Hugging Face's logo

X1in
/
anlp_bart_level_aware

Transformers
Safetensors
bart
text2text-generation
Generated from Trainer
Model card Files
xet
Community
X1in commited on
Commit
690236f
·
verified ·
1 Parent(s): 6275ef8

Model save

Browse files
Files changed (2) hide show
  1. README.md +12 -7
  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: 0.8216
20
 
21
  ## Model description
22
 
@@ -41,18 +41,23 @@ The following hyperparameters were used during training:
41
  - seed: 42
42
  - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
43
  - lr_scheduler_type: linear
44
- - num_epochs: 5
45
  - mixed_precision_training: Native AMP
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
- | 0.9935 | 1.0 | 282 | 0.8667 |
52
- | 0.8691 | 2.0 | 564 | 0.8344 |
53
- | 0.8099 | 3.0 | 846 | 0.8253 |
54
- | 0.772 | 4.0 | 1128 | 0.8257 |
55
- | 0.7484 | 5.0 | 1410 | 0.8216 |
 
 
 
 
 
56
 
57
 
58
  ### 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: 0.8295
20
 
21
  ## Model description
22
 
 
41
  - seed: 42
42
  - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
43
  - lr_scheduler_type: linear
44
+ - num_epochs: 10
45
  - mixed_precision_training: Native AMP
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
+ | 0.9928 | 1.0 | 282 | 0.8691 |
52
+ | 0.8659 | 2.0 | 564 | 0.8382 |
53
+ | 0.8021 | 3.0 | 846 | 0.8223 |
54
+ | 0.7573 | 4.0 | 1128 | 0.8222 |
55
+ | 0.7233 | 5.0 | 1410 | 0.8196 |
56
+ | 0.6797 | 6.0 | 1692 | 0.8185 |
57
+ | 0.663 | 7.0 | 1974 | 0.8195 |
58
+ | 0.6427 | 8.0 | 2256 | 0.8198 |
59
+ | 0.6308 | 9.0 | 2538 | 0.8273 |
60
+ | 0.6161 | 10.0 | 2820 | 0.8295 |
61
 
62
 
63
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a148f69d06c775bb5da3bddd50977246c8d4a7caf3290d6ca17be8454b06237
3
  size 557912620
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0087205c33619999463274ae4e0793aa3caccf118096a10049d9555eed8316f6
3
  size 557912620