Hugging Face's logo

Edens-Gate
/
KTOloraepoch1

PEFT
Safetensors
Model card Files Community
Delta-Vector commited on
Commit
672a623
·
verified ·
1 Parent(s): 5ec8ab6

Upload 19 files

Browse files
Files changed (19) hide show
  1. README.md +202 -0
  2. adapter_config.json +34 -0
  3. adapter_model.safetensors +3 -0
  4. latest +1 -0
  5. rng_state_0.pth +3 -0
  6. rng_state_1.pth +3 -0
  7. rng_state_2.pth +3 -0
  8. rng_state_3.pth +3 -0
  9. rng_state_4.pth +3 -0
  10. rng_state_5.pth +3 -0
  11. rng_state_6.pth +3 -0
  12. rng_state_7.pth +3 -0
  13. scheduler.pt +3 -0
  14. special_tokens_map.json +32 -0
  15. tokenizer.json +0 -0
  16. tokenizer_config.json +2068 -0
  17. trainer_state.json +1613 -0
  18. training_args.bin +3 -0
  19. zero_to_fp32.py +604 -0
README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: anthracite-org/magnum-v2-4b
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 0.12.0
adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "anthracite-org/magnum-v2-4b",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.0,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 32,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "v_proj",
24
+ "o_proj",
25
+ "gate_proj",
26
+ "q_proj",
27
+ "down_proj",
28
+ "k_proj",
29
+ "up_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aab4af9417c096c66f8a20ca1644c1167ebd8144e10b61a6d59979289754b5d3
3
+ size 121695024
latest ADDED
@@ -0,0 +1 @@
 
 
1
+ global_step114
rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae9162e03c562553a5d9d13120f544d3c47ea71bb39aa44e18253675e17ed4a4
3
+ size 15984
rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4809456871b3a40c8db7e0926a9db11b01149a1d483fb29b16fc69dabaf36c6f
3
+ size 15984
rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bb6bcf25ff148b74eea7dd4895fc42e9433538fff5d75f0d2ae6cb0c2fdadf0
3
+ size 15984
rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f00ea04cd1a52c539d9cc948ac8a04676d6b99702acd09149565f781806f63f
3
+ size 15984
rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5571fb2fc1b413792b01ac691c759786855573992bab1d14875faccdaf8c881e
3
+ size 15984
rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59019ba23ead9c15851cb4349397254458ce50ea3c2987090404f4f3842c6d8f
3
+ size 15984
rng_state_6.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45fdffda57fda4a555da7a5de6fc6ec7324e0dae048b92519af6c4f6a1bc7412
3
+ size 15984
rng_state_7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62fb2c13e63aba83c4505fae1639f79a33853d8f1bebe20cecb73bf53c8e7c46
3
+ size 15984
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa94fc7bb1a263c2faa29424b1671bf14bbc711dc42c3829a24e96ea64ad909b
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|im_start|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ }
10
+ ],
11
+ "bos_token": {
12
+ "content": "<|begin_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "eos_token": {
19
+ "content": "<|im_end|>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "pad_token": {
26
+ "content": "<|finetune_right_pad_id|>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ }
32
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,2068 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "additional_special_tokens": [
2053
+ "<|im_start|>"
2054
+ ],
2055
+ "bos_token": "<|begin_of_text|>",
2056
+ "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\n' }}{% endif %}{% endfor %}",
2057
+ "clean_up_tokenization_spaces": true,
2058
+ "eos_token": "<|im_end|>",
2059
+ "model_input_names": [
2060
+ "input_ids",
2061
+ "attention_mask"
2062
+ ],
2063
+ "model_max_length": 131072,
2064
+ "pad_token": "<|finetune_right_pad_id|>",
2065
+ "padding_side": "right",
2066
+ "split_special_tokens": false,
2067
+ "tokenizer_class": "PreTrainedTokenizerFast"
2068
+ }
trainer_state.json ADDED
@@ -0,0 +1,1613 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.986206896551724,
5
+ "eval_steps": 16,
6
+ "global_step": 114,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.017422867513611617,
13
+ "grad_norm": 0.39681947231292725,
14
+ "kl": 0.0,
15
+ "learning_rate": 2.5e-06,
16
+ "logps/chosen": -11.77645784980106,
17
+ "logps/rejected": -10.591483425911125,
18
+ "loss": 0.5,
19
+ "rewards/chosen": 0.0,
20
+ "rewards/margins": 0.0,
21
+ "rewards/rejected": 0.0,
22
+ "step": 1
23
+ },
24
+ {
25
+ "epoch": 0.03484573502722323,
26
+ "grad_norm": 0.1452127993106842,
27
+ "kl": 0.0,
28
+ "learning_rate": 5e-06,
29
+ "logps/chosen": -11.32990430748981,
30
+ "logps/rejected": -10.54532470703125,
31
+ "loss": 0.5,
32
+ "rewards/chosen": 0.0,
33
+ "rewards/margins": 0.0,
34
+ "rewards/rejected": 0.0,
35
+ "step": 2
36
+ },
37
+ {
38
+ "epoch": 0.052268602540834846,
39
+ "grad_norm": 0.3266962170600891,
40
+ "kl": 0.0029318034648895264,
41
+ "learning_rate": 4.955357142857144e-06,
42
+ "logps/chosen": -11.723511402027027,
43
+ "logps/rejected": -10.767559722440327,
44
+ "loss": 0.5049,
45
+ "rewards/chosen": -0.000146248413098825,
46
+ "rewards/margins": -0.00010965315489224665,
47
+ "rewards/rejected": -3.6595258206578356e-05,
48
+ "step": 3
49
+ },
50
+ {
51
+ "epoch": 0.06969147005444647,
52
+ "grad_norm": 0.222149059176445,
53
+ "kl": 0.0028855118434876204,
54
+ "learning_rate": 4.910714285714286e-06,
55
+ "logps/chosen": -11.060244668496622,
56
+ "logps/rejected": -10.751804677685302,
57
+ "loss": 0.5038,
58
+ "rewards/chosen": -6.2011333333479394e-06,
59
+ "rewards/margins": 0.0002193756961875533,
60
+ "rewards/rejected": -0.00022557682952090125,
61
+ "step": 4
62
+ },
63
+ {
64
+ "epoch": 0.08711433756805807,
65
+ "grad_norm": 0.23216503858566284,
66
+ "kl": 0.003043340751901269,
67
+ "learning_rate": 4.866071428571429e-06,
68
+ "logps/chosen": -11.470826369065504,
69
+ "logps/rejected": -10.402360395951705,
70
+ "loss": 0.5049,
71
+ "rewards/chosen": -6.513710384472058e-05,
72
+ "rewards/margins": -2.0336450510690883e-05,
73
+ "rewards/rejected": -4.48006533340297e-05,
74
+ "step": 5
75
+ },
76
+ {
77
+ "epoch": 0.10453720508166969,
78
+ "grad_norm": 0.2607983946800232,
79
+ "kl": 0.0025751441717147827,
80
+ "learning_rate": 4.821428571428572e-06,
81
+ "logps/chosen": -11.465345632399025,
82
+ "logps/rejected": -10.64196449037286,
83
+ "loss": 0.5036,
84
+ "rewards/chosen": 0.00024762971736594494,
85
+ "rewards/margins": 0.0002127551913608797,
86
+ "rewards/rejected": 3.4874526005065234e-05,
87
+ "step": 6
88
+ },
89
+ {
90
+ "epoch": 0.12196007259528131,
91
+ "grad_norm": 0.335457444190979,
92
+ "kl": 0.0026024316903203726,
93
+ "learning_rate": 4.776785714285715e-06,
94
+ "logps/chosen": -11.233088825579573,
95
+ "logps/rejected": -10.439390931995257,
96
+ "loss": 0.5047,
97
+ "rewards/chosen": -1.1002241089977418e-05,
98
+ "rewards/margins": 5.897991155423426e-05,
99
+ "rewards/rejected": -6.998215264421168e-05,
100
+ "step": 7
101
+ },
102
+ {
103
+ "epoch": 0.13938294010889293,
104
+ "grad_norm": 0.21088895201683044,
105
+ "kl": 0.004203550051897764,
106
+ "learning_rate": 4.732142857142857e-06,
107
+ "logps/chosen": -11.42248280843099,
108
+ "logps/rejected": -10.589916229248047,
109
+ "loss": 0.5049,
110
+ "rewards/chosen": -0.00014668223836148778,
111
+ "rewards/margins": 8.747742200891179e-05,
112
+ "rewards/rejected": -0.00023415966037039956,
113
+ "step": 8
114
+ },
115
+ {
116
+ "epoch": 0.15680580762250454,
117
+ "grad_norm": 0.2334163337945938,
118
+ "kl": 0.0023759554605931044,
119
+ "learning_rate": 4.6875000000000004e-06,
120
+ "logps/chosen": -11.515217052940232,
121
+ "logps/rejected": -10.479249335216029,
122
+ "loss": 0.5047,
123
+ "rewards/chosen": 1.3712330321496433e-05,
124
+ "rewards/margins": 0.00026004273796865194,
125
+ "rewards/rejected": -0.0002463304076471555,
126
+ "step": 9
127
+ },
128
+ {
129
+ "epoch": 0.17422867513611615,
130
+ "grad_norm": 0.2604079246520996,
131
+ "kl": 0.002872834214940667,
132
+ "learning_rate": 4.642857142857144e-06,
133
+ "logps/chosen": -11.413588686342592,
134
+ "logps/rejected": -10.579748568784435,
135
+ "loss": 0.5047,
136
+ "rewards/chosen": -1.3620075252321032e-05,
137
+ "rewards/margins": 0.00010424906420423088,
138
+ "rewards/rejected": -0.00011786913945655192,
139
+ "step": 10
140
+ },
141
+ {
142
+ "epoch": 0.19165154264972778,
143
+ "grad_norm": 0.2593174874782562,
144
+ "kl": 0.0022250190377235413,
145
+ "learning_rate": 4.5982142857142854e-06,
146
+ "logps/chosen": -11.424675119011056,
147
+ "logps/rejected": -10.487614428237535,
148
+ "loss": 0.5044,
149
+ "rewards/chosen": 0.00014462312843641426,
150
+ "rewards/margins": 0.0003136567206988408,
151
+ "rewards/rejected": -0.00016903359226242657,
152
+ "step": 11
153
+ },
154
+ {
155
+ "epoch": 0.20907441016333939,
156
+ "grad_norm": 0.1917509138584137,
157
+ "kl": 0.0026314922142773867,
158
+ "learning_rate": 4.553571428571429e-06,
159
+ "logps/chosen": -11.320460956057007,
160
+ "logps/rejected": -10.401315122928674,
161
+ "loss": 0.5045,
162
+ "rewards/chosen": 0.00016278723993663833,
163
+ "rewards/margins": 0.0006349250786245901,
164
+ "rewards/rejected": -0.0004721378386879517,
165
+ "step": 12
166
+ },
167
+ {
168
+ "epoch": 0.226497277676951,
169
+ "grad_norm": 0.2281549721956253,
170
+ "kl": 0.0019408013904467225,
171
+ "learning_rate": 4.508928571428572e-06,
172
+ "logps/chosen": -11.184846626695736,
173
+ "logps/rejected": -10.86145371965223,
174
+ "loss": 0.5041,
175
+ "rewards/chosen": 0.00017400297699664605,
176
+ "rewards/margins": 0.0004404290903305609,
177
+ "rewards/rejected": -0.00026642611333391484,
178
+ "step": 13
179
+ },
180
+ {
181
+ "epoch": 0.24392014519056263,
182
+ "grad_norm": 0.29345858097076416,
183
+ "kl": 0.0032534776255488396,
184
+ "learning_rate": 4.464285714285715e-06,
185
+ "logps/chosen": -11.328454192120928,
186
+ "logps/rejected": -10.352222804454607,
187
+ "loss": 0.5055,
188
+ "rewards/chosen": -0.00023024088532703563,
189
+ "rewards/margins": 0.00022275829169079655,
190
+ "rewards/rejected": -0.0004529991770178322,
191
+ "step": 14
192
+ },
193
+ {
194
+ "epoch": 0.2613430127041742,
195
+ "grad_norm": 0.20449300110340118,
196
+ "kl": 0.003026653779670596,
197
+ "learning_rate": 4.419642857142857e-06,
198
+ "logps/chosen": -11.203996222636421,
199
+ "logps/rejected": -10.722607944100936,
200
+ "loss": 0.5043,
201
+ "rewards/chosen": 0.00018860261679300803,
202
+ "rewards/margins": 0.0004592195771910241,
203
+ "rewards/rejected": -0.0002706169603980161,
204
+ "step": 15
205
+ },
206
+ {
207
+ "epoch": 0.27876588021778587,
208
+ "grad_norm": 0.201906219124794,
209
+ "kl": 0.002389234723523259,
210
+ "learning_rate": 4.3750000000000005e-06,
211
+ "logps/chosen": -11.154755261479592,
212
+ "logps/rejected": -10.722290688372674,
213
+ "loss": 0.5042,
214
+ "rewards/chosen": 0.00029305163390782414,
215
+ "rewards/margins": 0.0007897253288582932,
216
+ "rewards/rejected": -0.000496673694950469,
217
+ "step": 16
218
+ },
219
+ {
220
+ "epoch": 0.27876588021778587,
221
+ "eval_kl": 0.002219570567831397,
222
+ "eval_logps/chosen": -11.288407461983818,
223
+ "eval_logps/rejected": -10.652853829520089,
224
+ "eval_loss": 0.5038086175918579,
225
+ "eval_rewards/chosen": 0.0004127062524535826,
226
+ "eval_rewards/margins": 0.0008178721514663526,
227
+ "eval_rewards/rejected": -0.00040516589901276996,
228
+ "eval_runtime": 41.7888,
229
+ "eval_samples_per_second": 10.673,
230
+ "eval_steps_per_second": 0.67,
231
+ "step": 16
232
+ },
233
+ {
234
+ "epoch": 0.2961887477313975,
235
+ "grad_norm": 0.2981337308883667,
236
+ "kl": 0.0040084668435156345,
237
+ "learning_rate": 4.330357142857143e-06,
238
+ "logps/chosen": -11.60596080662049,
239
+ "logps/rejected": -10.618717876233553,
240
+ "loss": 0.5046,
241
+ "rewards/chosen": 0.00017366750338642867,
242
+ "rewards/margins": 0.0006427841346935287,
243
+ "rewards/rejected": -0.0004691166313071,
244
+ "step": 17
245
+ },
246
+ {
247
+ "epoch": 0.3136116152450091,
248
+ "grad_norm": 0.1905021220445633,
249
+ "kl": 0.0029678388964384794,
250
+ "learning_rate": 4.2857142857142855e-06,
251
+ "logps/chosen": -11.358947906876567,
252
+ "logps/rejected": -10.434524660188009,
253
+ "loss": 0.5048,
254
+ "rewards/chosen": 2.532637675752616e-05,
255
+ "rewards/margins": 0.0007196114555040427,
256
+ "rewards/rejected": -0.0006942850787465166,
257
+ "step": 18
258
+ },
259
+ {
260
+ "epoch": 0.3310344827586207,
261
+ "grad_norm": 0.21423697471618652,
262
+ "kl": 0.002790730679407716,
263
+ "learning_rate": 4.241071428571429e-06,
264
+ "logps/chosen": -11.554482736895162,
265
+ "logps/rejected": -11.022931956281566,
266
+ "loss": 0.504,
267
+ "rewards/chosen": 0.00010277342892462207,
268
+ "rewards/margins": 0.0007622132545750395,
269
+ "rewards/rejected": -0.0006594398256504174,
270
+ "step": 19
271
+ },
272
+ {
273
+ "epoch": 0.3484573502722323,
274
+ "grad_norm": 0.19702628254890442,
275
+ "kl": 0.002327132970094681,
276
+ "learning_rate": 4.196428571428572e-06,
277
+ "logps/chosen": -11.411150614420572,
278
+ "logps/rejected": -10.28190549214681,
279
+ "loss": 0.504,
280
+ "rewards/chosen": 0.000137356905421863,
281
+ "rewards/margins": 0.0005323387255581716,
282
+ "rewards/rejected": -0.00039498182013630867,
283
+ "step": 20
284
+ },
285
+ {
286
+ "epoch": 0.3658802177858439,
287
+ "grad_norm": 0.20904229581356049,
288
+ "kl": 0.002573903650045395,
289
+ "learning_rate": 4.151785714285715e-06,
290
+ "logps/chosen": -11.281766930404974,
291
+ "logps/rejected": -10.511914841672207,
292
+ "loss": 0.504,
293
+ "rewards/chosen": 0.00020978350800519087,
294
+ "rewards/margins": 0.0008185515050823616,
295
+ "rewards/rejected": -0.0006087679970771708,
296
+ "step": 21
297
+ },
298
+ {
299
+ "epoch": 0.38330308529945556,
300
+ "grad_norm": 0.19066323339939117,
301
+ "kl": 0.004084563348442316,
302
+ "learning_rate": 4.107142857142857e-06,
303
+ "logps/chosen": -11.57584678589191,
304
+ "logps/rejected": -11.04019266504156,
305
+ "loss": 0.5042,
306
+ "rewards/chosen": 0.00028499441137364435,
307
+ "rewards/margins": 0.0007805728857745476,
308
+ "rewards/rejected": -0.0004955784744009032,
309
+ "step": 22
310
+ },
311
+ {
312
+ "epoch": 0.40072595281306717,
313
+ "grad_norm": 0.21532228589057922,
314
+ "kl": 0.0018439519917592406,
315
+ "learning_rate": 4.0625000000000005e-06,
316
+ "logps/chosen": -11.395969251063482,
317
+ "logps/rejected": -10.348430416126943,
318
+ "loss": 0.5039,
319
+ "rewards/chosen": 0.0002833760065558069,
320
+ "rewards/margins": 0.000828726542101749,
321
+ "rewards/rejected": -0.0005453505355459421,
322
+ "step": 23
323
+ },
324
+ {
325
+ "epoch": 0.41814882032667877,
326
+ "grad_norm": 0.1852329671382904,
327
+ "kl": 0.002771291183307767,
328
+ "learning_rate": 4.017857142857143e-06,
329
+ "logps/chosen": -11.074297150088029,
330
+ "logps/rejected": -10.626986228813559,
331
+ "loss": 0.5035,
332
+ "rewards/chosen": 0.00041746350241379,
333
+ "rewards/margins": 0.0010044164534086372,
334
+ "rewards/rejected": -0.0005869529509948472,
335
+ "step": 24
336
+ },
337
+ {
338
+ "epoch": 0.4355716878402904,
339
+ "grad_norm": 0.2030268907546997,
340
+ "kl": 0.004407358821481466,
341
+ "learning_rate": 3.9732142857142855e-06,
342
+ "logps/chosen": -11.303015870474727,
343
+ "logps/rejected": -10.537113018889926,
344
+ "loss": 0.5033,
345
+ "rewards/chosen": 0.000330610088800472,
346
+ "rewards/margins": 0.0013877044688375805,
347
+ "rewards/rejected": -0.0010570943800371085,
348
+ "step": 25
349
+ },
350
+ {
351
+ "epoch": 0.452994555353902,
352
+ "grad_norm": 0.330771803855896,
353
+ "kl": 0.0028855446726083755,
354
+ "learning_rate": 3.928571428571429e-06,
355
+ "logps/chosen": -11.326861509342784,
356
+ "logps/rejected": -10.294227359169408,
357
+ "loss": 0.5044,
358
+ "rewards/chosen": 0.0002357424380853004,
359
+ "rewards/margins": 0.0008208984113942651,
360
+ "rewards/rejected": -0.0005851559733089647,
361
+ "step": 26
362
+ },
363
+ {
364
+ "epoch": 0.4704174228675136,
365
+ "grad_norm": 0.204763263463974,
366
+ "kl": 0.0029878586065024137,
367
+ "learning_rate": 3.883928571428572e-06,
368
+ "logps/chosen": -11.238988330696202,
369
+ "logps/rejected": -10.748736097729557,
370
+ "loss": 0.5038,
371
+ "rewards/chosen": 0.0004333936338183246,
372
+ "rewards/margins": 0.0012179940220870076,
373
+ "rewards/rejected": -0.0007846003882686829,
374
+ "step": 27
375
+ },
376
+ {
377
+ "epoch": 0.48784029038112525,
378
+ "grad_norm": 0.4104137420654297,
379
+ "kl": 0.002435252070426941,
380
+ "learning_rate": 3.839285714285715e-06,
381
+ "logps/chosen": -11.65949259124677,
382
+ "logps/rejected": -10.41943679769521,
383
+ "loss": 0.505,
384
+ "rewards/chosen": -4.84786946952189e-05,
385
+ "rewards/margins": 0.0007131273978328765,
386
+ "rewards/rejected": -0.0007616060925280954,
387
+ "step": 28
388
+ },
389
+ {
390
+ "epoch": 0.5052631578947369,
391
+ "grad_norm": 0.1900724321603775,
392
+ "kl": 0.003689997596666217,
393
+ "learning_rate": 3.794642857142857e-06,
394
+ "logps/chosen": -11.369253954475308,
395
+ "logps/rejected": -10.650356996814738,
396
+ "loss": 0.5035,
397
+ "rewards/chosen": 0.0005172402034571141,
398
+ "rewards/margins": 0.0012426704372049484,
399
+ "rewards/rejected": -0.0007254302337478343,
400
+ "step": 29
401
+ },
402
+ {
403
+ "epoch": 0.5226860254083484,
404
+ "grad_norm": 0.25149452686309814,
405
+ "kl": 0.003089333651587367,
406
+ "learning_rate": 3.7500000000000005e-06,
407
+ "logps/chosen": -11.706775306138677,
408
+ "logps/rejected": -10.319467447916667,
409
+ "loss": 0.5048,
410
+ "rewards/chosen": 0.00012126840821659293,
411
+ "rewards/margins": 0.0005743338433082473,
412
+ "rewards/rejected": -0.00045306543509165444,
413
+ "step": 30
414
+ },
415
+ {
416
+ "epoch": 0.5401088929219601,
417
+ "grad_norm": 0.2375558316707611,
418
+ "kl": 0.0021258096676319838,
419
+ "learning_rate": 3.7053571428571434e-06,
420
+ "logps/chosen": -11.040724951044387,
421
+ "logps/rejected": -10.158553799715909,
422
+ "loss": 0.504,
423
+ "rewards/chosen": 0.00032178575158430455,
424
+ "rewards/margins": 0.001046311172281009,
425
+ "rewards/rejected": -0.0007245254206967044,
426
+ "step": 31
427
+ },
428
+ {
429
+ "epoch": 0.5575317604355717,
430
+ "grad_norm": 0.20534147322177887,
431
+ "kl": 0.002767733531072736,
432
+ "learning_rate": 3.660714285714286e-06,
433
+ "logps/chosen": -11.517271468581537,
434
+ "logps/rejected": -10.606380126338161,
435
+ "loss": 0.5037,
436
+ "rewards/chosen": 0.0005935063821607523,
437
+ "rewards/margins": 0.0013072239592998884,
438
+ "rewards/rejected": -0.0007137175771391362,
439
+ "step": 32
440
+ },
441
+ {
442
+ "epoch": 0.5575317604355717,
443
+ "eval_kl": 0.0013082654913887382,
444
+ "eval_logps/chosen": -11.286455426897321,
445
+ "eval_logps/rejected": -10.656499590192523,
446
+ "eval_loss": 0.5032945275306702,
447
+ "eval_rewards/chosen": 0.0006079860031604767,
448
+ "eval_rewards/margins": 0.001377601841730731,
449
+ "eval_rewards/rejected": -0.0007696158385702542,
450
+ "eval_runtime": 41.5226,
451
+ "eval_samples_per_second": 10.741,
452
+ "eval_steps_per_second": 0.674,
453
+ "step": 32
454
+ },
455
+ {
456
+ "epoch": 0.5749546279491833,
457
+ "grad_norm": 0.240458145737648,
458
+ "kl": 0.002010853262618184,
459
+ "learning_rate": 3.616071428571429e-06,
460
+ "logps/chosen": -11.25503524547906,
461
+ "logps/rejected": -11.051669034090908,
462
+ "loss": 0.5043,
463
+ "rewards/chosen": 0.00019917678711983152,
464
+ "rewards/margins": 0.0007490985231613238,
465
+ "rewards/rejected": -0.0005499217360414923,
466
+ "step": 33
467
+ },
468
+ {
469
+ "epoch": 0.592377495462795,
470
+ "grad_norm": 0.18933577835559845,
471
+ "kl": 0.0021181467454880476,
472
+ "learning_rate": 3.5714285714285718e-06,
473
+ "logps/chosen": -11.664008105974741,
474
+ "logps/rejected": -10.828131391115837,
475
+ "loss": 0.5032,
476
+ "rewards/chosen": 0.0005863340947912147,
477
+ "rewards/margins": 0.0013070002798906317,
478
+ "rewards/rejected": -0.000720666185099417,
479
+ "step": 34
480
+ },
481
+ {
482
+ "epoch": 0.6098003629764065,
483
+ "grad_norm": 0.20784388482570648,
484
+ "kl": 0.002850498305633664,
485
+ "learning_rate": 3.5267857142857147e-06,
486
+ "logps/chosen": -11.464662464007452,
487
+ "logps/rejected": -10.13366056743421,
488
+ "loss": 0.5041,
489
+ "rewards/chosen": 0.00017015952970277326,
490
+ "rewards/margins": 0.0008830348158433109,
491
+ "rewards/rejected": -0.0007128752861405376,
492
+ "step": 35
493
+ },
494
+ {
495
+ "epoch": 0.6272232304900182,
496
+ "grad_norm": 0.1830260157585144,
497
+ "kl": 0.003351332386955619,
498
+ "learning_rate": 3.482142857142857e-06,
499
+ "logps/chosen": -11.203702368776113,
500
+ "logps/rejected": -10.977577265433986,
501
+ "loss": 0.5036,
502
+ "rewards/chosen": 0.00040133928356064395,
503
+ "rewards/margins": 0.0009519243287689104,
504
+ "rewards/rejected": -0.0005505850452082664,
505
+ "step": 36
506
+ },
507
+ {
508
+ "epoch": 0.6446460980036298,
509
+ "grad_norm": 0.18368099629878998,
510
+ "kl": 0.0037287927698343992,
511
+ "learning_rate": 3.4375e-06,
512
+ "logps/chosen": -11.507929849361188,
513
+ "logps/rejected": -10.265622594673646,
514
+ "loss": 0.503,
515
+ "rewards/chosen": 0.00047660240316917883,
516
+ "rewards/margins": 0.0012168469473675392,
517
+ "rewards/rejected": -0.0007402445441983603,
518
+ "step": 37
519
+ },
520
+ {
521
+ "epoch": 0.6620689655172414,
522
+ "grad_norm": 0.22299793362617493,
523
+ "kl": 0.0025776519905775785,
524
+ "learning_rate": 3.3928571428571435e-06,
525
+ "logps/chosen": -11.776427912833121,
526
+ "logps/rejected": -10.537473627590241,
527
+ "loss": 0.5041,
528
+ "rewards/chosen": 0.00029345284107372844,
529
+ "rewards/margins": 0.0009656724311435042,
530
+ "rewards/rejected": -0.0006722195900697759,
531
+ "step": 38
532
+ },
533
+ {
534
+ "epoch": 0.679491833030853,
535
+ "grad_norm": 0.21307651698589325,
536
+ "kl": 0.0029651224613189697,
537
+ "learning_rate": 3.3482142857142855e-06,
538
+ "logps/chosen": -11.337782663316583,
539
+ "logps/rejected": -10.489964500633446,
540
+ "loss": 0.5041,
541
+ "rewards/chosen": 0.000353607026176836,
542
+ "rewards/margins": 0.0009334429436754503,
543
+ "rewards/rejected": -0.0005798359174986143,
544
+ "step": 39
545
+ },
546
+ {
547
+ "epoch": 0.6969147005444646,
548
+ "grad_norm": 0.21936196088790894,
549
+ "kl": 0.0019360833102837205,
550
+ "learning_rate": 3.303571428571429e-06,
551
+ "logps/chosen": -12.052929194286616,
552
+ "logps/rejected": -10.637656591271842,
553
+ "loss": 0.5044,
554
+ "rewards/chosen": 0.000453127905575916,
555
+ "rewards/margins": 0.0010775220099412956,
556
+ "rewards/rejected": -0.0006243941043653796,
557
+ "step": 40
558
+ },
559
+ {
560
+ "epoch": 0.7143375680580762,
561
+ "grad_norm": 0.5484824180603027,
562
+ "kl": 0.0032773923594504595,
563
+ "learning_rate": 3.258928571428572e-06,
564
+ "logps/chosen": -11.568930269491792,
565
+ "logps/rejected": -10.71394266108031,
566
+ "loss": 0.5054,
567
+ "rewards/chosen": 5.686828264533871e-05,
568
+ "rewards/margins": 0.0006258111605199182,
569
+ "rewards/rejected": -0.0005689428778745795,
570
+ "step": 41
571
+ },
572
+ {
573
+ "epoch": 0.7317604355716878,
574
+ "grad_norm": 0.20393657684326172,
575
+ "kl": 0.003910336643457413,
576
+ "learning_rate": 3.2142857142857147e-06,
577
+ "logps/chosen": -11.504363593319558,
578
+ "logps/rejected": -10.101014539930556,
579
+ "loss": 0.5036,
580
+ "rewards/chosen": 0.00029671770974624257,
581
+ "rewards/margins": 0.001082045991996541,
582
+ "rewards/rejected": -0.0007853282822502984,
583
+ "step": 42
584
+ },
585
+ {
586
+ "epoch": 0.7491833030852995,
587
+ "grad_norm": 0.16519714891910553,
588
+ "kl": 0.003650219878181815,
589
+ "learning_rate": 3.1696428571428572e-06,
590
+ "logps/chosen": -10.816071234809028,
591
+ "logps/rejected": -10.322287166819853,
592
+ "loss": 0.503,
593
+ "rewards/chosen": 0.0007183290190166897,
594
+ "rewards/margins": 0.0015814549685303683,
595
+ "rewards/rejected": -0.0008631259495136785,
596
+ "step": 43
597
+ },
598
+ {
599
+ "epoch": 0.7666061705989111,
600
+ "grad_norm": 0.20090065896511078,
601
+ "kl": 0.002337512793019414,
602
+ "learning_rate": 3.125e-06,
603
+ "logps/chosen": -11.918630044291339,
604
+ "logps/rejected": -11.223259346737725,
605
+ "loss": 0.5041,
606
+ "rewards/chosen": 0.00022355469036602912,
607
+ "rewards/margins": 0.0007338886578213189,
608
+ "rewards/rejected": -0.0005103339674552898,
609
+ "step": 44
610
+ },
611
+ {
612
+ "epoch": 0.7840290381125227,
613
+ "grad_norm": 0.23820927739143372,
614
+ "kl": 0.0014156276592984796,
615
+ "learning_rate": 3.080357142857143e-06,
616
+ "logps/chosen": -11.657449557086615,
617
+ "logps/rejected": -10.76135790132429,
618
+ "loss": 0.5037,
619
+ "rewards/chosen": 0.0006081545994350604,
620
+ "rewards/margins": 0.0009453997203017225,
621
+ "rewards/rejected": -0.0003372451208666622,
622
+ "step": 45
623
+ },
624
+ {
625
+ "epoch": 0.8014519056261343,
626
+ "grad_norm": 0.2038673311471939,
627
+ "kl": 0.0020267742220312357,
628
+ "learning_rate": 3.0357142857142856e-06,
629
+ "logps/chosen": -11.508970748546512,
630
+ "logps/rejected": -10.532100327058727,
631
+ "loss": 0.5043,
632
+ "rewards/chosen": 0.0003054198599600977,
633
+ "rewards/margins": 0.0006779901515518521,
634
+ "rewards/rejected": -0.0003725702915917544,
635
+ "step": 46
636
+ },
637
+ {
638
+ "epoch": 0.8188747731397459,
639
+ "grad_norm": 0.2023131251335144,
640
+ "kl": 0.0036333007737994194,
641
+ "learning_rate": 2.991071428571429e-06,
642
+ "logps/chosen": -11.018499706769436,
643
+ "logps/rejected": -10.779378461234177,
644
+ "loss": 0.5039,
645
+ "rewards/chosen": 0.00048798394586701177,
646
+ "rewards/margins": 0.0010197794913363682,
647
+ "rewards/rejected": -0.0005317955454693565,
648
+ "step": 47
649
+ },
650
+ {
651
+ "epoch": 0.8362976406533575,
652
+ "grad_norm": 0.19009532034397125,
653
+ "kl": 0.0020073249470442533,
654
+ "learning_rate": 2.946428571428572e-06,
655
+ "logps/chosen": -11.3989532127809,
656
+ "logps/rejected": -11.23740068454187,
657
+ "loss": 0.5035,
658
+ "rewards/chosen": 0.0002772415035896087,
659
+ "rewards/margins": 0.0007655857580138798,
660
+ "rewards/rejected": -0.0004883442544242711,
661
+ "step": 48
662
+ },
663
+ {
664
+ "epoch": 0.8362976406533575,
665
+ "eval_kl": 0.001558297430165112,
666
+ "eval_logps/chosen": -11.289903913225446,
667
+ "eval_logps/rejected": -10.654574802943639,
668
+ "eval_loss": 0.5040844082832336,
669
+ "eval_rewards/chosen": 0.00026316663050757986,
670
+ "eval_rewards/margins": 0.0008403176741142358,
671
+ "eval_rewards/rejected": -0.000577151043606656,
672
+ "eval_runtime": 41.5721,
673
+ "eval_samples_per_second": 10.728,
674
+ "eval_steps_per_second": 0.674,
675
+ "step": 48
676
+ },
677
+ {
678
+ "epoch": 0.8537205081669691,
679
+ "grad_norm": 0.2040846198797226,
680
+ "kl": 0.0028173942118883133,
681
+ "learning_rate": 2.9017857142857148e-06,
682
+ "logps/chosen": -11.502028847760695,
683
+ "logps/rejected": -9.920858160493337,
684
+ "loss": 0.5037,
685
+ "rewards/chosen": 0.0003798981720113499,
686
+ "rewards/margins": 0.001099527059744577,
687
+ "rewards/rejected": -0.0007196288877332271,
688
+ "step": 49
689
+ },
690
+ {
691
+ "epoch": 0.8711433756805808,
692
+ "grad_norm": 0.46055036783218384,
693
+ "kl": 0.001712739816866815,
694
+ "learning_rate": 2.8571428571428573e-06,
695
+ "logps/chosen": -11.66295957325691,
696
+ "logps/rejected": -10.606267155827704,
697
+ "loss": 0.5046,
698
+ "rewards/chosen": 8.328470527826242e-05,
699
+ "rewards/margins": 0.0005694089115119315,
700
+ "rewards/rejected": -0.000486124206233669,
701
+ "step": 50
702
+ },
703
+ {
704
+ "epoch": 0.8885662431941924,
705
+ "grad_norm": 0.2116948515176773,
706
+ "kl": 0.0014734516153112054,
707
+ "learning_rate": 2.8125e-06,
708
+ "logps/chosen": -11.087164900249377,
709
+ "logps/rejected": -10.773697606224456,
710
+ "loss": 0.5046,
711
+ "rewards/chosen": 0.0002402601545291054,
712
+ "rewards/margins": 0.0008381397699308074,
713
+ "rewards/rejected": -0.000597879615401702,
714
+ "step": 51
715
+ },
716
+ {
717
+ "epoch": 0.905989110707804,
718
+ "grad_norm": 0.2204010933637619,
719
+ "kl": 0.0023574617225676775,
720
+ "learning_rate": 2.767857142857143e-06,
721
+ "logps/chosen": -11.274248798076924,
722
+ "logps/rejected": -10.153245391038359,
723
+ "loss": 0.5032,
724
+ "rewards/chosen": 0.0005002290392533327,
725
+ "rewards/margins": 0.0011188293800006614,
726
+ "rewards/rejected": -0.0006186003407473286,
727
+ "step": 52
728
+ },
729
+ {
730
+ "epoch": 0.9234119782214156,
731
+ "grad_norm": 0.22388231754302979,
732
+ "kl": 0.002206307603046298,
733
+ "learning_rate": 2.7232142857142856e-06,
734
+ "logps/chosen": -11.911312705592104,
735
+ "logps/rejected": -10.432602086018042,
736
+ "loss": 0.5041,
737
+ "rewards/chosen": 0.0004630535840988159,
738
+ "rewards/margins": 0.0009620043727540478,
739
+ "rewards/rejected": -0.0004989507886552319,
740
+ "step": 53
741
+ },
742
+ {
743
+ "epoch": 0.9408348457350272,
744
+ "grad_norm": 0.20113378763198853,
745
+ "kl": 0.0021755837369710207,
746
+ "learning_rate": 2.6785714285714285e-06,
747
+ "logps/chosen": -11.37064292594178,
748
+ "logps/rejected": -10.506611788539082,
749
+ "loss": 0.5036,
750
+ "rewards/chosen": 0.00027320436010622,
751
+ "rewards/margins": 0.0005519093562507254,
752
+ "rewards/rejected": -0.0002787049961445054,
753
+ "step": 54
754
+ },
755
+ {
756
+ "epoch": 0.9582577132486388,
757
+ "grad_norm": 0.7052344083786011,
758
+ "kl": 0.002290615811944008,
759
+ "learning_rate": 2.633928571428572e-06,
760
+ "logps/chosen": -11.785455354221204,
761
+ "logps/rejected": -10.28837688228627,
762
+ "loss": 0.5038,
763
+ "rewards/chosen": 0.0004812158371141444,
764
+ "rewards/margins": 0.0010049399622622454,
765
+ "rewards/rejected": -0.0005237241251481011,
766
+ "step": 55
767
+ },
768
+ {
769
+ "epoch": 0.9756805807622505,
770
+ "grad_norm": 0.18455247581005096,
771
+ "kl": 0.001295599271543324,
772
+ "learning_rate": 2.5892857142857148e-06,
773
+ "logps/chosen": -11.051934689891581,
774
+ "logps/rejected": -10.790322161735372,
775
+ "loss": 0.5038,
776
+ "rewards/chosen": 0.00037732340243397925,
777
+ "rewards/margins": 0.0009394810824965168,
778
+ "rewards/rejected": -0.0005621576800625375,
779
+ "step": 56
780
+ },
781
+ {
782
+ "epoch": 0.993103448275862,
783
+ "grad_norm": 0.1891961693763733,
784
+ "kl": 0.00294533371925354,
785
+ "learning_rate": 2.5446428571428573e-06,
786
+ "logps/chosen": -11.06938274166127,
787
+ "logps/rejected": -10.141628405186518,
788
+ "loss": 0.5034,
789
+ "rewards/chosen": 0.00042142599357842164,
790
+ "rewards/margins": 0.0006545582687216406,
791
+ "rewards/rejected": -0.0002331322751432189,
792
+ "step": 57
793
+ },
794
+ {
795
+ "epoch": 1.0105263157894737,
796
+ "grad_norm": 0.22368647158145905,
797
+ "kl": 0.002181227086111903,
798
+ "learning_rate": 2.5e-06,
799
+ "logps/chosen": -11.29225919699367,
800
+ "logps/rejected": -10.528809902815013,
801
+ "loss": 0.5036,
802
+ "rewards/chosen": 0.0002977928406075586,
803
+ "rewards/margins": 0.0008452181976182237,
804
+ "rewards/rejected": -0.000547425357010665,
805
+ "step": 58
806
+ },
807
+ {
808
+ "epoch": 1.0279491833030854,
809
+ "grad_norm": 0.19894687831401825,
810
+ "kl": 0.0022480275947600603,
811
+ "learning_rate": 2.455357142857143e-06,
812
+ "logps/chosen": -11.208153912401574,
813
+ "logps/rejected": -10.815308563468992,
814
+ "loss": 0.5037,
815
+ "rewards/chosen": 0.00028297573015132913,
816
+ "rewards/margins": 0.0009500956342332799,
817
+ "rewards/rejected": -0.0006671199040819508,
818
+ "step": 59
819
+ },
820
+ {
821
+ "epoch": 1.0453720508166968,
822
+ "grad_norm": 0.19452357292175293,
823
+ "kl": 0.003947921562939882,
824
+ "learning_rate": 2.410714285714286e-06,
825
+ "logps/chosen": -11.397494791666666,
826
+ "logps/rejected": -10.136647309359097,
827
+ "loss": 0.5036,
828
+ "rewards/chosen": 0.0006445555686950684,
829
+ "rewards/margins": 0.0011657039269842872,
830
+ "rewards/rejected": -0.0005211483582892187,
831
+ "step": 60
832
+ },
833
+ {
834
+ "epoch": 1.0627949183303085,
835
+ "grad_norm": 0.2021968960762024,
836
+ "kl": 0.00338422111235559,
837
+ "learning_rate": 2.3660714285714285e-06,
838
+ "logps/chosen": -11.75505078125,
839
+ "logps/rejected": -10.338195024252544,
840
+ "loss": 0.5035,
841
+ "rewards/chosen": 0.0006066491603851318,
842
+ "rewards/margins": 0.0008883069659614078,
843
+ "rewards/rejected": -0.0002816578055762759,
844
+ "step": 61
845
+ },
846
+ {
847
+ "epoch": 1.0802177858439201,
848
+ "grad_norm": 0.18729077279567719,
849
+ "kl": 0.0022495612502098083,
850
+ "learning_rate": 2.321428571428572e-06,
851
+ "logps/chosen": -11.218356103012242,
852
+ "logps/rejected": -10.509180972450658,
853
+ "loss": 0.5034,
854
+ "rewards/chosen": 0.0004960870005420803,
855
+ "rewards/margins": 0.0008710139801466005,
856
+ "rewards/rejected": -0.0003749269796045203,
857
+ "step": 62
858
+ },
859
+ {
860
+ "epoch": 1.0976406533575318,
861
+ "grad_norm": 0.19914378225803375,
862
+ "kl": 0.003042086260393262,
863
+ "learning_rate": 2.2767857142857144e-06,
864
+ "logps/chosen": -11.236100905012377,
865
+ "logps/rejected": -10.941490760216347,
866
+ "loss": 0.5034,
867
+ "rewards/chosen": 0.0013145432613863803,
868
+ "rewards/margins": 0.0017898373715980775,
869
+ "rewards/rejected": -0.00047529411021169726,
870
+ "step": 63
871
+ },
872
+ {
873
+ "epoch": 1.1150635208711435,
874
+ "grad_norm": 0.19482098519802094,
875
+ "kl": 0.002518598223105073,
876
+ "learning_rate": 2.2321428571428573e-06,
877
+ "logps/chosen": -11.394892939814815,
878
+ "logps/rejected": -10.390007762419872,
879
+ "loss": 0.5037,
880
+ "rewards/chosen": 0.0003466351480080337,
881
+ "rewards/margins": 0.0006846176696153592,
882
+ "rewards/rejected": -0.0003379825216073256,
883
+ "step": 64
884
+ },
885
+ {
886
+ "epoch": 1.1150635208711435,
887
+ "eval_kl": 0.0016980862710624933,
888
+ "eval_logps/chosen": -11.287184579031807,
889
+ "eval_logps/rejected": -10.654030936104911,
890
+ "eval_loss": 0.5034511089324951,
891
+ "eval_rewards/chosen": 0.0005350507396672453,
892
+ "eval_rewards/margins": 0.0010578856537384646,
893
+ "eval_rewards/rejected": -0.0005228349140712193,
894
+ "eval_runtime": 41.5198,
895
+ "eval_samples_per_second": 10.742,
896
+ "eval_steps_per_second": 0.674,
897
+ "step": 64
898
+ },
899
+ {
900
+ "epoch": 1.132486388384755,
901
+ "grad_norm": 0.20668481290340424,
902
+ "kl": 0.003911910578608513,
903
+ "learning_rate": 2.1875000000000002e-06,
904
+ "logps/chosen": -11.54857183807525,
905
+ "logps/rejected": -11.033686736893785,
906
+ "loss": 0.504,
907
+ "rewards/chosen": 0.0006883917608071322,
908
+ "rewards/margins": 0.0012867070528502448,
909
+ "rewards/rejected": -0.0005983152920431127,
910
+ "step": 65
911
+ },
912
+ {
913
+ "epoch": 1.1499092558983666,
914
+ "grad_norm": 0.20961228013038635,
915
+ "kl": 0.0017986433813348413,
916
+ "learning_rate": 2.1428571428571427e-06,
917
+ "logps/chosen": -11.831485829454786,
918
+ "logps/rejected": -10.89035345583546,
919
+ "loss": 0.504,
920
+ "rewards/chosen": 0.0002542631502481217,
921
+ "rewards/margins": 0.0006354290375722992,
922
+ "rewards/rejected": -0.0003811658873241775,
923
+ "step": 66
924
+ },
925
+ {
926
+ "epoch": 1.1673321234119782,
927
+ "grad_norm": 0.19809454679489136,
928
+ "kl": 0.002224177587777376,
929
+ "learning_rate": 2.098214285714286e-06,
930
+ "logps/chosen": -11.331428947029533,
931
+ "logps/rejected": -10.59391437190594,
932
+ "loss": 0.5034,
933
+ "rewards/chosen": 0.0005333201325201727,
934
+ "rewards/margins": 0.001024618166864742,
935
+ "rewards/rejected": -0.0004912980343445693,
936
+ "step": 67
937
+ },
938
+ {
939
+ "epoch": 1.18475499092559,
940
+ "grad_norm": 0.19940558075904846,
941
+ "kl": 0.00197195284999907,
942
+ "learning_rate": 2.0535714285714286e-06,
943
+ "logps/chosen": -11.550331552282016,
944
+ "logps/rejected": -10.52055773651808,
945
+ "loss": 0.503,
946
+ "rewards/chosen": 0.0006965530340937892,
947
+ "rewards/margins": 0.0013385297657675268,
948
+ "rewards/rejected": -0.0006419767316737377,
949
+ "step": 68
950
+ },
951
+ {
952
+ "epoch": 1.2021778584392013,
953
+ "grad_norm": 0.21953897178173065,
954
+ "kl": 0.0020015963818877935,
955
+ "learning_rate": 2.0089285714285715e-06,
956
+ "logps/chosen": -10.969684954573935,
957
+ "logps/rejected": -10.10690514375847,
958
+ "loss": 0.5042,
959
+ "rewards/chosen": 0.0001828334385291078,
960
+ "rewards/margins": 0.0006383278937348235,
961
+ "rewards/rejected": -0.00045549445520571576,
962
+ "step": 69
963
+ },
964
+ {
965
+ "epoch": 1.219600725952813,
966
+ "grad_norm": 0.19710642099380493,
967
+ "kl": 0.00231179385446012,
968
+ "learning_rate": 1.9642857142857144e-06,
969
+ "logps/chosen": -11.595243038467848,
970
+ "logps/rejected": -10.112245387193152,
971
+ "loss": 0.5033,
972
+ "rewards/chosen": 0.00039139722432364314,
973
+ "rewards/margins": 0.0010068912661115128,
974
+ "rewards/rejected": -0.0006154940417878696,
975
+ "step": 70
976
+ },
977
+ {
978
+ "epoch": 1.2370235934664247,
979
+ "grad_norm": 0.1987324059009552,
980
+ "kl": 0.002300393534824252,
981
+ "learning_rate": 1.9196428571428573e-06,
982
+ "logps/chosen": -11.305307889174403,
983
+ "logps/rejected": -10.520050751278772,
984
+ "loss": 0.5035,
985
+ "rewards/chosen": 0.0004280993729750737,
986
+ "rewards/margins": 0.0009470002607156162,
987
+ "rewards/rejected": -0.0005189008877405425,
988
+ "step": 71
989
+ },
990
+ {
991
+ "epoch": 1.2544464609800363,
992
+ "grad_norm": 0.18199442327022552,
993
+ "kl": 0.0023830088321119547,
994
+ "learning_rate": 1.8750000000000003e-06,
995
+ "logps/chosen": -11.361725593834231,
996
+ "logps/rejected": -10.366453233233628,
997
+ "loss": 0.5029,
998
+ "rewards/chosen": 0.000802040341086786,
999
+ "rewards/margins": 0.0015088396506467594,
1000
+ "rewards/rejected": -0.0007067993095599734,
1001
+ "step": 72
1002
+ },
1003
+ {
1004
+ "epoch": 1.271869328493648,
1005
+ "grad_norm": 0.2903735339641571,
1006
+ "kl": 0.0014767992543056607,
1007
+ "learning_rate": 1.830357142857143e-06,
1008
+ "logps/chosen": -11.19476151596653,
1009
+ "logps/rejected": -10.959830972092663,
1010
+ "loss": 0.5034,
1011
+ "rewards/chosen": 0.00034413270937289043,
1012
+ "rewards/margins": 0.0008636754093954977,
1013
+ "rewards/rejected": -0.0005195427000226073,
1014
+ "step": 73
1015
+ },
1016
+ {
1017
+ "epoch": 1.2892921960072594,
1018
+ "grad_norm": 0.20160308480262756,
1019
+ "kl": 0.003358997404575348,
1020
+ "learning_rate": 1.7857142857142859e-06,
1021
+ "logps/chosen": -10.99349352108535,
1022
+ "logps/rejected": -10.71151579269255,
1023
+ "loss": 0.5032,
1024
+ "rewards/chosen": 0.0006134921023922582,
1025
+ "rewards/margins": 0.0010400663268667124,
1026
+ "rewards/rejected": -0.00042657422447445415,
1027
+ "step": 74
1028
+ },
1029
+ {
1030
+ "epoch": 1.306715063520871,
1031
+ "grad_norm": 0.23630282282829285,
1032
+ "kl": 0.0023285781498998404,
1033
+ "learning_rate": 1.7410714285714286e-06,
1034
+ "logps/chosen": -11.506769643439947,
1035
+ "logps/rejected": -10.45025872564935,
1036
+ "loss": 0.5036,
1037
+ "rewards/chosen": 0.0006310967801445147,
1038
+ "rewards/margins": 0.0013577277155657525,
1039
+ "rewards/rejected": -0.0007266309354212377,
1040
+ "step": 75
1041
+ },
1042
+ {
1043
+ "epoch": 1.3241379310344827,
1044
+ "grad_norm": 0.18052582442760468,
1045
+ "kl": 0.0017558973049744964,
1046
+ "learning_rate": 1.6964285714285717e-06,
1047
+ "logps/chosen": -11.271184662723785,
1048
+ "logps/rejected": -10.48470008910809,
1049
+ "loss": 0.5033,
1050
+ "rewards/chosen": 0.0006234512076048595,
1051
+ "rewards/margins": 0.0013483937273518372,
1052
+ "rewards/rejected": -0.0007249425197469777,
1053
+ "step": 76
1054
+ },
1055
+ {
1056
+ "epoch": 1.3415607985480944,
1057
+ "grad_norm": 0.18041782081127167,
1058
+ "kl": 0.0014101862907409668,
1059
+ "learning_rate": 1.6517857142857144e-06,
1060
+ "logps/chosen": -11.356517080872704,
1061
+ "logps/rejected": -10.676619024547804,
1062
+ "loss": 0.5033,
1063
+ "rewards/chosen": 0.0006575664979579255,
1064
+ "rewards/margins": 0.001282264682831324,
1065
+ "rewards/rejected": -0.0006246981848733986,
1066
+ "step": 77
1067
+ },
1068
+ {
1069
+ "epoch": 1.358983666061706,
1070
+ "grad_norm": 0.2689516544342041,
1071
+ "kl": 0.0018190672853961587,
1072
+ "learning_rate": 1.6071428571428574e-06,
1073
+ "logps/chosen": -11.690565026324728,
1074
+ "logps/rejected": -10.228720703125,
1075
+ "loss": 0.5034,
1076
+ "rewards/chosen": 0.0008241140648074772,
1077
+ "rewards/margins": 0.0013455211176820424,
1078
+ "rewards/rejected": -0.0005214070528745652,
1079
+ "step": 78
1080
+ },
1081
+ {
1082
+ "epoch": 1.3764065335753175,
1083
+ "grad_norm": 0.20166873931884766,
1084
+ "kl": 0.0017292723059654236,
1085
+ "learning_rate": 1.5625e-06,
1086
+ "logps/chosen": -11.26230097903481,
1087
+ "logps/rejected": -11.479227756367292,
1088
+ "loss": 0.5034,
1089
+ "rewards/chosen": 0.0006177344654179827,
1090
+ "rewards/margins": 0.0012838053047731855,
1091
+ "rewards/rejected": -0.0006660708393552028,
1092
+ "step": 79
1093
+ },
1094
+ {
1095
+ "epoch": 1.3938294010889292,
1096
+ "grad_norm": 0.19607041776180267,
1097
+ "kl": 0.0031144104432314634,
1098
+ "learning_rate": 1.5178571428571428e-06,
1099
+ "logps/chosen": -11.208266241253181,
1100
+ "logps/rejected": -10.324174479166667,
1101
+ "loss": 0.5036,
1102
+ "rewards/chosen": 0.0007915615883795663,
1103
+ "rewards/margins": 0.0014803941892910246,
1104
+ "rewards/rejected": -0.0006888326009114583,
1105
+ "step": 80
1106
+ },
1107
+ {
1108
+ "epoch": 1.3938294010889292,
1109
+ "eval_kl": 0.0010345944901928306,
1110
+ "eval_logps/chosen": -11.287428719656807,
1111
+ "eval_logps/rejected": -10.653524126325335,
1112
+ "eval_loss": 0.5035938024520874,
1113
+ "eval_rewards/chosen": 0.0005107134514089141,
1114
+ "eval_rewards/margins": 0.0009828850826514618,
1115
+ "eval_rewards/rejected": -0.0004721716312425477,
1116
+ "eval_runtime": 41.5877,
1117
+ "eval_samples_per_second": 10.724,
1118
+ "eval_steps_per_second": 0.673,
1119
+ "step": 80
1120
+ },
1121
+ {
1122
+ "epoch": 1.4112522686025408,
1123
+ "grad_norm": 0.2139582335948944,
1124
+ "kl": 0.0026578225661069155,
1125
+ "learning_rate": 1.473214285714286e-06,
1126
+ "logps/chosen": -11.404391783887467,
1127
+ "logps/rejected": -10.326293621518568,
1128
+ "loss": 0.5037,
1129
+ "rewards/chosen": 0.0004199028701123679,
1130
+ "rewards/margins": 0.0008872187001457688,
1131
+ "rewards/rejected": -0.00046731583003340095,
1132
+ "step": 81
1133
+ },
1134
+ {
1135
+ "epoch": 1.4286751361161525,
1136
+ "grad_norm": 0.3459619879722595,
1137
+ "kl": 0.001983026973903179,
1138
+ "learning_rate": 1.4285714285714286e-06,
1139
+ "logps/chosen": -11.670273977308417,
1140
+ "logps/rejected": -10.357556482263513,
1141
+ "loss": 0.5033,
1142
+ "rewards/chosen": 0.0005598089203762649,
1143
+ "rewards/margins": 0.0007428220220635673,
1144
+ "rewards/rejected": -0.00018301310168730245,
1145
+ "step": 82
1146
+ },
1147
+ {
1148
+ "epoch": 1.4460980036297642,
1149
+ "grad_norm": 0.21906645596027374,
1150
+ "kl": 0.0028725937008857727,
1151
+ "learning_rate": 1.3839285714285715e-06,
1152
+ "logps/chosen": -11.741632576689632,
1153
+ "logps/rejected": -10.43268595062177,
1154
+ "loss": 0.5033,
1155
+ "rewards/chosen": 0.0006233549962832234,
1156
+ "rewards/margins": 0.001042224365689024,
1157
+ "rewards/rejected": -0.0004188693694058007,
1158
+ "step": 83
1159
+ },
1160
+ {
1161
+ "epoch": 1.4635208711433756,
1162
+ "grad_norm": 0.17626065015792847,
1163
+ "kl": 0.00280402391217649,
1164
+ "learning_rate": 1.3392857142857143e-06,
1165
+ "logps/chosen": -11.461028108891753,
1166
+ "logps/rejected": -10.382724480879935,
1167
+ "loss": 0.5028,
1168
+ "rewards/chosen": 0.000817755371639409,
1169
+ "rewards/margins": 0.0010563352754176859,
1170
+ "rewards/rejected": -0.00023857990377827696,
1171
+ "step": 84
1172
+ },
1173
+ {
1174
+ "epoch": 1.4809437386569873,
1175
+ "grad_norm": 0.21237261593341827,
1176
+ "kl": 0.002868844196200371,
1177
+ "learning_rate": 1.2946428571428574e-06,
1178
+ "logps/chosen": -11.554072961329156,
1179
+ "logps/rejected": -10.606980036953727,
1180
+ "loss": 0.5036,
1181
+ "rewards/chosen": 0.00040721653476554046,
1182
+ "rewards/margins": 0.0007238921818244932,
1183
+ "rewards/rejected": -0.00031667564705895274,
1184
+ "step": 85
1185
+ },
1186
+ {
1187
+ "epoch": 1.498366606170599,
1188
+ "grad_norm": 0.21006950736045837,
1189
+ "kl": 0.0021779753733426332,
1190
+ "learning_rate": 1.25e-06,
1191
+ "logps/chosen": -11.395751308954486,
1192
+ "logps/rejected": -10.509847842022815,
1193
+ "loss": 0.5039,
1194
+ "rewards/chosen": 0.0002953462833464932,
1195
+ "rewards/margins": 0.0009452639913045675,
1196
+ "rewards/rejected": -0.0006499177079580743,
1197
+ "step": 86
1198
+ },
1199
+ {
1200
+ "epoch": 1.5157894736842106,
1201
+ "grad_norm": 0.2044811248779297,
1202
+ "kl": 0.0027360066305845976,
1203
+ "learning_rate": 1.205357142857143e-06,
1204
+ "logps/chosen": -11.286482900943396,
1205
+ "logps/rejected": -10.226171383028968,
1206
+ "loss": 0.5036,
1207
+ "rewards/chosen": 0.00042764071345007963,
1208
+ "rewards/margins": 0.000754331256658454,
1209
+ "rewards/rejected": -0.00032669054320837447,
1210
+ "step": 87
1211
+ },
1212
+ {
1213
+ "epoch": 1.5332123411978222,
1214
+ "grad_norm": 0.1994449943304062,
1215
+ "kl": 0.0012993334094062448,
1216
+ "learning_rate": 1.160714285714286e-06,
1217
+ "logps/chosen": -11.429487209875607,
1218
+ "logps/rejected": -10.525211634260884,
1219
+ "loss": 0.5034,
1220
+ "rewards/chosen": 0.0006345899649036741,
1221
+ "rewards/margins": 0.0010494590537087978,
1222
+ "rewards/rejected": -0.0004148690888051237,
1223
+ "step": 88
1224
+ },
1225
+ {
1226
+ "epoch": 1.5506352087114337,
1227
+ "grad_norm": 0.2269240915775299,
1228
+ "kl": 0.0028356958646327257,
1229
+ "learning_rate": 1.1160714285714287e-06,
1230
+ "logps/chosen": -11.494557624315693,
1231
+ "logps/rejected": -10.647711232930673,
1232
+ "loss": 0.5039,
1233
+ "rewards/chosen": 0.0005171763055806032,
1234
+ "rewards/margins": 0.0010993786980465312,
1235
+ "rewards/rejected": -0.000582202392465928,
1236
+ "step": 89
1237
+ },
1238
+ {
1239
+ "epoch": 1.5680580762250453,
1240
+ "grad_norm": 0.17898203432559967,
1241
+ "kl": 0.0027232880238443613,
1242
+ "learning_rate": 1.0714285714285714e-06,
1243
+ "logps/chosen": -11.28170191988032,
1244
+ "logps/rejected": -10.416350695551658,
1245
+ "loss": 0.5031,
1246
+ "rewards/chosen": 0.0005683141978497201,
1247
+ "rewards/margins": 0.0011697266601863967,
1248
+ "rewards/rejected": -0.0006014124623366765,
1249
+ "step": 90
1250
+ },
1251
+ {
1252
+ "epoch": 1.585480943738657,
1253
+ "grad_norm": 0.30514323711395264,
1254
+ "kl": 0.003049398772418499,
1255
+ "learning_rate": 1.0267857142857143e-06,
1256
+ "logps/chosen": -11.509693008814102,
1257
+ "logps/rejected": -10.68894675925926,
1258
+ "loss": 0.5045,
1259
+ "rewards/chosen": 0.0003556648890177409,
1260
+ "rewards/margins": 0.0007876505769749797,
1261
+ "rewards/rejected": -0.0004319856879572389,
1262
+ "step": 91
1263
+ },
1264
+ {
1265
+ "epoch": 1.6029038112522684,
1266
+ "grad_norm": 0.22825570404529572,
1267
+ "kl": 0.001876774593256414,
1268
+ "learning_rate": 9.821428571428572e-07,
1269
+ "logps/chosen": -11.782056884765625,
1270
+ "logps/rejected": -10.345401929772418,
1271
+ "loss": 0.5035,
1272
+ "rewards/chosen": 0.0005325853452086449,
1273
+ "rewards/margins": 0.0011105023842790853,
1274
+ "rewards/rejected": -0.0005779170390704404,
1275
+ "step": 92
1276
+ },
1277
+ {
1278
+ "epoch": 1.6203266787658803,
1279
+ "grad_norm": 0.1923515647649765,
1280
+ "kl": 0.0026991041377186775,
1281
+ "learning_rate": 9.375000000000001e-07,
1282
+ "logps/chosen": -11.152751884075126,
1283
+ "logps/rejected": -9.97277569514449,
1284
+ "loss": 0.5036,
1285
+ "rewards/chosen": 0.0005818240043490824,
1286
+ "rewards/margins": 0.0010237199423968812,
1287
+ "rewards/rejected": -0.0004418959380477987,
1288
+ "step": 93
1289
+ },
1290
+ {
1291
+ "epoch": 1.6377495462794918,
1292
+ "grad_norm": 0.21557894349098206,
1293
+ "kl": 0.001241236925125122,
1294
+ "learning_rate": 8.928571428571429e-07,
1295
+ "logps/chosen": -11.167566068672839,
1296
+ "logps/rejected": -11.65214332601584,
1297
+ "loss": 0.5034,
1298
+ "rewards/chosen": 0.0005508374652744811,
1299
+ "rewards/margins": 0.0011452616979097689,
1300
+ "rewards/rejected": -0.0005944242326352879,
1301
+ "step": 94
1302
+ },
1303
+ {
1304
+ "epoch": 1.6551724137931034,
1305
+ "grad_norm": 0.15490390360355377,
1306
+ "kl": 0.0023578277323395014,
1307
+ "learning_rate": 8.482142857142859e-07,
1308
+ "logps/chosen": -11.630532976752022,
1309
+ "logps/rejected": -10.874779842962846,
1310
+ "loss": 0.5024,
1311
+ "rewards/chosen": 0.001025584428458201,
1312
+ "rewards/margins": 0.0015268274366321843,
1313
+ "rewards/rejected": -0.0005012430081739834,
1314
+ "step": 95
1315
+ },
1316
+ {
1317
+ "epoch": 1.672595281306715,
1318
+ "grad_norm": 0.21339836716651917,
1319
+ "kl": 0.0030644694343209267,
1320
+ "learning_rate": 8.035714285714287e-07,
1321
+ "logps/chosen": -11.422396998881075,
1322
+ "logps/rejected": -10.11446374544098,
1323
+ "loss": 0.5032,
1324
+ "rewards/chosen": 0.0006199539698603208,
1325
+ "rewards/margins": 0.0011987829361300795,
1326
+ "rewards/rejected": -0.0005788289662697587,
1327
+ "step": 96
1328
+ },
1329
+ {
1330
+ "epoch": 1.672595281306715,
1331
+ "eval_kl": 0.0012286369455978274,
1332
+ "eval_logps/chosen": -11.286660330636161,
1333
+ "eval_logps/rejected": -10.654095241001674,
1334
+ "eval_loss": 0.503455400466919,
1335
+ "eval_rewards/chosen": 0.0005875181938920702,
1336
+ "eval_rewards/margins": 0.0011167954320886306,
1337
+ "eval_rewards/rejected": -0.0005292772381965603,
1338
+ "eval_runtime": 41.5081,
1339
+ "eval_samples_per_second": 10.745,
1340
+ "eval_steps_per_second": 0.675,
1341
+ "step": 96
1342
+ },
1343
+ {
1344
+ "epoch": 1.6900181488203265,
1345
+ "grad_norm": 0.1822512149810791,
1346
+ "kl": 0.0018086197087541223,
1347
+ "learning_rate": 7.589285714285714e-07,
1348
+ "logps/chosen": -11.162734347797702,
1349
+ "logps/rejected": -10.495764249694377,
1350
+ "loss": 0.5024,
1351
+ "rewards/chosen": 0.0007518338957868911,
1352
+ "rewards/margins": 0.0012704190070132039,
1353
+ "rewards/rejected": -0.0005185851112263127,
1354
+ "step": 97
1355
+ },
1356
+ {
1357
+ "epoch": 1.7074410163339384,
1358
+ "grad_norm": 0.25983884930610657,
1359
+ "kl": 0.001475659548304975,
1360
+ "learning_rate": 7.142857142857143e-07,
1361
+ "logps/chosen": -11.400912198153408,
1362
+ "logps/rejected": -10.339601098037347,
1363
+ "loss": 0.5035,
1364
+ "rewards/chosen": 0.0009949224916371432,
1365
+ "rewards/margins": 0.0013851757258375045,
1366
+ "rewards/rejected": -0.00039025323420036127,
1367
+ "step": 98
1368
+ },
1369
+ {
1370
+ "epoch": 1.7248638838475499,
1371
+ "grad_norm": 0.18693022429943085,
1372
+ "kl": 0.002064686268568039,
1373
+ "learning_rate": 6.696428571428571e-07,
1374
+ "logps/chosen": -11.613883205191799,
1375
+ "logps/rejected": -10.563515374599358,
1376
+ "loss": 0.5033,
1377
+ "rewards/chosen": 0.0007188759310535653,
1378
+ "rewards/margins": 0.0014389748514110983,
1379
+ "rewards/rejected": -0.000720098920357533,
1380
+ "step": 99
1381
+ },
1382
+ {
1383
+ "epoch": 1.7422867513611615,
1384
+ "grad_norm": 0.2225840985774994,
1385
+ "kl": 0.0023758753668516874,
1386
+ "learning_rate": 6.25e-07,
1387
+ "logps/chosen": -11.64061211658971,
1388
+ "logps/rejected": -10.474972761688624,
1389
+ "loss": 0.503,
1390
+ "rewards/chosen": 0.0006008470986323495,
1391
+ "rewards/margins": 0.0013913730829674177,
1392
+ "rewards/rejected": -0.0007905259843350682,
1393
+ "step": 100
1394
+ },
1395
+ {
1396
+ "epoch": 1.7597096188747732,
1397
+ "grad_norm": 0.20069453120231628,
1398
+ "kl": 0.001968987053260207,
1399
+ "learning_rate": 5.80357142857143e-07,
1400
+ "logps/chosen": -11.33251953125,
1401
+ "logps/rejected": -10.533562193525599,
1402
+ "loss": 0.5042,
1403
+ "rewards/chosen": 0.0002462785234864877,
1404
+ "rewards/margins": 0.0005758832525453824,
1405
+ "rewards/rejected": -0.0003296047290588947,
1406
+ "step": 101
1407
+ },
1408
+ {
1409
+ "epoch": 1.7771324863883846,
1410
+ "grad_norm": 0.1894039809703827,
1411
+ "kl": 0.003226263215765357,
1412
+ "learning_rate": 5.357142857142857e-07,
1413
+ "logps/chosen": -11.40087890625,
1414
+ "logps/rejected": -10.571763671875,
1415
+ "loss": 0.504,
1416
+ "rewards/chosen": 0.00039598065174869607,
1417
+ "rewards/margins": 0.0011867985482737612,
1418
+ "rewards/rejected": -0.0007908178965250651,
1419
+ "step": 102
1420
+ },
1421
+ {
1422
+ "epoch": 1.7945553539019965,
1423
+ "grad_norm": 0.16288532316684723,
1424
+ "kl": 0.002215030835941434,
1425
+ "learning_rate": 4.910714285714286e-07,
1426
+ "logps/chosen": -11.702183131167763,
1427
+ "logps/rejected": -10.757870389014176,
1428
+ "loss": 0.5027,
1429
+ "rewards/chosen": 0.0007084523376665617,
1430
+ "rewards/margins": 0.001386926632437186,
1431
+ "rewards/rejected": -0.0006784742947706242,
1432
+ "step": 103
1433
+ },
1434
+ {
1435
+ "epoch": 1.811978221415608,
1436
+ "grad_norm": 0.18168872594833374,
1437
+ "kl": 0.0029251668602228165,
1438
+ "learning_rate": 4.4642857142857147e-07,
1439
+ "logps/chosen": -11.455708379330842,
1440
+ "logps/rejected": -11.033857421875,
1441
+ "loss": 0.5029,
1442
+ "rewards/chosen": 0.0005165521136444548,
1443
+ "rewards/margins": 0.0011331064335030059,
1444
+ "rewards/rejected": -0.0006165543198585511,
1445
+ "step": 104
1446
+ },
1447
+ {
1448
+ "epoch": 1.8294010889292196,
1449
+ "grad_norm": 0.17783309519290924,
1450
+ "kl": 0.0027887674514204264,
1451
+ "learning_rate": 4.0178571428571434e-07,
1452
+ "logps/chosen": -11.572852601396276,
1453
+ "logps/rejected": -9.61759107940051,
1454
+ "loss": 0.5029,
1455
+ "rewards/chosen": 0.0006706785965473093,
1456
+ "rewards/margins": 0.001759196485623659,
1457
+ "rewards/rejected": -0.0010885178890763497,
1458
+ "step": 105
1459
+ },
1460
+ {
1461
+ "epoch": 1.8468239564428313,
1462
+ "grad_norm": 0.18048368394374847,
1463
+ "kl": 0.0018043291056528687,
1464
+ "learning_rate": 3.5714285714285716e-07,
1465
+ "logps/chosen": -11.548997631962436,
1466
+ "logps/rejected": -11.18207649910013,
1467
+ "loss": 0.5038,
1468
+ "rewards/chosen": 0.00041619074468167953,
1469
+ "rewards/margins": 0.0005713092191551835,
1470
+ "rewards/rejected": -0.00015511847447350388,
1471
+ "step": 106
1472
+ },
1473
+ {
1474
+ "epoch": 1.8642468239564427,
1475
+ "grad_norm": 0.4144538938999176,
1476
+ "kl": 0.0020457797218114138,
1477
+ "learning_rate": 3.125e-07,
1478
+ "logps/chosen": -10.976453261876685,
1479
+ "logps/rejected": -10.985627066278338,
1480
+ "loss": 0.5048,
1481
+ "rewards/chosen": 0.00022244479537331512,
1482
+ "rewards/margins": 0.0006958120098764712,
1483
+ "rewards/rejected": -0.00047336721450315616,
1484
+ "step": 107
1485
+ },
1486
+ {
1487
+ "epoch": 1.8816696914700546,
1488
+ "grad_norm": 0.19312834739685059,
1489
+ "kl": 0.0014575794339179993,
1490
+ "learning_rate": 2.6785714285714284e-07,
1491
+ "logps/chosen": -11.37527155066906,
1492
+ "logps/rejected": -10.887072595373377,
1493
+ "loss": 0.5035,
1494
+ "rewards/chosen": 0.0006041409686091052,
1495
+ "rewards/margins": 0.0013794575971519186,
1496
+ "rewards/rejected": -0.0007753166285428134,
1497
+ "step": 108
1498
+ },
1499
+ {
1500
+ "epoch": 1.899092558983666,
1501
+ "grad_norm": 0.24906954169273376,
1502
+ "kl": 0.002399616641923785,
1503
+ "learning_rate": 2.2321428571428574e-07,
1504
+ "logps/chosen": -11.331646469763092,
1505
+ "logps/rejected": -10.6643505460235,
1506
+ "loss": 0.5046,
1507
+ "rewards/chosen": 0.0009270152843503881,
1508
+ "rewards/margins": 0.001616924349477436,
1509
+ "rewards/rejected": -0.0006899090651270479,
1510
+ "step": 109
1511
+ },
1512
+ {
1513
+ "epoch": 1.9165154264972777,
1514
+ "grad_norm": 0.1880314201116562,
1515
+ "kl": 0.0026240963488817215,
1516
+ "learning_rate": 1.7857142857142858e-07,
1517
+ "logps/chosen": -11.29613597972973,
1518
+ "logps/rejected": -10.615358285568467,
1519
+ "loss": 0.5031,
1520
+ "rewards/chosen": 0.0010521258051330979,
1521
+ "rewards/margins": 0.0013450532624429453,
1522
+ "rewards/rejected": -0.0002929274573098475,
1523
+ "step": 110
1524
+ },
1525
+ {
1526
+ "epoch": 1.9339382940108893,
1527
+ "grad_norm": 0.18609453737735748,
1528
+ "kl": 0.002484673634171486,
1529
+ "learning_rate": 1.3392857142857142e-07,
1530
+ "logps/chosen": -11.604450023938023,
1531
+ "logps/rejected": -10.78327236781785,
1532
+ "loss": 0.5028,
1533
+ "rewards/chosen": 0.0006836153836635494,
1534
+ "rewards/margins": 0.001532551150396621,
1535
+ "rewards/rejected": -0.0008489357667330717,
1536
+ "step": 111
1537
+ },
1538
+ {
1539
+ "epoch": 1.9513611615245008,
1540
+ "grad_norm": 0.20338238775730133,
1541
+ "kl": 0.0025711385533213615,
1542
+ "learning_rate": 8.928571428571429e-08,
1543
+ "logps/chosen": -11.439998413705585,
1544
+ "logps/rejected": -10.535859296666109,
1545
+ "loss": 0.5036,
1546
+ "rewards/chosen": 0.0005479781760782154,
1547
+ "rewards/margins": 0.0011845395663098528,
1548
+ "rewards/rejected": -0.0006365613902316374,
1549
+ "step": 112
1550
+ },
1551
+ {
1552
+ "epoch": 1.9513611615245008,
1553
+ "eval_kl": 0.000932498718611896,
1554
+ "eval_logps/chosen": -11.286882672991071,
1555
+ "eval_logps/rejected": -10.654556274414062,
1556
+ "eval_loss": 0.5036724805831909,
1557
+ "eval_rewards/chosen": 0.0005651861429214478,
1558
+ "eval_rewards/margins": 0.0011406249499746732,
1559
+ "eval_rewards/rejected": -0.0005754388070532254,
1560
+ "eval_runtime": 41.5261,
1561
+ "eval_samples_per_second": 10.74,
1562
+ "eval_steps_per_second": 0.674,
1563
+ "step": 112
1564
+ },
1565
+ {
1566
+ "epoch": 1.9687840290381127,
1567
+ "grad_norm": 0.18693436682224274,
1568
+ "kl": 0.0030837843660265207,
1569
+ "learning_rate": 4.4642857142857145e-08,
1570
+ "logps/chosen": -11.600828793174342,
1571
+ "logps/rejected": -10.943336722777062,
1572
+ "loss": 0.5031,
1573
+ "rewards/chosen": 0.0006475970541176044,
1574
+ "rewards/margins": 0.0013402001844336014,
1575
+ "rewards/rejected": -0.0006926031303159969,
1576
+ "step": 113
1577
+ },
1578
+ {
1579
+ "epoch": 1.986206896551724,
1580
+ "grad_norm": 0.1876712143421173,
1581
+ "kl": 0.0018025139579549432,
1582
+ "learning_rate": 0.0,
1583
+ "logps/chosen": -11.169455056662088,
1584
+ "logps/rejected": -10.222750522122524,
1585
+ "loss": 0.5029,
1586
+ "rewards/chosen": 0.0007852382221064725,
1587
+ "rewards/margins": 0.0014990826276489785,
1588
+ "rewards/rejected": -0.0007138444055425059,
1589
+ "step": 114
1590
+ }
1591
+ ],
1592
+ "logging_steps": 1,
1593
+ "max_steps": 114,
1594
+ "num_input_tokens_seen": 0,
1595
+ "num_train_epochs": 2,
1596
+ "save_steps": 500,
1597
+ "stateful_callbacks": {
1598
+ "TrainerControl": {
1599
+ "args": {
1600
+ "should_epoch_stop": false,
1601
+ "should_evaluate": false,
1602
+ "should_log": false,
1603
+ "should_save": true,
1604
+ "should_training_stop": true
1605
+ },
1606
+ "attributes": {}
1607
+ }
1608
+ },
1609
+ "total_flos": 2.0165964255461376e+18,
1610
+ "train_batch_size": 2,
1611
+ "trial_name": null,
1612
+ "trial_params": null
1613
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2301e5cdb48416ef732c6e22ced1cfa5122c5cd89849f16d6895ba91d6ccfe58
3
+ size 6648
zero_to_fp32.py ADDED
@@ -0,0 +1,604 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #!/usr/bin/env python
2
+
3
+ # Copyright (c) Microsoft Corporation.
4
+ # SPDX-License-Identifier: Apache-2.0
5
+
6
+ # DeepSpeed Team
7
+
8
+ # This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
9
+ # copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
10
+ # the future. Once extracted, the weights don't require DeepSpeed and can be used in any
11
+ # application.
12
+ #
13
+ # example: python zero_to_fp32.py . pytorch_model.bin
14
+
15
+ import argparse
16
+ import torch
17
+ import glob
18
+ import math
19
+ import os
20
+ import re
21
+ from collections import OrderedDict
22
+ from dataclasses import dataclass
23
+
24
+ # while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
25
+ # DeepSpeed data structures it has to be available in the current python environment.
26
+ from deepspeed.utils import logger
27
+ from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
28
+ FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
29
+ FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
30
+
31
+
32
+ @dataclass
33
+ class zero_model_state:
34
+ buffers: dict()
35
+ param_shapes: dict()
36
+ shared_params: list
37
+ ds_version: int
38
+ frozen_param_shapes: dict()
39
+ frozen_param_fragments: dict()
40
+
41
+
42
+ debug = 0
43
+
44
+ # load to cpu
45
+ device = torch.device('cpu')
46
+
47
+
48
+ def atoi(text):
49
+ return int(text) if text.isdigit() else text
50
+
51
+
52
+ def natural_keys(text):
53
+ '''
54
+ alist.sort(key=natural_keys) sorts in human order
55
+ http://nedbatchelder.com/blog/200712/human_sorting.html
56
+ (See Toothy's implementation in the comments)
57
+ '''
58
+ return [atoi(c) for c in re.split(r'(\d+)', text)]
59
+
60
+
61
+ def get_model_state_file(checkpoint_dir, zero_stage):
62
+ if not os.path.isdir(checkpoint_dir):
63
+ raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
64
+
65
+ # there should be only one file
66
+ if zero_stage <= 2:
67
+ file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
68
+ elif zero_stage == 3:
69
+ file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
70
+
71
+ if not os.path.exists(file):
72
+ raise FileNotFoundError(f"can't find model states file at '{file}'")
73
+
74
+ return file
75
+
76
+
77
+ def get_checkpoint_files(checkpoint_dir, glob_pattern):
78
+ # XXX: need to test that this simple glob rule works for multi-node setup too
79
+ ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
80
+
81
+ if len(ckpt_files) == 0:
82
+ raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
83
+
84
+ return ckpt_files
85
+
86
+
87
+ def get_optim_files(checkpoint_dir):
88
+ return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
89
+
90
+
91
+ def get_model_state_files(checkpoint_dir):
92
+ return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
93
+
94
+
95
+ def parse_model_states(files):
96
+ zero_model_states = []
97
+ for file in files:
98
+ state_dict = torch.load(file, map_location=device)
99
+
100
+ if BUFFER_NAMES not in state_dict:
101
+ raise ValueError(f"{file} is not a model state checkpoint")
102
+ buffer_names = state_dict[BUFFER_NAMES]
103
+ if debug:
104
+ print("Found buffers:", buffer_names)
105
+
106
+ # recover just the buffers while restoring them to fp32 if they were saved in fp16
107
+ buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
108
+ param_shapes = state_dict[PARAM_SHAPES]
109
+
110
+ # collect parameters that are included in param_shapes
111
+ param_names = []
112
+ for s in param_shapes:
113
+ for name in s.keys():
114
+ param_names.append(name)
115
+
116
+ # update with frozen parameters
117
+ frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
118
+ if frozen_param_shapes is not None:
119
+ if debug:
120
+ print(f"Found frozen_param_shapes: {frozen_param_shapes}")
121
+ param_names += list(frozen_param_shapes.keys())
122
+
123
+ # handle shared params
124
+ shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
125
+
126
+ ds_version = state_dict.get(DS_VERSION, None)
127
+
128
+ frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
129
+
130
+ z_model_state = zero_model_state(buffers=buffers,
131
+ param_shapes=param_shapes,
132
+ shared_params=shared_params,
133
+ ds_version=ds_version,
134
+ frozen_param_shapes=frozen_param_shapes,
135
+ frozen_param_fragments=frozen_param_fragments)
136
+ zero_model_states.append(z_model_state)
137
+
138
+ return zero_model_states
139
+
140
+
141
+ def parse_optim_states(files, ds_checkpoint_dir):
142
+
143
+ total_files = len(files)
144
+ state_dicts = []
145
+ for f in files:
146
+ state_dict = torch.load(f, map_location=device)
147
+ # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
148
+ # and also handle the case where it was already removed by another helper script
149
+ state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
150
+ state_dicts.append(state_dict)
151
+
152
+ if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
153
+ raise ValueError(f"{files[0]} is not a zero checkpoint")
154
+ zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
155
+ world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
156
+
157
+ # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
158
+ # parameters can be different from data parallelism for non-expert parameters. So we can just
159
+ # use the max of the partition_count to get the dp world_size.
160
+
161
+ if type(world_size) is list:
162
+ world_size = max(world_size)
163
+
164
+ if world_size != total_files:
165
+ raise ValueError(
166
+ f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
167
+ "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
168
+ )
169
+
170
+ # the groups are named differently in each stage
171
+ if zero_stage <= 2:
172
+ fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
173
+ elif zero_stage == 3:
174
+ fp32_groups_key = FP32_FLAT_GROUPS
175
+ else:
176
+ raise ValueError(f"unknown zero stage {zero_stage}")
177
+
178
+ if zero_stage <= 2:
179
+ fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
180
+ elif zero_stage == 3:
181
+ # if there is more than one param group, there will be multiple flattened tensors - one
182
+ # flattened tensor per group - for simplicity merge them into a single tensor
183
+ #
184
+ # XXX: could make the script more memory efficient for when there are multiple groups - it
185
+ # will require matching the sub-lists of param_shapes for each param group flattened tensor
186
+
187
+ fp32_flat_groups = [
188
+ torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
189
+ ]
190
+
191
+ return zero_stage, world_size, fp32_flat_groups
192
+
193
+
194
+ def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
195
+ """
196
+ Returns fp32 state_dict reconstructed from ds checkpoint
197
+
198
+ Args:
199
+ - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
200
+
201
+ """
202
+ print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
203
+
204
+ optim_files = get_optim_files(ds_checkpoint_dir)
205
+ zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
206
+ print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
207
+
208
+ model_files = get_model_state_files(ds_checkpoint_dir)
209
+
210
+ zero_model_states = parse_model_states(model_files)
211
+ print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
212
+
213
+ if zero_stage <= 2:
214
+ return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
215
+ exclude_frozen_parameters)
216
+ elif zero_stage == 3:
217
+ return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
218
+ exclude_frozen_parameters)
219
+
220
+
221
+ def _zero2_merge_frozen_params(state_dict, zero_model_states):
222
+ if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
223
+ return
224
+
225
+ frozen_param_shapes = zero_model_states[0].frozen_param_shapes
226
+ frozen_param_fragments = zero_model_states[0].frozen_param_fragments
227
+
228
+ if debug:
229
+ num_elem = sum(s.numel() for s in frozen_param_shapes.values())
230
+ print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
231
+
232
+ wanted_params = len(frozen_param_shapes)
233
+ wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
234
+ avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
235
+ print(f'Frozen params: Have {avail_numel} numels to process.')
236
+ print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
237
+
238
+ total_params = 0
239
+ total_numel = 0
240
+ for name, shape in frozen_param_shapes.items():
241
+ total_params += 1
242
+ unpartitioned_numel = shape.numel()
243
+ total_numel += unpartitioned_numel
244
+
245
+ state_dict[name] = frozen_param_fragments[name]
246
+
247
+ if debug:
248
+ print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
249
+
250
+ print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
251
+
252
+
253
+ def _has_callable(obj, fn):
254
+ attr = getattr(obj, fn, None)
255
+ return callable(attr)
256
+
257
+
258
+ def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
259
+ param_shapes = zero_model_states[0].param_shapes
260
+
261
+ # Reconstruction protocol:
262
+ #
263
+ # XXX: document this
264
+
265
+ if debug:
266
+ for i in range(world_size):
267
+ for j in range(len(fp32_flat_groups[0])):
268
+ print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
269
+
270
+ # XXX: memory usage doubles here (zero2)
271
+ num_param_groups = len(fp32_flat_groups[0])
272
+ merged_single_partition_of_fp32_groups = []
273
+ for i in range(num_param_groups):
274
+ merged_partitions = [sd[i] for sd in fp32_flat_groups]
275
+ full_single_fp32_vector = torch.cat(merged_partitions, 0)
276
+ merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
277
+ avail_numel = sum(
278
+ [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
279
+
280
+ if debug:
281
+ wanted_params = sum([len(shapes) for shapes in param_shapes])
282
+ wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
283
+ # not asserting if there is a mismatch due to possible padding
284
+ print(f"Have {avail_numel} numels to process.")
285
+ print(f"Need {wanted_numel} numels in {wanted_params} params.")
286
+
287
+ # params
288
+ # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
289
+ # out-of-core computing solution
290
+ total_numel = 0
291
+ total_params = 0
292
+ for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
293
+ offset = 0
294
+ avail_numel = full_single_fp32_vector.numel()
295
+ for name, shape in shapes.items():
296
+
297
+ unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
298
+ total_numel += unpartitioned_numel
299
+ total_params += 1
300
+
301
+ if debug:
302
+ print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
303
+ state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
304
+ offset += unpartitioned_numel
305
+
306
+ # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
307
+ # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
308
+ # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
309
+ # live optimizer object, so we are checking that the numbers are within the right range
310
+ align_to = 2 * world_size
311
+
312
+ def zero2_align(x):
313
+ return align_to * math.ceil(x / align_to)
314
+
315
+ if debug:
316
+ print(f"original offset={offset}, avail_numel={avail_numel}")
317
+
318
+ offset = zero2_align(offset)
319
+ avail_numel = zero2_align(avail_numel)
320
+
321
+ if debug:
322
+ print(f"aligned offset={offset}, avail_numel={avail_numel}")
323
+
324
+ # Sanity check
325
+ if offset != avail_numel:
326
+ raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
327
+
328
+ print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
329
+
330
+
331
+ def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
332
+ exclude_frozen_parameters):
333
+ state_dict = OrderedDict()
334
+
335
+ # buffers
336
+ buffers = zero_model_states[0].buffers
337
+ state_dict.update(buffers)
338
+ if debug:
339
+ print(f"added {len(buffers)} buffers")
340
+
341
+ if not exclude_frozen_parameters:
342
+ _zero2_merge_frozen_params(state_dict, zero_model_states)
343
+
344
+ _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
345
+
346
+ # recover shared parameters
347
+ for pair in zero_model_states[0].shared_params:
348
+ if pair[1] in state_dict:
349
+ state_dict[pair[0]] = state_dict[pair[1]]
350
+
351
+ return state_dict
352
+
353
+
354
+ def zero3_partitioned_param_info(unpartitioned_numel, world_size):
355
+ remainder = unpartitioned_numel % world_size
356
+ padding_numel = (world_size - remainder) if remainder else 0
357
+ partitioned_numel = math.ceil(unpartitioned_numel / world_size)
358
+ return partitioned_numel, padding_numel
359
+
360
+
361
+ def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
362
+ if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
363
+ return
364
+
365
+ if debug:
366
+ for i in range(world_size):
367
+ num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
368
+ print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
369
+
370
+ frozen_param_shapes = zero_model_states[0].frozen_param_shapes
371
+ wanted_params = len(frozen_param_shapes)
372
+ wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
373
+ avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
374
+ print(f'Frozen params: Have {avail_numel} numels to process.')
375
+ print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
376
+
377
+ total_params = 0
378
+ total_numel = 0
379
+ for name, shape in zero_model_states[0].frozen_param_shapes.items():
380
+ total_params += 1
381
+ unpartitioned_numel = shape.numel()
382
+ total_numel += unpartitioned_numel
383
+
384
+ param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
385
+ state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
386
+
387
+ partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
388
+
389
+ if debug:
390
+ print(
391
+ f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
392
+ )
393
+
394
+ print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
395
+
396
+
397
+ def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
398
+ param_shapes = zero_model_states[0].param_shapes
399
+ avail_numel = fp32_flat_groups[0].numel() * world_size
400
+ # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
401
+ # param, re-consolidating each param, while dealing with padding if any
402
+
403
+ # merge list of dicts, preserving order
404
+ param_shapes = {k: v for d in param_shapes for k, v in d.items()}
405
+
406
+ if debug:
407
+ for i in range(world_size):
408
+ print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
409
+
410
+ wanted_params = len(param_shapes)
411
+ wanted_numel = sum(shape.numel() for shape in param_shapes.values())
412
+ # not asserting if there is a mismatch due to possible padding
413
+ avail_numel = fp32_flat_groups[0].numel() * world_size
414
+ print(f"Trainable params: Have {avail_numel} numels to process.")
415
+ print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
416
+
417
+ # params
418
+ # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
419
+ # out-of-core computing solution
420
+ offset = 0
421
+ total_numel = 0
422
+ total_params = 0
423
+ for name, shape in param_shapes.items():
424
+
425
+ unpartitioned_numel = shape.numel()
426
+ total_numel += unpartitioned_numel
427
+ total_params += 1
428
+
429
+ partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
430
+
431
+ if debug:
432
+ print(
433
+ f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
434
+ )
435
+
436
+ # XXX: memory usage doubles here
437
+ state_dict[name] = torch.cat(
438
+ tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
439
+ 0).narrow(0, 0, unpartitioned_numel).view(shape)
440
+ offset += partitioned_numel
441
+
442
+ offset *= world_size
443
+
444
+ # Sanity check
445
+ if offset != avail_numel:
446
+ raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
447
+
448
+ print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
449
+
450
+
451
+ def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
452
+ exclude_frozen_parameters):
453
+ state_dict = OrderedDict()
454
+
455
+ # buffers
456
+ buffers = zero_model_states[0].buffers
457
+ state_dict.update(buffers)
458
+ if debug:
459
+ print(f"added {len(buffers)} buffers")
460
+
461
+ if not exclude_frozen_parameters:
462
+ _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
463
+
464
+ _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
465
+
466
+ # recover shared parameters
467
+ for pair in zero_model_states[0].shared_params:
468
+ if pair[1] in state_dict:
469
+ state_dict[pair[0]] = state_dict[pair[1]]
470
+
471
+ return state_dict
472
+
473
+
474
+ def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
475
+ """
476
+ Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
477
+ ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
478
+ via a model hub.
479
+
480
+ Args:
481
+ - ``checkpoint_dir``: path to the desired checkpoint folder
482
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
483
+ - ``exclude_frozen_parameters``: exclude frozen parameters
484
+
485
+ Returns:
486
+ - pytorch ``state_dict``
487
+
488
+ Note: this approach may not work if your application doesn't have sufficient free CPU memory and
489
+ you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
490
+ the checkpoint.
491
+
492
+ A typical usage might be ::
493
+
494
+ from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
495
+ # do the training and checkpoint saving
496
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
497
+ model = model.cpu() # move to cpu
498
+ model.load_state_dict(state_dict)
499
+ # submit to model hub or save the model to share with others
500
+
501
+ In this example the ``model`` will no longer be usable in the deepspeed context of the same
502
+ application. i.e. you will need to re-initialize the deepspeed engine, since
503
+ ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
504
+
505
+ If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
506
+
507
+ """
508
+ if tag is None:
509
+ latest_path = os.path.join(checkpoint_dir, 'latest')
510
+ if os.path.isfile(latest_path):
511
+ with open(latest_path, 'r') as fd:
512
+ tag = fd.read().strip()
513
+ else:
514
+ raise ValueError(f"Unable to find 'latest' file at {latest_path}")
515
+
516
+ ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
517
+
518
+ if not os.path.isdir(ds_checkpoint_dir):
519
+ raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
520
+
521
+ return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
522
+
523
+
524
+ def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None, exclude_frozen_parameters=False):
525
+ """
526
+ Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
527
+ loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
528
+
529
+ Args:
530
+ - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
531
+ - ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
532
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
533
+ - ``exclude_frozen_parameters``: exclude frozen parameters
534
+ """
535
+
536
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
537
+ print(f"Saving fp32 state dict to {output_file}")
538
+ torch.save(state_dict, output_file)
539
+
540
+
541
+ def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
542
+ """
543
+ 1. Put the provided model to cpu
544
+ 2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
545
+ 3. Load it into the provided model
546
+
547
+ Args:
548
+ - ``model``: the model object to update
549
+ - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
550
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
551
+
552
+ Returns:
553
+ - ``model`: modified model
554
+
555
+ Make sure you have plenty of CPU memory available before you call this function. If you don't
556
+ have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
557
+ conveniently placed for you in the checkpoint folder.
558
+
559
+ A typical usage might be ::
560
+
561
+ from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
562
+ model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
563
+ # submit to model hub or save the model to share with others
564
+
565
+ Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
566
+ of the same application. i.e. you will need to re-initialize the deepspeed engine, since
567
+ ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
568
+
569
+ """
570
+ logger.info(f"Extracting fp32 weights")
571
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
572
+
573
+ logger.info(f"Overwriting model with fp32 weights")
574
+ model = model.cpu()
575
+ model.load_state_dict(state_dict, strict=False)
576
+
577
+ return model
578
+
579
+
580
+ if __name__ == "__main__":
581
+
582
+ parser = argparse.ArgumentParser()
583
+ parser.add_argument("checkpoint_dir",
584
+ type=str,
585
+ help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
586
+ parser.add_argument(
587
+ "output_file",
588
+ type=str,
589
+ help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
590
+ parser.add_argument("-t",
591
+ "--tag",
592
+ type=str,
593
+ default=None,
594
+ help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
595
+ parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
596
+ parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
597
+ args = parser.parse_args()
598
+
599
+ debug = args.debug
600
+
601
+ convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
602
+ args.output_file,
603
+ tag=args.tag,
604
+ exclude_frozen_parameters=args.exclude_frozen_parameters)