Hugging Face's logo

BluebrainAI
/
gpt2-medium-wikitext

Text Generation
Transformers
Safetensors
gpt2
Generated from Trainer
text-generation-inference
Model card Files Community
shivanandmn commited on
Commit
69a0cd3
·
verified ·
1 Parent(s): 465e24a

Model save

Browse files
Files changed (1) hide show
  1. README.md +21 -21
README.md CHANGED
@@ -17,10 +17,10 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 3.1671
21
- - Accuracy: 0.4217
22
- - Perplexity: 23.7377
23
- - Bleu: 0.1460
24
 
25
  ## Model description
26
 
@@ -52,23 +52,23 @@ The following hyperparameters were used during training:
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Perplexity | Bleu |
54
  |:-------------:|:------:|:----:|:---------------:|:--------:|:----------:|:------:|
55
- | 6.0809 | 0.2806 | 500 | 5.9580 | 0.1883 | 386.8254 | 0.0333 |
56
- | 5.0644 | 0.5612 | 1000 | 4.9191 | 0.2623 | 136.8761 | 0.0651 |
57
- | 4.3331 | 0.8418 | 1500 | 4.2124 | 0.3226 | 67.5163 | 0.0890 |
58
- | 3.9451 | 1.1223 | 2000 | 3.8835 | 0.3532 | 48.5942 | 0.1090 |
59
- | 3.7568 | 1.4029 | 2500 | 3.7051 | 0.3684 | 40.6559 | 0.1226 |
60
- | 3.6478 | 1.6835 | 3000 | 3.5827 | 0.3787 | 35.9710 | 0.1311 |
61
- | 3.5435 | 1.9641 | 3500 | 3.4940 | 0.3877 | 32.9179 | 0.1343 |
62
- | 3.4222 | 2.2447 | 4000 | 3.4292 | 0.3936 | 30.8527 | 0.1343 |
63
- | 3.3604 | 2.5253 | 4500 | 3.3728 | 0.3990 | 29.1601 | 0.1414 |
64
- | 3.3288 | 2.8058 | 5000 | 3.3269 | 0.4038 | 27.8518 | 0.1381 |
65
- | 3.2074 | 3.0864 | 5500 | 3.2887 | 0.4079 | 26.8092 | 0.1423 |
66
- | 3.2007 | 3.3670 | 6000 | 3.2605 | 0.4115 | 26.0632 | 0.1464 |
67
- | 3.1787 | 3.6476 | 6500 | 3.2328 | 0.4140 | 25.3497 | 0.1428 |
68
- | 3.1529 | 3.9282 | 7000 | 3.2085 | 0.4166 | 24.7424 | 0.1425 |
69
- | 3.0849 | 4.2088 | 7500 | 3.1921 | 0.4184 | 24.3384 | 0.1430 |
70
- | 3.0471 | 4.4893 | 8000 | 3.1796 | 0.4202 | 24.0366 | 0.1428 |
71
- | 3.0569 | 4.7699 | 8500 | 3.1671 | 0.4217 | 23.7377 | 0.1460 |
72
 
73
 
74
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 3.1666
21
+ - Accuracy: 0.4218
22
+ - Perplexity: 23.7262
23
+ - Bleu: 0.1462
24
 
25
  ## Model description
26
 
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Perplexity | Bleu |
54
  |:-------------:|:------:|:----:|:---------------:|:--------:|:----------:|:------:|
55
+ | 6.078 | 0.2806 | 500 | 5.9534 | 0.1875 | 385.0606 | 0.0310 |
56
+ | 5.0653 | 0.5612 | 1000 | 4.9232 | 0.2616 | 137.4410 | 0.0633 |
57
+ | 4.3357 | 0.8418 | 1500 | 4.2163 | 0.3222 | 67.7828 | 0.0857 |
58
+ | 3.9453 | 1.1223 | 2000 | 3.8824 | 0.3534 | 48.5418 | 0.1107 |
59
+ | 3.7572 | 1.4029 | 2500 | 3.7058 | 0.3684 | 40.6810 | 0.1217 |
60
+ | 3.6475 | 1.6835 | 3000 | 3.5827 | 0.3788 | 35.9700 | 0.1306 |
61
+ | 3.5431 | 1.9641 | 3500 | 3.4927 | 0.3878 | 32.8733 | 0.1347 |
62
+ | 3.4221 | 2.2447 | 4000 | 3.4283 | 0.3939 | 30.8231 | 0.1356 |
63
+ | 3.36 | 2.5253 | 4500 | 3.3719 | 0.3996 | 29.1351 | 0.1384 |
64
+ | 3.3281 | 2.8058 | 5000 | 3.3257 | 0.4041 | 27.8193 | 0.1369 |
65
+ | 3.2071 | 3.0864 | 5500 | 3.2885 | 0.4080 | 26.8024 | 0.1442 |
66
+ | 3.2002 | 3.3670 | 6000 | 3.2594 | 0.4117 | 26.0335 | 0.1477 |
67
+ | 3.1778 | 3.6476 | 6500 | 3.2319 | 0.4142 | 25.3278 | 0.1436 |
68
+ | 3.1523 | 3.9282 | 7000 | 3.2091 | 0.4167 | 24.7565 | 0.1462 |
69
+ | 3.0842 | 4.2088 | 7500 | 3.1917 | 0.4185 | 24.3289 | 0.1434 |
70
+ | 3.0465 | 4.4893 | 8000 | 3.1789 | 0.4201 | 24.0197 | 0.1460 |
71
+ | 3.0563 | 4.7699 | 8500 | 3.1666 | 0.4218 | 23.7262 | 0.1462 |
72
 
73
 
74
  ### Framework versions