Hugging Face's logo

alexlop
/
detr_t5_captioning_model

Transformers
Safetensors
t5
text2text-generation
Generated from Trainer
text-generation-inference
Model card Files
xet
Community
alexlop commited on
Commit
52300da
·
verified ·
1 Parent(s): fd941d4

detr-t5-medical-captioning

Browse files
Files changed (3) hide show
  1. README.md +5 -13
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.2843
20
- - Rougel: 0.1179
21
 
22
  ## Model description
23
 
@@ -42,23 +42,15 @@ The following hyperparameters were used during training:
42
  - seed: 42
43
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
44
  - lr_scheduler_type: linear
45
- - num_epochs: 10
46
  - mixed_precision_training: Native AMP
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Rougel |
51
  |:-------------:|:-----:|:----:|:---------------:|:------:|
52
- | 1.0915 | 1.0 | 236 | 1.0522 | 0.1784 |
53
- | 0.6349 | 2.0 | 472 | 0.5972 | 0.1179 |
54
- | 0.5186 | 3.0 | 708 | 0.4307 | 0.1179 |
55
- | 0.5036 | 4.0 | 944 | 0.3281 | 0.4648 |
56
- | 0.4559 | 5.0 | 1180 | 0.3233 | 0.1179 |
57
- | 0.3973 | 6.0 | 1416 | 0.3013 | 0.3958 |
58
- | 0.4032 | 7.0 | 1652 | 0.2943 | 0.1179 |
59
- | 0.3626 | 8.0 | 1888 | 0.2892 | 0.1179 |
60
- | 0.3783 | 9.0 | 2124 | 0.2878 | 0.1179 |
61
- | 0.413 | 10.0 | 2360 | 0.2843 | 0.1179 |
62
 
63
 
64
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.9834
20
+ - Rougel: 0.1565
21
 
22
  ## Model description
23
 
 
42
  - seed: 42
43
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
44
  - lr_scheduler_type: linear
45
+ - num_epochs: 2
46
  - mixed_precision_training: Native AMP
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Rougel |
51
  |:-------------:|:-----:|:----:|:---------------:|:------:|
52
+ | 1.3246 | 1.0 | 236 | 1.2553 | 0.1565 |
53
+ | 0.9549 | 2.0 | 472 | 0.9834 | 0.1565 |
 
 
 
 
 
 
 
 
54
 
55
 
56
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d921af22e2699e03bad483400d86c44f17d93d964f9a0f54442a8b313a310e91
3
  size 242041896
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d78973b1986e90c854e2892a4b3514125873723548be5745e1d1a9a218119ce4
3
  size 242041896
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3710c348a61bbd9b095fb5ce2407f35ea389943a3cb083c84c16893460e927b2
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:baae9994b055f7496a6f4887f7576f7e5e8bc655719478ffa89969174c8c3920
3
  size 5368