Hugging Face's logo

pabRomero
/
BART-Firefox-Simplification

Text2Text Generation
Transformers
Safetensors
bart
Generated from Trainer
Inference Endpoints
Model card Files Community
pabRomero commited on
Commit
a80e94c
·
verified ·
1 Parent(s): 8a30bd5

End of training

Browse files
Files changed (3) hide show
  1. README.md +18 -17
  2. generation_config.json +1 -2
  3. model.safetensors +1 -1
README.md CHANGED
@@ -1,6 +1,7 @@
1
  ---
2
- base_model: facebook/bart-base
3
  license: apache-2.0
 
4
  tags:
5
  - generated_from_trainer
6
  model-index:
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.5106
19
 
20
  ## Model description
21
 
@@ -38,7 +39,7 @@ The following hyperparameters were used during training:
38
  - train_batch_size: 4
39
  - eval_batch_size: 4
40
  - seed: 42
41
- - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
  - lr_scheduler_warmup_steps: 1486
44
  - num_epochs: 10
@@ -47,21 +48,21 @@ The following hyperparameters were used during training:
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:-----:|:---------------:|
50
- | 0.7243 | 1.0 | 1487 | 0.6370 |
51
- | 0.6341 | 2.0 | 2974 | 0.5809 |
52
- | 0.6233 | 3.0 | 4461 | 0.5453 |
53
- | 0.5423 | 4.0 | 5948 | 0.5398 |
54
- | 0.5203 | 5.0 | 7435 | 0.5270 |
55
- | 0.4592 | 6.0 | 8922 | 0.5196 |
56
- | 0.4737 | 7.0 | 10409 | 0.5184 |
57
- | 0.4591 | 8.0 | 11896 | 0.5141 |
58
- | 0.4384 | 9.0 | 13383 | 0.5106 |
59
- | 0.4199 | 10.0 | 14870 | 0.5128 |
60
 
61
 
62
  ### Framework versions
63
 
64
- - Transformers 4.44.0
65
- - Pytorch 2.4.0+cu124
66
- - Datasets 2.21.0
67
- - Tokenizers 0.19.1
 
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: 0.5104
20
 
21
  ## Model description
22
 
 
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: 1486
45
  - num_epochs: 10
 
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:-----:|:---------------:|
51
+ | 0.7257 | 1.0 | 1487 | 0.6373 |
52
+ | 0.6347 | 2.0 | 2974 | 0.5829 |
53
+ | 0.6218 | 3.0 | 4461 | 0.5461 |
54
+ | 0.5425 | 4.0 | 5948 | 0.5402 |
55
+ | 0.5202 | 5.0 | 7435 | 0.5261 |
56
+ | 0.46 | 6.0 | 8922 | 0.5193 |
57
+ | 0.4749 | 7.0 | 10409 | 0.5174 |
58
+ | 0.4587 | 8.0 | 11896 | 0.5141 |
59
+ | 0.439 | 9.0 | 13383 | 0.5104 |
60
+ | 0.42 | 10.0 | 14870 | 0.5126 |
61
 
62
 
63
  ### Framework versions
64
 
65
+ - Transformers 4.48.3
66
+ - Pytorch 2.6.0+cu126
67
+ - Datasets 3.0.1
68
+ - Tokenizers 0.21.0
generation_config.json CHANGED
@@ -9,6 +9,5 @@
9
  "no_repeat_ngram_size": 3,
10
  "num_beams": 4,
11
  "pad_token_id": 1,
12
- "transformers_version": "4.44.0",
13
- "use_cache": false
14
  }
 
9
  "no_repeat_ngram_size": 3,
10
  "num_beams": 4,
11
  "pad_token_id": 1,
12
+ "transformers_version": "4.48.3"
 
13
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:77932635c7d253ec82b49abcdcca5e3f26377b5296c241122f8dcefb8442dd2c
3
  size 557921848
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f25fd538cc5d0d90b14bdeff8a72fd21c29a33e028ae4366cb2e0c4ca5ab2c5
3
  size 557921848