rbelanec commited on
Commit
2d27492
verified
1 Parent(s): c60f932

Model save

Browse files
Files changed (1) hide show
  1. README.md +83 -0
README.md ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ - transformers
9
+ pipeline_tag: text-generation
10
+ model-index:
11
+ - name: train_svamp_101112_1760638004
12
+ results: []
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+ # train_svamp_101112_1760638004
19
+
20
+ 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.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 0.2142
23
+ - Num Input Tokens Seen: 1430592
24
+
25
+ ## Model description
26
+
27
+ More information needed
28
+
29
+ ## Intended uses & limitations
30
+
31
+ More information needed
32
+
33
+ ## Training and evaluation data
34
+
35
+ More information needed
36
+
37
+ ## Training procedure
38
+
39
+ ### Training hyperparameters
40
+
41
+ The following hyperparameters were used during training:
42
+ - learning_rate: 5e-05
43
+ - train_batch_size: 4
44
+ - eval_batch_size: 4
45
+ - seed: 101112
46
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
47
+ - lr_scheduler_type: cosine
48
+ - lr_scheduler_warmup_ratio: 0.1
49
+ - num_epochs: 20
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Input Tokens Seen |
54
+ |:-------------:|:-----:|:----:|:---------------:|:-----------------:|
55
+ | 2.4702 | 1.0 | 158 | 2.4417 | 71552 |
56
+ | 1.5492 | 2.0 | 316 | 1.5887 | 142960 |
57
+ | 0.8332 | 3.0 | 474 | 0.9196 | 214432 |
58
+ | 0.4267 | 4.0 | 632 | 0.5329 | 286000 |
59
+ | 0.2682 | 5.0 | 790 | 0.3736 | 357888 |
60
+ | 0.1618 | 6.0 | 948 | 0.3068 | 429456 |
61
+ | 0.1109 | 7.0 | 1106 | 0.2751 | 501136 |
62
+ | 0.1032 | 8.0 | 1264 | 0.2582 | 573104 |
63
+ | 0.1209 | 9.0 | 1422 | 0.2467 | 644752 |
64
+ | 0.1224 | 10.0 | 1580 | 0.2368 | 716192 |
65
+ | 0.0463 | 11.0 | 1738 | 0.2299 | 787200 |
66
+ | 0.1375 | 12.0 | 1896 | 0.2260 | 858736 |
67
+ | 0.1195 | 13.0 | 2054 | 0.2231 | 930160 |
68
+ | 0.0919 | 14.0 | 2212 | 0.2209 | 1001792 |
69
+ | 0.0831 | 15.0 | 2370 | 0.2172 | 1073248 |
70
+ | 0.0659 | 16.0 | 2528 | 0.2180 | 1144672 |
71
+ | 0.0959 | 17.0 | 2686 | 0.2169 | 1216160 |
72
+ | 0.0386 | 18.0 | 2844 | 0.2155 | 1287728 |
73
+ | 0.0871 | 19.0 | 3002 | 0.2143 | 1359120 |
74
+ | 0.0834 | 20.0 | 3160 | 0.2142 | 1430592 |
75
+
76
+
77
+ ### Framework versions
78
+
79
+ - PEFT 0.17.1
80
+ - Transformers 4.51.3
81
+ - Pytorch 2.9.0+cu128
82
+ - Datasets 4.0.0
83
+ - Tokenizers 0.21.4