End of training
Browse files- README.md +74 -0
- pytorch_model.bin +1 -1
README.md
ADDED
|
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: gokuls/HBERTv1_48_L12_H768_A12
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- accuracy
|
| 7 |
+
model-index:
|
| 8 |
+
- name: HBERTv1_48_L12_H768_A12_massive_data_augmented
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# HBERTv1_48_L12_H768_A12_massive_data_augmented
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [gokuls/HBERTv1_48_L12_H768_A12](https://huggingface.co/gokuls/HBERTv1_48_L12_H768_A12) on an unknown dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.6902
|
| 20 |
+
- Accuracy: 0.8377
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 5e-05
|
| 40 |
+
- train_batch_size: 64
|
| 41 |
+
- eval_batch_size: 64
|
| 42 |
+
- seed: 33
|
| 43 |
+
- distributed_type: multi-GPU
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: linear
|
| 46 |
+
- num_epochs: 15
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 51 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
| 52 |
+
| 1.0914 | 1.0 | 4000 | 0.6902 | 0.8377 |
|
| 53 |
+
| 0.6178 | 2.0 | 8000 | 0.6890 | 0.8283 |
|
| 54 |
+
| 0.463 | 3.0 | 12000 | 0.7721 | 0.8254 |
|
| 55 |
+
| 0.3683 | 4.0 | 16000 | 0.7829 | 0.8288 |
|
| 56 |
+
| 0.3005 | 5.0 | 20000 | 0.8556 | 0.8303 |
|
| 57 |
+
| 0.2502 | 6.0 | 24000 | 0.9171 | 0.8214 |
|
| 58 |
+
| 0.2106 | 7.0 | 28000 | 1.0074 | 0.8160 |
|
| 59 |
+
| 0.1779 | 8.0 | 32000 | 1.0923 | 0.8239 |
|
| 60 |
+
| 0.1506 | 9.0 | 36000 | 1.1525 | 0.8254 |
|
| 61 |
+
| 0.1259 | 10.0 | 40000 | 1.2103 | 0.8249 |
|
| 62 |
+
| 0.1059 | 11.0 | 44000 | 1.3093 | 0.8269 |
|
| 63 |
+
| 0.0894 | 12.0 | 48000 | 1.4000 | 0.8288 |
|
| 64 |
+
| 0.0745 | 13.0 | 52000 | 1.5050 | 0.8313 |
|
| 65 |
+
| 0.0624 | 14.0 | 56000 | 1.5424 | 0.8288 |
|
| 66 |
+
| 0.0521 | 15.0 | 60000 | 1.5973 | 0.8308 |
|
| 67 |
+
|
| 68 |
+
|
| 69 |
+
### Framework versions
|
| 70 |
+
|
| 71 |
+
- Transformers 4.34.1
|
| 72 |
+
- Pytorch 1.14.0a0+410ce96
|
| 73 |
+
- Datasets 2.14.6
|
| 74 |
+
- Tokenizers 0.14.1
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 481277597
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:05dd7defbfd556845be306e702193caa3a9e41a7e8b78738207ba97a4ffbc14f
|
| 3 |
size 481277597
|