Hugging Face's logo

wzhouad
/
zephyr-7b-dpo-full

Text Generation
Transformers
Safetensors
llama
trl
dpo
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
wzhouad commited on
Commit
a914407
•
1 Parent(s): 9a54ae0

Model save

Browse files
Files changed (7) hide show
  1. README.md +34 -15
  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. train_results.json +5 -5
  7. trainer_state.json +0 -0
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 [HuggingFaceH4/mistral-7b-sft-beta](https://huggingface.co/HuggingFaceH4/mistral-7b-sft-beta) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.0945
21
- - Rewards/chosen: -1.3600
22
- - Rewards/rejected: -2.1836
23
- - Rewards/accuracies: 0.7656
24
- - Rewards/margins: 0.8237
25
- - Logps/rejected: -475.7151
26
- - Logps/chosen: -393.0347
27
- - Logits/rejected: -2.3019
28
- - Logits/chosen: -2.3254
29
 
30
  ## Model description
31
 
@@ -47,7 +47,7 @@ The following hyperparameters were used during training:
47
  - learning_rate: 5e-07
48
  - train_batch_size: 8
49
  - eval_batch_size: 8
50
- - seed: 5
51
  - distributed_type: multi-GPU
52
  - num_devices: 8
53
  - gradient_accumulation_steps: 2
@@ -56,16 +56,35 @@ 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: 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
- | 0.1643 | 0.21 | 100 | 0.1558 | -0.4076 | -0.7972 | 0.7461 | 0.3896 | -337.0709 | -297.7996 | -2.7691 | -2.7902 |
66
- | 0.1003 | 0.42 | 200 | 0.0997 | -1.2712 | -1.9340 | 0.7031 | 0.6629 | -450.7552 | -384.1553 | -2.5137 | -2.5340 |
67
- | 0.0953 | 0.63 | 300 | 0.1024 | -1.2036 | -1.9243 | 0.7539 | 0.7207 | -449.7823 | -377.3981 | -2.3837 | -2.4030 |
68
- | 0.0811 | 0.84 | 400 | 0.0945 | -1.3600 | -2.1836 | 0.7656 | 0.8237 | -475.7151 | -393.0347 | -2.3019 | -2.3254 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
 
70
 
71
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [HuggingFaceH4/mistral-7b-sft-beta](https://huggingface.co/HuggingFaceH4/mistral-7b-sft-beta) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.0108
21
+ - Rewards/chosen: -5.9141
22
+ - Rewards/rejected: -7.7338
23
+ - Rewards/accuracies: 0.7266
24
+ - Rewards/margins: 1.8197
25
+ - Logps/rejected: -1030.7371
26
+ - Logps/chosen: -848.4521
27
+ - Logits/rejected: -1.6334
28
+ - Logits/chosen: -1.6493
29
 
30
  ## Model description
31
 
 
47
  - learning_rate: 5e-07
48
  - train_batch_size: 8
49
  - eval_batch_size: 8
50
+ - seed: 42
51
  - distributed_type: multi-GPU
52
  - num_devices: 8
53
  - gradient_accumulation_steps: 2
 
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: 5
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
+ | 0.2786 | 0.21 | 100 | 0.2781 | -0.0080 | -0.0710 | 0.6719 | 0.0631 | -264.4583 | -257.8367 | -2.7623 | -2.7774 |
66
+ | 0.1377 | 0.42 | 200 | 0.1450 | -0.5817 | -1.0385 | 0.6992 | 0.4567 | -361.2018 | -315.2145 | -2.7365 | -2.7512 |
67
+ | 0.1162 | 0.63 | 300 | 0.1186 | -1.0407 | -1.6725 | 0.7266 | 0.6318 | -424.5983 | -361.1053 | -2.4888 | -2.5058 |
68
+ | 0.1019 | 0.84 | 400 | 0.0997 | -1.6327 | -2.4828 | 0.7461 | 0.8501 | -505.6364 | -420.3094 | -2.2736 | -2.3013 |
69
+ | 0.0226 | 1.05 | 500 | 0.0406 | -2.9554 | -4.2565 | 0.7266 | 1.3012 | -683.0034 | -552.5746 | -2.1929 | -2.2303 |
70
+ | 0.0116 | 1.26 | 600 | 0.0298 | -3.0110 | -4.3717 | 0.7305 | 1.3607 | -694.5244 | -558.1376 | -2.1365 | -2.1643 |
71
+ | 0.0132 | 1.46 | 700 | 0.0320 | -2.8731 | -4.1217 | 0.7383 | 1.2486 | -669.5266 | -544.3542 | -2.1173 | -2.1453 |
72
+ | 0.0141 | 1.67 | 800 | 0.0285 | -2.8506 | -4.0446 | 0.7383 | 1.1939 | -661.8126 | -542.1040 | -2.0387 | -2.0557 |
73
+ | 0.008 | 1.88 | 900 | 0.0217 | -3.7087 | -4.9874 | 0.7148 | 1.2786 | -756.0888 | -627.9131 | -1.8927 | -1.9084 |
74
+ | 0.0015 | 2.09 | 1000 | 0.0135 | -4.8936 | -6.4137 | 0.7109 | 1.5202 | -898.7281 | -746.3977 | -1.7007 | -1.7103 |
75
+ | 0.0019 | 2.3 | 1100 | 0.0140 | -4.8675 | -6.4410 | 0.7188 | 1.5735 | -901.4539 | -743.7909 | -1.7341 | -1.7490 |
76
+ | 0.0014 | 2.51 | 1200 | 0.0128 | -5.1432 | -6.7584 | 0.7188 | 1.6152 | -933.1906 | -771.3603 | -1.7194 | -1.7313 |
77
+ | 0.0012 | 2.72 | 1300 | 0.0126 | -5.2094 | -6.8051 | 0.7227 | 1.5957 | -937.8638 | -777.9802 | -1.7283 | -1.7387 |
78
+ | 0.0012 | 2.93 | 1400 | 0.0126 | -5.3124 | -6.9529 | 0.7148 | 1.6405 | -952.6434 | -788.2790 | -1.7056 | -1.7185 |
79
+ | 0.0009 | 3.14 | 1500 | 0.0113 | -5.6394 | -7.3683 | 0.7188 | 1.7289 | -994.1813 | -820.9806 | -1.6707 | -1.6834 |
80
+ | 0.0007 | 3.35 | 1600 | 0.0115 | -5.6409 | -7.3656 | 0.7227 | 1.7247 | -993.9130 | -821.1270 | -1.6691 | -1.6823 |
81
+ | 0.0011 | 3.56 | 1700 | 0.0114 | -5.6893 | -7.4555 | 0.7227 | 1.7662 | -1002.9027 | -825.9682 | -1.6580 | -1.6727 |
82
+ | 0.0007 | 3.77 | 1800 | 0.0113 | -5.7534 | -7.5287 | 0.7227 | 1.7753 | -1010.2194 | -832.3766 | -1.6467 | -1.6620 |
83
+ | 0.0009 | 3.97 | 1900 | 0.0113 | -5.7308 | -7.5090 | 0.7227 | 1.7782 | -1008.2513 | -830.1171 | -1.6581 | -1.6731 |
84
+ | 0.0006 | 4.18 | 2000 | 0.0109 | -5.8887 | -7.6915 | 0.7266 | 1.8028 | -1026.5013 | -845.9089 | -1.6381 | -1.6538 |
85
+ | 0.0006 | 4.39 | 2100 | 0.0109 | -5.9096 | -7.7239 | 0.7266 | 1.8144 | -1029.7469 | -847.9958 | -1.6345 | -1.6501 |
86
+ | 0.0006 | 4.6 | 2200 | 0.0109 | -5.8953 | -7.7105 | 0.7266 | 1.8152 | -1028.4065 | -846.5691 | -1.6360 | -1.6516 |
87
+ | 0.0007 | 4.81 | 2300 | 0.0108 | -5.9141 | -7.7338 | 0.7266 | 1.8197 | -1030.7371 | -848.4521 | -1.6334 | -1.6493 |
88
 
89
 
90
  ### Framework versions
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 1.0,
3
- "train_loss": 0.13007899894375183,
4
- "train_runtime": 3956.3918,
5
  "train_samples": 61134,
6
- "train_samples_per_second": 15.452,
7
- "train_steps_per_second": 0.121
8
  }
 
1
  {
2
+ "epoch": 5.0,
3
+ "train_loss": 0.035704591817896675,
4
+ "train_runtime": 20238.2555,
5
  "train_samples": 61134,
6
+ "train_samples_per_second": 15.104,
7
+ "train_steps_per_second": 0.118
8
  }
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e47517cfb73405f7bf5d01294c3a110798173231e018029481b0de05019a0d5
3
  size 4943162336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11442a359aebd446ce125ba8018eb02f21837e57e0322c88d013ded626927932
3
  size 4943162336
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3d629d1ed6bc30b2268feb5f0fd326e9d78f1f4b1e67ba64737866501c3c6231
3
  size 4999819336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c74625da00d5a294bafa9e72a42ad588018cc1ec0f0934f8db120798d831612b
3
  size 4999819336
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:42f17dfe6c68b6934688f9caf72473729842e30bb46aab3751edb49af3ac7626
3
  size 4540516344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ed21c3b2478fca01ce2cecc2a5355d0429c83a631ffbcf96204e95e214eb3ea
3
  size 4540516344
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 1.0,
3
- "train_loss": 0.13007899894375183,
4
- "train_runtime": 3956.3918,
5
  "train_samples": 61134,
6
- "train_samples_per_second": 15.452,
7
- "train_steps_per_second": 0.121
8
  }
 
1
  {
2
+ "epoch": 5.0,
3
+ "train_loss": 0.035704591817896675,
4
+ "train_runtime": 20238.2555,
5
  "train_samples": 61134,
6
+ "train_samples_per_second": 15.104,
7
+ "train_steps_per_second": 0.118
8
  }
trainer_state.json CHANGED
The diff for this file is too large to render. See raw diff