Hugging Face's logo

pabRomero
/
BART-Firefox-Simplification-Elementary

Transformers
Safetensors
bart
text2text-generation
Generated from Trainer
Model card Files
xet
Community
pabRomero commited on
Commit
04179d8
·
verified ·
1 Parent(s): b390676

End of training

Browse files
Files changed (2) hide show
  1. README.md +19 -19
  2. model.safetensors +1 -1
README.md CHANGED
@@ -1,7 +1,7 @@
1
  ---
2
- base_model: facebook/bart-base
3
  library_name: transformers
4
  license: apache-2.0
 
5
  tags:
6
  - generated_from_trainer
7
  model-index:
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.1630
20
 
21
  ## Model description
22
 
@@ -35,34 +35,34 @@ More information needed
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
- - learning_rate: 0.0001
39
  - train_batch_size: 32
40
  - eval_batch_size: 32
41
  - seed: 42
42
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
43
  - lr_scheduler_type: linear
44
- - lr_scheduler_warmup_steps: 317
45
  - num_epochs: 15
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
- | 2.1803 | 1.0 | 212 | 1.9622 |
52
- | 1.5022 | 2.0 | 424 | 1.3894 |
53
- | 0.9 | 3.0 | 636 | 0.9155 |
54
- | 0.5436 | 4.0 | 848 | 0.6259 |
55
- | 0.3291 | 5.0 | 1060 | 0.4608 |
56
- | 0.2152 | 6.0 | 1272 | 0.3565 |
57
- | 0.1512 | 7.0 | 1484 | 0.2608 |
58
- | 0.1075 | 8.0 | 1696 | 0.2425 |
59
- | 0.0805 | 9.0 | 1908 | 0.1872 |
60
- | 0.0612 | 10.0 | 2120 | 0.1925 |
61
- | 0.0472 | 11.0 | 2332 | 0.1881 |
62
- | 0.0384 | 12.0 | 2544 | 0.1630 |
63
- | 0.0294 | 13.0 | 2756 | 0.1869 |
64
- | 0.0219 | 14.0 | 2968 | 0.1823 |
65
- | 0.0207 | 15.0 | 3180 | 0.1783 |
66
 
67
 
68
  ### Framework versions
 
1
  ---
 
2
  library_name: transformers
3
  license: apache-2.0
4
+ base_model: facebook/bart-base
5
  tags:
6
  - generated_from_trainer
7
  model-index:
 
16
 
17
  This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.0465
20
 
21
  ## Model description
22
 
 
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
+ - learning_rate: 0.0002
39
  - train_batch_size: 32
40
  - eval_batch_size: 32
41
  - seed: 42
42
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
43
  - lr_scheduler_type: linear
44
+ - lr_scheduler_warmup_steps: 404
45
  - num_epochs: 15
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
+ | 1.7681 | 1.0 | 270 | 1.2737 |
52
+ | 1.1619 | 2.0 | 540 | 0.7112 |
53
+ | 0.5612 | 3.0 | 810 | 0.4396 |
54
+ | 0.3226 | 4.0 | 1080 | 0.2830 |
55
+ | 0.1885 | 5.0 | 1350 | 0.1619 |
56
+ | 0.1304 | 6.0 | 1620 | 0.1719 |
57
+ | 0.0871 | 7.0 | 1890 | 0.1755 |
58
+ | 0.0656 | 8.0 | 2160 | 0.1026 |
59
+ | 0.0467 | 9.0 | 2430 | 0.0465 |
60
+ | 0.0292 | 10.0 | 2700 | 0.0660 |
61
+ | 0.0212 | 11.0 | 2970 | 0.0654 |
62
+ | 0.0143 | 12.0 | 3240 | 0.0728 |
63
+ | 0.0094 | 13.0 | 3510 | 0.0648 |
64
+ | 0.0068 | 14.0 | 3780 | 0.0589 |
65
+ | 0.0064 | 15.0 | 4050 | 0.0570 |
66
 
67
 
68
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:825b46959d6becb936f0abdcb04cef40d60fde221cc679aa550d50fcf9fbf3bc
3
  size 557912620
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57f482752433d79c6ece764dec9af3e9ba62b066705d11d103c41814bbe33e01
3
  size 557912620