Hugging Face's logo

LBK95
/
Llama-2-7b-hf-DPO-LookAhead-5_TTree1.4_TT0.9_TP0.7_TE0.2_V7

PEFT
Safetensors
trl
dpo
Generated from Trainer
Model card Files Community
LBK95 commited on
Commit
366f89d
·
verified ·
1 Parent(s): 80ab5a0

End of training

Browse files
Files changed (1) hide show
  1. README.md +81 -0
README.md ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: llama2
4
+ base_model: meta-llama/Llama-2-7b-hf
5
+ tags:
6
+ - trl
7
+ - dpo
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: Llama-2-7b-hf-DPO-LookAhead-5_TTree1.4_TT0.9_TP0.7_TE0.2_V7
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # Llama-2-7b-hf-DPO-LookAhead-5_TTree1.4_TT0.9_TP0.7_TE0.2_V7
18
+
19
+ This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the None dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.4437
22
+ - Rewards/chosen: -1.5898
23
+ - Rewards/rejected: -2.7509
24
+ - Rewards/accuracies: 0.7000
25
+ - Rewards/margins: 1.1611
26
+ - Logps/rejected: -114.1047
27
+ - Logps/chosen: -92.5540
28
+ - Logits/rejected: -0.0729
29
+ - Logits/chosen: -0.0526
30
+
31
+ ## Model description
32
+
33
+ More information needed
34
+
35
+ ## Intended uses & limitations
36
+
37
+ More information needed
38
+
39
+ ## Training and evaluation data
40
+
41
+ More information needed
42
+
43
+ ## Training procedure
44
+
45
+ ### Training hyperparameters
46
+
47
+ The following hyperparameters were used during training:
48
+ - learning_rate: 5e-05
49
+ - train_batch_size: 2
50
+ - eval_batch_size: 2
51
+ - seed: 42
52
+ - gradient_accumulation_steps: 2
53
+ - total_train_batch_size: 4
54
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
55
+ - lr_scheduler_type: cosine
56
+ - lr_scheduler_warmup_steps: 10
57
+ - num_epochs: 3
58
+
59
+ ### Training results
60
+
61
+ | Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
62
+ |:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
63
+ | 0.6702 | 0.2993 | 66 | 0.6613 | 0.0837 | -0.0035 | 0.7000 | 0.0872 | -86.6308 | -75.8190 | 0.3314 | 0.3469 |
64
+ | 0.686 | 0.5986 | 132 | 0.5646 | 0.0172 | -0.3322 | 0.8000 | 0.3494 | -89.9173 | -76.4838 | 0.3494 | 0.3651 |
65
+ | 0.7758 | 0.8980 | 198 | 0.5747 | 0.0543 | -0.2153 | 0.9000 | 0.2696 | -88.7488 | -76.1133 | 0.3694 | 0.3845 |
66
+ | 0.6695 | 1.1973 | 264 | 0.5693 | -0.2661 | -0.6699 | 0.7000 | 0.4038 | -93.2946 | -79.3173 | 0.3321 | 0.3466 |
67
+ | 0.5453 | 1.4966 | 330 | 0.5472 | -0.6038 | -1.1332 | 0.6000 | 0.5294 | -97.9278 | -82.6945 | 0.2266 | 0.2424 |
68
+ | 0.5922 | 1.7959 | 396 | 0.5142 | -0.9005 | -1.6462 | 0.6000 | 0.7457 | -103.0579 | -85.6614 | 0.1303 | 0.1477 |
69
+ | 0.2128 | 2.0952 | 462 | 0.4825 | -1.1082 | -1.9752 | 0.8000 | 0.8670 | -106.3474 | -87.7384 | 0.0713 | 0.0898 |
70
+ | 0.1372 | 2.3946 | 528 | 0.4425 | -1.4160 | -2.5347 | 0.8000 | 1.1187 | -111.9428 | -90.8164 | -0.0224 | -0.0028 |
71
+ | 0.3622 | 2.6939 | 594 | 0.4437 | -1.5113 | -2.6570 | 0.8000 | 1.1457 | -113.1660 | -91.7698 | -0.0636 | -0.0435 |
72
+ | 0.1555 | 2.9932 | 660 | 0.4437 | -1.5898 | -2.7509 | 0.7000 | 1.1611 | -114.1047 | -92.5540 | -0.0729 | -0.0526 |
73
+
74
+
75
+ ### Framework versions
76
+
77
+ - PEFT 0.12.0
78
+ - Transformers 4.45.2
79
+ - Pytorch 2.4.0+cu121
80
+ - Datasets 3.2.0
81
+ - Tokenizers 0.20.3