aabidk commited on
Commit
be257cf
1 Parent(s): 3d7b7de

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +111 -0
README.md ADDED
@@ -0,0 +1,111 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: distilgpt2
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: distilgpt2-sd
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
+ # distilgpt2-sd
15
+
16
+ This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 1.4481
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: 5e-05
38
+ - train_batch_size: 8
39
+ - eval_batch_size: 8
40
+ - seed: 42
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: linear
43
+ - num_epochs: 3
44
+
45
+ ### Training results
46
+
47
+ | Training Loss | Epoch | Step | Validation Loss |
48
+ |:-------------:|:-----:|:-----:|:---------------:|
49
+ | 3.36 | 0.05 | 500 | 2.8209 |
50
+ | 2.8086 | 0.11 | 1000 | 2.5757 |
51
+ | 2.6126 | 0.16 | 1500 | 2.4096 |
52
+ | 2.4771 | 0.22 | 2000 | 2.3027 |
53
+ | 2.3986 | 0.27 | 2500 | 2.2076 |
54
+ | 2.3148 | 0.33 | 3000 | 2.1547 |
55
+ | 2.237 | 0.38 | 3500 | 2.0825 |
56
+ | 2.1731 | 0.43 | 4000 | 2.0334 |
57
+ | 2.1256 | 0.49 | 4500 | 1.9806 |
58
+ | 2.081 | 0.54 | 5000 | 1.9345 |
59
+ | 2.0677 | 0.6 | 5500 | 1.9053 |
60
+ | 1.9794 | 0.65 | 6000 | 1.8691 |
61
+ | 2.0072 | 0.71 | 6500 | 1.8429 |
62
+ | 1.9597 | 0.76 | 7000 | 1.8061 |
63
+ | 1.9318 | 0.82 | 7500 | 1.7857 |
64
+ | 1.9283 | 0.87 | 8000 | 1.7610 |
65
+ | 1.8959 | 0.92 | 8500 | 1.7378 |
66
+ | 1.8626 | 0.98 | 9000 | 1.7185 |
67
+ | 1.8126 | 1.03 | 9500 | 1.7040 |
68
+ | 1.7789 | 1.09 | 10000 | 1.6855 |
69
+ | 1.7794 | 1.14 | 10500 | 1.6756 |
70
+ | 1.7284 | 1.2 | 11000 | 1.6529 |
71
+ | 1.7478 | 1.25 | 11500 | 1.6384 |
72
+ | 1.7065 | 1.3 | 12000 | 1.6321 |
73
+ | 1.7092 | 1.36 | 12500 | 1.6133 |
74
+ | 1.6897 | 1.41 | 13000 | 1.6146 |
75
+ | 1.6902 | 1.47 | 13500 | 1.5952 |
76
+ | 1.6888 | 1.52 | 14000 | 1.5792 |
77
+ | 1.6862 | 1.58 | 14500 | 1.5730 |
78
+ | 1.6458 | 1.63 | 15000 | 1.5661 |
79
+ | 1.6594 | 1.68 | 15500 | 1.5537 |
80
+ | 1.6486 | 1.74 | 16000 | 1.5484 |
81
+ | 1.6556 | 1.79 | 16500 | 1.5360 |
82
+ | 1.6187 | 1.85 | 17000 | 1.5264 |
83
+ | 1.6377 | 1.9 | 17500 | 1.5223 |
84
+ | 1.6129 | 1.96 | 18000 | 1.5180 |
85
+ | 1.6025 | 2.01 | 18500 | 1.5030 |
86
+ | 1.5697 | 2.06 | 19000 | 1.4991 |
87
+ | 1.5616 | 2.12 | 19500 | 1.5012 |
88
+ | 1.558 | 2.17 | 20000 | 1.4984 |
89
+ | 1.549 | 2.23 | 20500 | 1.4809 |
90
+ | 1.5048 | 2.28 | 21000 | 1.4827 |
91
+ | 1.5207 | 2.34 | 21500 | 1.4740 |
92
+ | 1.5097 | 2.39 | 22000 | 1.4699 |
93
+ | 1.541 | 2.45 | 22500 | 1.4701 |
94
+ | 1.5355 | 2.5 | 23000 | 1.4637 |
95
+ | 1.5318 | 2.55 | 23500 | 1.4609 |
96
+ | 1.5352 | 2.61 | 24000 | 1.4580 |
97
+ | 1.5202 | 2.66 | 24500 | 1.4566 |
98
+ | 1.5073 | 2.72 | 25000 | 1.4547 |
99
+ | 1.5462 | 2.77 | 25500 | 1.4520 |
100
+ | 1.5347 | 2.83 | 26000 | 1.4491 |
101
+ | 1.52 | 2.88 | 26500 | 1.4488 |
102
+ | 1.5154 | 2.93 | 27000 | 1.4475 |
103
+ | 1.4855 | 2.99 | 27500 | 1.4481 |
104
+
105
+
106
+ ### Framework versions
107
+
108
+ - Transformers 4.31.0
109
+ - Pytorch 2.0.1+cu118
110
+ - Datasets 2.13.1
111
+ - Tokenizers 0.13.3