Llama-3.2-1B

This model is a fine-tuned version of meta-llama/Llama-3.2-1B on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2404

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: 0.0005
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 30
  • training_steps: 2000

Training results

Training Loss Epoch Step Validation Loss
0.4565 0.05 100 0.4042
0.355 0.1 200 0.3224
0.3004 0.15 300 0.3054
0.2844 0.2 400 0.2904
0.2331 0.25 500 0.2829
0.241 0.3 600 0.2737
0.3013 0.35 700 0.2682
0.2619 0.4 800 0.2626
0.2367 0.45 900 0.2588
0.2152 0.5 1000 0.2563
0.2464 0.55 1100 0.2521
0.2443 0.6 1200 0.2491
0.2639 0.65 1300 0.2467
0.2602 0.7 1400 0.2447
0.291 0.75 1500 0.2434
0.2524 0.8 1600 0.2419
0.272 0.85 1700 0.2410
0.2273 0.9 1800 0.2406
0.2584 0.95 1900 0.2405
0.237 1.0 2000 0.2404

Framework versions

  • PEFT 0.13.0
  • Transformers 4.44.2
  • Pytorch 2.4.1+cu121
  • Datasets 3.0.1
  • Tokenizers 0.19.1
Downloads last month
130
Inference API
Unable to determine this model’s pipeline type. Check the docs .

Model tree for doganmustafa/Llama-3.2-1B

Adapter
(83)
this model