Hugging Face's logo

LBK95
/
Llama-2-7b-hf-DPO-LookAhead5_FullEval_TTree1.4_TLoop0.7_TEval0.2_V2.0

PEFT
Safetensors
trl
dpo
Generated from Trainer
Model card Files Community
LBK95 commited on
Commit
4047841
•
1 Parent(s): 3e07d4c

End of training

Browse files
Files changed (1) hide show
  1. README.md +81 -0
README.md ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Llama-2-7b-hf
3
+ library_name: peft
4
+ license: llama2
5
+ tags:
6
+ - trl
7
+ - dpo
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: Llama-2-7b-hf-DPO-LookAhead5_FullEval_TTree1.4_TLoop0.7_TEval0.2_V2.0
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-LookAhead5_FullEval_TTree1.4_TLoop0.7_TEval0.2_V2.0
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: 0.9728
22
+ - Rewards/chosen: -2.0556
23
+ - Rewards/rejected: -1.8953
24
+ - Rewards/accuracies: 0.4167
25
+ - Rewards/margins: -0.1602
26
+ - Logps/rejected: -146.9038
27
+ - Logps/chosen: -163.5856
28
+ - Logits/rejected: -0.8198
29
+ - Logits/chosen: -0.8110
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
+ | 0.6766 | 0.2994 | 78 | 0.7200 | 0.0401 | 0.0730 | 0.4167 | -0.0329 | -127.2202 | -142.6290 | -0.3528 | -0.3393 |
64
+ | 0.6875 | 0.5988 | 156 | 0.6657 | -0.4080 | -0.4881 | 0.5833 | 0.0801 | -132.8311 | -147.1099 | -0.3720 | -0.3575 |
65
+ | 0.7999 | 0.8983 | 234 | 0.6842 | -0.3659 | -0.4094 | 0.6667 | 0.0435 | -132.0449 | -146.6892 | -0.3674 | -0.3517 |
66
+ | 0.4879 | 1.1977 | 312 | 0.6694 | -0.2237 | -0.2979 | 0.4167 | 0.0742 | -130.9293 | -145.2672 | -0.3979 | -0.3821 |
67
+ | 0.6233 | 1.4971 | 390 | 0.6523 | -0.9992 | -1.1797 | 0.5 | 0.1804 | -139.7471 | -153.0225 | -0.5012 | -0.4885 |
68
+ | 0.4034 | 1.7965 | 468 | 0.7021 | -0.9141 | -1.0257 | 0.4167 | 0.1116 | -138.2080 | -152.1710 | -0.4511 | -0.4394 |
69
+ | 0.1778 | 2.0960 | 546 | 0.7896 | -1.2322 | -1.2047 | 0.4167 | -0.0275 | -139.9971 | -155.3521 | -0.5752 | -0.5642 |
70
+ | 0.2732 | 2.3954 | 624 | 0.9364 | -1.8694 | -1.7281 | 0.4167 | -0.1412 | -145.2318 | -161.7236 | -0.7728 | -0.7633 |
71
+ | 0.1812 | 2.6948 | 702 | 0.9683 | -2.0710 | -1.9135 | 0.4167 | -0.1575 | -147.0860 | -163.7400 | -0.8137 | -0.8049 |
72
+ | 0.1798 | 2.9942 | 780 | 0.9728 | -2.0556 | -1.8953 | 0.4167 | -0.1602 | -146.9038 | -163.5856 | -0.8198 | -0.8110 |
73
+
74
+
75
+ ### Framework versions
76
+
77
+ - PEFT 0.12.0
78
+ - Transformers 4.44.2
79
+ - Pytorch 2.4.1+cu121
80
+ - Datasets 2.21.0
81
+ - Tokenizers 0.19.1