Hugging Face's logo

NasimB
/
gpt2_left_out_qed

Text Generation
Transformers
PyTorch
gpt2
Generated from Trainer
text-generation-inference
Model card Files
xet
Community
1
NasimB commited on
Commit
052dfef
·
1 Parent(s): d04cf53

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +96 -0
README.md ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - generator
7
+ model-index:
8
+ - name: gpt2_left_out_qed
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
+ # gpt2_left_out_qed
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: 3.9486
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: 10
46
+ - mixed_precision_training: Native AMP
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss |
51
+ |:-------------:|:-----:|:-----:|:---------------:|
52
+ | 5.9695 | 0.27 | 500 | 5.0679 |
53
+ | 4.7417 | 0.53 | 1000 | 4.6811 |
54
+ | 4.4136 | 0.8 | 1500 | 4.4369 |
55
+ | 4.2076 | 1.06 | 2000 | 4.2985 |
56
+ | 4.0279 | 1.33 | 2500 | 4.2048 |
57
+ | 3.9505 | 1.59 | 3000 | 4.1137 |
58
+ | 3.8781 | 1.86 | 3500 | 4.0482 |
59
+ | 3.7338 | 2.12 | 4000 | 4.0046 |
60
+ | 3.6392 | 2.39 | 4500 | 3.9628 |
61
+ | 3.6228 | 2.65 | 5000 | 3.9115 |
62
+ | 3.5944 | 2.92 | 5500 | 3.8738 |
63
+ | 3.4222 | 3.18 | 6000 | 3.8797 |
64
+ | 3.3836 | 3.45 | 6500 | 3.8576 |
65
+ | 3.3995 | 3.71 | 7000 | 3.8251 |
66
+ | 3.3827 | 3.98 | 7500 | 3.7995 |
67
+ | 3.1568 | 4.24 | 8000 | 3.8348 |
68
+ | 3.1778 | 4.51 | 8500 | 3.8171 |
69
+ | 3.1853 | 4.77 | 9000 | 3.7963 |
70
+ | 3.1451 | 5.04 | 9500 | 3.8059 |
71
+ | 2.9278 | 5.31 | 10000 | 3.8298 |
72
+ | 2.9608 | 5.57 | 10500 | 3.8176 |
73
+ | 2.9762 | 5.84 | 11000 | 3.8047 |
74
+ | 2.8716 | 6.1 | 11500 | 3.8433 |
75
+ | 2.7239 | 6.37 | 12000 | 3.8523 |
76
+ | 2.7435 | 6.63 | 12500 | 3.8541 |
77
+ | 2.7524 | 6.9 | 13000 | 3.8446 |
78
+ | 2.6032 | 7.16 | 13500 | 3.8854 |
79
+ | 2.5322 | 7.43 | 14000 | 3.8967 |
80
+ | 2.5369 | 7.69 | 14500 | 3.8983 |
81
+ | 2.5467 | 7.96 | 15000 | 3.8966 |
82
+ | 2.3979 | 8.22 | 15500 | 3.9284 |
83
+ | 2.3767 | 8.49 | 16000 | 3.9334 |
84
+ | 2.3852 | 8.75 | 16500 | 3.9357 |
85
+ | 2.3805 | 9.02 | 17000 | 3.9395 |
86
+ | 2.3012 | 9.28 | 17500 | 3.9463 |
87
+ | 2.3044 | 9.55 | 18000 | 3.9484 |
88
+ | 2.3007 | 9.81 | 18500 | 3.9486 |
89
+
90
+
91
+ ### Framework versions
92
+
93
+ - Transformers 4.26.1
94
+ - Pytorch 1.11.0+cu113
95
+ - Datasets 2.13.0
96
+ - Tokenizers 0.13.3