BraylonDash commited on
Commit
2974093
1 Parent(s): c57d01a

Model save

Browse files
README.md ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ library_name: peft
4
+ tags:
5
+ - trl
6
+ - dpo
7
+ - generated_from_trainer
8
+ base_model: microsoft/phi-2
9
+ model-index:
10
+ - name: phi-2-gpo-test-longest-iter-4
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # phi-2-gpo-test-longest-iter-4
18
+
19
+ This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on the None dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.0107
22
+ - Rewards/chosen: -0.0000
23
+ - Rewards/rejected: -0.0005
24
+ - Rewards/accuracies: 0.5085
25
+ - Rewards/margins: 0.0005
26
+ - Logps/rejected: -278.6688
27
+ - Logps/chosen: -306.3621
28
+ - Logits/rejected: 0.0917
29
+ - Logits/chosen: -0.0055
30
+
31
+ ## Model description
32
+
33
+ More information needed
34
+
35
+ ## Intended uses & limitations
36
+
37
+ More information needed
38
+
39
+ ## Training and evaluation data
40
+
41
+ More information needed
42
+
43
+ ## Training procedure
44
+
45
+ ### Training hyperparameters
46
+
47
+ The following hyperparameters were used during training:
48
+ - learning_rate: 5e-06
49
+ - train_batch_size: 4
50
+ - eval_batch_size: 4
51
+ - seed: 42
52
+ - distributed_type: multi-GPU
53
+ - gradient_accumulation_steps: 4
54
+ - total_train_batch_size: 16
55
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
56
+ - lr_scheduler_type: cosine
57
+ - lr_scheduler_warmup_ratio: 0.1
58
+ - num_epochs: 2
59
+
60
+ ### Training results
61
+
62
+ | Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
63
+ |:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
64
+ | 0.0105 | 1.6 | 100 | 0.0108 | 0.0006 | 0.0007 | 0.4945 | -0.0001 | -278.5431 | -306.2985 | 0.0955 | -0.0024 |
65
+
66
+
67
+ ### Framework versions
68
+
69
+ - PEFT 0.7.1
70
+ - Transformers 4.36.2
71
+ - Pytorch 2.2.1+cu121
72
+ - Datasets 2.14.6
73
+ - Tokenizers 0.15.2
adapter_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "microsoft/phi-2",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 16,
13
+ "lora_dropout": 0.05,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 32,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "q_proj",
23
+ "dense",
24
+ "k_proj",
25
+ "v_proj"
26
+ ],
27
+ "task_type": "CAUSAL_LM"
28
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3708c870b803553a5a9db89a2ef6b2d50dd99aab489302c72ece1535a83d0c0d
3
+ size 41977616
added_tokens.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "\t\t": 50294,
3
+ "\t\t\t": 50293,
4
+ "\t\t\t\t": 50292,
5
+ "\t\t\t\t\t": 50291,
6
+ "\t\t\t\t\t\t": 50290,
7
+ "\t\t\t\t\t\t\t": 50289,
8
+ "\t\t\t\t\t\t\t\t": 50288,
9
+ "\t\t\t\t\t\t\t\t\t": 50287,
10
+ " ": 50286,
11
+ " ": 50285,
12
+ " ": 50284,
13
+ " ": 50283,
14
+ " ": 50282,
15
+ " ": 50281,
16
+ " ": 50280,
17
+ " ": 50279,
18
+ " ": 50278,
19
+ " ": 50277,
20
+ " ": 50276,
21
+ " ": 50275,
22
+ " ": 50274,
23
+ " ": 50273,
24
+ " ": 50272,
25
+ " ": 50271,
26
+ " ": 50270,
27
+ " ": 50269,
28
+ " ": 50268,
29
+ " ": 50267,
30
+ " ": 50266,
31
+ " ": 50265,
32
+ " ": 50264,
33
+ " ": 50263,
34
+ " ": 50262,
35
+ " ": 50261,
36
+ " ": 50260,
37
+ " ": 50259,
38
+ " ": 50258,
39
+ " ": 50257
40
+ }
all_results.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.98,
3
+ "eval_logits/chosen": -0.0055040339939296246,
4
+ "eval_logits/rejected": 0.09165824949741364,
5
+ "eval_logps/chosen": -306.3620910644531,
6
+ "eval_logps/rejected": -278.66876220703125,
7
+ "eval_loss": 0.010676206089556217,
8
+ "eval_rewards/accuracies": 0.5084999799728394,
9
+ "eval_rewards/chosen": -2.4409100660705008e-05,
10
+ "eval_rewards/margins": 0.00048807679559104145,
11
+ "eval_rewards/rejected": -0.0005124859162606299,
12
+ "eval_runtime": 433.0135,
13
+ "eval_samples": 2000,
14
+ "eval_samples_per_second": 4.619,
15
+ "eval_steps_per_second": 1.155,
16
+ "train_loss": 0.010321829197627882,
17
+ "train_runtime": 1406.1718,
18
+ "train_samples": 61135,
19
+ "train_samples_per_second": 1.422,
20
+ "train_steps_per_second": 0.088
21
+ }
eval_results.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.98,
3
+ "eval_logits/chosen": -0.0055040339939296246,
4
+ "eval_logits/rejected": 0.09165824949741364,
5
+ "eval_logps/chosen": -306.3620910644531,
6
+ "eval_logps/rejected": -278.66876220703125,
7
+ "eval_loss": 0.010676206089556217,
8
+ "eval_rewards/accuracies": 0.5084999799728394,
9
+ "eval_rewards/chosen": -2.4409100660705008e-05,
10
+ "eval_rewards/margins": 0.00048807679559104145,
11
+ "eval_rewards/rejected": -0.0005124859162606299,
12
+ "eval_runtime": 433.0135,
13
+ "eval_samples": 2000,
14
+ "eval_samples_per_second": 4.619,
15
+ "eval_steps_per_second": 1.155
16
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,325 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "50257": {
13
+ "content": " ",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": false
19
+ },
20
+ "50258": {
21
+ "content": " ",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": false
27
+ },
28
+ "50259": {
29
+ "content": " ",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": false
35
+ },
36
+ "50260": {
37
+ "content": " ",
38
+ "lstrip": false,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": false
43
+ },
44
+ "50261": {
45
+ "content": " ",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": false
51
+ },
52
+ "50262": {
53
+ "content": " ",
54
+ "lstrip": false,
55
+ "normalized": true,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": false
59
+ },
60
+ "50263": {
61
+ "content": " ",
62
+ "lstrip": false,
63
+ "normalized": true,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": false
67
+ },
68
+ "50264": {
69
+ "content": " ",
70
+ "lstrip": false,
71
+ "normalized": true,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": false
75
+ },
76
+ "50265": {
77
+ "content": " ",
78
+ "lstrip": false,
79
+ "normalized": true,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": false
83
+ },
84
+ "50266": {
85
+ "content": " ",
86
+ "lstrip": false,
87
+ "normalized": true,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": false
91
+ },
92
+ "50267": {
93
+ "content": " ",
94
+ "lstrip": false,
95
+ "normalized": true,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": false
99
+ },
100
+ "50268": {
101
+ "content": " ",
102
+ "lstrip": false,
103
+ "normalized": true,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": false
107
+ },
108
+ "50269": {
109
+ "content": " ",
110
+ "lstrip": false,
111
+ "normalized": true,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": false
115
+ },
116
+ "50270": {
117
+ "content": " ",
118
+ "lstrip": false,
119
+ "normalized": true,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": false
123
+ },
124
+ "50271": {
125
+ "content": " ",
126
+ "lstrip": false,
127
+ "normalized": true,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": false
131
+ },
132
+ "50272": {
133
+ "content": " ",
134
+ "lstrip": false,
135
+ "normalized": true,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": false
139
+ },
140
+ "50273": {
141
+ "content": " ",
142
+ "lstrip": false,
143
+ "normalized": true,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": false
147
+ },
148
+ "50274": {
149
+ "content": " ",
150
+ "lstrip": false,
151
+ "normalized": true,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": false
155
+ },
156
+ "50275": {
157
+ "content": " ",
158
+ "lstrip": false,
159
+ "normalized": true,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": false
163
+ },
164
+ "50276": {
165
+ "content": " ",
166
+ "lstrip": false,
167
+ "normalized": true,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": false
171
+ },
172
+ "50277": {
173
+ "content": " ",
174
+ "lstrip": false,
175
+ "normalized": true,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": false
179
+ },
180
+ "50278": {
181
+ "content": " ",
182
+ "lstrip": false,
183
+ "normalized": true,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": false
187
+ },
188
+ "50279": {
189
+ "content": " ",
190
+ "lstrip": false,
191
+ "normalized": true,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": false
195
+ },
196
+ "50280": {
197
+ "content": " ",
198
+ "lstrip": false,
199
+ "normalized": true,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": false
203
+ },
204
+ "50281": {
205
+ "content": " ",
206
+ "lstrip": false,
207
+ "normalized": true,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": false
211
+ },
212
+ "50282": {
213
+ "content": " ",
214
+ "lstrip": false,
215
+ "normalized": true,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": false
219
+ },
220
+ "50283": {
221
+ "content": " ",
222
+ "lstrip": false,
223
+ "normalized": true,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": false
227
+ },
228
+ "50284": {
229
+ "content": " ",
230
+ "lstrip": false,
231
+ "normalized": true,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": false
235
+ },
236
+ "50285": {
237
+ "content": " ",
238
+ "lstrip": false,
239
+ "normalized": true,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": false
243
+ },
244
+ "50286": {
245
+ "content": " ",
246
+ "lstrip": false,
247
+ "normalized": true,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": false
251
+ },
252
+ "50287": {
253
+ "content": "\t\t\t\t\t\t\t\t\t",
254
+ "lstrip": false,
255
+ "normalized": true,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": false
259
+ },
260
+ "50288": {
261
+ "content": "\t\t\t\t\t\t\t\t",
262
+ "lstrip": false,
263
+ "normalized": true,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": false
267
+ },
268
+ "50289": {
269
+ "content": "\t\t\t\t\t\t\t",
270
+ "lstrip": false,
271
+ "normalized": true,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": false
275
+ },
276
+ "50290": {
277
+ "content": "\t\t\t\t\t\t",
278
+ "lstrip": false,
279
+ "normalized": true,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": false
283
+ },
284
+ "50291": {
285
+ "content": "\t\t\t\t\t",
286
+ "lstrip": false,
287
+ "normalized": true,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": false
291
+ },
292
+ "50292": {
293
+ "content": "\t\t\t\t",
294
+ "lstrip": false,
295
+ "normalized": true,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": false
299
+ },
300
+ "50293": {
301
+ "content": "\t\t\t",
302
+ "lstrip": false,
303
+ "normalized": true,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": false
307
+ },
308
+ "50294": {
309
+ "content": "\t\t",
310
+ "lstrip": false,
311
+ "normalized": true,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": false
315
+ }
316
+ },
317
+ "bos_token": "<|endoftext|>",
318
+ "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
319
+ "clean_up_tokenization_spaces": true,
320
+ "eos_token": "<|endoftext|>",
321
+ "model_max_length": 2048,
322
+ "pad_token": "<|endoftext|>",
323
+ "tokenizer_class": "CodeGenTokenizer",
324
+ "unk_token": "<|endoftext|>"
325
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.98,
3
+ "train_loss": 0.010321829197627882,
4
+ "train_runtime": 1406.1718,
5
+ "train_samples": 61135,
6
+ "train_samples_per_second": 1.422,
7
+ "train_steps_per_second": 0.088
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,228 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.984,
5
+ "eval_steps": 100,
6
+ "global_step": 124,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.02,
13
+ "learning_rate": 3.846153846153847e-07,
14
+ "logits/chosen": 0.33759647607803345,
15
+ "logits/rejected": 0.28577902913093567,
16
+ "logps/chosen": -217.51107788085938,
17
+ "logps/rejected": -154.6298065185547,
18
+ "loss": 0.0102,
19
+ "rewards/accuracies": 0.0,
20
+ "rewards/chosen": 0.0,
21
+ "rewards/margins": 0.0,
22
+ "rewards/rejected": 0.0,
23
+ "step": 1
24
+ },
25
+ {
26
+ "epoch": 0.16,
27
+ "learning_rate": 3.846153846153847e-06,
28
+ "logits/chosen": 0.23491337895393372,
29
+ "logits/rejected": 0.185601606965065,
30
+ "logps/chosen": -189.5899200439453,
31
+ "logps/rejected": -162.4447784423828,
32
+ "loss": 0.0106,
33
+ "rewards/accuracies": 0.3333333432674408,
34
+ "rewards/chosen": -0.0008325728122144938,
35
+ "rewards/margins": -0.0011730334954336286,
36
+ "rewards/rejected": 0.0003404606832191348,
37
+ "step": 10
38
+ },
39
+ {
40
+ "epoch": 0.32,
41
+ "learning_rate": 4.951096619903317e-06,
42
+ "logits/chosen": 0.11001434177160263,
43
+ "logits/rejected": 0.06706250458955765,
44
+ "logps/chosen": -170.3766632080078,
45
+ "logps/rejected": -145.70187377929688,
46
+ "loss": 0.0102,
47
+ "rewards/accuracies": 0.42500001192092896,
48
+ "rewards/chosen": 0.0003622249641921371,
49
+ "rewards/margins": 0.0007274674135260284,
50
+ "rewards/rejected": -0.000365242303814739,
51
+ "step": 20
52
+ },
53
+ {
54
+ "epoch": 0.48,
55
+ "learning_rate": 4.716164218065246e-06,
56
+ "logits/chosen": 0.15306313335895538,
57
+ "logits/rejected": 0.14907678961753845,
58
+ "logps/chosen": -184.689453125,
59
+ "logps/rejected": -146.67767333984375,
60
+ "loss": 0.01,
61
+ "rewards/accuracies": 0.4937500059604645,
62
+ "rewards/chosen": 0.0019506055396050215,
63
+ "rewards/margins": 0.001728715025819838,
64
+ "rewards/rejected": 0.0002218906593043357,
65
+ "step": 30
66
+ },
67
+ {
68
+ "epoch": 0.64,
69
+ "learning_rate": 4.3048902348863116e-06,
70
+ "logits/chosen": 0.11253954470157623,
71
+ "logits/rejected": 0.2042957991361618,
72
+ "logps/chosen": -182.73019409179688,
73
+ "logps/rejected": -147.92068481445312,
74
+ "loss": 0.0104,
75
+ "rewards/accuracies": 0.3375000059604645,
76
+ "rewards/chosen": 0.0024931146763265133,
77
+ "rewards/margins": -0.0002410466258879751,
78
+ "rewards/rejected": 0.002734161214902997,
79
+ "step": 40
80
+ },
81
+ {
82
+ "epoch": 0.8,
83
+ "learning_rate": 3.7500000000000005e-06,
84
+ "logits/chosen": 0.26959556341171265,
85
+ "logits/rejected": 0.17199485003948212,
86
+ "logps/chosen": -196.38694763183594,
87
+ "logps/rejected": -161.71762084960938,
88
+ "loss": 0.0102,
89
+ "rewards/accuracies": 0.4124999940395355,
90
+ "rewards/chosen": 0.00301692564971745,
91
+ "rewards/margins": 0.0006210061255842447,
92
+ "rewards/rejected": 0.0023959192913025618,
93
+ "step": 50
94
+ },
95
+ {
96
+ "epoch": 0.96,
97
+ "learning_rate": 3.0956464785579125e-06,
98
+ "logits/chosen": 0.19740340113639832,
99
+ "logits/rejected": 0.1762491911649704,
100
+ "logps/chosen": -182.07997131347656,
101
+ "logps/rejected": -150.88436889648438,
102
+ "loss": 0.0105,
103
+ "rewards/accuracies": 0.35624998807907104,
104
+ "rewards/chosen": -0.00115151796489954,
105
+ "rewards/margins": -0.0006008323980495334,
106
+ "rewards/rejected": -0.0005506856250576675,
107
+ "step": 60
108
+ },
109
+ {
110
+ "epoch": 1.12,
111
+ "learning_rate": 2.39389699200963e-06,
112
+ "logits/chosen": 0.11103002727031708,
113
+ "logits/rejected": 0.17598359286785126,
114
+ "logps/chosen": -203.237548828125,
115
+ "logps/rejected": -173.33811950683594,
116
+ "loss": 0.0104,
117
+ "rewards/accuracies": 0.35624998807907104,
118
+ "rewards/chosen": 0.001459635910578072,
119
+ "rewards/margins": -0.0005474772187881172,
120
+ "rewards/rejected": 0.0020071130711585283,
121
+ "step": 70
122
+ },
123
+ {
124
+ "epoch": 1.28,
125
+ "learning_rate": 1.700590188571887e-06,
126
+ "logits/chosen": 0.13080066442489624,
127
+ "logits/rejected": 0.154659703373909,
128
+ "logps/chosen": -193.30853271484375,
129
+ "logps/rejected": -161.02102661132812,
130
+ "loss": 0.0102,
131
+ "rewards/accuracies": 0.44999998807907104,
132
+ "rewards/chosen": 0.0017246768111363053,
133
+ "rewards/margins": 0.0007789047667756677,
134
+ "rewards/rejected": 0.0009457715786993504,
135
+ "step": 80
136
+ },
137
+ {
138
+ "epoch": 1.44,
139
+ "learning_rate": 1.0708929268538034e-06,
140
+ "logits/chosen": 0.10300946235656738,
141
+ "logits/rejected": 0.11627539247274399,
142
+ "logps/chosen": -184.31507873535156,
143
+ "logps/rejected": -151.22093200683594,
144
+ "loss": 0.0101,
145
+ "rewards/accuracies": 0.41874998807907104,
146
+ "rewards/chosen": 0.0029378323815762997,
147
+ "rewards/margins": 0.0010877925669774413,
148
+ "rewards/rejected": 0.0018500399310141802,
149
+ "step": 90
150
+ },
151
+ {
152
+ "epoch": 1.6,
153
+ "learning_rate": 5.549106142039018e-07,
154
+ "logits/chosen": 0.17798453569412231,
155
+ "logits/rejected": 0.1302061527967453,
156
+ "logps/chosen": -176.29644775390625,
157
+ "logps/rejected": -149.06594848632812,
158
+ "loss": 0.0105,
159
+ "rewards/accuracies": 0.3499999940395355,
160
+ "rewards/chosen": 0.0017444228287786245,
161
+ "rewards/margins": -0.0010295301908627152,
162
+ "rewards/rejected": 0.0027739531360566616,
163
+ "step": 100
164
+ },
165
+ {
166
+ "epoch": 1.6,
167
+ "eval_logits/chosen": -0.002386125735938549,
168
+ "eval_logits/rejected": 0.09546130150556564,
169
+ "eval_logps/chosen": -306.2984924316406,
170
+ "eval_logps/rejected": -278.5430908203125,
171
+ "eval_loss": 0.010826661251485348,
172
+ "eval_rewards/accuracies": 0.4945000112056732,
173
+ "eval_rewards/chosen": 0.0006116966251283884,
174
+ "eval_rewards/margins": -0.00013227059389464557,
175
+ "eval_rewards/rejected": 0.0007439671317115426,
176
+ "eval_runtime": 433.1922,
177
+ "eval_samples_per_second": 4.617,
178
+ "eval_steps_per_second": 1.154,
179
+ "step": 100
180
+ },
181
+ {
182
+ "epoch": 1.76,
183
+ "learning_rate": 1.937002879188285e-07,
184
+ "logits/chosen": 0.13854524493217468,
185
+ "logits/rejected": 0.09755973517894745,
186
+ "logps/chosen": -194.58871459960938,
187
+ "logps/rejected": -159.81277465820312,
188
+ "loss": 0.0105,
189
+ "rewards/accuracies": 0.33125001192092896,
190
+ "rewards/chosen": 0.0010774679249152541,
191
+ "rewards/margins": -0.0008498074603267014,
192
+ "rewards/rejected": 0.0019272754434496164,
193
+ "step": 110
194
+ },
195
+ {
196
+ "epoch": 1.92,
197
+ "learning_rate": 1.6003680950742728e-08,
198
+ "logits/chosen": 0.18497225642204285,
199
+ "logits/rejected": 0.25526371598243713,
200
+ "logps/chosen": -182.73492431640625,
201
+ "logps/rejected": -146.8502197265625,
202
+ "loss": 0.0103,
203
+ "rewards/accuracies": 0.3812499940395355,
204
+ "rewards/chosen": 0.0014311736449599266,
205
+ "rewards/margins": 0.00013411189138423651,
206
+ "rewards/rejected": 0.001297061680816114,
207
+ "step": 120
208
+ },
209
+ {
210
+ "epoch": 1.98,
211
+ "step": 124,
212
+ "total_flos": 0.0,
213
+ "train_loss": 0.010321829197627882,
214
+ "train_runtime": 1406.1718,
215
+ "train_samples_per_second": 1.422,
216
+ "train_steps_per_second": 0.088
217
+ }
218
+ ],
219
+ "logging_steps": 10,
220
+ "max_steps": 124,
221
+ "num_input_tokens_seen": 0,
222
+ "num_train_epochs": 2,
223
+ "save_steps": 100,
224
+ "total_flos": 0.0,
225
+ "train_batch_size": 4,
226
+ "trial_name": null,
227
+ "trial_params": null
228
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:999b7dc3fed4312838535ab95cfee21e1e5dec2e7505a3f9fd2129072e1100b9
3
+ size 5880
vocab.json ADDED
The diff for this file is too large to render. See raw diff