Hugging Face's logo

rbelanec
/
train_hellaswag_1754652170

PEFT
Safetensors
llama-factory
prefix-tuning
Generated from Trainer
Model card Files
xet
Community
rbelanec commited on
Commit
49e29a6
路
verified 路
1 Parent(s): cca8a4f

Model save

Browse files
Files changed (2) hide show
  1. README.md +80 -0
  2. adapter_model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: llama3
4
+ base_model: meta-llama/Meta-Llama-3-8B-Instruct
5
+ tags:
6
+ - llama-factory
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: train_hellaswag_1754652170
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
+ # train_hellaswag_1754652170
17
+
18
+ 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 an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.4641
21
+ - Num Input Tokens Seen: 103491728
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 5e-05
41
+ - train_batch_size: 4
42
+ - eval_batch_size: 4
43
+ - seed: 123
44
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
+ - lr_scheduler_type: cosine
46
+ - lr_scheduler_warmup_ratio: 0.1
47
+ - num_epochs: 10.0
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Input Tokens Seen |
52
+ |:-------------:|:------:|:-----:|:---------------:|:-----------------:|
53
+ | 0.5018 | 0.5001 | 4490 | 0.5131 | 5450816 |
54
+ | 0.4862 | 1.0001 | 8980 | 0.4738 | 10899840 |
55
+ | 0.4703 | 1.5002 | 13470 | 0.4673 | 16338976 |
56
+ | 0.4736 | 2.0002 | 17960 | 0.4660 | 21789168 |
57
+ | 0.4783 | 2.5003 | 22450 | 0.4658 | 27236592 |
58
+ | 0.4663 | 3.0003 | 26940 | 0.4649 | 32696128 |
59
+ | 0.4541 | 3.5004 | 31430 | 0.4646 | 38137920 |
60
+ | 0.4581 | 4.0004 | 35920 | 0.4643 | 43579472 |
61
+ | 0.4528 | 4.5005 | 40410 | 0.4643 | 49022960 |
62
+ | 0.4502 | 5.0006 | 44900 | 0.4639 | 54468496 |
63
+ | 0.4639 | 5.5006 | 49390 | 0.4635 | 59917136 |
64
+ | 0.4624 | 6.0007 | 53880 | 0.4643 | 65358976 |
65
+ | 0.4692 | 6.5007 | 58370 | 0.4642 | 70806016 |
66
+ | 0.4549 | 7.0008 | 62860 | 0.4644 | 76259312 |
67
+ | 0.4698 | 7.5008 | 67350 | 0.4640 | 81705616 |
68
+ | 0.4546 | 8.0009 | 71840 | 0.4641 | 87153488 |
69
+ | 0.4462 | 8.5009 | 76330 | 0.4635 | 92602480 |
70
+ | 0.4564 | 9.0010 | 80820 | 0.4640 | 98051504 |
71
+ | 0.466 | 9.5011 | 85310 | 0.4641 | 103491728 |
72
+
73
+
74
+ ### Framework versions
75
+
76
+ - PEFT 0.15.2
77
+ - Transformers 4.51.3
78
+ - Pytorch 2.8.0+cu128
79
+ - Datasets 3.6.0
80
+ - Tokenizers 0.21.1
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:963f6c017cbe79224fe76dbe1ee72219d319415df29bc671163960d62dda61bd
3
  size 26214528
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:731f10df40c1de479846841b288323333b43d913135894d8786621681bc8d6de
3
  size 26214528