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
2de7880
•
1 Parent(s): 48fc934

Model save

Browse files
Files changed (10) hide show
  1. README.md +16 -26
  2. all_results.json +5 -5
  3. config.json +1 -1
  4. model-00001-of-00003.safetensors +1 -1
  5. model-00002-of-00003.safetensors +1 -1
  6. model-00003-of-00003.safetensors +1 -1
  7. tokenizer.json +0 -1
  8. train_results.json +5 -5
  9. trainer_state.json +0 -0
  10. training_args.bin +1 -1
README.md CHANGED
@@ -17,15 +17,15 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.6824
21
- - Rewards/chosen: -4.2277
22
- - Rewards/rejected: -7.2864
23
- - Rewards/accuracies: 0.7773
24
- - Rewards/margins: 3.0587
25
- - Logps/rejected: -408.3961
26
- - Logps/chosen: -347.1476
27
- - Logits/rejected: -0.8310
28
- - Logits/chosen: -1.2135
29
 
30
  ## Model description
31
 
@@ -56,26 +56,16 @@ The following hyperparameters were used during training:
56
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
57
  - lr_scheduler_type: cosine
58
  - lr_scheduler_warmup_ratio: 0.1
59
- - num_epochs: 3
60
 
61
  ### Training results
62
 
63
- | Training Loss | Epoch | Step | Logits/chosen | Logits/rejected | Logps/chosen | Logps/rejected | Validation Loss | Rewards/accuracies | Rewards/chosen | Rewards/margins | Rewards/rejected |
64
- |:-------------:|:-----:|:----:|:-------------:|:---------------:|:------------:|:--------------:|:---------------:|:------------------:|:--------------:|:---------------:|:----------------:|
65
- | 0.582 | 0.21 | 100 | -2.5812 | -2.5431 | -254.2386 | -263.2876 | 0.5878 | 0.7188 | 0.4177 | 0.4488 | -0.0310 |
66
- | 0.558 | 0.42 | 200 | -2.3893 | -2.3398 | -261.4734 | -280.4191 | 0.5196 | 0.7773 | 0.0560 | 0.9436 | -0.8876 |
67
- | 0.4914 | 0.63 | 300 | -2.3653 | -2.3039 | -264.2936 | -286.6201 | 0.5110 | 0.7656 | -0.0850 | 1.1126 | -1.1976 |
68
- | 0.4922 | 0.84 | 400 | -2.3145 | -2.2570 | -263.2854 | -285.4248 | 0.5095 | 0.7852 | -0.0346 | 1.1033 | -1.1379 |
69
- | 0.1908 | 1.05 | 500 | -2.2442 | -2.1660 | -269.8426 | -300.6474 | 0.5179 | 0.7852 | -0.3625 | 1.5366 | -1.8990 |
70
- | 0.1675 | 1.26 | 600 | -2.2220 | -2.1249 | -287.2300 | -324.0812 | 0.5377 | 0.8008 | -1.2318 | 1.8389 | -3.0707 |
71
- | 0.1567 | 1.46 | 700 | -2.0453 | -1.9285 | -298.7820 | -333.3354 | 0.5348 | 0.7891 | -1.8094 | 1.7240 | -3.5334 |
72
- | 0.1475 | 1.67 | 800 | -2.2409 | -2.1202 | -296.3533 | -332.4951 | 0.5382 | 0.8008 | -1.6880 | 1.8034 | -3.4914 |
73
- | 0.1422 | 1.88 | 900 | -2.1980 | -2.0630 | -296.0324 | -335.6016 | 0.5518 | 0.7852 | -1.6719 | 1.9748 | -3.6467 |
74
- | 0.044 | 2.09 | 1000 | -1.7406 | -1.4629 | -316.4520 | -365.4959 | 0.6058 | 0.7891 | -2.6929 | 2.4485 | -5.1414 |
75
- | 0.0307 | 2.3 | 1100 | -1.3310 | -0.9162 | -337.0383 | -397.1617 | 0.6700 | 0.7695 | -3.7222 | 3.0025 | -6.7247 |
76
- | 0.0317 | 2.51 | 1200 | 0.6711 | -3.9616 | -6.9639 | 0.7773 | 3.0023 | -401.9448 | -341.8261 | -0.9227 | -1.2927 |
77
- | 0.0264 | 2.72 | 1300 | 0.6778 | -4.2314 | -7.2584 | 0.7773 | 3.0270 | -407.8352 | -347.2216 | -0.8370 | -1.2190 |
78
- | 0.0343 | 2.93 | 1400 | 0.6824 | -4.2277 | -7.2864 | 0.7773 | 3.0587 | -408.3961 | -347.1476 | -0.8310 | -1.2135 |
79
 
80
 
81
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.5348
21
+ - Rewards/chosen: 0.6286
22
+ - Rewards/rejected: -0.2212
23
+ - Rewards/accuracies: 0.7539
24
+ - Rewards/margins: 0.8498
25
+ - Logps/rejected: -267.0915
26
+ - Logps/chosen: -250.0218
27
+ - Logits/rejected: -2.4324
28
+ - Logits/chosen: -2.4731
29
 
30
  ## Model description
31
 
 
56
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
57
  - lr_scheduler_type: cosine
58
  - lr_scheduler_warmup_ratio: 0.1
59
+ - num_epochs: 1
60
 
61
  ### Training results
62
 
63
+ | Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
64
+ |:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
65
+ | 0.565 | 0.21 | 100 | 0.5718 | 0.5950 | -0.0056 | 0.7383 | 0.6006 | -262.7792 | -250.6930 | -2.5105 | -2.5504 |
66
+ | 0.5467 | 0.42 | 200 | 0.5433 | 0.6478 | -0.1115 | 0.7461 | 0.7594 | -264.8979 | -249.6371 | -2.4783 | -2.5179 |
67
+ | 0.517 | 0.63 | 300 | 0.5370 | 0.5686 | -0.2689 | 0.7695 | 0.8374 | -268.0445 | -251.2220 | -2.5203 | -2.5623 |
68
+ | 0.518 | 0.84 | 400 | 0.5348 | 0.6286 | -0.2212 | 0.7539 | 0.8498 | -267.0915 | -250.0218 | -2.4324 | -2.4731 |
 
 
 
 
 
 
 
 
 
 
69
 
70
 
71
  ### Framework versions
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 3.0,
3
- "train_loss": 0.007373018379906397,
4
- "train_runtime": 5373.2533,
5
  "train_samples": 61134,
6
- "train_samples_per_second": 34.132,
7
- "train_steps_per_second": 0.267
8
  }
 
1
  {
2
+ "epoch": 1.0,
3
+ "train_loss": 0.5478911828795238,
4
+ "train_runtime": 7553.9268,
5
  "train_samples": 61134,
6
+ "train_samples_per_second": 8.093,
7
+ "train_steps_per_second": 0.063
8
  }
config.json CHANGED
@@ -20,7 +20,7 @@
20
  "sliding_window": 4096,
21
  "tie_word_embeddings": false,
22
  "torch_dtype": "bfloat16",
23
- "transformers_version": "4.40.1",
24
  "use_cache": false,
25
  "vocab_size": 32000
26
  }
 
20
  "sliding_window": 4096,
21
  "tie_word_embeddings": false,
22
  "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.38.2",
24
  "use_cache": false,
25
  "vocab_size": 32000
26
  }
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f6108f92c0bc4c2834053762de98cc5c2078cf240bf3f4bf2226a02dc4314d19
3
  size 4943162336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b668f8f887f1df175ea3fede818f9956dde3a4f82b012ed40e1f75f528510af
3
  size 4943162336
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8dd45abf9705483eca1786a8485bfa9e8fce12425a0630df8190c9074c81ae2e
3
  size 4999819336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ab93f64cdd679c94fb82526772aa1ddff9407c1f21541bf00dadf1482df2e87
3
  size 4999819336
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c43191053486250291b313a6e33349fc47cb611fa7ee1af51bdfba716087d7e
3
  size 4540516344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dabcfcdd26b2c41b402da15a5fc4afd601be2f77a064f1dacd450e2fbd05129f
3
  size 4540516344
tokenizer.json CHANGED
@@ -134,7 +134,6 @@
134
  "end_of_word_suffix": null,
135
  "fuse_unk": true,
136
  "byte_fallback": true,
137
- "ignore_merges": false,
138
  "vocab": {
139
  "<unk>": 0,
140
  "<s>": 1,
 
134
  "end_of_word_suffix": null,
135
  "fuse_unk": true,
136
  "byte_fallback": true,
 
137
  "vocab": {
138
  "<unk>": 0,
139
  "<s>": 1,
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 3.0,
3
- "train_loss": 0.007373018379906397,
4
- "train_runtime": 5373.2533,
5
  "train_samples": 61134,
6
- "train_samples_per_second": 34.132,
7
- "train_steps_per_second": 0.267
8
  }
 
1
  {
2
+ "epoch": 1.0,
3
+ "train_loss": 0.5478911828795238,
4
+ "train_runtime": 7553.9268,
5
  "train_samples": 61134,
6
+ "train_samples_per_second": 8.093,
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 sha256:94259a0321f76f500807b588d497162b448fa4d503beb2408e257b680d50bd71
3
  size 6264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae435f4d34b494d0a87771354b8caf1ae96faaff04dcd34569840c7fccbca4e8
3
  size 6264