Hugging Face's logo

PaulD
/
llama3_false_positives_1010_KTO_hp_screening_seeds

PEFT
Safetensors
trl
kto
Generated from Trainer
Model card Files Community
PaulD commited on
Commit
dc37578
•
1 Parent(s): 7db5dcf

End of training

Browse files
Files changed (8) hide show
  1. README.md +12 -12
  2. adapter_model.safetensors +1 -1
  3. metrics.jsonl +2 -0
  4. metrics_epoch_0.96_fold_0_lr_1e-05_seed_1234_weight_2.0.json +1 -0
  5. metrics_epoch_2.0_fold_0_lr_1e-05_seed_1234_weight_2.0.json +1 -0
  6. results_epoch_0.96_fold_0_lr_1e-05_seed_1234_weight_2.0.json +0 -0
  7. results_epoch_2.0_fold_0_lr_1e-05_seed_1234_weight_2.0.json +0 -0
  8. training_args.bin +1 -1
README.md CHANGED
@@ -18,13 +18,13 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.6324
22
- - Eval/rewards/chosen: 1.4100
23
- - Eval/logps/chosen: -183.3489
24
- - Eval/rewards/rejected: 1.3516
25
- - Eval/logps/rejected: -240.8897
26
- - Eval/rewards/margins: 0.0584
27
- - Eval/kl: 14.3395
28
 
29
  ## Model description
30
 
@@ -43,7 +43,7 @@ More information needed
43
  ### Training hyperparameters
44
 
45
  The following hyperparameters were used during training:
46
- - learning_rate: 0.0001
47
  - train_batch_size: 1
48
  - eval_batch_size: 2
49
  - seed: 1234
@@ -56,10 +56,10 @@ The following hyperparameters were used during training:
56
 
57
  ### Training results
58
 
59
- | Training Loss | Epoch | Step | Validation Loss | |
60
- |:-------------:|:-----:|:----:|:---------------:|:-------:|
61
- | 0.6561 | 0.96 | 12 | 0.6281 | 0.1571 |
62
- | 0.3245 | 2.0 | 25 | 0.6324 | 14.3395 |
63
 
64
 
65
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.6495
22
+ - Eval/rewards/chosen: -0.0147
23
+ - Eval/logps/chosen: -197.5959
24
+ - Eval/rewards/rejected: -0.0005
25
+ - Eval/logps/rejected: -254.4111
26
+ - Eval/rewards/margins: -0.0142
27
+ - Eval/kl: 0.0906
28
 
29
  ## Model description
30
 
 
43
  ### Training hyperparameters
44
 
45
  The following hyperparameters were used during training:
46
+ - learning_rate: 1e-05
47
  - train_batch_size: 1
48
  - eval_batch_size: 2
49
  - seed: 1234
 
56
 
57
  ### Training results
58
 
59
+ | Training Loss | Epoch | Step | Validation Loss | |
60
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
61
+ | 0.8104 | 0.96 | 12 | 0.6455 | 0.1366 |
62
+ | 0.6833 | 2.0 | 25 | 0.6495 | 0.0906 |
63
 
64
 
65
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c19d7e7815d0a7ac4e697c4b94d61f128a09b7bda2c1b68497d125ee7f49616f
3
  size 27297544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b45cc67d6d667c4d8a1ab0f3032f7cedab6dc4f309fe56b539f7300495bed3f
3
  size 27297544
metrics.jsonl CHANGED
@@ -2,3 +2,5 @@
2
  {"epoch": 2.0, "precision": 0.0, "recall": 0.0, "fold": 0}
3
  {"epoch": 0.96, "precision": 0.6363636349173554, "recall": 0.9333333302222222, "fold": 0}
4
  {"epoch": 2.0, "precision": 0.8529411739619377, "recall": 0.9666666634444444, "fold": 0}
 
 
 
2
  {"epoch": 2.0, "precision": 0.0, "recall": 0.0, "fold": 0}
3
  {"epoch": 0.96, "precision": 0.6363636349173554, "recall": 0.9333333302222222, "fold": 0}
4
  {"epoch": 2.0, "precision": 0.8529411739619377, "recall": 0.9666666634444444, "fold": 0}
5
+ {"epoch": 0.96, "precision": 0.43548387026534857, "recall": 0.899999997, "fold": 0}
6
+ {"epoch": 2.0, "precision": 0.4754098352862134, "recall": 0.9666666634444444, "fold": 0}
metrics_epoch_0.96_fold_0_lr_1e-05_seed_1234_weight_2.0.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"epoch": 0.96, "precision": 0.43548387026534857, "recall": 0.899999997, "fold": 0}
metrics_epoch_2.0_fold_0_lr_1e-05_seed_1234_weight_2.0.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"epoch": 2.0, "precision": 0.4754098352862134, "recall": 0.9666666634444444, "fold": 0}
results_epoch_0.96_fold_0_lr_1e-05_seed_1234_weight_2.0.json ADDED
The diff for this file is too large to render. See raw diff
 
results_epoch_2.0_fold_0_lr_1e-05_seed_1234_weight_2.0.json ADDED
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 sha256:3b8a74797043c53ab902975cf24619e88f2c8d298a72217fb300e0b4c8618d38
3
  size 5688
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97cd3fa005c4ebb2d26706ac9858584ceae99f4a07a031c4da87805249f0f73a
3
  size 5688