chandank commited on
Commit
1d885d8
1 Parent(s): 3bc25b7
README.md CHANGED
@@ -3,12 +3,18 @@ tags:
3
  - generated_from_trainer
4
  datasets:
5
  - null
 
 
6
  model_index:
7
  - name: bart-base-finetuned-xsum
8
  results:
9
  - task:
10
  name: Sequence-to-sequence Language Modeling
11
  type: text2text-generation
 
 
 
 
12
  ---
13
 
14
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -17,6 +23,13 @@ should probably proofread and complete it, then remove this comment. -->
17
  # bart-base-finetuned-xsum
18
 
19
  This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the None dataset.
 
 
 
 
 
 
 
20
 
21
  ## Model description
22
 
@@ -45,9 +58,9 @@ The following hyperparameters were used during training:
45
 
46
  ### Training results
47
 
48
- | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
49
- |:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:|
50
- | No log | 1.0 | 8 | 1.6632 | 35.3863 | 25.955 | 31.4867 | 34.0508 | 20.0 |
51
 
52
 
53
  ### Framework versions
 
3
  - generated_from_trainer
4
  datasets:
5
  - null
6
+ metrics:
7
+ - rouge
8
  model_index:
9
  - name: bart-base-finetuned-xsum
10
  results:
11
  - task:
12
  name: Sequence-to-sequence Language Modeling
13
  type: text2text-generation
14
+ metric:
15
+ name: Rouge1
16
+ type: rouge
17
+ value: 27.8379
18
  ---
19
 
20
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
23
  # bart-base-finetuned-xsum
24
 
25
  This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the None dataset.
26
+ It achieves the following results on the evaluation set:
27
+ - Loss: 1.5671
28
+ - Rouge1: 27.8379
29
+ - Rouge2: 16.2683
30
+ - Rougel: 24.1898
31
+ - Rougelsum: 25.5234
32
+ - Gen Len: 20.0
33
 
34
  ## Model description
35
 
 
58
 
59
  ### Training results
60
 
61
+ | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
62
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
63
+ | 1.9931 | 1.0 | 879 | 1.5671 | 27.8379 | 16.2683 | 24.1898 | 25.5234 | 20.0 |
64
 
65
 
66
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f213e64bda09e9ba66539bc8e9f990decc9905482b2d1bc12d06bd3b3983ba37
3
  size 557975481
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b806787b60e05563e3315ba3fd250605569f7f2f7b42c9389f65b1c12d05f02a
3
  size 557975481
runs/Aug23_09-27-55_ip-172-16-147-34/1629710885.6860564/events.out.tfevents.1629710885.ip-172-16-147-34.32749.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9927e165bf0eb4f6e58eea5bbd115e70a5ea2efa33274970e707ef3525679df
3
+ size 4336
runs/Aug23_09-27-55_ip-172-16-147-34/events.out.tfevents.1629710885.ip-172-16-147-34.32749.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c7ebb92f895c53c569d0e0254a6875d747fbee71d21ece0402993f420d675a4
3
+ size 5099
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:99ed31a542f3305dc89cf58cf12af5392b3d03fba1377602193984d104806147
3
  size 2735
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:198e7e6835969a288c77ba585dd8bfa2ca0601cc409e1193b3dedb41d62ca063
3
  size 2735