Hugging Face's logo

rbelanec
/
train_hellaswag_101112_1760638083

Text Generation
PEFT
Safetensors
Transformers
llama-factory
lora
conversational
Model card Files
xet
Community
rbelanec commited on
Commit
a677ba1
路
verified 路
1 Parent(s): c126ecc

Model save

Browse files
Files changed (2) hide show
  1. README.md +84 -0
  2. adapter_model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: llama3
4
+ base_model: meta-llama/Meta-Llama-3-8B-Instruct
5
+ tags:
6
+ - base_model:adapter:meta-llama/Meta-Llama-3-8B-Instruct
7
+ - llama-factory
8
+ - lora
9
+ - transformers
10
+ pipeline_tag: text-generation
11
+ model-index:
12
+ - name: train_hellaswag_101112_1760638083
13
+ results: []
14
+ ---
15
+
16
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
+ should probably proofread and complete it, then remove this comment. -->
18
+
19
+ # train_hellaswag_101112_1760638083
20
+
21
+ 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.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 0.2429
24
+ - Num Input Tokens Seen: 218373904
25
+
26
+ ## Model description
27
+
28
+ More information needed
29
+
30
+ ## Intended uses & limitations
31
+
32
+ More information needed
33
+
34
+ ## Training and evaluation data
35
+
36
+ More information needed
37
+
38
+ ## Training procedure
39
+
40
+ ### Training hyperparameters
41
+
42
+ The following hyperparameters were used during training:
43
+ - learning_rate: 5e-05
44
+ - train_batch_size: 4
45
+ - eval_batch_size: 4
46
+ - seed: 101112
47
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
+ - lr_scheduler_type: cosine
49
+ - lr_scheduler_warmup_ratio: 0.1
50
+ - num_epochs: 20
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss | Input Tokens Seen |
55
+ |:-------------:|:-----:|:------:|:---------------:|:-----------------:|
56
+ | 0.0089 | 1.0 | 8979 | 0.0911 | 10920768 |
57
+ | 0.0957 | 2.0 | 17958 | 0.0606 | 21838176 |
58
+ | 0.1047 | 3.0 | 26937 | 0.0671 | 32764400 |
59
+ | 0.0001 | 4.0 | 35916 | 0.0873 | 43678848 |
60
+ | 0.0939 | 5.0 | 44895 | 0.0949 | 54599824 |
61
+ | 0.0267 | 6.0 | 53874 | 0.1401 | 65511392 |
62
+ | 0.0 | 7.0 | 62853 | 0.1377 | 76440704 |
63
+ | 0.0018 | 8.0 | 71832 | 0.1116 | 87358976 |
64
+ | 0.1397 | 9.0 | 80811 | 0.1159 | 98270752 |
65
+ | 0.0 | 10.0 | 89790 | 0.1133 | 109182912 |
66
+ | 0.0 | 11.0 | 98769 | 0.1682 | 120100304 |
67
+ | 0.0 | 12.0 | 107748 | 0.1336 | 131010176 |
68
+ | 0.0 | 13.0 | 116727 | 0.1828 | 141940544 |
69
+ | 0.0 | 14.0 | 125706 | 0.2001 | 152867360 |
70
+ | 0.0 | 15.0 | 134685 | 0.2017 | 163792736 |
71
+ | 0.0 | 16.0 | 143664 | 0.2334 | 174711344 |
72
+ | 0.0 | 17.0 | 152643 | 0.2356 | 185629312 |
73
+ | 0.0 | 18.0 | 161622 | 0.2409 | 196536784 |
74
+ | 0.0 | 19.0 | 170601 | 0.2430 | 207451408 |
75
+ | 0.0 | 20.0 | 179580 | 0.2429 | 218373904 |
76
+
77
+
78
+ ### Framework versions
79
+
80
+ - PEFT 0.17.1
81
+ - Transformers 4.51.3
82
+ - Pytorch 2.9.0+cu128
83
+ - Datasets 4.0.0
84
+ - Tokenizers 0.21.4
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:61ccd9f99cf358a42be06c463a238b658f02651092c98756461a6925c65c42c5
3
  size 58745928
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a77e8018193958ad29703fd72eaad876f6a7a66bd73fff4e05e43732e4cbe83
3
  size 58745928