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
51c96d0
•
1 Parent(s): 280420c

End of training

Browse files
Files changed (9) hide show
  1. README.md +11 -11
  2. adapter_config.json +3 -3
  3. adapter_model.safetensors +1 -1
  4. metrics.jsonl +2 -0
  5. metrics_epoch_0.96_fold_0_lr_1e-05_seed_1234_weight_5.0.json +1 -0
  6. metrics_epoch_2.0_fold_0_lr_1e-05_seed_1234_weight_5.0.json +1 -0
  7. results_epoch_0.96_fold_0_lr_1e-05_seed_1234_weight_5.0.json +0 -0
  8. results_epoch_2.0_fold_0_lr_1e-05_seed_1234_weight_5.0.json +0 -0
  9. training_args.bin +1 -1
README.md CHANGED
@@ -18,12 +18,12 @@ 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: 0.6893
22
- - Eval/rewards/chosen: -5.9942
23
- - Eval/logps/chosen: -257.3902
24
- - Eval/rewards/rejected: -8.3440
25
- - Eval/logps/rejected: -337.8455
26
- - Eval/rewards/margins: 2.3498
27
  - Eval/kl: 0.0
28
 
29
  ## Model description
@@ -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
- | 0.4731 | 0.96 | 12 | 0.7020 | 0.0 |
62
- | 0.6028 | 2.0 | 25 | 0.6893 | 0.0 |
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: 1.0466
22
+ - Eval/rewards/chosen: -0.2063
23
+ - Eval/logps/chosen: -199.5112
24
+ - Eval/rewards/rejected: -0.2128
25
+ - Eval/logps/rejected: -256.5334
26
+ - Eval/rewards/margins: 0.0065
27
  - Eval/kl: 0.0
28
 
29
  ## Model description
 
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
+ | 1.7092 | 0.96 | 12 | 1.0871 | 0.0293 |
62
+ | 1.1814 | 2.0 | 25 | 1.0466 | 0.0 |
63
 
64
 
65
  ### Framework versions
adapter_config.json CHANGED
@@ -20,10 +20,10 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "v_proj",
24
- "o_proj",
25
  "k_proj",
26
- "q_proj"
 
27
  ],
28
  "task_type": "CAUSAL_LM",
29
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
+ "q_proj",
 
24
  "k_proj",
25
+ "v_proj",
26
+ "o_proj"
27
  ],
28
  "task_type": "CAUSAL_LM",
29
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8ee9b9511364014c5d194d04e7765fa39220c9b39a63101365315e7e5e1db9bc
3
  size 27297544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27903a3b3043c02e2d7dc42d3e7f7c844117961a2c15068be632dd5d9ddfb031
3
  size 27297544
metrics.jsonl CHANGED
@@ -8,3 +8,5 @@
8
  {"epoch": 2.0, "precision": 0.0, "recall": 0.0, "fold": 0}
9
  {"epoch": 0.96, "precision": 0.6666666648148148, "recall": 0.7999999973333333, "fold": 0}
10
  {"epoch": 2.0, "precision": 0.8333333287037037, "recall": 0.4999999983333333, "fold": 0}
 
 
 
8
  {"epoch": 2.0, "precision": 0.0, "recall": 0.0, "fold": 0}
9
  {"epoch": 0.96, "precision": 0.6666666648148148, "recall": 0.7999999973333333, "fold": 0}
10
  {"epoch": 2.0, "precision": 0.8333333287037037, "recall": 0.4999999983333333, "fold": 0}
11
+ {"epoch": 0.96, "precision": 0.4915254228957196, "recall": 0.9666666634444444, "fold": 0}
12
+ {"epoch": 2.0, "precision": 0.5686274498654363, "recall": 0.9666666634444444, "fold": 0}
metrics_epoch_0.96_fold_0_lr_1e-05_seed_1234_weight_5.0.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"epoch": 0.96, "precision": 0.4915254228957196, "recall": 0.9666666634444444, "fold": 0}
metrics_epoch_2.0_fold_0_lr_1e-05_seed_1234_weight_5.0.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"epoch": 2.0, "precision": 0.5686274498654363, "recall": 0.9666666634444444, "fold": 0}
results_epoch_0.96_fold_0_lr_1e-05_seed_1234_weight_5.0.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_5.0.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 sha256:7e06d7f1837f9a183a6ec729c140859913a36845b45b9e0429aa2635a2669007
3
  size 5688
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d7fb04fe53a69c0947a1c162ecc7667487c5218a7fa30cd0338ed7127717252
3
  size 5688