WillHeld commited on
Commit
95eb869
1 Parent(s): 3d37b51

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +73 -0
README.md ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: byt5-base-cstop_artificial
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # byt5-base-cstop_artificial
14
+
15
+ This model is a fine-tuned version of [google/byt5-base](https://huggingface.co/google/byt5-base) on the None dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 0.0745
18
+ - Exact Match: 0.0394
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: 0.001
38
+ - train_batch_size: 8
39
+ - eval_batch_size: 8
40
+ - seed: 42
41
+ - gradient_accumulation_steps: 64
42
+ - total_train_batch_size: 512
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - training_steps: 3000
46
+
47
+ ### Training results
48
+
49
+ | Training Loss | Epoch | Step | Validation Loss | Exact Match |
50
+ |:-------------:|:------:|:----:|:---------------:|:-----------:|
51
+ | 0.2563 | 28.5 | 200 | 0.0461 | 0.0376 |
52
+ | 0.0065 | 57.13 | 400 | 0.0563 | 0.0376 |
53
+ | 0.0021 | 85.63 | 600 | 0.0592 | 0.0358 |
54
+ | 0.0013 | 114.25 | 800 | 0.0569 | 0.0376 |
55
+ | 0.0008 | 142.75 | 1000 | 0.0675 | 0.0358 |
56
+ | 0.0007 | 171.38 | 1200 | 0.0627 | 0.0394 |
57
+ | 0.0004 | 199.88 | 1400 | 0.0677 | 0.0358 |
58
+ | 0.0003 | 228.5 | 1600 | 0.0650 | 0.0376 |
59
+ | 0.0002 | 257.13 | 1800 | 0.0693 | 0.0394 |
60
+ | 0.0002 | 285.63 | 2000 | 0.0721 | 0.0394 |
61
+ | 0.0002 | 314.25 | 2200 | 0.0714 | 0.0376 |
62
+ | 0.0002 | 342.75 | 2400 | 0.0701 | 0.0394 |
63
+ | 0.0002 | 371.38 | 2600 | 0.0750 | 0.0394 |
64
+ | 0.0001 | 399.88 | 2800 | 0.0739 | 0.0394 |
65
+ | 0.0001 | 428.5 | 3000 | 0.0745 | 0.0394 |
66
+
67
+
68
+ ### Framework versions
69
+
70
+ - Transformers 4.24.0
71
+ - Pytorch 1.13.0+cu117
72
+ - Datasets 2.7.0
73
+ - Tokenizers 0.13.2