Hugging Face's logo

seungbo7747
/
summarization_model

Transformers
Safetensors
t5
text2text-generation
Generated from Trainer
text-generation-inference
Model card Files
xet
Community
seungbo7747 commited on
Commit
f16bb3b
·
verified ·
1 Parent(s): ca495a5

End of training

Browse files
Files changed (3) hide show
  1. README.md +6 -18
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -18,11 +18,11 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [paust/pko-t5-base](https://huggingface.co/paust/pko-t5-base) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.7192
22
- - Rouge1: 0.0663
23
- - Rouge2: 0.0167
24
- - Rougel: 0.0663
25
- - Rougelsum: 0.0663
26
 
27
  ## Model description
28
 
@@ -47,23 +47,11 @@ The following hyperparameters were used during training:
47
  - seed: 42
48
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
49
  - lr_scheduler_type: linear
50
- - training_steps: 5000
51
  - mixed_precision_training: Native AMP
52
 
53
  ### Training results
54
 
55
- | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
56
- |:-------------:|:------:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
57
- | 1.1412 | 0.0111 | 500 | 0.8112 | 0.0612 | 0.0136 | 0.0611 | 0.0611 |
58
- | 0.8494 | 0.0222 | 1000 | 0.7681 | 0.0651 | 0.0150 | 0.0651 | 0.0650 |
59
- | 0.8299 | 0.0333 | 1500 | 0.7493 | 0.0659 | 0.0155 | 0.0658 | 0.0658 |
60
- | 0.7919 | 0.0444 | 2000 | 0.7379 | 0.0663 | 0.0158 | 0.0662 | 0.0662 |
61
- | 0.7858 | 0.0555 | 2500 | 0.7339 | 0.0667 | 0.0163 | 0.0667 | 0.0667 |
62
- | 0.7953 | 0.0666 | 3000 | 0.7330 | 0.0674 | 0.0164 | 0.0674 | 0.0674 |
63
- | 0.7769 | 0.0777 | 3500 | 0.7261 | 0.0679 | 0.0163 | 0.0679 | 0.0678 |
64
- | 0.7752 | 0.0888 | 4000 | 0.7182 | 0.0683 | 0.0163 | 0.0683 | 0.0683 |
65
- | 0.7743 | 0.0998 | 4500 | 0.7203 | 0.0682 | 0.0164 | 0.0681 | 0.0681 |
66
- | 0.7851 | 0.1109 | 5000 | 0.7179 | 0.0684 | 0.0165 | 0.0683 | 0.0683 |
67
 
68
 
69
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [paust/pko-t5-base](https://huggingface.co/paust/pko-t5-base) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.6324
22
+ - Rouge1: 0.0659
23
+ - Rouge2: 0.0156
24
+ - Rougel: 0.0658
25
+ - Rougelsum: 0.0659
26
 
27
  ## Model description
28
 
 
47
  - seed: 42
48
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
49
  - lr_scheduler_type: linear
50
+ - num_epochs: 1
51
  - mixed_precision_training: Native AMP
52
 
53
  ### Training results
54
 
 
 
 
 
 
 
 
 
 
 
 
 
55
 
56
 
57
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c7695f6cb2eb7b97708cd8464d7223ea0bc2a0fe8846cedc9124c35f4723564b
3
  size 1102350184
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99a75dd45f5868165be6953bd2f22d3937d31e784fedaba9cc8394b1604d0f52
3
  size 1102350184
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9d7873673bc720e72537bf4e33a6337b67a6fa36414171e3c9ebda81c392dc99
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c39910fff6ecb131e98d4394d25aa0174556afa517677d8c19091a780ac1ff6
3
  size 5368