End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,90 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: google/bert_uncased_L-12_H-256_A-4
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- massive
|
| 8 |
+
metrics:
|
| 9 |
+
- accuracy
|
| 10 |
+
model-index:
|
| 11 |
+
- name: bert_uncased_L-12_H-256_A-4_massive
|
| 12 |
+
results:
|
| 13 |
+
- task:
|
| 14 |
+
name: Text Classification
|
| 15 |
+
type: text-classification
|
| 16 |
+
dataset:
|
| 17 |
+
name: massive
|
| 18 |
+
type: massive
|
| 19 |
+
config: en-US
|
| 20 |
+
split: validation
|
| 21 |
+
args: en-US
|
| 22 |
+
metrics:
|
| 23 |
+
- name: Accuracy
|
| 24 |
+
type: accuracy
|
| 25 |
+
value: 0.8617806197737334
|
| 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 |
+
# bert_uncased_L-12_H-256_A-4_massive
|
| 32 |
+
|
| 33 |
+
This model is a fine-tuned version of [google/bert_uncased_L-12_H-256_A-4](https://huggingface.co/google/bert_uncased_L-12_H-256_A-4) on the massive dataset.
|
| 34 |
+
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.6679
|
| 36 |
+
- Accuracy: 0.8618
|
| 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: 64
|
| 57 |
+
- eval_batch_size: 64
|
| 58 |
+
- seed: 33
|
| 59 |
+
- distributed_type: multi-GPU
|
| 60 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 61 |
+
- lr_scheduler_type: linear
|
| 62 |
+
- num_epochs: 15
|
| 63 |
+
|
| 64 |
+
### Training results
|
| 65 |
+
|
| 66 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 67 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 68 |
+
| 3.3504 | 1.0 | 180 | 2.5753 | 0.5726 |
|
| 69 |
+
| 2.2201 | 2.0 | 360 | 1.7801 | 0.7280 |
|
| 70 |
+
| 1.5878 | 3.0 | 540 | 1.3596 | 0.7747 |
|
| 71 |
+
| 1.218 | 4.0 | 720 | 1.1112 | 0.8032 |
|
| 72 |
+
| 0.9707 | 5.0 | 900 | 0.9673 | 0.8111 |
|
| 73 |
+
| 0.7935 | 6.0 | 1080 | 0.8617 | 0.8313 |
|
| 74 |
+
| 0.6704 | 7.0 | 1260 | 0.8082 | 0.8455 |
|
| 75 |
+
| 0.572 | 8.0 | 1440 | 0.7746 | 0.8446 |
|
| 76 |
+
| 0.5015 | 9.0 | 1620 | 0.7387 | 0.8500 |
|
| 77 |
+
| 0.4434 | 10.0 | 1800 | 0.7024 | 0.8534 |
|
| 78 |
+
| 0.3947 | 11.0 | 1980 | 0.7013 | 0.8549 |
|
| 79 |
+
| 0.362 | 12.0 | 2160 | 0.6884 | 0.8544 |
|
| 80 |
+
| 0.3365 | 13.0 | 2340 | 0.6821 | 0.8549 |
|
| 81 |
+
| 0.3172 | 14.0 | 2520 | 0.6704 | 0.8593 |
|
| 82 |
+
| 0.3067 | 15.0 | 2700 | 0.6679 | 0.8618 |
|
| 83 |
+
|
| 84 |
+
|
| 85 |
+
### Framework versions
|
| 86 |
+
|
| 87 |
+
- Transformers 4.34.0
|
| 88 |
+
- Pytorch 1.14.0a0+410ce96
|
| 89 |
+
- Datasets 2.14.5
|
| 90 |
+
- Tokenizers 0.14.1
|