metadata

base_model: vinai/phobert-base-v2
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - f1
model-index:
  - name: PhoBert_Dataset59KBoDuoi
    results: []

PhoBert_Dataset59KBoDuoi

This model is a fine-tuned version of vinai/phobert-base-v2 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.2985
Accuracy: 0.9307
F1: 0.9312

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: 128
eval_batch_size: 128
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 256
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	1.0230	200	0.1511	0.9390	0.9395
No log	2.0460	400	0.1571	0.9351	0.9356
No log	3.0691	600	0.1750	0.9340	0.9347
0.15	4.0921	800	0.1731	0.9334	0.9339
0.15	5.1151	1000	0.1912	0.9321	0.9326
0.15	6.1381	1200	0.2302	0.9273	0.9283
0.15	7.1611	1400	0.2180	0.9325	0.9330
0.0918	8.1841	1600	0.2620	0.9292	0.9300
0.0918	9.2072	1800	0.2363	0.9326	0.9329
0.0918	10.2302	2000	0.2687	0.9243	0.9252
0.0918	11.2532	2200	0.2621	0.9312	0.9317
0.0608	12.2762	2400	0.2741	0.9306	0.9312
0.0608	13.2992	2600	0.2614	0.9302	0.9306
0.0608	14.3223	2800	0.2830	0.9317	0.9321
0.0608	15.3453	3000	0.2874	0.9285	0.9291
0.0429	16.3683	3200	0.2844	0.9318	0.9323
0.0429	17.3913	3400	0.2836	0.9310	0.9313
0.0429	18.4143	3600	0.2885	0.9309	0.9312
0.0429	19.4373	3800	0.2985	0.9307	0.9312

Framework versions

Transformers 4.41.2
Pytorch 2.1.2
Datasets 2.19.2
Tokenizers 0.19.1