bf2ce252-289d-4690-8f94-09cdeaf7ee33

This model is a fine-tuned version of aisingapore/llama3-8b-cpt-sea-lionv2.1-instruct on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.9434

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: 0.000207
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 50
• training_steps: 500

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0015	1	2.5286
2.2296	0.0726	50	2.3830
2.1251	0.1451	100	2.3280
2.0485	0.2177	150	2.1815
2.0577	0.2903	200	2.1186
2.0216	0.3628	250	2.0796
1.9868	0.4354	300	2.0350
1.9566	0.5080	350	1.9907
1.8083	0.5806	400	1.9605
1.8876	0.6531	450	1.9460
1.8801	0.7257	500	1.9434

Framework versions

• PEFT 0.13.2
• Transformers 4.46.0
• Pytorch 2.5.0+cu124
• Datasets 3.0.1
• Tokenizers 0.20.1