End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,91 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: t5-base
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- glue
|
| 8 |
+
metrics:
|
| 9 |
+
- accuracy
|
| 10 |
+
model-index:
|
| 11 |
+
- name: t5-base_cola_dense_epochs-3
|
| 12 |
+
results:
|
| 13 |
+
- task:
|
| 14 |
+
name: Text Classification
|
| 15 |
+
type: text-classification
|
| 16 |
+
dataset:
|
| 17 |
+
name: glue
|
| 18 |
+
type: glue
|
| 19 |
+
config: cola
|
| 20 |
+
split: validation
|
| 21 |
+
args: cola
|
| 22 |
+
metrics:
|
| 23 |
+
- name: Accuracy
|
| 24 |
+
type: accuracy
|
| 25 |
+
value: 0.8264621284755513
|
| 26 |
+
---
|
| 27 |
+
|
| 28 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 29 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 30 |
+
|
| 31 |
+
# t5-base_cola_dense_epochs-3
|
| 32 |
+
|
| 33 |
+
This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the glue dataset.
|
| 34 |
+
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.4436
|
| 36 |
+
- Accuracy: 0.8265
|
| 37 |
+
|
| 38 |
+
## Model description
|
| 39 |
+
|
| 40 |
+
More information needed
|
| 41 |
+
|
| 42 |
+
## Intended uses & limitations
|
| 43 |
+
|
| 44 |
+
More information needed
|
| 45 |
+
|
| 46 |
+
## Training and evaluation data
|
| 47 |
+
|
| 48 |
+
More information needed
|
| 49 |
+
|
| 50 |
+
## Training procedure
|
| 51 |
+
|
| 52 |
+
### Training hyperparameters
|
| 53 |
+
|
| 54 |
+
The following hyperparameters were used during training:
|
| 55 |
+
- learning_rate: 5e-05
|
| 56 |
+
- train_batch_size: 32
|
| 57 |
+
- eval_batch_size: 64
|
| 58 |
+
- seed: 0
|
| 59 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 60 |
+
- lr_scheduler_type: linear
|
| 61 |
+
- lr_scheduler_warmup_steps: 20
|
| 62 |
+
- num_epochs: 3
|
| 63 |
+
|
| 64 |
+
### Training results
|
| 65 |
+
|
| 66 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 67 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 68 |
+
| 0.5779 | 0.19 | 50 | 0.5663 | 0.6913 |
|
| 69 |
+
| 0.4499 | 0.37 | 100 | 0.5698 | 0.7689 |
|
| 70 |
+
| 0.4599 | 0.56 | 150 | 0.4754 | 0.7996 |
|
| 71 |
+
| 0.3906 | 0.75 | 200 | 0.4966 | 0.8102 |
|
| 72 |
+
| 0.474 | 0.93 | 250 | 0.5193 | 0.8092 |
|
| 73 |
+
| 0.3694 | 1.12 | 300 | 0.4917 | 0.8245 |
|
| 74 |
+
| 0.3585 | 1.31 | 350 | 0.4704 | 0.8226 |
|
| 75 |
+
| 0.3412 | 1.49 | 400 | 0.4762 | 0.8207 |
|
| 76 |
+
| 0.429 | 1.68 | 450 | 0.4945 | 0.8245 |
|
| 77 |
+
| 0.3743 | 1.87 | 500 | 0.4436 | 0.8265 |
|
| 78 |
+
| 0.3028 | 2.05 | 550 | 0.5025 | 0.8265 |
|
| 79 |
+
| 0.3253 | 2.24 | 600 | 0.5310 | 0.8245 |
|
| 80 |
+
| 0.2961 | 2.43 | 650 | 0.4966 | 0.8303 |
|
| 81 |
+
| 0.2434 | 2.61 | 700 | 0.5028 | 0.8293 |
|
| 82 |
+
| 0.3262 | 2.8 | 750 | 0.5044 | 0.8284 |
|
| 83 |
+
| 0.2562 | 2.99 | 800 | 0.4945 | 0.8274 |
|
| 84 |
+
|
| 85 |
+
|
| 86 |
+
### Framework versions
|
| 87 |
+
|
| 88 |
+
- Transformers 4.34.1
|
| 89 |
+
- Pytorch 2.1.0+cu118
|
| 90 |
+
- Datasets 2.14.6
|
| 91 |
+
- Tokenizers 0.14.1
|