rbelanec commited on
Commit
7a2643d
verified
1 Parent(s): 783fff7

Model save

Browse files
Files changed (1) hide show
  1. README.md +81 -0
README.md ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_boolq_123_1762589801
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_boolq_123_1762589801
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: 0.3213
21
+ - Num Input Tokens Seen: 42678144
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: 0.03
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: 20
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Input Tokens Seen |
52
+ |:-------------:|:-----:|:-----:|:---------------:|:-----------------:|
53
+ | 0.2872 | 1.0 | 2121 | 0.3391 | 2131904 |
54
+ | 0.3153 | 2.0 | 4242 | 0.3294 | 4264768 |
55
+ | 0.3251 | 3.0 | 6363 | 0.3346 | 6404896 |
56
+ | 0.3535 | 4.0 | 8484 | 0.3308 | 8537088 |
57
+ | 0.3267 | 5.0 | 10605 | 0.3278 | 10677088 |
58
+ | 0.3159 | 6.0 | 12726 | 0.3298 | 12814080 |
59
+ | 0.2604 | 7.0 | 14847 | 0.3271 | 14950432 |
60
+ | 0.3271 | 8.0 | 16968 | 0.3267 | 17082336 |
61
+ | 0.3257 | 9.0 | 19089 | 0.3424 | 19211360 |
62
+ | 0.3441 | 10.0 | 21210 | 0.3264 | 21342336 |
63
+ | 0.3417 | 11.0 | 23331 | 0.3277 | 23472352 |
64
+ | 0.3086 | 12.0 | 25452 | 0.3271 | 25602144 |
65
+ | 0.3027 | 13.0 | 27573 | 0.3251 | 27739072 |
66
+ | 0.3239 | 14.0 | 29694 | 0.3250 | 29880544 |
67
+ | 0.3697 | 15.0 | 31815 | 0.3236 | 32013760 |
68
+ | 0.3328 | 16.0 | 33936 | 0.3237 | 34138272 |
69
+ | 0.3275 | 17.0 | 36057 | 0.3222 | 36269152 |
70
+ | 0.3746 | 18.0 | 38178 | 0.3221 | 38408800 |
71
+ | 0.339 | 19.0 | 40299 | 0.3219 | 40541312 |
72
+ | 0.2792 | 20.0 | 42420 | 0.3213 | 42678144 |
73
+
74
+
75
+ ### Framework versions
76
+
77
+ - PEFT 0.15.2
78
+ - Transformers 4.51.3
79
+ - Pytorch 2.8.0+cu128
80
+ - Datasets 3.6.0
81
+ - Tokenizers 0.21.1