81c89eeb-6a0c-4dac-a659-5d5a9487286f

This model is a fine-tuned version of NousResearch/Llama-3.2-1B on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.7895

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: 0.000213
• 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	0.0002	1	1.3080
1.0015	0.0121	50	1.0154
0.9323	0.0242	100	1.0086
0.8871	0.0363	150	0.9642
0.9651	0.0484	200	0.9314
0.8652	0.0605	250	0.8826
0.8418	0.0726	300	0.8545
0.8331	0.0847	350	0.8212
0.7855	0.0968	400	0.8026
0.669	0.1089	450	0.7915
0.7701	0.1210	500	0.7895

Framework versions

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