Hugging Face's logo

GlycerinLOL
/
LLM_Teached_Pegasus

Text2Text Generation
Transformers
TensorBoard
Safetensors
pegasus
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
GlycerinLOL commited on
Commit
333f300
•
1 Parent(s): 70f4485

Model save

Browse files
Files changed (2) hide show
  1. README.md +21 -12
  2. runs/Dec28_22-03-28_n4bcoectr1703727001286-fmclw/events.out.tfevents.1703772212.n4bcoectr1703727001286-fmclw.87757.0 +2 -2
README.md CHANGED
@@ -1,8 +1,12 @@
1
  ---
 
2
  tags:
3
  - generated_from_trainer
4
  metrics:
5
  - rouge
 
 
 
6
  model-index:
7
  - name: LLM_Teached_Pegasus
8
  results: []
@@ -13,14 +17,17 @@ should probably proofread and complete it, then remove this comment. -->
13
 
14
  # LLM_Teached_Pegasus
15
 
16
- This model was trained from scratch on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 1.6452
19
- - Rouge1: 0.4595
20
- - Rouge2: 0.2033
21
- - Rougel: 0.3629
22
- - Rougelsum: 0.3628
23
- - Gen Len: 30.8536
 
 
 
24
 
25
  ## Model description
26
 
@@ -47,15 +54,17 @@ The following hyperparameters were used during training:
47
  - total_train_batch_size: 32
48
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
  - lr_scheduler_type: linear
50
- - num_epochs: 2
51
  - mixed_precision_training: Native AMP
52
 
53
  ### Training results
54
 
55
- | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
56
- |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
57
- | 1.7637 | 1.0 | 625 | 1.6549 | 0.4591 | 0.205 | 0.3628 | 0.3628 | 30.8636 |
58
- | 1.7226 | 2.0 | 1250 | 1.6452 | 0.4595 | 0.2033 | 0.3629 | 0.3628 | 30.8536 |
 
 
59
 
60
 
61
  ### Framework versions
 
1
  ---
2
+ base_model: google/pegasus-large
3
  tags:
4
  - generated_from_trainer
5
  metrics:
6
  - rouge
7
+ - precision
8
+ - recall
9
+ - f1
10
  model-index:
11
  - name: LLM_Teached_Pegasus
12
  results: []
 
17
 
18
  # LLM_Teached_Pegasus
19
 
20
+ This model is a fine-tuned version of [google/pegasus-large](https://huggingface.co/google/pegasus-large) on an unknown dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 1.6606
23
+ - Rouge1: 0.4557
24
+ - Rouge2: 0.2019
25
+ - Rougel: 0.3603
26
+ - Rougelsum: 0.3597
27
+ - Gen Len: 30.8509
28
+ - Precision: 0.9078
29
+ - Recall: 0.9053
30
+ - F1: 0.9064
31
 
32
  ## Model description
33
 
 
54
  - total_train_batch_size: 32
55
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
56
  - lr_scheduler_type: linear
57
+ - num_epochs: 4
58
  - mixed_precision_training: Native AMP
59
 
60
  ### Training results
61
 
62
+ | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | Precision | Recall | F1 |
63
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|:---------:|:------:|:------:|
64
+ | 2.0887 | 1.0 | 625 | 1.7362 | 0.4326 | 0.1871 | 0.3375 | 0.3373 | 31.2482 | 0.9035 | 0.9015 | 0.9023 |
65
+ | 1.8362 | 2.0 | 1250 | 1.6844 | 0.4466 | 0.1942 | 0.3511 | 0.3507 | 30.3036 | 0.9071 | 0.9032 | 0.905 |
66
+ | 1.7784 | 3.0 | 1875 | 1.6666 | 0.451 | 0.1992 | 0.3554 | 0.3551 | 30.7991 | 0.907 | 0.9045 | 0.9056 |
67
+ | 1.7261 | 4.0 | 2500 | 1.6606 | 0.4557 | 0.2019 | 0.3603 | 0.3597 | 30.8509 | 0.9078 | 0.9053 | 0.9064 |
68
 
69
 
70
  ### Framework versions
runs/Dec28_22-03-28_n4bcoectr1703727001286-fmclw/events.out.tfevents.1703772212.n4bcoectr1703727001286-fmclw.87757.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a03167fb730dafeebe1093f9e7308c8806be6c431e5fe9961e5160b044bc638b
3
- size 9764
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e364efadd6bf8e07a8b406bbcbdccf4dd082d409611448bf78d0d8ce86c1ecd7
3
+ size 10792