results_llama_1b

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

• Loss: 1.2093

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: 5e-05
• train_batch_size: 1
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 2
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 2
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.2917	0.1431	1000	1.2842
1.2761	0.2862	2000	1.2652
1.2755	0.4292	3000	1.2545
1.234	0.5723	4000	1.2463
1.1903	0.7154	5000	1.2400
1.1828	0.8585	6000	1.2353
1.1757	1.0016	7000	1.2305
1.2446	1.1447	8000	1.2279
1.1145	1.2877	9000	1.2250
1.2765	1.4308	10000	1.2222
1.2232	1.5739	11000	1.2196
1.1182	1.7170	12000	1.2176
1.1981	1.8601	13000	1.2156
1.2217	2.0031	14000	1.2141
1.2394	2.1462	15000	1.2134
1.1538	2.2893	16000	1.2124
1.1579	2.4324	17000	1.2116
1.1557	2.5755	18000	1.2107
1.1528	2.7186	19000	1.2098
1.1833	2.8616	20000	1.2093

Framework versions

• PEFT 0.14.0
• Transformers 4.47.1
• Pytorch 2.5.1+cu124
• Datasets 2.17.0
• Tokenizers 0.21.0