Hugging Face's logo

aisuko
/
ft-facebook-bart-large-xsum-on-samsum

Text2Text Generation
Transformers
Safetensors
bart
Generated from Trainer
Inference Endpoints
Model card Files Community
aisuko commited on
Commit
aacffe3
•
1 Parent(s): e863fb8

End of training

Browse files
Files changed (4) hide show
  1. README.md +8 -8
  2. generation_config.json +4 -0
  3. model.safetensors +1 -1
  4. training_args.bin +1 -1
README.md CHANGED
@@ -1,10 +1,10 @@
1
  ---
2
  license: mit
 
3
  tags:
4
  - generated_from_trainer
5
  metrics:
6
  - rouge
7
- base_model: facebook/bart-large-xsum
8
  model-index:
9
  - name: ft-facebook-bart-large-xsum-on-samsum
10
  results: []
@@ -17,12 +17,12 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [facebook/bart-large-xsum](https://huggingface.co/facebook/bart-large-xsum) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 1.4689
21
- - Rouge1: 50.9912
22
- - Rouge2: 25.7585
23
- - Rougel: 41.4197
24
- - Rougelsum: 46.5946
25
- - Gen Len: 26.8814
26
 
27
  ## Model description
28
 
@@ -56,7 +56,7 @@ The following hyperparameters were used during training:
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
58
  |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
59
- | No log | 0.22 | 100 | 1.5055 | 49.5512 | 24.5568 | 40.7039 | 45.2274 | 26.4237 |
60
 
61
 
62
  ### Framework versions
 
1
  ---
2
  license: mit
3
+ base_model: facebook/bart-large-xsum
4
  tags:
5
  - generated_from_trainer
6
  metrics:
7
  - rouge
 
8
  model-index:
9
  - name: ft-facebook-bart-large-xsum-on-samsum
10
  results: []
 
17
 
18
  This model is a fine-tuned version of [facebook/bart-large-xsum](https://huggingface.co/facebook/bart-large-xsum) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 1.4691
21
+ - Rouge1: 51.1221
22
+ - Rouge2: 25.9275
23
+ - Rougel: 41.5903
24
+ - Rougelsum: 46.7354
25
+ - Gen Len: 26.89
26
 
27
  ## Model description
28
 
 
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
58
  |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
59
+ | No log | 0.22 | 100 | 1.5053 | 49.3903 | 24.5197 | 40.7578 | 45.2724 | 26.3272 |
60
 
61
 
62
  ### Framework versions
generation_config.json CHANGED
@@ -1,9 +1,13 @@
1
  {
 
 
2
  "early_stopping": true,
 
3
  "forced_eos_token_id": 2,
4
  "max_length": 62,
5
  "min_length": 11,
6
  "no_repeat_ngram_size": 3,
7
  "num_beams": 6,
 
8
  "transformers_version": "4.37.2"
9
  }
 
1
  {
2
+ "bos_token_id": 0,
3
+ "decoder_start_token_id": 2,
4
  "early_stopping": true,
5
+ "eos_token_id": 2,
6
  "forced_eos_token_id": 2,
7
  "max_length": 62,
8
  "min_length": 11,
9
  "no_repeat_ngram_size": 3,
10
  "num_beams": 6,
11
+ "pad_token_id": 1,
12
  "transformers_version": "4.37.2"
13
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f05d9db4b8f13febdea52447cd5e7df742bb6cae41d19d42a6c2d6a7920bdced
3
  size 1625422896
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:388374e630771e997bf530aece6d276cb7a43934219134d0812ffbdf0cbfaf1b
3
  size 1625422896
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0f99aea148d7400adf0825cfaf7d04451f2e476e698554549d4e7b1f11c41818
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ad9f76233b0c45eee265be4dbb2b5fd8493ad0e864c4bb486e6574c3b617b45
3
  size 4920