train_copa_789_1760637872

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on the copa dataset. It achieves the following results on the evaluation set:

• Loss: 0.6325
• Num Input Tokens Seen: 501888

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: 4
• eval_batch_size: 4
• seed: 789
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Input Tokens Seen
0.2428	2.0	160	0.2389	50208
0.2334	4.0	320	0.2317	100384
0.2085	6.0	480	0.2517	150400
0.2214	8.0	640	0.2480	200640
0.2534	10.0	800	0.2512	250848
0.1347	12.0	960	0.3083	301088
0.0685	14.0	1120	0.4576	351424
0.0203	16.0	1280	0.5270	401504
0.0132	18.0	1440	0.6124	451648
0.0032	20.0	1600	0.6325	501888

Framework versions

• PEFT 0.17.1
• Transformers 4.51.3
• Pytorch 2.9.0+cu128
• Datasets 4.0.0
• Tokenizers 0.21.4