gayanin commited on
Commit
e996e21
·
verified ·
1 Parent(s): b90093e

End of training

Browse files
Files changed (1) hide show
  1. README.md +6 -33
README.md CHANGED
@@ -4,18 +4,18 @@ base_model: facebook/bart-base
4
  tags:
5
  - generated_from_trainer
6
  model-index:
7
- - name: pubmed-abs-noise-mixed-v1
8
  results: []
9
  ---
10
 
11
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
  should probably proofread and complete it, then remove this comment. -->
13
 
14
- # pubmed-abs-noise-mixed-v1
15
 
16
  This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 1.0138
19
 
20
  ## Model description
21
 
@@ -46,36 +46,9 @@ The following hyperparameters were used during training:
46
 
47
  ### Training results
48
 
49
- | Training Loss | Epoch | Step | Validation Loss |
50
- |:-------------:|:-----:|:-----:|:---------------:|
51
- | 1.6354 | 0.11 | 500 | 1.4407 |
52
- | 1.5086 | 0.21 | 1000 | 1.3654 |
53
- | 1.3652 | 0.32 | 1500 | 1.2886 |
54
- | 1.3916 | 0.43 | 2000 | 1.2498 |
55
- | 1.1973 | 0.54 | 2500 | 1.2173 |
56
- | 1.3319 | 0.64 | 3000 | 1.1865 |
57
- | 1.2166 | 0.75 | 3500 | 1.1537 |
58
- | 1.2442 | 0.86 | 4000 | 1.1397 |
59
- | 1.213 | 0.96 | 4500 | 1.1154 |
60
- | 1.0495 | 1.07 | 5000 | 1.1122 |
61
- | 1.0197 | 1.18 | 5500 | 1.1020 |
62
- | 1.0838 | 1.28 | 6000 | 1.0941 |
63
- | 1.0746 | 1.39 | 6500 | 1.0796 |
64
- | 1.0549 | 1.5 | 7000 | 1.0648 |
65
- | 1.0146 | 1.61 | 7500 | 1.0585 |
66
- | 1.0384 | 1.71 | 8000 | 1.0564 |
67
- | 0.9587 | 1.82 | 8500 | 1.0506 |
68
- | 0.9968 | 1.93 | 9000 | 1.0392 |
69
- | 0.9058 | 2.03 | 9500 | 1.0464 |
70
- | 0.9116 | 2.14 | 10000 | 1.0335 |
71
- | 0.8652 | 2.25 | 10500 | 1.0386 |
72
- | 0.8749 | 2.35 | 11000 | 1.0301 |
73
- | 0.8391 | 2.46 | 11500 | 1.0292 |
74
- | 0.8816 | 2.57 | 12000 | 1.0192 |
75
- | 0.919 | 2.68 | 12500 | 1.0196 |
76
- | 0.9479 | 2.78 | 13000 | 1.0185 |
77
- | 0.892 | 2.89 | 13500 | 1.0156 |
78
- | 0.875 | 3.0 | 14000 | 1.0138 |
79
 
80
 
81
  ### Framework versions
 
4
  tags:
5
  - generated_from_trainer
6
  model-index:
7
+ - name: kaggle-clinical-native
8
  results: []
9
  ---
10
 
11
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
  should probably proofread and complete it, then remove this comment. -->
13
 
14
+ # kaggle-clinical-native
15
 
16
  This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.2701
19
 
20
  ## Model description
21
 
 
46
 
47
  ### Training results
48
 
49
+ | Training Loss | Epoch | Step | Validation Loss |
50
+ |:-------------:|:-----:|:----:|:---------------:|
51
+ | 0.1736 | 1.52 | 500 | 0.2701 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
52
 
53
 
54
  ### Framework versions