Hugging Face's logo

pabRomero
/
BART-Firefox-Simplification

Transformers
Safetensors
bart
text2text-generation
Generated from Trainer
Model card Files
xet
Community
pabRomero commited on
Commit
41c702f
·
verified ·
1 Parent(s): c5fefc4

End of training

Browse files
Files changed (2) hide show
  1. README.md +23 -18
  2. model.safetensors +1 -1
README.md CHANGED
@@ -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: 2.1026
20
 
21
  ## Model description
22
 
@@ -35,29 +35,34 @@ More information needed
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
- - learning_rate: 5e-06
39
- - train_batch_size: 4
40
- - eval_batch_size: 4
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: 1695
45
- - num_epochs: 10
46
 
47
  ### Training results
48
 
49
- | Training Loss | Epoch | Step | Validation Loss |
50
- |:-------------:|:-----:|:-----:|:---------------:|
51
- | 2.9356 | 1.0 | 1696 | 2.6397 |
52
- | 2.6065 | 2.0 | 3392 | 2.4075 |
53
- | 2.4067 | 3.0 | 5088 | 2.2693 |
54
- | 2.319 | 4.0 | 6784 | 2.2217 |
55
- | 2.2325 | 5.0 | 8480 | 2.1939 |
56
- | 2.1475 | 6.0 | 10176 | 2.1746 |
57
- | 2.0414 | 7.0 | 11872 | 2.1443 |
58
- | 2.0622 | 8.0 | 13568 | 2.1175 |
59
- | 1.9606 | 9.0 | 15264 | 2.1103 |
60
- | 1.9139 | 10.0 | 16960 | 2.1026 |
 
 
 
 
 
61
 
62
 
63
  ### Framework versions
 
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: 1.8845
20
 
21
  ## Model description
22
 
 
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
+ - learning_rate: 2.5e-05
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
+ | 2.9105 | 1.0 | 212 | 2.6066 |
52
+ | 2.5528 | 2.0 | 424 | 2.2820 |
53
+ | 2.2435 | 3.0 | 636 | 2.1249 |
54
+ | 2.0536 | 4.0 | 848 | 2.0488 |
55
+ | 1.8914 | 5.0 | 1060 | 2.0239 |
56
+ | 1.8098 | 6.0 | 1272 | 1.9841 |
57
+ | 1.7267 | 7.0 | 1484 | 1.9589 |
58
+ | 1.6515 | 8.0 | 1696 | 1.9342 |
59
+ | 1.5856 | 9.0 | 1908 | 1.9000 |
60
+ | 1.5154 | 10.0 | 2120 | 1.9103 |
61
+ | 1.457 | 11.0 | 2332 | 1.9085 |
62
+ | 1.4072 | 12.0 | 2544 | 1.8845 |
63
+ | 1.369 | 13.0 | 2756 | 1.8903 |
64
+ | 1.3603 | 14.0 | 2968 | 1.8887 |
65
+ | 1.3215 | 15.0 | 3180 | 1.8869 |
66
 
67
 
68
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d59cd7c33fd4816f359801d4d711b68dc72616349b4e0beeab5db422a530c8ce
3
  size 557921848
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc2710abc2bfddad13725d0e3a7438e377611e02ddb9550234c1bcf8adce658d
3
  size 557921848