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
f4bd8c9
•
1 Parent(s): a11c741

Model save

Browse files
Files changed (9) hide show
  1. README.md +18 -18
  2. all_results.json +4 -4
  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/May10_12-22-14_n136-082-130/events.out.tfevents.1715315025.n136-082-130.295839.0 +2 -2
  7. train_results.json +4 -4
  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: 1.3947
19
- - Rewards/chosen: -2.4314
20
- - Rewards/rejected: -2.0023
21
- - Rewards/accuracies: 0.3867
22
- - Rewards/margins: -0.4292
23
- - Logps/rejected: -517.7516
24
- - Logps/chosen: -554.9180
25
- - Logits/rejected: -1.0823
26
- - Logits/chosen: -1.1239
27
 
28
  ## Model description
29
 
@@ -60,15 +60,15 @@ The following hyperparameters were used during training:
60
 
61
  | Training Loss | Epoch | Step | Logits/chosen | Logits/rejected | Logps/chosen | Logps/rejected | Validation Loss | Rewards/accuracies | Rewards/chosen | Rewards/margins | Rewards/rejected |
62
  |:-------------:|:-----:|:----:|:-------------:|:---------------:|:------------:|:--------------:|:---------------:|:------------------:|:--------------:|:---------------:|:----------------:|
63
- | 0.3047 | 0.1 | 100 | -2.4405 | -2.3863 | -361.0801 | -337.7748 | 0.8551 | 0.3203 | -0.4930 | -0.2905 | -0.2025 |
64
- | 0.1861 | 0.21 | 200 | -1.5418 | -1.5107 | -450.2716 | -421.0934 | 1.0495 | 0.3867 | -1.3850 | -0.3493 | -1.0357 |
65
- | 0.1608 | 0.31 | 300 | -1.4367 | -1.4022 | -454.9446 | -422.9684 | 1.0910 | 0.3945 | -1.4317 | -0.3772 | -1.0544 |
66
- | 0.1368 | 0.42 | 400 | -1.0538 | -1.0131 | -520.1699 | -479.6456 | 1.3010 | 0.4102 | -2.0839 | -0.4627 | -1.6212 |
67
- | 0.1364 | 0.52 | 500 | -1.6466 | -1.6090 | -470.0934 | -430.8614 | 1.1773 | 0.3711 | -1.5832 | -0.4498 | -1.1334 |
68
- | 0.1223 | 0.63 | 600 | 1.3206 | -2.2971 | -1.8297 | 0.4141 | -0.4674 | -500.4930 | -541.4883 | -1.1541 | -1.1880 |
69
- | 0.0971 | 0.73 | 700 | 1.4638 | -2.6554 | -2.1594 | 0.3906 | -0.4959 | -533.4667 | -577.3128 | -0.9392 | -0.9712 |
70
- | 0.1035 | 0.84 | 800 | 1.4475 | -2.5761 | -2.1538 | 0.3945 | -0.4222 | -532.9068 | -569.3817 | -0.8902 | -0.9232 |
71
- | 0.088 | 0.94 | 900 | 1.3947 | -2.4314 | -2.0023 | 0.3867 | -0.4292 | -517.7516 | -554.9180 | -1.0823 | -1.1239 |
72
 
73
 
74
  ### 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: 1.4971
19
+ - Rewards/chosen: -4.5102
20
+ - Rewards/rejected: -4.6591
21
+ - Rewards/accuracies: 0.5156
22
+ - Rewards/margins: 0.1490
23
+ - Logps/rejected: -753.6738
24
+ - Logps/chosen: -732.6489
25
+ - Logits/rejected: 1.5926
26
+ - Logits/chosen: 1.5057
27
 
28
  ## Model description
29
 
 
60
 
61
  | Training Loss | Epoch | Step | Logits/chosen | Logits/rejected | Logps/chosen | Logps/rejected | Validation Loss | Rewards/accuracies | Rewards/chosen | Rewards/margins | Rewards/rejected |
62
  |:-------------:|:-----:|:----:|:-------------:|:---------------:|:------------:|:--------------:|:---------------:|:------------------:|:--------------:|:---------------:|:----------------:|
63
+ | 0.2876 | 0.1 | 100 | -2.3965 | -2.3559 | -391.6134 | -394.6287 | 0.8317 | 0.4883 | -1.0998 | -0.0311 | -1.0687 |
64
+ | 0.1728 | 0.21 | 200 | -0.2344 | -0.1269 | -464.6779 | -471.8403 | 1.0232 | 0.4766 | -1.8304 | 0.0103 | -1.8408 |
65
+ | 0.1485 | 0.31 | 300 | -0.3320 | -0.2139 | -506.0840 | -508.1475 | 1.1085 | 0.4883 | -2.2445 | -0.0406 | -2.2039 |
66
+ | 0.1363 | 0.42 | 400 | -0.2901 | -0.1728 | -477.3530 | -486.5422 | 1.1616 | 0.4961 | -1.9572 | 0.0306 | -1.9878 |
67
+ | 0.1192 | 0.52 | 500 | 0.8077 | 0.8821 | -553.1240 | -562.3370 | 1.2602 | 0.4961 | -2.7149 | 0.0308 | -2.7458 |
68
+ | 0.1061 | 0.63 | 600 | 1.3570 | -3.5510 | -3.6801 | 0.5078 | 0.1291 | -655.7740 | -636.7335 | 1.4624 | 1.3499 |
69
+ | 0.0916 | 0.73 | 700 | 1.5923 | -4.9928 | -5.1535 | 0.5195 | 0.1607 | -803.1144 | -780.9122 | 1.8370 | 1.7244 |
70
+ | 0.0982 | 0.84 | 800 | 1.4367 | -4.1982 | -4.3446 | 0.5117 | 0.1464 | -722.2228 | -701.4560 | 1.5885 | 1.4960 |
71
+ | 0.0798 | 0.94 | 900 | 1.4971 | -4.5102 | -4.6591 | 0.5156 | 0.1490 | -753.6738 | -732.6489 | 1.5926 | 1.5057 |
72
 
73
 
74
  ### Framework versions
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 1.0,
3
- "train_loss": 0.05187356284775659,
4
- "train_runtime": 7314.4586,
5
  "train_samples": 122268,
6
- "train_samples_per_second": 16.716,
7
- "train_steps_per_second": 0.131
8
  }
 
1
  {
2
  "epoch": 1.0,
3
+ "train_loss": 0.04742721384732511,
4
+ "train_runtime": 7350.5302,
5
  "train_samples": 122268,
6
+ "train_samples_per_second": 16.634,
7
+ "train_steps_per_second": 0.13
8
  }
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:938e0d524d2c5b738205f45cbd32d084ef09b48fc55b42d2357ec2767acdf6c6
3
  size 4943178720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd0d1884a8b45d0de1e90c92985f8203fb2783935e71bdd96bd796f278e035d6
3
  size 4943178720
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1ec78470671379c923d72d3be323be44ae390376154e5d9fd23e55a6f9be5d44
3
  size 4999819336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:558503735ec0abd267f67456472c8c72174e08e0fd01a475d9d1eb983c4283b8
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:e68bdcd164f3a46f36753fb22642732b303167d2c92a5668db1be3f302bf4b44
3
  size 4540532728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95eef01440ee3fb063a713d4575231456ee2001b5ff7505be8157f14ddf6e624
3
  size 4540532728
runs/May10_12-22-14_n136-082-130/events.out.tfevents.1715315025.n136-082-130.295839.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:57763e6fcf1cc1927663571df3f33fec8e1518271dcb302468d320e4a924d3bf
3
- size 35395
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c13d588efda433465f94acfdafa33e3d9868bfd9011d3edcc521950ee2b60339
3
+ size 39189
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 1.0,
3
- "train_loss": 0.05187356284775659,
4
- "train_runtime": 7314.4586,
5
  "train_samples": 122268,
6
- "train_samples_per_second": 16.716,
7
- "train_steps_per_second": 0.131
8
  }
 
1
  {
2
  "epoch": 1.0,
3
+ "train_loss": 0.04742721384732511,
4
+ "train_runtime": 7350.5302,
5
  "train_samples": 122268,
6
+ "train_samples_per_second": 16.634,
7
+ "train_steps_per_second": 0.13
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 sha256:5ee00489c1463fae472326de1af05f14960d5729e1f2cab6ea21d656cab52f1b
3
  size 6264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:291902e71a2a4585a72bed7e38f885273985e04787086b5e9c772897150379c6
3
  size 6264