Hugging Face's logo

mNLP-project
/
distilgpt2-finetuned

Text Generation
Transformers
TensorBoard
Safetensors
gpt2
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
thymiantheherb commited on
Commit
eb69a08
•
1 Parent(s): 49586e6

End of training

Browse files
Files changed (3) hide show
  1. README.md +28 -9
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -17,11 +17,11 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [distilbert/distilgpt2](https://huggingface.co/distilbert/distilgpt2) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 4.0665
21
- - Bleu: 0.0085
22
- - Bertscore Precision: 0.1478
23
- - Bertscore Recall: 0.1636
24
- - Bertscore F1: 0.1550
25
 
26
  ## Model description
27
 
@@ -48,14 +48,33 @@ The following hyperparameters were used during training:
48
  - total_train_batch_size: 16
49
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
  - lr_scheduler_type: linear
51
- - num_epochs: 1
52
  - mixed_precision_training: Native AMP
53
 
54
  ### Training results
55
 
56
- | Training Loss | Epoch | Step | Validation Loss | Bleu | Bertscore Precision | Bertscore Recall | Bertscore F1 |
57
- |:-------------:|:-----:|:----:|:---------------:|:------:|:-------------------:|:----------------:|:------------:|
58
- | 5.0162 | 1.0 | 3223 | 4.0665 | 0.0085 | 0.1478 | 0.1636 | 0.1550 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
59
 
60
 
61
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [distilbert/distilgpt2](https://huggingface.co/distilbert/distilgpt2) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 2.7322
21
+ - Bleu: 0.0145
22
+ - Bertscore Precision: 0.1505
23
+ - Bertscore Recall: 0.1674
24
+ - Bertscore F1: 0.1581
25
 
26
  ## Model description
27
 
 
48
  - total_train_batch_size: 16
49
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
  - lr_scheduler_type: linear
51
+ - num_epochs: 20
52
  - mixed_precision_training: Native AMP
53
 
54
  ### Training results
55
 
56
+ | Training Loss | Epoch | Step | Validation Loss | Bleu | Bertscore Precision | Bertscore Recall | Bertscore F1 |
57
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|:-------------------:|:----------------:|:------------:|
58
+ | 5.0087 | 1.0 | 3223 | 3.9456 | 0.0088 | 0.1478 | 0.1638 | 0.1551 |
59
+ | 4.8889 | 2.0 | 6446 | 3.7706 | 0.0093 | 0.1480 | 0.1642 | 0.1554 |
60
+ | 4.9152 | 3.0 | 9669 | 3.6252 | 0.0097 | 0.1483 | 0.1646 | 0.1557 |
61
+ | 4.647 | 4.0 | 12892 | 3.5105 | 0.0103 | 0.1486 | 0.1649 | 0.1560 |
62
+ | 4.4683 | 5.0 | 16115 | 3.4093 | 0.0108 | 0.1489 | 0.1652 | 0.1563 |
63
+ | 4.4007 | 6.0 | 19338 | 3.3225 | 0.0110 | 0.1491 | 0.1654 | 0.1565 |
64
+ | 4.3966 | 7.0 | 22561 | 3.2444 | 0.0115 | 0.1493 | 0.1656 | 0.1567 |
65
+ | 4.3414 | 8.0 | 25784 | 3.1662 | 0.0117 | 0.1494 | 0.1657 | 0.1568 |
66
+ | 4.2446 | 9.0 | 29007 | 3.1021 | 0.0122 | 0.1497 | 0.1660 | 0.1571 |
67
+ | 4.2464 | 10.0 | 32230 | 3.0384 | 0.0125 | 0.1499 | 0.1662 | 0.1573 |
68
+ | 4.1739 | 11.0 | 35453 | 2.9789 | 0.0128 | 0.1499 | 0.1665 | 0.1574 |
69
+ | 4.08 | 12.0 | 38676 | 2.9295 | 0.0131 | 0.1501 | 0.1666 | 0.1576 |
70
+ | 4.001 | 13.0 | 41899 | 2.8857 | 0.0135 | 0.1502 | 0.1668 | 0.1577 |
71
+ | 3.9277 | 14.0 | 45122 | 2.8464 | 0.0136 | 0.1502 | 0.1669 | 0.1578 |
72
+ | 3.9709 | 15.0 | 48345 | 2.8137 | 0.0139 | 0.1503 | 0.1670 | 0.1578 |
73
+ | 3.9192 | 16.0 | 51568 | 2.7872 | 0.0141 | 0.1503 | 0.1672 | 0.1579 |
74
+ | 3.8916 | 17.0 | 54791 | 2.7644 | 0.0143 | 0.1504 | 0.1673 | 0.1580 |
75
+ | 3.8489 | 18.0 | 58014 | 2.7475 | 0.0144 | 0.1505 | 0.1674 | 0.1581 |
76
+ | 3.9091 | 19.0 | 61237 | 2.7364 | 0.0145 | 0.1505 | 0.1674 | 0.1581 |
77
+ | 3.9271 | 20.0 | 64460 | 2.7322 | 0.0145 | 0.1505 | 0.1674 | 0.1581 |
78
 
79
 
80
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:29300574d12fdd5ebc15042cd87ab92c44f018161802c6d5d5d17c1eda221c16
3
  size 327657928
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b574ae6e391830f0a95a76e80b94866c850baf74787e8419926dcfb19345c12c
3
  size 327657928
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:17db93795a362c9298df2f82088391ff7ea583f9b96abb0f083048e4907e3d2f
3
  size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d77920b0104b12edff8c354f631586651b29501f7d06ff790f7912c2251bacd
3
  size 5048