Hugging Face's logo

Zamoranesis
/
clinical_transcripts_roberta

Fill-Mask
Transformers
PyTorch
roberta
medical transcriptions
healthcare
Inference Endpoints
Model card Files Community
Zamoranesis commited on
Commit
f08052e
•
1 Parent(s): 026de76

clinical_transcripts_roberta

Browse files
Files changed (3) hide show
  1. README.md +41 -21
  2. pytorch_model.bin +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [allenai/biomed_roberta_base](https://huggingface.co/allenai/biomed_roberta_base) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 1.0798
18
 
19
  ## Model description
20
 
@@ -41,32 +41,52 @@ The following hyperparameters were used during training:
41
  - lr_scheduler_type: linear
42
  - lr_scheduler_warmup_ratio: 0.1
43
  - lr_scheduler_warmup_steps: 100
44
- - training_steps: 2000
45
 
46
  ### Training results
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:----:|:---------------:|
50
  | 1.405 | 0.51 | 100 | 1.2925 |
51
- | 1.3155 | 1.01 | 200 | 1.2096 |
52
- | 1.276 | 1.52 | 300 | 1.1683 |
53
- | 1.2876 | 2.02 | 400 | 1.1698 |
54
- | 1.2189 | 2.53 | 500 | 1.1662 |
55
- | 1.1993 | 3.03 | 600 | 1.1183 |
56
- | 1.1656 | 3.54 | 700 | 1.1337 |
57
- | 1.1486 | 4.04 | 800 | 1.1396 |
58
- | 1.14 | 4.55 | 900 | 1.1034 |
59
- | 1.1411 | 5.05 | 1000 | 1.1279 |
60
- | 1.1132 | 5.56 | 1100 | 1.0999 |
61
- | 1.1039 | 6.06 | 1200 | 1.0912 |
62
- | 1.0986 | 6.57 | 1300 | 1.0948 |
63
- | 1.077 | 7.07 | 1400 | 1.0866 |
64
- | 1.0649 | 7.58 | 1500 | 1.0695 |
65
- | 1.0564 | 8.08 | 1600 | 1.0676 |
66
- | 1.028 | 8.59 | 1700 | 1.0567 |
67
- | 1.0917 | 9.09 | 1800 | 1.0642 |
68
- | 1.0456 | 9.6 | 1900 | 1.0386 |
69
- | 1.0353 | 10.1 | 2000 | 1.0798 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
70
 
71
 
72
  ### Framework versions
 
14
 
15
  This model is a fine-tuned version of [allenai/biomed_roberta_base](https://huggingface.co/allenai/biomed_roberta_base) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 1.0331
18
 
19
  ## Model description
20
 
 
41
  - lr_scheduler_type: linear
42
  - lr_scheduler_warmup_ratio: 0.1
43
  - lr_scheduler_warmup_steps: 100
44
+ - training_steps: 4000
45
 
46
  ### Training results
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:----:|:---------------:|
50
  | 1.405 | 0.51 | 100 | 1.2925 |
51
+ | 1.316 | 1.01 | 200 | 1.2107 |
52
+ | 1.2781 | 1.52 | 300 | 1.1704 |
53
+ | 1.2911 | 2.02 | 400 | 1.1745 |
54
+ | 1.2241 | 2.53 | 500 | 1.1730 |
55
+ | 1.2063 | 3.03 | 600 | 1.1248 |
56
+ | 1.174 | 3.54 | 700 | 1.1416 |
57
+ | 1.1588 | 4.04 | 800 | 1.1495 |
58
+ | 1.1513 | 4.55 | 900 | 1.1145 |
59
+ | 1.1541 | 5.05 | 1000 | 1.1402 |
60
+ | 1.1266 | 5.56 | 1100 | 1.1156 |
61
+ | 1.1205 | 6.06 | 1200 | 1.1075 |
62
+ | 1.1141 | 6.57 | 1300 | 1.1157 |
63
+ | 1.0956 | 7.07 | 1400 | 1.1047 |
64
+ | 1.0809 | 7.58 | 1500 | 1.0921 |
65
+ | 1.0755 | 8.08 | 1600 | 1.0891 |
66
+ | 1.044 | 8.59 | 1700 | 1.0758 |
67
+ | 1.1103 | 9.09 | 1800 | 1.0881 |
68
+ | 1.0578 | 9.6 | 1900 | 1.0578 |
69
+ | 1.0462 | 10.1 | 2000 | 1.1043 |
70
+ | 1.0302 | 10.61 | 2100 | 1.0787 |
71
+ | 1.0236 | 11.11 | 2200 | 1.0841 |
72
+ | 1.0371 | 11.62 | 2300 | 1.0904 |
73
+ | 1.0178 | 12.12 | 2400 | 1.0593 |
74
+ | 0.999 | 12.63 | 2500 | 1.0661 |
75
+ | 0.9867 | 13.13 | 2600 | 1.0670 |
76
+ | 0.9986 | 13.64 | 2700 | 1.0470 |
77
+ | 0.9867 | 14.14 | 2800 | 1.0347 |
78
+ | 0.9848 | 14.65 | 2900 | 1.0274 |
79
+ | 0.9627 | 15.15 | 3000 | 1.0550 |
80
+ | 0.9659 | 15.66 | 3100 | 1.0499 |
81
+ | 0.9743 | 16.16 | 3200 | 1.0419 |
82
+ | 0.9507 | 16.67 | 3300 | 1.0679 |
83
+ | 0.941 | 17.17 | 3400 | 1.0142 |
84
+ | 0.9548 | 17.68 | 3500 | 1.0422 |
85
+ | 0.9378 | 18.18 | 3600 | 1.0471 |
86
+ | 0.9339 | 18.69 | 3700 | 1.0473 |
87
+ | 0.9195 | 19.19 | 3800 | 1.0248 |
88
+ | 0.9254 | 19.7 | 3900 | 1.0235 |
89
+ | 0.9393 | 20.2 | 4000 | 1.0331 |
90
 
91
 
92
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d25c88ad5c9a7bd7a5057a23ff8c050e4cfc80983f0fa3ce7386a0da0a20701c
3
  size 498859189
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad817072eb1ceb3bbbe40ac506911b58038a316c74d5f4d0c9ef502a32e21c5b
3
  size 498859189
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3f10fd92599479d44b10e18639c72a5c6512e9977695f540858c90d4ad1eaa43
3
  size 4091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c54963a77fe862b0c74451982ce413bd39b153ca25c4ac18dade5a2ce7f42f6a
3
  size 4091