Hugging Face's logo

DUAL-GPO
/
phi-2-gpo-test-longest-iter-random-1

PEFT
Safetensors
phi
alignment-handbook
Generated from Trainer
trl
dpo
custom_code
Model card Files Community
BraylonDash commited on
Commit
c014d7e
•
1 Parent(s): 1d511e3

Model save

Browse files
Files changed (14) hide show
  1. README.md +74 -0
  2. adapter_config.json +28 -0
  3. adapter_model.safetensors +3 -0
  4. added_tokens.json +40 -0
  5. all_results.json +21 -0
  6. eval_results.json +16 -0
  7. merges.txt +0 -0
  8. special_tokens_map.json +30 -0
  9. tokenizer.json +0 -0
  10. tokenizer_config.json +325 -0
  11. train_results.json +8 -0
  12. trainer_state.json +412 -0
  13. training_args.bin +3 -0
  14. vocab.json +0 -0
README.md ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-random-1
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-random-1
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: 0.0022
22
+ - Rewards/chosen: 0.0010
23
+ - Rewards/rejected: 0.0016
24
+ - Rewards/accuracies: 0.4790
25
+ - Rewards/margins: -0.0006
26
+ - Logps/rejected: -278.5288
27
+ - Logps/chosen: -306.2895
28
+ - Logits/rejected: 0.0882
29
+ - Logits/chosen: -0.0097
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: 4
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
+ | 0.0016 | 1.6 | 100 | 0.0021 | 0.0005 | 0.0001 | 0.4910 | 0.0004 | -278.6740 | -306.3399 | 0.0933 | -0.0050 |
65
+ | 0.0017 | 3.2 | 200 | 0.0022 | -0.0007 | -0.0006 | 0.4950 | -0.0001 | -278.7457 | -306.4609 | 0.0886 | -0.0095 |
66
+
67
+
68
+ ### Framework versions
69
+
70
+ - PEFT 0.7.1
71
+ - Transformers 4.36.2
72
+ - Pytorch 2.2.1+cu121
73
+ - Datasets 2.14.6
74
+ - 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
+ "k_proj",
23
+ "dense",
24
+ "v_proj",
25
+ "q_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:c4b5bf52cb54c65c7c9cb8dba406e24ab3ca05738e4b41441aec4c006c59088a
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": 3.97,
3
+ "eval_logits/chosen": -0.00967690534889698,
4
+ "eval_logits/rejected": 0.0881744921207428,
5
+ "eval_logps/chosen": -306.2895202636719,
6
+ "eval_logps/rejected": -278.5288391113281,
7
+ "eval_loss": 0.0022096126340329647,
8
+ "eval_rewards/accuracies": 0.4790000021457672,
9
+ "eval_rewards/chosen": 0.0010312977246940136,
10
+ "eval_rewards/margins": -0.0005611819215118885,
11
+ "eval_rewards/rejected": 0.0015924794133752584,
12
+ "eval_runtime": 412.1601,
13
+ "eval_samples": 2000,
14
+ "eval_samples_per_second": 4.852,
15
+ "eval_steps_per_second": 1.213,
16
+ "train_loss": 0.0016499216942447088,
17
+ "train_runtime": 2661.6314,
18
+ "train_samples": 61135,
19
+ "train_samples_per_second": 1.503,
20
+ "train_steps_per_second": 0.093
21
+ }
eval_results.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.97,
3
+ "eval_logits/chosen": -0.00967690534889698,
4
+ "eval_logits/rejected": 0.0881744921207428,
5
+ "eval_logps/chosen": -306.2895202636719,
6
+ "eval_logps/rejected": -278.5288391113281,
7
+ "eval_loss": 0.0022096126340329647,
8
+ "eval_rewards/accuracies": 0.4790000021457672,
9
+ "eval_rewards/chosen": 0.0010312977246940136,
10
+ "eval_rewards/margins": -0.0005611819215118885,
11
+ "eval_rewards/rejected": 0.0015924794133752584,
12
+ "eval_runtime": 412.1601,
13
+ "eval_samples": 2000,
14
+ "eval_samples_per_second": 4.852,
15
+ "eval_steps_per_second": 1.213
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": 3.97,
3
+ "train_loss": 0.0016499216942447088,
4
+ "train_runtime": 2661.6314,
5
+ "train_samples": 61135,
6
+ "train_samples_per_second": 1.503,
7
+ "train_steps_per_second": 0.093
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,412 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.968,
5
+ "eval_steps": 100,
6
+ "global_step": 248,
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": 2.0000000000000002e-07,
14
+ "logits/chosen": 0.4729592502117157,
15
+ "logits/rejected": 0.38554269075393677,
16
+ "logps/chosen": -213.08737182617188,
17
+ "logps/rejected": -203.01974487304688,
18
+ "loss": 0.0016,
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": 2.0000000000000003e-06,
28
+ "logits/chosen": 0.15001463890075684,
29
+ "logits/rejected": 0.20593884587287903,
30
+ "logps/chosen": -161.55821228027344,
31
+ "logps/rejected": -135.95449829101562,
32
+ "loss": 0.0015,
33
+ "rewards/accuracies": 0.3819444477558136,
34
+ "rewards/chosen": 3.554481372702867e-05,
35
+ "rewards/margins": 0.0017159796552732587,
36
+ "rewards/rejected": -0.001680435030721128,
37
+ "step": 10
38
+ },
39
+ {
40
+ "epoch": 0.32,
41
+ "learning_rate": 4.000000000000001e-06,
42
+ "logits/chosen": 0.09242797642946243,
43
+ "logits/rejected": 0.04898233711719513,
44
+ "logps/chosen": -181.7728271484375,
45
+ "logps/rejected": -151.2571563720703,
46
+ "loss": 0.0017,
47
+ "rewards/accuracies": 0.375,
48
+ "rewards/chosen": -0.0012837719405069947,
49
+ "rewards/margins": -0.0005185201880522072,
50
+ "rewards/rejected": -0.0007652518688701093,
51
+ "step": 20
52
+ },
53
+ {
54
+ "epoch": 0.48,
55
+ "learning_rate": 4.993800445762451e-06,
56
+ "logits/chosen": 0.1974470317363739,
57
+ "logits/rejected": 0.24875693023204803,
58
+ "logps/chosen": -175.55596923828125,
59
+ "logps/rejected": -143.77584838867188,
60
+ "loss": 0.0019,
61
+ "rewards/accuracies": 0.39375001192092896,
62
+ "rewards/chosen": -0.003100383561104536,
63
+ "rewards/margins": -0.0019143905956298113,
64
+ "rewards/rejected": -0.0011859927326440811,
65
+ "step": 30
66
+ },
67
+ {
68
+ "epoch": 0.64,
69
+ "learning_rate": 4.944388344834205e-06,
70
+ "logits/chosen": 0.1500740945339203,
71
+ "logits/rejected": 0.2011214792728424,
72
+ "logps/chosen": -181.77581787109375,
73
+ "logps/rejected": -164.48788452148438,
74
+ "loss": 0.0016,
75
+ "rewards/accuracies": 0.3499999940395355,
76
+ "rewards/chosen": -0.0005139185814186931,
77
+ "rewards/margins": 0.0008601135341450572,
78
+ "rewards/rejected": -0.0013740319991484284,
79
+ "step": 40
80
+ },
81
+ {
82
+ "epoch": 0.8,
83
+ "learning_rate": 4.8465431931347904e-06,
84
+ "logits/chosen": 0.08030920475721359,
85
+ "logits/rejected": 0.15738067030906677,
86
+ "logps/chosen": -169.9337158203125,
87
+ "logps/rejected": -144.90228271484375,
88
+ "loss": 0.0017,
89
+ "rewards/accuracies": 0.375,
90
+ "rewards/chosen": -0.0008664874476380646,
91
+ "rewards/margins": -0.0005486059235408902,
92
+ "rewards/rejected": -0.00031788164051249623,
93
+ "step": 50
94
+ },
95
+ {
96
+ "epoch": 0.96,
97
+ "learning_rate": 4.702203692102539e-06,
98
+ "logits/chosen": 0.1897524893283844,
99
+ "logits/rejected": 0.17828692495822906,
100
+ "logps/chosen": -173.4358367919922,
101
+ "logps/rejected": -145.06625366210938,
102
+ "loss": 0.0016,
103
+ "rewards/accuracies": 0.42500001192092896,
104
+ "rewards/chosen": -0.0021182517521083355,
105
+ "rewards/margins": 0.0011023099068552256,
106
+ "rewards/rejected": -0.0032205611933022738,
107
+ "step": 60
108
+ },
109
+ {
110
+ "epoch": 1.12,
111
+ "learning_rate": 4.514229781074239e-06,
112
+ "logits/chosen": 0.2607804834842682,
113
+ "logits/rejected": 0.23584774136543274,
114
+ "logps/chosen": -188.595947265625,
115
+ "logps/rejected": -160.49171447753906,
116
+ "loss": 0.0018,
117
+ "rewards/accuracies": 0.34375,
118
+ "rewards/chosen": -0.0020389086566865444,
119
+ "rewards/margins": -0.001390365301631391,
120
+ "rewards/rejected": -0.0006485433550551534,
121
+ "step": 70
122
+ },
123
+ {
124
+ "epoch": 1.28,
125
+ "learning_rate": 4.286345970517195e-06,
126
+ "logits/chosen": 0.17552152276039124,
127
+ "logits/rejected": 0.24562516808509827,
128
+ "logps/chosen": -165.12591552734375,
129
+ "logps/rejected": -137.75808715820312,
130
+ "loss": 0.0016,
131
+ "rewards/accuracies": 0.44999998807907104,
132
+ "rewards/chosen": -0.00046771267079748213,
133
+ "rewards/margins": 0.0003761005064006895,
134
+ "rewards/rejected": -0.0008438131771981716,
135
+ "step": 80
136
+ },
137
+ {
138
+ "epoch": 1.44,
139
+ "learning_rate": 4.023067544670082e-06,
140
+ "logits/chosen": 0.16295495629310608,
141
+ "logits/rejected": 0.1336701214313507,
142
+ "logps/chosen": -176.12887573242188,
143
+ "logps/rejected": -145.37673950195312,
144
+ "loss": 0.0016,
145
+ "rewards/accuracies": 0.42500001192092896,
146
+ "rewards/chosen": -0.0007470982382073998,
147
+ "rewards/margins": 0.0005909097963012755,
148
+ "rewards/rejected": -0.001338008209131658,
149
+ "step": 90
150
+ },
151
+ {
152
+ "epoch": 1.6,
153
+ "learning_rate": 3.7296110958116845e-06,
154
+ "logits/chosen": 0.18624618649482727,
155
+ "logits/rejected": 0.15213565528392792,
156
+ "logps/chosen": -177.76405334472656,
157
+ "logps/rejected": -152.70240783691406,
158
+ "loss": 0.0016,
159
+ "rewards/accuracies": 0.4000000059604645,
160
+ "rewards/chosen": 0.000859270163346082,
161
+ "rewards/margins": 0.0012418597470968962,
162
+ "rewards/rejected": -0.0003825899329967797,
163
+ "step": 100
164
+ },
165
+ {
166
+ "epoch": 1.6,
167
+ "eval_logits/chosen": -0.004967109765857458,
168
+ "eval_logits/rejected": 0.09325645118951797,
169
+ "eval_logps/chosen": -306.3399353027344,
170
+ "eval_logps/rejected": -278.6739501953125,
171
+ "eval_loss": 0.0021029466297477484,
172
+ "eval_rewards/accuracies": 0.4909999966621399,
173
+ "eval_rewards/chosen": 0.0005270715337246656,
174
+ "eval_rewards/margins": 0.00038576460792683065,
175
+ "eval_rewards/rejected": 0.00014130691124591976,
176
+ "eval_runtime": 412.1139,
177
+ "eval_samples_per_second": 4.853,
178
+ "eval_steps_per_second": 1.213,
179
+ "step": 100
180
+ },
181
+ {
182
+ "epoch": 1.76,
183
+ "learning_rate": 3.4117911628292944e-06,
184
+ "logits/chosen": 0.18669767677783966,
185
+ "logits/rejected": 0.193131685256958,
186
+ "logps/chosen": -186.2015380859375,
187
+ "logps/rejected": -160.41812133789062,
188
+ "loss": 0.0017,
189
+ "rewards/accuracies": 0.35624998807907104,
190
+ "rewards/chosen": -0.0022148210555315018,
191
+ "rewards/margins": -0.0006464887410402298,
192
+ "rewards/rejected": -0.0015683325473219156,
193
+ "step": 110
194
+ },
195
+ {
196
+ "epoch": 1.92,
197
+ "learning_rate": 3.075905022087675e-06,
198
+ "logits/chosen": 0.07856817543506622,
199
+ "logits/rejected": 0.13352298736572266,
200
+ "logps/chosen": -174.9341278076172,
201
+ "logps/rejected": -154.233642578125,
202
+ "loss": 0.0017,
203
+ "rewards/accuracies": 0.40625,
204
+ "rewards/chosen": 0.0001242739672306925,
205
+ "rewards/margins": 0.0005846145795658231,
206
+ "rewards/rejected": -0.00046034049591980875,
207
+ "step": 120
208
+ },
209
+ {
210
+ "epoch": 2.08,
211
+ "learning_rate": 2.728607913349464e-06,
212
+ "logits/chosen": 0.19492605328559875,
213
+ "logits/rejected": 0.16430191695690155,
214
+ "logps/chosen": -174.35968017578125,
215
+ "logps/rejected": -150.935302734375,
216
+ "loss": 0.0016,
217
+ "rewards/accuracies": 0.45625001192092896,
218
+ "rewards/chosen": -0.0011604964965954423,
219
+ "rewards/margins": 0.0007132277823984623,
220
+ "rewards/rejected": -0.0018737241625785828,
221
+ "step": 130
222
+ },
223
+ {
224
+ "epoch": 2.24,
225
+ "learning_rate": 2.376781173017589e-06,
226
+ "logits/chosen": 0.2628365159034729,
227
+ "logits/rejected": 0.19500017166137695,
228
+ "logps/chosen": -187.58023071289062,
229
+ "logps/rejected": -166.26370239257812,
230
+ "loss": 0.0017,
231
+ "rewards/accuracies": 0.35624998807907104,
232
+ "rewards/chosen": -0.0010837314184755087,
233
+ "rewards/margins": -0.00033805653220042586,
234
+ "rewards/rejected": -0.0007456748280674219,
235
+ "step": 140
236
+ },
237
+ {
238
+ "epoch": 2.4,
239
+ "learning_rate": 2.0273958875043877e-06,
240
+ "logits/chosen": 0.14645084738731384,
241
+ "logits/rejected": 0.1681375354528427,
242
+ "logps/chosen": -157.08926391601562,
243
+ "logps/rejected": -131.46810913085938,
244
+ "loss": 0.0016,
245
+ "rewards/accuracies": 0.45625001192092896,
246
+ "rewards/chosen": -0.002456915332004428,
247
+ "rewards/margins": 0.0014492868212983012,
248
+ "rewards/rejected": -0.0039062027353793383,
249
+ "step": 150
250
+ },
251
+ {
252
+ "epoch": 2.56,
253
+ "learning_rate": 1.6873747682962393e-06,
254
+ "logits/chosen": 0.16395077109336853,
255
+ "logits/rejected": 0.14529384672641754,
256
+ "logps/chosen": -188.40296936035156,
257
+ "logps/rejected": -158.95834350585938,
258
+ "loss": 0.0016,
259
+ "rewards/accuracies": 0.40625,
260
+ "rewards/chosen": 0.00022082138457335532,
261
+ "rewards/margins": 0.000981360673904419,
262
+ "rewards/rejected": -0.0007605393184348941,
263
+ "step": 160
264
+ },
265
+ {
266
+ "epoch": 2.72,
267
+ "learning_rate": 1.363454985517803e-06,
268
+ "logits/chosen": 0.21595752239227295,
269
+ "logits/rejected": 0.17811095714569092,
270
+ "logps/chosen": -178.89500427246094,
271
+ "logps/rejected": -150.37576293945312,
272
+ "loss": 0.0016,
273
+ "rewards/accuracies": 0.4437499940395355,
274
+ "rewards/chosen": 0.0017019693041220307,
275
+ "rewards/margins": 0.0014590112259611487,
276
+ "rewards/rejected": 0.00024295765615534037,
277
+ "step": 170
278
+ },
279
+ {
280
+ "epoch": 2.88,
281
+ "learning_rate": 1.062054677808238e-06,
282
+ "logits/chosen": 0.11008661985397339,
283
+ "logits/rejected": 0.1656235158443451,
284
+ "logps/chosen": -166.90554809570312,
285
+ "logps/rejected": -149.75042724609375,
286
+ "loss": 0.0017,
287
+ "rewards/accuracies": 0.4000000059604645,
288
+ "rewards/chosen": -0.0004684976884163916,
289
+ "rewards/margins": 0.0005998688284307718,
290
+ "rewards/rejected": -0.0010683666914701462,
291
+ "step": 180
292
+ },
293
+ {
294
+ "epoch": 3.04,
295
+ "learning_rate": 7.891457834794711e-07,
296
+ "logits/chosen": 0.2820424437522888,
297
+ "logits/rejected": 0.16322749853134155,
298
+ "logps/chosen": -180.0753173828125,
299
+ "logps/rejected": -143.658203125,
300
+ "loss": 0.0016,
301
+ "rewards/accuracies": 0.4312500059604645,
302
+ "rewards/chosen": 1.5354249853771762e-06,
303
+ "rewards/margins": 0.0018281619995832443,
304
+ "rewards/rejected": -0.0018266268307343125,
305
+ "step": 190
306
+ },
307
+ {
308
+ "epoch": 3.2,
309
+ "learning_rate": 5.501357126768117e-07,
310
+ "logits/chosen": 0.15994948148727417,
311
+ "logits/rejected": 0.14330127835273743,
312
+ "logps/chosen": -183.79759216308594,
313
+ "logps/rejected": -155.71310424804688,
314
+ "loss": 0.0017,
315
+ "rewards/accuracies": 0.4375,
316
+ "rewards/chosen": 0.001569538377225399,
317
+ "rewards/margins": 0.0009444955503568053,
318
+ "rewards/rejected": 0.000625042652245611,
319
+ "step": 200
320
+ },
321
+ {
322
+ "epoch": 3.2,
323
+ "eval_logits/chosen": -0.009462343528866768,
324
+ "eval_logits/rejected": 0.08856771141290665,
325
+ "eval_logps/chosen": -306.4609375,
326
+ "eval_logps/rejected": -278.74566650390625,
327
+ "eval_loss": 0.0021845391020178795,
328
+ "eval_rewards/accuracies": 0.4950000047683716,
329
+ "eval_rewards/chosen": -0.0006826075841672719,
330
+ "eval_rewards/margins": -0.00010681045387173072,
331
+ "eval_rewards/rejected": -0.0005757971666753292,
332
+ "eval_runtime": 412.5188,
333
+ "eval_samples_per_second": 4.848,
334
+ "eval_steps_per_second": 1.212,
335
+ "step": 200
336
+ },
337
+ {
338
+ "epoch": 3.36,
339
+ "learning_rate": 3.4976020508682345e-07,
340
+ "logits/chosen": 0.1456301361322403,
341
+ "logits/rejected": 0.2356918305158615,
342
+ "logps/chosen": -183.83010864257812,
343
+ "logps/rejected": -155.9720458984375,
344
+ "loss": 0.0015,
345
+ "rewards/accuracies": 0.44999998807907104,
346
+ "rewards/chosen": 0.0012806833256036043,
347
+ "rewards/margins": 0.0026433460880070925,
348
+ "rewards/rejected": -0.0013626629952341318,
349
+ "step": 210
350
+ },
351
+ {
352
+ "epoch": 3.52,
353
+ "learning_rate": 1.9198949610721273e-07,
354
+ "logits/chosen": 0.11089984327554703,
355
+ "logits/rejected": 0.18088462948799133,
356
+ "logps/chosen": -183.67636108398438,
357
+ "logps/rejected": -146.19009399414062,
358
+ "loss": 0.0015,
359
+ "rewards/accuracies": 0.46875,
360
+ "rewards/chosen": 0.0020343190990388393,
361
+ "rewards/margins": 0.0024411864578723907,
362
+ "rewards/rejected": -0.00040686698048375547,
363
+ "step": 220
364
+ },
365
+ {
366
+ "epoch": 3.68,
367
+ "learning_rate": 7.994965069994143e-08,
368
+ "logits/chosen": 0.15200337767601013,
369
+ "logits/rejected": 0.0883503332734108,
370
+ "logps/chosen": -152.91159057617188,
371
+ "logps/rejected": -137.67068481445312,
372
+ "loss": 0.0017,
373
+ "rewards/accuracies": 0.4437499940395355,
374
+ "rewards/chosen": -0.0002739583433140069,
375
+ "rewards/margins": 0.00024719498469494283,
376
+ "rewards/rejected": -0.0005211535608395934,
377
+ "step": 230
378
+ },
379
+ {
380
+ "epoch": 3.84,
381
+ "learning_rate": 1.5860623616664183e-08,
382
+ "logits/chosen": 0.21818551421165466,
383
+ "logits/rejected": 0.26517254114151,
384
+ "logps/chosen": -185.5134735107422,
385
+ "logps/rejected": -156.71102905273438,
386
+ "loss": 0.0018,
387
+ "rewards/accuracies": 0.3125,
388
+ "rewards/chosen": -0.0007516987388953567,
389
+ "rewards/margins": -0.001160649349913001,
390
+ "rewards/rejected": 0.0004089508147444576,
391
+ "step": 240
392
+ },
393
+ {
394
+ "epoch": 3.97,
395
+ "step": 248,
396
+ "total_flos": 0.0,
397
+ "train_loss": 0.0016499216942447088,
398
+ "train_runtime": 2661.6314,
399
+ "train_samples_per_second": 1.503,
400
+ "train_steps_per_second": 0.093
401
+ }
402
+ ],
403
+ "logging_steps": 10,
404
+ "max_steps": 248,
405
+ "num_input_tokens_seen": 0,
406
+ "num_train_epochs": 4,
407
+ "save_steps": 100,
408
+ "total_flos": 0.0,
409
+ "train_batch_size": 4,
410
+ "trial_name": null,
411
+ "trial_params": null
412
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c1ee57b26fed14ebe66da58ed00de6652648e41e701665e87137027009e9fac
3
+ size 5880
vocab.json ADDED
The diff for this file is too large to render. See raw diff