Hugging Face's logo

RikkiXu
/
zephyr-7b-dpo-full

Text Generation
Transformers
TensorBoard
Safetensors
mistral
trl
dpo
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
RikkiXu commited on
Commit
6f9ad2c
•
1 Parent(s): eb7e456

Model save

Browse files
Files changed (9) hide show
  1. README.md +22 -22
  2. all_results.json +3 -3
  3. model-00001-of-00003.safetensors +1 -1
  4. model-00002-of-00003.safetensors +1 -1
  5. model-00003-of-00003.safetensors +1 -1
  6. runs/May17_14-57-56_n136-100-194/events.out.tfevents.1715930027.n136-100-194.4076912.0 +2 -2
  7. train_results.json +3 -3
  8. trainer_state.json +0 -0
  9. training_args.bin +2 -2
README.md CHANGED
@@ -15,15 +15,15 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model was trained from scratch on the None dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.5418
19
- - Rewards/chosen: -3.1726
20
- - Rewards/rejected: -4.7390
21
- - Rewards/accuracies: 0.7539
22
- - Rewards/margins: 1.5664
23
- - Logps/rejected: -761.6608
24
- - Logps/chosen: -598.8974
25
- - Logits/rejected: 0.2389
26
- - Logits/chosen: -0.0634
27
 
28
  ## Model description
29
 
@@ -60,19 +60,19 @@ The following hyperparameters were used during training:
60
 
61
  | Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
62
  |:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
63
- | 0.6142 | 0.07 | 100 | 0.6372 | -0.2112 | -0.4255 | 0.6992 | 0.2143 | -330.3116 | -302.7545 | -1.7521 | -1.7871 |
64
- | 0.4726 | 0.15 | 200 | 0.5516 | -1.3441 | -2.1046 | 0.75 | 0.7605 | -498.2208 | -416.0410 | -2.0018 | -2.0471 |
65
- | 0.4421 | 0.22 | 300 | 0.5335 | -1.1470 | -2.0463 | 0.7539 | 0.8992 | -492.3901 | -396.3379 | -1.7522 | -1.8325 |
66
- | 0.3828 | 0.3 | 400 | 0.5238 | -1.6652 | -2.7617 | 0.7695 | 1.0965 | -563.9280 | -448.1488 | -0.9530 | -1.1204 |
67
- | 0.3576 | 0.37 | 500 | 0.5184 | -1.6238 | -2.7277 | 0.7695 | 1.1039 | -560.5328 | -444.0173 | -0.8922 | -1.1202 |
68
- | 0.3328 | 0.45 | 600 | 0.5151 | -2.1202 | -3.4092 | 0.7656 | 1.2890 | -628.6859 | -493.6552 | 0.2423 | -0.0694 |
69
- | 0.3131 | 0.52 | 700 | 0.5153 | -1.7034 | -2.9038 | 0.7656 | 1.2004 | -578.1398 | -451.9696 | 0.1729 | -0.1656 |
70
- | 0.2547 | 0.59 | 800 | 0.5256 | -2.5366 | -3.8570 | 0.7617 | 1.3204 | -673.4565 | -535.2915 | 0.4476 | 0.1270 |
71
- | 0.2764 | 0.67 | 900 | 0.5221 | -2.5675 | -3.9457 | 0.7773 | 1.3782 | -682.3342 | -538.3813 | 0.0520 | -0.2431 |
72
- | 0.2261 | 0.74 | 1000 | 0.5298 | -2.7657 | -4.2499 | 0.7695 | 1.4842 | -712.7483 | -558.2006 | 0.2023 | -0.1104 |
73
- | 0.2219 | 0.82 | 1100 | 0.5380 | -3.0986 | -4.6646 | 0.7695 | 1.5660 | -754.2211 | -591.4904 | 0.3078 | -0.0067 |
74
- | 0.2165 | 0.89 | 1200 | 0.5336 | -2.9855 | -4.5026 | 0.7617 | 1.5170 | -738.0179 | -580.1855 | 0.2015 | -0.0980 |
75
- | 0.1728 | 0.97 | 1300 | 0.5418 | -3.1726 | -4.7390 | 0.7539 | 1.5664 | -761.6608 | -598.8974 | 0.2389 | -0.0634 |
76
 
77
 
78
  ### Framework versions
 
15
 
16
  This model was trained from scratch on the None dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.5366
19
+ - Rewards/chosen: -2.9738
20
+ - Rewards/rejected: -4.4991
21
+ - Rewards/accuracies: 0.7617
22
+ - Rewards/margins: 1.5252
23
+ - Logps/rejected: -767.4317
24
+ - Logps/chosen: -609.1594
25
+ - Logits/rejected: 1.6095
26
+ - Logits/chosen: 0.9559
27
 
28
  ## Model description
29
 
 
60
 
61
  | Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
62
  |:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
63
+ | 0.5905 | 0.07 | 100 | 0.6429 | -0.1380 | -0.3441 | 0.6719 | 0.2061 | -351.9318 | -325.5744 | -1.7244 | -1.7878 |
64
+ | 0.4495 | 0.15 | 200 | 0.5600 | -0.4940 | -1.0973 | 0.7461 | 0.6032 | -427.2510 | -361.1815 | -1.3665 | -1.4371 |
65
+ | 0.3963 | 0.22 | 300 | 0.5291 | -1.1123 | -2.0359 | 0.7422 | 0.9236 | -521.1155 | -423.0034 | -1.2770 | -1.4609 |
66
+ | 0.4012 | 0.3 | 400 | 0.5315 | -1.0588 | -1.9923 | 0.7734 | 0.9334 | -516.7505 | -417.6586 | -1.1223 | -1.3373 |
67
+ | 0.3559 | 0.37 | 500 | 0.5276 | -1.4423 | -2.5146 | 0.7578 | 1.0723 | -568.9822 | -456.0086 | -0.6834 | -1.0067 |
68
+ | 0.3291 | 0.45 | 600 | 0.5103 | -1.6617 | -2.7811 | 0.7695 | 1.1194 | -595.6332 | -477.9445 | 0.1886 | -0.2334 |
69
+ | 0.2735 | 0.52 | 700 | 0.5289 | -2.2950 | -3.7006 | 0.7617 | 1.4056 | -687.5872 | -541.2795 | 0.6722 | 0.1870 |
70
+ | 0.2752 | 0.59 | 800 | 0.5229 | -2.2134 | -3.5070 | 0.7656 | 1.2935 | -668.2236 | -533.1202 | 0.2752 | -0.1628 |
71
+ | 0.2492 | 0.67 | 900 | 0.5152 | -2.0646 | -3.3529 | 0.7734 | 1.2882 | -652.8116 | -518.2382 | 1.0726 | 0.5184 |
72
+ | 0.262 | 0.74 | 1000 | 0.5241 | -2.4505 | -3.8564 | 0.7617 | 1.4059 | -703.1603 | -556.8265 | 1.3124 | 0.6805 |
73
+ | 0.2299 | 0.82 | 1100 | 0.5313 | -2.7647 | -4.2433 | 0.7578 | 1.4786 | -741.8574 | -588.2495 | 1.4834 | 0.8391 |
74
+ | 0.1974 | 0.89 | 1200 | 0.5367 | -2.9484 | -4.4713 | 0.7617 | 1.5229 | -764.6512 | -606.6174 | 1.5458 | 0.8964 |
75
+ | 0.1842 | 0.97 | 1300 | 0.5366 | -2.9738 | -4.4991 | 0.7617 | 1.5252 | -767.4317 | -609.1594 | 1.6095 | 0.9559 |
76
 
77
 
78
  ### Framework versions
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 1.0,
3
- "train_loss": 0.3438705863959722,
4
- "train_runtime": 21850.8794,
5
  "train_samples": 172268,
6
- "train_samples_per_second": 7.884,
7
  "train_steps_per_second": 0.062
8
  }
 
1
  {
2
  "epoch": 1.0,
3
+ "train_loss": 0.335402155391883,
4
+ "train_runtime": 21644.3608,
5
  "train_samples": 172268,
6
+ "train_samples_per_second": 7.959,
7
  "train_steps_per_second": 0.062
8
  }
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dd6ded02da6ed2a67b1ccb05b3e25c1a08de70168c93e24452883b16a331d860
3
  size 4943178720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9f836055bbd8c90fff82b466785b3c0bb773e39b03a40c15c13a2e943087d51
3
  size 4943178720
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:89ce8ea846a3d7c9e49af7bf0cabce9bf61d2357db44c6a45bf678e5f26f2442
3
  size 4999819336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb1b6c8b26fd22edeb102b325e8c1fbfb5a31ab5cd157cb8b276c563db6e9c41
3
  size 4999819336
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6fd7ad7a8a30cf5d12237b54b2b2736d530ebb352c2b25a8a564e6dd23102581
3
  size 4540532728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:959b85a59ee4907acea070d073fd679eee4438a9f246c343a20944bc8cecd8c7
3
  size 4540532728
runs/May17_14-57-56_n136-100-194/events.out.tfevents.1715930027.n136-100-194.4076912.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9fef9caf1b1ec4f3fe749967e8892b92238853f89e0ab970a9ba1865fa9a1532
3
- size 104443
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b360ec29705dac95256bbf377f3b2e33f5187a31f2a6fb46a20456d52033f914
3
+ size 107549
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 1.0,
3
- "train_loss": 0.3438705863959722,
4
- "train_runtime": 21850.8794,
5
  "train_samples": 172268,
6
- "train_samples_per_second": 7.884,
7
  "train_steps_per_second": 0.062
8
  }
 
1
  {
2
  "epoch": 1.0,
3
+ "train_loss": 0.335402155391883,
4
+ "train_runtime": 21644.3608,
5
  "train_samples": 172268,
6
+ "train_samples_per_second": 7.959,
7
  "train_steps_per_second": 0.062
8
  }
trainer_state.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c0caf9fbe23969e1c8a215e53c1fd063c17f339e7fb0eda9b65ed88e2360b089
3
- size 6200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e502af158ed3a6fabdbc5ad5001d9718cbe7ad4aeeca45d421c1857817025938
3
+ size 6264