Hugging Face's logo

LA1512
/
bart-fine-tuning-FindSum-TextOnly

Text2Text Generation
Transformers
Safetensors
bart
Generated from Trainer
Inference Endpoints
Model card Files Community
LA1512 commited on
Commit
e257a98
•
1 Parent(s): 22b9740

LA1512/fine-tuned-distilbart-xsum-12-3-FindSum

Browse files
Files changed (3) hide show
  1. README.md +19 -11
  2. model.safetensors +1 -1
  3. training_args.bin +2 -2
README.md CHANGED
@@ -3,6 +3,8 @@ license: apache-2.0
3
  base_model: sshleifer/distilbart-xsum-12-3
4
  tags:
5
  - generated_from_trainer
 
 
6
  model-index:
7
  - name: results
8
  results: []
@@ -15,17 +17,12 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [sshleifer/distilbart-xsum-12-3](https://huggingface.co/sshleifer/distilbart-xsum-12-3) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
- - eval_loss: 3.1834
19
- - eval_rouge1: 36.6214
20
- - eval_rouge2: 11.487
21
- - eval_rougeL: 19.8571
22
- - eval_rougeLsum: 32.1107
23
- - eval_gen_len: 304.0
24
- - eval_runtime: 2425.0255
25
- - eval_samples_per_second: 0.867
26
- - eval_steps_per_second: 0.108
27
- - epoch: 0.48
28
- - step: 1000
29
 
30
  ## Model description
31
 
@@ -54,6 +51,17 @@ The following hyperparameters were used during training:
54
  - num_epochs: 5
55
  - label_smoothing_factor: 0.04
56
 
 
 
 
 
 
 
 
 
 
 
 
57
  ### Framework versions
58
 
59
  - Transformers 4.39.3
 
3
  base_model: sshleifer/distilbart-xsum-12-3
4
  tags:
5
  - generated_from_trainer
6
+ metrics:
7
+ - rouge
8
  model-index:
9
  - name: results
10
  results: []
 
17
 
18
  This model is a fine-tuned version of [sshleifer/distilbart-xsum-12-3](https://huggingface.co/sshleifer/distilbart-xsum-12-3) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 3.0029
21
+ - Rouge1: 38.0446
22
+ - Rouge2: 9.7772
23
+ - Rougel: 16.8698
24
+ - Rougelsum: 33.5627
25
+ - Gen Len: 360.0
 
 
 
 
 
26
 
27
  ## Model description
28
 
 
51
  - num_epochs: 5
52
  - label_smoothing_factor: 0.04
53
 
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
57
+ |:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
58
+ | 2.8683 | 1.0 | 2103 | 2.9785 | 38.4791 | 10.8563 | 18.9729 | 33.7913 | 398.0 |
59
+ | 2.5296 | 2.0 | 4206 | 2.9247 | 33.8821 | 10.3228 | 18.7384 | 30.1673 | 179.0 |
60
+ | 2.3212 | 3.0 | 6309 | 2.9111 | 38.1082 | 10.4958 | 19.915 | 33.3763 | 303.0 |
61
+ | 2.1286 | 4.0 | 8412 | 2.9644 | 36.3381 | 9.3725 | 17.9411 | 32.1316 | 289.0 |
62
+ | 1.9651 | 5.0 | 10515 | 3.0029 | 38.0446 | 9.7772 | 16.8698 | 33.5627 | 360.0 |
63
+
64
+
65
  ### Framework versions
66
 
67
  - Transformers 4.39.3
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:698258b5f0d61af908686a961f744f24e981c07f2664aa21a6c7695bf144b028
3
  size 1020714768
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b35ca3bee585851100895d4c5e072165a3735d5cebeb11369f7b96e16c525233
3
  size 1020714768
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d390cb5fe8318e0e70a0ccbf4c3b652580f923853fc5579ac1587a3fde3cc937
3
- size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4df94969b40afd71f486c03ca70cdca0bf6ead106e6bb8d21dcac5133c3577cc
3
+ size 5048