cls-comment-phobert-base-v2-v2.0

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: 0.4011
• Accuracy: 0.8991
• F1 Score: 0.8423
• Recall: 0.8383
• Precision: 0.8520

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: 1e-05
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 128
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• training_steps: 1500

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1 Score	Recall	Precision
1.4259	2.11	100	1.1000	0.6748	0.3033	0.3441	0.2724
0.8607	4.21	200	0.6240	0.8074	0.4765	0.4924	0.4627
0.5307	6.32	300	0.4730	0.8536	0.6024	0.5973	0.6534
0.3704	8.42	400	0.4261	0.8615	0.6547	0.6542	0.6680
0.2839	10.53	500	0.3887	0.8760	0.7141	0.6891	0.8438
0.2141	12.63	600	0.3706	0.8879	0.8283	0.8043	0.8608
0.166	14.74	700	0.3703	0.8958	0.8516	0.8356	0.8755
0.1358	16.84	800	0.3852	0.8918	0.8494	0.8419	0.8595
0.1131	18.95	900	0.3849	0.8918	0.8406	0.8243	0.8643
0.093	21.05	1000	0.3629	0.9070	0.8633	0.8436	0.8875
0.0807	23.16	1100	0.3881	0.8984	0.8442	0.8344	0.8622
0.0728	25.26	1200	0.3943	0.8945	0.8398	0.8343	0.8518
0.0643	27.37	1300	0.4023	0.8991	0.8533	0.8386	0.8767
0.0581	29.47	1400	0.4024	0.9011	0.8557	0.8447	0.8733
0.0546	31.58	1500	0.4011	0.8991	0.8423	0.8383	0.8520

Framework versions

• Transformers 4.38.2
• Pytorch 2.1.0+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2