Hugging Face's logo

NanQiangHF
/
llama3.1_8b_dpo_bwgenerator_test2

PEFT
Safetensors
llama
trl
dpo
Generated from Trainer
Model card Files Community
NanQiangHF commited on
Commit
6e202d4
•
1 Parent(s): ee1da52

NanQiangHF/llama3.1_8b_dpo_bwgenerator_test2

Browse files
Files changed (3) hide show
  1. README.md +25 -16
  2. adapter_model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -18,15 +18,15 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.0977
22
- - Rewards/chosen: -12.6599
23
- - Rewards/rejected: -40.7969
24
- - Rewards/accuracies: 0.9925
25
- - Rewards/margins: 28.1371
26
- - Logps/rejected: -518.0425
27
- - Logps/chosen: -211.2417
28
- - Logits/rejected: -1.2740
29
- - Logits/chosen: -1.8549
30
 
31
  ## Model description
32
 
@@ -45,7 +45,7 @@ More information needed
45
  ### Training hyperparameters
46
 
47
  The following hyperparameters were used during training:
48
- - learning_rate: 5e-05
49
  - train_batch_size: 4
50
  - eval_batch_size: 4
51
  - seed: 42
@@ -55,12 +55,21 @@ The following hyperparameters were used during training:
55
 
56
  ### Training results
57
 
58
- | Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
59
- |:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
60
- | 0.065 | 0.2396 | 1000 | 0.1978 | -24.9705 | -63.8717 | 0.9881 | 38.9011 | -748.7902 | -334.3486 | -1.2031 | -1.8039 |
61
- | 0.0803 | 0.4793 | 2000 | 0.1339 | -16.1506 | -46.8097 | 0.9925 | 30.6591 | -578.1700 | -246.1489 | -1.2214 | -1.8149 |
62
- | 0.0588 | 0.7189 | 3000 | 0.1012 | -12.8597 | -41.3756 | 0.9925 | 28.5159 | -523.8289 | -213.2401 | -1.2775 | -1.8541 |
63
- | 0.0422 | 0.9585 | 4000 | 0.0977 | -12.6599 | -40.7969 | 0.9925 | 28.1371 | -518.0425 | -211.2417 | -1.2740 | -1.8549 |
 
 
 
 
 
 
 
 
 
64
 
65
 
66
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.5181
22
+ - Rewards/chosen: -0.4278
23
+ - Rewards/rejected: -0.8508
24
+ - Rewards/accuracies: 0.9255
25
+ - Rewards/margins: 0.4230
26
+ - Logps/rejected: -118.6553
27
+ - Logps/chosen: -88.8263
28
+ - Logits/rejected: -0.9049
29
+ - Logits/chosen: -1.6027
30
 
31
  ## Model description
32
 
 
45
  ### Training hyperparameters
46
 
47
  The following hyperparameters were used during training:
48
+ - learning_rate: 2e-06
49
  - train_batch_size: 4
50
  - eval_batch_size: 4
51
  - seed: 42
 
55
 
56
  ### Training results
57
 
58
+ | Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
59
+ |:-------------:|:------:|:-----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
60
+ | 0.6002 | 0.0719 | 1000 | 0.5390 | -0.3845 | -0.7489 | 0.9194 | 0.3644 | -117.6367 | -88.3940 | -0.9017 | -1.6013 |
61
+ | 0.5325 | 0.1438 | 2000 | 0.5237 | -0.4184 | -0.8254 | 0.9200 | 0.4070 | -118.4018 | -88.7330 | -0.9052 | -1.6035 |
62
+ | 0.5221 | 0.2157 | 3000 | 0.5199 | -0.4201 | -0.8376 | 0.9210 | 0.4175 | -118.5239 | -88.7496 | -0.9038 | -1.6021 |
63
+ | 0.518 | 0.2876 | 4000 | 0.5178 | -0.4376 | -0.8621 | 0.9220 | 0.4246 | -118.7688 | -88.9242 | -0.9056 | -1.6036 |
64
+ | 0.5177 | 0.3595 | 5000 | 0.5176 | -0.4317 | -0.8563 | 0.9213 | 0.4246 | -118.7104 | -88.8652 | -0.9063 | -1.6039 |
65
+ | 0.5186 | 0.4313 | 6000 | 0.5180 | -0.4361 | -0.8604 | 0.9200 | 0.4243 | -118.7512 | -88.9096 | -0.9063 | -1.6040 |
66
+ | 0.522 | 0.5032 | 7000 | 0.5175 | -0.4358 | -0.8614 | 0.9210 | 0.4255 | -118.7612 | -88.9070 | -0.9057 | -1.6035 |
67
+ | 0.5194 | 0.5751 | 8000 | 0.5182 | -0.4280 | -0.8506 | 0.9249 | 0.4226 | -118.6538 | -88.8285 | -0.9039 | -1.6020 |
68
+ | 0.5149 | 0.6470 | 9000 | 0.5179 | -0.4413 | -0.8651 | 0.9229 | 0.4238 | -118.7981 | -88.9612 | -0.9060 | -1.6038 |
69
+ | 0.5209 | 0.7189 | 10000 | 0.5178 | -0.4355 | -0.8600 | 0.9216 | 0.4244 | -118.7471 | -88.9040 | -0.9049 | -1.6027 |
70
+ | 0.517 | 0.7908 | 11000 | 0.5187 | -0.4343 | -0.8561 | 0.9194 | 0.4217 | -118.7081 | -88.8918 | -0.9046 | -1.6027 |
71
+ | 0.5202 | 0.8627 | 12000 | 0.5186 | -0.4321 | -0.8540 | 0.9197 | 0.4220 | -118.6880 | -88.8693 | -0.9047 | -1.6026 |
72
+ | 0.5212 | 0.9346 | 13000 | 0.5181 | -0.4278 | -0.8508 | 0.9255 | 0.4230 | -118.6553 | -88.8263 | -0.9049 | -1.6027 |
73
 
74
 
75
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b40d9454bd74b6b75ee3ef86dc681ec53c57225fd21457b9302cfe32178105de
3
  size 6832728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b8a6bef242915c290add5500f883d382a2ddad3e4de62d7360d15990e55b49b
3
  size 6832728
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2d738bea601de8ba45f05c7f68d6ede51996087feebaf26001f43e3582a4100d
3
  size 6072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f668a41a4c986acd257572534b95e68170cb025005a5b82fb7ecfd56f17c7ab
3
  size 6072