Hugging Face's logo

bigmorning
/
distilgpt_new2_0060

Text Generation
Transformers
TensorFlow
gpt2
generated_from_keras_callback
Inference Endpoints
text-generation-inference
Model card Files Community
bigmorning commited on
Commit
2414ade
•
1 Parent(s): fe9f9f7

add model

Browse files
Files changed (2) hide show
  1. README.md +63 -63
  2. tf_model.h5 +1 -1
README.md CHANGED
@@ -11,10 +11,10 @@ probably proofread and complete it, then remove this comment. -->
11
 
12
  # distilgpt_new2_0060
13
 
14
- This model is a fine-tuned version of [/content/drive/MyDrive/Colab Notebooks/oscar/trybackup/new_backup_008585](https://huggingface.co//content/drive/MyDrive/Colab Notebooks/oscar/trybackup/new_backup_008585) on an unknown dataset.
15
  It achieves the following results on the evaluation set:
16
- - Train Loss: 2.6610
17
- - Validation Loss: 2.5503
18
  - Epoch: 59
19
 
20
  ## Model description
@@ -41,66 +41,66 @@ The following hyperparameters were used during training:
41
 
42
  | Train Loss | Validation Loss | Epoch |
43
  |:----------:|:---------------:|:-----:|
44
- | 2.7786 | 2.6701 | 0 |
45
- | 2.7759 | 2.6662 | 1 |
46
- | 2.7730 | 2.6642 | 2 |
47
- | 2.7704 | 2.6602 | 3 |
48
- | 2.7679 | 2.6590 | 4 |
49
- | 2.7654 | 2.6565 | 5 |
50
- | 2.7629 | 2.6538 | 6 |
51
- | 2.7604 | 2.6525 | 7 |
52
- | 2.7579 | 2.6489 | 8 |
53
- | 2.7556 | 2.6452 | 9 |
54
- | 2.7531 | 2.6454 | 10 |
55
- | 2.7505 | 2.6411 | 11 |
56
- | 2.7483 | 2.6387 | 12 |
57
- | 2.7458 | 2.6370 | 13 |
58
- | 2.7435 | 2.6365 | 14 |
59
- | 2.7412 | 2.6308 | 15 |
60
- | 2.7391 | 2.6289 | 16 |
61
- | 2.7368 | 2.6288 | 17 |
62
- | 2.7347 | 2.6257 | 18 |
63
- | 2.7325 | 2.6238 | 19 |
64
- | 2.7303 | 2.6228 | 20 |
65
- | 2.7282 | 2.6189 | 21 |
66
- | 2.7262 | 2.6170 | 22 |
67
- | 2.7240 | 2.6145 | 23 |
68
- | 2.7221 | 2.6137 | 24 |
69
- | 2.7201 | 2.6108 | 25 |
70
- | 2.7181 | 2.6082 | 26 |
71
- | 2.7161 | 2.6057 | 27 |
72
- | 2.7141 | 2.6039 | 28 |
73
- | 2.7122 | 2.6031 | 29 |
74
- | 2.7103 | 2.6018 | 30 |
75
- | 2.7083 | 2.5984 | 31 |
76
- | 2.7064 | 2.5975 | 32 |
77
- | 2.7045 | 2.5941 | 33 |
78
- | 2.7026 | 2.5945 | 34 |
79
- | 2.7008 | 2.5930 | 35 |
80
- | 2.6989 | 2.5874 | 36 |
81
- | 2.6972 | 2.5864 | 37 |
82
- | 2.6953 | 2.5858 | 38 |
83
- | 2.6935 | 2.5831 | 39 |
84
- | 2.6917 | 2.5809 | 40 |
85
- | 2.6900 | 2.5791 | 41 |
86
- | 2.6881 | 2.5780 | 42 |
87
- | 2.6865 | 2.5765 | 43 |
88
- | 2.6848 | 2.5761 | 44 |
89
- | 2.6832 | 2.5720 | 45 |
90
- | 2.6814 | 2.5709 | 46 |
91
- | 2.6797 | 2.5689 | 47 |
92
- | 2.6782 | 2.5692 | 48 |
93
- | 2.6766 | 2.5672 | 49 |
94
- | 2.6750 | 2.5646 | 50 |
95
- | 2.6733 | 2.5635 | 51 |
96
- | 2.6719 | 2.5623 | 52 |
97
- | 2.6701 | 2.5594 | 53 |
98
- | 2.6684 | 2.5586 | 54 |
99
- | 2.6670 | 2.5584 | 55 |
100
- | 2.6655 | 2.5556 | 56 |
101
- | 2.6640 | 2.5542 | 57 |
102
- | 2.6626 | 2.5521 | 58 |
103
- | 2.6610 | 2.5503 | 59 |
104
 
105
 
106
  ### Framework versions
 
11
 
12
  # distilgpt_new2_0060
13
 
14
+ This model was trained from scratch on an unknown dataset.
15
  It achieves the following results on the evaluation set:
16
+ - Train Loss: 2.5626
17
+ - Validation Loss: 2.4481
18
  - Epoch: 59
19
 
20
  ## Model description
 
41
 
42
  | Train Loss | Validation Loss | Epoch |
43
  |:----------:|:---------------:|:-----:|
44
+ | 2.6241 | 2.5129 | 0 |
45
+ | 2.6228 | 2.5112 | 1 |
46
+ | 2.6216 | 2.5105 | 2 |
47
+ | 2.6204 | 2.5101 | 3 |
48
+ | 2.6191 | 2.5088 | 4 |
49
+ | 2.6180 | 2.5064 | 5 |
50
+ | 2.6166 | 2.5045 | 6 |
51
+ | 2.6155 | 2.5038 | 7 |
52
+ | 2.6143 | 2.5024 | 8 |
53
+ | 2.6132 | 2.5009 | 9 |
54
+ | 2.6120 | 2.5014 | 10 |
55
+ | 2.6108 | 2.4984 | 11 |
56
+ | 2.6097 | 2.4983 | 12 |
57
+ | 2.6085 | 2.4976 | 13 |
58
+ | 2.6073 | 2.4948 | 14 |
59
+ | 2.6064 | 2.4945 | 15 |
60
+ | 2.6052 | 2.4939 | 16 |
61
+ | 2.6039 | 2.4925 | 17 |
62
+ | 2.6030 | 2.4912 | 18 |
63
+ | 2.6019 | 2.4890 | 19 |
64
+ | 2.6007 | 2.4889 | 20 |
65
+ | 2.5998 | 2.4872 | 21 |
66
+ | 2.5987 | 2.4865 | 22 |
67
+ | 2.5977 | 2.4859 | 23 |
68
+ | 2.5965 | 2.4844 | 24 |
69
+ | 2.5956 | 2.4834 | 25 |
70
+ | 2.5944 | 2.4821 | 26 |
71
+ | 2.5934 | 2.4805 | 27 |
72
+ | 2.5925 | 2.4790 | 28 |
73
+ | 2.5914 | 2.4798 | 29 |
74
+ | 2.5904 | 2.4777 | 30 |
75
+ | 2.5893 | 2.4781 | 31 |
76
+ | 2.5883 | 2.4755 | 32 |
77
+ | 2.5872 | 2.4763 | 33 |
78
+ | 2.5862 | 2.4743 | 34 |
79
+ | 2.5851 | 2.4736 | 35 |
80
+ | 2.5841 | 2.4732 | 36 |
81
+ | 2.5831 | 2.4726 | 37 |
82
+ | 2.5822 | 2.4691 | 38 |
83
+ | 2.5812 | 2.4689 | 39 |
84
+ | 2.5803 | 2.4670 | 40 |
85
+ | 2.5792 | 2.4675 | 41 |
86
+ | 2.5783 | 2.4650 | 42 |
87
+ | 2.5773 | 2.4650 | 43 |
88
+ | 2.5763 | 2.4625 | 44 |
89
+ | 2.5754 | 2.4615 | 45 |
90
+ | 2.5743 | 2.4619 | 46 |
91
+ | 2.5735 | 2.4597 | 47 |
92
+ | 2.5725 | 2.4594 | 48 |
93
+ | 2.5715 | 2.4582 | 49 |
94
+ | 2.5707 | 2.4568 | 50 |
95
+ | 2.5699 | 2.4562 | 51 |
96
+ | 2.5689 | 2.4565 | 52 |
97
+ | 2.5680 | 2.4550 | 53 |
98
+ | 2.5671 | 2.4536 | 54 |
99
+ | 2.5661 | 2.4529 | 55 |
100
+ | 2.5653 | 2.4513 | 56 |
101
+ | 2.5644 | 2.4515 | 57 |
102
+ | 2.5635 | 2.4510 | 58 |
103
+ | 2.5626 | 2.4481 | 59 |
104
 
105
 
106
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4edbbca9708770b376aa81a993e7c271c10b81961463a6a68248350c33a91bf6
3
  size 258364376
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5860f80abddb4accb0b0feca4dc6cb43feab97f9eb6a5aa56b7f6255ec3fa5c
3
  size 258364376