train_wsc_42_1760622256

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

• Loss: 0.4184
• Num Input Tokens Seen: 1308280

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: 42
• 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: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Input Tokens Seen
0.4705	3.0	333	0.3602	130808
0.36	6.0	666	0.3695	260688
0.3574	9.0	999	0.3521	390936
0.3623	12.0	1332	0.3540	521840
0.3333	15.0	1665	0.3653	653216
0.3303	18.0	1998	0.3671	784328
0.3656	21.0	2331	0.3820	916192
0.3146	24.0	2664	0.4047	1046952
0.3334	27.0	2997	0.4169	1177504
0.3318	30.0	3330	0.4184	1308280

Framework versions

• PEFT 0.15.2
• Transformers 4.51.3
• Pytorch 2.8.0+cu128
• Datasets 3.6.0
• Tokenizers 0.21.1