train_openbookqa_101112_1760638024

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: 1.7548
• Num Input Tokens Seen: 7525936

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: 101112
• 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
0.7321	2.0	1984	0.6975	753416
0.6936	4.0	3968	0.6935	1506176
0.6545	6.0	5952	0.6467	2258056
0.5385	8.0	7936	0.5927	3010184
0.4355	10.0	9920	0.6243	3762248
0.661	12.0	11904	0.6530	4514808
0.6277	14.0	13888	0.9617	5267208
0.1964	16.0	15872	1.3436	6019304
0.1112	18.0	17856	1.6950	6773080
0.0004	20.0	19840	1.7548	7525936

Framework versions

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