Hugging Face's logo

RikkiXu
/
zephyr-7b-dpo-full

Text Generation
Transformers
TensorBoard
Safetensors
mistral
trl
dpo
Generated from Trainer
conversational
Inference Endpoints
text-generation-inference
Model card Files Metrics Community
RikkiXu commited on
Commit
f06080f
•
1 Parent(s): bc713ae

Model save

Browse files
Files changed (9) hide show
  1. README.md +17 -22
  2. all_results.json +5 -5
  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/May20_00-19-57_n136-100-194/events.out.tfevents.1716136109.n136-100-194.871503.0 +2 -2
  7. train_results.json +5 -5
  8. trainer_state.json +0 -0
  9. training_args.bin +1 -1
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: 0.5366
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
 
@@ -60,19 +60,14 @@ 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
- | 0.5905 | 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
 
15
 
16
  This model was trained from scratch on the None dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.4283
19
+ - Rewards/chosen: -1.4066
20
+ - Rewards/rejected: -2.3431
21
+ - Rewards/accuracies: 0.8594
22
+ - Rewards/margins: 0.9365
23
+ - Logps/rejected: -567.4185
24
+ - Logps/chosen: -476.1736
25
+ - Logits/rejected: 0.8733
26
+ - Logits/chosen: 0.3446
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
+ | 0.5295 | 0.12 | 100 | 0.6076 | -0.4310 | -0.7253 | 0.6992 | 0.2943 | -405.6328 | -378.6121 | -1.6941 | -1.7860 |
64
+ | 0.436 | 0.23 | 200 | 0.5481 | -1.0281 | -1.5447 | 0.7578 | 0.5166 | -487.5739 | -438.3181 | -0.9160 | -1.0564 |
65
+ | 0.4266 | 0.35 | 300 | 0.4992 | -1.6631 | -2.4082 | 0.8086 | 0.7450 | -573.9229 | -501.8244 | -0.0079 | -0.2921 |
66
+ | 0.3779 | 0.46 | 400 | 0.4760 | -1.5291 | -2.2881 | 0.8164 | 0.7591 | -561.9199 | -488.4168 | 0.0913 | -0.2997 |
67
+ | 0.3713 | 0.58 | 500 | 0.4527 | -1.3552 | -2.2406 | 0.8320 | 0.8854 | -557.1675 | -471.0288 | 0.4886 | 0.0541 |
68
+ | 0.3817 | 0.69 | 600 | 0.4398 | -1.5276 | -2.4352 | 0.8516 | 0.9076 | -576.6248 | -488.2740 | 0.9378 | 0.4596 |
69
+ | 0.3613 | 0.81 | 700 | 0.4308 | -1.4716 | -2.3968 | 0.8711 | 0.9252 | -572.7809 | -482.6695 | 0.9228 | 0.4112 |
70
+ | 0.4032 | 0.92 | 800 | 0.4283 | -1.4066 | -2.3431 | 0.8594 | 0.9365 | -567.4185 | -476.1736 | 0.8733 | 0.3446 |
 
 
 
 
 
71
 
72
 
73
  ### Framework versions
all_results.json CHANGED
@@ -1,8 +1,8 @@
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
  }
 
1
  {
2
  "epoch": 1.0,
3
+ "train_loss": 0.42703192135156026,
4
+ "train_runtime": 13837.373,
5
+ "train_samples": 111134,
6
+ "train_samples_per_second": 8.031,
7
+ "train_steps_per_second": 0.063
8
  }
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e9f836055bbd8c90fff82b466785b3c0bb773e39b03a40c15c13a2e943087d51
3
  size 4943178720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d79be581ca4db04064a86c601510c713774b5d2212defedb547ca5140a1ea938
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:bb1b6c8b26fd22edeb102b325e8c1fbfb5a31ab5cd157cb8b276c563db6e9c41
3
  size 4999819336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cc6378b4ecc04b565b7ba5c0687c590bc3ce5d97bdac059d5b1bd176ba33a5f
3
  size 4999819336
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:959b85a59ee4907acea070d073fd679eee4438a9f246c343a20944bc8cecd8c7
3
  size 4540532728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d04242828ce6ba6f2d64d16aab8c8df98c4aaff7c486dd771a5797817ba55cb8
3
  size 4540532728
runs/May20_00-19-57_n136-100-194/events.out.tfevents.1716136109.n136-100-194.871503.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1ddcff838e03a8db37bc2080e67cdd23837c45705161072a7e8d5148878862e6
3
- size 66367
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88c8fb39162a1e0c31e5142469d7bf7b5d760cdb3f5b5438d73da6a3db9e076d
3
+ size 70849
train_results.json CHANGED
@@ -1,8 +1,8 @@
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
  }
 
1
  {
2
  "epoch": 1.0,
3
+ "train_loss": 0.42703192135156026,
4
+ "train_runtime": 13837.373,
5
+ "train_samples": 111134,
6
+ "train_samples_per_second": 8.031,
7
+ "train_steps_per_second": 0.063
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 sha256:3077373225b1a919a01dd0dd5247b886bff39d3d7ce4c7bf8dd5920f3b027fe1
3
  size 6264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ad993e59763b6deb1a45e1763f37981a00bcfe17b4c33793e0c48bbe37f3f7a
3
  size 6264