yumiian commited on
Commit
ca9ba64
verified
1 Parent(s): bc708d9

End of training

Browse files
Files changed (1) hide show
  1. README.md +77 -0
README.md ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ base_model: mesolitica/finetune-qa-t5-small-standard-bahasa-cased
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: qa_en_ms_model_v3
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # qa_en_ms_model_v3
15
+
16
+ This model is a fine-tuned version of [mesolitica/finetune-qa-t5-small-standard-bahasa-cased](https://huggingface.co/mesolitica/finetune-qa-t5-small-standard-bahasa-cased) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 0.8296
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 2e-05
38
+ - train_batch_size: 24
39
+ - eval_batch_size: 24
40
+ - seed: 42
41
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
42
+ - lr_scheduler_type: linear
43
+ - num_epochs: 20
44
+ - mixed_precision_training: Native AMP
45
+
46
+ ### Training results
47
+
48
+ | Training Loss | Epoch | Step | Validation Loss |
49
+ |:-------------:|:-----:|:-----:|:---------------:|
50
+ | 1.3752 | 1.0 | 1047 | 1.0868 |
51
+ | 1.1233 | 2.0 | 2094 | 0.9799 |
52
+ | 1.0295 | 3.0 | 3141 | 0.9326 |
53
+ | 0.9485 | 4.0 | 4188 | 0.9051 |
54
+ | 0.8883 | 5.0 | 5235 | 0.8748 |
55
+ | 0.8485 | 6.0 | 6282 | 0.8605 |
56
+ | 0.8243 | 7.0 | 7329 | 0.8485 |
57
+ | 0.7977 | 8.0 | 8376 | 0.8417 |
58
+ | 0.7597 | 9.0 | 9423 | 0.8286 |
59
+ | 0.7495 | 10.0 | 10470 | 0.8306 |
60
+ | 0.7211 | 11.0 | 11517 | 0.8255 |
61
+ | 0.7076 | 12.0 | 12564 | 0.8291 |
62
+ | 0.7012 | 13.0 | 13611 | 0.8350 |
63
+ | 0.6833 | 14.0 | 14658 | 0.8288 |
64
+ | 0.6687 | 15.0 | 15705 | 0.8230 |
65
+ | 0.6574 | 16.0 | 16752 | 0.8313 |
66
+ | 0.6342 | 17.0 | 17799 | 0.8239 |
67
+ | 0.6419 | 18.0 | 18846 | 0.8271 |
68
+ | 0.6451 | 19.0 | 19893 | 0.8302 |
69
+ | 0.6278 | 20.0 | 20940 | 0.8296 |
70
+
71
+
72
+ ### Framework versions
73
+
74
+ - Transformers 4.52.4
75
+ - Pytorch 2.5.1+cu121
76
+ - Datasets 3.6.0
77
+ - Tokenizers 0.21.1