Hugging Face's logo

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

Text2Text Generation
Transformers
TensorBoard
Safetensors
bart
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
nandavikas16 commited on
Commit
a4fffd7
·
verified ·
1 Parent(s): cb0f142

Model save

Browse files
Files changed (5) hide show
  1. README.md +27 -27
  2. model.safetensors +1 -1
  3. runs/Mar09_08-40-11_nctv9mkenw/events.out.tfevents.1709974346.nctv9mkenw.278.0 +3 -0
  4. runs/Mar09_08-40-11_nctv9mkenw/events.out.tfevents.1709986586.nctv9mkenw.278.1 +3 -0
  5. 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: 0.0320
21
- - Rouge1: 68.9308
22
- - Rouge2: 57.4053
23
- - Rougel: 66.8076
24
- - Rougelsum: 66.8081
25
 
26
  ## Model description
27
 
@@ -41,8 +41,8 @@ More information needed
41
 
42
  The following hyperparameters were used during training:
43
  - learning_rate: 5.6e-05
44
- - train_batch_size: 8
45
- - eval_batch_size: 8
46
  - seed: 42
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
@@ -52,26 +52,26 @@ The following hyperparameters were used during training:
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
54
  |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|
55
- | 0.5951 | 1.0 | 43 | 0.3629 | 55.5555 | 36.8881 | 50.5214 | 50.3938 |
56
- | 0.355 | 2.0 | 86 | 0.3255 | 56.5617 | 38.8383 | 52.1122 | 52.1338 |
57
- | 0.3034 | 3.0 | 129 | 0.2861 | 62.6103 | 39.5617 | 58.1436 | 58.0926 |
58
- | 0.2739 | 4.0 | 172 | 0.2438 | 59.8522 | 42.3079 | 56.2315 | 56.1528 |
59
- | 0.2419 | 5.0 | 215 | 0.2209 | 60.6664 | 42.1228 | 56.5815 | 56.5675 |
60
- | 0.2181 | 6.0 | 258 | 0.1923 | 66.3468 | 45.9889 | 60.7055 | 60.7051 |
61
- | 0.1954 | 7.0 | 301 | 0.1744 | 62.4993 | 46.8847 | 57.8644 | 57.9921 |
62
- | 0.1652 | 8.0 | 344 | 0.1448 | 63.1495 | 46.7447 | 58.7703 | 58.7584 |
63
- | 0.1351 | 9.0 | 387 | 0.1211 | 61.9121 | 48.057 | 58.2305 | 58.3135 |
64
- | 0.0984 | 10.0 | 430 | 0.1181 | 64.3015 | 49.9335 | 60.9836 | 61.0381 |
65
- | 0.0701 | 11.0 | 473 | 0.0729 | 69.2083 | 55.1905 | 66.5834 | 66.5658 |
66
- | 0.0515 | 12.0 | 516 | 0.0518 | 67.9952 | 54.2532 | 65.1305 | 65.071 |
67
- | 0.0361 | 13.0 | 559 | 0.0590 | 62.9846 | 51.6252 | 61.847 | 61.8582 |
68
- | 0.0266 | 14.0 | 602 | 0.0481 | 67.7713 | 53.66 | 65.2245 | 65.087 |
69
- | 0.0194 | 15.0 | 645 | 0.0461 | 67.7427 | 54.1529 | 64.7487 | 64.5543 |
70
- | 0.0129 | 16.0 | 688 | 0.0247 | 68.6572 | 56.1596 | 65.8355 | 65.7232 |
71
- | 0.008 | 17.0 | 731 | 0.0357 | 67.562 | 53.9853 | 64.5544 | 64.4777 |
72
- | 0.0062 | 18.0 | 774 | 0.0435 | 68.3624 | 55.6939 | 65.9531 | 65.7978 |
73
- | 0.0052 | 19.0 | 817 | 0.0373 | 65.4457 | 53.3074 | 62.8389 | 63.0017 |
74
- | 0.0043 | 20.0 | 860 | 0.0320 | 68.9308 | 57.4053 | 66.8076 | 66.8081 |
75
 
76
 
77
  ### Framework versions
 
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: 0.0384
21
+ - Rouge1: 67.0012
22
+ - Rouge2: 55.1201
23
+ - Rougel: 64.9916
24
+ - Rougelsum: 65.0
25
 
26
  ## Model description
27
 
 
41
 
42
  The following hyperparameters were used during training:
43
  - learning_rate: 5.6e-05
44
+ - train_batch_size: 15
45
+ - eval_batch_size: 15
46
  - seed: 42
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
54
  |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|
55
+ | 0.6964 | 1.0 | 23 | 0.3699 | 50.5808 | 36.0599 | 48.8381 | 48.7816 |
56
+ | 0.3654 | 2.0 | 46 | 0.3412 | 56.4293 | 40.3615 | 53.4553 | 53.366 |
57
+ | 0.3112 | 3.0 | 69 | 0.2891 | 55.2786 | 41.4255 | 52.7934 | 52.7485 |
58
+ | 0.2749 | 4.0 | 92 | 0.2826 | 61.501 | 42.4993 | 56.3623 | 56.2897 |
59
+ | 0.2534 | 5.0 | 115 | 0.2314 | 62.1301 | 45.1421 | 58.4136 | 58.6102 |
60
+ | 0.2363 | 6.0 | 138 | 0.2202 | 60.738 | 43.6776 | 56.4619 | 56.553 |
61
+ | 0.2015 | 7.0 | 161 | 0.1876 | 65.3434 | 48.4004 | 61.6649 | 61.6797 |
62
+ | 0.1911 | 8.0 | 184 | 0.1667 | 62.5351 | 48.4521 | 59.7955 | 59.7174 |
63
+ | 0.1587 | 9.0 | 207 | 0.1280 | 63.6654 | 48.5257 | 61.1761 | 61.3154 |
64
+ | 0.1419 | 10.0 | 230 | 0.0920 | 65.0905 | 50.0418 | 61.9516 | 62.1153 |
65
+ | 0.1105 | 11.0 | 253 | 0.0632 | 64.3945 | 51.397 | 61.1146 | 61.0697 |
66
+ | 0.0855 | 12.0 | 276 | 0.0448 | 66.9018 | 55.0888 | 65.0609 | 65.0079 |
67
+ | 0.0652 | 13.0 | 299 | 0.0601 | 64.0396 | 52.9896 | 62.2512 | 62.2246 |
68
+ | 0.0441 | 14.0 | 322 | 0.0398 | 66.3833 | 55.1127 | 64.038 | 64.0185 |
69
+ | 0.0366 | 15.0 | 345 | 0.0241 | 66.9502 | 55.7562 | 64.8033 | 64.8408 |
70
+ | 0.0268 | 16.0 | 368 | 0.0594 | 69.0772 | 56.148 | 66.4356 | 66.5236 |
71
+ | 0.02 | 17.0 | 391 | 0.0344 | 66.4522 | 55.175 | 64.7948 | 64.7399 |
72
+ | 0.0155 | 18.0 | 414 | 0.0456 | 68.6415 | 56.1231 | 66.1926 | 66.2718 |
73
+ | 0.0119 | 19.0 | 437 | 0.0392 | 66.9798 | 55.3614 | 65.0161 | 64.9401 |
74
+ | 0.0096 | 20.0 | 460 | 0.0384 | 67.0012 | 55.1201 | 64.9916 | 65.0 |
75
 
76
 
77
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dc1d27ebdce9a47f657fb8eb9d57561de0a522284d89217faa9a3aff5b67520a
3
  size 1625422896
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aad6497d55a64668afa0072ed8407fbcb3435fb85fec01e686560e0f65f68b73
3
  size 1625422896
runs/Mar09_08-40-11_nctv9mkenw/events.out.tfevents.1709974346.nctv9mkenw.278.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63c6e896867c7886f18d451bf02c13bdd09f54e47795da0874ce770c9120ece3
3
+ size 19787
runs/Mar09_08-40-11_nctv9mkenw/events.out.tfevents.1709986586.nctv9mkenw.278.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ac19e0df881e2726386394d8d510796f0903af019b863849ff17ecb84d0dcd7
3
+ size 514
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:423f150df7f63dc214e28fbad6917d9e2daacb189b8142d63e2d91f6fd3d6d31
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33fbf263970f8043b25c41748f7c2957415a2e93325b656865ef4782553b3e40
3
  size 5112