update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- glue
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
model-index:
|
| 10 |
+
- name: mobilebert_add_GLUE_Experiment_sst2
|
| 11 |
+
results:
|
| 12 |
+
- task:
|
| 13 |
+
name: Text Classification
|
| 14 |
+
type: text-classification
|
| 15 |
+
dataset:
|
| 16 |
+
name: glue
|
| 17 |
+
type: glue
|
| 18 |
+
config: sst2
|
| 19 |
+
split: validation
|
| 20 |
+
args: sst2
|
| 21 |
+
metrics:
|
| 22 |
+
- name: Accuracy
|
| 23 |
+
type: accuracy
|
| 24 |
+
value: 0.8027522935779816
|
| 25 |
+
---
|
| 26 |
+
|
| 27 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 28 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 29 |
+
|
| 30 |
+
# mobilebert_add_GLUE_Experiment_sst2
|
| 31 |
+
|
| 32 |
+
This model is a fine-tuned version of [google/mobilebert-uncased](https://huggingface.co/google/mobilebert-uncased) on the glue dataset.
|
| 33 |
+
It achieves the following results on the evaluation set:
|
| 34 |
+
- Loss: 0.5706
|
| 35 |
+
- Accuracy: 0.8028
|
| 36 |
+
|
| 37 |
+
## Model description
|
| 38 |
+
|
| 39 |
+
More information needed
|
| 40 |
+
|
| 41 |
+
## Intended uses & limitations
|
| 42 |
+
|
| 43 |
+
More information needed
|
| 44 |
+
|
| 45 |
+
## Training and evaluation data
|
| 46 |
+
|
| 47 |
+
More information needed
|
| 48 |
+
|
| 49 |
+
## Training procedure
|
| 50 |
+
|
| 51 |
+
### Training hyperparameters
|
| 52 |
+
|
| 53 |
+
The following hyperparameters were used during training:
|
| 54 |
+
- learning_rate: 5e-05
|
| 55 |
+
- train_batch_size: 128
|
| 56 |
+
- eval_batch_size: 128
|
| 57 |
+
- seed: 10
|
| 58 |
+
- distributed_type: multi-GPU
|
| 59 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 60 |
+
- lr_scheduler_type: linear
|
| 61 |
+
- num_epochs: 50
|
| 62 |
+
|
| 63 |
+
### Training results
|
| 64 |
+
|
| 65 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 66 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 67 |
+
| 0.6635 | 1.0 | 527 | 0.6994 | 0.5390 |
|
| 68 |
+
| 0.5959 | 2.0 | 1054 | 0.6921 | 0.5665 |
|
| 69 |
+
| 0.5684 | 3.0 | 1581 | 0.7082 | 0.5516 |
|
| 70 |
+
| 0.5544 | 4.0 | 2108 | 0.6883 | 0.5619 |
|
| 71 |
+
| 0.5471 | 5.0 | 2635 | 0.6938 | 0.5940 |
|
| 72 |
+
| 0.5414 | 6.0 | 3162 | 0.7045 | 0.5803 |
|
| 73 |
+
| 0.5381 | 7.0 | 3689 | 0.7354 | 0.5654 |
|
| 74 |
+
| 0.5338 | 8.0 | 4216 | 0.7316 | 0.5826 |
|
| 75 |
+
| 0.3529 | 9.0 | 4743 | 0.4671 | 0.7970 |
|
| 76 |
+
| 0.2415 | 10.0 | 5270 | 0.4722 | 0.7982 |
|
| 77 |
+
| 0.2075 | 11.0 | 5797 | 0.4797 | 0.8062 |
|
| 78 |
+
| 0.1862 | 12.0 | 6324 | 0.5134 | 0.7993 |
|
| 79 |
+
| 0.1724 | 13.0 | 6851 | 0.5256 | 0.7993 |
|
| 80 |
+
| 0.1662 | 14.0 | 7378 | 0.5706 | 0.8028 |
|
| 81 |
+
|
| 82 |
+
|
| 83 |
+
### Framework versions
|
| 84 |
+
|
| 85 |
+
- Transformers 4.26.0
|
| 86 |
+
- Pytorch 1.14.0a0+410ce96
|
| 87 |
+
- Datasets 2.8.0
|
| 88 |
+
- Tokenizers 0.13.2
|