NasimB commited on
Commit
176e7a2
·
1 Parent(s): bbb1cca

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +78 -0
README.md ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - generator
7
+ model-index:
8
+ - name: guten-2p5k-new-loop-tokenize
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # guten-2p5k-new-loop-tokenize
16
+
17
+ This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the generator dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 4.3833
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 0.0005
39
+ - train_batch_size: 64
40
+ - eval_batch_size: 64
41
+ - seed: 42
42
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
+ - lr_scheduler_type: cosine
44
+ - lr_scheduler_warmup_steps: 1000
45
+ - num_epochs: 6
46
+ - mixed_precision_training: Native AMP
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss |
51
+ |:-------------:|:-----:|:----:|:---------------:|
52
+ | 6.721 | 0.31 | 500 | 5.7074 |
53
+ | 5.3696 | 0.63 | 1000 | 5.2582 |
54
+ | 5.0072 | 0.94 | 1500 | 5.0135 |
55
+ | 4.7225 | 1.26 | 2000 | 4.8583 |
56
+ | 4.5837 | 1.57 | 2500 | 4.7320 |
57
+ | 4.4669 | 1.89 | 3000 | 4.6175 |
58
+ | 4.2663 | 2.2 | 3500 | 4.5607 |
59
+ | 4.1693 | 2.51 | 4000 | 4.4896 |
60
+ | 4.1248 | 2.83 | 4500 | 4.4286 |
61
+ | 3.976 | 3.14 | 5000 | 4.4119 |
62
+ | 3.8481 | 3.46 | 5500 | 4.3787 |
63
+ | 3.8327 | 3.77 | 6000 | 4.3406 |
64
+ | 3.7401 | 4.09 | 6500 | 4.3356 |
65
+ | 3.5641 | 4.4 | 7000 | 4.3274 |
66
+ | 3.5468 | 4.71 | 7500 | 4.3126 |
67
+ | 3.5201 | 5.03 | 8000 | 4.3081 |
68
+ | 3.3625 | 5.34 | 8500 | 4.3132 |
69
+ | 3.3604 | 5.66 | 9000 | 4.3114 |
70
+ | 3.36 | 5.97 | 9500 | 4.3106 |
71
+
72
+
73
+ ### Framework versions
74
+
75
+ - Transformers 4.26.1
76
+ - Pytorch 1.11.0+cu113
77
+ - Datasets 2.13.0
78
+ - Tokenizers 0.13.3