update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- xsum
|
| 7 |
+
model-index:
|
| 8 |
+
- name: t5-small-xsum
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# t5-small-xsum
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the xsum dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 2.3953
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 5e-05
|
| 39 |
+
- train_batch_size: 1
|
| 40 |
+
- eval_batch_size: 1
|
| 41 |
+
- seed: 42
|
| 42 |
+
- gradient_accumulation_steps: 16
|
| 43 |
+
- total_train_batch_size: 16
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: linear
|
| 46 |
+
- lr_scheduler_warmup_steps: 500
|
| 47 |
+
- num_epochs: 1
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
| 53 |
+
| 2.8641 | 0.04 | 500 | 2.6202 |
|
| 54 |
+
| 2.7466 | 0.08 | 1000 | 2.5660 |
|
| 55 |
+
| 2.8767 | 0.12 | 1500 | 2.5319 |
|
| 56 |
+
| 2.7099 | 0.16 | 2000 | 2.5107 |
|
| 57 |
+
| 2.7752 | 0.2 | 2500 | 2.4922 |
|
| 58 |
+
| 2.6037 | 0.24 | 3000 | 2.4800 |
|
| 59 |
+
| 2.8236 | 0.27 | 3500 | 2.4677 |
|
| 60 |
+
| 2.7089 | 0.31 | 4000 | 2.4581 |
|
| 61 |
+
| 2.7299 | 0.35 | 4500 | 2.4498 |
|
| 62 |
+
| 2.7498 | 0.39 | 5000 | 2.4420 |
|
| 63 |
+
| 2.6186 | 0.43 | 5500 | 2.4346 |
|
| 64 |
+
| 2.7817 | 0.47 | 6000 | 2.4288 |
|
| 65 |
+
| 2.5559 | 0.51 | 6500 | 2.4239 |
|
| 66 |
+
| 2.6725 | 0.55 | 7000 | 2.4186 |
|
| 67 |
+
| 2.6316 | 0.59 | 7500 | 2.4149 |
|
| 68 |
+
| 2.5561 | 0.63 | 8000 | 2.4115 |
|
| 69 |
+
| 2.5708 | 0.67 | 8500 | 2.4097 |
|
| 70 |
+
| 2.5861 | 0.71 | 9000 | 2.4052 |
|
| 71 |
+
| 2.6363 | 0.74 | 9500 | 2.4024 |
|
| 72 |
+
| 2.7435 | 0.78 | 10000 | 2.4003 |
|
| 73 |
+
| 2.7258 | 0.82 | 10500 | 2.3992 |
|
| 74 |
+
| 2.6113 | 0.86 | 11000 | 2.3983 |
|
| 75 |
+
| 2.6006 | 0.9 | 11500 | 2.3972 |
|
| 76 |
+
| 2.5684 | 0.94 | 12000 | 2.3960 |
|
| 77 |
+
| 2.6181 | 0.98 | 12500 | 2.3953 |
|
| 78 |
+
|
| 79 |
+
|
| 80 |
+
### Framework versions
|
| 81 |
+
|
| 82 |
+
- Transformers 4.18.0
|
| 83 |
+
- Pytorch 1.10.0+cu111
|
| 84 |
+
- Datasets 2.0.0
|
| 85 |
+
- Tokenizers 0.11.6
|