Hugging Face's logo

zbigi
/
bart-base-summarization-medical-47

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
zbigi commited on
Commit
d4c9755
•
1 Parent(s): 219fe0f

End of training

Browse files
Files changed (3) hide show
  1. README.md +20 -10
  2. adapter_model.safetensors +1 -1
  3. runs/Jul26_10-25-04_e858228a3e53/events.out.tfevents.1721989760.e858228a3e53.989.1 +2 -2
README.md CHANGED
@@ -2,6 +2,8 @@
2
  base_model: facebook/bart-base
3
  library_name: peft
4
  license: apache-2.0
 
 
5
  tags:
6
  - generated_from_trainer
7
  model-index:
@@ -16,16 +18,12 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
- - eval_loss: 3.8635
20
- - eval_rouge1: 0.2106
21
- - eval_rouge2: 0.0787
22
- - eval_rougeL: 0.1796
23
- - eval_rougeLsum: 0.1799
24
- - eval_gen_len: 19.976
25
- - eval_runtime: 255.5196
26
- - eval_samples_per_second: 3.914
27
- - eval_steps_per_second: 3.914
28
- - step: 0
29
 
30
  ## Model description
31
 
@@ -55,6 +53,18 @@ The following hyperparameters were used during training:
55
  - num_epochs: 6
56
  - mixed_precision_training: Native AMP
57
 
 
 
 
 
 
 
 
 
 
 
 
 
58
  ### Framework versions
59
 
60
  - PEFT 0.12.0
 
2
  base_model: facebook/bart-base
3
  library_name: peft
4
  license: apache-2.0
5
+ metrics:
6
+ - rouge
7
  tags:
8
  - generated_from_trainer
9
  model-index:
 
18
 
19
  This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 2.1308
22
+ - Rouge1: 0.4191
23
+ - Rouge2: 0.2227
24
+ - Rougel: 0.3552
25
+ - Rougelsum: 0.3555
26
+ - Gen Len: 18.216
 
 
 
 
27
 
28
  ## Model description
29
 
 
53
  - num_epochs: 6
54
  - mixed_precision_training: Native AMP
55
 
56
+ ### Training results
57
+
58
+ | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
59
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
60
+ | 2.7197 | 1.0 | 1250 | 2.2012 | 0.4139 | 0.2191 | 0.3517 | 0.3522 | 17.835 |
61
+ | 2.6119 | 2.0 | 2500 | 2.1664 | 0.416 | 0.2218 | 0.3517 | 0.3519 | 18.075 |
62
+ | 2.5724 | 3.0 | 3750 | 2.1502 | 0.4162 | 0.2197 | 0.3522 | 0.3526 | 18.298 |
63
+ | 2.548 | 4.0 | 5000 | 2.1390 | 0.4144 | 0.2197 | 0.3509 | 0.3511 | 18.138 |
64
+ | 2.5441 | 5.0 | 6250 | 2.1296 | 0.4199 | 0.224 | 0.3558 | 0.356 | 18.267 |
65
+ | 2.5115 | 6.0 | 7500 | 2.1308 | 0.4191 | 0.2227 | 0.3552 | 0.3555 | 18.216 |
66
+
67
+
68
  ### Framework versions
69
 
70
  - PEFT 0.12.0
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:59d5de61e963a5ea6676b5c8de70c1abe6946d32185f356032af8f4f659235bd
3
  size 894624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fec7f3f068b2febcc6c2e4c161af176c71f396b5e79785ea9740fe2577c1412
3
  size 894624
runs/Jul26_10-25-04_e858228a3e53/events.out.tfevents.1721989760.e858228a3e53.989.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b35670b03eb813e8884d44bbcc3229845a18175f84a7c400e997b30ce21df31
3
- size 536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4791874b81b9e080b419dea368e10612e844fb3925594b6581fb1157fa3b92c
3
+ size 13262