Hugging Face's logo

nandavikas16
/
bart-large-cnn-finetuned-scope-summarization

Text2Text Generation
Transformers
TensorBoard
Safetensors
bart
Generated from Trainer
Model card Files Metrics Community
nandavikas16 commited on
Commit
aabefd5
·
verified ·
1 Parent(s): 4b9cab4

Model save

Browse files
Files changed (7) hide show
  1. README.md +18 -28
  2. config.json +1 -1
  3. generation_config.json +1 -1
  4. model.safetensors +1 -1
  5. runs/Apr24_20-08-18_npy210lwh9/events.out.tfevents.1713989340.npy210lwh9.224.0 +3 -0
  6. runs/Apr24_20-08-18_npy210lwh9/events.out.tfevents.1713991087.npy210lwh9.224.1 +3 -0
  7. training_args.bin +1 -1
README.md CHANGED
@@ -17,11 +17,11 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.0243
21
- - Rouge1: 55.9358
22
- - Rouge2: 45.6813
23
- - Rougel: 49.2605
24
- - Rougelsum: 49.2571
25
 
26
  ## Model description
27
 
@@ -46,37 +46,27 @@ The following hyperparameters were used during training:
46
  - seed: 42
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
- - num_epochs: 20
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
54
  |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|
55
- | 0.6983 | 1.0 | 40 | 0.2685 | 44.58 | 29.0429 | 33.1495 | 33.1669 |
56
- | 0.2633 | 2.0 | 80 | 0.2441 | 43.3662 | 28.4897 | 33.4037 | 33.4937 |
57
- | 0.237 | 3.0 | 120 | 0.2337 | 45.9311 | 31.605 | 36.3412 | 36.4591 |
58
- | 0.225 | 4.0 | 160 | 0.2181 | 44.6684 | 30.2624 | 33.897 | 34.0548 |
59
- | 0.2021 | 5.0 | 200 | 0.2001 | 47.4399 | 33.8502 | 37.3868 | 37.5961 |
60
- | 0.2052 | 6.0 | 240 | 0.1894 | 49.5407 | 34.8779 | 38.7442 | 38.9632 |
61
- | 0.181 | 7.0 | 280 | 0.1772 | 50.5942 | 37.1982 | 39.6862 | 39.9688 |
62
- | 0.1764 | 8.0 | 320 | 0.1724 | 48.7175 | 34.9565 | 39.7672 | 40.0419 |
63
- | 0.1626 | 9.0 | 360 | 0.1568 | 49.6688 | 36.5888 | 40.6817 | 41.0034 |
64
- | 0.1429 | 10.0 | 400 | 0.1324 | 51.4759 | 39.2328 | 43.5475 | 43.6525 |
65
- | 0.1338 | 11.0 | 440 | 0.1206 | 50.0612 | 37.7502 | 42.3231 | 42.4899 |
66
- | 0.1142 | 12.0 | 480 | 0.0899 | 52.8525 | 40.2391 | 45.0142 | 45.1042 |
67
- | 0.1004 | 13.0 | 520 | 0.0706 | 54.8157 | 43.1336 | 46.6612 | 46.6237 |
68
- | 0.086 | 14.0 | 560 | 0.0564 | 55.0703 | 43.5883 | 47.3974 | 47.5532 |
69
- | 0.0695 | 15.0 | 600 | 0.0451 | 53.8285 | 44.1487 | 48.4204 | 48.5559 |
70
- | 0.0594 | 16.0 | 640 | 0.0357 | 55.0319 | 43.9487 | 47.9211 | 47.969 |
71
- | 0.0508 | 17.0 | 680 | 0.0346 | 56.3059 | 45.3574 | 49.1356 | 49.2768 |
72
- | 0.04 | 18.0 | 720 | 0.0279 | 57.2262 | 46.371 | 50.2692 | 50.2699 |
73
- | 0.0358 | 19.0 | 760 | 0.0259 | 55.606 | 45.1493 | 49.3667 | 49.4148 |
74
- | 0.0337 | 20.0 | 800 | 0.0243 | 55.9358 | 45.6813 | 49.2605 | 49.2571 |
75
 
76
 
77
  ### Framework versions
78
 
79
- - Transformers 4.40.0
80
- - Pytorch 2.2.2+cu121
81
  - Datasets 2.19.0
82
  - Tokenizers 0.19.1
 
17
 
18
  This model is a fine-tuned version of [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.1308
21
+ - Rouge1: 49.6683
22
+ - Rouge2: 37.3929
23
+ - Rougel: 41.666
24
+ - Rougelsum: 41.5602
25
 
26
  ## Model description
27
 
 
46
  - seed: 42
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
+ - num_epochs: 10
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
54
  |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|
55
+ | 0.696 | 1.0 | 40 | 0.2500 | 43.2634 | 27.0334 | 33.128 | 32.9348 |
56
+ | 0.2625 | 2.0 | 80 | 0.2228 | 42.4679 | 27.647 | 31.9258 | 31.7877 |
57
+ | 0.2425 | 3.0 | 120 | 0.2082 | 44.0252 | 30.8098 | 33.9707 | 33.9697 |
58
+ | 0.2266 | 4.0 | 160 | 0.1936 | 45.3968 | 32.4864 | 36.0748 | 35.9962 |
59
+ | 0.2031 | 5.0 | 200 | 0.1823 | 47.2956 | 34.832 | 38.3544 | 38.2526 |
60
+ | 0.2056 | 6.0 | 240 | 0.1677 | 46.3752 | 34.4471 | 37.3837 | 37.262 |
61
+ | 0.1819 | 7.0 | 280 | 0.1570 | 47.8024 | 35.2228 | 39.4649 | 39.3768 |
62
+ | 0.1762 | 8.0 | 320 | 0.1461 | 47.9403 | 37.0271 | 41.7617 | 41.6654 |
63
+ | 0.1637 | 9.0 | 360 | 0.1376 | 48.2515 | 36.0442 | 40.149 | 40.0905 |
64
+ | 0.1484 | 10.0 | 400 | 0.1308 | 49.6683 | 37.3929 | 41.666 | 41.5602 |
 
 
 
 
 
 
 
 
 
 
65
 
66
 
67
  ### Framework versions
68
 
69
+ - Transformers 4.40.1
70
+ - Pytorch 2.3.0+cu121
71
  - Datasets 2.19.0
72
  - Tokenizers 0.19.1
config.json CHANGED
@@ -65,7 +65,7 @@
65
  }
66
  },
67
  "torch_dtype": "float32",
68
- "transformers_version": "4.40.0",
69
  "use_cache": false,
70
  "vocab_size": 50264
71
  }
 
65
  }
66
  },
67
  "torch_dtype": "float32",
68
+ "transformers_version": "4.40.1",
69
  "use_cache": false,
70
  "vocab_size": 50264
71
  }
generation_config.json CHANGED
@@ -11,6 +11,6 @@
11
  "no_repeat_ngram_size": 3,
12
  "num_beams": 4,
13
  "pad_token_id": 1,
14
- "transformers_version": "4.40.0",
15
  "use_cache": false
16
  }
 
11
  "no_repeat_ngram_size": 3,
12
  "num_beams": 4,
13
  "pad_token_id": 1,
14
+ "transformers_version": "4.40.1",
15
  "use_cache": false
16
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aabe198442b74d9abec8a4b4c1826f27f336c8a80fc99c6501d40eb43e373c5d
3
  size 1625422896
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:274dbb6fdedb096bf296e8f1b5aab15da3b68d75a336208a875f114d66bac85e
3
  size 1625422896
runs/Apr24_20-08-18_npy210lwh9/events.out.tfevents.1713989340.npy210lwh9.224.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a2b40532f29a3e21bc35f8d0f3c80ab0ee25820e3b5d2ecf069a7eba2c4e8d6
3
+ size 13069
runs/Apr24_20-08-18_npy210lwh9/events.out.tfevents.1713991087.npy210lwh9.224.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1250ff5aaf065888142dbb2140e6a10c6acb1053fdaf70add34cd89fd827074
3
+ size 514
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d4310e994c5443befc0cc091e1be4decbb1b73131030fda5511a1547456c4de
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a58d954d914fd7dfd7b9b131bfe639c42338ac97f8b99b58bb3de1ed17551d17
3
  size 5240