End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,112 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: t5-large
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- glue
|
| 8 |
+
metrics:
|
| 9 |
+
- accuracy
|
| 10 |
+
model-index:
|
| 11 |
+
- name: t5-large_cola_sp0_ar0_one
|
| 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: 0.87890625
|
| 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-large_cola_sp0_ar0_one
|
| 32 |
+
|
| 33 |
+
This model is a fine-tuned version of [t5-large](https://huggingface.co/t5-large) on the glue dataset.
|
| 34 |
+
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.4212
|
| 36 |
+
- Accuracy: 0.8789
|
| 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: 16
|
| 57 |
+
- eval_batch_size: 32
|
| 58 |
+
- seed: 1
|
| 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 |
+
- training_steps: 0
|
| 63 |
+
|
| 64 |
+
### Training results
|
| 65 |
+
|
| 66 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 67 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 68 |
+
| 0.6975 | 0.05 | 25 | 0.6708 | 0.6913 |
|
| 69 |
+
| 0.5747 | 0.11 | 50 | 0.5123 | 0.7210 |
|
| 70 |
+
| 0.4924 | 0.16 | 75 | 0.5004 | 0.7939 |
|
| 71 |
+
| 0.4259 | 0.21 | 100 | 0.4760 | 0.7987 |
|
| 72 |
+
| 0.3834 | 0.27 | 125 | 0.5001 | 0.8111 |
|
| 73 |
+
| 0.3942 | 0.32 | 150 | 0.4982 | 0.8092 |
|
| 74 |
+
| 0.4213 | 0.37 | 175 | 0.5078 | 0.8150 |
|
| 75 |
+
| 0.3845 | 0.42 | 200 | 0.4346 | 0.8092 |
|
| 76 |
+
| 0.4145 | 0.48 | 225 | 0.4562 | 0.8150 |
|
| 77 |
+
| 0.3751 | 0.53 | 250 | 0.4948 | 0.8169 |
|
| 78 |
+
| 0.4134 | 0.58 | 275 | 0.4356 | 0.8236 |
|
| 79 |
+
| 0.3777 | 0.64 | 300 | 0.4627 | 0.8188 |
|
| 80 |
+
| 0.3815 | 0.69 | 325 | 0.4772 | 0.8226 |
|
| 81 |
+
| 0.367 | 0.74 | 350 | 0.4117 | 0.8313 |
|
| 82 |
+
| 0.342 | 0.8 | 375 | 0.4177 | 0.8351 |
|
| 83 |
+
| 0.3136 | 0.85 | 400 | 0.5026 | 0.8265 |
|
| 84 |
+
| 0.3222 | 0.9 | 425 | 0.5323 | 0.8303 |
|
| 85 |
+
| 0.3863 | 0.96 | 450 | 0.4937 | 0.8245 |
|
| 86 |
+
| 0.348 | 1.01 | 475 | 0.4704 | 0.8188 |
|
| 87 |
+
| 0.2134 | 1.06 | 500 | 0.6430 | 0.8207 |
|
| 88 |
+
| 0.2671 | 1.11 | 525 | 0.5518 | 0.8226 |
|
| 89 |
+
| 0.1892 | 1.17 | 550 | 0.5869 | 0.8370 |
|
| 90 |
+
| 0.2184 | 1.22 | 575 | 0.5816 | 0.8332 |
|
| 91 |
+
| 0.22 | 1.27 | 600 | 0.5451 | 0.8274 |
|
| 92 |
+
| 0.1982 | 1.33 | 625 | 0.7300 | 0.8313 |
|
| 93 |
+
| 0.2734 | 1.38 | 650 | 0.7040 | 0.8351 |
|
| 94 |
+
| 0.2186 | 1.43 | 675 | 0.6650 | 0.8341 |
|
| 95 |
+
| 0.2835 | 1.49 | 700 | 0.6628 | 0.8322 |
|
| 96 |
+
| 0.2503 | 1.54 | 725 | 0.5194 | 0.8341 |
|
| 97 |
+
| 0.2438 | 1.59 | 750 | 0.5362 | 0.8313 |
|
| 98 |
+
| 0.2307 | 1.65 | 775 | 0.5405 | 0.8293 |
|
| 99 |
+
| 0.2111 | 1.7 | 800 | 0.6129 | 0.8265 |
|
| 100 |
+
| 0.1952 | 1.75 | 825 | 0.6411 | 0.8255 |
|
| 101 |
+
| 0.2873 | 1.8 | 850 | 0.6279 | 0.8245 |
|
| 102 |
+
| 0.295 | 1.86 | 875 | 0.5938 | 0.8236 |
|
| 103 |
+
| 0.2967 | 1.91 | 900 | 0.5694 | 0.8265 |
|
| 104 |
+
| 0.2128 | 1.96 | 925 | 0.5576 | 0.8265 |
|
| 105 |
+
|
| 106 |
+
|
| 107 |
+
### Framework versions
|
| 108 |
+
|
| 109 |
+
- Transformers 4.33.2
|
| 110 |
+
- Pytorch 2.0.1+cu117
|
| 111 |
+
- Datasets 2.14.5
|
| 112 |
+
- Tokenizers 0.11.6
|