ever17 commited on
Commit
fa792f0
1 Parent(s): 40fe412

Upload 11 files

Browse files
Kr_model_for_Llama3_8b/.DS_Store ADDED
Binary file (8.2 kB). View file
 
Kr_model_for_Llama3_8b/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: /home/lixz23/pretrain-model/Llama3-8b-instruct
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.10.0
Kr_model_for_Llama3_8b/adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "/home/lixz23/pretrain-model/Llama3-8b-instruct",
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": 0.1,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 8,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "q_proj",
24
+ "v_proj"
25
+ ],
26
+ "task_type": "CAUSAL_LM",
27
+ "use_dora": false,
28
+ "use_rslora": false
29
+ }
Kr_model_for_Llama3_8b/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46b3a658eaa9f19a8bf7e9aec8ed1d426349a5333ceca97a2f3b816419c8e36b
3
+ size 6832728
Kr_model_for_Llama3_8b/latest ADDED
@@ -0,0 +1 @@
 
 
1
+ global_step1300
Kr_model_for_Llama3_8b/special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|eot_id|>"
17
+ }
Kr_model_for_Llama3_8b/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
Kr_model_for_Llama3_8b/tokenizer_config.json ADDED
@@ -0,0 +1,2063 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
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": "<|reserved_special_token_4|>",
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": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 1000000000000000019884624838656,
2061
+ "pad_token": "<|eot_id|>",
2062
+ "tokenizer_class": "PreTrainedTokenizerFast"
2063
+ }
Kr_model_for_Llama3_8b/trainer_state.json ADDED
@@ -0,0 +1,2387 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9973149213655543,
5
+ "eval_steps": 50,
6
+ "global_step": 1300,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.007671653241273495,
13
+ "grad_norm": 1.4047255516052246,
14
+ "learning_rate": 4.9616270145817344e-05,
15
+ "logits/chosen": -0.5156614184379578,
16
+ "logits/rejected": -0.5155973434448242,
17
+ "logps/chosen": -1.6896766424179077,
18
+ "logps/rejected": -3.5133140087127686,
19
+ "loss": 0.6952,
20
+ "rewards/accuracies": 0.5,
21
+ "rewards/chosen": 0.00019091162539552897,
22
+ "rewards/margins": 0.001644002622924745,
23
+ "rewards/rejected": -0.0014530897606164217,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 0.01534330648254699,
28
+ "grad_norm": 1.5815409421920776,
29
+ "learning_rate": 4.923254029163469e-05,
30
+ "logits/chosen": -0.5282754302024841,
31
+ "logits/rejected": -0.5348799824714661,
32
+ "logps/chosen": -2.51069974899292,
33
+ "logps/rejected": -2.873567819595337,
34
+ "loss": 0.6911,
35
+ "rewards/accuracies": 0.550000011920929,
36
+ "rewards/chosen": 0.003554452210664749,
37
+ "rewards/margins": 0.004838407970964909,
38
+ "rewards/rejected": -0.0012839583214372396,
39
+ "step": 20
40
+ },
41
+ {
42
+ "epoch": 0.023014959723820484,
43
+ "grad_norm": 1.5293035507202148,
44
+ "learning_rate": 4.8848810437452035e-05,
45
+ "logits/chosen": -0.46481943130493164,
46
+ "logits/rejected": -0.4620364308357239,
47
+ "logps/chosen": -2.9464457035064697,
48
+ "logps/rejected": -4.222188472747803,
49
+ "loss": 0.6923,
50
+ "rewards/accuracies": 0.6000000238418579,
51
+ "rewards/chosen": -0.02544591762125492,
52
+ "rewards/margins": 0.06909430772066116,
53
+ "rewards/rejected": -0.09454023092985153,
54
+ "step": 30
55
+ },
56
+ {
57
+ "epoch": 0.03068661296509398,
58
+ "grad_norm": 2.4810216426849365,
59
+ "learning_rate": 4.846508058326938e-05,
60
+ "logits/chosen": -0.4796638488769531,
61
+ "logits/rejected": -0.4740970730781555,
62
+ "logps/chosen": -4.077430725097656,
63
+ "logps/rejected": -2.8998451232910156,
64
+ "loss": 0.6951,
65
+ "rewards/accuracies": 0.4000000059604645,
66
+ "rewards/chosen": -0.0723290666937828,
67
+ "rewards/margins": -0.027712786570191383,
68
+ "rewards/rejected": -0.044616274535655975,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.038358266206367474,
73
+ "grad_norm": 1.7016780376434326,
74
+ "learning_rate": 4.8081350729086726e-05,
75
+ "logits/chosen": -0.4345604479312897,
76
+ "logits/rejected": -0.4407508969306946,
77
+ "logps/chosen": -2.6753084659576416,
78
+ "logps/rejected": -3.9175124168395996,
79
+ "loss": 0.6948,
80
+ "rewards/accuracies": 0.6000000238418579,
81
+ "rewards/chosen": -0.022549040615558624,
82
+ "rewards/margins": 0.023919526487588882,
83
+ "rewards/rejected": -0.046468570828437805,
84
+ "step": 50
85
+ },
86
+ {
87
+ "epoch": 0.038358266206367474,
88
+ "eval_logits/chosen": -0.2606842815876007,
89
+ "eval_logits/rejected": -0.2579291760921478,
90
+ "eval_logps/chosen": -3.532228946685791,
91
+ "eval_logps/rejected": -3.719329833984375,
92
+ "eval_loss": 0.6931471824645996,
93
+ "eval_rewards/accuracies": 0.47187501192092896,
94
+ "eval_rewards/chosen": -0.04993545264005661,
95
+ "eval_rewards/margins": -0.011583473533391953,
96
+ "eval_rewards/rejected": -0.03835199028253555,
97
+ "eval_runtime": 92.1681,
98
+ "eval_samples_per_second": 27.71,
99
+ "eval_steps_per_second": 0.868,
100
+ "step": 50
101
+ },
102
+ {
103
+ "epoch": 0.04602991944764097,
104
+ "grad_norm": 1.5512512922286987,
105
+ "learning_rate": 4.769762087490407e-05,
106
+ "logits/chosen": -0.41122546792030334,
107
+ "logits/rejected": -0.4166368544101715,
108
+ "logps/chosen": -3.745007276535034,
109
+ "logps/rejected": -2.612656593322754,
110
+ "loss": 0.6999,
111
+ "rewards/accuracies": 0.5,
112
+ "rewards/chosen": -0.02822841703891754,
113
+ "rewards/margins": -0.011006011627614498,
114
+ "rewards/rejected": -0.01722240075469017,
115
+ "step": 60
116
+ },
117
+ {
118
+ "epoch": 0.05370157268891446,
119
+ "grad_norm": 1.307566523551941,
120
+ "learning_rate": 4.731389102072141e-05,
121
+ "logits/chosen": -0.45976758003234863,
122
+ "logits/rejected": -0.4562222361564636,
123
+ "logps/chosen": -2.7820112705230713,
124
+ "logps/rejected": -3.3871638774871826,
125
+ "loss": 0.694,
126
+ "rewards/accuracies": 0.4749999940395355,
127
+ "rewards/chosen": -0.015000693500041962,
128
+ "rewards/margins": 0.0025637741200625896,
129
+ "rewards/rejected": -0.01756446808576584,
130
+ "step": 70
131
+ },
132
+ {
133
+ "epoch": 0.06137322593018796,
134
+ "grad_norm": 1.6361109018325806,
135
+ "learning_rate": 4.693016116653876e-05,
136
+ "logits/chosen": -0.3749166429042816,
137
+ "logits/rejected": -0.37954169511795044,
138
+ "logps/chosen": -2.275099992752075,
139
+ "logps/rejected": -4.181614398956299,
140
+ "loss": 0.6907,
141
+ "rewards/accuracies": 0.550000011920929,
142
+ "rewards/chosen": -0.020970512181520462,
143
+ "rewards/margins": 0.025806229561567307,
144
+ "rewards/rejected": -0.04677674546837807,
145
+ "step": 80
146
+ },
147
+ {
148
+ "epoch": 0.06904487917146145,
149
+ "grad_norm": 1.83301842212677,
150
+ "learning_rate": 4.65464313123561e-05,
151
+ "logits/chosen": -0.5111284255981445,
152
+ "logits/rejected": -0.5044411420822144,
153
+ "logps/chosen": -2.0928683280944824,
154
+ "logps/rejected": -5.220086574554443,
155
+ "loss": 0.6899,
156
+ "rewards/accuracies": 0.7250000238418579,
157
+ "rewards/chosen": -0.017647314816713333,
158
+ "rewards/margins": 0.07800659537315369,
159
+ "rewards/rejected": -0.09565390646457672,
160
+ "step": 90
161
+ },
162
+ {
163
+ "epoch": 0.07671653241273495,
164
+ "grad_norm": 2.6800460815429688,
165
+ "learning_rate": 4.6162701458173444e-05,
166
+ "logits/chosen": -0.44164401292800903,
167
+ "logits/rejected": -0.44124874472618103,
168
+ "logps/chosen": -3.620197296142578,
169
+ "logps/rejected": -3.795258045196533,
170
+ "loss": 0.7065,
171
+ "rewards/accuracies": 0.550000011920929,
172
+ "rewards/chosen": -0.06498938798904419,
173
+ "rewards/margins": 0.0013415880966931581,
174
+ "rewards/rejected": -0.06633097678422928,
175
+ "step": 100
176
+ },
177
+ {
178
+ "epoch": 0.07671653241273495,
179
+ "eval_logits/chosen": -0.25962817668914795,
180
+ "eval_logits/rejected": -0.25671660900115967,
181
+ "eval_logps/chosen": -3.3411738872528076,
182
+ "eval_logps/rejected": -3.666893720626831,
183
+ "eval_loss": 0.6914116144180298,
184
+ "eval_rewards/accuracies": 0.53125,
185
+ "eval_rewards/chosen": -0.030829980969429016,
186
+ "eval_rewards/margins": 0.002278365660458803,
187
+ "eval_rewards/rejected": -0.03310834616422653,
188
+ "eval_runtime": 87.6826,
189
+ "eval_samples_per_second": 29.128,
190
+ "eval_steps_per_second": 0.912,
191
+ "step": 100
192
+ },
193
+ {
194
+ "epoch": 0.08438818565400844,
195
+ "grad_norm": 1.4465539455413818,
196
+ "learning_rate": 4.577897160399079e-05,
197
+ "logits/chosen": -0.32688966393470764,
198
+ "logits/rejected": -0.3221715986728668,
199
+ "logps/chosen": -3.515720844268799,
200
+ "logps/rejected": -4.333282470703125,
201
+ "loss": 0.6929,
202
+ "rewards/accuracies": 0.550000011920929,
203
+ "rewards/chosen": -0.0163725558668375,
204
+ "rewards/margins": 0.029236530885100365,
205
+ "rewards/rejected": -0.04560908302664757,
206
+ "step": 110
207
+ },
208
+ {
209
+ "epoch": 0.09205983889528194,
210
+ "grad_norm": 1.4560517072677612,
211
+ "learning_rate": 4.5395241749808135e-05,
212
+ "logits/chosen": -0.48749834299087524,
213
+ "logits/rejected": -0.4916568696498871,
214
+ "logps/chosen": -3.262430191040039,
215
+ "logps/rejected": -3.4948978424072266,
216
+ "loss": 0.6837,
217
+ "rewards/accuracies": 0.5,
218
+ "rewards/chosen": -0.01899554952979088,
219
+ "rewards/margins": 0.03163793310523033,
220
+ "rewards/rejected": -0.05063347890973091,
221
+ "step": 120
222
+ },
223
+ {
224
+ "epoch": 0.09973149213655542,
225
+ "grad_norm": 1.2213283777236938,
226
+ "learning_rate": 4.501151189562548e-05,
227
+ "logits/chosen": -0.4065719544887543,
228
+ "logits/rejected": -0.4011871814727783,
229
+ "logps/chosen": -3.5878148078918457,
230
+ "logps/rejected": -4.147099494934082,
231
+ "loss": 0.703,
232
+ "rewards/accuracies": 0.4749999940395355,
233
+ "rewards/chosen": -0.047407474368810654,
234
+ "rewards/margins": 0.005889671854674816,
235
+ "rewards/rejected": -0.05329713970422745,
236
+ "step": 130
237
+ },
238
+ {
239
+ "epoch": 0.10740314537782893,
240
+ "grad_norm": 2.1541309356689453,
241
+ "learning_rate": 4.4627782041442826e-05,
242
+ "logits/chosen": -0.48593592643737793,
243
+ "logits/rejected": -0.4823059141635895,
244
+ "logps/chosen": -3.6085586547851562,
245
+ "logps/rejected": -3.899576187133789,
246
+ "loss": 0.7012,
247
+ "rewards/accuracies": 0.4749999940395355,
248
+ "rewards/chosen": -0.06346064805984497,
249
+ "rewards/margins": -0.018461909145116806,
250
+ "rewards/rejected": -0.044998738914728165,
251
+ "step": 140
252
+ },
253
+ {
254
+ "epoch": 0.11507479861910241,
255
+ "grad_norm": 1.4447782039642334,
256
+ "learning_rate": 4.424405218726017e-05,
257
+ "logits/chosen": -0.5145712494850159,
258
+ "logits/rejected": -0.5148640275001526,
259
+ "logps/chosen": -4.518651962280273,
260
+ "logps/rejected": -3.0175552368164062,
261
+ "loss": 0.6934,
262
+ "rewards/accuracies": 0.42500001192092896,
263
+ "rewards/chosen": -0.06713158637285233,
264
+ "rewards/margins": -0.025863245129585266,
265
+ "rewards/rejected": -0.04126833751797676,
266
+ "step": 150
267
+ },
268
+ {
269
+ "epoch": 0.11507479861910241,
270
+ "eval_logits/chosen": -0.2573604881763458,
271
+ "eval_logits/rejected": -0.25465065240859985,
272
+ "eval_logps/chosen": -3.439135789871216,
273
+ "eval_logps/rejected": -3.6858487129211426,
274
+ "eval_loss": 0.691031813621521,
275
+ "eval_rewards/accuracies": 0.512499988079071,
276
+ "eval_rewards/chosen": -0.04062613099813461,
277
+ "eval_rewards/margins": -0.005622314754873514,
278
+ "eval_rewards/rejected": -0.035003818571567535,
279
+ "eval_runtime": 87.701,
280
+ "eval_samples_per_second": 29.122,
281
+ "eval_steps_per_second": 0.912,
282
+ "step": 150
283
+ },
284
+ {
285
+ "epoch": 0.12274645186037592,
286
+ "grad_norm": 2.1208548545837402,
287
+ "learning_rate": 4.386032233307752e-05,
288
+ "logits/chosen": -0.4267118573188782,
289
+ "logits/rejected": -0.42528724670410156,
290
+ "logps/chosen": -2.49307918548584,
291
+ "logps/rejected": -5.034300804138184,
292
+ "loss": 0.6927,
293
+ "rewards/accuracies": 0.574999988079071,
294
+ "rewards/chosen": -0.02940777875483036,
295
+ "rewards/margins": 0.01965685375034809,
296
+ "rewards/rejected": -0.04906462877988815,
297
+ "step": 160
298
+ },
299
+ {
300
+ "epoch": 0.13041810510164942,
301
+ "grad_norm": 1.4776760339736938,
302
+ "learning_rate": 4.347659247889486e-05,
303
+ "logits/chosen": -0.5030231475830078,
304
+ "logits/rejected": -0.5042341947555542,
305
+ "logps/chosen": -2.0654220581054688,
306
+ "logps/rejected": -4.4005961418151855,
307
+ "loss": 0.6875,
308
+ "rewards/accuracies": 0.7250000238418579,
309
+ "rewards/chosen": 0.0012591822305694222,
310
+ "rewards/margins": 0.07784555107355118,
311
+ "rewards/rejected": -0.07658636569976807,
312
+ "step": 170
313
+ },
314
+ {
315
+ "epoch": 0.1380897583429229,
316
+ "grad_norm": 1.282079815864563,
317
+ "learning_rate": 4.309286262471221e-05,
318
+ "logits/chosen": -0.45819562673568726,
319
+ "logits/rejected": -0.4634513258934021,
320
+ "logps/chosen": -3.5271224975585938,
321
+ "logps/rejected": -3.9698429107666016,
322
+ "loss": 0.6878,
323
+ "rewards/accuracies": 0.5249999761581421,
324
+ "rewards/chosen": -0.026808280497789383,
325
+ "rewards/margins": 0.02008042298257351,
326
+ "rewards/rejected": -0.04688870906829834,
327
+ "step": 180
328
+ },
329
+ {
330
+ "epoch": 0.1457614115841964,
331
+ "grad_norm": 1.368600606918335,
332
+ "learning_rate": 4.270913277052955e-05,
333
+ "logits/chosen": -0.384149432182312,
334
+ "logits/rejected": -0.3903164267539978,
335
+ "logps/chosen": -3.522733211517334,
336
+ "logps/rejected": -3.272055149078369,
337
+ "loss": 0.7013,
338
+ "rewards/accuracies": 0.4749999940395355,
339
+ "rewards/chosen": -0.037452831864356995,
340
+ "rewards/margins": -0.00283648818731308,
341
+ "rewards/rejected": -0.034616343677043915,
342
+ "step": 190
343
+ },
344
+ {
345
+ "epoch": 0.1534330648254699,
346
+ "grad_norm": 1.9209519624710083,
347
+ "learning_rate": 4.23254029163469e-05,
348
+ "logits/chosen": -0.5128501653671265,
349
+ "logits/rejected": -0.5161421298980713,
350
+ "logps/chosen": -2.724151134490967,
351
+ "logps/rejected": -3.3391120433807373,
352
+ "loss": 0.6932,
353
+ "rewards/accuracies": 0.5,
354
+ "rewards/chosen": -0.008422130718827248,
355
+ "rewards/margins": 0.02306986413896084,
356
+ "rewards/rejected": -0.03149199113249779,
357
+ "step": 200
358
+ },
359
+ {
360
+ "epoch": 0.1534330648254699,
361
+ "eval_logits/chosen": -0.2552909255027771,
362
+ "eval_logits/rejected": -0.25272154808044434,
363
+ "eval_logps/chosen": -3.351407527923584,
364
+ "eval_logps/rejected": -3.6925933361053467,
365
+ "eval_loss": 0.6919052600860596,
366
+ "eval_rewards/accuracies": 0.528124988079071,
367
+ "eval_rewards/chosen": -0.031853340566158295,
368
+ "eval_rewards/margins": 0.0038249720819294453,
369
+ "eval_rewards/rejected": -0.03567831218242645,
370
+ "eval_runtime": 87.7075,
371
+ "eval_samples_per_second": 29.12,
372
+ "eval_steps_per_second": 0.912,
373
+ "step": 200
374
+ },
375
+ {
376
+ "epoch": 0.1611047180667434,
377
+ "grad_norm": 1.575499415397644,
378
+ "learning_rate": 4.194167306216424e-05,
379
+ "logits/chosen": -0.45738959312438965,
380
+ "logits/rejected": -0.45437225699424744,
381
+ "logps/chosen": -4.087313175201416,
382
+ "logps/rejected": -2.974914073944092,
383
+ "loss": 0.7002,
384
+ "rewards/accuracies": 0.4749999940395355,
385
+ "rewards/chosen": -0.051591504365205765,
386
+ "rewards/margins": -0.020506689324975014,
387
+ "rewards/rejected": -0.0310848206281662,
388
+ "step": 210
389
+ },
390
+ {
391
+ "epoch": 0.16877637130801687,
392
+ "grad_norm": 1.5426521301269531,
393
+ "learning_rate": 4.155794320798158e-05,
394
+ "logits/chosen": -0.4632241725921631,
395
+ "logits/rejected": -0.4625597596168518,
396
+ "logps/chosen": -2.200758457183838,
397
+ "logps/rejected": -3.836440324783325,
398
+ "loss": 0.6852,
399
+ "rewards/accuracies": 0.6499999761581421,
400
+ "rewards/chosen": 0.030624931678175926,
401
+ "rewards/margins": 0.11931898444890976,
402
+ "rewards/rejected": -0.08869405090808868,
403
+ "step": 220
404
+ },
405
+ {
406
+ "epoch": 0.17644802454929037,
407
+ "grad_norm": 1.3270576000213623,
408
+ "learning_rate": 4.117421335379893e-05,
409
+ "logits/chosen": -0.4626352787017822,
410
+ "logits/rejected": -0.4678708016872406,
411
+ "logps/chosen": -2.704134464263916,
412
+ "logps/rejected": -3.5658984184265137,
413
+ "loss": 0.6898,
414
+ "rewards/accuracies": 0.6000000238418579,
415
+ "rewards/chosen": -0.010677630081772804,
416
+ "rewards/margins": 0.02222255989909172,
417
+ "rewards/rejected": -0.032900188118219376,
418
+ "step": 230
419
+ },
420
+ {
421
+ "epoch": 0.18411967779056387,
422
+ "grad_norm": 1.4585351943969727,
423
+ "learning_rate": 4.0790483499616274e-05,
424
+ "logits/chosen": -0.32787808775901794,
425
+ "logits/rejected": -0.3283527195453644,
426
+ "logps/chosen": -3.4351840019226074,
427
+ "logps/rejected": -3.090237617492676,
428
+ "loss": 0.6953,
429
+ "rewards/accuracies": 0.4749999940395355,
430
+ "rewards/chosen": -0.02141396515071392,
431
+ "rewards/margins": -0.00582413375377655,
432
+ "rewards/rejected": -0.01558983325958252,
433
+ "step": 240
434
+ },
435
+ {
436
+ "epoch": 0.19179133103183735,
437
+ "grad_norm": 1.5329344272613525,
438
+ "learning_rate": 4.0406753645433616e-05,
439
+ "logits/chosen": -0.4365290105342865,
440
+ "logits/rejected": -0.431086927652359,
441
+ "logps/chosen": -4.269787788391113,
442
+ "logps/rejected": -2.5051932334899902,
443
+ "loss": 0.7021,
444
+ "rewards/accuracies": 0.42500001192092896,
445
+ "rewards/chosen": -0.03114442527294159,
446
+ "rewards/margins": -0.03054250404238701,
447
+ "rewards/rejected": -0.0006019207648932934,
448
+ "step": 250
449
+ },
450
+ {
451
+ "epoch": 0.19179133103183735,
452
+ "eval_logits/chosen": -0.25592881441116333,
453
+ "eval_logits/rejected": -0.2537047863006592,
454
+ "eval_logps/chosen": -2.992680311203003,
455
+ "eval_logps/rejected": -3.351801633834839,
456
+ "eval_loss": 0.6899347901344299,
457
+ "eval_rewards/accuracies": 0.5249999761581421,
458
+ "eval_rewards/chosen": 0.00401937635615468,
459
+ "eval_rewards/margins": 0.005618534050881863,
460
+ "eval_rewards/rejected": -0.0015991575783118606,
461
+ "eval_runtime": 87.6512,
462
+ "eval_samples_per_second": 29.138,
463
+ "eval_steps_per_second": 0.913,
464
+ "step": 250
465
+ },
466
+ {
467
+ "epoch": 0.19946298427311085,
468
+ "grad_norm": 2.1084399223327637,
469
+ "learning_rate": 4.0023023791250965e-05,
470
+ "logits/chosen": -0.4519824981689453,
471
+ "logits/rejected": -0.4398951530456543,
472
+ "logps/chosen": -2.484307050704956,
473
+ "logps/rejected": -3.2058215141296387,
474
+ "loss": 0.6891,
475
+ "rewards/accuracies": 0.6000000238418579,
476
+ "rewards/chosen": 0.010583693161606789,
477
+ "rewards/margins": 0.03147741034626961,
478
+ "rewards/rejected": -0.02089371532201767,
479
+ "step": 260
480
+ },
481
+ {
482
+ "epoch": 0.20713463751438435,
483
+ "grad_norm": 1.2669779062271118,
484
+ "learning_rate": 3.963929393706831e-05,
485
+ "logits/chosen": -0.4561208188533783,
486
+ "logits/rejected": -0.46242856979370117,
487
+ "logps/chosen": -2.3247485160827637,
488
+ "logps/rejected": -4.493135929107666,
489
+ "loss": 0.6886,
490
+ "rewards/accuracies": 0.550000011920929,
491
+ "rewards/chosen": -0.0006832152721472085,
492
+ "rewards/margins": 0.01231946051120758,
493
+ "rewards/rejected": -0.013002678751945496,
494
+ "step": 270
495
+ },
496
+ {
497
+ "epoch": 0.21480629075565785,
498
+ "grad_norm": 2.359649181365967,
499
+ "learning_rate": 3.925556408288565e-05,
500
+ "logits/chosen": -0.41936391592025757,
501
+ "logits/rejected": -0.4227515161037445,
502
+ "logps/chosen": -3.846536636352539,
503
+ "logps/rejected": -2.6847872734069824,
504
+ "loss": 0.6942,
505
+ "rewards/accuracies": 0.42500001192092896,
506
+ "rewards/chosen": -0.0359012708067894,
507
+ "rewards/margins": -0.027397548779845238,
508
+ "rewards/rejected": -0.00850372388958931,
509
+ "step": 280
510
+ },
511
+ {
512
+ "epoch": 0.22247794399693133,
513
+ "grad_norm": 2.732644557952881,
514
+ "learning_rate": 3.8871834228703e-05,
515
+ "logits/chosen": -0.41848206520080566,
516
+ "logits/rejected": -0.42105674743652344,
517
+ "logps/chosen": -3.4439868927001953,
518
+ "logps/rejected": -3.4636013507843018,
519
+ "loss": 0.692,
520
+ "rewards/accuracies": 0.5249999761581421,
521
+ "rewards/chosen": -0.038081876933574677,
522
+ "rewards/margins": -0.0026010065339505672,
523
+ "rewards/rejected": -0.03548087924718857,
524
+ "step": 290
525
+ },
526
+ {
527
+ "epoch": 0.23014959723820483,
528
+ "grad_norm": 1.7410922050476074,
529
+ "learning_rate": 3.848810437452034e-05,
530
+ "logits/chosen": -0.41233521699905396,
531
+ "logits/rejected": -0.4056723117828369,
532
+ "logps/chosen": -2.7670276165008545,
533
+ "logps/rejected": -4.538814544677734,
534
+ "loss": 0.6859,
535
+ "rewards/accuracies": 0.6000000238418579,
536
+ "rewards/chosen": -0.03271554037928581,
537
+ "rewards/margins": 0.008648352697491646,
538
+ "rewards/rejected": -0.04136389121413231,
539
+ "step": 300
540
+ },
541
+ {
542
+ "epoch": 0.23014959723820483,
543
+ "eval_logits/chosen": -0.25867313146591187,
544
+ "eval_logits/rejected": -0.2568739354610443,
545
+ "eval_logps/chosen": -3.2079968452453613,
546
+ "eval_logps/rejected": -3.6974151134490967,
547
+ "eval_loss": 0.6905180215835571,
548
+ "eval_rewards/accuracies": 0.543749988079071,
549
+ "eval_rewards/chosen": -0.01751227304339409,
550
+ "eval_rewards/margins": 0.018648196011781693,
551
+ "eval_rewards/rejected": -0.03616046532988548,
552
+ "eval_runtime": 87.8864,
553
+ "eval_samples_per_second": 29.06,
554
+ "eval_steps_per_second": 0.91,
555
+ "step": 300
556
+ },
557
+ {
558
+ "epoch": 0.23782125047947833,
559
+ "grad_norm": 1.6948188543319702,
560
+ "learning_rate": 3.810437452033768e-05,
561
+ "logits/chosen": -0.4763808250427246,
562
+ "logits/rejected": -0.47943514585494995,
563
+ "logps/chosen": -3.1502089500427246,
564
+ "logps/rejected": -4.5027756690979,
565
+ "loss": 0.6943,
566
+ "rewards/accuracies": 0.6499999761581421,
567
+ "rewards/chosen": -0.018290940672159195,
568
+ "rewards/margins": 0.01174425520002842,
569
+ "rewards/rejected": -0.030035194009542465,
570
+ "step": 310
571
+ },
572
+ {
573
+ "epoch": 0.24549290372075183,
574
+ "grad_norm": 1.2756513357162476,
575
+ "learning_rate": 3.772064466615503e-05,
576
+ "logits/chosen": -0.5276287198066711,
577
+ "logits/rejected": -0.5248805284500122,
578
+ "logps/chosen": -3.315579891204834,
579
+ "logps/rejected": -2.8239669799804688,
580
+ "loss": 0.689,
581
+ "rewards/accuracies": 0.6000000238418579,
582
+ "rewards/chosen": 0.0013980341609567404,
583
+ "rewards/margins": 0.03776642307639122,
584
+ "rewards/rejected": -0.036368388682603836,
585
+ "step": 320
586
+ },
587
+ {
588
+ "epoch": 0.25316455696202533,
589
+ "grad_norm": 1.7512315511703491,
590
+ "learning_rate": 3.733691481197237e-05,
591
+ "logits/chosen": -0.4925498366355896,
592
+ "logits/rejected": -0.49201974272727966,
593
+ "logps/chosen": -2.7408628463745117,
594
+ "logps/rejected": -3.967554807662964,
595
+ "loss": 0.6947,
596
+ "rewards/accuracies": 0.550000011920929,
597
+ "rewards/chosen": 0.011951248161494732,
598
+ "rewards/margins": 0.022660424932837486,
599
+ "rewards/rejected": -0.01070917397737503,
600
+ "step": 330
601
+ },
602
+ {
603
+ "epoch": 0.26083621020329883,
604
+ "grad_norm": 2.073042869567871,
605
+ "learning_rate": 3.6953184957789715e-05,
606
+ "logits/chosen": -0.4371699392795563,
607
+ "logits/rejected": -0.4345782697200775,
608
+ "logps/chosen": -2.061657190322876,
609
+ "logps/rejected": -3.6886394023895264,
610
+ "loss": 0.691,
611
+ "rewards/accuracies": 0.5249999761581421,
612
+ "rewards/chosen": 0.018956389278173447,
613
+ "rewards/margins": 0.023976778611540794,
614
+ "rewards/rejected": -0.005020388402044773,
615
+ "step": 340
616
+ },
617
+ {
618
+ "epoch": 0.2685078634445723,
619
+ "grad_norm": 1.3207100629806519,
620
+ "learning_rate": 3.6569455103607064e-05,
621
+ "logits/chosen": -0.3427134156227112,
622
+ "logits/rejected": -0.3307674825191498,
623
+ "logps/chosen": -2.7634048461914062,
624
+ "logps/rejected": -3.556063413619995,
625
+ "loss": 0.6961,
626
+ "rewards/accuracies": 0.5,
627
+ "rewards/chosen": -0.006752232555299997,
628
+ "rewards/margins": 0.004960778169333935,
629
+ "rewards/rejected": -0.01171301119029522,
630
+ "step": 350
631
+ },
632
+ {
633
+ "epoch": 0.2685078634445723,
634
+ "eval_logits/chosen": -0.2583015561103821,
635
+ "eval_logits/rejected": -0.2559833824634552,
636
+ "eval_logps/chosen": -3.264441728591919,
637
+ "eval_logps/rejected": -3.69817852973938,
638
+ "eval_loss": 0.6912429928779602,
639
+ "eval_rewards/accuracies": 0.5375000238418579,
640
+ "eval_rewards/chosen": -0.023156724870204926,
641
+ "eval_rewards/margins": 0.013080140575766563,
642
+ "eval_rewards/rejected": -0.03623687103390694,
643
+ "eval_runtime": 87.903,
644
+ "eval_samples_per_second": 29.055,
645
+ "eval_steps_per_second": 0.91,
646
+ "step": 350
647
+ },
648
+ {
649
+ "epoch": 0.2761795166858458,
650
+ "grad_norm": 1.3935655355453491,
651
+ "learning_rate": 3.6185725249424406e-05,
652
+ "logits/chosen": -0.34501805901527405,
653
+ "logits/rejected": -0.3470131456851959,
654
+ "logps/chosen": -3.49810791015625,
655
+ "logps/rejected": -3.8505330085754395,
656
+ "loss": 0.689,
657
+ "rewards/accuracies": 0.4749999940395355,
658
+ "rewards/chosen": -0.05252550169825554,
659
+ "rewards/margins": -0.009586334228515625,
660
+ "rewards/rejected": -0.042939163744449615,
661
+ "step": 360
662
+ },
663
+ {
664
+ "epoch": 0.2838511699271193,
665
+ "grad_norm": 1.6383577585220337,
666
+ "learning_rate": 3.580199539524175e-05,
667
+ "logits/chosen": -0.48913854360580444,
668
+ "logits/rejected": -0.4845835566520691,
669
+ "logps/chosen": -3.775874376296997,
670
+ "logps/rejected": -2.7326130867004395,
671
+ "loss": 0.6899,
672
+ "rewards/accuracies": 0.574999988079071,
673
+ "rewards/chosen": -0.04597536846995354,
674
+ "rewards/margins": -0.018767457455396652,
675
+ "rewards/rejected": -0.027207905426621437,
676
+ "step": 370
677
+ },
678
+ {
679
+ "epoch": 0.2915228231683928,
680
+ "grad_norm": 1.5284889936447144,
681
+ "learning_rate": 3.54182655410591e-05,
682
+ "logits/chosen": -0.3916495442390442,
683
+ "logits/rejected": -0.3948409855365753,
684
+ "logps/chosen": -3.680704116821289,
685
+ "logps/rejected": -3.731623411178589,
686
+ "loss": 0.6865,
687
+ "rewards/accuracies": 0.5249999761581421,
688
+ "rewards/chosen": -0.02748117782175541,
689
+ "rewards/margins": 0.013354331254959106,
690
+ "rewards/rejected": -0.04083551466464996,
691
+ "step": 380
692
+ },
693
+ {
694
+ "epoch": 0.2991944764096663,
695
+ "grad_norm": 1.75348699092865,
696
+ "learning_rate": 3.503453568687644e-05,
697
+ "logits/chosen": -0.3796854615211487,
698
+ "logits/rejected": -0.38789474964141846,
699
+ "logps/chosen": -2.4654390811920166,
700
+ "logps/rejected": -5.180593490600586,
701
+ "loss": 0.6917,
702
+ "rewards/accuracies": 0.6499999761581421,
703
+ "rewards/chosen": -0.019467497244477272,
704
+ "rewards/margins": 0.08367259800434113,
705
+ "rewards/rejected": -0.10314009338617325,
706
+ "step": 390
707
+ },
708
+ {
709
+ "epoch": 0.3068661296509398,
710
+ "grad_norm": 1.9211453199386597,
711
+ "learning_rate": 3.465080583269378e-05,
712
+ "logits/chosen": -0.42692264914512634,
713
+ "logits/rejected": -0.42641615867614746,
714
+ "logps/chosen": -2.586097240447998,
715
+ "logps/rejected": -4.711082458496094,
716
+ "loss": 0.6978,
717
+ "rewards/accuracies": 0.5249999761581421,
718
+ "rewards/chosen": -0.04758203774690628,
719
+ "rewards/margins": 0.018220845609903336,
720
+ "rewards/rejected": -0.06580288708209991,
721
+ "step": 400
722
+ },
723
+ {
724
+ "epoch": 0.3068661296509398,
725
+ "eval_logits/chosen": -0.25191357731819153,
726
+ "eval_logits/rejected": -0.24964801967144012,
727
+ "eval_logps/chosen": -3.459468126296997,
728
+ "eval_logps/rejected": -3.9026706218719482,
729
+ "eval_loss": 0.6893244385719299,
730
+ "eval_rewards/accuracies": 0.5249999761581421,
731
+ "eval_rewards/chosen": -0.04265937954187393,
732
+ "eval_rewards/margins": 0.014026666060090065,
733
+ "eval_rewards/rejected": -0.05668604373931885,
734
+ "eval_runtime": 87.8645,
735
+ "eval_samples_per_second": 29.068,
736
+ "eval_steps_per_second": 0.91,
737
+ "step": 400
738
+ },
739
+ {
740
+ "epoch": 0.3145377828922133,
741
+ "grad_norm": 1.5234233140945435,
742
+ "learning_rate": 3.426707597851113e-05,
743
+ "logits/chosen": -0.28339290618896484,
744
+ "logits/rejected": -0.27566584944725037,
745
+ "logps/chosen": -3.7383079528808594,
746
+ "logps/rejected": -3.349996566772461,
747
+ "loss": 0.6824,
748
+ "rewards/accuracies": 0.4749999940395355,
749
+ "rewards/chosen": -0.04696209728717804,
750
+ "rewards/margins": -0.0003062840551137924,
751
+ "rewards/rejected": -0.0466558113694191,
752
+ "step": 410
753
+ },
754
+ {
755
+ "epoch": 0.3222094361334868,
756
+ "grad_norm": 1.5943760871887207,
757
+ "learning_rate": 3.388334612432847e-05,
758
+ "logits/chosen": -0.440364271402359,
759
+ "logits/rejected": -0.4411134719848633,
760
+ "logps/chosen": -2.43839430809021,
761
+ "logps/rejected": -4.264366626739502,
762
+ "loss": 0.6874,
763
+ "rewards/accuracies": 0.625,
764
+ "rewards/chosen": -0.002678838325664401,
765
+ "rewards/margins": 0.06886979192495346,
766
+ "rewards/rejected": -0.07154864072799683,
767
+ "step": 420
768
+ },
769
+ {
770
+ "epoch": 0.32988108937476024,
771
+ "grad_norm": 2.3275911808013916,
772
+ "learning_rate": 3.3499616270145814e-05,
773
+ "logits/chosen": -0.4382743239402771,
774
+ "logits/rejected": -0.4452611804008484,
775
+ "logps/chosen": -4.034234523773193,
776
+ "logps/rejected": -3.718547821044922,
777
+ "loss": 0.6962,
778
+ "rewards/accuracies": 0.550000011920929,
779
+ "rewards/chosen": -0.05849426984786987,
780
+ "rewards/margins": 0.03669988363981247,
781
+ "rewards/rejected": -0.09519414603710175,
782
+ "step": 430
783
+ },
784
+ {
785
+ "epoch": 0.33755274261603374,
786
+ "grad_norm": 1.7006807327270508,
787
+ "learning_rate": 3.311588641596316e-05,
788
+ "logits/chosen": -0.488353431224823,
789
+ "logits/rejected": -0.4902741014957428,
790
+ "logps/chosen": -2.8092918395996094,
791
+ "logps/rejected": -4.1550493240356445,
792
+ "loss": 0.6961,
793
+ "rewards/accuracies": 0.550000011920929,
794
+ "rewards/chosen": -0.017056407406926155,
795
+ "rewards/margins": 0.026486407965421677,
796
+ "rewards/rejected": -0.04354281350970268,
797
+ "step": 440
798
+ },
799
+ {
800
+ "epoch": 0.34522439585730724,
801
+ "grad_norm": 2.1540279388427734,
802
+ "learning_rate": 3.2732156561780505e-05,
803
+ "logits/chosen": -0.46933096647262573,
804
+ "logits/rejected": -0.47831687331199646,
805
+ "logps/chosen": -3.4161593914031982,
806
+ "logps/rejected": -3.7839865684509277,
807
+ "loss": 0.6963,
808
+ "rewards/accuracies": 0.4749999940395355,
809
+ "rewards/chosen": -0.062318772077560425,
810
+ "rewards/margins": -0.014327460899949074,
811
+ "rewards/rejected": -0.0479913167655468,
812
+ "step": 450
813
+ },
814
+ {
815
+ "epoch": 0.34522439585730724,
816
+ "eval_logits/chosen": -0.2543574869632721,
817
+ "eval_logits/rejected": -0.25201791524887085,
818
+ "eval_logps/chosen": -3.321566343307495,
819
+ "eval_logps/rejected": -3.75457763671875,
820
+ "eval_loss": 0.6880484819412231,
821
+ "eval_rewards/accuracies": 0.5249999761581421,
822
+ "eval_rewards/chosen": -0.028869222849607468,
823
+ "eval_rewards/margins": 0.01300754863768816,
824
+ "eval_rewards/rejected": -0.04187677055597305,
825
+ "eval_runtime": 87.6848,
826
+ "eval_samples_per_second": 29.127,
827
+ "eval_steps_per_second": 0.912,
828
+ "step": 450
829
+ },
830
+ {
831
+ "epoch": 0.35289604909858074,
832
+ "grad_norm": 2.41361665725708,
833
+ "learning_rate": 3.2348426707597854e-05,
834
+ "logits/chosen": -0.517076849937439,
835
+ "logits/rejected": -0.5212947130203247,
836
+ "logps/chosen": -3.707463026046753,
837
+ "logps/rejected": -2.6402366161346436,
838
+ "loss": 0.6878,
839
+ "rewards/accuracies": 0.42500001192092896,
840
+ "rewards/chosen": -0.03469429910182953,
841
+ "rewards/margins": -0.0030276328325271606,
842
+ "rewards/rejected": -0.03166666626930237,
843
+ "step": 460
844
+ },
845
+ {
846
+ "epoch": 0.36056770233985425,
847
+ "grad_norm": 1.4909201860427856,
848
+ "learning_rate": 3.1964696853415196e-05,
849
+ "logits/chosen": -0.44358164072036743,
850
+ "logits/rejected": -0.4401718080043793,
851
+ "logps/chosen": -2.663454532623291,
852
+ "logps/rejected": -4.2893218994140625,
853
+ "loss": 0.6871,
854
+ "rewards/accuracies": 0.699999988079071,
855
+ "rewards/chosen": 0.005995375569909811,
856
+ "rewards/margins": 0.09306643158197403,
857
+ "rewards/rejected": -0.08707105368375778,
858
+ "step": 470
859
+ },
860
+ {
861
+ "epoch": 0.36823935558112775,
862
+ "grad_norm": 1.5664546489715576,
863
+ "learning_rate": 3.1580966999232545e-05,
864
+ "logits/chosen": -0.5029574632644653,
865
+ "logits/rejected": -0.5032514333724976,
866
+ "logps/chosen": -3.0805327892303467,
867
+ "logps/rejected": -3.4728941917419434,
868
+ "loss": 0.7022,
869
+ "rewards/accuracies": 0.44999998807907104,
870
+ "rewards/chosen": -0.03778943419456482,
871
+ "rewards/margins": 0.011032382026314735,
872
+ "rewards/rejected": -0.048821814358234406,
873
+ "step": 480
874
+ },
875
+ {
876
+ "epoch": 0.37591100882240125,
877
+ "grad_norm": 1.4422327280044556,
878
+ "learning_rate": 3.119723714504989e-05,
879
+ "logits/chosen": -0.4989328384399414,
880
+ "logits/rejected": -0.49760347604751587,
881
+ "logps/chosen": -3.063786745071411,
882
+ "logps/rejected": -3.134028434753418,
883
+ "loss": 0.6919,
884
+ "rewards/accuracies": 0.5,
885
+ "rewards/chosen": -0.03893281891942024,
886
+ "rewards/margins": -0.007891304790973663,
887
+ "rewards/rejected": -0.03104151412844658,
888
+ "step": 490
889
+ },
890
+ {
891
+ "epoch": 0.3835826620636747,
892
+ "grad_norm": 1.7234938144683838,
893
+ "learning_rate": 3.0813507290867236e-05,
894
+ "logits/chosen": -0.4708559513092041,
895
+ "logits/rejected": -0.4755636155605316,
896
+ "logps/chosen": -3.4675452709198,
897
+ "logps/rejected": -4.40737247467041,
898
+ "loss": 0.6909,
899
+ "rewards/accuracies": 0.4749999940395355,
900
+ "rewards/chosen": -0.02458677999675274,
901
+ "rewards/margins": 0.0017846006667241454,
902
+ "rewards/rejected": -0.02637138031423092,
903
+ "step": 500
904
+ },
905
+ {
906
+ "epoch": 0.3835826620636747,
907
+ "eval_logits/chosen": -0.25855669379234314,
908
+ "eval_logits/rejected": -0.2564457058906555,
909
+ "eval_logps/chosen": -3.37125825881958,
910
+ "eval_logps/rejected": -3.7394096851348877,
911
+ "eval_loss": 0.6893431544303894,
912
+ "eval_rewards/accuracies": 0.515625,
913
+ "eval_rewards/chosen": -0.03383838012814522,
914
+ "eval_rewards/margins": 0.006521561183035374,
915
+ "eval_rewards/rejected": -0.04035994037985802,
916
+ "eval_runtime": 87.8159,
917
+ "eval_samples_per_second": 29.084,
918
+ "eval_steps_per_second": 0.911,
919
+ "step": 500
920
+ },
921
+ {
922
+ "epoch": 0.3912543153049482,
923
+ "grad_norm": 1.5501247644424438,
924
+ "learning_rate": 3.0429777436684575e-05,
925
+ "logits/chosen": -0.4411280155181885,
926
+ "logits/rejected": -0.4376070499420166,
927
+ "logps/chosen": -3.4258601665496826,
928
+ "logps/rejected": -3.10990309715271,
929
+ "loss": 0.6846,
930
+ "rewards/accuracies": 0.5,
931
+ "rewards/chosen": -0.0510549321770668,
932
+ "rewards/margins": -0.015095305629074574,
933
+ "rewards/rejected": -0.035959623754024506,
934
+ "step": 510
935
+ },
936
+ {
937
+ "epoch": 0.3989259685462217,
938
+ "grad_norm": 1.5012112855911255,
939
+ "learning_rate": 3.0046047582501917e-05,
940
+ "logits/chosen": -0.4509127140045166,
941
+ "logits/rejected": -0.4517589509487152,
942
+ "logps/chosen": -2.4196524620056152,
943
+ "logps/rejected": -3.98419451713562,
944
+ "loss": 0.6872,
945
+ "rewards/accuracies": 0.625,
946
+ "rewards/chosen": 0.0005872026085853577,
947
+ "rewards/margins": 0.0763540267944336,
948
+ "rewards/rejected": -0.07576681673526764,
949
+ "step": 520
950
+ },
951
+ {
952
+ "epoch": 0.4065976217874952,
953
+ "grad_norm": 2.1596052646636963,
954
+ "learning_rate": 2.9662317728319266e-05,
955
+ "logits/chosen": -0.41014641523361206,
956
+ "logits/rejected": -0.4043218195438385,
957
+ "logps/chosen": -3.8312087059020996,
958
+ "logps/rejected": -2.908543109893799,
959
+ "loss": 0.6886,
960
+ "rewards/accuracies": 0.44999998807907104,
961
+ "rewards/chosen": -0.02407076209783554,
962
+ "rewards/margins": 0.02513458952307701,
963
+ "rewards/rejected": -0.04920535162091255,
964
+ "step": 530
965
+ },
966
+ {
967
+ "epoch": 0.4142692750287687,
968
+ "grad_norm": 1.4137400388717651,
969
+ "learning_rate": 2.9278587874136608e-05,
970
+ "logits/chosen": -0.4017483592033386,
971
+ "logits/rejected": -0.39557427167892456,
972
+ "logps/chosen": -3.8227367401123047,
973
+ "logps/rejected": -3.195641279220581,
974
+ "loss": 0.6934,
975
+ "rewards/accuracies": 0.4749999940395355,
976
+ "rewards/chosen": -0.03194689378142357,
977
+ "rewards/margins": -0.01945153810083866,
978
+ "rewards/rejected": -0.012495351955294609,
979
+ "step": 540
980
+ },
981
+ {
982
+ "epoch": 0.4219409282700422,
983
+ "grad_norm": 1.4084391593933105,
984
+ "learning_rate": 2.8894858019953953e-05,
985
+ "logits/chosen": -0.4596850872039795,
986
+ "logits/rejected": -0.4715039134025574,
987
+ "logps/chosen": -3.1471800804138184,
988
+ "logps/rejected": -3.90801739692688,
989
+ "loss": 0.6944,
990
+ "rewards/accuracies": 0.5,
991
+ "rewards/chosen": -0.019990995526313782,
992
+ "rewards/margins": 0.018570415675640106,
993
+ "rewards/rejected": -0.03856140747666359,
994
+ "step": 550
995
+ },
996
+ {
997
+ "epoch": 0.4219409282700422,
998
+ "eval_logits/chosen": -0.26123708486557007,
999
+ "eval_logits/rejected": -0.25891199707984924,
1000
+ "eval_logps/chosen": -3.1744627952575684,
1001
+ "eval_logps/rejected": -3.591878890991211,
1002
+ "eval_loss": 0.6874387264251709,
1003
+ "eval_rewards/accuracies": 0.515625,
1004
+ "eval_rewards/chosen": -0.014158882200717926,
1005
+ "eval_rewards/margins": 0.011447983793914318,
1006
+ "eval_rewards/rejected": -0.02560686506330967,
1007
+ "eval_runtime": 90.5755,
1008
+ "eval_samples_per_second": 28.197,
1009
+ "eval_steps_per_second": 0.883,
1010
+ "step": 550
1011
+ },
1012
+ {
1013
+ "epoch": 0.4296125815113157,
1014
+ "grad_norm": 3.040137529373169,
1015
+ "learning_rate": 2.85111281657713e-05,
1016
+ "logits/chosen": -0.41563597321510315,
1017
+ "logits/rejected": -0.41134652495384216,
1018
+ "logps/chosen": -2.954399824142456,
1019
+ "logps/rejected": -2.869027853012085,
1020
+ "loss": 0.7005,
1021
+ "rewards/accuracies": 0.699999988079071,
1022
+ "rewards/chosen": 0.04915647208690643,
1023
+ "rewards/margins": 0.0781073272228241,
1024
+ "rewards/rejected": -0.02895086072385311,
1025
+ "step": 560
1026
+ },
1027
+ {
1028
+ "epoch": 0.4372842347525892,
1029
+ "grad_norm": 1.730731725692749,
1030
+ "learning_rate": 2.8127398311588644e-05,
1031
+ "logits/chosen": -0.43522629141807556,
1032
+ "logits/rejected": -0.42925986647605896,
1033
+ "logps/chosen": -3.231485366821289,
1034
+ "logps/rejected": -3.533066511154175,
1035
+ "loss": 0.6926,
1036
+ "rewards/accuracies": 0.6499999761581421,
1037
+ "rewards/chosen": 0.012996886856853962,
1038
+ "rewards/margins": 0.05765851214528084,
1039
+ "rewards/rejected": -0.04466162249445915,
1040
+ "step": 570
1041
+ },
1042
+ {
1043
+ "epoch": 0.44495588799386265,
1044
+ "grad_norm": 1.4563325643539429,
1045
+ "learning_rate": 2.7743668457405987e-05,
1046
+ "logits/chosen": -0.4720652103424072,
1047
+ "logits/rejected": -0.46499529480934143,
1048
+ "logps/chosen": -3.880791187286377,
1049
+ "logps/rejected": -3.5834224224090576,
1050
+ "loss": 0.7003,
1051
+ "rewards/accuracies": 0.5,
1052
+ "rewards/chosen": -0.055101800709962845,
1053
+ "rewards/margins": -0.01127576269209385,
1054
+ "rewards/rejected": -0.043826036155223846,
1055
+ "step": 580
1056
+ },
1057
+ {
1058
+ "epoch": 0.45262754123513615,
1059
+ "grad_norm": 1.680908441543579,
1060
+ "learning_rate": 2.7359938603223335e-05,
1061
+ "logits/chosen": -0.2684255540370941,
1062
+ "logits/rejected": -0.2682047188282013,
1063
+ "logps/chosen": -2.8263630867004395,
1064
+ "logps/rejected": -3.5271003246307373,
1065
+ "loss": 0.6887,
1066
+ "rewards/accuracies": 0.699999988079071,
1067
+ "rewards/chosen": 0.018410243093967438,
1068
+ "rewards/margins": 0.04611648991703987,
1069
+ "rewards/rejected": -0.027706250548362732,
1070
+ "step": 590
1071
+ },
1072
+ {
1073
+ "epoch": 0.46029919447640966,
1074
+ "grad_norm": 1.4875671863555908,
1075
+ "learning_rate": 2.6976208749040678e-05,
1076
+ "logits/chosen": -0.5006714463233948,
1077
+ "logits/rejected": -0.5000745058059692,
1078
+ "logps/chosen": -2.8757147789001465,
1079
+ "logps/rejected": -3.4219863414764404,
1080
+ "loss": 0.6837,
1081
+ "rewards/accuracies": 0.675000011920929,
1082
+ "rewards/chosen": 0.022861991077661514,
1083
+ "rewards/margins": 0.0631416067481041,
1084
+ "rewards/rejected": -0.04027962684631348,
1085
+ "step": 600
1086
+ },
1087
+ {
1088
+ "epoch": 0.46029919447640966,
1089
+ "eval_logits/chosen": -0.25836092233657837,
1090
+ "eval_logits/rejected": -0.2553294599056244,
1091
+ "eval_logps/chosen": -3.034031867980957,
1092
+ "eval_logps/rejected": -3.487445116043091,
1093
+ "eval_loss": 0.6917591691017151,
1094
+ "eval_rewards/accuracies": 0.515625,
1095
+ "eval_rewards/chosen": -0.00011577569239307195,
1096
+ "eval_rewards/margins": 0.015047714114189148,
1097
+ "eval_rewards/rejected": -0.015163486823439598,
1098
+ "eval_runtime": 95.32,
1099
+ "eval_samples_per_second": 26.794,
1100
+ "eval_steps_per_second": 0.839,
1101
+ "step": 600
1102
+ },
1103
+ {
1104
+ "epoch": 0.46797084771768316,
1105
+ "grad_norm": 1.0080013275146484,
1106
+ "learning_rate": 2.659247889485802e-05,
1107
+ "logits/chosen": -0.4055057466030121,
1108
+ "logits/rejected": -0.4117734432220459,
1109
+ "logps/chosen": -2.3307080268859863,
1110
+ "logps/rejected": -3.9688384532928467,
1111
+ "loss": 0.6911,
1112
+ "rewards/accuracies": 0.6000000238418579,
1113
+ "rewards/chosen": -0.004725713282823563,
1114
+ "rewards/margins": -4.6133995965647046e-06,
1115
+ "rewards/rejected": -0.004721099976450205,
1116
+ "step": 610
1117
+ },
1118
+ {
1119
+ "epoch": 0.47564250095895666,
1120
+ "grad_norm": 1.2446097135543823,
1121
+ "learning_rate": 2.620874904067537e-05,
1122
+ "logits/chosen": -0.3564910292625427,
1123
+ "logits/rejected": -0.3598317801952362,
1124
+ "logps/chosen": -2.8816721439361572,
1125
+ "logps/rejected": -3.8162410259246826,
1126
+ "loss": 0.7045,
1127
+ "rewards/accuracies": 0.4749999940395355,
1128
+ "rewards/chosen": -0.04238850623369217,
1129
+ "rewards/margins": -0.050994087010622025,
1130
+ "rewards/rejected": 0.00860558170825243,
1131
+ "step": 620
1132
+ },
1133
+ {
1134
+ "epoch": 0.48331415420023016,
1135
+ "grad_norm": 2.1006405353546143,
1136
+ "learning_rate": 2.582501918649271e-05,
1137
+ "logits/chosen": -0.4763752520084381,
1138
+ "logits/rejected": -0.4724522531032562,
1139
+ "logps/chosen": -3.6634361743927,
1140
+ "logps/rejected": -3.523616313934326,
1141
+ "loss": 0.6876,
1142
+ "rewards/accuracies": 0.550000011920929,
1143
+ "rewards/chosen": -0.015630219131708145,
1144
+ "rewards/margins": 0.03971021622419357,
1145
+ "rewards/rejected": -0.05534043163061142,
1146
+ "step": 630
1147
+ },
1148
+ {
1149
+ "epoch": 0.49098580744150366,
1150
+ "grad_norm": 1.9049338102340698,
1151
+ "learning_rate": 2.5441289332310053e-05,
1152
+ "logits/chosen": -0.46114760637283325,
1153
+ "logits/rejected": -0.4514070451259613,
1154
+ "logps/chosen": -3.082925796508789,
1155
+ "logps/rejected": -3.305220365524292,
1156
+ "loss": 0.6923,
1157
+ "rewards/accuracies": 0.44999998807907104,
1158
+ "rewards/chosen": -0.03719641640782356,
1159
+ "rewards/margins": -0.010646897368133068,
1160
+ "rewards/rejected": -0.02654952183365822,
1161
+ "step": 640
1162
+ },
1163
+ {
1164
+ "epoch": 0.49865746068277716,
1165
+ "grad_norm": 1.5372164249420166,
1166
+ "learning_rate": 2.50575594781274e-05,
1167
+ "logits/chosen": -0.4374101758003235,
1168
+ "logits/rejected": -0.4314614236354828,
1169
+ "logps/chosen": -3.3405063152313232,
1170
+ "logps/rejected": -3.743143081665039,
1171
+ "loss": 0.6894,
1172
+ "rewards/accuracies": 0.6000000238418579,
1173
+ "rewards/chosen": -0.011367046274244785,
1174
+ "rewards/margins": 0.05027226731181145,
1175
+ "rewards/rejected": -0.061639316380023956,
1176
+ "step": 650
1177
+ },
1178
+ {
1179
+ "epoch": 0.49865746068277716,
1180
+ "eval_logits/chosen": -0.25022387504577637,
1181
+ "eval_logits/rejected": -0.24710026383399963,
1182
+ "eval_logps/chosen": -3.5461456775665283,
1183
+ "eval_logps/rejected": -3.8798840045928955,
1184
+ "eval_loss": 0.688687801361084,
1185
+ "eval_rewards/accuracies": 0.49687498807907104,
1186
+ "eval_rewards/chosen": -0.0513271763920784,
1187
+ "eval_rewards/margins": 0.0030801701359450817,
1188
+ "eval_rewards/rejected": -0.05440734699368477,
1189
+ "eval_runtime": 89.1213,
1190
+ "eval_samples_per_second": 28.658,
1191
+ "eval_steps_per_second": 0.898,
1192
+ "step": 650
1193
+ },
1194
+ {
1195
+ "epoch": 0.5063291139240507,
1196
+ "grad_norm": 1.4859964847564697,
1197
+ "learning_rate": 2.4673829623944744e-05,
1198
+ "logits/chosen": -0.4470909535884857,
1199
+ "logits/rejected": -0.4404575228691101,
1200
+ "logps/chosen": -3.57057523727417,
1201
+ "logps/rejected": -4.062138080596924,
1202
+ "loss": 0.6839,
1203
+ "rewards/accuracies": 0.550000011920929,
1204
+ "rewards/chosen": -0.05643466114997864,
1205
+ "rewards/margins": 0.012388080358505249,
1206
+ "rewards/rejected": -0.06882274150848389,
1207
+ "step": 660
1208
+ },
1209
+ {
1210
+ "epoch": 0.5140007671653242,
1211
+ "grad_norm": 2.348560333251953,
1212
+ "learning_rate": 2.429009976976209e-05,
1213
+ "logits/chosen": -0.4324890971183777,
1214
+ "logits/rejected": -0.4288514256477356,
1215
+ "logps/chosen": -3.4150989055633545,
1216
+ "logps/rejected": -3.761260509490967,
1217
+ "loss": 0.6905,
1218
+ "rewards/accuracies": 0.574999988079071,
1219
+ "rewards/chosen": -0.047535546123981476,
1220
+ "rewards/margins": 0.00843095313757658,
1221
+ "rewards/rejected": -0.05596649646759033,
1222
+ "step": 670
1223
+ },
1224
+ {
1225
+ "epoch": 0.5216724204065977,
1226
+ "grad_norm": 2.114100933074951,
1227
+ "learning_rate": 2.390636991557943e-05,
1228
+ "logits/chosen": -0.4224484860897064,
1229
+ "logits/rejected": -0.41605424880981445,
1230
+ "logps/chosen": -3.8406059741973877,
1231
+ "logps/rejected": -3.227407455444336,
1232
+ "loss": 0.6923,
1233
+ "rewards/accuracies": 0.4749999940395355,
1234
+ "rewards/chosen": -0.09835998713970184,
1235
+ "rewards/margins": -0.028456950560212135,
1236
+ "rewards/rejected": -0.06990303844213486,
1237
+ "step": 680
1238
+ },
1239
+ {
1240
+ "epoch": 0.5293440736478712,
1241
+ "grad_norm": 2.143270254135132,
1242
+ "learning_rate": 2.3522640061396777e-05,
1243
+ "logits/chosen": -0.35925137996673584,
1244
+ "logits/rejected": -0.35858094692230225,
1245
+ "logps/chosen": -4.149369239807129,
1246
+ "logps/rejected": -4.207783222198486,
1247
+ "loss": 0.6901,
1248
+ "rewards/accuracies": 0.574999988079071,
1249
+ "rewards/chosen": -0.07230309396982193,
1250
+ "rewards/margins": 0.022937068715691566,
1251
+ "rewards/rejected": -0.09524016082286835,
1252
+ "step": 690
1253
+ },
1254
+ {
1255
+ "epoch": 0.5370157268891446,
1256
+ "grad_norm": 1.3052890300750732,
1257
+ "learning_rate": 2.3138910207214122e-05,
1258
+ "logits/chosen": -0.4177284836769104,
1259
+ "logits/rejected": -0.4176989197731018,
1260
+ "logps/chosen": -2.371631622314453,
1261
+ "logps/rejected": -5.967281341552734,
1262
+ "loss": 0.6972,
1263
+ "rewards/accuracies": 0.699999988079071,
1264
+ "rewards/chosen": -0.025050634518265724,
1265
+ "rewards/margins": 0.0979982241988182,
1266
+ "rewards/rejected": -0.12304886430501938,
1267
+ "step": 700
1268
+ },
1269
+ {
1270
+ "epoch": 0.5370157268891446,
1271
+ "eval_logits/chosen": -0.2624206840991974,
1272
+ "eval_logits/rejected": -0.259426087141037,
1273
+ "eval_logps/chosen": -3.501861572265625,
1274
+ "eval_logps/rejected": -3.8878912925720215,
1275
+ "eval_loss": 0.6871370673179626,
1276
+ "eval_rewards/accuracies": 0.48124998807907104,
1277
+ "eval_rewards/chosen": -0.046898726373910904,
1278
+ "eval_rewards/margins": 0.008309418335556984,
1279
+ "eval_rewards/rejected": -0.05520814657211304,
1280
+ "eval_runtime": 91.2498,
1281
+ "eval_samples_per_second": 27.989,
1282
+ "eval_steps_per_second": 0.877,
1283
+ "step": 700
1284
+ },
1285
+ {
1286
+ "epoch": 0.5446873801304181,
1287
+ "grad_norm": 1.2912267446517944,
1288
+ "learning_rate": 2.2755180353031468e-05,
1289
+ "logits/chosen": -0.45912307500839233,
1290
+ "logits/rejected": -0.4561159014701843,
1291
+ "logps/chosen": -3.2371792793273926,
1292
+ "logps/rejected": -3.8025176525115967,
1293
+ "loss": 0.6983,
1294
+ "rewards/accuracies": 0.574999988079071,
1295
+ "rewards/chosen": -0.024336762726306915,
1296
+ "rewards/margins": 0.016023293137550354,
1297
+ "rewards/rejected": -0.040360044687986374,
1298
+ "step": 710
1299
+ },
1300
+ {
1301
+ "epoch": 0.5523590333716916,
1302
+ "grad_norm": 1.5830397605895996,
1303
+ "learning_rate": 2.2371450498848813e-05,
1304
+ "logits/chosen": -0.382514089345932,
1305
+ "logits/rejected": -0.3864609897136688,
1306
+ "logps/chosen": -1.6761538982391357,
1307
+ "logps/rejected": -4.973038673400879,
1308
+ "loss": 0.6851,
1309
+ "rewards/accuracies": 0.6499999761581421,
1310
+ "rewards/chosen": -0.012824362143874168,
1311
+ "rewards/margins": 0.0575835183262825,
1312
+ "rewards/rejected": -0.07040788233280182,
1313
+ "step": 720
1314
+ },
1315
+ {
1316
+ "epoch": 0.5600306866129651,
1317
+ "grad_norm": 1.851820707321167,
1318
+ "learning_rate": 2.198772064466616e-05,
1319
+ "logits/chosen": -0.30062246322631836,
1320
+ "logits/rejected": -0.3018190860748291,
1321
+ "logps/chosen": -2.90508770942688,
1322
+ "logps/rejected": -3.7549374103546143,
1323
+ "loss": 0.6959,
1324
+ "rewards/accuracies": 0.625,
1325
+ "rewards/chosen": -0.02952618896961212,
1326
+ "rewards/margins": 0.014450429007411003,
1327
+ "rewards/rejected": -0.04397661238908768,
1328
+ "step": 730
1329
+ },
1330
+ {
1331
+ "epoch": 0.5677023398542386,
1332
+ "grad_norm": 1.2601155042648315,
1333
+ "learning_rate": 2.16039907904835e-05,
1334
+ "logits/chosen": -0.5282914042472839,
1335
+ "logits/rejected": -0.5290226936340332,
1336
+ "logps/chosen": -2.747199535369873,
1337
+ "logps/rejected": -3.397148609161377,
1338
+ "loss": 0.6875,
1339
+ "rewards/accuracies": 0.550000011920929,
1340
+ "rewards/chosen": 0.023777935653924942,
1341
+ "rewards/margins": 0.060780882835388184,
1342
+ "rewards/rejected": -0.03700294345617294,
1343
+ "step": 740
1344
+ },
1345
+ {
1346
+ "epoch": 0.5753739930955121,
1347
+ "grad_norm": 1.9561665058135986,
1348
+ "learning_rate": 2.1220260936300846e-05,
1349
+ "logits/chosen": -0.46929964423179626,
1350
+ "logits/rejected": -0.4689921736717224,
1351
+ "logps/chosen": -3.4335849285125732,
1352
+ "logps/rejected": -3.539712429046631,
1353
+ "loss": 0.6861,
1354
+ "rewards/accuracies": 0.6499999761581421,
1355
+ "rewards/chosen": -0.01373897772282362,
1356
+ "rewards/margins": 0.052022386342287064,
1357
+ "rewards/rejected": -0.06576136499643326,
1358
+ "step": 750
1359
+ },
1360
+ {
1361
+ "epoch": 0.5753739930955121,
1362
+ "eval_logits/chosen": -0.26118698716163635,
1363
+ "eval_logits/rejected": -0.25837644934654236,
1364
+ "eval_logps/chosen": -3.3246681690216064,
1365
+ "eval_logps/rejected": -3.706329345703125,
1366
+ "eval_loss": 0.6877872943878174,
1367
+ "eval_rewards/accuracies": 0.512499988079071,
1368
+ "eval_rewards/chosen": -0.029179394245147705,
1369
+ "eval_rewards/margins": 0.007872538641095161,
1370
+ "eval_rewards/rejected": -0.03705193102359772,
1371
+ "eval_runtime": 95.7364,
1372
+ "eval_samples_per_second": 26.677,
1373
+ "eval_steps_per_second": 0.836,
1374
+ "step": 750
1375
+ },
1376
+ {
1377
+ "epoch": 0.5830456463367856,
1378
+ "grad_norm": 1.3404334783554077,
1379
+ "learning_rate": 2.0836531082118192e-05,
1380
+ "logits/chosen": -0.37314945459365845,
1381
+ "logits/rejected": -0.3766701817512512,
1382
+ "logps/chosen": -2.7383177280426025,
1383
+ "logps/rejected": -2.9454519748687744,
1384
+ "loss": 0.693,
1385
+ "rewards/accuracies": 0.4749999940395355,
1386
+ "rewards/chosen": -0.04017211124300957,
1387
+ "rewards/margins": -0.045864250510931015,
1388
+ "rewards/rejected": 0.005692136473953724,
1389
+ "step": 760
1390
+ },
1391
+ {
1392
+ "epoch": 0.5907172995780591,
1393
+ "grad_norm": 1.4485934972763062,
1394
+ "learning_rate": 2.0452801227935534e-05,
1395
+ "logits/chosen": -0.46926283836364746,
1396
+ "logits/rejected": -0.46992430090904236,
1397
+ "logps/chosen": -3.8600451946258545,
1398
+ "logps/rejected": -3.410430431365967,
1399
+ "loss": 0.6925,
1400
+ "rewards/accuracies": 0.5,
1401
+ "rewards/chosen": -0.031888850033283234,
1402
+ "rewards/margins": 0.010654223151504993,
1403
+ "rewards/rejected": -0.042543068528175354,
1404
+ "step": 770
1405
+ },
1406
+ {
1407
+ "epoch": 0.5983889528193326,
1408
+ "grad_norm": 1.8931002616882324,
1409
+ "learning_rate": 2.006907137375288e-05,
1410
+ "logits/chosen": -0.3966008424758911,
1411
+ "logits/rejected": -0.4044922888278961,
1412
+ "logps/chosen": -2.1048827171325684,
1413
+ "logps/rejected": -4.816119194030762,
1414
+ "loss": 0.6858,
1415
+ "rewards/accuracies": 0.625,
1416
+ "rewards/chosen": 0.002983979182317853,
1417
+ "rewards/margins": 0.08909803628921509,
1418
+ "rewards/rejected": -0.0861140564084053,
1419
+ "step": 780
1420
+ },
1421
+ {
1422
+ "epoch": 0.6060606060606061,
1423
+ "grad_norm": 2.2583765983581543,
1424
+ "learning_rate": 1.9685341519570225e-05,
1425
+ "logits/chosen": -0.4961305558681488,
1426
+ "logits/rejected": -0.4885970652103424,
1427
+ "logps/chosen": -3.6672680377960205,
1428
+ "logps/rejected": -3.291787624359131,
1429
+ "loss": 0.692,
1430
+ "rewards/accuracies": 0.5249999761581421,
1431
+ "rewards/chosen": -0.02681976929306984,
1432
+ "rewards/margins": 0.014080104418098927,
1433
+ "rewards/rejected": -0.04089986905455589,
1434
+ "step": 790
1435
+ },
1436
+ {
1437
+ "epoch": 0.6137322593018796,
1438
+ "grad_norm": 1.8438897132873535,
1439
+ "learning_rate": 1.9301611665387567e-05,
1440
+ "logits/chosen": -0.46609607338905334,
1441
+ "logits/rejected": -0.4627665877342224,
1442
+ "logps/chosen": -3.5119385719299316,
1443
+ "logps/rejected": -3.595712184906006,
1444
+ "loss": 0.6866,
1445
+ "rewards/accuracies": 0.6000000238418579,
1446
+ "rewards/chosen": -0.025941628962755203,
1447
+ "rewards/margins": 0.030908849090337753,
1448
+ "rewards/rejected": -0.056850481778383255,
1449
+ "step": 800
1450
+ },
1451
+ {
1452
+ "epoch": 0.6137322593018796,
1453
+ "eval_logits/chosen": -0.2616404891014099,
1454
+ "eval_logits/rejected": -0.25945189595222473,
1455
+ "eval_logps/chosen": -3.2828381061553955,
1456
+ "eval_logps/rejected": -3.7320716381073,
1457
+ "eval_loss": 0.6877512335777283,
1458
+ "eval_rewards/accuracies": 0.518750011920929,
1459
+ "eval_rewards/chosen": -0.024996396154165268,
1460
+ "eval_rewards/margins": 0.014629754237830639,
1461
+ "eval_rewards/rejected": -0.03962615132331848,
1462
+ "eval_runtime": 96.9287,
1463
+ "eval_samples_per_second": 26.349,
1464
+ "eval_steps_per_second": 0.825,
1465
+ "step": 800
1466
+ },
1467
+ {
1468
+ "epoch": 0.6214039125431531,
1469
+ "grad_norm": 1.5462312698364258,
1470
+ "learning_rate": 1.8917881811204912e-05,
1471
+ "logits/chosen": -0.5312341451644897,
1472
+ "logits/rejected": -0.5319844484329224,
1473
+ "logps/chosen": -3.227830410003662,
1474
+ "logps/rejected": -3.9378840923309326,
1475
+ "loss": 0.6881,
1476
+ "rewards/accuracies": 0.625,
1477
+ "rewards/chosen": -0.031698137521743774,
1478
+ "rewards/margins": 0.033506251871585846,
1479
+ "rewards/rejected": -0.06520438939332962,
1480
+ "step": 810
1481
+ },
1482
+ {
1483
+ "epoch": 0.6290755657844266,
1484
+ "grad_norm": 1.644169807434082,
1485
+ "learning_rate": 1.8534151957022258e-05,
1486
+ "logits/chosen": -0.42604535818099976,
1487
+ "logits/rejected": -0.42680415511131287,
1488
+ "logps/chosen": -3.025153875350952,
1489
+ "logps/rejected": -3.5833792686462402,
1490
+ "loss": 0.6951,
1491
+ "rewards/accuracies": 0.6000000238418579,
1492
+ "rewards/chosen": -0.017264336347579956,
1493
+ "rewards/margins": 0.03092106617987156,
1494
+ "rewards/rejected": -0.048185400664806366,
1495
+ "step": 820
1496
+ },
1497
+ {
1498
+ "epoch": 0.6367472190257001,
1499
+ "grad_norm": 2.567456007003784,
1500
+ "learning_rate": 1.81504221028396e-05,
1501
+ "logits/chosen": -0.3624061048030853,
1502
+ "logits/rejected": -0.3603518605232239,
1503
+ "logps/chosen": -2.727677583694458,
1504
+ "logps/rejected": -4.618671417236328,
1505
+ "loss": 0.6831,
1506
+ "rewards/accuracies": 0.675000011920929,
1507
+ "rewards/chosen": 0.013222327455878258,
1508
+ "rewards/margins": 0.04956119880080223,
1509
+ "rewards/rejected": -0.03633887320756912,
1510
+ "step": 830
1511
+ },
1512
+ {
1513
+ "epoch": 0.6444188722669736,
1514
+ "grad_norm": 1.6993279457092285,
1515
+ "learning_rate": 1.7766692248656946e-05,
1516
+ "logits/chosen": -0.43364423513412476,
1517
+ "logits/rejected": -0.43153029680252075,
1518
+ "logps/chosen": -3.7280707359313965,
1519
+ "logps/rejected": -3.3984951972961426,
1520
+ "loss": 0.6892,
1521
+ "rewards/accuracies": 0.6000000238418579,
1522
+ "rewards/chosen": -0.003762350883334875,
1523
+ "rewards/margins": 0.04601341485977173,
1524
+ "rewards/rejected": -0.04977576062083244,
1525
+ "step": 840
1526
+ },
1527
+ {
1528
+ "epoch": 0.652090525508247,
1529
+ "grad_norm": 1.2924683094024658,
1530
+ "learning_rate": 1.738296239447429e-05,
1531
+ "logits/chosen": -0.40035882592201233,
1532
+ "logits/rejected": -0.39904215931892395,
1533
+ "logps/chosen": -2.473344087600708,
1534
+ "logps/rejected": -4.267284393310547,
1535
+ "loss": 0.6901,
1536
+ "rewards/accuracies": 0.574999988079071,
1537
+ "rewards/chosen": -0.02397814765572548,
1538
+ "rewards/margins": 0.036180444061756134,
1539
+ "rewards/rejected": -0.060158587992191315,
1540
+ "step": 850
1541
+ },
1542
+ {
1543
+ "epoch": 0.652090525508247,
1544
+ "eval_logits/chosen": -0.264896422624588,
1545
+ "eval_logits/rejected": -0.2623136341571808,
1546
+ "eval_logps/chosen": -3.455109119415283,
1547
+ "eval_logps/rejected": -3.909381866455078,
1548
+ "eval_loss": 0.6873416304588318,
1549
+ "eval_rewards/accuracies": 0.503125011920929,
1550
+ "eval_rewards/chosen": -0.04222346469759941,
1551
+ "eval_rewards/margins": 0.015133677050471306,
1552
+ "eval_rewards/rejected": -0.057357143610715866,
1553
+ "eval_runtime": 87.969,
1554
+ "eval_samples_per_second": 29.033,
1555
+ "eval_steps_per_second": 0.909,
1556
+ "step": 850
1557
+ },
1558
+ {
1559
+ "epoch": 0.6597621787495205,
1560
+ "grad_norm": 1.6212762594223022,
1561
+ "learning_rate": 1.6999232540291633e-05,
1562
+ "logits/chosen": -0.41735363006591797,
1563
+ "logits/rejected": -0.4102698266506195,
1564
+ "logps/chosen": -3.7062439918518066,
1565
+ "logps/rejected": -3.9006316661834717,
1566
+ "loss": 0.6915,
1567
+ "rewards/accuracies": 0.5249999761581421,
1568
+ "rewards/chosen": -0.0529264435172081,
1569
+ "rewards/margins": 0.005926959216594696,
1570
+ "rewards/rejected": -0.0588533990085125,
1571
+ "step": 860
1572
+ },
1573
+ {
1574
+ "epoch": 0.667433831990794,
1575
+ "grad_norm": 2.2773942947387695,
1576
+ "learning_rate": 1.661550268610898e-05,
1577
+ "logits/chosen": -0.37981244921684265,
1578
+ "logits/rejected": -0.3839191496372223,
1579
+ "logps/chosen": -2.9031481742858887,
1580
+ "logps/rejected": -4.830349922180176,
1581
+ "loss": 0.6897,
1582
+ "rewards/accuracies": 0.625,
1583
+ "rewards/chosen": -0.02680964395403862,
1584
+ "rewards/margins": 0.06183745339512825,
1585
+ "rewards/rejected": -0.08864708989858627,
1586
+ "step": 870
1587
+ },
1588
+ {
1589
+ "epoch": 0.6751054852320675,
1590
+ "grad_norm": 1.763682246208191,
1591
+ "learning_rate": 1.6231772831926324e-05,
1592
+ "logits/chosen": -0.34375470876693726,
1593
+ "logits/rejected": -0.3387607932090759,
1594
+ "logps/chosen": -3.3046181201934814,
1595
+ "logps/rejected": -4.335677146911621,
1596
+ "loss": 0.6843,
1597
+ "rewards/accuracies": 0.574999988079071,
1598
+ "rewards/chosen": -0.04779592901468277,
1599
+ "rewards/margins": 0.02044987678527832,
1600
+ "rewards/rejected": -0.06824581325054169,
1601
+ "step": 880
1602
+ },
1603
+ {
1604
+ "epoch": 0.682777138473341,
1605
+ "grad_norm": 2.387399196624756,
1606
+ "learning_rate": 1.584804297774367e-05,
1607
+ "logits/chosen": -0.4725160598754883,
1608
+ "logits/rejected": -0.4763157367706299,
1609
+ "logps/chosen": -2.8794379234313965,
1610
+ "logps/rejected": -4.024861812591553,
1611
+ "loss": 0.6943,
1612
+ "rewards/accuracies": 0.5,
1613
+ "rewards/chosen": -0.046050556004047394,
1614
+ "rewards/margins": 0.01775188557803631,
1615
+ "rewards/rejected": -0.06380244344472885,
1616
+ "step": 890
1617
+ },
1618
+ {
1619
+ "epoch": 0.6904487917146145,
1620
+ "grad_norm": 1.5189565420150757,
1621
+ "learning_rate": 1.5464313123561015e-05,
1622
+ "logits/chosen": -0.31694844365119934,
1623
+ "logits/rejected": -0.3208076059818268,
1624
+ "logps/chosen": -2.9370594024658203,
1625
+ "logps/rejected": -4.222288608551025,
1626
+ "loss": 0.6835,
1627
+ "rewards/accuracies": 0.6499999761581421,
1628
+ "rewards/chosen": -0.04458096995949745,
1629
+ "rewards/margins": 0.028453299775719643,
1630
+ "rewards/rejected": -0.07303427159786224,
1631
+ "step": 900
1632
+ },
1633
+ {
1634
+ "epoch": 0.6904487917146145,
1635
+ "eval_logits/chosen": -0.2631658613681793,
1636
+ "eval_logits/rejected": -0.2605777382850647,
1637
+ "eval_logps/chosen": -3.5630836486816406,
1638
+ "eval_logps/rejected": -4.000800132751465,
1639
+ "eval_loss": 0.6874542832374573,
1640
+ "eval_rewards/accuracies": 0.5093749761581421,
1641
+ "eval_rewards/chosen": -0.053020983934402466,
1642
+ "eval_rewards/margins": 0.013478020206093788,
1643
+ "eval_rewards/rejected": -0.0664990097284317,
1644
+ "eval_runtime": 87.9229,
1645
+ "eval_samples_per_second": 29.048,
1646
+ "eval_steps_per_second": 0.91,
1647
+ "step": 900
1648
+ },
1649
+ {
1650
+ "epoch": 0.698120444955888,
1651
+ "grad_norm": 1.9298661947250366,
1652
+ "learning_rate": 1.5080583269378359e-05,
1653
+ "logits/chosen": -0.4393790364265442,
1654
+ "logits/rejected": -0.43957772850990295,
1655
+ "logps/chosen": -3.8378818035125732,
1656
+ "logps/rejected": -3.808051586151123,
1657
+ "loss": 0.6941,
1658
+ "rewards/accuracies": 0.4749999940395355,
1659
+ "rewards/chosen": -0.08017073571681976,
1660
+ "rewards/margins": -0.014708010479807854,
1661
+ "rewards/rejected": -0.06546272337436676,
1662
+ "step": 910
1663
+ },
1664
+ {
1665
+ "epoch": 0.7057920981971615,
1666
+ "grad_norm": 1.7689329385757446,
1667
+ "learning_rate": 1.4696853415195703e-05,
1668
+ "logits/chosen": -0.46744298934936523,
1669
+ "logits/rejected": -0.4742264747619629,
1670
+ "logps/chosen": -3.0718374252319336,
1671
+ "logps/rejected": -3.5021071434020996,
1672
+ "loss": 0.6854,
1673
+ "rewards/accuracies": 0.574999988079071,
1674
+ "rewards/chosen": -0.03193381056189537,
1675
+ "rewards/margins": 0.04194425791501999,
1676
+ "rewards/rejected": -0.07387807220220566,
1677
+ "step": 920
1678
+ },
1679
+ {
1680
+ "epoch": 0.713463751438435,
1681
+ "grad_norm": 1.4333994388580322,
1682
+ "learning_rate": 1.4313123561013048e-05,
1683
+ "logits/chosen": -0.3608981966972351,
1684
+ "logits/rejected": -0.3596799373626709,
1685
+ "logps/chosen": -4.751004219055176,
1686
+ "logps/rejected": -3.0089735984802246,
1687
+ "loss": 0.6926,
1688
+ "rewards/accuracies": 0.4000000059604645,
1689
+ "rewards/chosen": -0.0744011402130127,
1690
+ "rewards/margins": -0.03302520513534546,
1691
+ "rewards/rejected": -0.04137593135237694,
1692
+ "step": 930
1693
+ },
1694
+ {
1695
+ "epoch": 0.7211354046797085,
1696
+ "grad_norm": 1.605447769165039,
1697
+ "learning_rate": 1.3929393706830394e-05,
1698
+ "logits/chosen": -0.3481396734714508,
1699
+ "logits/rejected": -0.3457208275794983,
1700
+ "logps/chosen": -4.311774253845215,
1701
+ "logps/rejected": -3.5297610759735107,
1702
+ "loss": 0.6945,
1703
+ "rewards/accuracies": 0.44999998807907104,
1704
+ "rewards/chosen": -0.06438607722520828,
1705
+ "rewards/margins": -0.021948862820863724,
1706
+ "rewards/rejected": -0.04243721812963486,
1707
+ "step": 940
1708
+ },
1709
+ {
1710
+ "epoch": 0.728807057920982,
1711
+ "grad_norm": 0.9545491337776184,
1712
+ "learning_rate": 1.3545663852647736e-05,
1713
+ "logits/chosen": -0.45011836290359497,
1714
+ "logits/rejected": -0.4549293518066406,
1715
+ "logps/chosen": -2.901266098022461,
1716
+ "logps/rejected": -3.653916835784912,
1717
+ "loss": 0.6907,
1718
+ "rewards/accuracies": 0.550000011920929,
1719
+ "rewards/chosen": -0.004453243222087622,
1720
+ "rewards/margins": 0.06575339287519455,
1721
+ "rewards/rejected": -0.07020662724971771,
1722
+ "step": 950
1723
+ },
1724
+ {
1725
+ "epoch": 0.728807057920982,
1726
+ "eval_logits/chosen": -0.2597009241580963,
1727
+ "eval_logits/rejected": -0.25726523995399475,
1728
+ "eval_logps/chosen": -3.299370288848877,
1729
+ "eval_logps/rejected": -3.774941921234131,
1730
+ "eval_loss": 0.6873298287391663,
1731
+ "eval_rewards/accuracies": 0.53125,
1732
+ "eval_rewards/chosen": -0.0266495980322361,
1733
+ "eval_rewards/margins": 0.01726352609694004,
1734
+ "eval_rewards/rejected": -0.04391312599182129,
1735
+ "eval_runtime": 87.9968,
1736
+ "eval_samples_per_second": 29.024,
1737
+ "eval_steps_per_second": 0.909,
1738
+ "step": 950
1739
+ },
1740
+ {
1741
+ "epoch": 0.7364787111622555,
1742
+ "grad_norm": 1.472712755203247,
1743
+ "learning_rate": 1.3161933998465081e-05,
1744
+ "logits/chosen": -0.43601498007774353,
1745
+ "logits/rejected": -0.4370816648006439,
1746
+ "logps/chosen": -2.949425220489502,
1747
+ "logps/rejected": -3.2113566398620605,
1748
+ "loss": 0.6916,
1749
+ "rewards/accuracies": 0.4000000059604645,
1750
+ "rewards/chosen": -0.03191310912370682,
1751
+ "rewards/margins": -0.030944937840104103,
1752
+ "rewards/rejected": -0.0009681672090664506,
1753
+ "step": 960
1754
+ },
1755
+ {
1756
+ "epoch": 0.744150364403529,
1757
+ "grad_norm": 1.710877537727356,
1758
+ "learning_rate": 1.2778204144282427e-05,
1759
+ "logits/chosen": -0.46664342284202576,
1760
+ "logits/rejected": -0.466810941696167,
1761
+ "logps/chosen": -3.9124972820281982,
1762
+ "logps/rejected": -3.6439247131347656,
1763
+ "loss": 0.6928,
1764
+ "rewards/accuracies": 0.550000011920929,
1765
+ "rewards/chosen": -0.05568718910217285,
1766
+ "rewards/margins": -0.004351111128926277,
1767
+ "rewards/rejected": -0.05133608728647232,
1768
+ "step": 970
1769
+ },
1770
+ {
1771
+ "epoch": 0.7518220176448025,
1772
+ "grad_norm": 1.8609956502914429,
1773
+ "learning_rate": 1.239447429009977e-05,
1774
+ "logits/chosen": -0.5233210325241089,
1775
+ "logits/rejected": -0.5286127328872681,
1776
+ "logps/chosen": -3.5049729347229004,
1777
+ "logps/rejected": -2.9099135398864746,
1778
+ "loss": 0.6877,
1779
+ "rewards/accuracies": 0.5249999761581421,
1780
+ "rewards/chosen": -0.02429554983973503,
1781
+ "rewards/margins": 0.04005228728055954,
1782
+ "rewards/rejected": -0.06434784084558487,
1783
+ "step": 980
1784
+ },
1785
+ {
1786
+ "epoch": 0.759493670886076,
1787
+ "grad_norm": 2.3433878421783447,
1788
+ "learning_rate": 1.2010744435917114e-05,
1789
+ "logits/chosen": -0.5355673432350159,
1790
+ "logits/rejected": -0.5309178233146667,
1791
+ "logps/chosen": -2.8020567893981934,
1792
+ "logps/rejected": -4.379094123840332,
1793
+ "loss": 0.6869,
1794
+ "rewards/accuracies": 0.44999998807907104,
1795
+ "rewards/chosen": -0.034182898700237274,
1796
+ "rewards/margins": 0.029533013701438904,
1797
+ "rewards/rejected": -0.06371591240167618,
1798
+ "step": 990
1799
+ },
1800
+ {
1801
+ "epoch": 0.7671653241273494,
1802
+ "grad_norm": 1.5511538982391357,
1803
+ "learning_rate": 1.162701458173446e-05,
1804
+ "logits/chosen": -0.41299349069595337,
1805
+ "logits/rejected": -0.4154202342033386,
1806
+ "logps/chosen": -2.535586357116699,
1807
+ "logps/rejected": -4.728541851043701,
1808
+ "loss": 0.6938,
1809
+ "rewards/accuracies": 0.6499999761581421,
1810
+ "rewards/chosen": -0.01752440631389618,
1811
+ "rewards/margins": 0.10527894645929337,
1812
+ "rewards/rejected": -0.12280334532260895,
1813
+ "step": 1000
1814
+ },
1815
+ {
1816
+ "epoch": 0.7671653241273494,
1817
+ "eval_logits/chosen": -0.25718361139297485,
1818
+ "eval_logits/rejected": -0.2549431622028351,
1819
+ "eval_logps/chosen": -3.5508739948272705,
1820
+ "eval_logps/rejected": -3.9987282752990723,
1821
+ "eval_loss": 0.687543511390686,
1822
+ "eval_rewards/accuracies": 0.512499988079071,
1823
+ "eval_rewards/chosen": -0.051799990236759186,
1824
+ "eval_rewards/margins": 0.014491766691207886,
1825
+ "eval_rewards/rejected": -0.06629175692796707,
1826
+ "eval_runtime": 87.5816,
1827
+ "eval_samples_per_second": 29.161,
1828
+ "eval_steps_per_second": 0.913,
1829
+ "step": 1000
1830
+ },
1831
+ {
1832
+ "epoch": 0.7748369773686229,
1833
+ "grad_norm": 1.9154669046401978,
1834
+ "learning_rate": 1.1243284727551805e-05,
1835
+ "logits/chosen": -0.5070533156394958,
1836
+ "logits/rejected": -0.5113304853439331,
1837
+ "logps/chosen": -3.3207507133483887,
1838
+ "logps/rejected": -4.22388219833374,
1839
+ "loss": 0.6931,
1840
+ "rewards/accuracies": 0.4749999940395355,
1841
+ "rewards/chosen": -0.0673786848783493,
1842
+ "rewards/margins": -0.0010321959853172302,
1843
+ "rewards/rejected": -0.06634648889303207,
1844
+ "step": 1010
1845
+ },
1846
+ {
1847
+ "epoch": 0.7825086306098964,
1848
+ "grad_norm": 1.3908665180206299,
1849
+ "learning_rate": 1.0859554873369149e-05,
1850
+ "logits/chosen": -0.45152488350868225,
1851
+ "logits/rejected": -0.4454428553581238,
1852
+ "logps/chosen": -4.341331481933594,
1853
+ "logps/rejected": -2.536820650100708,
1854
+ "loss": 0.688,
1855
+ "rewards/accuracies": 0.42500001192092896,
1856
+ "rewards/chosen": -0.0593075156211853,
1857
+ "rewards/margins": -0.003714442951604724,
1858
+ "rewards/rejected": -0.05559306591749191,
1859
+ "step": 1020
1860
+ },
1861
+ {
1862
+ "epoch": 0.7901802838511699,
1863
+ "grad_norm": 1.4446948766708374,
1864
+ "learning_rate": 1.0475825019186493e-05,
1865
+ "logits/chosen": -0.4947948455810547,
1866
+ "logits/rejected": -0.4966978132724762,
1867
+ "logps/chosen": -3.387843608856201,
1868
+ "logps/rejected": -3.6044819355010986,
1869
+ "loss": 0.6969,
1870
+ "rewards/accuracies": 0.4749999940395355,
1871
+ "rewards/chosen": -0.06083371490240097,
1872
+ "rewards/margins": -0.006257879547774792,
1873
+ "rewards/rejected": -0.0545758493244648,
1874
+ "step": 1030
1875
+ },
1876
+ {
1877
+ "epoch": 0.7978519370924434,
1878
+ "grad_norm": 1.610182523727417,
1879
+ "learning_rate": 1.0092095165003838e-05,
1880
+ "logits/chosen": -0.46212753653526306,
1881
+ "logits/rejected": -0.46821293234825134,
1882
+ "logps/chosen": -4.950307846069336,
1883
+ "logps/rejected": -3.0810484886169434,
1884
+ "loss": 0.69,
1885
+ "rewards/accuracies": 0.375,
1886
+ "rewards/chosen": -0.04846534878015518,
1887
+ "rewards/margins": -0.025759827345609665,
1888
+ "rewards/rejected": -0.022705521434545517,
1889
+ "step": 1040
1890
+ },
1891
+ {
1892
+ "epoch": 0.8055235903337169,
1893
+ "grad_norm": 2.2419750690460205,
1894
+ "learning_rate": 9.708365310821182e-06,
1895
+ "logits/chosen": -0.5252290964126587,
1896
+ "logits/rejected": -0.5231043100357056,
1897
+ "logps/chosen": -3.5570881366729736,
1898
+ "logps/rejected": -3.7880332469940186,
1899
+ "loss": 0.6942,
1900
+ "rewards/accuracies": 0.5,
1901
+ "rewards/chosen": -0.06180233880877495,
1902
+ "rewards/margins": -0.026278842240571976,
1903
+ "rewards/rejected": -0.03552350401878357,
1904
+ "step": 1050
1905
+ },
1906
+ {
1907
+ "epoch": 0.8055235903337169,
1908
+ "eval_logits/chosen": -0.25850772857666016,
1909
+ "eval_logits/rejected": -0.25608521699905396,
1910
+ "eval_logps/chosen": -3.3484771251678467,
1911
+ "eval_logps/rejected": -3.820146083831787,
1912
+ "eval_loss": 0.6879977583885193,
1913
+ "eval_rewards/accuracies": 0.515625,
1914
+ "eval_rewards/chosen": -0.031560301780700684,
1915
+ "eval_rewards/margins": 0.01687331683933735,
1916
+ "eval_rewards/rejected": -0.04843362048268318,
1917
+ "eval_runtime": 87.9503,
1918
+ "eval_samples_per_second": 29.039,
1919
+ "eval_steps_per_second": 0.91,
1920
+ "step": 1050
1921
+ },
1922
+ {
1923
+ "epoch": 0.8131952435749904,
1924
+ "grad_norm": 1.5563366413116455,
1925
+ "learning_rate": 9.324635456638526e-06,
1926
+ "logits/chosen": -0.4408280849456787,
1927
+ "logits/rejected": -0.44397348165512085,
1928
+ "logps/chosen": -3.351261854171753,
1929
+ "logps/rejected": -3.4453811645507812,
1930
+ "loss": 0.6788,
1931
+ "rewards/accuracies": 0.5,
1932
+ "rewards/chosen": -0.03186880797147751,
1933
+ "rewards/margins": 0.015346929430961609,
1934
+ "rewards/rejected": -0.04721573740243912,
1935
+ "step": 1060
1936
+ },
1937
+ {
1938
+ "epoch": 0.8208668968162639,
1939
+ "grad_norm": 1.7316789627075195,
1940
+ "learning_rate": 8.940905602455871e-06,
1941
+ "logits/chosen": -0.4371892511844635,
1942
+ "logits/rejected": -0.43460506200790405,
1943
+ "logps/chosen": -3.015501022338867,
1944
+ "logps/rejected": -4.129702091217041,
1945
+ "loss": 0.6886,
1946
+ "rewards/accuracies": 0.625,
1947
+ "rewards/chosen": 0.010989089496433735,
1948
+ "rewards/margins": 0.06226798892021179,
1949
+ "rewards/rejected": -0.05127890035510063,
1950
+ "step": 1070
1951
+ },
1952
+ {
1953
+ "epoch": 0.8285385500575374,
1954
+ "grad_norm": 1.842515230178833,
1955
+ "learning_rate": 8.557175748273217e-06,
1956
+ "logits/chosen": -0.43732374906539917,
1957
+ "logits/rejected": -0.4389157295227051,
1958
+ "logps/chosen": -3.6136844158172607,
1959
+ "logps/rejected": -4.016729354858398,
1960
+ "loss": 0.6864,
1961
+ "rewards/accuracies": 0.5,
1962
+ "rewards/chosen": -0.029665043577551842,
1963
+ "rewards/margins": 0.018349073827266693,
1964
+ "rewards/rejected": -0.04801411181688309,
1965
+ "step": 1080
1966
+ },
1967
+ {
1968
+ "epoch": 0.8362102032988109,
1969
+ "grad_norm": 1.4809995889663696,
1970
+ "learning_rate": 8.17344589409056e-06,
1971
+ "logits/chosen": -0.39032843708992004,
1972
+ "logits/rejected": -0.3862852156162262,
1973
+ "logps/chosen": -3.43218731880188,
1974
+ "logps/rejected": -3.326885223388672,
1975
+ "loss": 0.7062,
1976
+ "rewards/accuracies": 0.550000011920929,
1977
+ "rewards/chosen": -0.03662601485848427,
1978
+ "rewards/margins": 2.0000337826786563e-05,
1979
+ "rewards/rejected": -0.03664601594209671,
1980
+ "step": 1090
1981
+ },
1982
+ {
1983
+ "epoch": 0.8438818565400844,
1984
+ "grad_norm": 1.7941354513168335,
1985
+ "learning_rate": 7.789716039907906e-06,
1986
+ "logits/chosen": -0.3972841799259186,
1987
+ "logits/rejected": -0.4001404643058777,
1988
+ "logps/chosen": -2.768026828765869,
1989
+ "logps/rejected": -3.8738293647766113,
1990
+ "loss": 0.6784,
1991
+ "rewards/accuracies": 0.5249999761581421,
1992
+ "rewards/chosen": -0.028935182839632034,
1993
+ "rewards/margins": -0.008622194640338421,
1994
+ "rewards/rejected": -0.020312989130616188,
1995
+ "step": 1100
1996
+ },
1997
+ {
1998
+ "epoch": 0.8438818565400844,
1999
+ "eval_logits/chosen": -0.25824981927871704,
2000
+ "eval_logits/rejected": -0.2558724284172058,
2001
+ "eval_logps/chosen": -3.438009262084961,
2002
+ "eval_logps/rejected": -3.9306366443634033,
2003
+ "eval_loss": 0.6873763203620911,
2004
+ "eval_rewards/accuracies": 0.5218750238418579,
2005
+ "eval_rewards/chosen": -0.04051350802183151,
2006
+ "eval_rewards/margins": 0.018969083204865456,
2007
+ "eval_rewards/rejected": -0.05948259308934212,
2008
+ "eval_runtime": 103.4451,
2009
+ "eval_samples_per_second": 24.689,
2010
+ "eval_steps_per_second": 0.773,
2011
+ "step": 1100
2012
+ },
2013
+ {
2014
+ "epoch": 0.8515535097813579,
2015
+ "grad_norm": 1.5570868253707886,
2016
+ "learning_rate": 7.40598618572525e-06,
2017
+ "logits/chosen": -0.4041014611721039,
2018
+ "logits/rejected": -0.4015308916568756,
2019
+ "logps/chosen": -3.7765114307403564,
2020
+ "logps/rejected": -3.0345726013183594,
2021
+ "loss": 0.6972,
2022
+ "rewards/accuracies": 0.4749999940395355,
2023
+ "rewards/chosen": -0.04268242418766022,
2024
+ "rewards/margins": -0.022908544167876244,
2025
+ "rewards/rejected": -0.019773881882429123,
2026
+ "step": 1110
2027
+ },
2028
+ {
2029
+ "epoch": 0.8592251630226314,
2030
+ "grad_norm": 1.0964603424072266,
2031
+ "learning_rate": 7.022256331542594e-06,
2032
+ "logits/chosen": -0.4172094464302063,
2033
+ "logits/rejected": -0.41948825120925903,
2034
+ "logps/chosen": -3.422609329223633,
2035
+ "logps/rejected": -3.803391933441162,
2036
+ "loss": 0.6869,
2037
+ "rewards/accuracies": 0.42500001192092896,
2038
+ "rewards/chosen": -0.06300051510334015,
2039
+ "rewards/margins": -0.010609099641442299,
2040
+ "rewards/rejected": -0.0523914210498333,
2041
+ "step": 1120
2042
+ },
2043
+ {
2044
+ "epoch": 0.8668968162639049,
2045
+ "grad_norm": 1.906252145767212,
2046
+ "learning_rate": 6.638526477359939e-06,
2047
+ "logits/chosen": -0.44013237953186035,
2048
+ "logits/rejected": -0.4369295537471771,
2049
+ "logps/chosen": -3.6771011352539062,
2050
+ "logps/rejected": -3.834157943725586,
2051
+ "loss": 0.6724,
2052
+ "rewards/accuracies": 0.4749999940395355,
2053
+ "rewards/chosen": -0.033518821001052856,
2054
+ "rewards/margins": 0.04495871439576149,
2055
+ "rewards/rejected": -0.07847753912210464,
2056
+ "step": 1130
2057
+ },
2058
+ {
2059
+ "epoch": 0.8745684695051784,
2060
+ "grad_norm": 1.4220091104507446,
2061
+ "learning_rate": 6.254796623177284e-06,
2062
+ "logits/chosen": -0.5218509435653687,
2063
+ "logits/rejected": -0.527131199836731,
2064
+ "logps/chosen": -2.6902661323547363,
2065
+ "logps/rejected": -3.8175301551818848,
2066
+ "loss": 0.6918,
2067
+ "rewards/accuracies": 0.5249999761581421,
2068
+ "rewards/chosen": -0.05095089226961136,
2069
+ "rewards/margins": 0.008214332163333893,
2070
+ "rewards/rejected": -0.059165216982364655,
2071
+ "step": 1140
2072
+ },
2073
+ {
2074
+ "epoch": 0.8822401227464519,
2075
+ "grad_norm": 1.280017375946045,
2076
+ "learning_rate": 5.871066768994628e-06,
2077
+ "logits/chosen": -0.3222968280315399,
2078
+ "logits/rejected": -0.32637038826942444,
2079
+ "logps/chosen": -3.7984070777893066,
2080
+ "logps/rejected": -3.347282886505127,
2081
+ "loss": 0.6897,
2082
+ "rewards/accuracies": 0.5,
2083
+ "rewards/chosen": -0.050425935536623,
2084
+ "rewards/margins": 0.01578127220273018,
2085
+ "rewards/rejected": -0.06620721518993378,
2086
+ "step": 1150
2087
+ },
2088
+ {
2089
+ "epoch": 0.8822401227464519,
2090
+ "eval_logits/chosen": -0.25547298789024353,
2091
+ "eval_logits/rejected": -0.25304776430130005,
2092
+ "eval_logps/chosen": -3.5789942741394043,
2093
+ "eval_logps/rejected": -4.070747375488281,
2094
+ "eval_loss": 0.6874914169311523,
2095
+ "eval_rewards/accuracies": 0.5218750238418579,
2096
+ "eval_rewards/chosen": -0.05461201071739197,
2097
+ "eval_rewards/margins": 0.01888173446059227,
2098
+ "eval_rewards/rejected": -0.07349374145269394,
2099
+ "eval_runtime": 94.5303,
2100
+ "eval_samples_per_second": 27.018,
2101
+ "eval_steps_per_second": 0.846,
2102
+ "step": 1150
2103
+ },
2104
+ {
2105
+ "epoch": 0.8899117759877253,
2106
+ "grad_norm": 1.3330215215682983,
2107
+ "learning_rate": 5.487336914811972e-06,
2108
+ "logits/chosen": -0.4289553165435791,
2109
+ "logits/rejected": -0.42481836676597595,
2110
+ "logps/chosen": -4.021355628967285,
2111
+ "logps/rejected": -2.860283374786377,
2112
+ "loss": 0.6836,
2113
+ "rewards/accuracies": 0.675000011920929,
2114
+ "rewards/chosen": -0.00559669965878129,
2115
+ "rewards/margins": 0.03529663756489754,
2116
+ "rewards/rejected": -0.04089333862066269,
2117
+ "step": 1160
2118
+ },
2119
+ {
2120
+ "epoch": 0.8975834292289988,
2121
+ "grad_norm": 2.0986618995666504,
2122
+ "learning_rate": 5.103607060629317e-06,
2123
+ "logits/chosen": -0.4019424021244049,
2124
+ "logits/rejected": -0.39785686135292053,
2125
+ "logps/chosen": -2.8404293060302734,
2126
+ "logps/rejected": -5.334328651428223,
2127
+ "loss": 0.6977,
2128
+ "rewards/accuracies": 0.550000011920929,
2129
+ "rewards/chosen": -0.03890450671315193,
2130
+ "rewards/margins": 0.015505614690482616,
2131
+ "rewards/rejected": -0.05441011115908623,
2132
+ "step": 1170
2133
+ },
2134
+ {
2135
+ "epoch": 0.9052550824702723,
2136
+ "grad_norm": 1.6253297328948975,
2137
+ "learning_rate": 4.719877206446662e-06,
2138
+ "logits/chosen": -0.2909601032733917,
2139
+ "logits/rejected": -0.2908070385456085,
2140
+ "logps/chosen": -2.6695282459259033,
2141
+ "logps/rejected": -4.1958699226379395,
2142
+ "loss": 0.6873,
2143
+ "rewards/accuracies": 0.6499999761581421,
2144
+ "rewards/chosen": -0.02150137722492218,
2145
+ "rewards/margins": 0.053162820637226105,
2146
+ "rewards/rejected": -0.07466419786214828,
2147
+ "step": 1180
2148
+ },
2149
+ {
2150
+ "epoch": 0.9129267357115458,
2151
+ "grad_norm": 1.6267880201339722,
2152
+ "learning_rate": 4.336147352264006e-06,
2153
+ "logits/chosen": -0.49156007170677185,
2154
+ "logits/rejected": -0.49580636620521545,
2155
+ "logps/chosen": -2.781247854232788,
2156
+ "logps/rejected": -4.9970293045043945,
2157
+ "loss": 0.6777,
2158
+ "rewards/accuracies": 0.574999988079071,
2159
+ "rewards/chosen": -0.03273757919669151,
2160
+ "rewards/margins": 0.08275122940540314,
2161
+ "rewards/rejected": -0.11548881232738495,
2162
+ "step": 1190
2163
+ },
2164
+ {
2165
+ "epoch": 0.9205983889528193,
2166
+ "grad_norm": 1.53132164478302,
2167
+ "learning_rate": 3.952417498081351e-06,
2168
+ "logits/chosen": -0.4613899290561676,
2169
+ "logits/rejected": -0.45741963386535645,
2170
+ "logps/chosen": -3.1849541664123535,
2171
+ "logps/rejected": -4.181215763092041,
2172
+ "loss": 0.6808,
2173
+ "rewards/accuracies": 0.5249999761581421,
2174
+ "rewards/chosen": -0.048704423010349274,
2175
+ "rewards/margins": 0.04184052720665932,
2176
+ "rewards/rejected": -0.09054495394229889,
2177
+ "step": 1200
2178
+ },
2179
+ {
2180
+ "epoch": 0.9205983889528193,
2181
+ "eval_logits/chosen": -0.25466716289520264,
2182
+ "eval_logits/rejected": -0.2519235908985138,
2183
+ "eval_logps/chosen": -3.6220946311950684,
2184
+ "eval_logps/rejected": -4.108763694763184,
2185
+ "eval_loss": 0.6875774264335632,
2186
+ "eval_rewards/accuracies": 0.5062500238418579,
2187
+ "eval_rewards/chosen": -0.05892205238342285,
2188
+ "eval_rewards/margins": 0.018373344093561172,
2189
+ "eval_rewards/rejected": -0.07729540020227432,
2190
+ "eval_runtime": 87.859,
2191
+ "eval_samples_per_second": 29.069,
2192
+ "eval_steps_per_second": 0.911,
2193
+ "step": 1200
2194
+ },
2195
+ {
2196
+ "epoch": 0.9282700421940928,
2197
+ "grad_norm": 1.241278052330017,
2198
+ "learning_rate": 3.568687643898695e-06,
2199
+ "logits/chosen": -0.4009276032447815,
2200
+ "logits/rejected": -0.40318647027015686,
2201
+ "logps/chosen": -4.127172470092773,
2202
+ "logps/rejected": -3.866589069366455,
2203
+ "loss": 0.6829,
2204
+ "rewards/accuracies": 0.42500001192092896,
2205
+ "rewards/chosen": -0.09695043414831161,
2206
+ "rewards/margins": -0.046161942183971405,
2207
+ "rewards/rejected": -0.05078849941492081,
2208
+ "step": 1210
2209
+ },
2210
+ {
2211
+ "epoch": 0.9359416954353663,
2212
+ "grad_norm": 1.5091854333877563,
2213
+ "learning_rate": 3.18495778971604e-06,
2214
+ "logits/chosen": -0.4826277196407318,
2215
+ "logits/rejected": -0.478055864572525,
2216
+ "logps/chosen": -3.1896512508392334,
2217
+ "logps/rejected": -4.594376564025879,
2218
+ "loss": 0.6881,
2219
+ "rewards/accuracies": 0.574999988079071,
2220
+ "rewards/chosen": -0.04869696497917175,
2221
+ "rewards/margins": 0.07252007722854614,
2222
+ "rewards/rejected": -0.12121704965829849,
2223
+ "step": 1220
2224
+ },
2225
+ {
2226
+ "epoch": 0.9436133486766398,
2227
+ "grad_norm": 1.8513944149017334,
2228
+ "learning_rate": 2.8012279355333845e-06,
2229
+ "logits/chosen": -0.44737452268600464,
2230
+ "logits/rejected": -0.4507928788661957,
2231
+ "logps/chosen": -2.7748920917510986,
2232
+ "logps/rejected": -4.892573356628418,
2233
+ "loss": 0.6837,
2234
+ "rewards/accuracies": 0.675000011920929,
2235
+ "rewards/chosen": -0.0341179221868515,
2236
+ "rewards/margins": 0.06964664161205292,
2237
+ "rewards/rejected": -0.10376457124948502,
2238
+ "step": 1230
2239
+ },
2240
+ {
2241
+ "epoch": 0.9512850019179133,
2242
+ "grad_norm": 1.2888293266296387,
2243
+ "learning_rate": 2.417498081350729e-06,
2244
+ "logits/chosen": -0.42681989073753357,
2245
+ "logits/rejected": -0.4308759570121765,
2246
+ "logps/chosen": -3.6465072631835938,
2247
+ "logps/rejected": -4.087521553039551,
2248
+ "loss": 0.6922,
2249
+ "rewards/accuracies": 0.4749999940395355,
2250
+ "rewards/chosen": -0.08686716109514236,
2251
+ "rewards/margins": -0.01433576364070177,
2252
+ "rewards/rejected": -0.07253140956163406,
2253
+ "step": 1240
2254
+ },
2255
+ {
2256
+ "epoch": 0.9589566551591868,
2257
+ "grad_norm": 1.8460888862609863,
2258
+ "learning_rate": 2.0337682271680737e-06,
2259
+ "logits/chosen": -0.4428413510322571,
2260
+ "logits/rejected": -0.4398593008518219,
2261
+ "logps/chosen": -3.1560444831848145,
2262
+ "logps/rejected": -4.46377420425415,
2263
+ "loss": 0.6783,
2264
+ "rewards/accuracies": 0.550000011920929,
2265
+ "rewards/chosen": -0.02867904305458069,
2266
+ "rewards/margins": 0.08603222668170929,
2267
+ "rewards/rejected": -0.11471126228570938,
2268
+ "step": 1250
2269
+ },
2270
+ {
2271
+ "epoch": 0.9589566551591868,
2272
+ "eval_logits/chosen": -0.257295697927475,
2273
+ "eval_logits/rejected": -0.25472259521484375,
2274
+ "eval_logps/chosen": -3.5708394050598145,
2275
+ "eval_logps/rejected": -4.090200424194336,
2276
+ "eval_loss": 0.6876680850982666,
2277
+ "eval_rewards/accuracies": 0.5249999761581421,
2278
+ "eval_rewards/chosen": -0.053796518594026566,
2279
+ "eval_rewards/margins": 0.021642494946718216,
2280
+ "eval_rewards/rejected": -0.07543901354074478,
2281
+ "eval_runtime": 88.4028,
2282
+ "eval_samples_per_second": 28.89,
2283
+ "eval_steps_per_second": 0.905,
2284
+ "step": 1250
2285
+ },
2286
+ {
2287
+ "epoch": 0.9666283084004603,
2288
+ "grad_norm": 2.0357563495635986,
2289
+ "learning_rate": 1.6500383729854182e-06,
2290
+ "logits/chosen": -0.40101394057273865,
2291
+ "logits/rejected": -0.40456658601760864,
2292
+ "logps/chosen": -3.5583319664001465,
2293
+ "logps/rejected": -4.374687194824219,
2294
+ "loss": 0.6872,
2295
+ "rewards/accuracies": 0.550000011920929,
2296
+ "rewards/chosen": -0.056288547813892365,
2297
+ "rewards/margins": 0.033787138760089874,
2298
+ "rewards/rejected": -0.09007568657398224,
2299
+ "step": 1260
2300
+ },
2301
+ {
2302
+ "epoch": 0.9742999616417338,
2303
+ "grad_norm": 1.2816194295883179,
2304
+ "learning_rate": 1.266308518802763e-06,
2305
+ "logits/chosen": -0.45148950815200806,
2306
+ "logits/rejected": -0.4437050223350525,
2307
+ "logps/chosen": -4.794127464294434,
2308
+ "logps/rejected": -2.5109446048736572,
2309
+ "loss": 0.6883,
2310
+ "rewards/accuracies": 0.42500001192092896,
2311
+ "rewards/chosen": -0.08158718794584274,
2312
+ "rewards/margins": -0.058057576417922974,
2313
+ "rewards/rejected": -0.023529618978500366,
2314
+ "step": 1270
2315
+ },
2316
+ {
2317
+ "epoch": 0.9819716148830073,
2318
+ "grad_norm": 1.3781119585037231,
2319
+ "learning_rate": 8.825786646201075e-07,
2320
+ "logits/chosen": -0.37359991669654846,
2321
+ "logits/rejected": -0.3782901167869568,
2322
+ "logps/chosen": -3.121410369873047,
2323
+ "logps/rejected": -4.8245930671691895,
2324
+ "loss": 0.6868,
2325
+ "rewards/accuracies": 0.6499999761581421,
2326
+ "rewards/chosen": -0.03528415039181709,
2327
+ "rewards/margins": 0.05396044999361038,
2328
+ "rewards/rejected": -0.08924460411071777,
2329
+ "step": 1280
2330
+ },
2331
+ {
2332
+ "epoch": 0.9896432681242808,
2333
+ "grad_norm": 1.4439499378204346,
2334
+ "learning_rate": 4.988488104374521e-07,
2335
+ "logits/chosen": -0.4285728335380554,
2336
+ "logits/rejected": -0.43194809556007385,
2337
+ "logps/chosen": -4.162619113922119,
2338
+ "logps/rejected": -3.23869252204895,
2339
+ "loss": 0.687,
2340
+ "rewards/accuracies": 0.375,
2341
+ "rewards/chosen": -0.0661448985338211,
2342
+ "rewards/margins": -0.029600393027067184,
2343
+ "rewards/rejected": -0.036544498056173325,
2344
+ "step": 1290
2345
+ },
2346
+ {
2347
+ "epoch": 0.9973149213655543,
2348
+ "grad_norm": 1.6206567287445068,
2349
+ "learning_rate": 1.1511895625479663e-07,
2350
+ "logits/chosen": -0.4840824604034424,
2351
+ "logits/rejected": -0.4765002727508545,
2352
+ "logps/chosen": -3.34405255317688,
2353
+ "logps/rejected": -3.7568817138671875,
2354
+ "loss": 0.6942,
2355
+ "rewards/accuracies": 0.5249999761581421,
2356
+ "rewards/chosen": -0.05117567628622055,
2357
+ "rewards/margins": 0.012036425992846489,
2358
+ "rewards/rejected": -0.06321209669113159,
2359
+ "step": 1300
2360
+ },
2361
+ {
2362
+ "epoch": 0.9973149213655543,
2363
+ "eval_logits/chosen": -0.2575662434101105,
2364
+ "eval_logits/rejected": -0.2548866271972656,
2365
+ "eval_logps/chosen": -3.5700440406799316,
2366
+ "eval_logps/rejected": -4.087610721588135,
2367
+ "eval_loss": 0.6874552369117737,
2368
+ "eval_rewards/accuracies": 0.528124988079071,
2369
+ "eval_rewards/chosen": -0.05371702462434769,
2370
+ "eval_rewards/margins": 0.021463003009557724,
2371
+ "eval_rewards/rejected": -0.07518003135919571,
2372
+ "eval_runtime": 87.8745,
2373
+ "eval_samples_per_second": 29.064,
2374
+ "eval_steps_per_second": 0.91,
2375
+ "step": 1300
2376
+ }
2377
+ ],
2378
+ "logging_steps": 10,
2379
+ "max_steps": 1303,
2380
+ "num_input_tokens_seen": 0,
2381
+ "num_train_epochs": 1,
2382
+ "save_steps": 50,
2383
+ "total_flos": 0.0,
2384
+ "train_batch_size": 2,
2385
+ "trial_name": null,
2386
+ "trial_params": null
2387
+ }
Kr_model_for_Llama3_8b/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:126240089abca89c11484144b0304fc5adab5d1aa96e4270876e118e38abfc53
3
+ size 6392
Kr_model_for_Llama3_8b/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)