fil_checkpoint

This model is a fine-tuned version of mikhail-panzo/malay_full_checkpoint on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.4735

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-06
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 2000
• training_steps: 3000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.7579	6.76	500	0.7164
0.6196	13.51	1000	0.5662
0.5622	20.27	1500	0.5077
0.5341	27.03	2000	0.4858
0.52	33.78	2500	0.4772
0.5233	40.54	3000	0.4735

Framework versions

• Transformers 4.40.0.dev0
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2