llama-3.2-1b-finetuned-corpus

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

  • Loss: 1.8084

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: 0.0001
  • train_batch_size: 4
  • eval_batch_size: 8
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 4
  • gradient_accumulation_steps: 16
  • total_train_batch_size: 256
  • total_eval_batch_size: 32
  • 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: 1.0

Training results

Training Loss Epoch Step Validation Loss
2.0687 0.0700 200 2.0610
1.9664 0.1400 400 1.9985
1.9066 0.2101 600 1.9431
1.8604 0.2801 800 1.9049
1.8181 0.3501 1000 1.8786
1.813 0.4201 1200 1.8582
1.8095 0.4902 1400 1.8415
1.7891 0.5602 1600 1.8284
1.7767 0.6302 1800 1.8188
1.7777 0.7002 2000 1.8130
1.7725 0.7703 2200 1.8099
1.768 0.8403 2400 1.8087
1.7633 0.9103 2600 1.8084
1.7646 0.9803 2800 1.8084

Framework versions

  • Transformers 4.50.0
  • Pytorch 2.5.1+cu124
  • Datasets 3.6.0
  • Tokenizers 0.21.1
Downloads last month
2
Safetensors
Model size
1B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for sghosts/llama-3.2-1b-finetuned-corpus

Finetuned
(122)
this model