Hugging Face's logo

DUAL-GPO
/
phi-2-gpo-renew2-b0.001-log-i0

PEFT
Safetensors
phi
alignment-handbook
Generated from Trainer
trl
dpo
custom_code
Model card Files Community
BraylonDash commited on
Commit
d49272b
•
1 Parent(s): 6f83aa8

Model save

Browse files
Files changed (6) hide show
  1. README.md +110 -0
  2. adapter_model.safetensors +1 -1
  3. all_results.json +21 -0
  4. eval_results.json +16 -0
  5. train_results.json +8 -0
  6. trainer_state.json +0 -0
README.md ADDED
@@ -0,0 +1,110 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-renew2-b0.001-log-i0
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-renew2-b0.001-log-i0
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: 0.0367
22
+ - Rewards/chosen: -0.0859
23
+ - Rewards/rejected: -0.1297
24
+ - Rewards/accuracies: 0.6335
25
+ - Rewards/margins: 0.0439
26
+ - Logps/rejected: -373.5459
27
+ - Logps/chosen: -363.4243
28
+ - Logits/rejected: 0.0915
29
+ - Logits/chosen: 0.0487
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: 1
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
+ | 0.066 | 0.03 | 100 | 0.0537 | -0.0000 | -0.0001 | 0.4725 | 0.0000 | -243.8812 | -277.5782 | 1.0637 | 0.9712 |
65
+ | 0.0611 | 0.05 | 200 | 0.0535 | 0.0003 | -0.0002 | 0.5780 | 0.0005 | -243.9921 | -277.2496 | 1.0643 | 0.9716 |
66
+ | 0.0609 | 0.08 | 300 | 0.0529 | 0.0015 | -0.0005 | 0.6165 | 0.0020 | -244.3336 | -276.0178 | 1.0636 | 0.9689 |
67
+ | 0.0513 | 0.1 | 400 | 0.0511 | -0.0031 | -0.0095 | 0.6150 | 0.0064 | -253.2858 | -280.6138 | 0.9583 | 0.8601 |
68
+ | 0.0501 | 0.13 | 500 | 0.0475 | -0.0293 | -0.0455 | 0.6050 | 0.0162 | -289.3190 | -306.8101 | 0.5770 | 0.4970 |
69
+ | 0.0508 | 0.16 | 600 | 0.0449 | -0.0439 | -0.0691 | 0.6055 | 0.0252 | -312.9566 | -321.4783 | 0.3282 | 0.2749 |
70
+ | 0.0421 | 0.18 | 700 | 0.0437 | -0.0501 | -0.0791 | 0.6055 | 0.0290 | -322.8759 | -327.6276 | 0.3240 | 0.2708 |
71
+ | 0.0437 | 0.21 | 800 | 0.0428 | -0.0468 | -0.0742 | 0.6005 | 0.0274 | -318.0196 | -324.3805 | 0.3805 | 0.3236 |
72
+ | 0.0387 | 0.24 | 900 | 0.0423 | -0.0603 | -0.0976 | 0.6055 | 0.0373 | -341.3827 | -337.8515 | 0.2503 | 0.1997 |
73
+ | 0.0469 | 0.26 | 1000 | 0.0410 | -0.0415 | -0.0745 | 0.6120 | 0.0330 | -318.2856 | -319.0327 | 0.3303 | 0.2683 |
74
+ | 0.0405 | 0.29 | 1100 | 0.0413 | -0.0604 | -0.0953 | 0.6065 | 0.0350 | -339.1555 | -337.9239 | 0.3569 | 0.3022 |
75
+ | 0.0532 | 0.31 | 1200 | 0.0414 | -0.0616 | -0.1042 | 0.6150 | 0.0426 | -347.9869 | -339.1231 | 0.1742 | 0.1261 |
76
+ | 0.0421 | 0.34 | 1300 | 0.0401 | -0.0362 | -0.0677 | 0.6240 | 0.0316 | -311.5635 | -313.6982 | 0.3279 | 0.2688 |
77
+ | 0.0454 | 0.37 | 1400 | 0.0401 | -0.0665 | -0.1024 | 0.6130 | 0.0359 | -346.2302 | -344.0237 | 0.2565 | 0.2034 |
78
+ | 0.03 | 0.39 | 1500 | 0.0394 | -0.0809 | -0.1233 | 0.6185 | 0.0424 | -367.0958 | -358.4021 | 0.2512 | 0.1958 |
79
+ | 0.0455 | 0.42 | 1600 | 0.0390 | -0.0528 | -0.0864 | 0.6220 | 0.0336 | -330.2539 | -330.3630 | 0.3432 | 0.2802 |
80
+ | 0.0444 | 0.44 | 1700 | 0.0383 | -0.0576 | -0.0957 | 0.6215 | 0.0381 | -339.5015 | -335.1629 | 0.1956 | 0.1433 |
81
+ | 0.0411 | 0.47 | 1800 | 0.0391 | -0.0864 | -0.1297 | 0.6165 | 0.0433 | -373.5191 | -363.9651 | 0.1143 | 0.0721 |
82
+ | 0.0486 | 0.5 | 1900 | 0.0382 | -0.0792 | -0.1204 | 0.6260 | 0.0412 | -364.1853 | -356.7109 | 0.1764 | 0.1298 |
83
+ | 0.0378 | 0.52 | 2000 | 0.0378 | -0.0642 | -0.1013 | 0.6290 | 0.0371 | -345.1359 | -341.7246 | 0.1294 | 0.0808 |
84
+ | 0.0316 | 0.55 | 2100 | 0.0375 | -0.0770 | -0.1185 | 0.6275 | 0.0414 | -362.2671 | -354.5952 | 0.0687 | 0.0245 |
85
+ | 0.0375 | 0.58 | 2200 | 0.0376 | -0.0825 | -0.1250 | 0.6280 | 0.0425 | -368.8188 | -360.0626 | 0.0391 | 0.0007 |
86
+ | 0.0344 | 0.6 | 2300 | 0.0376 | -0.0705 | -0.1082 | 0.6315 | 0.0377 | -351.9891 | -348.0063 | 0.1002 | 0.0554 |
87
+ | 0.0393 | 0.63 | 2400 | 0.0374 | -0.0839 | -0.1244 | 0.6330 | 0.0404 | -368.2057 | -361.4958 | 0.0124 | -0.0271 |
88
+ | 0.0501 | 0.65 | 2500 | 0.0373 | -0.0970 | -0.1420 | 0.6265 | 0.0450 | -385.8456 | -374.5688 | 0.0053 | -0.0307 |
89
+ | 0.03 | 0.68 | 2600 | 0.0372 | -0.0948 | -0.1408 | 0.6280 | 0.0460 | -384.5748 | -372.3464 | 0.0325 | -0.0064 |
90
+ | 0.0445 | 0.71 | 2700 | 0.0372 | -0.0927 | -0.1378 | 0.6255 | 0.0450 | -381.6031 | -370.2887 | 0.0394 | -0.0008 |
91
+ | 0.0359 | 0.73 | 2800 | 0.0369 | -0.0822 | -0.1244 | 0.6375 | 0.0422 | -368.1677 | -359.7133 | 0.0926 | 0.0476 |
92
+ | 0.0454 | 0.76 | 2900 | 0.0368 | -0.0861 | -0.1308 | 0.6340 | 0.0447 | -374.6195 | -363.6591 | 0.0788 | 0.0362 |
93
+ | 0.0422 | 0.79 | 3000 | 0.0368 | -0.0872 | -0.1317 | 0.6350 | 0.0445 | -375.5086 | -364.7430 | 0.0778 | 0.0354 |
94
+ | 0.0401 | 0.81 | 3100 | 0.0368 | -0.0844 | -0.1284 | 0.6350 | 0.0440 | -372.1985 | -361.9238 | 0.0778 | 0.0345 |
95
+ | 0.0455 | 0.84 | 3200 | 0.0368 | -0.0842 | -0.1275 | 0.6335 | 0.0434 | -371.3240 | -361.7043 | 0.0871 | 0.0436 |
96
+ | 0.0537 | 0.86 | 3300 | 0.0368 | -0.0820 | -0.1248 | 0.6350 | 0.0428 | -368.5755 | -359.5146 | 0.0936 | 0.0492 |
97
+ | 0.0415 | 0.89 | 3400 | 0.0367 | -0.0845 | -0.1281 | 0.6365 | 0.0436 | -371.9387 | -362.0815 | 0.0925 | 0.0492 |
98
+ | 0.0399 | 0.92 | 3500 | 0.0367 | -0.0853 | -0.1290 | 0.6325 | 0.0437 | -372.8227 | -362.8265 | 0.0937 | 0.0507 |
99
+ | 0.0386 | 0.94 | 3600 | 0.0367 | -0.0855 | -0.1294 | 0.6330 | 0.0438 | -373.1803 | -363.0746 | 0.0909 | 0.0479 |
100
+ | 0.0372 | 0.97 | 3700 | 0.0367 | -0.0859 | -0.1297 | 0.6375 | 0.0438 | -373.5262 | -363.4134 | 0.0910 | 0.0480 |
101
+ | 0.033 | 0.99 | 3800 | 0.0367 | -0.0858 | -0.1297 | 0.6325 | 0.0439 | -373.5426 | -363.3738 | 0.0911 | 0.0481 |
102
+
103
+
104
+ ### Framework versions
105
+
106
+ - PEFT 0.7.1
107
+ - Transformers 4.36.2
108
+ - Pytorch 2.1.2
109
+ - Datasets 2.14.6
110
+ - Tokenizers 0.15.2
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f07abf5e1b8f166b54a4114fad4a6dad64b6a3b38ad5eac5d33fbb4d7c703b8d
3
  size 167807296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f78c5b21f37eaebd21af6669aecf20ddfbdbaeaefd301c3599acc9a28b0b3314
3
  size 167807296
all_results.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "eval_logits/chosen": 0.04874047264456749,
4
+ "eval_logits/rejected": 0.09153472632169724,
5
+ "eval_logps/chosen": -363.42431640625,
6
+ "eval_logps/rejected": -373.5458984375,
7
+ "eval_loss": 0.036668241024017334,
8
+ "eval_rewards/accuracies": 0.6334999799728394,
9
+ "eval_rewards/chosen": -0.08587750047445297,
10
+ "eval_rewards/margins": 0.04385250434279442,
11
+ "eval_rewards/rejected": -0.1297300010919571,
12
+ "eval_runtime": 545.8695,
13
+ "eval_samples": 2000,
14
+ "eval_samples_per_second": 3.664,
15
+ "eval_steps_per_second": 0.916,
16
+ "train_loss": 0.04185271042490998,
17
+ "train_runtime": 56342.1754,
18
+ "train_samples": 61135,
19
+ "train_samples_per_second": 1.085,
20
+ "train_steps_per_second": 0.068
21
+ }
eval_results.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "eval_logits/chosen": 0.04874047264456749,
4
+ "eval_logits/rejected": 0.09153472632169724,
5
+ "eval_logps/chosen": -363.42431640625,
6
+ "eval_logps/rejected": -373.5458984375,
7
+ "eval_loss": 0.036668241024017334,
8
+ "eval_rewards/accuracies": 0.6334999799728394,
9
+ "eval_rewards/chosen": -0.08587750047445297,
10
+ "eval_rewards/margins": 0.04385250434279442,
11
+ "eval_rewards/rejected": -0.1297300010919571,
12
+ "eval_runtime": 545.8695,
13
+ "eval_samples": 2000,
14
+ "eval_samples_per_second": 3.664,
15
+ "eval_steps_per_second": 0.916
16
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 0.04185271042490998,
4
+ "train_runtime": 56342.1754,
5
+ "train_samples": 61135,
6
+ "train_samples_per_second": 1.085,
7
+ "train_steps_per_second": 0.068
8
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff