bert-30M-uncased-classification-CMC-first-intent

This model is a fine-tuned version of vietgpt/bert-30M-uncased on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0086
  • Accuracy: 1.0

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 2e-05
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 50

Training results

Training Loss Epoch Step Validation Loss Accuracy
No log 1.0 28 0.9113 0.4694
No log 2.0 56 0.8776 0.4898
No log 3.0 84 0.8197 0.5714
No log 4.0 112 0.5064 0.9388
No log 5.0 140 0.2618 0.9388
No log 6.0 168 0.2210 0.9388
No log 7.0 196 0.1956 0.9592
No log 8.0 224 0.1718 0.9796
No log 9.0 252 0.1478 0.9592
No log 10.0 280 0.1190 0.9796
No log 11.0 308 0.0898 0.9796
No log 12.0 336 0.0926 0.9796
No log 13.0 364 0.0654 0.9796
No log 14.0 392 0.0635 0.9796
No log 15.0 420 0.0475 0.9796
No log 16.0 448 0.0469 0.9796
No log 17.0 476 0.0391 0.9796
0.4397 18.0 504 0.0325 1.0
0.4397 19.0 532 0.0272 1.0
0.4397 20.0 560 0.0267 1.0
0.4397 21.0 588 0.0216 1.0
0.4397 22.0 616 0.0200 1.0
0.4397 23.0 644 0.0185 1.0
0.4397 24.0 672 0.0185 1.0
0.4397 25.0 700 0.0141 1.0
0.4397 26.0 728 0.0151 1.0
0.4397 27.0 756 0.0140 1.0
0.4397 28.0 784 0.0132 1.0
0.4397 29.0 812 0.0127 1.0
0.4397 30.0 840 0.0118 1.0
0.4397 31.0 868 0.0113 1.0
0.4397 32.0 896 0.0113 1.0
0.4397 33.0 924 0.0107 1.0
0.4397 34.0 952 0.0103 1.0
0.4397 35.0 980 0.0103 1.0
0.0247 36.0 1008 0.0098 1.0
0.0247 37.0 1036 0.0097 1.0
0.0247 38.0 1064 0.0094 1.0
0.0247 39.0 1092 0.0096 1.0
0.0247 40.0 1120 0.0094 1.0
0.0247 41.0 1148 0.0095 1.0
0.0247 42.0 1176 0.0094 1.0
0.0247 43.0 1204 0.0092 1.0
0.0247 44.0 1232 0.0090 1.0
0.0247 45.0 1260 0.0090 1.0
0.0247 46.0 1288 0.0086 1.0
0.0247 47.0 1316 0.0086 1.0
0.0247 48.0 1344 0.0086 1.0
0.0247 49.0 1372 0.0086 1.0
0.0247 50.0 1400 0.0086 1.0

Framework versions

  • Transformers 4.37.1
  • Pytorch 2.1.0+cu121
  • Datasets 2.16.1
  • Tokenizers 0.15.1
Downloads last month
47
Safetensors
Model size
34.5M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for thangvip/bert-30M-uncased-classification-CMC-first-intent

Finetuned
(6)
this model