train_openbookqa_123_1760637682

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

• Loss: 3.2291
• Num Input Tokens Seen: 7562680

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: 123
• 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
0.6481	2.0	1984	0.7158	756712
0.6436	4.0	3968	0.6126	1511320
0.5719	6.0	5952	0.5990	2268224
0.4238	8.0	7936	0.6520	3026592
0.0895	10.0	9920	1.0263	3783608
0.1966	12.0	11904	1.4614	4539008
0.0977	14.0	13888	2.3419	5296232
0.0041	16.0	15872	3.0044	6050584
0.0047	18.0	17856	3.1775	6805960
0.0	20.0	19840	3.2291	7562680

Framework versions

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