Hugging Face's logo

GlycerinLOL
/
LLM_Teached_Bart_From_Scratch

Text2Text Generation
Transformers
TensorBoard
Safetensors
bart
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
GlycerinLOL commited on
Commit
5cfa814
•
1 Parent(s): e791723

Model save

Browse files
Files changed (3) hide show
  1. README.md +23 -17
  2. model.safetensors +1 -1
  3. runs/Mar04_21-07-04_oi5vv8ctr1709312124223-tkfr5/events.out.tfevents.1709557637.oi5vv8ctr1709312124223-tkfr5.22386.0 +2 -2
README.md CHANGED
@@ -20,15 +20,15 @@ should probably proofread and complete it, then remove this comment. -->
20
 
21
  This model is a fine-tuned version of [facebook/bart-large](https://huggingface.co/facebook/bart-large) on an unknown dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 1.6053
24
- - Rouge1: 0.4481
25
- - Rouge2: 0.2283
26
- - Rougel: 0.3861
27
- - Rougelsum: 0.3863
28
- - Gen Len: 19.9029
29
- - Precision: 0.9159
30
- - Recall: 0.8916
31
- - F1: 0.9034
32
 
33
  ## Model description
34
 
@@ -55,7 +55,7 @@ The following hyperparameters were used during training:
55
  - total_train_batch_size: 96
56
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
57
  - lr_scheduler_type: linear
58
- - num_epochs: 24
59
  - mixed_precision_training: Native AMP
60
 
61
  ### Training results
@@ -79,13 +79,19 @@ The following hyperparameters were used during training:
79
  | 0.8927 | 15.0 | 7815 | 0.9029 | 19.9065 | 1.5351 | 0.9156 | 0.8909 | 0.4457 | 0.2267 | 0.3842 | 0.384 |
80
  | 0.8773 | 16.0 | 8336 | 0.9025 | 19.9425 | 1.5440 | 0.9151 | 0.8905 | 0.4427 | 0.225 | 0.382 | 0.382 |
81
  | 0.8806 | 17.0 | 8857 | 0.9036 | 19.8851 | 1.5510 | 0.9159 | 0.8919 | 0.4495 | 0.2279 | 0.3868 | 0.3869 |
82
- | 0.8683 | 18.0 | 9378 | 1.5679 | 0.4473 | 0.2282 | 0.3856 | 0.3857 | 19.8829| 0.9161 | 0.8921 | 0.9038 |
83
- | 0.8413 | 19.0 | 9899 | 1.5745 | 0.4492 | 0.2282 | 0.3861 | 0.3864 | 19.9135| 0.9159 | 0.8918 | 0.9035 |
84
- | 0.8257 | 20.0 | 10420 | 1.5835 | 0.4471 | 0.2266 | 0.3852 | 0.3853 | 19.8996| 0.9153 | 0.8915 | 0.9031 |
85
- | 0.8097 | 21.0 | 10941 | 1.5957 | 0.4472 | 0.2271 | 0.3856 | 0.3856 | 19.9073| 0.9156 | 0.8919 | 0.9034 |
86
- | 0.7926 | 22.0 | 11462 | 1.5956 | 0.4479 | 0.2282 | 0.3855 | 0.3857 | 19.892 | 0.9159 | 0.8916 | 0.9034 |
87
- | 0.7841 | 23.0 | 11983 | 1.5990 | 0.4444 | 0.2261 | 0.3833 | 0.3834 | 19.912 | 0.9155 | 0.8908 | 0.9028 |
88
- | 0.7669 | 24.0 | 12504 | 1.6053 | 0.4481 | 0.2283 | 0.3861 | 0.3863 | 19.9029| 0.9159 | 0.8916 | 0.9034 |
 
 
 
 
 
 
89
 
90
 
91
  ### Framework versions
 
20
 
21
  This model is a fine-tuned version of [facebook/bart-large](https://huggingface.co/facebook/bart-large) on an unknown dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 1.6350
24
+ - Rouge1: 0.4471
25
+ - Rouge2: 0.2259
26
+ - Rougel: 0.3846
27
+ - Rougelsum: 0.3845
28
+ - Gen Len: 19.9087
29
+ - Precision: 0.9156
30
+ - Recall: 0.8915
31
+ - F1: 0.9033
32
 
33
  ## Model description
34
 
 
55
  - total_train_batch_size: 96
56
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
57
  - lr_scheduler_type: linear
58
+ - num_epochs: 30
59
  - mixed_precision_training: Native AMP
60
 
61
  ### Training results
 
79
  | 0.8927 | 15.0 | 7815 | 0.9029 | 19.9065 | 1.5351 | 0.9156 | 0.8909 | 0.4457 | 0.2267 | 0.3842 | 0.384 |
80
  | 0.8773 | 16.0 | 8336 | 0.9025 | 19.9425 | 1.5440 | 0.9151 | 0.8905 | 0.4427 | 0.225 | 0.382 | 0.382 |
81
  | 0.8806 | 17.0 | 8857 | 0.9036 | 19.8851 | 1.5510 | 0.9159 | 0.8919 | 0.4495 | 0.2279 | 0.3868 | 0.3869 |
82
+ | 0.8683 | 18.0 | 9378 | 0.9038 | 19.8829 | 1.5679 | 0.9161 | 0.8921 | 0.4473 | 0.2282 | 0.3856 | 0.3857 |
83
+ | 0.8413 | 19.0 | 9899 | 0.9035 | 19.9135 | 1.5745 | 0.9159 | 0.8918 | 0.4492 | 0.2282 | 0.3861 | 0.3864 |
84
+ | 0.8257 | 20.0 | 10420 | 0.9031 | 19.8996 | 1.5835 | 0.9153 | 0.8915 | 0.4471 | 0.2266 | 0.3852 | 0.3853 |
85
+ | 0.8097 | 21.0 | 10941 | 0.9034 | 19.9073 | 1.5957 | 0.9156 | 0.8919 | 0.4472 | 0.2271 | 0.3856 | 0.3856 |
86
+ | 0.7926 | 22.0 | 11462 | 0.9034 | 19.892 | 1.5956 | 0.9159 | 0.8916 | 0.4479 | 0.2282 | 0.3855 | 0.3857 |
87
+ | 0.7841 | 23.0 | 11983 | 0.9028 | 19.912 | 1.5990 | 0.9155 | 0.8908 | 0.4444 | 0.2261 | 0.3833 | 0.3834 |
88
+ | 0.7669 | 24.0 | 12504 | 1.6097 | 0.4491 | 0.2284 | 0.3872 | 0.387 | 19.9007| 0.9162 | 0.892 | 0.9037 |
89
+ | 0.7733 | 25.0 | 13025 | 1.6060 | 0.4442 | 0.2257 | 0.3827 | 0.3828 | 19.9178| 0.9154 | 0.8906 | 0.9027 |
90
+ | 0.7631 | 26.0 | 13546 | 1.6187 | 0.4472 | 0.2276 | 0.3861 | 0.3861 | 19.9175| 0.9154 | 0.8915 | 0.9031 |
91
+ | 0.7505 | 27.0 | 14067 | 1.6208 | 0.4463 | 0.227 | 0.3852 | 0.3851 | 19.8967| 0.9155 | 0.8914 | 0.9031 |
92
+ | 0.7413 | 28.0 | 14588 | 1.6237 | 0.4468 | 0.2273 | 0.3854 | 0.3853 | 19.9153| 0.9159 | 0.8912 | 0.9032 |
93
+ | 0.7348 | 29.0 | 15109 | 1.6312 | 0.4482 | 0.2268 | 0.3858 | 0.3858 | 19.8938| 0.9158 | 0.8918 | 0.9035 |
94
+ | 0.7286 | 30.0 | 15630 | 1.6350 | 0.4471 | 0.2259 | 0.3846 | 0.3845 | 19.9087| 0.9156 | 0.8915 | 0.9033 |
95
 
96
 
97
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:61d60e2875b9ab24774ea03a2445941f9271575b5634c9abc9e42a90e3ecb56d
3
  size 1625426996
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92e2e3bb6c5492e767df277fa27a2835f6aaca19b078845dcb2c7c435163d9a5
3
  size 1625426996
runs/Mar04_21-07-04_oi5vv8ctr1709312124223-tkfr5/events.out.tfevents.1709557637.oi5vv8ctr1709312124223-tkfr5.22386.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:52df640ff0f874f11ab8d489662040e49eb57e1d4758ed3056006b6c8c14bd69
3
- size 10551
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9faac5114715f3a07a50be091511275526e4d5d749181fb5a160ae56cfe59c45
3
+ size 11579