eudesfilho commited on
Commit
1536ea1
·
verified ·
1 Parent(s): f4c7489

End of training

Browse files
Files changed (1) hide show
  1. README.md +11 -11
README.md CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [pierreguillou/gpt2-small-portuguese](https://huggingface.co/pierreguillou/gpt2-small-portuguese) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 4.3158
20
 
21
  ## Model description
22
 
@@ -48,16 +48,16 @@ The following hyperparameters were used during training:
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
- | 3.489 | 1.0 | 38 | 4.1621 |
52
- | 3.3342 | 2.0 | 76 | 4.1957 |
53
- | 3.2612 | 3.0 | 114 | 4.2147 |
54
- | 3.1731 | 4.0 | 152 | 4.2456 |
55
- | 3.077 | 5.0 | 190 | 4.2690 |
56
- | 3.0259 | 6.0 | 228 | 4.2881 |
57
- | 2.9368 | 7.0 | 266 | 4.2997 |
58
- | 2.9735 | 8.0 | 304 | 4.3109 |
59
- | 2.9558 | 9.0 | 342 | 4.3141 |
60
- | 2.9048 | 10.0 | 380 | 4.3158 |
61
 
62
 
63
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [pierreguillou/gpt2-small-portuguese](https://huggingface.co/pierreguillou/gpt2-small-portuguese) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 4.1675
20
 
21
  ## Model description
22
 
 
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
+ | 4.0373 | 1.0 | 38 | 4.1597 |
52
+ | 3.8691 | 2.0 | 76 | 4.1377 |
53
+ | 3.8037 | 3.0 | 114 | 4.1324 |
54
+ | 3.6804 | 4.0 | 152 | 4.1339 |
55
+ | 3.5658 | 5.0 | 190 | 4.1412 |
56
+ | 3.4922 | 6.0 | 228 | 4.1479 |
57
+ | 3.379 | 7.0 | 266 | 4.1537 |
58
+ | 3.4002 | 8.0 | 304 | 4.1620 |
59
+ | 3.3623 | 9.0 | 342 | 4.1654 |
60
+ | 3.3001 | 10.0 | 380 | 4.1675 |
61
 
62
 
63
  ### Framework versions