Hugging Face's logo

JimmyPin
/
mt5-finetuned-summarize

Summarization
Transformers
Safetensors
mt5
text2text-generation
Generated from Trainer
Inference Endpoints
Model card Files Community
JimmyPin commited on
Commit
5a64bd8
·
verified ·
1 Parent(s): c0676f5

Training complete

Browse files
Files changed (1) hide show
  1. README.md +14 -12
README.md CHANGED
@@ -19,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  This model is a fine-tuned version of [google/mt5-base](https://huggingface.co/google/mt5-base) on an unknown dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.2613
23
  - Rouge1: 2.1127
24
  - Rouge2: 0.0
25
  - Rougel: 2.1127
@@ -43,25 +43,27 @@ More information needed
43
 
44
  The following hyperparameters were used during training:
45
  - learning_rate: 5.6e-05
46
- - train_batch_size: 8
47
- - eval_batch_size: 8
48
  - seed: 42
49
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
50
  - lr_scheduler_type: linear
51
- - num_epochs: 8
52
 
53
  ### Training results
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
56
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
57
- | 5.8246 | 1.0 | 159 | 1.4914 | 2.1127 | 0.0 | 2.1127 | 2.1127 |
58
- | 1.4676 | 2.0 | 318 | 0.4395 | 1.6432 | 0.0 | 1.8779 | 1.8779 |
59
- | 0.6332 | 3.0 | 477 | 0.3840 | 1.6432 | 0.0 | 1.8779 | 1.8779 |
60
- | 0.4717 | 4.0 | 636 | 0.3274 | 1.6432 | 0.0 | 1.8779 | 1.8779 |
61
- | 0.3878 | 5.0 | 795 | 0.3058 | 2.1127 | 0.0 | 2.1127 | 2.1127 |
62
- | 0.3826 | 6.0 | 954 | 0.2466 | 2.1127 | 0.0 | 2.1127 | 2.1127 |
63
- | 0.3243 | 7.0 | 1113 | 0.2535 | 2.1127 | 0.0 | 2.1127 | 2.1127 |
64
- | 0.2976 | 8.0 | 1272 | 0.2613 | 2.1127 | 0.0 | 2.1127 | 2.1127 |
 
 
65
 
66
 
67
  ### Framework versions
 
19
 
20
  This model is a fine-tuned version of [google/mt5-base](https://huggingface.co/google/mt5-base) on an unknown dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 0.2541
23
  - Rouge1: 2.1127
24
  - Rouge2: 0.0
25
  - Rougel: 2.1127
 
43
 
44
  The following hyperparameters were used during training:
45
  - learning_rate: 5.6e-05
46
+ - train_batch_size: 4
47
+ - eval_batch_size: 4
48
  - seed: 42
49
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
50
  - lr_scheduler_type: linear
51
+ - num_epochs: 10
52
 
53
  ### Training results
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
56
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
57
+ | 5.0046 | 1.0 | 318 | 0.6492 | 1.8779 | 0.0 | 1.8779 | 1.8779 |
58
+ | 0.7442 | 2.0 | 636 | 0.3680 | 1.8779 | 0.0 | 1.8779 | 1.8779 |
59
+ | 0.3964 | 3.0 | 954 | 0.3406 | 1.8779 | 0.0 | 1.8779 | 1.8779 |
60
+ | 0.3123 | 4.0 | 1272 | 0.3082 | 2.1127 | 0.0 | 2.1127 | 2.1127 |
61
+ | 0.2566 | 5.0 | 1590 | 0.2820 | 2.1127 | 0.0 | 2.1127 | 2.1127 |
62
+ | 0.2184 | 6.0 | 1908 | 0.2531 | 2.1127 | 0.0 | 2.1127 | 2.1127 |
63
+ | 0.1725 | 7.0 | 2226 | 0.2482 | 2.1127 | 0.0 | 2.1127 | 2.1127 |
64
+ | 0.17 | 8.0 | 2544 | 0.2537 | 2.1127 | 0.0 | 2.1127 | 2.1127 |
65
+ | 0.1355 | 9.0 | 2862 | 0.2528 | 2.1127 | 0.0 | 2.1127 | 2.1127 |
66
+ | 0.1284 | 10.0 | 3180 | 0.2541 | 2.1127 | 0.0 | 2.1127 | 2.1127 |
67
 
68
 
69
  ### Framework versions