Commit ·
0380167
1
Parent(s): 7b5981d
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: output
|
| 7 |
+
results: []
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 11 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 12 |
+
|
| 13 |
+
# output
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 0.2735
|
| 18 |
+
- Rouge2 Precision: 0.5815
|
| 19 |
+
- Rouge2 Recall: 0.3607
|
| 20 |
+
- Rouge2 Fmeasure: 0.4211
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 5e-05
|
| 40 |
+
- train_batch_size: 32
|
| 41 |
+
- eval_batch_size: 32
|
| 42 |
+
- seed: 42
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- num_epochs: 20
|
| 46 |
+
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge2 Precision | Rouge2 Recall | Rouge2 Fmeasure |
|
| 50 |
+
|:-------------:|:-----:|:----:|:---------------:|:----------------:|:-------------:|:---------------:|
|
| 51 |
+
| No log | 1.0 | 303 | 0.5304 | 0.3963 | 0.2303 | 0.2724 |
|
| 52 |
+
| 0.5763 | 2.0 | 606 | 0.4784 | 0.4264 | 0.2542 | 0.2991 |
|
| 53 |
+
| 0.5763 | 3.0 | 909 | 0.4394 | 0.4446 | 0.2702 | 0.3162 |
|
| 54 |
+
| 0.4884 | 4.0 | 1212 | 0.4117 | 0.4607 | 0.2834 | 0.331 |
|
| 55 |
+
| 0.4346 | 5.0 | 1515 | 0.3852 | 0.4756 | 0.2931 | 0.3422 |
|
| 56 |
+
| 0.4346 | 6.0 | 1818 | 0.3677 | 0.4914 | 0.3016 | 0.3527 |
|
| 57 |
+
| 0.4035 | 7.0 | 2121 | 0.3520 | 0.5147 | 0.3197 | 0.3731 |
|
| 58 |
+
| 0.4035 | 8.0 | 2424 | 0.3382 | 0.5239 | 0.3228 | 0.3779 |
|
| 59 |
+
| 0.3726 | 9.0 | 2727 | 0.3251 | 0.5279 | 0.3243 | 0.3797 |
|
| 60 |
+
| 0.3512 | 10.0 | 3030 | 0.3128 | 0.5443 | 0.3364 | 0.3933 |
|
| 61 |
+
| 0.3512 | 11.0 | 3333 | 0.3085 | 0.5536 | 0.3437 | 0.4013 |
|
| 62 |
+
| 0.3342 | 12.0 | 3636 | 0.2983 | 0.5555 | 0.3439 | 0.4017 |
|
| 63 |
+
| 0.3342 | 13.0 | 3939 | 0.2935 | 0.5557 | 0.3452 | 0.403 |
|
| 64 |
+
| 0.3249 | 14.0 | 4242 | 0.2867 | 0.5635 | 0.3496 | 0.408 |
|
| 65 |
+
| 0.3132 | 15.0 | 4545 | 0.2832 | 0.5654 | 0.3496 | 0.4084 |
|
| 66 |
+
| 0.3132 | 16.0 | 4848 | 0.2797 | 0.5724 | 0.3545 | 0.4141 |
|
| 67 |
+
| 0.3074 | 17.0 | 5151 | 0.2768 | 0.5724 | 0.3547 | 0.414 |
|
| 68 |
+
| 0.3074 | 18.0 | 5454 | 0.2757 | 0.5799 | 0.3596 | 0.4201 |
|
| 69 |
+
| 0.3005 | 19.0 | 5757 | 0.2736 | 0.5831 | 0.3623 | 0.4231 |
|
| 70 |
+
| 0.2986 | 20.0 | 6060 | 0.2735 | 0.5815 | 0.3607 | 0.4211 |
|
| 71 |
+
|
| 72 |
+
|
| 73 |
+
### Framework versions
|
| 74 |
+
|
| 75 |
+
- Transformers 4.27.3
|
| 76 |
+
- Pytorch 2.0.0+cu117
|
| 77 |
+
- Tokenizers 0.13.2
|