Hugging Face's logo

statking
/
Meta-Llama-3-8B-Instruct-DPO-QLoRA

PEFT
Safetensors
llama
alignment-handbook
trl
dpo
Generated from Trainer
Model card Files
xet
 Community
statking commited on
Commit
0083b65
·
verified ·
1 Parent(s): d6b856c

Model save

Browse files
Files changed (5) hide show
  1. README.md +93 -0
  2. adapter_model.safetensors +1 -1
  3. all_results.json +9 -0
  4. train_results.json +9 -0
  5. trainer_state.json +0 -0
README.md ADDED
@@ -0,0 +1,93 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ tags:
4
+ - trl
5
+ - dpo
6
+ - generated_from_trainer
7
+ base_model: data/Meta-Llama-3-8B-Instruct-Merged
8
+ model-index:
9
+ - name: Meta-Llama-3-8B-Instruct-DPO-QLoRA
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/statking/huggingface/runs/ficbttt2)
17
+ # Meta-Llama-3-8B-Instruct-DPO-QLoRA
18
+
19
+ This model was trained from scratch on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.4785
22
+ - Rewards/chosen: -2.3086
23
+ - Rewards/rejected: -3.5093
24
+ - Rewards/accuracies: 0.7740
25
+ - Rewards/margins: 1.2007
26
+ - Logps/rejected: -604.1885
27
+ - Logps/chosen: -507.2548
28
+ - Logits/rejected: -0.8544
29
+ - Logits/chosen: -0.8360
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-06
49
+ - train_batch_size: 4
50
+ - eval_batch_size: 8
51
+ - seed: 42
52
+ - distributed_type: multi-GPU
53
+ - num_devices: 2
54
+ - gradient_accumulation_steps: 4
55
+ - total_train_batch_size: 32
56
+ - total_eval_batch_size: 16
57
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
58
+ - lr_scheduler_type: cosine
59
+ - lr_scheduler_warmup_ratio: 0.1
60
+ - num_epochs: 1
61
+
62
+ ### Training results
63
+
64
+ | Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
65
+ |:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
66
+ | 0.6865 | 0.0523 | 100 | 0.6857 | 0.0202 | 0.0036 | 0.6810 | 0.0166 | -252.9014 | -274.3707 | -0.6048 | -0.5953 |
67
+ | 0.5773 | 0.1047 | 200 | 0.5802 | -0.5398 | -0.9390 | 0.7080 | 0.3992 | -347.1614 | -330.3779 | -0.9408 | -0.9089 |
68
+ | 0.546 | 0.1570 | 300 | 0.5337 | -0.9951 | -1.7352 | 0.7370 | 0.7401 | -426.7812 | -375.9071 | -1.0937 | -1.0510 |
69
+ | 0.501 | 0.2094 | 400 | 0.5120 | -1.8215 | -2.7617 | 0.7530 | 0.9401 | -529.4277 | -458.5479 | -1.1011 | -1.0595 |
70
+ | 0.4525 | 0.2617 | 500 | 0.5090 | -1.9857 | -3.0848 | 0.7510 | 1.0991 | -561.7446 | -474.9624 | -0.9430 | -0.9134 |
71
+ | 0.508 | 0.3141 | 600 | 0.5005 | -2.2106 | -3.1511 | 0.7600 | 0.9405 | -568.3763 | -497.4550 | -0.9955 | -0.9626 |
72
+ | 0.4852 | 0.3664 | 700 | 0.5028 | -1.3971 | -2.4127 | 0.7770 | 1.0156 | -494.5317 | -416.1026 | -0.9794 | -0.9476 |
73
+ | 0.5474 | 0.4187 | 800 | 0.4966 | -1.7948 | -2.7637 | 0.7670 | 0.9689 | -529.6284 | -455.8714 | -0.9115 | -0.8851 |
74
+ | 0.5246 | 0.4711 | 900 | 0.4943 | -1.5285 | -2.5416 | 0.7660 | 1.0131 | -507.4219 | -429.2431 | -0.8138 | -0.7980 |
75
+ | 0.4635 | 0.5234 | 1000 | 0.4908 | -2.8177 | -4.0337 | 0.7630 | 1.2160 | -656.6334 | -558.1610 | -0.8713 | -0.8521 |
76
+ | 0.4856 | 0.5758 | 1100 | 0.4817 | -2.3661 | -3.4921 | 0.7720 | 1.1260 | -602.4694 | -512.9990 | -0.8044 | -0.7913 |
77
+ | 0.5013 | 0.6281 | 1200 | 0.4860 | -2.1162 | -3.2907 | 0.7720 | 1.1745 | -582.3287 | -488.0108 | -0.7890 | -0.7745 |
78
+ | 0.4497 | 0.6805 | 1300 | 0.4850 | -2.4840 | -3.7371 | 0.7730 | 1.2531 | -626.9694 | -524.7895 | -0.8096 | -0.7940 |
79
+ | 0.4734 | 0.7328 | 1400 | 0.4833 | -2.1466 | -3.3699 | 0.7740 | 1.2233 | -590.2520 | -491.0496 | -0.8148 | -0.7990 |
80
+ | 0.4482 | 0.7851 | 1500 | 0.4812 | -2.5061 | -3.7160 | 0.7760 | 1.2100 | -624.8656 | -527.0021 | -0.8423 | -0.8246 |
81
+ | 0.4982 | 0.8375 | 1600 | 0.4787 | -2.2293 | -3.3886 | 0.7770 | 1.1593 | -592.1224 | -499.3264 | -0.8377 | -0.8203 |
82
+ | 0.4594 | 0.8898 | 1700 | 0.4790 | -2.3679 | -3.5723 | 0.7730 | 1.2044 | -610.4911 | -513.1796 | -0.8566 | -0.8379 |
83
+ | 0.4551 | 0.9422 | 1800 | 0.4786 | -2.3275 | -3.5261 | 0.7730 | 1.1986 | -605.8722 | -509.1397 | -0.8587 | -0.8397 |
84
+ | 0.4605 | 0.9945 | 1900 | 0.4785 | -2.3086 | -3.5093 | 0.7740 | 1.2007 | -604.1885 | -507.2548 | -0.8544 | -0.8360 |
85
+
86
+
87
+ ### Framework versions
88
+
89
+ - PEFT 0.11.1
90
+ - Transformers 4.41.0
91
+ - Pytorch 2.3.0+cu121
92
+ - Datasets 2.19.1
93
+ - Tokenizers 0.19.1
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ea57a040b61dc6cabbaaf5844925667c397543350d6b4fd4d16e5a041e13fa7
3
  size 671150064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:521cf32b5deef7914694e46bf9a97d58c6f4c30486e572a01968517f276321c2
3
  size 671150064
all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9997382884061764,
3
+ "total_flos": 0.0,
4
+ "train_loss": 0.504705511212973,
5
+ "train_runtime": 53071.3067,
6
+ "train_samples": 61134,
7
+ "train_samples_per_second": 1.152,
8
+ "train_steps_per_second": 0.036
9
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9997382884061764,
3
+ "total_flos": 0.0,
4
+ "train_loss": 0.504705511212973,
5
+ "train_runtime": 53071.3067,
6
+ "train_samples": 61134,
7
+ "train_samples_per_second": 1.152,
8
+ "train_steps_per_second": 0.036
9
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff