Hugging Face's logo

CyrexPro
/
pegasus-large-finetuned-cnn_dailymail

Text2Text Generation
Transformers
TensorBoard
Safetensors
pegasus
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
CyrexPro commited on
Commit
8a58bed
•
1 Parent(s): 91d2bd8

Model save

Browse files
Files changed (3) hide show
  1. README.md +18 -19
  2. model.safetensors +1 -1
  3. runs/May07_01-02-18_DESKTOP-I570M0U/events.out.tfevents.1715032946.DESKTOP-I570M0U.722.0 +2 -2
README.md CHANGED
@@ -16,16 +16,17 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [google/pegasus-large](https://huggingface.co/google/pegasus-large) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.5155
20
- - Rouge1: 53.2323
21
- - Rouge2: 38.6836
22
- - Rougel: 41.8756
23
- - Rougelsum: 50.7526
24
- - Bleu 1: 39.2946
25
- - Bleu 2: 33.2337
26
- - Bleu 3: 30.2125
27
- - Meteor: 40.4525
28
- - Compression rate: 1.4202
 
29
 
30
  ## Model description
31
 
@@ -50,18 +51,16 @@ The following hyperparameters were used during training:
50
  - seed: 42
51
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
  - lr_scheduler_type: linear
53
- - num_epochs: 6
54
 
55
  ### Training results
56
 
57
- | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Bleu 1 | Bleu 2 | Bleu 3 | Meteor | Compression rate |
58
- |:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|:-------:|:-------:|:-------:|:----------------:|
59
- | 1.1676 | 1.0 | 5000 | 0.4626 | 58.2243 | 46.8729 | 49.6754 | 56.3425 | 45.8036 | 41.0494 | 38.8167 | 47.5864 | 1.3223 |
60
- | 0.8474 | 2.0 | 10000 | 0.4951 | 51.7813 | 37.5081 | 40.999 | 49.3373 | 38.9702 | 32.8144 | 30.0222 | 39.7542 | 1.3725 |
61
- | 0.7632 | 3.0 | 15000 | 0.4712 | 54.9872 | 41.6279 | 44.557 | 52.6927 | 42.0867 | 36.3443 | 33.5877 | 43.0071 | 1.3649 |
62
- | 0.7009 | 4.0 | 20000 | 0.4875 | 54.5016 | 40.85 | 44.0557 | 52.0705 | 40.2939 | 34.6751 | 31.8994 | 41.8203 | 1.4397 |
63
- | 0.6563 | 5.0 | 25000 | 0.5036 | 52.3997 | 37.6472 | 41.0743 | 49.8349 | 38.2882 | 32.1617 | 29.1582 | 39.4024 | 1.441 |
64
- | 0.6274 | 6.0 | 30000 | 0.5155 | 53.2323 | 38.6836 | 41.8756 | 50.7526 | 39.2946 | 33.2337 | 30.2125 | 40.4525 | 1.4202 |
65
 
66
 
67
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [google/pegasus-large](https://huggingface.co/google/pegasus-large) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.8591
20
+ - Rouge1: 47.5545
21
+ - Rouge2: 24.7124
22
+ - Rougel: 34.1029
23
+ - Rougelsum: 44.0189
24
+ - Bleu 1: 37.0636
25
+ - Bleu 2: 25.5604
26
+ - Bleu 3: 19.3415
27
+ - Meteor: 38.0261
28
+ - Lungime rezumat: 57.9183
29
+ - Lungime original: 48.6393
30
 
31
  ## Model description
32
 
 
51
  - seed: 42
52
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
53
  - lr_scheduler_type: linear
54
+ - num_epochs: 4
55
 
56
  ### Training results
57
 
58
+ | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Bleu 1 | Bleu 2 | Bleu 3 | Meteor | Lungime rezumat | Lungime original |
59
+ |:-------------:|:-----:|:------:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|:-------:|:-------:|:-------:|:---------------:|:----------------:|
60
+ | 0.9693 | 1.0 | 28660 | 0.8691 | 47.0692 | 24.3586 | 33.6526 | 43.4825 | 36.2858 | 24.9738 | 18.8926 | 37.8237 | 59.475 | 48.6393 |
61
+ | 0.8248 | 2.0 | 57320 | 0.8598 | 46.751 | 24.0748 | 33.3009 | 43.1207 | 36.0845 | 24.7477 | 18.6962 | 37.8529 | 60.7557 | 48.6393 |
62
+ | 0.7578 | 3.0 | 85980 | 0.8570 | 47.2636 | 24.4414 | 33.8604 | 43.6832 | 36.6893 | 25.2309 | 19.0981 | 38.0561 | 59.0953 | 48.6393 |
63
+ | 0.7145 | 4.0 | 114640 | 0.8591 | 47.5545 | 24.7124 | 34.1029 | 44.0189 | 37.0636 | 25.5604 | 19.3415 | 38.0261 | 57.9183 | 48.6393 |
 
 
64
 
65
 
66
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:df70144d3e36db09772de9d279822f0d61695c277ac2ad458523680591fb907b
3
  size 2283652852
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb962bd456bc6e97f0773d694fe4b19247578650f7ca2c251b903c6033da9f42
3
  size 2283652852
runs/May07_01-02-18_DESKTOP-I570M0U/events.out.tfevents.1715032946.DESKTOP-I570M0U.722.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b9f5a1a91050047e78063b6c2fc97d93dd87631384338c919ae16f112bb86143
3
- size 10405
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3226e340f32ae5f7d9b3d75e41df0e285db031383d1756383b19bafa003d89b5
3
+ size 11788