Hugging Face's logo

LBK95
/
Llama-2-7b-hf-DPO-LookAhead-5_Q2_TTree1.4_TT0.9_TP0.7_TE0.2_V4

PEFT
Safetensors
trl
dpo
Generated from Trainer
Model card Files Community
LBK95 commited on
Commit
7ba3d99
·
verified ·
1 Parent(s): b2f97ae

End of training

Browse files
Files changed (1) hide show
  1. README.md +80 -0
README.md ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_Q2_TTree1.4_TT0.9_TP0.7_TE0.2_V4
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_Q2_TTree1.4_TT0.9_TP0.7_TE0.2_V4
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: 0.6849
22
+ - Rewards/chosen: -1.3255
23
+ - Rewards/rejected: -1.6674
24
+ - Rewards/accuracies: 0.5
25
+ - Rewards/margins: 0.3419
26
+ - Logps/rejected: -134.9012
27
+ - Logps/chosen: -95.5139
28
+ - Logits/rejected: 0.0033
29
+ - Logits/chosen: 0.1072
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
+ | 0.7204 | 0.3043 | 63 | 0.6808 | 0.0801 | 0.0519 | 0.7000 | 0.0281 | -117.7079 | -81.4587 | 0.4903 | 0.5915 |
64
+ | 0.6989 | 0.6087 | 126 | 0.6930 | 0.0550 | 0.0726 | 0.6000 | -0.0176 | -117.5013 | -81.7093 | 0.4748 | 0.5762 |
65
+ | 0.6896 | 0.9130 | 189 | 0.6579 | 0.1170 | 0.0536 | 0.5 | 0.0633 | -117.6909 | -81.0896 | 0.4569 | 0.5574 |
66
+ | 0.3332 | 1.2174 | 252 | 0.6831 | -0.2141 | -0.2394 | 0.5 | 0.0253 | -120.6211 | -84.4000 | 0.3842 | 0.4834 |
67
+ | 0.3687 | 1.5217 | 315 | 0.7069 | -0.6436 | -0.7406 | 0.5 | 0.0970 | -125.6332 | -88.6952 | 0.2816 | 0.3799 |
68
+ | 0.2083 | 1.8261 | 378 | 0.6389 | -0.4156 | -0.5567 | 0.5 | 0.1411 | -123.7943 | -86.4158 | 0.2329 | 0.3317 |
69
+ | 0.1191 | 2.1304 | 441 | 0.6451 | -0.8600 | -1.1248 | 0.5 | 0.2648 | -129.4748 | -90.8590 | 0.1067 | 0.2079 |
70
+ | 0.1435 | 2.4348 | 504 | 0.6878 | -1.2620 | -1.5788 | 0.5 | 0.3168 | -134.0153 | -94.8793 | 0.0284 | 0.1320 |
71
+ | 0.0848 | 2.7391 | 567 | 0.6849 | -1.3255 | -1.6674 | 0.5 | 0.3419 | -134.9012 | -95.5139 | 0.0033 | 0.1072 |
72
+
73
+
74
+ ### Framework versions
75
+
76
+ - PEFT 0.12.0
77
+ - Transformers 4.45.2
78
+ - Pytorch 2.4.0+cu121
79
+ - Datasets 3.2.0
80
+ - Tokenizers 0.20.3