Hugging Face's logo

PaulD
/
llama3_false_positives_0609_KTO_hp_screening_seeds

PEFT
Safetensors
trl
kto
Generated from Trainer
Model card Files Community
PaulD commited on
Commit
1ba86fd
•
1 Parent(s): 85a6511

End of training

Browse files
Files changed (7) hide show
  1. README.md +5 -5
  2. adapter_config.json +3 -3
  3. adapter_model.safetensors +1 -1
  4. metrics.jsonl +1 -0
  5. metrics_epoch_0.96_fold_0_lr_0.0_seed_5678_weight_2.0.json +1 -0
  6. results_epoch_0.96_fold_0_lr_0.0_seed_5678_weight_2.0.json +0 -0
  7. training_args.bin +1 -1
README.md CHANGED
@@ -18,11 +18,11 @@ 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: 1.3382
22
  - Eval/rewards/chosen: 0.0
23
- - Eval/logps/chosen: -192.8253
24
  - Eval/rewards/rejected: 0.0
25
- - Eval/logps/rejected: -229.8692
26
  - Eval/rewards/margins: 0.0
27
  - Eval/kl: 0.0
28
 
@@ -46,7 +46,7 @@ The following hyperparameters were used during training:
46
  - learning_rate: 0.0
47
  - train_batch_size: 1
48
  - eval_batch_size: 2
49
- - seed: 1234
50
  - gradient_accumulation_steps: 8
51
  - total_train_batch_size: 8
52
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
@@ -58,7 +58,7 @@ The following hyperparameters were used during training:
58
 
59
  | Training Loss | Epoch | Step | Validation Loss | |
60
  |:-------------:|:-----:|:----:|:---------------:|:---:|
61
- | 3.3125 | 0.96 | 12 | 1.3382 | 0.0 |
62
 
63
 
64
  ### 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: 0.6324
22
  - Eval/rewards/chosen: 0.0
23
+ - Eval/logps/chosen: -203.5358
24
  - Eval/rewards/rejected: 0.0
25
+ - Eval/logps/rejected: -215.2117
26
  - Eval/rewards/margins: 0.0
27
  - Eval/kl: 0.0
28
 
 
46
  - learning_rate: 0.0
47
  - train_batch_size: 1
48
  - eval_batch_size: 2
49
+ - seed: 5678
50
  - gradient_accumulation_steps: 8
51
  - total_train_batch_size: 8
52
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 
58
 
59
  | Training Loss | Epoch | Step | Validation Loss | |
60
  |:-------------:|:-----:|:----:|:---------------:|:---:|
61
+ | 0.5625 | 0.96 | 12 | 0.6324 | 0.0 |
62
 
63
 
64
  ### Framework versions
adapter_config.json CHANGED
@@ -20,10 +20,10 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "k_proj",
24
- "q_proj",
25
  "o_proj",
26
- "v_proj"
 
27
  ],
28
  "task_type": "CAUSAL_LM",
29
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
+ "v_proj",
 
24
  "o_proj",
25
+ "q_proj",
26
+ "k_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 sha256:42d136e0b0e73d38dc7c67bedb6732e527d052b8c2640d6e3f1b100b2c46a2a8
3
  size 27297544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c21ab0c04e30634c1e6c3d153a150d25a226a07a986f1724f5da941a4be84dd
3
  size 27297544
metrics.jsonl CHANGED
@@ -6,3 +6,4 @@
6
  {"epoch": 0.96, "precision": 0.41463414533016063, "recall": 0.9444444391975308, "fold": 0}
7
  {"epoch": 0.96, "precision": 0.41463414533016063, "recall": 0.9444444391975308, "fold": 0}
8
  {"epoch": 0.96, "precision": 0.41463414533016063, "recall": 0.9444444391975308, "fold": 0}
 
 
6
  {"epoch": 0.96, "precision": 0.41463414533016063, "recall": 0.9444444391975308, "fold": 0}
7
  {"epoch": 0.96, "precision": 0.41463414533016063, "recall": 0.9444444391975308, "fold": 0}
8
  {"epoch": 0.96, "precision": 0.41463414533016063, "recall": 0.9444444391975308, "fold": 0}
9
+ {"epoch": 0.96, "precision": 0.3529411757785467, "recall": 0.9999999944444444, "fold": 0}
metrics_epoch_0.96_fold_0_lr_0.0_seed_5678_weight_2.0.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"epoch": 0.96, "precision": 0.3529411757785467, "recall": 0.9999999944444444, "fold": 0}
results_epoch_0.96_fold_0_lr_0.0_seed_5678_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 sha256:29269a821ba8c9148b4233cf327acfe3816eedc202fda9c83cd9017b8adb4c4d
3
  size 5688
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4f50a080d4769e1a32b76a700456e6b6165c36d10cf9f60223d64022442eb1c
3
  size 5688