metadata

license: apache-2.0
base_model: bert-base-cased
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: Sentiment-classfication-distilBERT-model
    results: []

Sentiment-classfication-distilBERT-model

This model is a fine-tuned version of bert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.3217
Accuracy: 0.9301

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: 5e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
num_epochs: 4
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.11	0.14	100	1.0458	0.4603
0.9647	0.27	200	0.9241	0.5743
0.8498	0.41	300	0.7957	0.6365
0.7436	0.54	400	0.7044	0.7043
0.683	0.68	500	0.7109	0.7040
0.6407	0.81	600	0.5602	0.7872
0.5388	0.95	700	0.5073	0.8031
0.449	1.09	800	0.4736	0.8316
0.4136	1.22	900	0.5387	0.8147
0.3329	1.36	1000	0.4277	0.8615
0.3405	1.49	1100	0.3667	0.8730
0.2806	1.63	1200	0.3420	0.8832
0.2648	1.77	1300	0.3437	0.8975
0.2912	1.9	1400	0.3503	0.8914
0.2109	2.04	1500	0.3268	0.9182
0.1267	2.17	1600	0.3676	0.9182
0.0931	2.31	1700	0.3635	0.9250
0.1447	2.44	1800	0.3144	0.9233
0.0979	2.58	1900	0.3197	0.9301
0.1156	2.72	2000	0.3217	0.9301
0.0922	2.85	2100	0.3323	0.9294
0.1094	2.99	2200	0.2976	0.9304
0.0667	3.12	2300	0.3554	0.9318
0.0479	3.26	2400	0.3648	0.9318
0.0427	3.39	2500	0.3615	0.9331
0.0499	3.53	2600	0.3251	0.9389
0.0381	3.67	2700	0.3391	0.9362
0.0498	3.8	2800	0.3350	0.9365
0.0565	3.94	2900	0.3331	0.9375

Framework versions

Transformers 4.35.0
Pytorch 2.1.0+cu118
Datasets 2.14.6
Tokenizers 0.14.1