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: distilbert-gest-pred-seqeval-partialmatch
    results: []
datasets:
  - Jsevisal/gesture_pred
language:
  - en
pipeline_tag: token-classification

distilbert-gest-pred-seqeval-partialmatch

This model is a fine-tuned version of elastic/distilbert-base-cased-finetuned-conll03-english on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.711886
Precision: 0.832250
Recall: 0.832250
F1: 0.832250
Accuracy: 0.817295

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
1.9119	1.0	147	1.1835	0.7412	0.7412	0.7412	0.7204
0.9884	2.0	294	0.8666	0.7906	0.7906	0.7906	0.7731
0.7238	3.0	441	0.7754	0.8056	0.8056	0.8056	0.7906
0.5564	4.0	588	0.7129	0.8114	0.8114	0.8114	0.7965
0.4343	5.0	735	0.7119	0.8322	0.8322	0.8322	0.8173
0.3261	6.0	882	0.7545	0.8179	0.8179	0.8179	0.8075
0.2688	7.0	1029	0.7760	0.8121	0.8121	0.8121	0.8010
0.2178	8.0	1176	0.7744	0.8283	0.8283	0.8283	0.8179
0.1822	9.0	1323	0.7894	0.8322	0.8322	0.8322	0.8231
0.1636	10.0	1470	0.7941	0.8316	0.8316	0.8316	0.8218

Framework versions

Transformers 4.26.1
Pytorch 1.13.1+cu116
Datasets 2.10.1
Tokenizers 0.13.2