jkhan447 commited on
Commit
ce6456f
·
1 Parent(s): 277d440

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +140 -0
README.md ADDED
@@ -0,0 +1,140 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: gpt2-medium
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: results
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
+ # results
15
+
16
+ This model is a fine-tuned version of [gpt2-medium](https://huggingface.co/gpt2-medium) on the None dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 0.9560
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
+ | 0.8376 | 0.04 | 50 | 0.6634 |
50
+ | 0.564 | 0.07 | 100 | 0.5862 |
51
+ | 0.6271 | 0.11 | 150 | 0.5533 |
52
+ | 0.6125 | 0.14 | 200 | 0.5456 |
53
+ | 0.7069 | 0.18 | 250 | 0.5478 |
54
+ | 0.6945 | 0.21 | 300 | 0.5811 |
55
+ | 0.7125 | 0.25 | 350 | 0.6016 |
56
+ | 0.5495 | 0.29 | 400 | 0.5479 |
57
+ | 0.5943 | 0.32 | 450 | 0.6216 |
58
+ | 0.5727 | 0.36 | 500 | 0.5383 |
59
+ | 0.6411 | 0.39 | 550 | 0.5331 |
60
+ | 0.5362 | 0.43 | 600 | 0.5235 |
61
+ | 0.4939 | 0.46 | 650 | 0.5226 |
62
+ | 0.5034 | 0.5 | 700 | 0.5358 |
63
+ | 0.528 | 0.54 | 750 | 0.5729 |
64
+ | 0.6313 | 0.57 | 800 | 0.5339 |
65
+ | 0.4727 | 0.61 | 850 | 0.5055 |
66
+ | 0.472 | 0.64 | 900 | 0.5016 |
67
+ | 0.7186 | 0.68 | 950 | 0.5162 |
68
+ | 0.5895 | 0.71 | 1000 | 0.4998 |
69
+ | 0.5312 | 0.75 | 1050 | 0.4987 |
70
+ | 0.6059 | 0.79 | 1100 | 0.4991 |
71
+ | 0.536 | 0.82 | 1150 | 0.4849 |
72
+ | 0.4559 | 0.86 | 1200 | 0.4963 |
73
+ | 0.4382 | 0.89 | 1250 | 0.5148 |
74
+ | 0.5866 | 0.93 | 1300 | 0.5319 |
75
+ | 0.5382 | 0.96 | 1350 | 0.5145 |
76
+ | 0.5006 | 1.0 | 1400 | 0.5000 |
77
+ | 0.336 | 1.04 | 1450 | 0.4846 |
78
+ | 0.5228 | 1.07 | 1500 | 0.5092 |
79
+ | 0.549 | 1.11 | 1550 | 0.4925 |
80
+ | 0.4061 | 1.14 | 1600 | 0.5010 |
81
+ | 0.3972 | 1.18 | 1650 | 0.5194 |
82
+ | 0.4721 | 1.21 | 1700 | 0.4919 |
83
+ | 0.47 | 1.25 | 1750 | 0.5485 |
84
+ | 0.5275 | 1.29 | 1800 | 0.5080 |
85
+ | 0.4819 | 1.32 | 1850 | 0.5871 |
86
+ | 0.6606 | 1.36 | 1900 | 0.4946 |
87
+ | 0.5049 | 1.39 | 1950 | 0.5406 |
88
+ | 0.3779 | 1.43 | 2000 | 0.4913 |
89
+ | 0.5383 | 1.46 | 2050 | 0.4894 |
90
+ | 0.5097 | 1.5 | 2100 | 0.4905 |
91
+ | 0.5123 | 1.54 | 2150 | 0.4913 |
92
+ | 0.5565 | 1.57 | 2200 | 0.5117 |
93
+ | 0.4505 | 1.61 | 2250 | 0.5118 |
94
+ | 0.4465 | 1.64 | 2300 | 0.5078 |
95
+ | 0.5235 | 1.68 | 2350 | 0.5291 |
96
+ | 0.4292 | 1.71 | 2400 | 0.5221 |
97
+ | 0.3368 | 1.75 | 2450 | 0.5458 |
98
+ | 0.4065 | 1.79 | 2500 | 0.4915 |
99
+ | 0.4071 | 1.82 | 2550 | 0.5036 |
100
+ | 0.3895 | 1.86 | 2600 | 0.5139 |
101
+ | 0.4386 | 1.89 | 2650 | 0.5237 |
102
+ | 0.4839 | 1.93 | 2700 | 0.5086 |
103
+ | 0.3664 | 1.96 | 2750 | 0.4983 |
104
+ | 0.4612 | 2.0 | 2800 | 0.5170 |
105
+ | 0.453 | 2.04 | 2850 | 0.5584 |
106
+ | 0.1697 | 2.07 | 2900 | 0.6988 |
107
+ | 0.1763 | 2.11 | 2950 | 0.7424 |
108
+ | 0.2462 | 2.14 | 3000 | 0.8796 |
109
+ | 0.2649 | 2.18 | 3050 | 0.8260 |
110
+ | 0.3356 | 2.21 | 3100 | 0.7895 |
111
+ | 0.2405 | 2.25 | 3150 | 0.7047 |
112
+ | 0.0817 | 2.29 | 3200 | 0.8783 |
113
+ | 0.3479 | 2.32 | 3250 | 0.9104 |
114
+ | 0.2727 | 2.36 | 3300 | 0.9068 |
115
+ | 0.4241 | 2.39 | 3350 | 0.8165 |
116
+ | 0.2049 | 2.43 | 3400 | 0.7577 |
117
+ | 0.0979 | 2.46 | 3450 | 0.7535 |
118
+ | 0.3515 | 2.5 | 3500 | 0.9019 |
119
+ | 0.2383 | 2.54 | 3550 | 0.9160 |
120
+ | 0.1699 | 2.57 | 3600 | 1.0081 |
121
+ | 0.4976 | 2.61 | 3650 | 0.9987 |
122
+ | 0.5569 | 2.64 | 3700 | 0.9384 |
123
+ | 0.1119 | 2.68 | 3750 | 0.9036 |
124
+ | 0.3534 | 2.71 | 3800 | 0.9264 |
125
+ | 0.2139 | 2.75 | 3850 | 0.9323 |
126
+ | 0.2664 | 2.79 | 3900 | 0.9292 |
127
+ | 0.4916 | 2.82 | 3950 | 0.9459 |
128
+ | 0.2375 | 2.86 | 4000 | 0.9806 |
129
+ | 0.2114 | 2.89 | 4050 | 1.0095 |
130
+ | 0.2557 | 2.93 | 4100 | 0.9989 |
131
+ | 0.2056 | 2.96 | 4150 | 0.9937 |
132
+ | 0.2332 | 3.0 | 4200 | 0.9942 |
133
+
134
+
135
+ ### Framework versions
136
+
137
+ - Transformers 4.31.0
138
+ - Pytorch 2.0.1+cu118
139
+ - Datasets 2.14.4
140
+ - Tokenizers 0.13.3