g8a9 commited on
Commit
f2ef6c0
·
1 Parent(s): 5187c9e

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +94 -0
README.md ADDED
@@ -0,0 +1,94 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: gpt2-no_ear-loto_jews
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
+ # gpt2-no_ear-loto_jews
14
+
15
+ This model is a fine-tuned version of [gpt2-medium](https://huggingface.co/gpt2-medium) on an unknown dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 0.5270
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 5e-05
37
+ - train_batch_size: 8
38
+ - eval_batch_size: 4
39
+ - seed: 21
40
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
+ - lr_scheduler_type: linear
42
+ - lr_scheduler_warmup_ratio: 0.1
43
+ - num_epochs: 3.0
44
+
45
+ ### Training results
46
+
47
+ | Training Loss | Epoch | Step | Validation Loss |
48
+ |:-------------:|:-----:|:----:|:---------------:|
49
+ | 72.9514 | 0.03 | 10 | 65.3603 |
50
+ | 32.1127 | 0.06 | 20 | 18.4547 |
51
+ | 8.2152 | 0.08 | 30 | 6.7267 |
52
+ | 3.4911 | 0.11 | 40 | 2.9798 |
53
+ | 1.6339 | 0.14 | 50 | 1.2141 |
54
+ | 0.8984 | 0.17 | 60 | 0.9466 |
55
+ | 0.8166 | 0.2 | 70 | 0.7656 |
56
+ | 0.6533 | 0.23 | 80 | 0.6374 |
57
+ | 0.6208 | 0.25 | 90 | 0.6106 |
58
+ | 0.6942 | 0.28 | 100 | 0.5941 |
59
+ | 0.6241 | 0.31 | 110 | 0.5825 |
60
+ | 0.736 | 0.34 | 120 | 0.5790 |
61
+ | 0.5359 | 0.37 | 130 | 0.5745 |
62
+ | 0.6451 | 0.4 | 140 | 0.5694 |
63
+ | 0.5871 | 0.42 | 150 | 0.5625 |
64
+ | 0.6146 | 0.45 | 160 | 0.5635 |
65
+ | 0.5091 | 0.48 | 170 | 0.5578 |
66
+ | 0.5911 | 0.51 | 180 | 0.5580 |
67
+ | 0.5398 | 0.54 | 190 | 0.5528 |
68
+ | 0.6379 | 0.57 | 200 | 0.5484 |
69
+ | 0.5205 | 0.59 | 210 | 0.5481 |
70
+ | 0.5752 | 0.62 | 220 | 0.5448 |
71
+ | 0.6035 | 0.65 | 230 | 0.5419 |
72
+ | 0.5582 | 0.68 | 240 | 0.5417 |
73
+ | 0.5331 | 0.71 | 250 | 0.5407 |
74
+ | 0.5062 | 0.74 | 260 | 0.5398 |
75
+ | 0.562 | 0.76 | 270 | 0.5375 |
76
+ | 0.5845 | 0.79 | 280 | 0.5332 |
77
+ | 0.4904 | 0.82 | 290 | 0.5317 |
78
+ | 0.596 | 0.85 | 300 | 0.5303 |
79
+ | 0.5976 | 0.88 | 310 | 0.5298 |
80
+ | 0.5614 | 0.91 | 320 | 0.5284 |
81
+ | 0.6057 | 0.93 | 330 | 0.5287 |
82
+ | 0.4378 | 0.96 | 340 | 0.5290 |
83
+ | 0.6069 | 0.99 | 350 | 0.5267 |
84
+ | 0.4918 | 1.02 | 360 | 0.5291 |
85
+ | 0.5506 | 1.05 | 370 | 0.5315 |
86
+ | 0.4013 | 1.08 | 380 | 0.5270 |
87
+
88
+
89
+ ### Framework versions
90
+
91
+ - Transformers 4.28.0
92
+ - Pytorch 1.11.0+cu113
93
+ - Datasets 2.11.0
94
+ - Tokenizers 0.13.3