Hugging Face's logo

DUAL-GPO
/
phi-2-dpo-renew1

PEFT
TensorBoard
Safetensors
phi
alignment-handbook
Generated from Trainer
trl
dpo
custom_code
Model card Files Metrics Community
BraylonDash commited on
Commit
783733b
•
1 Parent(s): 96f63b1

Model save

Browse files
Files changed (8) 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. runs/Apr09_11-23-20_gpu4-119-5/events.out.tfevents.1712626138.gpu4-119-5.200164.0 +2 -2
  6. runs/Apr09_11-23-20_gpu4-119-5/events.out.tfevents.1712682927.gpu4-119-5.200164.1 +3 -0
  7. train_results.json +8 -0
  8. 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-dpo-renew1
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-dpo-renew1
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: 0.5780
22
+ - Rewards/chosen: -0.8278
23
+ - Rewards/rejected: -1.2811
24
+ - Rewards/accuracies: 0.6305
25
+ - Rewards/margins: 0.4532
26
+ - Logps/rejected: -371.9221
27
+ - Logps/chosen: -360.3287
28
+ - Logits/rejected: -0.0200
29
+ - Logits/chosen: -0.0541
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
+ | 0.6925 | 0.03 | 100 | 0.6928 | 0.0001 | -0.0008 | 0.4950 | 0.0008 | -243.8912 | -277.5416 | 1.0654 | 0.9728 |
65
+ | 0.6903 | 0.05 | 200 | 0.6900 | 0.0049 | -0.0015 | 0.5830 | 0.0064 | -243.9661 | -277.0526 | 1.0659 | 0.9732 |
66
+ | 0.682 | 0.08 | 300 | 0.6801 | 0.0215 | -0.0064 | 0.6055 | 0.0280 | -244.4588 | -275.3941 | 1.0974 | 1.0023 |
67
+ | 0.6574 | 0.1 | 400 | 0.6623 | -0.0453 | -0.1180 | 0.6055 | 0.0727 | -255.6189 | -282.0750 | 1.0541 | 0.9585 |
68
+ | 0.6262 | 0.13 | 500 | 0.6407 | -0.3256 | -0.4857 | 0.6045 | 0.1601 | -292.3858 | -310.1027 | 0.7972 | 0.7187 |
69
+ | 0.6441 | 0.16 | 600 | 0.6310 | -0.4984 | -0.7357 | 0.6040 | 0.2373 | -317.3828 | -327.3852 | 0.5041 | 0.4434 |
70
+ | 0.6238 | 0.18 | 700 | 0.6180 | -0.5136 | -0.7730 | 0.6175 | 0.2594 | -321.1137 | -328.9063 | 0.4768 | 0.4140 |
71
+ | 0.6022 | 0.21 | 800 | 0.6146 | -0.5608 | -0.8568 | 0.6095 | 0.2960 | -329.4937 | -333.6271 | 0.3469 | 0.2920 |
72
+ | 0.5893 | 0.24 | 900 | 0.6059 | -0.6665 | -1.0014 | 0.6170 | 0.3349 | -343.9540 | -344.1970 | 0.3136 | 0.2576 |
73
+ | 0.6435 | 0.26 | 1000 | 0.6007 | -0.5361 | -0.8713 | 0.6295 | 0.3352 | -330.9463 | -331.1562 | 0.3378 | 0.2766 |
74
+ | 0.5626 | 0.29 | 1100 | 0.5971 | -0.6841 | -1.0299 | 0.6195 | 0.3458 | -346.8068 | -345.9583 | 0.3416 | 0.2879 |
75
+ | 0.5319 | 0.31 | 1200 | 0.5971 | -0.8852 | -1.2896 | 0.6280 | 0.4044 | -372.7756 | -366.0687 | 0.1914 | 0.1477 |
76
+ | 0.5818 | 0.34 | 1300 | 0.5949 | -0.7178 | -1.1027 | 0.6315 | 0.3849 | -354.0860 | -349.3257 | 0.2165 | 0.1688 |
77
+ | 0.5981 | 0.37 | 1400 | 0.5936 | -0.6617 | -1.0257 | 0.6290 | 0.3641 | -346.3885 | -343.7120 | 0.1974 | 0.1465 |
78
+ | 0.5843 | 0.39 | 1500 | 0.5905 | -0.8861 | -1.3031 | 0.6335 | 0.4171 | -374.1299 | -366.1545 | 0.1004 | 0.0587 |
79
+ | 0.6283 | 0.42 | 1600 | 0.5882 | -0.7845 | -1.1706 | 0.6305 | 0.3860 | -360.8746 | -356.0013 | 0.2242 | 0.1738 |
80
+ | 0.5892 | 0.44 | 1700 | 0.5891 | -0.6741 | -1.0616 | 0.6310 | 0.3875 | -349.9719 | -344.9546 | 0.1718 | 0.1259 |
81
+ | 0.5821 | 0.47 | 1800 | 0.5856 | -0.8949 | -1.3353 | 0.6315 | 0.4404 | -377.3439 | -367.0341 | 0.1199 | 0.0761 |
82
+ | 0.6072 | 0.5 | 1900 | 0.5861 | -0.7180 | -1.1339 | 0.6270 | 0.4159 | -357.2063 | -349.3515 | 0.1237 | 0.0773 |
83
+ | 0.6338 | 0.52 | 2000 | 0.5852 | -0.7155 | -1.1277 | 0.6340 | 0.4122 | -356.5852 | -349.0984 | 0.0087 | -0.0301 |
84
+ | 0.5582 | 0.55 | 2100 | 0.5860 | -0.7383 | -1.1682 | 0.6340 | 0.4300 | -360.6402 | -351.3726 | -0.0229 | -0.0595 |
85
+ | 0.6103 | 0.58 | 2200 | 0.5821 | -0.9235 | -1.3855 | 0.6345 | 0.4620 | -382.3635 | -369.8921 | -0.0714 | -0.1065 |
86
+ | 0.5636 | 0.6 | 2300 | 0.5836 | -0.7656 | -1.2038 | 0.6335 | 0.4382 | -364.1970 | -354.1104 | -0.0481 | -0.0841 |
87
+ | 0.5846 | 0.63 | 2400 | 0.5804 | -0.8773 | -1.3343 | 0.6335 | 0.4570 | -377.2508 | -365.2781 | -0.0871 | -0.1200 |
88
+ | 0.5799 | 0.65 | 2500 | 0.5834 | -0.8420 | -1.3045 | 0.6340 | 0.4625 | -374.2641 | -361.7435 | -0.0576 | -0.0922 |
89
+ | 0.5565 | 0.68 | 2600 | 0.5810 | -0.8009 | -1.2549 | 0.6345 | 0.4540 | -369.3044 | -357.6355 | -0.0285 | -0.0643 |
90
+ | 0.5614 | 0.71 | 2700 | 0.5782 | -0.9522 | -1.4183 | 0.6325 | 0.4661 | -385.6433 | -372.7677 | -0.0358 | -0.0698 |
91
+ | 0.608 | 0.73 | 2800 | 0.5776 | -0.9378 | -1.3994 | 0.6360 | 0.4616 | -383.7585 | -371.3293 | -0.0229 | -0.0571 |
92
+ | 0.588 | 0.76 | 2900 | 0.5795 | -0.8330 | -1.2891 | 0.6345 | 0.4560 | -372.7224 | -360.8503 | -0.0442 | -0.0792 |
93
+ | 0.5324 | 0.79 | 3000 | 0.5807 | -0.7714 | -1.2134 | 0.6340 | 0.4420 | -365.1566 | -354.6904 | -0.0298 | -0.0648 |
94
+ | 0.6036 | 0.81 | 3100 | 0.5817 | -0.7454 | -1.1839 | 0.6360 | 0.4385 | -362.2076 | -352.0881 | -0.0359 | -0.0710 |
95
+ | 0.615 | 0.84 | 3200 | 0.5806 | -0.7630 | -1.2065 | 0.6330 | 0.4435 | -364.4670 | -353.8469 | -0.0295 | -0.0645 |
96
+ | 0.6211 | 0.86 | 3300 | 0.5794 | -0.7767 | -1.2207 | 0.6335 | 0.4439 | -365.8820 | -355.2186 | -0.0240 | -0.0585 |
97
+ | 0.535 | 0.89 | 3400 | 0.5777 | -0.8399 | -1.2929 | 0.6320 | 0.4530 | -373.1028 | -361.5366 | -0.0225 | -0.0558 |
98
+ | 0.5322 | 0.92 | 3500 | 0.5779 | -0.8260 | -1.2781 | 0.6335 | 0.4522 | -371.6272 | -360.1418 | -0.0210 | -0.0546 |
99
+ | 0.5527 | 0.94 | 3600 | 0.5780 | -0.8254 | -1.2779 | 0.6315 | 0.4525 | -371.6083 | -360.0847 | -0.0229 | -0.0565 |
100
+ | 0.5769 | 0.97 | 3700 | 0.5780 | -0.8286 | -1.2816 | 0.6315 | 0.4530 | -371.9745 | -360.4062 | -0.0225 | -0.0562 |
101
+ | 0.635 | 0.99 | 3800 | 0.5780 | -0.8268 | -1.2798 | 0.6300 | 0.4530 | -371.7967 | -360.2288 | -0.0237 | -0.0573 |
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 sha256:0de1f5130ef94fd83a18d3c07a29312ba9201c9578177cb38857fe7d821557b5
3
  size 167807296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:005328157354e64925da220715a1e9b06a187fbd2441be942ed88f64816bf06f
3
  size 167807296
all_results.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "eval_logits/chosen": -0.05413578823208809,
4
+ "eval_logits/rejected": -0.01999257504940033,
5
+ "eval_logps/chosen": -360.3287353515625,
6
+ "eval_logps/rejected": -371.92205810546875,
7
+ "eval_loss": 0.5779720544815063,
8
+ "eval_rewards/accuracies": 0.6305000185966492,
9
+ "eval_rewards/chosen": -0.8278191685676575,
10
+ "eval_rewards/margins": 0.4532422423362732,
11
+ "eval_rewards/rejected": -1.2810615301132202,
12
+ "eval_runtime": 545.1859,
13
+ "eval_samples": 2000,
14
+ "eval_samples_per_second": 3.668,
15
+ "eval_steps_per_second": 0.917,
16
+ "train_loss": 0.5976003442126336,
17
+ "train_runtime": 56244.0781,
18
+ "train_samples": 61135,
19
+ "train_samples_per_second": 1.087,
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": -0.05413578823208809,
4
+ "eval_logits/rejected": -0.01999257504940033,
5
+ "eval_logps/chosen": -360.3287353515625,
6
+ "eval_logps/rejected": -371.92205810546875,
7
+ "eval_loss": 0.5779720544815063,
8
+ "eval_rewards/accuracies": 0.6305000185966492,
9
+ "eval_rewards/chosen": -0.8278191685676575,
10
+ "eval_rewards/margins": 0.4532422423362732,
11
+ "eval_rewards/rejected": -1.2810615301132202,
12
+ "eval_runtime": 545.1859,
13
+ "eval_samples": 2000,
14
+ "eval_samples_per_second": 3.668,
15
+ "eval_steps_per_second": 0.917
16
+ }
runs/Apr09_11-23-20_gpu4-119-5/events.out.tfevents.1712626138.gpu4-119-5.200164.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca55648646e48b8fb2d46573bf7cf3f3035f716f459f0ce1ef5716a67d3adcc0
3
- size 274319
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dde4e512b2a452e4372f4053f58e4638cab415bf2089add211ceb9d3f0edc1ef
3
+ size 275941
runs/Apr09_11-23-20_gpu4-119-5/events.out.tfevents.1712682927.gpu4-119-5.200164.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76caabf4e9c45a63b1805a537c8e30877885dbfb4c2869e4d0d7a6e10900d29a
3
+ size 828
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 0.5976003442126336,
4
+ "train_runtime": 56244.0781,
5
+ "train_samples": 61135,
6
+ "train_samples_per_second": 1.087,
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