README.md

metadata

license: apache-2.0
widget:
  - text: I'm fine. Who is this?
  - text: You can't take anything seriously.
  - text: In the end he's going to croak, isn't he?
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: bert-gest-pred-seqeval-partialmatch
    results: []
datasets:
  - Jsevisal/gesture_pred
pipeline_tag: token-classification

bert-gest-pred-seqeval-partialmatch

This model is a fine-tuned version of bert-base-cased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.7270
• Precision: 0.771293
• Recall: 0.720130
• F1: 0.727670
• Accuracy: 0.819896

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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
1.8976	1.0	147	1.1361	0.4802	0.4141	0.4034	0.7009
0.916	2.0	294	0.8206	0.6045	0.5622	0.5493	0.7744
0.5893	3.0	441	0.7711	0.7318	0.6613	0.6747	0.7952
0.4019	4.0	588	0.7270	0.7713	0.7201	0.7277	0.8199
0.2713	5.0	735	0.7353	0.8000	0.7512	0.7545	0.8349
0.1831	6.0	882	0.7802	0.7958	0.7245	0.7375	0.8303
0.1343	7.0	1029	0.7785	0.7652	0.7351	0.7204	0.8362
0.0989	8.0	1176	0.8017	0.7753	0.7317	0.7313	0.8322
0.079	9.0	1323	0.8281	0.7844	0.7297	0.7325	0.8349
0.0673	10.0	1470	0.8238	0.7765	0.7347	0.7289	0.8355

Framework versions

• Transformers 4.27.3
• Pytorch 1.13.1+cu116
• Datasets 2.10.1
• Tokenizers 0.13.2