text-summarization-T5
Browse files
README.md
ADDED
|
@@ -0,0 +1,93 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: t5-small
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
datasets:
|
| 8 |
+
- xsum
|
| 9 |
+
model-index:
|
| 10 |
+
- name: text-summarization-T5
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# text-summarization-T5
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the xsum dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 2.6883
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 2e-05
|
| 41 |
+
- train_batch_size: 16
|
| 42 |
+
- eval_batch_size: 16
|
| 43 |
+
- seed: 42
|
| 44 |
+
- gradient_accumulation_steps: 8
|
| 45 |
+
- total_train_batch_size: 128
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: linear
|
| 48 |
+
- num_epochs: 2
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 54 |
+
| 3.8764 | 0.0627 | 100 | 3.6376 |
|
| 55 |
+
| 3.6129 | 0.1255 | 200 | 3.2631 |
|
| 56 |
+
| 3.3392 | 0.1882 | 300 | 3.0248 |
|
| 57 |
+
| 3.207 | 0.2509 | 400 | 2.9294 |
|
| 58 |
+
| 3.1548 | 0.3137 | 500 | 2.8725 |
|
| 59 |
+
| 3.0969 | 0.3764 | 600 | 2.8333 |
|
| 60 |
+
| 3.0718 | 0.4391 | 700 | 2.8018 |
|
| 61 |
+
| 3.0476 | 0.5018 | 800 | 2.7803 |
|
| 62 |
+
| 3.0431 | 0.5646 | 900 | 2.7651 |
|
| 63 |
+
| 3.0216 | 0.6273 | 1000 | 2.7538 |
|
| 64 |
+
| 3.0003 | 0.6900 | 1100 | 2.7440 |
|
| 65 |
+
| 3.0018 | 0.7528 | 1200 | 2.7363 |
|
| 66 |
+
| 2.9993 | 0.8155 | 1300 | 2.7289 |
|
| 67 |
+
| 2.9833 | 0.8782 | 1400 | 2.7236 |
|
| 68 |
+
| 2.9827 | 0.9410 | 1500 | 2.7181 |
|
| 69 |
+
| 2.9737 | 1.0037 | 1600 | 2.7145 |
|
| 70 |
+
| 2.968 | 1.0664 | 1700 | 2.7107 |
|
| 71 |
+
| 2.967 | 1.1291 | 1800 | 2.7074 |
|
| 72 |
+
| 2.9709 | 1.1919 | 1900 | 2.7042 |
|
| 73 |
+
| 2.9593 | 1.2546 | 2000 | 2.7011 |
|
| 74 |
+
| 2.9628 | 1.3173 | 2100 | 2.6987 |
|
| 75 |
+
| 2.9573 | 1.3801 | 2200 | 2.6969 |
|
| 76 |
+
| 2.955 | 1.4428 | 2300 | 2.6947 |
|
| 77 |
+
| 2.9483 | 1.5055 | 2400 | 2.6934 |
|
| 78 |
+
| 2.9546 | 1.5683 | 2500 | 2.6923 |
|
| 79 |
+
| 2.9492 | 1.6310 | 2600 | 2.6910 |
|
| 80 |
+
| 2.9493 | 1.6937 | 2700 | 2.6903 |
|
| 81 |
+
| 2.9482 | 1.7564 | 2800 | 2.6896 |
|
| 82 |
+
| 2.9524 | 1.8192 | 2900 | 2.6890 |
|
| 83 |
+
| 2.9399 | 1.8819 | 3000 | 2.6886 |
|
| 84 |
+
| 2.9347 | 1.9446 | 3100 | 2.6883 |
|
| 85 |
+
|
| 86 |
+
|
| 87 |
+
### Framework versions
|
| 88 |
+
|
| 89 |
+
- PEFT 0.14.0
|
| 90 |
+
- Transformers 4.44.2
|
| 91 |
+
- Pytorch 2.4.1+cu121
|
| 92 |
+
- Datasets 3.2.0
|
| 93 |
+
- Tokenizers 0.19.1
|