Delta-Vector commited on
Commit
9a4a12e
·
verified ·
1 Parent(s): a9075e1

Upload 11 files

Browse files
README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Delta-Vector/Control-8B
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 0.13.2
adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Delta-Vector/Control-8B",
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": 64,
14
+ "lora_dropout": 0,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 64,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "down_proj",
24
+ "o_proj",
25
+ "up_proj",
26
+ "gate_proj",
27
+ "k_proj",
28
+ "v_proj",
29
+ "q_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": true
34
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5cfe3747d9c980787a8c79190a32cf9ed558f581ef96e144337156073ee2647
3
+ size 671149168
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58286acca5773d2e7c51dcafc8a86ba940537a8742f2c627cd1d1832a78bd8a2
3
+ size 341314196
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de40ffc0bbc293cc5e26c89be2c2b14865af66d168dc4b4b3ada76d003c13718
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|finetune_right_pad_id|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,2064 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% 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": 131072,
2061
+ "pad_token": "<|finetune_right_pad_id|>",
2062
+ "padding_side": "right",
2063
+ "tokenizer_class": "PreTrainedTokenizerFast"
2064
+ }
trainer_state.json ADDED
@@ -0,0 +1,2313 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.9934426229508198,
5
+ "eval_steps": 500,
6
+ "global_step": 152,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.013114754098360656,
13
+ "grad_norm": NaN,
14
+ "learning_rate": 0.0,
15
+ "logits/chosen": -0.7201688289642334,
16
+ "logits/rejected": -0.25958356261253357,
17
+ "logps/chosen": -235.22982788085938,
18
+ "logps/rejected": -110.77284240722656,
19
+ "loss": 0.6931,
20
+ "rewards/accuracies": 0.0,
21
+ "rewards/chosen": 0.0,
22
+ "rewards/margins": 0.0,
23
+ "rewards/rejected": 0.0,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.02622950819672131,
28
+ "grad_norm": NaN,
29
+ "learning_rate": 0.0,
30
+ "logits/chosen": -0.6440946459770203,
31
+ "logits/rejected": -0.8803070783615112,
32
+ "logps/chosen": -233.35064697265625,
33
+ "logps/rejected": -270.211669921875,
34
+ "loss": 0.6931,
35
+ "rewards/accuracies": 0.0,
36
+ "rewards/chosen": 0.0,
37
+ "rewards/margins": 0.0,
38
+ "rewards/rejected": 0.0,
39
+ "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.03934426229508197,
43
+ "grad_norm": Infinity,
44
+ "learning_rate": 0.0,
45
+ "logits/chosen": -0.3529421091079712,
46
+ "logits/rejected": -0.46579116582870483,
47
+ "logps/chosen": -283.93499755859375,
48
+ "logps/rejected": -236.17298889160156,
49
+ "loss": 0.6931,
50
+ "rewards/accuracies": 0.0,
51
+ "rewards/chosen": 0.0,
52
+ "rewards/margins": 0.0,
53
+ "rewards/rejected": 0.0,
54
+ "step": 3
55
+ },
56
+ {
57
+ "epoch": 0.05245901639344262,
58
+ "grad_norm": 116.6382827758789,
59
+ "learning_rate": 3.125e-07,
60
+ "logits/chosen": -0.6149371862411499,
61
+ "logits/rejected": -0.6765552163124084,
62
+ "logps/chosen": -330.7442321777344,
63
+ "logps/rejected": -333.74853515625,
64
+ "loss": 0.6931,
65
+ "rewards/accuracies": 0.0,
66
+ "rewards/chosen": 0.0,
67
+ "rewards/margins": 0.0,
68
+ "rewards/rejected": 0.0,
69
+ "step": 4
70
+ },
71
+ {
72
+ "epoch": 0.06557377049180328,
73
+ "grad_norm": 96.14250946044922,
74
+ "learning_rate": 6.25e-07,
75
+ "logits/chosen": -0.48342880606651306,
76
+ "logits/rejected": -0.552554190158844,
77
+ "logps/chosen": -224.43968200683594,
78
+ "logps/rejected": -243.84121704101562,
79
+ "loss": 0.6931,
80
+ "rewards/accuracies": 0.0,
81
+ "rewards/chosen": 0.0,
82
+ "rewards/margins": 0.0,
83
+ "rewards/rejected": 0.0,
84
+ "step": 5
85
+ },
86
+ {
87
+ "epoch": 0.07868852459016394,
88
+ "grad_norm": 119.71466064453125,
89
+ "learning_rate": 9.375000000000001e-07,
90
+ "logits/chosen": -0.4438214600086212,
91
+ "logits/rejected": -0.41411423683166504,
92
+ "logps/chosen": -509.1705322265625,
93
+ "logps/rejected": -331.69927978515625,
94
+ "loss": 0.6942,
95
+ "rewards/accuracies": 0.5,
96
+ "rewards/chosen": -0.005420684814453125,
97
+ "rewards/margins": -0.0020191192161291838,
98
+ "rewards/rejected": -0.0034015655983239412,
99
+ "step": 6
100
+ },
101
+ {
102
+ "epoch": 0.09180327868852459,
103
+ "grad_norm": 89.92263793945312,
104
+ "learning_rate": 1.25e-06,
105
+ "logits/chosen": -0.5990754961967468,
106
+ "logits/rejected": -0.5052899718284607,
107
+ "logps/chosen": -353.8023376464844,
108
+ "logps/rejected": -293.9719543457031,
109
+ "loss": 0.6924,
110
+ "rewards/accuracies": 0.75,
111
+ "rewards/chosen": 0.0021602632477879524,
112
+ "rewards/margins": 0.001445007394067943,
113
+ "rewards/rejected": 0.0007152557955123484,
114
+ "step": 7
115
+ },
116
+ {
117
+ "epoch": 0.10491803278688525,
118
+ "grad_norm": 91.0330810546875,
119
+ "learning_rate": 1.5625e-06,
120
+ "logits/chosen": -0.7285553216934204,
121
+ "logits/rejected": -0.8203944563865662,
122
+ "logps/chosen": -201.29092407226562,
123
+ "logps/rejected": -310.0835876464844,
124
+ "loss": 0.6923,
125
+ "rewards/accuracies": 0.75,
126
+ "rewards/chosen": -0.0027733801398426294,
127
+ "rewards/margins": 0.00168361677788198,
128
+ "rewards/rejected": -0.004456996917724609,
129
+ "step": 8
130
+ },
131
+ {
132
+ "epoch": 0.1180327868852459,
133
+ "grad_norm": 115.72259521484375,
134
+ "learning_rate": 1.8750000000000003e-06,
135
+ "logits/chosen": -0.6387780904769897,
136
+ "logits/rejected": -0.4966055750846863,
137
+ "logps/chosen": -286.18316650390625,
138
+ "logps/rejected": -174.62039184570312,
139
+ "loss": 0.6924,
140
+ "rewards/accuracies": 0.75,
141
+ "rewards/chosen": -0.008039474487304688,
142
+ "rewards/margins": 0.0014192580711096525,
143
+ "rewards/rejected": -0.009458731859922409,
144
+ "step": 9
145
+ },
146
+ {
147
+ "epoch": 0.13114754098360656,
148
+ "grad_norm": 81.71347045898438,
149
+ "learning_rate": 2.1875000000000002e-06,
150
+ "logits/chosen": -0.43023377656936646,
151
+ "logits/rejected": -0.4917900860309601,
152
+ "logps/chosen": -123.80950164794922,
153
+ "logps/rejected": -231.78781127929688,
154
+ "loss": 0.6922,
155
+ "rewards/accuracies": 0.25,
156
+ "rewards/chosen": -0.013120556250214577,
157
+ "rewards/margins": 0.001862620934844017,
158
+ "rewards/rejected": -0.014983177185058594,
159
+ "step": 10
160
+ },
161
+ {
162
+ "epoch": 0.14426229508196722,
163
+ "grad_norm": 126.95443725585938,
164
+ "learning_rate": 2.5e-06,
165
+ "logits/chosen": -0.5431928634643555,
166
+ "logits/rejected": -0.6928932666778564,
167
+ "logps/chosen": -466.6590881347656,
168
+ "logps/rejected": -450.839111328125,
169
+ "loss": 0.6835,
170
+ "rewards/accuracies": 0.75,
171
+ "rewards/chosen": 0.003947257064282894,
172
+ "rewards/margins": 0.01957416534423828,
173
+ "rewards/rejected": -0.015626907348632812,
174
+ "step": 11
175
+ },
176
+ {
177
+ "epoch": 0.15737704918032788,
178
+ "grad_norm": 106.9858169555664,
179
+ "learning_rate": 2.8125e-06,
180
+ "logits/chosen": -0.8515354990959167,
181
+ "logits/rejected": -0.8400233387947083,
182
+ "logps/chosen": -496.6812438964844,
183
+ "logps/rejected": -367.9149169921875,
184
+ "loss": 0.6932,
185
+ "rewards/accuracies": 0.5,
186
+ "rewards/chosen": -0.013410568237304688,
187
+ "rewards/margins": 0.0008895890787243843,
188
+ "rewards/rejected": -0.014300156384706497,
189
+ "step": 12
190
+ },
191
+ {
192
+ "epoch": 0.17049180327868851,
193
+ "grad_norm": 94.6556167602539,
194
+ "learning_rate": 3.125e-06,
195
+ "logits/chosen": -0.8845179080963135,
196
+ "logits/rejected": -0.8273138403892517,
197
+ "logps/chosen": -332.0273742675781,
198
+ "logps/rejected": -263.0736389160156,
199
+ "loss": 0.6739,
200
+ "rewards/accuracies": 0.75,
201
+ "rewards/chosen": -0.0007216455414891243,
202
+ "rewards/margins": 0.03937549516558647,
203
+ "rewards/rejected": -0.04009714350104332,
204
+ "step": 13
205
+ },
206
+ {
207
+ "epoch": 0.18360655737704917,
208
+ "grad_norm": 110.63664245605469,
209
+ "learning_rate": 3.4375e-06,
210
+ "logits/chosen": -0.49672091007232666,
211
+ "logits/rejected": -0.7252901792526245,
212
+ "logps/chosen": -182.361572265625,
213
+ "logps/rejected": -378.4778747558594,
214
+ "loss": 0.6764,
215
+ "rewards/accuracies": 0.5,
216
+ "rewards/chosen": -0.03787527605891228,
217
+ "rewards/margins": 0.0358370766043663,
218
+ "rewards/rejected": -0.07371234893798828,
219
+ "step": 14
220
+ },
221
+ {
222
+ "epoch": 0.19672131147540983,
223
+ "grad_norm": 76.27680969238281,
224
+ "learning_rate": 3.7500000000000005e-06,
225
+ "logits/chosen": -0.5162211656570435,
226
+ "logits/rejected": -0.4975786507129669,
227
+ "logps/chosen": -179.30902099609375,
228
+ "logps/rejected": -132.12823486328125,
229
+ "loss": 0.6905,
230
+ "rewards/accuracies": 0.75,
231
+ "rewards/chosen": -0.037923429161310196,
232
+ "rewards/margins": 0.005405997391790152,
233
+ "rewards/rejected": -0.04332943260669708,
234
+ "step": 15
235
+ },
236
+ {
237
+ "epoch": 0.2098360655737705,
238
+ "grad_norm": 91.94597625732422,
239
+ "learning_rate": 4.0625000000000005e-06,
240
+ "logits/chosen": -0.3636321425437927,
241
+ "logits/rejected": -0.6324741840362549,
242
+ "logps/chosen": -153.548828125,
243
+ "logps/rejected": -371.84765625,
244
+ "loss": 0.713,
245
+ "rewards/accuracies": 0.25,
246
+ "rewards/chosen": -0.06001920625567436,
247
+ "rewards/margins": -0.038457777351140976,
248
+ "rewards/rejected": -0.021561432629823685,
249
+ "step": 16
250
+ },
251
+ {
252
+ "epoch": 0.22295081967213115,
253
+ "grad_norm": 75.85398864746094,
254
+ "learning_rate": 4.3750000000000005e-06,
255
+ "logits/chosen": -0.5712193250656128,
256
+ "logits/rejected": -0.3860137164592743,
257
+ "logps/chosen": -267.605224609375,
258
+ "logps/rejected": -104.8357162475586,
259
+ "loss": 0.6921,
260
+ "rewards/accuracies": 0.5,
261
+ "rewards/chosen": -0.022034931927919388,
262
+ "rewards/margins": 0.0022784238681197166,
263
+ "rewards/rejected": -0.02431335672736168,
264
+ "step": 17
265
+ },
266
+ {
267
+ "epoch": 0.2360655737704918,
268
+ "grad_norm": 117.28124237060547,
269
+ "learning_rate": 4.6875000000000004e-06,
270
+ "logits/chosen": -0.5285807251930237,
271
+ "logits/rejected": -0.3493229150772095,
272
+ "logps/chosen": -380.4576416015625,
273
+ "logps/rejected": -311.0014343261719,
274
+ "loss": 0.7359,
275
+ "rewards/accuracies": 0.5,
276
+ "rewards/chosen": -0.16734714806079865,
277
+ "rewards/margins": -0.07893352955579758,
278
+ "rewards/rejected": -0.08841361850500107,
279
+ "step": 18
280
+ },
281
+ {
282
+ "epoch": 0.24918032786885247,
283
+ "grad_norm": 90.01153564453125,
284
+ "learning_rate": 5e-06,
285
+ "logits/chosen": -0.6711679697036743,
286
+ "logits/rejected": -0.2690754532814026,
287
+ "logps/chosen": -462.41973876953125,
288
+ "logps/rejected": -297.78363037109375,
289
+ "loss": 0.6435,
290
+ "rewards/accuracies": 0.75,
291
+ "rewards/chosen": -0.0683719664812088,
292
+ "rewards/margins": 0.10821684449911118,
293
+ "rewards/rejected": -0.17658883333206177,
294
+ "step": 19
295
+ },
296
+ {
297
+ "epoch": 0.26229508196721313,
298
+ "grad_norm": 73.38824462890625,
299
+ "learning_rate": 4.9632352941176475e-06,
300
+ "logits/chosen": -0.6787087917327881,
301
+ "logits/rejected": -0.6652618050575256,
302
+ "logps/chosen": -361.91131591796875,
303
+ "logps/rejected": -243.35589599609375,
304
+ "loss": 0.6319,
305
+ "rewards/accuracies": 1.0,
306
+ "rewards/chosen": 0.04816999286413193,
307
+ "rewards/margins": 0.12730780243873596,
308
+ "rewards/rejected": -0.07913780957460403,
309
+ "step": 20
310
+ },
311
+ {
312
+ "epoch": 0.2754098360655738,
313
+ "grad_norm": 115.89125061035156,
314
+ "learning_rate": 4.9264705882352945e-06,
315
+ "logits/chosen": -0.3588840365409851,
316
+ "logits/rejected": -0.2116285115480423,
317
+ "logps/chosen": -400.4305419921875,
318
+ "logps/rejected": -362.8456726074219,
319
+ "loss": 0.6087,
320
+ "rewards/accuracies": 1.0,
321
+ "rewards/chosen": 0.10708275437355042,
322
+ "rewards/margins": 0.1842678040266037,
323
+ "rewards/rejected": -0.07718505710363388,
324
+ "step": 21
325
+ },
326
+ {
327
+ "epoch": 0.28852459016393445,
328
+ "grad_norm": 78.77503204345703,
329
+ "learning_rate": 4.889705882352942e-06,
330
+ "logits/chosen": -0.8203290700912476,
331
+ "logits/rejected": -0.8240777254104614,
332
+ "logps/chosen": -166.8377685546875,
333
+ "logps/rejected": -170.83688354492188,
334
+ "loss": 0.7257,
335
+ "rewards/accuracies": 0.5,
336
+ "rewards/chosen": -0.06841621547937393,
337
+ "rewards/margins": -0.061698053032159805,
338
+ "rewards/rejected": -0.0067181577906012535,
339
+ "step": 22
340
+ },
341
+ {
342
+ "epoch": 0.3016393442622951,
343
+ "grad_norm": 121.3331527709961,
344
+ "learning_rate": 4.852941176470589e-06,
345
+ "logits/chosen": -0.2023768126964569,
346
+ "logits/rejected": 0.14346128702163696,
347
+ "logps/chosen": -404.2669677734375,
348
+ "logps/rejected": -286.7450256347656,
349
+ "loss": 0.6238,
350
+ "rewards/accuracies": 0.75,
351
+ "rewards/chosen": 0.12858295440673828,
352
+ "rewards/margins": 0.14947663247585297,
353
+ "rewards/rejected": -0.020893670618534088,
354
+ "step": 23
355
+ },
356
+ {
357
+ "epoch": 0.31475409836065577,
358
+ "grad_norm": 103.55362701416016,
359
+ "learning_rate": 4.816176470588236e-06,
360
+ "logits/chosen": -0.5769512057304382,
361
+ "logits/rejected": -0.7388426661491394,
362
+ "logps/chosen": -483.7005310058594,
363
+ "logps/rejected": -367.4910583496094,
364
+ "loss": 0.5843,
365
+ "rewards/accuracies": 1.0,
366
+ "rewards/chosen": 0.05827799811959267,
367
+ "rewards/margins": 0.27695170044898987,
368
+ "rewards/rejected": -0.2186737060546875,
369
+ "step": 24
370
+ },
371
+ {
372
+ "epoch": 0.32786885245901637,
373
+ "grad_norm": 72.6626205444336,
374
+ "learning_rate": 4.779411764705883e-06,
375
+ "logits/chosen": -0.7255613803863525,
376
+ "logits/rejected": -0.884934663772583,
377
+ "logps/chosen": -183.0727081298828,
378
+ "logps/rejected": -202.55877685546875,
379
+ "loss": 0.6588,
380
+ "rewards/accuracies": 0.75,
381
+ "rewards/chosen": 0.0200653113424778,
382
+ "rewards/margins": 0.09606742858886719,
383
+ "rewards/rejected": -0.07600211352109909,
384
+ "step": 25
385
+ },
386
+ {
387
+ "epoch": 0.34098360655737703,
388
+ "grad_norm": 88.45654296875,
389
+ "learning_rate": 4.74264705882353e-06,
390
+ "logits/chosen": -0.5392031073570251,
391
+ "logits/rejected": -0.7600653171539307,
392
+ "logps/chosen": -405.0447998046875,
393
+ "logps/rejected": -448.3751220703125,
394
+ "loss": 0.5453,
395
+ "rewards/accuracies": 1.0,
396
+ "rewards/chosen": 0.170909121632576,
397
+ "rewards/margins": 0.33048784732818604,
398
+ "rewards/rejected": -0.15957871079444885,
399
+ "step": 26
400
+ },
401
+ {
402
+ "epoch": 0.3540983606557377,
403
+ "grad_norm": 72.38986206054688,
404
+ "learning_rate": 4.705882352941177e-06,
405
+ "logits/chosen": -0.8080704212188721,
406
+ "logits/rejected": -0.4376976788043976,
407
+ "logps/chosen": -242.55665588378906,
408
+ "logps/rejected": -131.02154541015625,
409
+ "loss": 0.7378,
410
+ "rewards/accuracies": 0.75,
411
+ "rewards/chosen": -0.07056399434804916,
412
+ "rewards/margins": -0.06801767647266388,
413
+ "rewards/rejected": -0.0025463104248046875,
414
+ "step": 27
415
+ },
416
+ {
417
+ "epoch": 0.36721311475409835,
418
+ "grad_norm": 89.0915298461914,
419
+ "learning_rate": 4.669117647058824e-06,
420
+ "logits/chosen": -0.7039719820022583,
421
+ "logits/rejected": -0.45313090085983276,
422
+ "logps/chosen": -357.1167297363281,
423
+ "logps/rejected": -254.34747314453125,
424
+ "loss": 0.6511,
425
+ "rewards/accuracies": 0.5,
426
+ "rewards/chosen": 0.1653575897216797,
427
+ "rewards/margins": 0.11446285247802734,
428
+ "rewards/rejected": 0.050894737243652344,
429
+ "step": 28
430
+ },
431
+ {
432
+ "epoch": 0.380327868852459,
433
+ "grad_norm": 72.88048553466797,
434
+ "learning_rate": 4.632352941176471e-06,
435
+ "logits/chosen": -0.4176654815673828,
436
+ "logits/rejected": -0.8021068572998047,
437
+ "logps/chosen": -118.46458435058594,
438
+ "logps/rejected": -266.1793518066406,
439
+ "loss": 0.6207,
440
+ "rewards/accuracies": 0.5,
441
+ "rewards/chosen": -0.03454189747571945,
442
+ "rewards/margins": 0.17219945788383484,
443
+ "rewards/rejected": -0.2067413479089737,
444
+ "step": 29
445
+ },
446
+ {
447
+ "epoch": 0.39344262295081966,
448
+ "grad_norm": 112.41997528076172,
449
+ "learning_rate": 4.595588235294118e-06,
450
+ "logits/chosen": -0.5515627264976501,
451
+ "logits/rejected": -0.3022332489490509,
452
+ "logps/chosen": -383.1882629394531,
453
+ "logps/rejected": -355.9986877441406,
454
+ "loss": 0.7112,
455
+ "rewards/accuracies": 0.25,
456
+ "rewards/chosen": 0.12149354070425034,
457
+ "rewards/margins": 0.018218979239463806,
458
+ "rewards/rejected": 0.10327454656362534,
459
+ "step": 30
460
+ },
461
+ {
462
+ "epoch": 0.4065573770491803,
463
+ "grad_norm": 99.6341781616211,
464
+ "learning_rate": 4.558823529411765e-06,
465
+ "logits/chosen": -0.32010310888290405,
466
+ "logits/rejected": -0.34287354350090027,
467
+ "logps/chosen": -433.3697509765625,
468
+ "logps/rejected": -427.46868896484375,
469
+ "loss": 0.5341,
470
+ "rewards/accuracies": 1.0,
471
+ "rewards/chosen": 0.1381477415561676,
472
+ "rewards/margins": 0.3722812533378601,
473
+ "rewards/rejected": -0.2341335415840149,
474
+ "step": 31
475
+ },
476
+ {
477
+ "epoch": 0.419672131147541,
478
+ "grad_norm": 141.9149932861328,
479
+ "learning_rate": 4.522058823529412e-06,
480
+ "logits/chosen": -0.3783895969390869,
481
+ "logits/rejected": -0.22028671205043793,
482
+ "logps/chosen": -438.865478515625,
483
+ "logps/rejected": -378.45306396484375,
484
+ "loss": 0.7389,
485
+ "rewards/accuracies": 0.75,
486
+ "rewards/chosen": -0.20297011733055115,
487
+ "rewards/margins": -0.03645037114620209,
488
+ "rewards/rejected": -0.16651973128318787,
489
+ "step": 32
490
+ },
491
+ {
492
+ "epoch": 0.43278688524590164,
493
+ "grad_norm": 83.45268249511719,
494
+ "learning_rate": 4.485294117647059e-06,
495
+ "logits/chosen": -0.4643877446651459,
496
+ "logits/rejected": -0.23612239956855774,
497
+ "logps/chosen": -323.2715148925781,
498
+ "logps/rejected": -257.071533203125,
499
+ "loss": 0.6477,
500
+ "rewards/accuracies": 0.5,
501
+ "rewards/chosen": 0.06585502624511719,
502
+ "rewards/margins": 0.09959708154201508,
503
+ "rewards/rejected": -0.03374204784631729,
504
+ "step": 33
505
+ },
506
+ {
507
+ "epoch": 0.4459016393442623,
508
+ "grad_norm": 123.2249526977539,
509
+ "learning_rate": 4.448529411764706e-06,
510
+ "logits/chosen": -0.7680925130844116,
511
+ "logits/rejected": -0.6171376705169678,
512
+ "logps/chosen": -480.37481689453125,
513
+ "logps/rejected": -430.70379638671875,
514
+ "loss": 0.7551,
515
+ "rewards/accuracies": 0.5,
516
+ "rewards/chosen": -0.217463880777359,
517
+ "rewards/margins": -0.08437519520521164,
518
+ "rewards/rejected": -0.13308867812156677,
519
+ "step": 34
520
+ },
521
+ {
522
+ "epoch": 0.45901639344262296,
523
+ "grad_norm": NaN,
524
+ "learning_rate": 4.448529411764706e-06,
525
+ "logits/chosen": -0.9053277969360352,
526
+ "logits/rejected": -0.691852331161499,
527
+ "logps/chosen": -409.5699462890625,
528
+ "logps/rejected": -475.8656005859375,
529
+ "loss": 0.8483,
530
+ "rewards/accuracies": 0.25,
531
+ "rewards/chosen": -0.18217086791992188,
532
+ "rewards/margins": -0.2824680209159851,
533
+ "rewards/rejected": 0.10029716044664383,
534
+ "step": 35
535
+ },
536
+ {
537
+ "epoch": 0.4721311475409836,
538
+ "grad_norm": 105.83935546875,
539
+ "learning_rate": 4.411764705882353e-06,
540
+ "logits/chosen": -0.28655514121055603,
541
+ "logits/rejected": -0.05234713852405548,
542
+ "logps/chosen": -563.8226318359375,
543
+ "logps/rejected": -375.774658203125,
544
+ "loss": 0.6024,
545
+ "rewards/accuracies": 0.75,
546
+ "rewards/chosen": 0.048460379242897034,
547
+ "rewards/margins": 0.28112107515335083,
548
+ "rewards/rejected": -0.2326606810092926,
549
+ "step": 36
550
+ },
551
+ {
552
+ "epoch": 0.4852459016393443,
553
+ "grad_norm": 68.51673126220703,
554
+ "learning_rate": 4.3750000000000005e-06,
555
+ "logits/chosen": -0.7692010402679443,
556
+ "logits/rejected": -0.9052639007568359,
557
+ "logps/chosen": -262.10467529296875,
558
+ "logps/rejected": -209.62413024902344,
559
+ "loss": 0.5991,
560
+ "rewards/accuracies": 1.0,
561
+ "rewards/chosen": 0.09292706847190857,
562
+ "rewards/margins": 0.20516462624073029,
563
+ "rewards/rejected": -0.11223754286766052,
564
+ "step": 37
565
+ },
566
+ {
567
+ "epoch": 0.49836065573770494,
568
+ "grad_norm": 152.35870361328125,
569
+ "learning_rate": 4.3382352941176475e-06,
570
+ "logits/chosen": -0.4434085190296173,
571
+ "logits/rejected": -0.5462446212768555,
572
+ "logps/chosen": -325.6352844238281,
573
+ "logps/rejected": -386.6681823730469,
574
+ "loss": 1.048,
575
+ "rewards/accuracies": 0.5,
576
+ "rewards/chosen": -0.2829402983188629,
577
+ "rewards/margins": -0.5018165707588196,
578
+ "rewards/rejected": 0.21887625753879547,
579
+ "step": 38
580
+ },
581
+ {
582
+ "epoch": 0.5114754098360655,
583
+ "grad_norm": 128.87644958496094,
584
+ "learning_rate": 4.301470588235295e-06,
585
+ "logits/chosen": -0.32321175932884216,
586
+ "logits/rejected": -0.6219479441642761,
587
+ "logps/chosen": -220.80865478515625,
588
+ "logps/rejected": -679.1721801757812,
589
+ "loss": 0.6471,
590
+ "rewards/accuracies": 0.75,
591
+ "rewards/chosen": -0.08989439904689789,
592
+ "rewards/margins": 0.1783585399389267,
593
+ "rewards/rejected": -0.268252968788147,
594
+ "step": 39
595
+ },
596
+ {
597
+ "epoch": 0.5245901639344263,
598
+ "grad_norm": 164.9374542236328,
599
+ "learning_rate": 4.264705882352942e-06,
600
+ "logits/chosen": -0.41436851024627686,
601
+ "logits/rejected": -0.3371754288673401,
602
+ "logps/chosen": -453.7709045410156,
603
+ "logps/rejected": -186.964599609375,
604
+ "loss": 0.7023,
605
+ "rewards/accuracies": 0.5,
606
+ "rewards/chosen": -0.012208174914121628,
607
+ "rewards/margins": 0.0052278414368629456,
608
+ "rewards/rejected": -0.01743602193892002,
609
+ "step": 40
610
+ },
611
+ {
612
+ "epoch": 0.5377049180327869,
613
+ "grad_norm": 85.42108917236328,
614
+ "learning_rate": 4.227941176470589e-06,
615
+ "logits/chosen": -0.3417915403842926,
616
+ "logits/rejected": -0.6106492280960083,
617
+ "logps/chosen": -410.3317565917969,
618
+ "logps/rejected": -356.129638671875,
619
+ "loss": 0.5101,
620
+ "rewards/accuracies": 0.75,
621
+ "rewards/chosen": 0.12232876569032669,
622
+ "rewards/margins": 0.4886293411254883,
623
+ "rewards/rejected": -0.3663005828857422,
624
+ "step": 41
625
+ },
626
+ {
627
+ "epoch": 0.5508196721311476,
628
+ "grad_norm": 92.59017181396484,
629
+ "learning_rate": 4.191176470588236e-06,
630
+ "logits/chosen": -0.3282807171344757,
631
+ "logits/rejected": -0.6609268188476562,
632
+ "logps/chosen": -273.1469421386719,
633
+ "logps/rejected": -394.88787841796875,
634
+ "loss": 0.5399,
635
+ "rewards/accuracies": 1.0,
636
+ "rewards/chosen": 0.09656943380832672,
637
+ "rewards/margins": 0.3409425616264343,
638
+ "rewards/rejected": -0.2443731427192688,
639
+ "step": 42
640
+ },
641
+ {
642
+ "epoch": 0.5639344262295082,
643
+ "grad_norm": 113.27176666259766,
644
+ "learning_rate": 4.154411764705883e-06,
645
+ "logits/chosen": -0.6696023941040039,
646
+ "logits/rejected": -0.4758712649345398,
647
+ "logps/chosen": -259.9328918457031,
648
+ "logps/rejected": -257.8404846191406,
649
+ "loss": 0.7035,
650
+ "rewards/accuracies": 0.5,
651
+ "rewards/chosen": -0.07427978515625,
652
+ "rewards/margins": 0.009069837629795074,
653
+ "rewards/rejected": -0.08334961533546448,
654
+ "step": 43
655
+ },
656
+ {
657
+ "epoch": 0.5770491803278689,
658
+ "grad_norm": 115.66248321533203,
659
+ "learning_rate": 4.11764705882353e-06,
660
+ "logits/chosen": -0.5908689498901367,
661
+ "logits/rejected": -0.6039953231811523,
662
+ "logps/chosen": -264.3017578125,
663
+ "logps/rejected": -345.41534423828125,
664
+ "loss": 0.758,
665
+ "rewards/accuracies": 0.5,
666
+ "rewards/chosen": -0.16783800721168518,
667
+ "rewards/margins": -0.07998895645141602,
668
+ "rewards/rejected": -0.08784904330968857,
669
+ "step": 44
670
+ },
671
+ {
672
+ "epoch": 0.5901639344262295,
673
+ "grad_norm": 114.06060028076172,
674
+ "learning_rate": 4.080882352941177e-06,
675
+ "logits/chosen": -0.4014369249343872,
676
+ "logits/rejected": -0.31871065497398376,
677
+ "logps/chosen": -365.35687255859375,
678
+ "logps/rejected": -380.46661376953125,
679
+ "loss": 0.7162,
680
+ "rewards/accuracies": 0.75,
681
+ "rewards/chosen": 0.09307613968849182,
682
+ "rewards/margins": -0.03436946123838425,
683
+ "rewards/rejected": 0.12744559347629547,
684
+ "step": 45
685
+ },
686
+ {
687
+ "epoch": 0.6032786885245902,
688
+ "grad_norm": 138.62567138671875,
689
+ "learning_rate": 4.044117647058824e-06,
690
+ "logits/chosen": -0.638996958732605,
691
+ "logits/rejected": -0.39604443311691284,
692
+ "logps/chosen": -286.7137451171875,
693
+ "logps/rejected": -220.05154418945312,
694
+ "loss": 0.8332,
695
+ "rewards/accuracies": 0.5,
696
+ "rewards/chosen": -0.1774437129497528,
697
+ "rewards/margins": -0.23038703203201294,
698
+ "rewards/rejected": 0.05294332653284073,
699
+ "step": 46
700
+ },
701
+ {
702
+ "epoch": 0.6163934426229508,
703
+ "grad_norm": 57.410499572753906,
704
+ "learning_rate": 4.007352941176471e-06,
705
+ "logits/chosen": -0.6090636253356934,
706
+ "logits/rejected": -0.5290719866752625,
707
+ "logps/chosen": -137.49166870117188,
708
+ "logps/rejected": -139.84095764160156,
709
+ "loss": 0.5675,
710
+ "rewards/accuracies": 1.0,
711
+ "rewards/chosen": 0.006125451996922493,
712
+ "rewards/margins": 0.29940930008888245,
713
+ "rewards/rejected": -0.2932838499546051,
714
+ "step": 47
715
+ },
716
+ {
717
+ "epoch": 0.6295081967213115,
718
+ "grad_norm": 74.56676483154297,
719
+ "learning_rate": 3.970588235294118e-06,
720
+ "logits/chosen": -0.7181419134140015,
721
+ "logits/rejected": -0.4697718024253845,
722
+ "logps/chosen": -189.2108154296875,
723
+ "logps/rejected": -129.29373168945312,
724
+ "loss": 0.6282,
725
+ "rewards/accuracies": 0.75,
726
+ "rewards/chosen": -0.16447561979293823,
727
+ "rewards/margins": 0.13910141587257385,
728
+ "rewards/rejected": -0.3035770356655121,
729
+ "step": 48
730
+ },
731
+ {
732
+ "epoch": 0.6426229508196721,
733
+ "grad_norm": 71.27189636230469,
734
+ "learning_rate": 3.933823529411765e-06,
735
+ "logits/chosen": -0.5085806846618652,
736
+ "logits/rejected": -0.44473588466644287,
737
+ "logps/chosen": -442.37554931640625,
738
+ "logps/rejected": -340.0184326171875,
739
+ "loss": 0.4663,
740
+ "rewards/accuracies": 1.0,
741
+ "rewards/chosen": 0.27928200364112854,
742
+ "rewards/margins": 0.581198513507843,
743
+ "rewards/rejected": -0.3019165098667145,
744
+ "step": 49
745
+ },
746
+ {
747
+ "epoch": 0.6557377049180327,
748
+ "grad_norm": 94.27779388427734,
749
+ "learning_rate": 3.897058823529412e-06,
750
+ "logits/chosen": -0.43181851506233215,
751
+ "logits/rejected": -0.2016599327325821,
752
+ "logps/chosen": -412.7520446777344,
753
+ "logps/rejected": -255.32366943359375,
754
+ "loss": 0.5602,
755
+ "rewards/accuracies": 0.75,
756
+ "rewards/chosen": 0.15803948044776917,
757
+ "rewards/margins": 0.30720824003219604,
758
+ "rewards/rejected": -0.14916877448558807,
759
+ "step": 50
760
+ },
761
+ {
762
+ "epoch": 0.6688524590163935,
763
+ "grad_norm": 105.73281860351562,
764
+ "learning_rate": 3.860294117647059e-06,
765
+ "logits/chosen": -0.8714503645896912,
766
+ "logits/rejected": -0.8866394758224487,
767
+ "logps/chosen": -234.35894775390625,
768
+ "logps/rejected": -381.7604064941406,
769
+ "loss": 0.679,
770
+ "rewards/accuracies": 0.5,
771
+ "rewards/chosen": 0.20015183091163635,
772
+ "rewards/margins": 0.0683051347732544,
773
+ "rewards/rejected": 0.13184669613838196,
774
+ "step": 51
775
+ },
776
+ {
777
+ "epoch": 0.6819672131147541,
778
+ "grad_norm": 114.59404754638672,
779
+ "learning_rate": 3.8235294117647055e-06,
780
+ "logits/chosen": -0.3797226846218109,
781
+ "logits/rejected": -0.28768518567085266,
782
+ "logps/chosen": -527.8758544921875,
783
+ "logps/rejected": -398.22833251953125,
784
+ "loss": 0.5557,
785
+ "rewards/accuracies": 0.75,
786
+ "rewards/chosen": 0.1556282937526703,
787
+ "rewards/margins": 0.3929787576198578,
788
+ "rewards/rejected": -0.2373504638671875,
789
+ "step": 52
790
+ },
791
+ {
792
+ "epoch": 0.6950819672131148,
793
+ "grad_norm": 79.82359313964844,
794
+ "learning_rate": 3.786764705882353e-06,
795
+ "logits/chosen": -0.36424490809440613,
796
+ "logits/rejected": -0.4016554355621338,
797
+ "logps/chosen": -264.1070556640625,
798
+ "logps/rejected": -228.17445373535156,
799
+ "loss": 0.5864,
800
+ "rewards/accuracies": 0.75,
801
+ "rewards/chosen": 0.08102244883775711,
802
+ "rewards/margins": 0.2558790147304535,
803
+ "rewards/rejected": -0.17485657334327698,
804
+ "step": 53
805
+ },
806
+ {
807
+ "epoch": 0.7081967213114754,
808
+ "grad_norm": 96.55302429199219,
809
+ "learning_rate": 3.7500000000000005e-06,
810
+ "logits/chosen": -0.2944083511829376,
811
+ "logits/rejected": -0.1153193861246109,
812
+ "logps/chosen": -548.8867797851562,
813
+ "logps/rejected": -476.7703857421875,
814
+ "loss": 0.4772,
815
+ "rewards/accuracies": 1.0,
816
+ "rewards/chosen": 0.578123152256012,
817
+ "rewards/margins": 0.5144607424736023,
818
+ "rewards/rejected": 0.0636623352766037,
819
+ "step": 54
820
+ },
821
+ {
822
+ "epoch": 0.7213114754098361,
823
+ "grad_norm": 99.41586303710938,
824
+ "learning_rate": 3.7132352941176476e-06,
825
+ "logits/chosen": -0.28071513772010803,
826
+ "logits/rejected": -0.3517005443572998,
827
+ "logps/chosen": -269.35107421875,
828
+ "logps/rejected": -245.49374389648438,
829
+ "loss": 0.6535,
830
+ "rewards/accuracies": 0.75,
831
+ "rewards/chosen": -0.32255783677101135,
832
+ "rewards/margins": 0.18369215726852417,
833
+ "rewards/rejected": -0.5062500238418579,
834
+ "step": 55
835
+ },
836
+ {
837
+ "epoch": 0.7344262295081967,
838
+ "grad_norm": 102.873046875,
839
+ "learning_rate": 3.6764705882352946e-06,
840
+ "logits/chosen": -0.5045206546783447,
841
+ "logits/rejected": -0.33617326617240906,
842
+ "logps/chosen": -446.717529296875,
843
+ "logps/rejected": -354.23199462890625,
844
+ "loss": 0.5308,
845
+ "rewards/accuracies": 1.0,
846
+ "rewards/chosen": 0.11581029742956161,
847
+ "rewards/margins": 0.36529916524887085,
848
+ "rewards/rejected": -0.24948886036872864,
849
+ "step": 56
850
+ },
851
+ {
852
+ "epoch": 0.7475409836065574,
853
+ "grad_norm": 107.32563018798828,
854
+ "learning_rate": 3.6397058823529413e-06,
855
+ "logits/chosen": -0.7487730979919434,
856
+ "logits/rejected": -0.5132504105567932,
857
+ "logps/chosen": -297.9276428222656,
858
+ "logps/rejected": -272.4541015625,
859
+ "loss": 0.6717,
860
+ "rewards/accuracies": 0.75,
861
+ "rewards/chosen": 0.00452117994427681,
862
+ "rewards/margins": 0.049825482070446014,
863
+ "rewards/rejected": -0.045304298400878906,
864
+ "step": 57
865
+ },
866
+ {
867
+ "epoch": 0.760655737704918,
868
+ "grad_norm": 197.63619995117188,
869
+ "learning_rate": 3.6029411764705883e-06,
870
+ "logits/chosen": -0.3516054153442383,
871
+ "logits/rejected": -0.4525684714317322,
872
+ "logps/chosen": -527.5667724609375,
873
+ "logps/rejected": -721.8489990234375,
874
+ "loss": 0.9658,
875
+ "rewards/accuracies": 0.5,
876
+ "rewards/chosen": -0.026310719549655914,
877
+ "rewards/margins": -0.28759005665779114,
878
+ "rewards/rejected": 0.26127931475639343,
879
+ "step": 58
880
+ },
881
+ {
882
+ "epoch": 0.7737704918032787,
883
+ "grad_norm": 58.864341735839844,
884
+ "learning_rate": 3.566176470588236e-06,
885
+ "logits/chosen": -0.8907312750816345,
886
+ "logits/rejected": -0.5560203194618225,
887
+ "logps/chosen": -356.2855224609375,
888
+ "logps/rejected": -259.6497802734375,
889
+ "loss": 0.5038,
890
+ "rewards/accuracies": 0.75,
891
+ "rewards/chosen": 0.31428688764572144,
892
+ "rewards/margins": 0.4714818000793457,
893
+ "rewards/rejected": -0.15719491243362427,
894
+ "step": 59
895
+ },
896
+ {
897
+ "epoch": 0.7868852459016393,
898
+ "grad_norm": 77.59774017333984,
899
+ "learning_rate": 3.529411764705883e-06,
900
+ "logits/chosen": -0.5632966160774231,
901
+ "logits/rejected": -0.6254044771194458,
902
+ "logps/chosen": -523.7625732421875,
903
+ "logps/rejected": -410.9280700683594,
904
+ "loss": 0.3917,
905
+ "rewards/accuracies": 0.75,
906
+ "rewards/chosen": 0.16903266310691833,
907
+ "rewards/margins": 0.9428247213363647,
908
+ "rewards/rejected": -0.7737920880317688,
909
+ "step": 60
910
+ },
911
+ {
912
+ "epoch": 0.8,
913
+ "grad_norm": 125.0260009765625,
914
+ "learning_rate": 3.4926470588235295e-06,
915
+ "logits/chosen": -0.7440542578697205,
916
+ "logits/rejected": -0.703271210193634,
917
+ "logps/chosen": -259.8118591308594,
918
+ "logps/rejected": -273.839599609375,
919
+ "loss": 0.8524,
920
+ "rewards/accuracies": 0.25,
921
+ "rewards/chosen": -0.13262319564819336,
922
+ "rewards/margins": -0.27512502670288086,
923
+ "rewards/rejected": 0.1425018012523651,
924
+ "step": 61
925
+ },
926
+ {
927
+ "epoch": 0.8131147540983606,
928
+ "grad_norm": 76.26204681396484,
929
+ "learning_rate": 3.4558823529411766e-06,
930
+ "logits/chosen": -0.7221469283103943,
931
+ "logits/rejected": -0.7659784555435181,
932
+ "logps/chosen": -184.25143432617188,
933
+ "logps/rejected": -179.50430297851562,
934
+ "loss": 0.6865,
935
+ "rewards/accuracies": 0.5,
936
+ "rewards/chosen": 0.0025919005274772644,
937
+ "rewards/margins": 0.019242577254772186,
938
+ "rewards/rejected": -0.016650676727294922,
939
+ "step": 62
940
+ },
941
+ {
942
+ "epoch": 0.8262295081967214,
943
+ "grad_norm": 98.49539184570312,
944
+ "learning_rate": 3.419117647058824e-06,
945
+ "logits/chosen": -0.39552026987075806,
946
+ "logits/rejected": -0.5626529455184937,
947
+ "logps/chosen": -299.3195495605469,
948
+ "logps/rejected": -409.58978271484375,
949
+ "loss": 0.6728,
950
+ "rewards/accuracies": 0.75,
951
+ "rewards/chosen": -0.10388422012329102,
952
+ "rewards/margins": 0.0691218301653862,
953
+ "rewards/rejected": -0.1730060577392578,
954
+ "step": 63
955
+ },
956
+ {
957
+ "epoch": 0.839344262295082,
958
+ "grad_norm": 121.93528747558594,
959
+ "learning_rate": 3.382352941176471e-06,
960
+ "logits/chosen": -0.3543356955051422,
961
+ "logits/rejected": -0.23809625208377838,
962
+ "logps/chosen": -189.68069458007812,
963
+ "logps/rejected": -349.9007263183594,
964
+ "loss": 0.8636,
965
+ "rewards/accuracies": 0.25,
966
+ "rewards/chosen": -0.3187013864517212,
967
+ "rewards/margins": -0.2557255029678345,
968
+ "rewards/rejected": -0.06297589093446732,
969
+ "step": 64
970
+ },
971
+ {
972
+ "epoch": 0.8524590163934426,
973
+ "grad_norm": 35.53516387939453,
974
+ "learning_rate": 3.3455882352941178e-06,
975
+ "logits/chosen": -0.9258323311805725,
976
+ "logits/rejected": -0.8565582036972046,
977
+ "logps/chosen": -272.64453125,
978
+ "logps/rejected": -173.0827178955078,
979
+ "loss": 0.5008,
980
+ "rewards/accuracies": 0.5,
981
+ "rewards/chosen": 0.3930124044418335,
982
+ "rewards/margins": 0.5905007123947144,
983
+ "rewards/rejected": -0.19748830795288086,
984
+ "step": 65
985
+ },
986
+ {
987
+ "epoch": 0.8655737704918033,
988
+ "grad_norm": 162.02955627441406,
989
+ "learning_rate": 3.308823529411765e-06,
990
+ "logits/chosen": -0.7951459288597107,
991
+ "logits/rejected": -0.9009961485862732,
992
+ "logps/chosen": -322.9057312011719,
993
+ "logps/rejected": -461.6522216796875,
994
+ "loss": 0.9941,
995
+ "rewards/accuracies": 0.25,
996
+ "rewards/chosen": -0.22350434958934784,
997
+ "rewards/margins": -0.43997135758399963,
998
+ "rewards/rejected": 0.2164669930934906,
999
+ "step": 66
1000
+ },
1001
+ {
1002
+ "epoch": 0.8786885245901639,
1003
+ "grad_norm": 49.46587371826172,
1004
+ "learning_rate": 3.272058823529412e-06,
1005
+ "logits/chosen": -0.8077062368392944,
1006
+ "logits/rejected": -0.7711391448974609,
1007
+ "logps/chosen": -334.55621337890625,
1008
+ "logps/rejected": -304.2231750488281,
1009
+ "loss": 0.4265,
1010
+ "rewards/accuracies": 1.0,
1011
+ "rewards/chosen": 0.5165804028511047,
1012
+ "rewards/margins": 0.7691186666488647,
1013
+ "rewards/rejected": -0.2525383234024048,
1014
+ "step": 67
1015
+ },
1016
+ {
1017
+ "epoch": 0.8918032786885246,
1018
+ "grad_norm": 113.88951110839844,
1019
+ "learning_rate": 3.2352941176470594e-06,
1020
+ "logits/chosen": -0.48406150937080383,
1021
+ "logits/rejected": -0.550665020942688,
1022
+ "logps/chosen": -252.42161560058594,
1023
+ "logps/rejected": -426.91375732421875,
1024
+ "loss": 0.7502,
1025
+ "rewards/accuracies": 0.5,
1026
+ "rewards/chosen": -0.13350410759449005,
1027
+ "rewards/margins": -0.05722009390592575,
1028
+ "rewards/rejected": -0.07628403604030609,
1029
+ "step": 68
1030
+ },
1031
+ {
1032
+ "epoch": 0.9049180327868852,
1033
+ "grad_norm": 82.540771484375,
1034
+ "learning_rate": 3.198529411764706e-06,
1035
+ "logits/chosen": -0.6168251633644104,
1036
+ "logits/rejected": -0.5766561031341553,
1037
+ "logps/chosen": -355.02587890625,
1038
+ "logps/rejected": -185.5700225830078,
1039
+ "loss": 0.5665,
1040
+ "rewards/accuracies": 1.0,
1041
+ "rewards/chosen": -0.07997532188892365,
1042
+ "rewards/margins": 0.31432589888572693,
1043
+ "rewards/rejected": -0.3943012058734894,
1044
+ "step": 69
1045
+ },
1046
+ {
1047
+ "epoch": 0.9180327868852459,
1048
+ "grad_norm": 80.47476196289062,
1049
+ "learning_rate": 3.161764705882353e-06,
1050
+ "logits/chosen": -0.44328969717025757,
1051
+ "logits/rejected": -0.23468244075775146,
1052
+ "logps/chosen": -298.8565673828125,
1053
+ "logps/rejected": -271.02874755859375,
1054
+ "loss": 0.5233,
1055
+ "rewards/accuracies": 1.0,
1056
+ "rewards/chosen": 0.3650921881198883,
1057
+ "rewards/margins": 0.4301413893699646,
1058
+ "rewards/rejected": -0.0650491714477539,
1059
+ "step": 70
1060
+ },
1061
+ {
1062
+ "epoch": 0.9311475409836065,
1063
+ "grad_norm": 183.71018981933594,
1064
+ "learning_rate": 3.125e-06,
1065
+ "logits/chosen": -0.7024189233779907,
1066
+ "logits/rejected": -0.3720092177391052,
1067
+ "logps/chosen": -663.25341796875,
1068
+ "logps/rejected": -509.05072021484375,
1069
+ "loss": 0.6182,
1070
+ "rewards/accuracies": 0.5,
1071
+ "rewards/chosen": 0.02078094333410263,
1072
+ "rewards/margins": 0.3649251461029053,
1073
+ "rewards/rejected": -0.3441442549228668,
1074
+ "step": 71
1075
+ },
1076
+ {
1077
+ "epoch": 0.9442622950819672,
1078
+ "grad_norm": 73.77120971679688,
1079
+ "learning_rate": 3.0882352941176476e-06,
1080
+ "logits/chosen": -0.7303851842880249,
1081
+ "logits/rejected": -0.5275728702545166,
1082
+ "logps/chosen": -273.287353515625,
1083
+ "logps/rejected": -248.97366333007812,
1084
+ "loss": 0.5902,
1085
+ "rewards/accuracies": 1.0,
1086
+ "rewards/chosen": 0.15096759796142578,
1087
+ "rewards/margins": 0.22571565210819244,
1088
+ "rewards/rejected": -0.07474804669618607,
1089
+ "step": 72
1090
+ },
1091
+ {
1092
+ "epoch": 0.9573770491803278,
1093
+ "grad_norm": 119.30152893066406,
1094
+ "learning_rate": 3.0514705882352947e-06,
1095
+ "logits/chosen": -0.7145899534225464,
1096
+ "logits/rejected": -0.6755335330963135,
1097
+ "logps/chosen": -358.4460144042969,
1098
+ "logps/rejected": -413.93402099609375,
1099
+ "loss": 0.715,
1100
+ "rewards/accuracies": 0.75,
1101
+ "rewards/chosen": -0.5442755818367004,
1102
+ "rewards/margins": -0.015435710549354553,
1103
+ "rewards/rejected": -0.5288398861885071,
1104
+ "step": 73
1105
+ },
1106
+ {
1107
+ "epoch": 0.9704918032786886,
1108
+ "grad_norm": Infinity,
1109
+ "learning_rate": 3.0514705882352947e-06,
1110
+ "logits/chosen": -0.37683844566345215,
1111
+ "logits/rejected": -0.19479577243328094,
1112
+ "logps/chosen": -191.80364990234375,
1113
+ "logps/rejected": -239.4271240234375,
1114
+ "loss": 0.6901,
1115
+ "rewards/accuracies": 0.5,
1116
+ "rewards/chosen": -0.12151336669921875,
1117
+ "rewards/margins": 0.011674299836158752,
1118
+ "rewards/rejected": -0.1331876814365387,
1119
+ "step": 74
1120
+ },
1121
+ {
1122
+ "epoch": 0.9836065573770492,
1123
+ "grad_norm": 37.73300552368164,
1124
+ "learning_rate": 3.0147058823529413e-06,
1125
+ "logits/chosen": -0.7108013033866882,
1126
+ "logits/rejected": -0.8427099585533142,
1127
+ "logps/chosen": -237.83132934570312,
1128
+ "logps/rejected": -235.86509704589844,
1129
+ "loss": 0.5368,
1130
+ "rewards/accuracies": 0.5,
1131
+ "rewards/chosen": 0.3780634105205536,
1132
+ "rewards/margins": 0.5749028921127319,
1133
+ "rewards/rejected": -0.19683943688869476,
1134
+ "step": 75
1135
+ },
1136
+ {
1137
+ "epoch": 0.9967213114754099,
1138
+ "grad_norm": 50.56627655029297,
1139
+ "learning_rate": 2.9779411764705884e-06,
1140
+ "logits/chosen": -0.3920336663722992,
1141
+ "logits/rejected": -0.5925789475440979,
1142
+ "logps/chosen": -352.024658203125,
1143
+ "logps/rejected": -319.0198669433594,
1144
+ "loss": 0.3911,
1145
+ "rewards/accuracies": 0.75,
1146
+ "rewards/chosen": 0.4176803529262543,
1147
+ "rewards/margins": 0.8605508804321289,
1148
+ "rewards/rejected": -0.44287049770355225,
1149
+ "step": 76
1150
+ },
1151
+ {
1152
+ "epoch": 1.0098360655737706,
1153
+ "grad_norm": 31.756732940673828,
1154
+ "learning_rate": 2.9411764705882355e-06,
1155
+ "logits/chosen": -0.9694571495056152,
1156
+ "logits/rejected": -0.7683681845664978,
1157
+ "logps/chosen": -397.28277587890625,
1158
+ "logps/rejected": -506.4493103027344,
1159
+ "loss": 0.2859,
1160
+ "rewards/accuracies": 1.0,
1161
+ "rewards/chosen": 3.0198912620544434,
1162
+ "rewards/margins": 6.584094524383545,
1163
+ "rewards/rejected": -3.5642035007476807,
1164
+ "step": 77
1165
+ },
1166
+ {
1167
+ "epoch": 1.022950819672131,
1168
+ "grad_norm": 15.996756553649902,
1169
+ "learning_rate": 2.904411764705883e-06,
1170
+ "logits/chosen": -0.4139990210533142,
1171
+ "logits/rejected": -0.5289357900619507,
1172
+ "logps/chosen": -157.25994873046875,
1173
+ "logps/rejected": -292.02252197265625,
1174
+ "loss": 0.0868,
1175
+ "rewards/accuracies": 1.0,
1176
+ "rewards/chosen": 0.7793710827827454,
1177
+ "rewards/margins": 3.51633358001709,
1178
+ "rewards/rejected": -2.73696231842041,
1179
+ "step": 78
1180
+ },
1181
+ {
1182
+ "epoch": 1.0360655737704918,
1183
+ "grad_norm": 4.163623809814453,
1184
+ "learning_rate": 2.8676470588235296e-06,
1185
+ "logits/chosen": -0.8043258190155029,
1186
+ "logits/rejected": -0.7802602052688599,
1187
+ "logps/chosen": -419.2426452636719,
1188
+ "logps/rejected": -306.1612548828125,
1189
+ "loss": 0.0156,
1190
+ "rewards/accuracies": 1.0,
1191
+ "rewards/chosen": 2.816192626953125,
1192
+ "rewards/margins": 5.203756332397461,
1193
+ "rewards/rejected": -2.3875632286071777,
1194
+ "step": 79
1195
+ },
1196
+ {
1197
+ "epoch": 1.0491803278688525,
1198
+ "grad_norm": 13.230965614318848,
1199
+ "learning_rate": 2.8308823529411766e-06,
1200
+ "logits/chosen": -0.6542176008224487,
1201
+ "logits/rejected": -0.3940190374851227,
1202
+ "logps/chosen": -421.56170654296875,
1203
+ "logps/rejected": -406.03619384765625,
1204
+ "loss": 0.1049,
1205
+ "rewards/accuracies": 1.0,
1206
+ "rewards/chosen": 3.0519039630889893,
1207
+ "rewards/margins": 5.3741607666015625,
1208
+ "rewards/rejected": -2.322256565093994,
1209
+ "step": 80
1210
+ },
1211
+ {
1212
+ "epoch": 1.0622950819672132,
1213
+ "grad_norm": 31.09598731994629,
1214
+ "learning_rate": 2.7941176470588237e-06,
1215
+ "logits/chosen": -0.7882400751113892,
1216
+ "logits/rejected": -0.755602240562439,
1217
+ "logps/chosen": -143.84951782226562,
1218
+ "logps/rejected": -207.64418029785156,
1219
+ "loss": 0.3054,
1220
+ "rewards/accuracies": 1.0,
1221
+ "rewards/chosen": 0.5518492460250854,
1222
+ "rewards/margins": 1.3898382186889648,
1223
+ "rewards/rejected": -0.8379888534545898,
1224
+ "step": 81
1225
+ },
1226
+ {
1227
+ "epoch": 1.0754098360655737,
1228
+ "grad_norm": 7.787254810333252,
1229
+ "learning_rate": 2.757352941176471e-06,
1230
+ "logits/chosen": -0.347468763589859,
1231
+ "logits/rejected": -0.34622734785079956,
1232
+ "logps/chosen": -263.9562072753906,
1233
+ "logps/rejected": -390.29901123046875,
1234
+ "loss": 0.0387,
1235
+ "rewards/accuracies": 1.0,
1236
+ "rewards/chosen": 2.743457555770874,
1237
+ "rewards/margins": 6.276088714599609,
1238
+ "rewards/rejected": -3.5326313972473145,
1239
+ "step": 82
1240
+ },
1241
+ {
1242
+ "epoch": 1.0885245901639344,
1243
+ "grad_norm": 12.739912986755371,
1244
+ "learning_rate": 2.720588235294118e-06,
1245
+ "logits/chosen": -0.5520642399787903,
1246
+ "logits/rejected": -0.632639467716217,
1247
+ "logps/chosen": -542.7330322265625,
1248
+ "logps/rejected": -477.4020080566406,
1249
+ "loss": 0.0857,
1250
+ "rewards/accuracies": 1.0,
1251
+ "rewards/chosen": 3.9007229804992676,
1252
+ "rewards/margins": 8.109764099121094,
1253
+ "rewards/rejected": -4.209041595458984,
1254
+ "step": 83
1255
+ },
1256
+ {
1257
+ "epoch": 1.1016393442622952,
1258
+ "grad_norm": 39.59391784667969,
1259
+ "learning_rate": 2.683823529411765e-06,
1260
+ "logits/chosen": -0.5291910767555237,
1261
+ "logits/rejected": -0.47945737838745117,
1262
+ "logps/chosen": -385.80242919921875,
1263
+ "logps/rejected": -362.5047912597656,
1264
+ "loss": 0.1411,
1265
+ "rewards/accuracies": 1.0,
1266
+ "rewards/chosen": 1.6711763143539429,
1267
+ "rewards/margins": 3.675436496734619,
1268
+ "rewards/rejected": -2.004260301589966,
1269
+ "step": 84
1270
+ },
1271
+ {
1272
+ "epoch": 1.1147540983606556,
1273
+ "grad_norm": 34.75082015991211,
1274
+ "learning_rate": 2.647058823529412e-06,
1275
+ "logits/chosen": -0.8582125902175903,
1276
+ "logits/rejected": -0.961124837398529,
1277
+ "logps/chosen": -127.2431640625,
1278
+ "logps/rejected": -181.58657836914062,
1279
+ "loss": 0.3015,
1280
+ "rewards/accuracies": 1.0,
1281
+ "rewards/chosen": 1.1156275272369385,
1282
+ "rewards/margins": 2.283085346221924,
1283
+ "rewards/rejected": -1.1674578189849854,
1284
+ "step": 85
1285
+ },
1286
+ {
1287
+ "epoch": 1.1278688524590164,
1288
+ "grad_norm": 18.05373191833496,
1289
+ "learning_rate": 2.610294117647059e-06,
1290
+ "logits/chosen": -0.8542808890342712,
1291
+ "logits/rejected": -0.6588492393493652,
1292
+ "logps/chosen": -249.22372436523438,
1293
+ "logps/rejected": -176.06527709960938,
1294
+ "loss": 0.1498,
1295
+ "rewards/accuracies": 1.0,
1296
+ "rewards/chosen": 1.803849697113037,
1297
+ "rewards/margins": 2.9191579818725586,
1298
+ "rewards/rejected": -1.115308165550232,
1299
+ "step": 86
1300
+ },
1301
+ {
1302
+ "epoch": 1.140983606557377,
1303
+ "grad_norm": 5.507705211639404,
1304
+ "learning_rate": 2.5735294117647057e-06,
1305
+ "logits/chosen": -0.4963078498840332,
1306
+ "logits/rejected": -0.8181336522102356,
1307
+ "logps/chosen": -108.07630920410156,
1308
+ "logps/rejected": -320.96392822265625,
1309
+ "loss": 0.0256,
1310
+ "rewards/accuracies": 1.0,
1311
+ "rewards/chosen": 1.0501946210861206,
1312
+ "rewards/margins": 4.599462032318115,
1313
+ "rewards/rejected": -3.549267292022705,
1314
+ "step": 87
1315
+ },
1316
+ {
1317
+ "epoch": 1.1540983606557378,
1318
+ "grad_norm": 12.978127479553223,
1319
+ "learning_rate": 2.536764705882353e-06,
1320
+ "logits/chosen": -0.8022123575210571,
1321
+ "logits/rejected": -0.8916893005371094,
1322
+ "logps/chosen": -98.68746948242188,
1323
+ "logps/rejected": -129.98577880859375,
1324
+ "loss": 0.2735,
1325
+ "rewards/accuracies": 1.0,
1326
+ "rewards/chosen": 0.5756351947784424,
1327
+ "rewards/margins": 1.4945859909057617,
1328
+ "rewards/rejected": -0.9189507961273193,
1329
+ "step": 88
1330
+ },
1331
+ {
1332
+ "epoch": 1.1672131147540983,
1333
+ "grad_norm": 8.445465087890625,
1334
+ "learning_rate": 2.5e-06,
1335
+ "logits/chosen": -0.238316610455513,
1336
+ "logits/rejected": -0.21277102828025818,
1337
+ "logps/chosen": -355.0726318359375,
1338
+ "logps/rejected": -468.03424072265625,
1339
+ "loss": 0.0439,
1340
+ "rewards/accuracies": 1.0,
1341
+ "rewards/chosen": 3.785343885421753,
1342
+ "rewards/margins": 8.177167892456055,
1343
+ "rewards/rejected": -4.391823768615723,
1344
+ "step": 89
1345
+ },
1346
+ {
1347
+ "epoch": 1.180327868852459,
1348
+ "grad_norm": 119.01290130615234,
1349
+ "learning_rate": 2.4632352941176473e-06,
1350
+ "logits/chosen": -0.38539862632751465,
1351
+ "logits/rejected": -0.2583141326904297,
1352
+ "logps/chosen": -479.6025695800781,
1353
+ "logps/rejected": -433.03045654296875,
1354
+ "loss": 0.2972,
1355
+ "rewards/accuracies": 0.75,
1356
+ "rewards/chosen": 2.800222873687744,
1357
+ "rewards/margins": 6.087710380554199,
1358
+ "rewards/rejected": -3.287487506866455,
1359
+ "step": 90
1360
+ },
1361
+ {
1362
+ "epoch": 1.1934426229508197,
1363
+ "grad_norm": 31.620267868041992,
1364
+ "learning_rate": 2.4264705882352943e-06,
1365
+ "logits/chosen": -0.5990991592407227,
1366
+ "logits/rejected": -0.4338776469230652,
1367
+ "logps/chosen": -287.31878662109375,
1368
+ "logps/rejected": -425.55963134765625,
1369
+ "loss": 0.2764,
1370
+ "rewards/accuracies": 1.0,
1371
+ "rewards/chosen": 1.9531813859939575,
1372
+ "rewards/margins": 4.420433044433594,
1373
+ "rewards/rejected": -2.4672515392303467,
1374
+ "step": 91
1375
+ },
1376
+ {
1377
+ "epoch": 1.2065573770491804,
1378
+ "grad_norm": 5.715668201446533,
1379
+ "learning_rate": 2.3897058823529414e-06,
1380
+ "logits/chosen": -0.5918264389038086,
1381
+ "logits/rejected": -0.34481585025787354,
1382
+ "logps/chosen": -462.36181640625,
1383
+ "logps/rejected": -291.8490295410156,
1384
+ "loss": 0.0246,
1385
+ "rewards/accuracies": 1.0,
1386
+ "rewards/chosen": 4.236080169677734,
1387
+ "rewards/margins": 6.656676292419434,
1388
+ "rewards/rejected": -2.420595645904541,
1389
+ "step": 92
1390
+ },
1391
+ {
1392
+ "epoch": 1.219672131147541,
1393
+ "grad_norm": 10.8475923538208,
1394
+ "learning_rate": 2.3529411764705885e-06,
1395
+ "logits/chosen": -0.48867395520210266,
1396
+ "logits/rejected": -0.2037501335144043,
1397
+ "logps/chosen": -248.76011657714844,
1398
+ "logps/rejected": -278.86505126953125,
1399
+ "loss": 0.0703,
1400
+ "rewards/accuracies": 1.0,
1401
+ "rewards/chosen": 2.4005353450775146,
1402
+ "rewards/margins": 3.532731056213379,
1403
+ "rewards/rejected": -1.1321957111358643,
1404
+ "step": 93
1405
+ },
1406
+ {
1407
+ "epoch": 1.2327868852459016,
1408
+ "grad_norm": 17.5373477935791,
1409
+ "learning_rate": 2.3161764705882355e-06,
1410
+ "logits/chosen": -0.800743043422699,
1411
+ "logits/rejected": -0.3216054141521454,
1412
+ "logps/chosen": -332.1054382324219,
1413
+ "logps/rejected": -262.9385070800781,
1414
+ "loss": 0.0781,
1415
+ "rewards/accuracies": 1.0,
1416
+ "rewards/chosen": 3.3670170307159424,
1417
+ "rewards/margins": 5.165108680725098,
1418
+ "rewards/rejected": -1.7980915307998657,
1419
+ "step": 94
1420
+ },
1421
+ {
1422
+ "epoch": 1.2459016393442623,
1423
+ "grad_norm": 17.166118621826172,
1424
+ "learning_rate": 2.2794117647058826e-06,
1425
+ "logits/chosen": -0.5876657366752625,
1426
+ "logits/rejected": -0.30134695768356323,
1427
+ "logps/chosen": -438.53070068359375,
1428
+ "logps/rejected": -283.11053466796875,
1429
+ "loss": 0.0878,
1430
+ "rewards/accuracies": 1.0,
1431
+ "rewards/chosen": 5.845110893249512,
1432
+ "rewards/margins": 7.538168430328369,
1433
+ "rewards/rejected": -1.6930572986602783,
1434
+ "step": 95
1435
+ },
1436
+ {
1437
+ "epoch": 1.2590163934426228,
1438
+ "grad_norm": 23.068361282348633,
1439
+ "learning_rate": 2.2426470588235296e-06,
1440
+ "logits/chosen": -0.6558918356895447,
1441
+ "logits/rejected": -0.3275706171989441,
1442
+ "logps/chosen": -370.03094482421875,
1443
+ "logps/rejected": -453.90203857421875,
1444
+ "loss": 0.1287,
1445
+ "rewards/accuracies": 1.0,
1446
+ "rewards/chosen": 2.0850746631622314,
1447
+ "rewards/margins": 4.879607677459717,
1448
+ "rewards/rejected": -2.7945332527160645,
1449
+ "step": 96
1450
+ },
1451
+ {
1452
+ "epoch": 1.2721311475409836,
1453
+ "grad_norm": 5.994075298309326,
1454
+ "learning_rate": 2.2058823529411767e-06,
1455
+ "logits/chosen": -0.6101892590522766,
1456
+ "logits/rejected": -0.5373432040214539,
1457
+ "logps/chosen": -347.5174560546875,
1458
+ "logps/rejected": -322.55023193359375,
1459
+ "loss": 0.0318,
1460
+ "rewards/accuracies": 1.0,
1461
+ "rewards/chosen": 2.3236427307128906,
1462
+ "rewards/margins": 4.85604190826416,
1463
+ "rewards/rejected": -2.5323991775512695,
1464
+ "step": 97
1465
+ },
1466
+ {
1467
+ "epoch": 1.2852459016393443,
1468
+ "grad_norm": 14.375985145568848,
1469
+ "learning_rate": 2.1691176470588238e-06,
1470
+ "logits/chosen": -0.6097806692123413,
1471
+ "logits/rejected": -0.5758112072944641,
1472
+ "logps/chosen": -341.9951477050781,
1473
+ "logps/rejected": -290.09136962890625,
1474
+ "loss": 0.1422,
1475
+ "rewards/accuracies": 1.0,
1476
+ "rewards/chosen": 2.372694253921509,
1477
+ "rewards/margins": 5.112575531005859,
1478
+ "rewards/rejected": -2.7398810386657715,
1479
+ "step": 98
1480
+ },
1481
+ {
1482
+ "epoch": 1.298360655737705,
1483
+ "grad_norm": 10.561140060424805,
1484
+ "learning_rate": 2.132352941176471e-06,
1485
+ "logits/chosen": -0.7798110842704773,
1486
+ "logits/rejected": -0.5334391593933105,
1487
+ "logps/chosen": -122.71707916259766,
1488
+ "logps/rejected": -138.75685119628906,
1489
+ "loss": 0.224,
1490
+ "rewards/accuracies": 0.75,
1491
+ "rewards/chosen": 0.45279568433761597,
1492
+ "rewards/margins": 2.1160295009613037,
1493
+ "rewards/rejected": -1.6632338762283325,
1494
+ "step": 99
1495
+ },
1496
+ {
1497
+ "epoch": 1.3114754098360657,
1498
+ "grad_norm": 8.718037605285645,
1499
+ "learning_rate": 2.095588235294118e-06,
1500
+ "logits/chosen": -0.5125188827514648,
1501
+ "logits/rejected": -0.35307127237319946,
1502
+ "logps/chosen": -180.09408569335938,
1503
+ "logps/rejected": -273.54046630859375,
1504
+ "loss": 0.0465,
1505
+ "rewards/accuracies": 1.0,
1506
+ "rewards/chosen": 1.8067989349365234,
1507
+ "rewards/margins": 5.022237777709961,
1508
+ "rewards/rejected": -3.2154390811920166,
1509
+ "step": 100
1510
+ },
1511
+ {
1512
+ "epoch": 1.3245901639344262,
1513
+ "grad_norm": 11.257354736328125,
1514
+ "learning_rate": 2.058823529411765e-06,
1515
+ "logits/chosen": -0.48480626940727234,
1516
+ "logits/rejected": -0.4184003174304962,
1517
+ "logps/chosen": -349.5723876953125,
1518
+ "logps/rejected": -458.3537902832031,
1519
+ "loss": 0.0341,
1520
+ "rewards/accuracies": 1.0,
1521
+ "rewards/chosen": 2.9435834884643555,
1522
+ "rewards/margins": 6.52362060546875,
1523
+ "rewards/rejected": -3.5800368785858154,
1524
+ "step": 101
1525
+ },
1526
+ {
1527
+ "epoch": 1.337704918032787,
1528
+ "grad_norm": 8.118950843811035,
1529
+ "learning_rate": 2.022058823529412e-06,
1530
+ "logits/chosen": -0.6667636632919312,
1531
+ "logits/rejected": -0.3804593086242676,
1532
+ "logps/chosen": -331.16015625,
1533
+ "logps/rejected": -266.6229248046875,
1534
+ "loss": 0.1422,
1535
+ "rewards/accuracies": 1.0,
1536
+ "rewards/chosen": 4.118168830871582,
1537
+ "rewards/margins": 5.915567398071289,
1538
+ "rewards/rejected": -1.797398328781128,
1539
+ "step": 102
1540
+ },
1541
+ {
1542
+ "epoch": 1.3508196721311476,
1543
+ "grad_norm": 14.03177547454834,
1544
+ "learning_rate": 1.985294117647059e-06,
1545
+ "logits/chosen": -0.34312984347343445,
1546
+ "logits/rejected": -0.5378394722938538,
1547
+ "logps/chosen": -205.9506378173828,
1548
+ "logps/rejected": -219.46360778808594,
1549
+ "loss": 0.113,
1550
+ "rewards/accuracies": 1.0,
1551
+ "rewards/chosen": 2.023257255554199,
1552
+ "rewards/margins": 3.4092535972595215,
1553
+ "rewards/rejected": -1.3859964609146118,
1554
+ "step": 103
1555
+ },
1556
+ {
1557
+ "epoch": 1.3639344262295081,
1558
+ "grad_norm": 2.7447023391723633,
1559
+ "learning_rate": 1.948529411764706e-06,
1560
+ "logits/chosen": -0.3522460162639618,
1561
+ "logits/rejected": -0.4929681122303009,
1562
+ "logps/chosen": -295.0723571777344,
1563
+ "logps/rejected": -344.48834228515625,
1564
+ "loss": 0.0114,
1565
+ "rewards/accuracies": 1.0,
1566
+ "rewards/chosen": 2.613781690597534,
1567
+ "rewards/margins": 6.21614408493042,
1568
+ "rewards/rejected": -3.602362871170044,
1569
+ "step": 104
1570
+ },
1571
+ {
1572
+ "epoch": 1.3770491803278688,
1573
+ "grad_norm": 3.9517393112182617,
1574
+ "learning_rate": 1.9117647058823528e-06,
1575
+ "logits/chosen": -0.5514786243438721,
1576
+ "logits/rejected": -0.515537440776825,
1577
+ "logps/chosen": -283.73504638671875,
1578
+ "logps/rejected": -354.9101257324219,
1579
+ "loss": 0.0147,
1580
+ "rewards/accuracies": 1.0,
1581
+ "rewards/chosen": 3.183412551879883,
1582
+ "rewards/margins": 6.139578819274902,
1583
+ "rewards/rejected": -2.9561657905578613,
1584
+ "step": 105
1585
+ },
1586
+ {
1587
+ "epoch": 1.3901639344262295,
1588
+ "grad_norm": 32.080848693847656,
1589
+ "learning_rate": 1.8750000000000003e-06,
1590
+ "logits/chosen": -0.34524667263031006,
1591
+ "logits/rejected": -0.2804412245750427,
1592
+ "logps/chosen": -487.1918029785156,
1593
+ "logps/rejected": -459.1595764160156,
1594
+ "loss": 0.1497,
1595
+ "rewards/accuracies": 1.0,
1596
+ "rewards/chosen": 3.4442732334136963,
1597
+ "rewards/margins": 6.211602210998535,
1598
+ "rewards/rejected": -2.767328977584839,
1599
+ "step": 106
1600
+ },
1601
+ {
1602
+ "epoch": 1.40327868852459,
1603
+ "grad_norm": 6.278583526611328,
1604
+ "learning_rate": 1.8382352941176473e-06,
1605
+ "logits/chosen": -1.0492626428604126,
1606
+ "logits/rejected": -0.637208878993988,
1607
+ "logps/chosen": -508.1822509765625,
1608
+ "logps/rejected": -264.3661804199219,
1609
+ "loss": 0.0256,
1610
+ "rewards/accuracies": 1.0,
1611
+ "rewards/chosen": 3.434685230255127,
1612
+ "rewards/margins": 5.93399715423584,
1613
+ "rewards/rejected": -2.4993114471435547,
1614
+ "step": 107
1615
+ },
1616
+ {
1617
+ "epoch": 1.4163934426229507,
1618
+ "grad_norm": 3.8192379474639893,
1619
+ "learning_rate": 1.8014705882352942e-06,
1620
+ "logits/chosen": -0.49397462606430054,
1621
+ "logits/rejected": -0.39174699783325195,
1622
+ "logps/chosen": -250.099853515625,
1623
+ "logps/rejected": -342.03033447265625,
1624
+ "loss": 0.0194,
1625
+ "rewards/accuracies": 1.0,
1626
+ "rewards/chosen": 1.3859384059906006,
1627
+ "rewards/margins": 4.495996475219727,
1628
+ "rewards/rejected": -3.110058307647705,
1629
+ "step": 108
1630
+ },
1631
+ {
1632
+ "epoch": 1.4295081967213115,
1633
+ "grad_norm": 5.807373523712158,
1634
+ "learning_rate": 1.7647058823529414e-06,
1635
+ "logits/chosen": -0.584580659866333,
1636
+ "logits/rejected": -0.15329986810684204,
1637
+ "logps/chosen": -442.9632873535156,
1638
+ "logps/rejected": -318.378173828125,
1639
+ "loss": 0.0165,
1640
+ "rewards/accuracies": 1.0,
1641
+ "rewards/chosen": 2.1344716548919678,
1642
+ "rewards/margins": 5.192463397979736,
1643
+ "rewards/rejected": -3.0579919815063477,
1644
+ "step": 109
1645
+ },
1646
+ {
1647
+ "epoch": 1.4426229508196722,
1648
+ "grad_norm": 3.5901246070861816,
1649
+ "learning_rate": 1.7279411764705883e-06,
1650
+ "logits/chosen": -0.5349779725074768,
1651
+ "logits/rejected": -0.2637510299682617,
1652
+ "logps/chosen": -414.6310729980469,
1653
+ "logps/rejected": -428.139404296875,
1654
+ "loss": 0.0136,
1655
+ "rewards/accuracies": 1.0,
1656
+ "rewards/chosen": 2.6161444187164307,
1657
+ "rewards/margins": 7.400443077087402,
1658
+ "rewards/rejected": -4.784298896789551,
1659
+ "step": 110
1660
+ },
1661
+ {
1662
+ "epoch": 1.455737704918033,
1663
+ "grad_norm": 17.46812629699707,
1664
+ "learning_rate": 1.6911764705882356e-06,
1665
+ "logits/chosen": -0.6205960512161255,
1666
+ "logits/rejected": -0.6515633463859558,
1667
+ "logps/chosen": -233.56886291503906,
1668
+ "logps/rejected": -327.51611328125,
1669
+ "loss": 0.1822,
1670
+ "rewards/accuracies": 1.0,
1671
+ "rewards/chosen": 1.1055248975753784,
1672
+ "rewards/margins": 4.226891994476318,
1673
+ "rewards/rejected": -3.1213672161102295,
1674
+ "step": 111
1675
+ },
1676
+ {
1677
+ "epoch": 1.4688524590163934,
1678
+ "grad_norm": 11.27214241027832,
1679
+ "learning_rate": 1.6544117647058824e-06,
1680
+ "logits/chosen": -0.3313244581222534,
1681
+ "logits/rejected": -0.22155167162418365,
1682
+ "logps/chosen": -391.53466796875,
1683
+ "logps/rejected": -230.6190643310547,
1684
+ "loss": 0.1142,
1685
+ "rewards/accuracies": 1.0,
1686
+ "rewards/chosen": 2.988477945327759,
1687
+ "rewards/margins": 5.188130855560303,
1688
+ "rewards/rejected": -2.199653148651123,
1689
+ "step": 112
1690
+ },
1691
+ {
1692
+ "epoch": 1.481967213114754,
1693
+ "grad_norm": 9.786858558654785,
1694
+ "learning_rate": 1.6176470588235297e-06,
1695
+ "logits/chosen": -0.5634331703186035,
1696
+ "logits/rejected": -0.4348165690898895,
1697
+ "logps/chosen": -252.67152404785156,
1698
+ "logps/rejected": -352.4822998046875,
1699
+ "loss": 0.0467,
1700
+ "rewards/accuracies": 1.0,
1701
+ "rewards/chosen": 1.8047726154327393,
1702
+ "rewards/margins": 6.142679691314697,
1703
+ "rewards/rejected": -4.337907314300537,
1704
+ "step": 113
1705
+ },
1706
+ {
1707
+ "epoch": 1.4950819672131148,
1708
+ "grad_norm": 4.376170635223389,
1709
+ "learning_rate": 1.5808823529411765e-06,
1710
+ "logits/chosen": -0.15515179932117462,
1711
+ "logits/rejected": -0.1870616376399994,
1712
+ "logps/chosen": -289.219970703125,
1713
+ "logps/rejected": -400.1667175292969,
1714
+ "loss": 0.0207,
1715
+ "rewards/accuracies": 1.0,
1716
+ "rewards/chosen": 2.1680092811584473,
1717
+ "rewards/margins": 4.854602336883545,
1718
+ "rewards/rejected": -2.6865930557250977,
1719
+ "step": 114
1720
+ },
1721
+ {
1722
+ "epoch": 1.5081967213114753,
1723
+ "grad_norm": 3.8763139247894287,
1724
+ "learning_rate": 1.5441176470588238e-06,
1725
+ "logits/chosen": -0.2717803716659546,
1726
+ "logits/rejected": -0.17628008127212524,
1727
+ "logps/chosen": -546.1766357421875,
1728
+ "logps/rejected": -451.3502502441406,
1729
+ "loss": 0.0166,
1730
+ "rewards/accuracies": 1.0,
1731
+ "rewards/chosen": 2.681325912475586,
1732
+ "rewards/margins": 5.725113868713379,
1733
+ "rewards/rejected": -3.0437874794006348,
1734
+ "step": 115
1735
+ },
1736
+ {
1737
+ "epoch": 1.521311475409836,
1738
+ "grad_norm": 30.37358283996582,
1739
+ "learning_rate": 1.5073529411764707e-06,
1740
+ "logits/chosen": -0.9199023246765137,
1741
+ "logits/rejected": -0.8192650079727173,
1742
+ "logps/chosen": -247.5410919189453,
1743
+ "logps/rejected": -390.4881896972656,
1744
+ "loss": 0.1679,
1745
+ "rewards/accuracies": 1.0,
1746
+ "rewards/chosen": 1.817814588546753,
1747
+ "rewards/margins": 4.526091575622559,
1748
+ "rewards/rejected": -2.7082767486572266,
1749
+ "step": 116
1750
+ },
1751
+ {
1752
+ "epoch": 1.5344262295081967,
1753
+ "grad_norm": 17.32929229736328,
1754
+ "learning_rate": 1.4705882352941177e-06,
1755
+ "logits/chosen": -0.4218984842300415,
1756
+ "logits/rejected": -0.411405086517334,
1757
+ "logps/chosen": -202.14004516601562,
1758
+ "logps/rejected": -220.29254150390625,
1759
+ "loss": 0.1733,
1760
+ "rewards/accuracies": 1.0,
1761
+ "rewards/chosen": 1.8182326555252075,
1762
+ "rewards/margins": 3.9761695861816406,
1763
+ "rewards/rejected": -2.1579370498657227,
1764
+ "step": 117
1765
+ },
1766
+ {
1767
+ "epoch": 1.5475409836065572,
1768
+ "grad_norm": 15.47387981414795,
1769
+ "learning_rate": 1.4338235294117648e-06,
1770
+ "logits/chosen": -0.6655436754226685,
1771
+ "logits/rejected": -0.9528688192367554,
1772
+ "logps/chosen": -110.75199890136719,
1773
+ "logps/rejected": -216.50701904296875,
1774
+ "loss": 0.0995,
1775
+ "rewards/accuracies": 1.0,
1776
+ "rewards/chosen": 0.448855996131897,
1777
+ "rewards/margins": 2.9766037464141846,
1778
+ "rewards/rejected": -2.5277481079101562,
1779
+ "step": 118
1780
+ },
1781
+ {
1782
+ "epoch": 1.5606557377049182,
1783
+ "grad_norm": 56.997802734375,
1784
+ "learning_rate": 1.3970588235294119e-06,
1785
+ "logits/chosen": -0.3543809652328491,
1786
+ "logits/rejected": -0.5634450912475586,
1787
+ "logps/chosen": -307.3863525390625,
1788
+ "logps/rejected": -422.4675598144531,
1789
+ "loss": 0.19,
1790
+ "rewards/accuracies": 0.75,
1791
+ "rewards/chosen": 1.821000337600708,
1792
+ "rewards/margins": 5.365086555480957,
1793
+ "rewards/rejected": -3.5440866947174072,
1794
+ "step": 119
1795
+ },
1796
+ {
1797
+ "epoch": 1.5737704918032787,
1798
+ "grad_norm": 5.717536926269531,
1799
+ "learning_rate": 1.360294117647059e-06,
1800
+ "logits/chosen": -0.394744873046875,
1801
+ "logits/rejected": -0.46669620275497437,
1802
+ "logps/chosen": -162.78341674804688,
1803
+ "logps/rejected": -354.51654052734375,
1804
+ "loss": 0.0251,
1805
+ "rewards/accuracies": 1.0,
1806
+ "rewards/chosen": 1.3121498823165894,
1807
+ "rewards/margins": 5.8546037673950195,
1808
+ "rewards/rejected": -4.542453765869141,
1809
+ "step": 120
1810
+ },
1811
+ {
1812
+ "epoch": 1.5868852459016394,
1813
+ "grad_norm": 102.92301177978516,
1814
+ "learning_rate": 1.323529411764706e-06,
1815
+ "logits/chosen": -0.8797488212585449,
1816
+ "logits/rejected": -0.5256719589233398,
1817
+ "logps/chosen": -400.2969055175781,
1818
+ "logps/rejected": -228.6015625,
1819
+ "loss": 0.3735,
1820
+ "rewards/accuracies": 0.75,
1821
+ "rewards/chosen": 1.3958312273025513,
1822
+ "rewards/margins": 2.500825881958008,
1823
+ "rewards/rejected": -1.1049946546554565,
1824
+ "step": 121
1825
+ },
1826
+ {
1827
+ "epoch": 1.6,
1828
+ "grad_norm": 12.96183967590332,
1829
+ "learning_rate": 1.2867647058823528e-06,
1830
+ "logits/chosen": -0.1941753625869751,
1831
+ "logits/rejected": -0.2740371525287628,
1832
+ "logps/chosen": -146.65438842773438,
1833
+ "logps/rejected": -286.4040832519531,
1834
+ "loss": 0.0833,
1835
+ "rewards/accuracies": 1.0,
1836
+ "rewards/chosen": 1.6577894687652588,
1837
+ "rewards/margins": 5.093594074249268,
1838
+ "rewards/rejected": -3.4358043670654297,
1839
+ "step": 122
1840
+ },
1841
+ {
1842
+ "epoch": 1.6131147540983606,
1843
+ "grad_norm": 1.308056354522705,
1844
+ "learning_rate": 1.25e-06,
1845
+ "logits/chosen": -0.2991219460964203,
1846
+ "logits/rejected": -0.608604371547699,
1847
+ "logps/chosen": -332.8055419921875,
1848
+ "logps/rejected": -501.82794189453125,
1849
+ "loss": 0.0056,
1850
+ "rewards/accuracies": 1.0,
1851
+ "rewards/chosen": 1.9228206872940063,
1852
+ "rewards/margins": 6.52579927444458,
1853
+ "rewards/rejected": -4.602978706359863,
1854
+ "step": 123
1855
+ },
1856
+ {
1857
+ "epoch": 1.6262295081967213,
1858
+ "grad_norm": 6.536846160888672,
1859
+ "learning_rate": 1.2132352941176472e-06,
1860
+ "logits/chosen": -0.5168918371200562,
1861
+ "logits/rejected": -0.8077197670936584,
1862
+ "logps/chosen": -200.44891357421875,
1863
+ "logps/rejected": -283.05535888671875,
1864
+ "loss": 0.0305,
1865
+ "rewards/accuracies": 1.0,
1866
+ "rewards/chosen": 1.2009633779525757,
1867
+ "rewards/margins": 4.113708019256592,
1868
+ "rewards/rejected": -2.9127449989318848,
1869
+ "step": 124
1870
+ },
1871
+ {
1872
+ "epoch": 1.639344262295082,
1873
+ "grad_norm": 14.031917572021484,
1874
+ "learning_rate": 1.1764705882352942e-06,
1875
+ "logits/chosen": -0.2985928952693939,
1876
+ "logits/rejected": -0.5871812701225281,
1877
+ "logps/chosen": -203.19163513183594,
1878
+ "logps/rejected": -404.0279846191406,
1879
+ "loss": 0.1122,
1880
+ "rewards/accuracies": 1.0,
1881
+ "rewards/chosen": 1.369646668434143,
1882
+ "rewards/margins": 5.168557643890381,
1883
+ "rewards/rejected": -3.7989113330841064,
1884
+ "step": 125
1885
+ },
1886
+ {
1887
+ "epoch": 1.6524590163934425,
1888
+ "grad_norm": 1.0998114347457886,
1889
+ "learning_rate": 1.1397058823529413e-06,
1890
+ "logits/chosen": -0.9684606790542603,
1891
+ "logits/rejected": -0.8049026727676392,
1892
+ "logps/chosen": -247.9980010986328,
1893
+ "logps/rejected": -212.36807250976562,
1894
+ "loss": 0.178,
1895
+ "rewards/accuracies": 0.75,
1896
+ "rewards/chosen": 2.4171135425567627,
1897
+ "rewards/margins": 5.950634002685547,
1898
+ "rewards/rejected": -3.533520460128784,
1899
+ "step": 126
1900
+ },
1901
+ {
1902
+ "epoch": 1.6655737704918034,
1903
+ "grad_norm": 1.8453718423843384,
1904
+ "learning_rate": 1.1029411764705884e-06,
1905
+ "logits/chosen": -0.4717595875263214,
1906
+ "logits/rejected": -0.13389728963375092,
1907
+ "logps/chosen": -400.8570251464844,
1908
+ "logps/rejected": -322.6037902832031,
1909
+ "loss": 0.0069,
1910
+ "rewards/accuracies": 1.0,
1911
+ "rewards/chosen": 3.168325901031494,
1912
+ "rewards/margins": 6.738244533538818,
1913
+ "rewards/rejected": -3.569918155670166,
1914
+ "step": 127
1915
+ },
1916
+ {
1917
+ "epoch": 1.678688524590164,
1918
+ "grad_norm": 9.327398300170898,
1919
+ "learning_rate": 1.0661764705882354e-06,
1920
+ "logits/chosen": -0.45057347416877747,
1921
+ "logits/rejected": -0.22152967751026154,
1922
+ "logps/chosen": -261.6713562011719,
1923
+ "logps/rejected": -318.07391357421875,
1924
+ "loss": 0.0558,
1925
+ "rewards/accuracies": 1.0,
1926
+ "rewards/chosen": 2.15228271484375,
1927
+ "rewards/margins": 5.979676723480225,
1928
+ "rewards/rejected": -3.8273940086364746,
1929
+ "step": 128
1930
+ },
1931
+ {
1932
+ "epoch": 1.6918032786885244,
1933
+ "grad_norm": 21.2039737701416,
1934
+ "learning_rate": 1.0294117647058825e-06,
1935
+ "logits/chosen": -0.5791776180267334,
1936
+ "logits/rejected": -0.8412386178970337,
1937
+ "logps/chosen": -132.2311553955078,
1938
+ "logps/rejected": -418.17657470703125,
1939
+ "loss": 0.1523,
1940
+ "rewards/accuracies": 1.0,
1941
+ "rewards/chosen": 0.6422145962715149,
1942
+ "rewards/margins": 6.080798625946045,
1943
+ "rewards/rejected": -5.438583850860596,
1944
+ "step": 129
1945
+ },
1946
+ {
1947
+ "epoch": 1.7049180327868854,
1948
+ "grad_norm": 0.3313053250312805,
1949
+ "learning_rate": 9.926470588235295e-07,
1950
+ "logits/chosen": -0.7310227155685425,
1951
+ "logits/rejected": -0.6085512638092041,
1952
+ "logps/chosen": -517.57373046875,
1953
+ "logps/rejected": -645.620849609375,
1954
+ "loss": 0.001,
1955
+ "rewards/accuracies": 1.0,
1956
+ "rewards/chosen": 3.5617308616638184,
1957
+ "rewards/margins": 8.085519790649414,
1958
+ "rewards/rejected": -4.5237884521484375,
1959
+ "step": 130
1960
+ },
1961
+ {
1962
+ "epoch": 1.7180327868852459,
1963
+ "grad_norm": 71.060546875,
1964
+ "learning_rate": 9.558823529411764e-07,
1965
+ "logits/chosen": -0.6338833570480347,
1966
+ "logits/rejected": -0.897128701210022,
1967
+ "logps/chosen": -193.55189514160156,
1968
+ "logps/rejected": -340.1580810546875,
1969
+ "loss": 0.3464,
1970
+ "rewards/accuracies": 0.75,
1971
+ "rewards/chosen": 0.23160991072654724,
1972
+ "rewards/margins": 1.533915400505066,
1973
+ "rewards/rejected": -1.3023054599761963,
1974
+ "step": 131
1975
+ },
1976
+ {
1977
+ "epoch": 1.7311475409836066,
1978
+ "grad_norm": 11.899687767028809,
1979
+ "learning_rate": 9.191176470588237e-07,
1980
+ "logits/chosen": -0.8149244785308838,
1981
+ "logits/rejected": -0.5785297155380249,
1982
+ "logps/chosen": -213.12173461914062,
1983
+ "logps/rejected": -237.8140411376953,
1984
+ "loss": 0.0893,
1985
+ "rewards/accuracies": 1.0,
1986
+ "rewards/chosen": 1.6387001276016235,
1987
+ "rewards/margins": 3.045469284057617,
1988
+ "rewards/rejected": -1.4067691564559937,
1989
+ "step": 132
1990
+ },
1991
+ {
1992
+ "epoch": 1.7442622950819673,
1993
+ "grad_norm": 1.8859055042266846,
1994
+ "learning_rate": 8.823529411764707e-07,
1995
+ "logits/chosen": -0.40556299686431885,
1996
+ "logits/rejected": -0.577975332736969,
1997
+ "logps/chosen": -514.1160888671875,
1998
+ "logps/rejected": -692.885009765625,
1999
+ "loss": 0.0032,
2000
+ "rewards/accuracies": 1.0,
2001
+ "rewards/chosen": 2.4865522384643555,
2002
+ "rewards/margins": 9.726764678955078,
2003
+ "rewards/rejected": -7.240212440490723,
2004
+ "step": 133
2005
+ },
2006
+ {
2007
+ "epoch": 1.7573770491803278,
2008
+ "grad_norm": 15.04454517364502,
2009
+ "learning_rate": 8.455882352941178e-07,
2010
+ "logits/chosen": -0.7795289754867554,
2011
+ "logits/rejected": -0.8595843315124512,
2012
+ "logps/chosen": -117.66368103027344,
2013
+ "logps/rejected": -155.0380859375,
2014
+ "loss": 0.1567,
2015
+ "rewards/accuracies": 1.0,
2016
+ "rewards/chosen": 1.0589184761047363,
2017
+ "rewards/margins": 2.530170440673828,
2018
+ "rewards/rejected": -1.4712518453598022,
2019
+ "step": 134
2020
+ },
2021
+ {
2022
+ "epoch": 1.7704918032786885,
2023
+ "grad_norm": 79.06763458251953,
2024
+ "learning_rate": 8.088235294117648e-07,
2025
+ "logits/chosen": -0.7521681189537048,
2026
+ "logits/rejected": -0.5849143862724304,
2027
+ "logps/chosen": -370.17303466796875,
2028
+ "logps/rejected": -297.7393493652344,
2029
+ "loss": 0.3304,
2030
+ "rewards/accuracies": 0.75,
2031
+ "rewards/chosen": 1.5731346607208252,
2032
+ "rewards/margins": 4.559065341949463,
2033
+ "rewards/rejected": -2.9859304428100586,
2034
+ "step": 135
2035
+ },
2036
+ {
2037
+ "epoch": 1.7836065573770492,
2038
+ "grad_norm": 75.73023223876953,
2039
+ "learning_rate": 7.720588235294119e-07,
2040
+ "logits/chosen": -0.24577771127223969,
2041
+ "logits/rejected": -0.2834129333496094,
2042
+ "logps/chosen": -169.0641632080078,
2043
+ "logps/rejected": -227.2678985595703,
2044
+ "loss": 0.1953,
2045
+ "rewards/accuracies": 1.0,
2046
+ "rewards/chosen": 0.9874727725982666,
2047
+ "rewards/margins": 2.466601848602295,
2048
+ "rewards/rejected": -1.4791290760040283,
2049
+ "step": 136
2050
+ },
2051
+ {
2052
+ "epoch": 1.7967213114754097,
2053
+ "grad_norm": 13.235738754272461,
2054
+ "learning_rate": 7.352941176470589e-07,
2055
+ "logits/chosen": -0.8364167213439941,
2056
+ "logits/rejected": -0.7191005349159241,
2057
+ "logps/chosen": -281.6129150390625,
2058
+ "logps/rejected": -327.17169189453125,
2059
+ "loss": 0.0731,
2060
+ "rewards/accuracies": 1.0,
2061
+ "rewards/chosen": 2.5926880836486816,
2062
+ "rewards/margins": 5.672669410705566,
2063
+ "rewards/rejected": -3.0799813270568848,
2064
+ "step": 137
2065
+ },
2066
+ {
2067
+ "epoch": 1.8098360655737706,
2068
+ "grad_norm": 5.092410087585449,
2069
+ "learning_rate": 6.985294117647059e-07,
2070
+ "logits/chosen": -0.6490945219993591,
2071
+ "logits/rejected": -0.9161443710327148,
2072
+ "logps/chosen": -366.2134704589844,
2073
+ "logps/rejected": -429.5161437988281,
2074
+ "loss": 0.0178,
2075
+ "rewards/accuracies": 1.0,
2076
+ "rewards/chosen": 1.8624721765518188,
2077
+ "rewards/margins": 6.365274906158447,
2078
+ "rewards/rejected": -4.50280237197876,
2079
+ "step": 138
2080
+ },
2081
+ {
2082
+ "epoch": 1.8229508196721311,
2083
+ "grad_norm": 3.215587615966797,
2084
+ "learning_rate": 6.61764705882353e-07,
2085
+ "logits/chosen": -0.7531751990318298,
2086
+ "logits/rejected": -0.30548983812332153,
2087
+ "logps/chosen": -386.60504150390625,
2088
+ "logps/rejected": -275.23779296875,
2089
+ "loss": 0.0127,
2090
+ "rewards/accuracies": 1.0,
2091
+ "rewards/chosen": 3.7106332778930664,
2092
+ "rewards/margins": 6.189945220947266,
2093
+ "rewards/rejected": -2.4793121814727783,
2094
+ "step": 139
2095
+ },
2096
+ {
2097
+ "epoch": 1.8360655737704918,
2098
+ "grad_norm": 0.22684346139431,
2099
+ "learning_rate": 6.25e-07,
2100
+ "logits/chosen": -0.38512834906578064,
2101
+ "logits/rejected": -0.39937111735343933,
2102
+ "logps/chosen": -506.0502624511719,
2103
+ "logps/rejected": -478.14990234375,
2104
+ "loss": 0.0006,
2105
+ "rewards/accuracies": 1.0,
2106
+ "rewards/chosen": 4.004444599151611,
2107
+ "rewards/margins": 9.403310775756836,
2108
+ "rewards/rejected": -5.398866653442383,
2109
+ "step": 140
2110
+ },
2111
+ {
2112
+ "epoch": 1.8491803278688526,
2113
+ "grad_norm": 8.121055603027344,
2114
+ "learning_rate": 5.882352941176471e-07,
2115
+ "logits/chosen": -0.5020557045936584,
2116
+ "logits/rejected": -0.6416282653808594,
2117
+ "logps/chosen": -369.1741027832031,
2118
+ "logps/rejected": -440.558837890625,
2119
+ "loss": 0.0314,
2120
+ "rewards/accuracies": 1.0,
2121
+ "rewards/chosen": 3.697706699371338,
2122
+ "rewards/margins": 7.363080024719238,
2123
+ "rewards/rejected": -3.6653730869293213,
2124
+ "step": 141
2125
+ },
2126
+ {
2127
+ "epoch": 1.862295081967213,
2128
+ "grad_norm": 25.55944061279297,
2129
+ "learning_rate": 5.514705882352942e-07,
2130
+ "logits/chosen": -0.6144732236862183,
2131
+ "logits/rejected": -0.5314571857452393,
2132
+ "logps/chosen": -412.43310546875,
2133
+ "logps/rejected": -425.11572265625,
2134
+ "loss": 0.0594,
2135
+ "rewards/accuracies": 1.0,
2136
+ "rewards/chosen": 2.2833995819091797,
2137
+ "rewards/margins": 5.651876926422119,
2138
+ "rewards/rejected": -3.3684768676757812,
2139
+ "step": 142
2140
+ },
2141
+ {
2142
+ "epoch": 1.8754098360655738,
2143
+ "grad_norm": 2.3017585277557373,
2144
+ "learning_rate": 5.147058823529412e-07,
2145
+ "logits/chosen": -0.7556811571121216,
2146
+ "logits/rejected": -0.8270020484924316,
2147
+ "logps/chosen": -401.3725280761719,
2148
+ "logps/rejected": -348.38067626953125,
2149
+ "loss": 0.181,
2150
+ "rewards/accuracies": 0.75,
2151
+ "rewards/chosen": 2.7437126636505127,
2152
+ "rewards/margins": 7.136537551879883,
2153
+ "rewards/rejected": -4.392825126647949,
2154
+ "step": 143
2155
+ },
2156
+ {
2157
+ "epoch": 1.8885245901639345,
2158
+ "grad_norm": 1.4070271253585815,
2159
+ "learning_rate": 4.779411764705882e-07,
2160
+ "logits/chosen": -0.24664568901062012,
2161
+ "logits/rejected": -0.640694797039032,
2162
+ "logps/chosen": -327.0250549316406,
2163
+ "logps/rejected": -863.6223754882812,
2164
+ "loss": 0.0034,
2165
+ "rewards/accuracies": 1.0,
2166
+ "rewards/chosen": 1.61453115940094,
2167
+ "rewards/margins": 6.990232467651367,
2168
+ "rewards/rejected": -5.375700950622559,
2169
+ "step": 144
2170
+ },
2171
+ {
2172
+ "epoch": 1.901639344262295,
2173
+ "grad_norm": 37.87571334838867,
2174
+ "learning_rate": 4.4117647058823536e-07,
2175
+ "logits/chosen": -0.7307272553443909,
2176
+ "logits/rejected": -0.5720311403274536,
2177
+ "logps/chosen": -393.85491943359375,
2178
+ "logps/rejected": -344.6254577636719,
2179
+ "loss": 0.352,
2180
+ "rewards/accuracies": 0.75,
2181
+ "rewards/chosen": 1.1627728939056396,
2182
+ "rewards/margins": 3.641770124435425,
2183
+ "rewards/rejected": -2.478997230529785,
2184
+ "step": 145
2185
+ },
2186
+ {
2187
+ "epoch": 1.9147540983606557,
2188
+ "grad_norm": 15.04370403289795,
2189
+ "learning_rate": 4.044117647058824e-07,
2190
+ "logits/chosen": -0.842681884765625,
2191
+ "logits/rejected": -0.4292832314968109,
2192
+ "logps/chosen": -297.94207763671875,
2193
+ "logps/rejected": -240.36907958984375,
2194
+ "loss": 0.0534,
2195
+ "rewards/accuracies": 1.0,
2196
+ "rewards/chosen": 3.2723472118377686,
2197
+ "rewards/margins": 5.443933963775635,
2198
+ "rewards/rejected": -2.171586751937866,
2199
+ "step": 146
2200
+ },
2201
+ {
2202
+ "epoch": 1.9278688524590164,
2203
+ "grad_norm": 15.202438354492188,
2204
+ "learning_rate": 3.6764705882352943e-07,
2205
+ "logits/chosen": -0.6476624011993408,
2206
+ "logits/rejected": -0.49806222319602966,
2207
+ "logps/chosen": -224.61077880859375,
2208
+ "logps/rejected": -169.60565185546875,
2209
+ "loss": 0.1546,
2210
+ "rewards/accuracies": 1.0,
2211
+ "rewards/chosen": 0.8692402839660645,
2212
+ "rewards/margins": 2.598930597305298,
2213
+ "rewards/rejected": -1.7296903133392334,
2214
+ "step": 147
2215
+ },
2216
+ {
2217
+ "epoch": 1.940983606557377,
2218
+ "grad_norm": 7.096276760101318,
2219
+ "learning_rate": 3.308823529411765e-07,
2220
+ "logits/chosen": -0.7730454802513123,
2221
+ "logits/rejected": -0.4797229766845703,
2222
+ "logps/chosen": -321.5426025390625,
2223
+ "logps/rejected": -219.32769775390625,
2224
+ "loss": 0.0219,
2225
+ "rewards/accuracies": 1.0,
2226
+ "rewards/chosen": 2.728835344314575,
2227
+ "rewards/margins": 5.427863597869873,
2228
+ "rewards/rejected": -2.699028253555298,
2229
+ "step": 148
2230
+ },
2231
+ {
2232
+ "epoch": 1.9540983606557378,
2233
+ "grad_norm": 66.5175552368164,
2234
+ "learning_rate": 2.9411764705882356e-07,
2235
+ "logits/chosen": -0.31179729104042053,
2236
+ "logits/rejected": -0.28874772787094116,
2237
+ "logps/chosen": -279.7017822265625,
2238
+ "logps/rejected": -289.318115234375,
2239
+ "loss": 0.2663,
2240
+ "rewards/accuracies": 0.75,
2241
+ "rewards/chosen": 1.061594009399414,
2242
+ "rewards/margins": 3.8362441062927246,
2243
+ "rewards/rejected": -2.7746498584747314,
2244
+ "step": 149
2245
+ },
2246
+ {
2247
+ "epoch": 1.9672131147540983,
2248
+ "grad_norm": 32.35987091064453,
2249
+ "learning_rate": 2.573529411764706e-07,
2250
+ "logits/chosen": -0.6153096556663513,
2251
+ "logits/rejected": -0.725881814956665,
2252
+ "logps/chosen": -301.1914367675781,
2253
+ "logps/rejected": -272.52825927734375,
2254
+ "loss": 0.233,
2255
+ "rewards/accuracies": 1.0,
2256
+ "rewards/chosen": 1.4337717294692993,
2257
+ "rewards/margins": 3.663452625274658,
2258
+ "rewards/rejected": -2.2296810150146484,
2259
+ "step": 150
2260
+ },
2261
+ {
2262
+ "epoch": 1.980327868852459,
2263
+ "grad_norm": 0.4960515797138214,
2264
+ "learning_rate": 2.2058823529411768e-07,
2265
+ "logits/chosen": -0.30176612734794617,
2266
+ "logits/rejected": 0.019010625779628754,
2267
+ "logps/chosen": -270.0059814453125,
2268
+ "logps/rejected": -376.6888732910156,
2269
+ "loss": 0.0017,
2270
+ "rewards/accuracies": 1.0,
2271
+ "rewards/chosen": 1.2527967691421509,
2272
+ "rewards/margins": 7.02215576171875,
2273
+ "rewards/rejected": -5.7693586349487305,
2274
+ "step": 151
2275
+ },
2276
+ {
2277
+ "epoch": 1.9934426229508198,
2278
+ "grad_norm": 29.579833984375,
2279
+ "learning_rate": 1.8382352941176472e-07,
2280
+ "logits/chosen": -0.753585696220398,
2281
+ "logits/rejected": -0.5951805114746094,
2282
+ "logps/chosen": -178.24880981445312,
2283
+ "logps/rejected": -202.90585327148438,
2284
+ "loss": 0.1476,
2285
+ "rewards/accuracies": 1.0,
2286
+ "rewards/chosen": 1.0991493463516235,
2287
+ "rewards/margins": 2.3130767345428467,
2288
+ "rewards/rejected": -1.2139275074005127,
2289
+ "step": 152
2290
+ }
2291
+ ],
2292
+ "logging_steps": 1,
2293
+ "max_steps": 152,
2294
+ "num_input_tokens_seen": 0,
2295
+ "num_train_epochs": 2,
2296
+ "save_steps": 500,
2297
+ "stateful_callbacks": {
2298
+ "TrainerControl": {
2299
+ "args": {
2300
+ "should_epoch_stop": false,
2301
+ "should_evaluate": false,
2302
+ "should_log": false,
2303
+ "should_save": true,
2304
+ "should_training_stop": true
2305
+ },
2306
+ "attributes": {}
2307
+ }
2308
+ },
2309
+ "total_flos": 0.0,
2310
+ "train_batch_size": 1,
2311
+ "trial_name": null,
2312
+ "trial_params": null
2313
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f08cf1af37eda7ad810f974896d5632aead7cd186400d413fab5415033be4b7e
3
+ size 5944