english-tamil-sawit-translator

This model is a fine-tuned version of unsloth/tinyllama-chat-bnb-4bit on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 6.4384

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: 0.0003
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 2
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
12.2792	0.5714	2	6.4552
14.402	1.0	4	6.4552
12.1438	1.5714	6	6.4552
14.1498	2.0	8	6.4552
13.7945	2.5714	10	6.4552
13.0275	3.0	12	6.4552
13.8713	3.5714	14	6.4552
12.5694	4.0	16	6.4558
8.3595	4.5714	18	6.4539
6.9887	5.0	20	6.4510
6.1087	5.5714	22	6.4480
6.3763	6.0	24	6.4455
4.7973	6.5714	26	6.4430
5.0016	7.0	28	6.4412
4.483	7.5714	30	6.4384

Framework versions

• PEFT 0.14.0
• Transformers 4.48.3
• Pytorch 2.6.0+cu124
• Datasets 3.3.1
• Tokenizers 0.21.0