "grad_norm": 0.08627078651851632,
2055
+ "learning_rate": 1.189669354622982e-05,
2056
+ "loss": 2.343,
2057
+ "step": 281
2058
+ },
2059
+ {
2060
+ "epoch": 2.35,
2061
+ "grad_norm": 0.08202097516344958,
2062
+ "learning_rate": 1.1797532770753842e-05,
2063
+ "loss": 2.326,
2064
+ "step": 282
2065
+ },
2066
+ {
2067
+ "epoch": 2.3583333333333334,
2068
+ "grad_norm": 0.08362611496815728,
2069
+ "learning_rate": 1.169849422621248e-05,
2070
+ "loss": 2.3035,
2071
+ "step": 283
2072
+ },
2073
+ {
2074
+ "epoch": 2.3666666666666667,
2075
+ "grad_norm": 0.08888611458113292,
2076
+ "learning_rate": 1.1599582848685506e-05,
2077
+ "loss": 2.2812,
2078
+ "step": 284
2079
+ },
2080
+ {
2081
+ "epoch": 2.375,
2082
+ "grad_norm": 0.08217261091117088,
2083
+ "learning_rate": 1.1500803567914671e-05,
2084
+ "loss": 2.3378,
2085
+ "step": 285
2086
+ },
2087
+ {
2088
+ "epoch": 2.3833333333333333,
2089
+ "grad_norm": 0.07985728135451624,
2090
+ "learning_rate": 1.1402161307058047e-05,
2091
+ "loss": 2.3522,
2092
+ "step": 286
2093
+ },
2094
+ {
2095
+ "epoch": 2.3916666666666666,
2096
+ "grad_norm": 0.08014525439116486,
2097
+ "learning_rate": 1.1303660982444624e-05,
2098
+ "loss": 2.2256,
2099
+ "step": 287
2100
+ },
2101
+ {
2102
+ "epoch": 2.4,
2103
+ "grad_norm": 0.08787593050595495,
2104
+ "learning_rate": 1.1205307503329286e-05,
2105
+ "loss": 2.2974,
2106
+ "step": 288
2107
+ },
2108
+ {
2109
+ "epoch": 2.408333333333333,
2110
+ "grad_norm": 0.08195162040998395,
2111
+ "learning_rate": 1.1107105771648151e-05,
2112
+ "loss": 2.353,
2113
+ "step": 289
2114
+ },
2115
+ {
2116
+ "epoch": 2.4166666666666665,
2117
+ "grad_norm": 0.08267743479386988,
2118
+ "learning_rate": 1.1009060681774236e-05,
2119
+ "loss": 2.3274,
2120
+ "step": 290
2121
+ },
2122
+ {
2123
+ "epoch": 2.425,
2124
+ "grad_norm": 0.08798947281948663,
2125
+ "learning_rate": 1.0911177120273537e-05,
2126
+ "loss": 2.3404,
2127
+ "step": 291
2128
+ },
2129
+ {
2130
+ "epoch": 2.4333333333333336,
2131
+ "grad_norm": 0.08828111892887862,
2132
+ "learning_rate": 1.0813459965661489e-05,
2133
+ "loss": 2.3348,
2134
+ "step": 292
2135
+ },
2136
+ {
2137
+ "epoch": 2.4416666666666664,
2138
+ "grad_norm": 0.08102528742267785,
2139
+ "learning_rate": 1.0715914088159789e-05,
2140
+ "loss": 2.2863,
2141
+ "step": 293
2142
+ },
2143
+ {
2144
+ "epoch": 2.45,
2145
+ "grad_norm": 0.0866645702075036,
2146
+ "learning_rate": 1.06185443494537e-05,
2147
+ "loss": 2.3357,
2148
+ "step": 294
2149
+ },
2150
+ {
2151
+ "epoch": 2.4583333333333335,
2152
+ "grad_norm": 0.08290121294865929,
2153
+ "learning_rate": 1.0521355602449723e-05,
2154
+ "loss": 2.3537,
2155
+ "step": 295
2156
+ },
2157
+ {
2158
+ "epoch": 2.466666666666667,
2159
+ "grad_norm": 0.08332374744178081,
2160
+ "learning_rate": 1.042435269103374e-05,
2161
+ "loss": 2.3554,
2162
+ "step": 296
2163
+ },
2164
+ {
2165
+ "epoch": 2.475,
2166
+ "grad_norm": 0.08367195510948358,
2167
+ "learning_rate": 1.0327540449829583e-05,
2168
+ "loss": 2.3384,
2169
+ "step": 297
2170
+ },
2171
+ {
2172
+ "epoch": 2.4833333333333334,
2173
+ "grad_norm": 0.08673119537467149,
2174
+ "learning_rate": 1.0230923703958083e-05,
2175
+ "loss": 2.2725,
2176
+ "step": 298
2177
+ },
2178
+ {
2179
+ "epoch": 2.4916666666666667,
2180
+ "grad_norm": 0.08235186060858125,
2181
+ "learning_rate": 1.0134507268796605e-05,
2182
+ "loss": 2.328,
2183
+ "step": 299
2184
+ },
2185
+ {
2186
+ "epoch": 2.5,
2187
+ "grad_norm": 0.08408079009588813,
2188
+ "learning_rate": 1.0038295949739004e-05,
2189
+ "loss": 2.3403,
2190
+ "step": 300
2191
+ },
2192
+ {
2193
+ "epoch": 2.5,
2194
+ "eval_loss": 2.3881967067718506,
2195
+ "eval_runtime": 82.1489,
2196
+ "eval_samples_per_second": 4.991,
2197
+ "eval_steps_per_second": 0.316,
2198
+ "step": 300
2199
+ },
2200
+ {
2201
+ "epoch": 2.5083333333333333,
2202
+ "grad_norm": 0.07909547450093556,
2203
+ "learning_rate": 9.942294541956169e-06,
2204
+ "loss": 2.3357,
2205
+ "step": 301
2206
+ },
2207
+ {
2208
+ "epoch": 2.5166666666666666,
2209
+ "grad_norm": 0.08766753125589274,
2210
+ "learning_rate": 9.846507830157e-06,
2211
+ "loss": 2.2503,
2212
+ "step": 302
2213
+ },
2214
+ {
2215
+ "epoch": 2.525,
2216
+ "grad_norm": 0.07987208695801865,
2217
+ "learning_rate": 9.75094058834997e-06,
2218
+ "loss": 2.3168,
2219
+ "step": 303
2220
+ },
2221
+ {
2222
+ "epoch": 2.533333333333333,
2223
+ "grad_norm": 0.08537107163629042,
2224
+ "learning_rate": 9.655597579605152e-06,
2225
+ "loss": 2.3036,
2226
+ "step": 304
2227
+ },
2228
+ {
2229
+ "epoch": 2.5416666666666665,
2230
+ "grad_norm": 0.08251527677113132,
2231
+ "learning_rate": 9.560483555816858e-06,
2232
+ "loss": 2.3419,
2233
+ "step": 305
2234
+ },
2235
+ {
2236
+ "epoch": 2.55,
2237
+ "grad_norm": 0.08523777732696665,
2238
+ "learning_rate": 9.465603257466792e-06,
2239
+ "loss": 2.3449,
2240
+ "step": 306
2241
+ },
2242
+ {
2243
+ "epoch": 2.5583333333333336,
2244
+ "grad_norm": 0.0848931418707024,
2245
+ "learning_rate": 9.370961413387778e-06,
2246
+ "loss": 2.2844,
2247
+ "step": 307
2248
+ },
2249
+ {
2250
+ "epoch": 2.5666666666666664,
2251
+ "grad_norm": 0.08156484852737556,
2252
+ "learning_rate": 9.27656274052809e-06,
2253
+ "loss": 2.3485,
2254
+ "step": 308
2255
+ },
2256
+ {
2257
+ "epoch": 2.575,
2258
+ "grad_norm": 0.08185057405642468,
2259
+ "learning_rate": 9.182411943716344e-06,
2260
+ "loss": 2.3748,
2261
+ "step": 309
2262
+ },
2263
+ {
2264
+ "epoch": 2.5833333333333335,
2265
+ "grad_norm": 0.08210521440208327,
2266
+ "learning_rate": 9.088513715427028e-06,
2267
+ "loss": 2.376,
2268
+ "step": 310
2269
+ },
2270
+ {
2271
+ "epoch": 2.591666666666667,
2272
+ "grad_norm": 0.08030540134328207,
2273
+ "learning_rate": 8.9948727355466e-06,
2274
+ "loss": 2.3196,
2275
+ "step": 311
2276
+ },
2277
+ {
2278
+ "epoch": 2.6,
2279
+ "grad_norm": 0.08216024303479584,
2280
+ "learning_rate": 8.901493671140283e-06,
2281
+ "loss": 2.3534,
2282
+ "step": 312
2283
+ },
2284
+ {
2285
+ "epoch": 2.6083333333333334,
2286
+ "grad_norm": 0.08105902557687622,
2287
+ "learning_rate": 8.808381176219426e-06,
2288
+ "loss": 2.2729,
2289
+ "step": 313
2290
+ },
2291
+ {
2292
+ "epoch": 2.6166666666666667,
2293
+ "grad_norm": 0.08410998796525411,
2294
+ "learning_rate": 8.71553989150955e-06,
2295
+ "loss": 2.3596,
2296
+ "step": 314
2297
+ },
2298
+ {
2299
+ "epoch": 2.625,
2300
+ "grad_norm": 0.08582437979635364,
2301
+ "learning_rate": 8.622974444219076e-06,
2302
+ "loss": 2.3063,
2303
+ "step": 315
2304
+ },
2305
+ {
2306
+ "epoch": 2.6333333333333333,
2307
+ "grad_norm": 0.08419960708603666,
2308
+ "learning_rate": 8.530689447808683e-06,
2309
+ "loss": 2.3468,
2310
+ "step": 316
2311
+ },
2312
+ {
2313
+ "epoch": 2.6416666666666666,
2314
+ "grad_norm": 0.08532017727647645,
2315
+ "learning_rate": 8.438689501761387e-06,
2316
+ "loss": 2.3378,
2317
+ "step": 317
2318
+ },
2319
+ {
2320
+ "epoch": 2.65,
2321
+ "grad_norm": 0.08544492639100988,
2322
+ "learning_rate": 8.346979191353288e-06,
2323
+ "loss": 2.2872,
2324
+ "step": 318
2325
+ },
2326
+ {
2327
+ "epoch": 2.658333333333333,
2328
+ "grad_norm": 0.0825611786693761,
2329
+ "learning_rate": 8.255563087425069e-06,
2330
+ "loss": 2.3037,
2331
+ "step": 319
2332
+ },
2333
+ {
2334
+ "epoch": 2.6666666666666665,
2335
+ "grad_norm": 0.07923900030264817,
2336
+ "learning_rate": 8.164445746154141e-06,
2337
+ "loss": 2.2746,
2338
+ "step": 320
2339
+ },
2340
+ {
2341
+ "epoch": 2.675,
2342
+ "grad_norm": 0.0805988851220756,
2343
+ "learning_rate": 8.073631708827614e-06,
2344
+ "loss": 2.3116,
2345
+ "step": 321
2346
+ },
2347
+ {
2348
+ "epoch": 2.6833333333333336,
2349
+ "grad_norm": 0.07902450485255898,
2350
+ "learning_rate": 7.983125501615913e-06,
2351
+ "loss": 2.3253,
2352
+ "step": 322
2353
+ },
2354
+ {
2355
+ "epoch": 2.6916666666666664,
2356
+ "grad_norm": 0.08586994856844313,
2357
+ "learning_rate": 7.892931635347223e-06,
2358
+ "loss": 2.3636,
2359
+ "step": 323
2360
+ },
2361
+ {
2362
+ "epoch": 2.7,
2363
+ "grad_norm": 0.08029033935205021,
2364
+ "learning_rate": 7.803054605282652e-06,
2365
+ "loss": 2.3023,
2366
+ "step": 324
2367
+ },
2368
+ {
2369
+ "epoch": 2.7083333333333335,
2370
+ "grad_norm": 0.08041087816983067,
2371
+ "learning_rate": 7.713498890892208e-06,
2372
+ "loss": 2.3629,
2373
+ "step": 325
2374
+ },
2375
+ {
2376
+ "epoch": 2.716666666666667,
2377
+ "grad_norm": 0.08451031313730265,
2378
+ "learning_rate": 7.624268955631531e-06,
2379
+ "loss": 2.2625,
2380
+ "step": 326
2381
+ },
2382
+ {
2383
+ "epoch": 2.725,
2384
+ "grad_norm": 0.07898217475608488,
2385
+ "learning_rate": 7.53536924671942e-06,
2386
+ "loss": 2.3106,
2387
+ "step": 327
2388
+ },
2389
+ {
2390
+ "epoch": 2.7333333333333334,
2391
+ "grad_norm": 0.08283676255780481,
2392
+ "learning_rate": 7.446804194916206e-06,
2393
+ "loss": 2.3576,
2394
+ "step": 328
2395
+ },
2396
+ {
2397
+ "epoch": 2.7416666666666667,
2398
+ "grad_norm": 0.08212231805524588,
2399
+ "learning_rate": 7.358578214302908e-06,
2400
+ "loss": 2.2791,
2401
+ "step": 329
2402
+ },
2403
+ {
2404
+ "epoch": 2.75,
2405
+ "grad_norm": 0.08251122557980495,
2406
+ "learning_rate": 7.270695702061248e-06,
2407
+ "loss": 2.3553,
2408
+ "step": 330
2409
+ },
2410
+ {
2411
+ "epoch": 2.75,
2412
+ "eval_loss": 2.387129783630371,
2413
+ "eval_runtime": 81.7826,
2414
+ "eval_samples_per_second": 5.013,
2415
+ "eval_steps_per_second": 0.318,
2416
+ "step": 330
2417
+ },
2418
+ {
2419
+ "epoch": 2.7583333333333333,
2420
+ "grad_norm": 0.08008513950564178,
2421
+ "learning_rate": 7.1831610382544856e-06,
2422
+ "loss": 2.2737,
2423
+ "step": 331
2424
+ },
2425
+ {
2426
+ "epoch": 2.7666666666666666,
2427
+ "grad_norm": 0.08378397772580942,
2428
+ "learning_rate": 7.095978585609125e-06,
2429
+ "loss": 2.362,
2430
+ "step": 332
2431
+ },
2432
+ {
2433
+ "epoch": 2.775,
2434
+ "grad_norm": 0.08519607549475229,
2435
+ "learning_rate": 7.009152689297463e-06,
2436
+ "loss": 2.2601,
2437
+ "step": 333
2438
+ },
2439
+ {
2440
+ "epoch": 2.783333333333333,
2441
+ "grad_norm": 0.08038464346170233,
2442
+ "learning_rate": 6.9226876767210355e-06,
2443
+ "loss": 2.3434,
2444
+ "step": 334
2445
+ },
2446
+ {
2447
+ "epoch": 2.7916666666666665,
2448
+ "grad_norm": 0.08107258257971683,
2449
+ "learning_rate": 6.83658785729493e-06,
2450
+ "loss": 2.2608,
2451
+ "step": 335
2452
+ },
2453
+ {
2454
+ "epoch": 2.8,
2455
+ "grad_norm": 0.0801095446046233,
2456
+ "learning_rate": 6.750857522233032e-06,
2457
+ "loss": 2.3562,
2458
+ "step": 336
2459
+ },
2460
+ {
2461
+ "epoch": 2.8083333333333336,
2462
+ "grad_norm": 0.08032953635285699,
2463
+ "learning_rate": 6.665500944334116e-06,
2464
+ "loss": 2.3473,
2465
+ "step": 337
2466
+ },
2467
+ {
2468
+ "epoch": 2.8166666666666664,
2469
+ "grad_norm": 0.08165787890975398,
2470
+ "learning_rate": 6.580522377768902e-06,
2471
+ "loss": 2.3662,
2472
+ "step": 338
2473
+ },
2474
+ {
2475
+ "epoch": 2.825,
2476
+ "grad_norm": 0.08186138228862638,
2477
+ "learning_rate": 6.495926057868045e-06,
2478
+ "loss": 2.3611,
2479
+ "step": 339
2480
+ },
2481
+ {
2482
+ "epoch": 2.8333333333333335,
2483
+ "grad_norm": 0.08409693406516083,
2484
+ "learning_rate": 6.4117162009110105e-06,
2485
+ "loss": 2.3014,
2486
+ "step": 340
2487
+ },
2488
+ {
2489
+ "epoch": 2.841666666666667,
2490
+ "grad_norm": 0.08426043237254878,
2491
+ "learning_rate": 6.327897003915982e-06,
2492
+ "loss": 2.3556,
2493
+ "step": 341
2494
+ },
2495
+ {
2496
+ "epoch": 2.85,
2497
+ "grad_norm": 0.07860767709618154,
2498
+ "learning_rate": 6.244472644430632e-06,
2499
+ "loss": 2.3986,
2500
+ "step": 342
2501
+ },
2502
+ {
2503
+ "epoch": 2.8583333333333334,
2504
+ "grad_norm": 0.07913910815896576,
2505
+ "learning_rate": 6.161447280323948e-06,
2506
+ "loss": 2.3041,
2507
+ "step": 343
2508
+ },
2509
+ {
2510
+ "epoch": 2.8666666666666667,
2511
+ "grad_norm": 0.0834686817566552,
2512
+ "learning_rate": 6.078825049578985e-06,
2513
+ "loss": 2.2694,
2514
+ "step": 344
2515
+ },
2516
+ {
2517
+ "epoch": 2.875,
2518
+ "grad_norm": 0.09464173421182612,
2519
+ "learning_rate": 5.996610070086646e-06,
2520
+ "loss": 2.3291,
2521
+ "step": 345
2522
+ },
2523
+ {
2524
+ "epoch": 2.8833333333333333,
2525
+ "grad_norm": 0.08924525286993587,
2526
+ "learning_rate": 5.914806439440443e-06,
2527
+ "loss": 2.2425,
2528
+ "step": 346
2529
+ },
2530
+ {
2531
+ "epoch": 2.8916666666666666,
2532
+ "grad_norm": 0.07984144031222275,
2533
+ "learning_rate": 5.833418234732248e-06,
2534
+ "loss": 2.3212,
2535
+ "step": 347
2536
+ },
2537
+ {
2538
+ "epoch": 2.9,
2539
+ "grad_norm": 0.08119999485058818,
2540
+ "learning_rate": 5.752449512349119e-06,
2541
+ "loss": 2.3043,
2542
+ "step": 348
2543
+ },
2544
+ {
2545
+ "epoch": 2.908333333333333,
2546
+ "grad_norm": 0.08130268904604636,
2547
+ "learning_rate": 5.671904307771115e-06,
2548
+ "loss": 2.3431,
2549
+ "step": 349
2550
+ },
2551
+ {
2552
+ "epoch": 2.9166666666666665,
2553
+ "grad_norm": 0.0886368269447557,
2554
+ "learning_rate": 5.591786635370193e-06,
2555
+ "loss": 2.2584,
2556
+ "step": 350
2557
+ },
2558
+ {
2559
+ "epoch": 2.925,
2560
+ "grad_norm": 0.08449560278602129,
2561
+ "learning_rate": 5.5121004882100805e-06,
2562
+ "loss": 2.2614,
2563
+ "step": 351
2564
+ },
2565
+ {
2566
+ "epoch": 2.9333333333333336,
2567
+ "grad_norm": 0.0877133422168611,
2568
+ "learning_rate": 5.4328498378473245e-06,
2569
+ "loss": 2.3467,
2570
+ "step": 352
2571
+ },
2572
+ {
2573
+ "epoch": 2.9416666666666664,
2574
+ "grad_norm": 0.0829503072213313,
2575
+ "learning_rate": 5.354038634133295e-06,
2576
+ "loss": 2.2975,
2577
+ "step": 353
2578
+ },
2579
+ {
2580
+ "epoch": 2.95,
2581
+ "grad_norm": 0.08436627929472401,
2582
+ "learning_rate": 5.27567080501735e-06,
2583
+ "loss": 2.3115,
2584
+ "step": 354
2585
+ },
2586
+ {
2587
+ "epoch": 2.9583333333333335,
2588
+ "grad_norm": 0.08048623155801396,
2589
+ "learning_rate": 5.197750256351076e-06,
2590
+ "loss": 2.2584,
2591
+ "step": 355
2592
+ },
2593
+ {
2594
+ "epoch": 2.966666666666667,
2595
+ "grad_norm": 0.08109596859654204,
2596
+ "learning_rate": 5.120280871693596e-06,
2597
+ "loss": 2.3677,
2598
+ "step": 356
2599
+ },
2600
+ {
2601
+ "epoch": 2.975,
2602
+ "grad_norm": 0.081013576151029,
2603
+ "learning_rate": 5.0432665121180266e-06,
2604
+ "loss": 2.3585,
2605
+ "step": 357
2606
+ },
2607
+ {
2608
+ "epoch": 2.9833333333333334,
2609
+ "grad_norm": 0.08546479543984016,
2610
+ "learning_rate": 4.966711016019037e-06,
2611
+ "loss": 2.303,
2612
+ "step": 358
2613
+ },
2614
+ {
2615
+ "epoch": 2.9916666666666667,
2616
+ "grad_norm": 0.08245660024002954,
2617
+ "learning_rate": 4.890618198921555e-06,
2618
+ "loss": 2.3149,
2619
+ "step": 359
2620
+ },
2621
+ {
2622
+ "epoch": 3.0,
2623
+ "grad_norm": 0.08512068224524219,
2624
+ "learning_rate": 4.814991853290595e-06,
2625
+ "loss": 2.2894,
2626
+ "step": 360
2627
+ },
2628
+ {
2629
+ "epoch": 3.0,
2630
+ "eval_loss": 2.386331081390381,
2631
+ "eval_runtime": 82.119,
2632
+ "eval_samples_per_second": 4.993,
2633
+ "eval_steps_per_second": 0.317,
2634
+ "step": 360
2635
+ },
2636
+ {
2637
+ "epoch": 3.0083333333333333,
2638
+ "grad_norm": 0.08558372235748295,
2639
+ "learning_rate": 4.739835748342228e-06,
2640
+ "loss": 2.2984,
2641
+ "step": 361
2642
+ },
2643
+ {
2644
+ "epoch": 3.0166666666666666,
2645
+ "grad_norm": 0.08035880067291258,
2646
+ "learning_rate": 4.665153629855744e-06,
2647
+ "loss": 2.3033,
2648
+ "step": 362
2649
+ },
2650
+ {
2651
+ "epoch": 3.025,
2652
+ "grad_norm": 0.07959465533779843,
2653
+ "learning_rate": 4.5909492199869445e-06,
2654
+ "loss": 2.3507,
2655
+ "step": 363
2656
+ },
2657
+ {
2658
+ "epoch": 3.033333333333333,
2659
+ "grad_norm": 0.08267174156962717,
2660
+ "learning_rate": 4.517226217082652e-06,
2661
+ "loss": 2.3425,
2662
+ "step": 364
2663
+ },
2664
+ {
2665
+ "epoch": 3.0416666666666665,
2666
+ "grad_norm": 0.07991572961673732,
2667
+ "learning_rate": 4.44398829549637e-06,
2668
+ "loss": 2.3261,
2669
+ "step": 365
2670
+ },
2671
+ {
2672
+ "epoch": 3.05,
2673
+ "grad_norm": 0.07847568885444599,
2674
+ "learning_rate": 4.371239105405148e-06,
2675
+ "loss": 2.3477,
2676
+ "step": 366
2677
+ },
2678
+ {
2679
+ "epoch": 3.058333333333333,
2680
+ "grad_norm": 0.08038194746327948,
2681
+ "learning_rate": 4.29898227262767e-06,
2682
+ "loss": 2.2698,
2683
+ "step": 367
2684
+ },
2685
+ {
2686
+ "epoch": 3.066666666666667,
2687
+ "grad_norm": 0.08253718833393997,
2688
+ "learning_rate": 4.22722139844353e-06,
2689
+ "loss": 2.3652,
2690
+ "step": 368
2691
+ },
2692
+ {
2693
+ "epoch": 3.075,
2694
+ "grad_norm": 0.08516413003066334,
2695
+ "learning_rate": 4.1559600594137686e-06,
2696
+ "loss": 2.3331,
2697
+ "step": 369
2698
+ },
2699
+ {
2700
+ "epoch": 3.0833333333333335,
2701
+ "grad_norm": 0.07953660852824361,
2702
+ "learning_rate": 4.085201807202586e-06,
2703
+ "loss": 2.3689,
2704
+ "step": 370
2705
+ },
2706
+ {
2707
+ "epoch": 3.091666666666667,
2708
+ "grad_norm": 0.08238213712670353,
2709
+ "learning_rate": 4.014950168400341e-06,
2710
+ "loss": 2.308,
2711
+ "step": 371
2712
+ },
2713
+ {
2714
+ "epoch": 3.1,
2715
+ "grad_norm": 0.08283454952311556,
2716
+ "learning_rate": 3.945208644347803e-06,
2717
+ "loss": 2.2875,
2718
+ "step": 372
2719
+ },
2720
+ {
2721
+ "epoch": 3.1083333333333334,
2722
+ "grad_norm": 0.08123988730396041,
2723
+ "learning_rate": 3.875980710961609e-06,
2724
+ "loss": 2.2607,
2725
+ "step": 373
2726
+ },
2727
+ {
2728
+ "epoch": 3.1166666666666667,
2729
+ "grad_norm": 0.08112099690166064,
2730
+ "learning_rate": 3.8072698185610614e-06,
2731
+ "loss": 2.3591,
2732
+ "step": 374
2733
+ },
2734
+ {
2735
+ "epoch": 3.125,
2736
+ "grad_norm": 0.0792957148134827,
2737
+ "learning_rate": 3.7390793916961342e-06,
2738
+ "loss": 2.3218,
2739
+ "step": 375
2740
+ },
2741
+ {
2742
+ "epoch": 3.1333333333333333,
2743
+ "grad_norm": 0.08349920233794074,
2744
+ "learning_rate": 3.671412828976812e-06,
2745
+ "loss": 2.298,
2746
+ "step": 376
2747
+ },
2748
+ {
2749
+ "epoch": 3.1416666666666666,
2750
+ "grad_norm": 0.07899532707809945,
2751
+ "learning_rate": 3.604273502903688e-06,
2752
+ "loss": 2.3226,
2753
+ "step": 377
2754
+ },
2755
+ {
2756
+ "epoch": 3.15,
2757
+ "grad_norm": 0.08573888823467567,
2758
+ "learning_rate": 3.537664759699903e-06,
2759
+ "loss": 2.316,
2760
+ "step": 378
2761
+ },
2762
+ {
2763
+ "epoch": 3.158333333333333,
2764
+ "grad_norm": 0.08115043743007767,
2765
+ "learning_rate": 3.4715899191443483e-06,
2766
+ "loss": 2.2912,
2767
+ "step": 379
2768
+ },
2769
+ {
2770
+ "epoch": 3.1666666666666665,
2771
+ "grad_norm": 0.08268384127740624,
2772
+ "learning_rate": 3.40605227440621e-06,
2773
+ "loss": 2.2777,
2774
+ "step": 380
2775
+ },
2776
+ {
2777
+ "epoch": 3.175,
2778
+ "grad_norm": 0.08106251418915893,
2779
+ "learning_rate": 3.3410550918808443e-06,
2780
+ "loss": 2.3159,
2781
+ "step": 381
2782
+ },
2783
+ {
2784
+ "epoch": 3.183333333333333,
2785
+ "grad_norm": 0.08286464503073644,
2786
+ "learning_rate": 3.276601611026974e-06,
2787
+ "loss": 2.3071,
2788
+ "step": 382
2789
+ },
2790
+ {
2791
+ "epoch": 3.191666666666667,
2792
+ "grad_norm": 0.08199773880110967,
2793
+ "learning_rate": 3.2126950442052483e-06,
2794
+ "loss": 2.3043,
2795
+ "step": 383
2796
+ },
2797
+ {
2798
+ "epoch": 3.2,
2799
+ "grad_norm": 0.08187041229316819,
2800
+ "learning_rate": 3.149338576518116e-06,
2801
+ "loss": 2.2955,
2802
+ "step": 384
2803
+ },
2804
+ {
2805
+ "epoch": 3.2083333333333335,
2806
+ "grad_norm": 0.08220875126507468,
2807
+ "learning_rate": 3.0865353656511014e-06,
2808
+ "loss": 2.3141,
2809
+ "step": 385
2810
+ },
2811
+ {
2812
+ "epoch": 3.216666666666667,
2813
+ "grad_norm": 0.08353220855881248,
2814
+ "learning_rate": 3.024288541715413e-06,
2815
+ "loss": 2.3677,
2816
+ "step": 386
2817
+ },
2818
+ {
2819
+ "epoch": 3.225,
2820
+ "grad_norm": 0.07903966810055228,
2821
+ "learning_rate": 2.9626012070919357e-06,
2822
+ "loss": 2.3359,
2823
+ "step": 387
2824
+ },
2825
+ {
2826
+ "epoch": 3.2333333333333334,
2827
+ "grad_norm": 0.08190032494339015,
2828
+ "learning_rate": 2.901476436276628e-06,
2829
+ "loss": 2.2796,
2830
+ "step": 388
2831
+ },
2832
+ {
2833
+ "epoch": 3.2416666666666667,
2834
+ "grad_norm": 0.08161746077320213,
2835
+ "learning_rate": 2.840917275727264e-06,
2836
+ "loss": 2.3368,
2837
+ "step": 389
2838
+ },
2839
+ {
2840
+ "epoch": 3.25,
2841
+ "grad_norm": 0.0815574105377222,
2842
+ "learning_rate": 2.780926743711611e-06,
2843
+ "loss": 2.2746,
2844
+ "step": 390
2845
+ },
2846
+ {
2847
+ "epoch": 3.25,
2848
+ "eval_loss": 2.385850667953491,
2849
+ "eval_runtime": 83.443,
2850
+ "eval_samples_per_second": 4.914,
2851
+ "eval_steps_per_second": 0.312,
2852
+ "step": 390
2853
+ },
2854
+ {
2855
+ "epoch": 3.2583333333333333,
2856
+ "grad_norm": 0.07940368361833833,
2857
+ "learning_rate": 2.7215078301570005e-06,
2858
+ "loss": 2.3239,
2859
+ "step": 391
2860
+ },
2861
+ {
2862
+ "epoch": 3.2666666666666666,
2863
+ "grad_norm": 0.0789092720450855,
2864
+ "learning_rate": 2.6626634965013064e-06,
2865
+ "loss": 2.3485,
2866
+ "step": 392
2867
+ },
2868
+ {
2869
+ "epoch": 3.275,
2870
+ "grad_norm": 0.07860086067453795,
2871
+ "learning_rate": 2.604396675545354e-06,
2872
+ "loss": 2.3022,
2873
+ "step": 393
2874
+ },
2875
+ {
2876
+ "epoch": 3.283333333333333,
2877
+ "grad_norm": 0.0827013915236191,
2878
+ "learning_rate": 2.546710271306732e-06,
2879
+ "loss": 2.3382,
2880
+ "step": 394
2881
+ },
2882
+ {
2883
+ "epoch": 3.2916666666666665,
2884
+ "grad_norm": 0.08392337720938575,
2885
+ "learning_rate": 2.4896071588750746e-06,
2886
+ "loss": 2.2495,
2887
+ "step": 395
2888
+ },
2889
+ {
2890
+ "epoch": 3.3,
2891
+ "grad_norm": 0.07896168168173961,
2892
+ "learning_rate": 2.433090184268755e-06,
2893
+ "loss": 2.3413,
2894
+ "step": 396
2895
+ },
2896
+ {
2897
+ "epoch": 3.3083333333333336,
2898
+ "grad_norm": 0.08513092869669563,
2899
+ "learning_rate": 2.3771621642930495e-06,
2900
+ "loss": 2.32,
2901
+ "step": 397
2902
+ },
2903
+ {
2904
+ "epoch": 3.3166666666666664,
2905
+ "grad_norm": 0.08158164066376497,
2906
+ "learning_rate": 2.3218258863997483e-06,
2907
+ "loss": 2.3159,
2908
+ "step": 398
2909
+ },
2910
+ {
2911
+ "epoch": 3.325,
2912
+ "grad_norm": 0.07850245543386242,
2913
+ "learning_rate": 2.2670841085482114e-06,
2914
+ "loss": 2.2892,
2915
+ "step": 399
2916
+ },
2917
+ {
2918
+ "epoch": 3.3333333333333335,
2919
+ "grad_norm": 0.07948289924872026,
2920
+ "learning_rate": 2.2129395590679325e-06,
2921
+ "loss": 2.3183,
2922
+ "step": 400
2923
+ },
2924
+ {
2925
+ "epoch": 3.341666666666667,
2926
+ "grad_norm": 0.08268427645613528,
2927
+ "learning_rate": 2.1593949365225455e-06,
2928
+ "loss": 2.3455,
2929
+ "step": 401
2930
+ },
2931
+ {
2932
+ "epoch": 3.35,
2933
+ "grad_norm": 0.0805567434916959,
2934
+ "learning_rate": 2.1064529095753457e-06,
2935
+ "loss": 2.323,
2936
+ "step": 402
2937
+ },
2938
+ {
2939
+ "epoch": 3.3583333333333334,
2940
+ "grad_norm": 0.08055664155765571,
2941
+ "learning_rate": 2.054116116856257e-06,
2942
+ "loss": 2.3334,
2943
+ "step": 403
2944
+ },
2945
+ {
2946
+ "epoch": 3.3666666666666667,
2947
+ "grad_norm": 0.082279494119965,
2948
+ "learning_rate": 2.0023871668303433e-06,
2949
+ "loss": 2.2938,
2950
+ "step": 404
2951
+ },
2952
+ {
2953
+ "epoch": 3.375,
2954
+ "grad_norm": 0.08252463940578399,
2955
+ "learning_rate": 1.9512686376678015e-06,
2956
+ "loss": 2.2965,
2957
+ "step": 405
2958
+ },
2959
+ {
2960
+ "epoch": 3.3833333333333333,
2961
+ "grad_norm": 0.08541294452389535,
2962
+ "learning_rate": 1.9007630771154532e-06,
2963
+ "loss": 2.2363,
2964
+ "step": 406
2965
+ },
2966
+ {
2967
+ "epoch": 3.3916666666666666,
2968
+ "grad_norm": 0.08261328178534114,
2969
+ "learning_rate": 1.850873002369778e-06,
2970
+ "loss": 2.3175,
2971
+ "step": 407
2972
+ },
2973
+ {
2974
+ "epoch": 3.4,
2975
+ "grad_norm": 0.0830385045862884,
2976
+ "learning_rate": 1.8016008999514467e-06,
2977
+ "loss": 2.2871,
2978
+ "step": 408
2979
+ },
2980
+ {
2981
+ "epoch": 3.408333333333333,
2982
+ "grad_norm": 0.08146738848250283,
2983
+ "learning_rate": 1.7529492255814008e-06,
2984
+ "loss": 2.3198,
2985
+ "step": 409
2986
+ },
2987
+ {
2988
+ "epoch": 3.4166666666666665,
2989
+ "grad_norm": 0.0827275148559704,
2990
+ "learning_rate": 1.704920404058452e-06,
2991
+ "loss": 2.2888,
2992
+ "step": 410
2993
+ },
2994
+ {
2995
+ "epoch": 3.425,
2996
+ "grad_norm": 0.0803715450561763,
2997
+ "learning_rate": 1.6575168291384352e-06,
2998
+ "loss": 2.3405,
2999
+ "step": 411
3000
+ },
3001
+ {
3002
+ "epoch": 3.4333333333333336,
3003
+ "grad_norm": 0.07862601957152224,
3004
+ "learning_rate": 1.6107408634149068e-06,
3005
+ "loss": 2.2978,
3006
+ "step": 412
3007
+ },
3008
+ {
3009
+ "epoch": 3.4416666666666664,
3010
+ "grad_norm": 0.0797822244213719,
3011
+ "learning_rate": 1.5645948382013898e-06,
3012
+ "loss": 2.3701,
3013
+ "step": 413
3014
+ },
3015
+ {
3016
+ "epoch": 3.45,
3017
+ "grad_norm": 0.07749237550393802,
3018
+ "learning_rate": 1.5190810534151723e-06,
3019
+ "loss": 2.3616,
3020
+ "step": 414
3021
+ },
3022
+ {
3023
+ "epoch": 3.4583333333333335,
3024
+ "grad_norm": 0.07924907970443268,
3025
+ "learning_rate": 1.474201777462696e-06,
3026
+ "loss": 2.2771,
3027
+ "step": 415
3028
+ },
3029
+ {
3030
+ "epoch": 3.466666666666667,
3031
+ "grad_norm": 0.07962985015963248,
3032
+ "learning_rate": 1.4299592471264814e-06,
3033
+ "loss": 2.3482,
3034
+ "step": 416
3035
+ },
3036
+ {
3037
+ "epoch": 3.475,
3038
+ "grad_norm": 0.08046145953371857,
3039
+ "learning_rate": 1.3863556674536668e-06,
3040
+ "loss": 2.2809,
3041
+ "step": 417
3042
+ },
3043
+ {
3044
+ "epoch": 3.4833333333333334,
3045
+ "grad_norm": 0.08300783210234308,
3046
+ "learning_rate": 1.3433932116460928e-06,
3047
+ "loss": 2.257,
3048
+ "step": 418
3049
+ },
3050
+ {
3051
+ "epoch": 3.4916666666666667,
3052
+ "grad_norm": 0.07975202760505942,
3053
+ "learning_rate": 1.3010740209519938e-06,
3054
+ "loss": 2.2887,
3055
+ "step": 419
3056
+ },
3057
+ {
3058
+ "epoch": 3.5,
3059
+ "grad_norm": 0.08236525138293024,
3060
+ "learning_rate": 1.2594002045592805e-06,
3061
+ "loss": 2.3372,
3062
+ "step": 420
3063
+ },
3064
+ {
3065
+ "epoch": 3.5,
3066
+ "eval_loss": 2.385662794113159,
3067
+ "eval_runtime": 83.0808,
3068
+ "eval_samples_per_second": 4.935,
3069
+ "eval_steps_per_second": 0.313,
3070
+ "step": 420
3071
+ }
3072
+ ],
3073
+ "logging_steps": 1,
3074
+ "max_steps": 480,
3075
+ "num_input_tokens_seen": 0,
3076
+ "num_train_epochs": 4,
3077
+ "save_steps": 60,
3078
+ "stateful_callbacks": {
3079
+ "TrainerControl": {
3080
+ "args": {
3081
+ "should_epoch_stop": false,
3082
+ "should_evaluate": false,
3083
+ "should_log": false,
3084
+ "should_save": true,
3085
+ "should_training_stop": false
3086
+ },
3087
+ "attributes": {}
3088
+ }
3089
+ },
3090
+ "total_flos": 5.210852912057549e+17,
3091
+ "train_batch_size": 4,
3092
+ "trial_name": null,
3093
+ "trial_params": null
3094
+ }
checkpoint-420/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0950ae128e4d4958ddb8a58739e4390730bca7076e922a94736a9f4ca7c6f0f1
3
+ size 8504
checkpoint-420/zero_to_fp32.py ADDED
@@ -0,0 +1,760 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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:
14
+ # python zero_to_fp32.py . output_dir/
15
+ # or
16
+ # python zero_to_fp32.py . output_dir/ --safe_serialization
17
+
18
+ import argparse
19
+ import torch
20
+ import glob
21
+ import math
22
+ import os
23
+ import re
24
+ import gc
25
+ import json
26
+ import numpy as np
27
+ from tqdm import tqdm
28
+ from collections import OrderedDict
29
+ from dataclasses import dataclass
30
+
31
+ # while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
32
+ # DeepSpeed data structures it has to be available in the current python environment.
33
+ from deepspeed.utils import logger
34
+ from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
35
+ FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
36
+ FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
37
+
38
+
39
+ @dataclass
40
+ class zero_model_state:
41
+ buffers: dict()
42
+ param_shapes: dict()
43
+ shared_params: list
44
+ ds_version: int
45
+ frozen_param_shapes: dict()
46
+ frozen_param_fragments: dict()
47
+
48
+
49
+ debug = 0
50
+
51
+ # load to cpu
52
+ device = torch.device('cpu')
53
+
54
+
55
+ def atoi(text):
56
+ return int(text) if text.isdigit() else text
57
+
58
+
59
+ def natural_keys(text):
60
+ '''
61
+ alist.sort(key=natural_keys) sorts in human order
62
+ http://nedbatchelder.com/blog/200712/human_sorting.html
63
+ (See Toothy's implementation in the comments)
64
+ '''
65
+ return [atoi(c) for c in re.split(r'(\d+)', text)]
66
+
67
+
68
+ def get_model_state_file(checkpoint_dir, zero_stage):
69
+ if not os.path.isdir(checkpoint_dir):
70
+ raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
71
+
72
+ # there should be only one file
73
+ if zero_stage <= 2:
74
+ file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
75
+ elif zero_stage == 3:
76
+ file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
77
+
78
+ if not os.path.exists(file):
79
+ raise FileNotFoundError(f"can't find model states file at '{file}'")
80
+
81
+ return file
82
+
83
+
84
+ def get_checkpoint_files(checkpoint_dir, glob_pattern):
85
+ # XXX: need to test that this simple glob rule works for multi-node setup too
86
+ ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
87
+
88
+ if len(ckpt_files) == 0:
89
+ raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
90
+
91
+ return ckpt_files
92
+
93
+
94
+ def get_optim_files(checkpoint_dir):
95
+ return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
96
+
97
+
98
+ def get_model_state_files(checkpoint_dir):
99
+ return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
100
+
101
+
102
+ def parse_model_states(files):
103
+ zero_model_states = []
104
+ for file in files:
105
+ state_dict = torch.load(file, map_location=device, weights_only=False)
106
+
107
+ if BUFFER_NAMES not in state_dict:
108
+ raise ValueError(f"{file} is not a model state checkpoint")
109
+ buffer_names = state_dict[BUFFER_NAMES]
110
+ if debug:
111
+ print("Found buffers:", buffer_names)
112
+
113
+ # recover just the buffers while restoring them to fp32 if they were saved in fp16
114
+ buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
115
+ param_shapes = state_dict[PARAM_SHAPES]
116
+
117
+ # collect parameters that are included in param_shapes
118
+ param_names = []
119
+ for s in param_shapes:
120
+ for name in s.keys():
121
+ param_names.append(name)
122
+
123
+ # update with frozen parameters
124
+ frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
125
+ if frozen_param_shapes is not None:
126
+ if debug:
127
+ print(f"Found frozen_param_shapes: {frozen_param_shapes}")
128
+ param_names += list(frozen_param_shapes.keys())
129
+
130
+ # handle shared params
131
+ shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
132
+
133
+ ds_version = state_dict.get(DS_VERSION, None)
134
+
135
+ frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
136
+
137
+ z_model_state = zero_model_state(buffers=buffers,
138
+ param_shapes=param_shapes,
139
+ shared_params=shared_params,
140
+ ds_version=ds_version,
141
+ frozen_param_shapes=frozen_param_shapes,
142
+ frozen_param_fragments=frozen_param_fragments)
143
+ zero_model_states.append(z_model_state)
144
+
145
+ return zero_model_states
146
+
147
+
148
+ def parse_optim_states(files, ds_checkpoint_dir):
149
+ total_files = len(files)
150
+ state_dicts = []
151
+ for f in tqdm(files, desc='Loading checkpoint shards'):
152
+ state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
153
+ # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
154
+ # and also handle the case where it was already removed by another helper script
155
+ state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
156
+ state_dicts.append(state_dict)
157
+
158
+ if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
159
+ raise ValueError(f"{files[0]} is not a zero checkpoint")
160
+ zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
161
+ world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
162
+
163
+ # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
164
+ # parameters can be different from data parallelism for non-expert parameters. So we can just
165
+ # use the max of the partition_count to get the dp world_size.
166
+
167
+ if type(world_size) is list:
168
+ world_size = max(world_size)
169
+
170
+ if world_size != total_files:
171
+ raise ValueError(
172
+ f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
173
+ "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
174
+ )
175
+
176
+ # the groups are named differently in each stage
177
+ if zero_stage <= 2:
178
+ fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
179
+ elif zero_stage == 3:
180
+ fp32_groups_key = FP32_FLAT_GROUPS
181
+ else:
182
+ raise ValueError(f"unknown zero stage {zero_stage}")
183
+
184
+ fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
185
+ return zero_stage, world_size, fp32_flat_groups
186
+
187
+
188
+ def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
189
+ """
190
+ Returns fp32 state_dict reconstructed from ds checkpoint
191
+
192
+ Args:
193
+ - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
194
+
195
+ """
196
+ print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
197
+
198
+ optim_files = get_optim_files(ds_checkpoint_dir)
199
+ zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
200
+ print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
201
+
202
+ model_files = get_model_state_files(ds_checkpoint_dir)
203
+
204
+ zero_model_states = parse_model_states(model_files)
205
+ print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
206
+
207
+ if zero_stage <= 2:
208
+ return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
209
+ exclude_frozen_parameters)
210
+ elif zero_stage == 3:
211
+ return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
212
+ exclude_frozen_parameters)
213
+
214
+
215
+ def _zero2_merge_frozen_params(state_dict, zero_model_states):
216
+ if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
217
+ return
218
+
219
+ frozen_param_shapes = zero_model_states[0].frozen_param_shapes
220
+ frozen_param_fragments = zero_model_states[0].frozen_param_fragments
221
+
222
+ if debug:
223
+ num_elem = sum(s.numel() for s in frozen_param_shapes.values())
224
+ print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
225
+
226
+ wanted_params = len(frozen_param_shapes)
227
+ wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
228
+ avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
229
+ print(f'Frozen params: Have {avail_numel} numels to process.')
230
+ print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
231
+
232
+ total_params = 0
233
+ total_numel = 0
234
+ for name, shape in frozen_param_shapes.items():
235
+ total_params += 1
236
+ unpartitioned_numel = shape.numel()
237
+ total_numel += unpartitioned_numel
238
+
239
+ state_dict[name] = frozen_param_fragments[name]
240
+
241
+ if debug:
242
+ print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
243
+
244
+ print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
245
+
246
+
247
+ def _has_callable(obj, fn):
248
+ attr = getattr(obj, fn, None)
249
+ return callable(attr)
250
+
251
+
252
+ def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
253
+ param_shapes = zero_model_states[0].param_shapes
254
+
255
+ # Reconstruction protocol:
256
+ #
257
+ # XXX: document this
258
+
259
+ if debug:
260
+ for i in range(world_size):
261
+ for j in range(len(fp32_flat_groups[0])):
262
+ print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
263
+
264
+ # XXX: memory usage doubles here (zero2)
265
+ num_param_groups = len(fp32_flat_groups[0])
266
+ merged_single_partition_of_fp32_groups = []
267
+ for i in range(num_param_groups):
268
+ merged_partitions = [sd[i] for sd in fp32_flat_groups]
269
+ full_single_fp32_vector = torch.cat(merged_partitions, 0)
270
+ merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
271
+ avail_numel = sum(
272
+ [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
273
+
274
+ if debug:
275
+ wanted_params = sum([len(shapes) for shapes in param_shapes])
276
+ wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
277
+ # not asserting if there is a mismatch due to possible padding
278
+ print(f"Have {avail_numel} numels to process.")
279
+ print(f"Need {wanted_numel} numels in {wanted_params} params.")
280
+
281
+ # params
282
+ # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
283
+ # out-of-core computing solution
284
+ total_numel = 0
285
+ total_params = 0
286
+ for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
287
+ offset = 0
288
+ avail_numel = full_single_fp32_vector.numel()
289
+ for name, shape in shapes.items():
290
+
291
+ unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
292
+ total_numel += unpartitioned_numel
293
+ total_params += 1
294
+
295
+ if debug:
296
+ print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
297
+ state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
298
+ offset += unpartitioned_numel
299
+
300
+ # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
301
+ # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
302
+ # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
303
+ # live optimizer object, so we are checking that the numbers are within the right range
304
+ align_to = 2 * world_size
305
+
306
+ def zero2_align(x):
307
+ return align_to * math.ceil(x / align_to)
308
+
309
+ if debug:
310
+ print(f"original offset={offset}, avail_numel={avail_numel}")
311
+
312
+ offset = zero2_align(offset)
313
+ avail_numel = zero2_align(avail_numel)
314
+
315
+ if debug:
316
+ print(f"aligned offset={offset}, avail_numel={avail_numel}")
317
+
318
+ # Sanity check
319
+ if offset != avail_numel:
320
+ raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
321
+
322
+ print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
323
+
324
+
325
+ def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
326
+ exclude_frozen_parameters):
327
+ state_dict = OrderedDict()
328
+
329
+ # buffers
330
+ buffers = zero_model_states[0].buffers
331
+ state_dict.update(buffers)
332
+ if debug:
333
+ print(f"added {len(buffers)} buffers")
334
+
335
+ if not exclude_frozen_parameters:
336
+ _zero2_merge_frozen_params(state_dict, zero_model_states)
337
+
338
+ _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
339
+
340
+ # recover shared parameters
341
+ for pair in zero_model_states[0].shared_params:
342
+ if pair[1] in state_dict:
343
+ state_dict[pair[0]] = state_dict[pair[1]]
344
+
345
+ return state_dict
346
+
347
+
348
+ def zero3_partitioned_param_info(unpartitioned_numel, world_size):
349
+ remainder = unpartitioned_numel % world_size
350
+ padding_numel = (world_size - remainder) if remainder else 0
351
+ partitioned_numel = math.ceil(unpartitioned_numel / world_size)
352
+ return partitioned_numel, padding_numel
353
+
354
+
355
+ def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
356
+ if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
357
+ return
358
+
359
+ if debug:
360
+ for i in range(world_size):
361
+ num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
362
+ print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
363
+
364
+ frozen_param_shapes = zero_model_states[0].frozen_param_shapes
365
+ wanted_params = len(frozen_param_shapes)
366
+ wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
367
+ avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
368
+ print(f'Frozen params: Have {avail_numel} numels to process.')
369
+ print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
370
+
371
+ total_params = 0
372
+ total_numel = 0
373
+ for name, shape in zero_model_states[0].frozen_param_shapes.items():
374
+ total_params += 1
375
+ unpartitioned_numel = shape.numel()
376
+ total_numel += unpartitioned_numel
377
+
378
+ param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
379
+ state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
380
+
381
+ partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
382
+
383
+ if debug:
384
+ print(
385
+ f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
386
+ )
387
+
388
+ print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
389
+
390
+
391
+ class GatheredTensor:
392
+ """
393
+ A pseudo tensor that collects partitioned weights.
394
+ It is more memory efficient when there are multiple groups.
395
+ """
396
+
397
+ def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
398
+ self.flat_groups = flat_groups
399
+ self.flat_groups_offset = flat_groups_offset
400
+ self.offset = offset
401
+ self.partitioned_numel = partitioned_numel
402
+ self.shape = shape
403
+ self.dtype = self.flat_groups[0][0].dtype
404
+
405
+ def contiguous(self):
406
+ """
407
+ Merge partitioned weights from flat_groups into a single tensor.
408
+ """
409
+ end_idx = self.offset + self.partitioned_numel
410
+ world_size = len(self.flat_groups)
411
+ pad_flat_param_chunks = []
412
+
413
+ for rank_i in range(world_size):
414
+ # for each rank, we need to collect weights from related group/groups
415
+ flat_groups_at_rank_i = self.flat_groups[rank_i]
416
+ start_group_id = None
417
+ end_group_id = None
418
+ for group_id in range(len(self.flat_groups_offset)):
419
+ if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
420
+ start_group_id = group_id
421
+ if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
422
+ end_group_id = group_id
423
+ break
424
+ # collect weights from related group/groups
425
+ for group_id in range(start_group_id, end_group_id + 1):
426
+ flat_tensor = flat_groups_at_rank_i[group_id]
427
+ start_offset = self.offset - self.flat_groups_offset[group_id]
428
+ end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
429
+ pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
430
+
431
+ # collect weights from all ranks
432
+ pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
433
+ param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
434
+ return param
435
+
436
+
437
+ def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
438
+ param_shapes = zero_model_states[0].param_shapes
439
+ avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size
440
+
441
+ # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
442
+ # param, re-consolidating each param, while dealing with padding if any
443
+
444
+ # merge list of dicts, preserving order
445
+ param_shapes = {k: v for d in param_shapes for k, v in d.items()}
446
+
447
+ if debug:
448
+ for i in range(world_size):
449
+ print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
450
+
451
+ wanted_params = len(param_shapes)
452
+ wanted_numel = sum(shape.numel() for shape in param_shapes.values())
453
+ # not asserting if there is a mismatch due to possible padding
454
+ avail_numel = fp32_flat_groups[0].numel() * world_size
455
+ print(f"Trainable params: Have {avail_numel} numels to process.")
456
+ print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
457
+
458
+ # params
459
+ # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
460
+ # out-of-core computing solution
461
+ offset = 0
462
+ total_numel = 0
463
+ total_params = 0
464
+ flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
465
+ for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
466
+ unpartitioned_numel = shape.numel()
467
+ total_numel += unpartitioned_numel
468
+ total_params += 1
469
+ partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
470
+
471
+ if debug:
472
+ print(
473
+ f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
474
+ )
475
+
476
+ # memory efficient tensor
477
+ tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
478
+ state_dict[name] = tensor
479
+ offset += partitioned_numel
480
+
481
+ offset *= world_size
482
+
483
+ # Sanity check
484
+ if offset != avail_numel:
485
+ raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
486
+
487
+ print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
488
+
489
+
490
+ def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
491
+ exclude_frozen_parameters):
492
+ state_dict = OrderedDict()
493
+
494
+ # buffers
495
+ buffers = zero_model_states[0].buffers
496
+ state_dict.update(buffers)
497
+ if debug:
498
+ print(f"added {len(buffers)} buffers")
499
+
500
+ if not exclude_frozen_parameters:
501
+ _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
502
+
503
+ _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
504
+
505
+ # recover shared parameters
506
+ for pair in zero_model_states[0].shared_params:
507
+ if pair[1] in state_dict:
508
+ state_dict[pair[0]] = state_dict[pair[1]]
509
+
510
+ return state_dict
511
+
512
+
513
+ def to_torch_tensor(state_dict, return_empty_tensor=False):
514
+ """
515
+ Convert state_dict of GatheredTensor to torch tensor
516
+ """
517
+ torch_state_dict = {}
518
+ converted_tensors = {}
519
+ for name, tensor in state_dict.items():
520
+ tensor_id = id(tensor)
521
+ if tensor_id in converted_tensors: # shared tensors
522
+ shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
523
+ torch_state_dict[name] = shared_tensor
524
+ else:
525
+ converted_tensors[tensor_id] = name
526
+ if return_empty_tensor:
527
+ torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
528
+ else:
529
+ torch_state_dict[name] = tensor.contiguous()
530
+ return torch_state_dict
531
+
532
+
533
+ def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
534
+ tag=None,
535
+ exclude_frozen_parameters=False,
536
+ lazy_mode=False):
537
+ """
538
+ Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
539
+ ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
540
+ via a model hub.
541
+
542
+ Args:
543
+ - ``checkpoint_dir``: path to the desired checkpoint folder
544
+ - ``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``
545
+ - ``exclude_frozen_parameters``: exclude frozen parameters
546
+ - ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
547
+ Convert the pesduo tensor to torch tensor by ``.contiguous()``
548
+
549
+ Returns:
550
+ - pytorch ``state_dict``
551
+
552
+ A typical usage might be ::
553
+
554
+ from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
555
+ # do the training and checkpoint saving
556
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
557
+ model = model.cpu() # move to cpu
558
+ model.load_state_dict(state_dict)
559
+ # submit to model hub or save the model to share with others
560
+
561
+ In this example the ``model`` will no longer be usable in the deepspeed context of the same
562
+ application. i.e. you will need to re-initialize the deepspeed engine, since
563
+ ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
564
+
565
+ If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
566
+
567
+ Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
568
+ You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
569
+ the checkpoint. Or you can load state_dict in lazy mode ::
570
+
571
+ from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
572
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
573
+ for name, lazy_tensor in state_dict.item():
574
+ tensor = lazy_tensor.contiguous() # to cpu
575
+ print(name, tensor)
576
+ # del tensor to release memory if it no longer in use
577
+ """
578
+ if tag is None:
579
+ latest_path = os.path.join(checkpoint_dir, 'latest')
580
+ if os.path.isfile(latest_path):
581
+ with open(latest_path, 'r') as fd:
582
+ tag = fd.read().strip()
583
+ else:
584
+ raise ValueError(f"Unable to find 'latest' file at {latest_path}")
585
+
586
+ ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
587
+
588
+ if not os.path.isdir(ds_checkpoint_dir):
589
+ raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
590
+
591
+ state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
592
+ if lazy_mode:
593
+ return state_dict
594
+ else:
595
+ return to_torch_tensor(state_dict)
596
+
597
+
598
+ def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
599
+ output_dir,
600
+ max_shard_size="5GB",
601
+ safe_serialization=False,
602
+ tag=None,
603
+ exclude_frozen_parameters=False):
604
+ """
605
+ Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
606
+ loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
607
+
608
+ Args:
609
+ - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
610
+ - ``output_dir``: directory to the pytorch fp32 state_dict output files
611
+ - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
612
+ - ``safe_serialization``: whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
613
+ - ``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``
614
+ - ``exclude_frozen_parameters``: exclude frozen parameters
615
+ """
616
+
617
+ # Dependency pre-check
618
+ if safe_serialization:
619
+ try:
620
+ from safetensors.torch import save_file
621
+ except ImportError:
622
+ print('If you want to use `safe_serialization`, please `pip install safetensors`')
623
+ raise
624
+ if max_shard_size is not None:
625
+ try:
626
+ from huggingface_hub import split_torch_state_dict_into_shards
627
+ except ImportError:
628
+ print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
629
+ raise
630
+
631
+ # Convert zero checkpoint to state_dict
632
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
633
+ tag,
634
+ exclude_frozen_parameters,
635
+ lazy_mode=True)
636
+
637
+ # Shard the model if it is too big.
638
+ weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
639
+ if max_shard_size is not None:
640
+ filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
641
+ # an memory-efficient approach for sharding
642
+ empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
643
+ state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
644
+ filename_pattern=filename_pattern,
645
+ max_shard_size=max_shard_size)
646
+ else:
647
+ from collections import namedtuple
648
+ StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
649
+ state_dict_split = StateDictSplit(is_sharded=False,
650
+ filename_to_tensors={weights_name: list(state_dict.keys())})
651
+
652
+ # Save the model by shard
653
+ os.makedirs(output_dir, exist_ok=True)
654
+ filename_to_tensors = state_dict_split.filename_to_tensors.items()
655
+ for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
656
+ shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
657
+ shard_state_dict = to_torch_tensor(shard_state_dict)
658
+ output_path = os.path.join(output_dir, shard_file)
659
+ if safe_serialization:
660
+ save_file(shard_state_dict, output_path, metadata={"format": "pt"})
661
+ else:
662
+ torch.save(shard_state_dict, output_path)
663
+ # release the memory of current shard
664
+ for tensor_name in list(shard_state_dict.keys()):
665
+ del state_dict[tensor_name]
666
+ del shard_state_dict[tensor_name]
667
+ del shard_state_dict
668
+ gc.collect()
669
+
670
+ # Save index if sharded
671
+ if state_dict_split.is_sharded:
672
+ index = {
673
+ "metadata": state_dict_split.metadata,
674
+ "weight_map": state_dict_split.tensor_to_filename,
675
+ }
676
+ save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
677
+ save_index_file = os.path.join(output_dir, save_index_file)
678
+ with open(save_index_file, "w", encoding="utf-8") as f:
679
+ content = json.dumps(index, indent=2, sort_keys=True) + "\n"
680
+ f.write(content)
681
+
682
+
683
+ def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
684
+ """
685
+ 1. Put the provided model to cpu
686
+ 2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
687
+ 3. Load it into the provided model
688
+
689
+ Args:
690
+ - ``model``: the model object to update
691
+ - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
692
+ - ``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``
693
+
694
+ Returns:
695
+ - ``model`: modified model
696
+
697
+ Make sure you have plenty of CPU memory available before you call this function. If you don't
698
+ have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
699
+ conveniently placed for you in the checkpoint folder.
700
+
701
+ A typical usage might be ::
702
+
703
+ from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
704
+ model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
705
+ # submit to model hub or save the model to share with others
706
+
707
+ Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
708
+ of the same application. i.e. you will need to re-initialize the deepspeed engine, since
709
+ ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
710
+
711
+ """
712
+ logger.info(f"Extracting fp32 weights")
713
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
714
+
715
+ logger.info(f"Overwriting model with fp32 weights")
716
+ model = model.cpu()
717
+ model.load_state_dict(state_dict, strict=False)
718
+
719
+ return model
720
+
721
+
722
+ if __name__ == "__main__":
723
+ parser = argparse.ArgumentParser()
724
+ parser.add_argument("checkpoint_dir",
725
+ type=str,
726
+ help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
727
+ parser.add_argument("output_dir",
728
+ type=str,
729
+ help="directory to the pytorch fp32 state_dict output files"
730
+ "(e.g. path/checkpoint-12-output/)")
731
+ parser.add_argument(
732
+ "--max_shard_size",
733
+ type=str,
734
+ default="5GB",
735
+ help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
736
+ "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
737
+ "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
738
+ "without CPU OOM issues.")
739
+ parser.add_argument(
740
+ "--safe_serialization",
741
+ default=False,
742
+ action='store_true',
743
+ help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
744
+ parser.add_argument("-t",
745
+ "--tag",
746
+ type=str,
747
+ default=None,
748
+ help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
749
+ parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
750
+ parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
751
+ args = parser.parse_args()
752
+
753
+ debug = args.debug
754
+
755
+ convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
756
+ args.output_dir,
757
+ max_shard_size=args.max_shard_size,
758
+ safe_serialization=args.safe_serialization,
759
+ tag=args.tag,
760
+ exclude_frozen_parameters=args.exclude_frozen_parameters)
checkpoint-480/adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "NewEden/Hamanasu-KTO-V2",
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": 16,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 128,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "gate_proj",
28
+ "o_proj",
29
+ "q_proj",
30
+ "k_proj",
31
+ "down_proj",
32
+ "up_proj",
33
+ "v_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": true
39
+ }
checkpoint-480/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f43dab069cfdcacbd2443671997ce7738bb6dc3830c63fa9d0e4d28a5903ffc
3
+ size 486600536