Hugging Face's logo

joshcarp
/
gpt2-evy

Text Generation
Transformers
Safetensors
gpt2
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
joshcarp commited on
Commit
d204061
•
1 Parent(s): a9515a3

Model save

Browse files
Files changed (4) hide show
  1. README.md +25 -105
  2. config.json +1 -1
  3. model.safetensors +1 -1
  4. training_args.bin +1 -1
README.md CHANGED
@@ -1,8 +1,8 @@
1
  ---
2
  license: mit
 
3
  tags:
4
  - generated_from_trainer
5
- base_model: joshcarp/gpt2-evy
6
  model-index:
7
  - name: gpt2-evy
8
  results: []
@@ -13,9 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
13
 
14
  # gpt2-evy
15
 
16
- This model is a fine-tuned version of [joshcarp/gpt2-evy](https://huggingface.co/joshcarp/gpt2-evy) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 2.3017
19
 
20
  ## Model description
21
 
@@ -35,117 +35,37 @@ More information needed
35
 
36
  The following hyperparameters were used during training:
37
  - learning_rate: 5e-05
38
- - train_batch_size: 2
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: 100
44
 
45
  ### Training results
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
- | No log | 1.0 | 19 | 1.9775 |
50
- | No log | 2.0 | 38 | 2.0492 |
51
- | No log | 3.0 | 57 | 2.0643 |
52
- | No log | 4.0 | 76 | 2.0102 |
53
- | No log | 5.0 | 95 | 1.9851 |
54
- | 0.0382 | 6.0 | 114 | 1.9408 |
55
- | 0.0382 | 7.0 | 133 | 2.0678 |
56
- | 0.0382 | 8.0 | 152 | 2.0022 |
57
- | 0.0382 | 9.0 | 171 | 2.0112 |
58
- | 0.0382 | 10.0 | 190 | 2.0664 |
59
- | 0.0406 | 11.0 | 209 | 2.0646 |
60
- | 0.0406 | 12.0 | 228 | 2.0033 |
61
- | 0.0406 | 13.0 | 247 | 2.0783 |
62
- | 0.0406 | 14.0 | 266 | 2.0601 |
63
- | 0.0406 | 15.0 | 285 | 2.0172 |
64
- | 0.0381 | 16.0 | 304 | 2.0543 |
65
- | 0.0381 | 17.0 | 323 | 2.1309 |
66
- | 0.0381 | 18.0 | 342 | 2.0796 |
67
- | 0.0381 | 19.0 | 361 | 2.0456 |
68
- | 0.0381 | 20.0 | 380 | 2.1159 |
69
- | 0.0381 | 21.0 | 399 | 2.0979 |
70
- | 0.0324 | 22.0 | 418 | 2.0862 |
71
- | 0.0324 | 23.0 | 437 | 2.1196 |
72
- | 0.0324 | 24.0 | 456 | 2.1273 |
73
- | 0.0324 | 25.0 | 475 | 2.1860 |
74
- | 0.0324 | 26.0 | 494 | 2.0690 |
75
- | 0.0252 | 27.0 | 513 | 2.1172 |
76
- | 0.0252 | 28.0 | 532 | 2.1453 |
77
- | 0.0252 | 29.0 | 551 | 2.0990 |
78
- | 0.0252 | 30.0 | 570 | 2.1250 |
79
- | 0.0252 | 31.0 | 589 | 2.1265 |
80
- | 0.0256 | 32.0 | 608 | 2.1649 |
81
- | 0.0256 | 33.0 | 627 | 2.1238 |
82
- | 0.0256 | 34.0 | 646 | 2.1757 |
83
- | 0.0256 | 35.0 | 665 | 2.1402 |
84
- | 0.0256 | 36.0 | 684 | 2.1569 |
85
- | 0.0239 | 37.0 | 703 | 2.1783 |
86
- | 0.0239 | 38.0 | 722 | 2.1934 |
87
- | 0.0239 | 39.0 | 741 | 2.1883 |
88
- | 0.0239 | 40.0 | 760 | 2.1831 |
89
- | 0.0239 | 41.0 | 779 | 2.1931 |
90
- | 0.0239 | 42.0 | 798 | 2.1697 |
91
- | 0.0222 | 43.0 | 817 | 2.1629 |
92
- | 0.0222 | 44.0 | 836 | 2.2133 |
93
- | 0.0222 | 45.0 | 855 | 2.1917 |
94
- | 0.0222 | 46.0 | 874 | 2.1547 |
95
- | 0.0222 | 47.0 | 893 | 2.1826 |
96
- | 0.0208 | 48.0 | 912 | 2.2125 |
97
- | 0.0208 | 49.0 | 931 | 2.2529 |
98
- | 0.0208 | 50.0 | 950 | 2.2400 |
99
- | 0.0208 | 51.0 | 969 | 2.2202 |
100
- | 0.0208 | 52.0 | 988 | 2.2158 |
101
- | 0.017 | 53.0 | 1007 | 2.2075 |
102
- | 0.017 | 54.0 | 1026 | 2.2320 |
103
- | 0.017 | 55.0 | 1045 | 2.2138 |
104
- | 0.017 | 56.0 | 1064 | 2.2015 |
105
- | 0.017 | 57.0 | 1083 | 2.2282 |
106
- | 0.0169 | 58.0 | 1102 | 2.2591 |
107
- | 0.0169 | 59.0 | 1121 | 2.2483 |
108
- | 0.0169 | 60.0 | 1140 | 2.2194 |
109
- | 0.0169 | 61.0 | 1159 | 2.2324 |
110
- | 0.0169 | 62.0 | 1178 | 2.2649 |
111
- | 0.0169 | 63.0 | 1197 | 2.2763 |
112
- | 0.0145 | 64.0 | 1216 | 2.2876 |
113
- | 0.0145 | 65.0 | 1235 | 2.2645 |
114
- | 0.0145 | 66.0 | 1254 | 2.2531 |
115
- | 0.0145 | 67.0 | 1273 | 2.2532 |
116
- | 0.0145 | 68.0 | 1292 | 2.2602 |
117
- | 0.0155 | 69.0 | 1311 | 2.2659 |
118
- | 0.0155 | 70.0 | 1330 | 2.2894 |
119
- | 0.0155 | 71.0 | 1349 | 2.2998 |
120
- | 0.0155 | 72.0 | 1368 | 2.2802 |
121
- | 0.0155 | 73.0 | 1387 | 2.2498 |
122
- | 0.0148 | 74.0 | 1406 | 2.2602 |
123
- | 0.0148 | 75.0 | 1425 | 2.2659 |
124
- | 0.0148 | 76.0 | 1444 | 2.2762 |
125
- | 0.0148 | 77.0 | 1463 | 2.2825 |
126
- | 0.0148 | 78.0 | 1482 | 2.2939 |
127
- | 0.014 | 79.0 | 1501 | 2.3115 |
128
- | 0.014 | 80.0 | 1520 | 2.3008 |
129
- | 0.014 | 81.0 | 1539 | 2.3054 |
130
- | 0.014 | 82.0 | 1558 | 2.2930 |
131
- | 0.014 | 83.0 | 1577 | 2.2872 |
132
- | 0.014 | 84.0 | 1596 | 2.2896 |
133
- | 0.014 | 85.0 | 1615 | 2.2853 |
134
- | 0.014 | 86.0 | 1634 | 2.2755 |
135
- | 0.014 | 87.0 | 1653 | 2.2781 |
136
- | 0.014 | 88.0 | 1672 | 2.2842 |
137
- | 0.014 | 89.0 | 1691 | 2.2788 |
138
- | 0.0129 | 90.0 | 1710 | 2.2850 |
139
- | 0.0129 | 91.0 | 1729 | 2.2908 |
140
- | 0.0129 | 92.0 | 1748 | 2.2964 |
141
- | 0.0129 | 93.0 | 1767 | 2.2966 |
142
- | 0.0129 | 94.0 | 1786 | 2.2975 |
143
- | 0.0121 | 95.0 | 1805 | 2.3019 |
144
- | 0.0121 | 96.0 | 1824 | 2.2990 |
145
- | 0.0121 | 97.0 | 1843 | 2.2985 |
146
- | 0.0121 | 98.0 | 1862 | 2.3000 |
147
- | 0.0121 | 99.0 | 1881 | 2.3014 |
148
- | 0.0121 | 100.0 | 1900 | 2.3017 |
149
 
150
 
151
  ### Framework versions
 
1
  ---
2
  license: mit
3
+ base_model: gpt2
4
  tags:
5
  - generated_from_trainer
 
6
  model-index:
7
  - name: gpt2-evy
8
  results: []
 
13
 
14
  # gpt2-evy
15
 
16
+ This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 1.1260
19
 
20
  ## Model description
21
 
 
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: 20
44
 
45
  ### Training results
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
+ | No log | 1.0 | 5 | 1.5273 |
50
+ | No log | 2.0 | 10 | 1.4087 |
51
+ | No log | 3.0 | 15 | 1.3498 |
52
+ | No log | 4.0 | 20 | 1.2882 |
53
+ | No log | 5.0 | 25 | 1.2503 |
54
+ | No log | 6.0 | 30 | 1.2191 |
55
+ | No log | 7.0 | 35 | 1.1865 |
56
+ | No log | 8.0 | 40 | 1.1655 |
57
+ | No log | 9.0 | 45 | 1.1593 |
58
+ | No log | 10.0 | 50 | 1.1447 |
59
+ | No log | 11.0 | 55 | 1.1350 |
60
+ | No log | 12.0 | 60 | 1.1356 |
61
+ | No log | 13.0 | 65 | 1.1286 |
62
+ | No log | 14.0 | 70 | 1.1314 |
63
+ | No log | 15.0 | 75 | 1.1218 |
64
+ | No log | 16.0 | 80 | 1.1291 |
65
+ | No log | 17.0 | 85 | 1.1261 |
66
+ | No log | 18.0 | 90 | 1.1259 |
67
+ | No log | 19.0 | 95 | 1.1261 |
68
+ | 0.9466 | 20.0 | 100 | 1.1260 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
 
70
 
71
  ### Framework versions
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "joshcarp/gpt2-evy",
3
  "activation_function": "gelu_new",
4
  "architectures": [
5
  "GPT2LMHeadModel"
 
1
  {
2
+ "_name_or_path": "gpt2",
3
  "activation_function": "gelu_new",
4
  "architectures": [
5
  "GPT2LMHeadModel"
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:28298d858c49e6915ed6bfcfb31fc420c65e2f7c4b5e45252520824c58cbd0a1
3
  size 497774208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c10b00d2630c4bbafd35a154e4750d8e647b758ea0f79b22766acc1932e66c6
3
  size 497774208
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6093674870375a92b53884d2da0ad7b72bf326aa22b6b9bbfffb2e9a55732a1d
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ad000c2be1f68e367753edec916b8db73258fae6466a45f905e70821e1042ef
3
  size 4920