Hugging Face's logo

X1in
/
anlp_bart_simplification

Transformers
Safetensors
bart
text2text-generation
Generated from Trainer
Model card Files
xet
Community
X1in commited on
Commit
93fa7bf
·
verified ·
1 Parent(s): 8ceecdb

Model save

Browse files
Files changed (4) hide show
  1. README.md +4 -18
  2. generation_config.json +1 -3
  3. model.safetensors +1 -1
  4. training_args.bin +1 -1
README.md CHANGED
@@ -15,8 +15,6 @@ should probably proofread and complete it, then remove this comment. -->
15
  # anlp_bart_simplification
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: 1.0519
20
 
21
  ## Model description
22
 
@@ -36,32 +34,20 @@ More information needed
36
 
37
  The following hyperparameters were used during training:
38
  - learning_rate: 5e-05
39
- - train_batch_size: 32
40
- - eval_batch_size: 32
41
  - seed: 42
42
  - gradient_accumulation_steps: 4
43
- - total_train_batch_size: 128
44
  - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
  - lr_scheduler_type: cosine
46
  - lr_scheduler_warmup_ratio: 0.1
47
  - num_epochs: 12
48
  - mixed_precision_training: Native AMP
49
 
50
- ### Training results
51
-
52
- | Training Loss | Epoch | Step | Validation Loss |
53
- |:-------------:|:-----:|:----:|:---------------:|
54
- | 0.9096 | 2.0 | 250 | 0.8385 |
55
- | 0.7604 | 4.0 | 500 | 0.8252 |
56
- | 0.6639 | 6.0 | 750 | 0.8294 |
57
- | 0.6019 | 8.0 | 1000 | 0.8392 |
58
- | 0.5654 | 10.0 | 1250 | 0.8494 |
59
- | 0.5491 | 12.0 | 1500 | 0.8518 |
60
-
61
-
62
  ### Framework versions
63
 
64
  - Transformers 4.57.3
65
  - Pytorch 2.9.1+cu128
66
  - Datasets 4.4.1
67
- - Tokenizers 0.22.1
 
15
  # anlp_bart_simplification
16
 
17
  This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the None dataset.
 
 
18
 
19
  ## Model description
20
 
 
34
 
35
  The following hyperparameters were used during training:
36
  - learning_rate: 5e-05
37
+ - train_batch_size: 8
38
+ - eval_batch_size: 8
39
  - seed: 42
40
  - gradient_accumulation_steps: 4
41
+ - total_train_batch_size: 32
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: cosine
44
  - lr_scheduler_warmup_ratio: 0.1
45
  - num_epochs: 12
46
  - mixed_precision_training: Native AMP
47
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  ### Framework versions
49
 
50
  - Transformers 4.57.3
51
  - Pytorch 2.9.1+cu128
52
  - Datasets 4.4.1
53
+ - Tokenizers 0.22.2
generation_config.json CHANGED
@@ -3,9 +3,7 @@
3
  "bos_token_id": 0,
4
  "decoder_start_token_id": 2,
5
  "early_stopping": true,
6
- "eos_token_id": [
7
- 2
8
- ],
9
  "forced_bos_token_id": 0,
10
  "forced_eos_token_id": 2,
11
  "no_repeat_ngram_size": 3,
 
3
  "bos_token_id": 0,
4
  "decoder_start_token_id": 2,
5
  "early_stopping": true,
6
+ "eos_token_id": 2,
 
 
7
  "forced_bos_token_id": 0,
8
  "forced_eos_token_id": 2,
9
  "no_repeat_ngram_size": 3,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c2a547d64999a2dadab674e250912dd24ffb775fb4cdaa0715326ed8d38a723
3
  size 557912620
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ae513196937a5107fd760a1abf1a4793bbbfa52059f5e3313a716265b73ef60
3
  size 557912620
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eb13fb99ec22dc493bf012b618c2176ed5043913514dc869819071db8ff6a26b
3
  size 5969
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c36297f4b1367489517c7855727aae87c4d5dcdc32e322f3275b70bd14d9f7bb
3
  size 5969