zbigi commited on
Commit
bbd8f1a
1 Parent(s): 276709a

End of training

Browse files
README.md CHANGED
@@ -2,6 +2,8 @@
2
  base_model: facebook/bart-base
3
  library_name: peft
4
  license: apache-2.0
 
 
5
  tags:
6
  - generated_from_trainer
7
  model-index:
@@ -16,16 +18,12 @@ 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
- - eval_loss: 4.0426
20
- - eval_rouge1: 0.1381
21
- - eval_rouge2: 0.0403
22
- - eval_rougeL: 0.1141
23
- - eval_rougeLsum: 0.1254
24
- - eval_gen_len: 20.0
25
- - eval_runtime: 279.9685
26
- - eval_samples_per_second: 3.572
27
- - eval_steps_per_second: 3.572
28
- - step: 0
29
 
30
  ## Model description
31
 
@@ -55,6 +53,18 @@ The following hyperparameters were used during training:
55
  - num_epochs: 6
56
  - mixed_precision_training: Native AMP
57
 
 
 
 
 
 
 
 
 
 
 
 
 
58
  ### Framework versions
59
 
60
  - PEFT 0.12.0
 
2
  base_model: facebook/bart-base
3
  library_name: peft
4
  license: apache-2.0
5
+ metrics:
6
+ - rouge
7
  tags:
8
  - generated_from_trainer
9
  model-index:
 
18
 
19
  This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 3.3867
22
+ - Rouge1: 0.2505
23
+ - Rouge2: 0.0917
24
+ - Rougel: 0.1982
25
+ - Rougelsum: 0.2221
26
+ - Gen Len: 18.509
 
 
 
 
27
 
28
  ## Model description
29
 
 
53
  - num_epochs: 6
54
  - mixed_precision_training: Native AMP
55
 
56
+ ### Training results
57
+
58
+ | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
59
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
60
+ | 2.7087 | 1.0 | 1250 | 3.3802 | 0.2509 | 0.0892 | 0.1958 | 0.221 | 19.092 |
61
+ | 2.615 | 2.0 | 2500 | 3.3801 | 0.249 | 0.0914 | 0.1958 | 0.22 | 18.594 |
62
+ | 2.5711 | 3.0 | 3750 | 3.3867 | 0.2514 | 0.0917 | 0.1969 | 0.2214 | 18.643 |
63
+ | 2.5534 | 4.0 | 5000 | 3.3886 | 0.252 | 0.0932 | 0.198 | 0.2223 | 18.467 |
64
+ | 2.5482 | 5.0 | 6250 | 3.3859 | 0.2508 | 0.0908 | 0.1972 | 0.2217 | 18.501 |
65
+ | 2.5367 | 6.0 | 7500 | 3.3867 | 0.2505 | 0.0917 | 0.1982 | 0.2221 | 18.509 |
66
+
67
+
68
  ### Framework versions
69
 
70
  - PEFT 0.12.0
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bcbf5a16c035678725133e560f392912053d44c05779371b56ebf05decca63b6
3
  size 894624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7513502b913070d69814993e6316948684052039562b45972515998c54bfcc9
3
  size 894624
runs/Jul25_07-27-47_46eb69058145/events.out.tfevents.1721892747.46eb69058145.217.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f0597955de9e1b6cbe9412849bdccee5f3ecad6ffb5aadf293b522c6c728f090
3
- size 536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64983f0a312aa56f947d78ec36dd89736b0a0689297312fa022d049873455561
3
+ size 13283