a176e17ab6c6863c4ff58dc7764affa0

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

  • Loss: 1.5289
  • Data Size: 1.0
  • Epoch Runtime: 29.1335
  • Accuracy: 0.9146
  • F1 Macro: 0.9316

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: 8
  • eval_batch_size: 8
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 4
  • total_train_batch_size: 32
  • 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: constant
  • num_epochs: 50

Training results

Training Loss Epoch Step Validation Loss Data Size Epoch Runtime Accuracy F1 Macro
No log 0 0 15.1356 0 1.6401 0.1792 0.1176
No log 1 170 14.2990 0.0078 1.6615 0.2917 0.1892
No log 2 340 3.5879 0.0156 2.6656 0.7479 0.5826
No log 3 510 2.2631 0.0312 5.2507 0.8521 0.7544
No log 4 680 1.1023 0.0625 6.1611 0.9354 0.9149
0.2064 5 850 2.0139 0.125 8.5063 0.8417 0.8115
0.2064 6 1020 1.5380 0.25 11.2561 0.9104 0.8875
1.1831 7 1190 1.5048 0.5 16.9064 0.9292 0.9263
0.7338 8.0 1360 1.5289 1.0 29.1335 0.9146 0.9316

Framework versions

  • Transformers 4.57.0
  • Pytorch 2.8.0+cu128
  • Datasets 4.3.0
  • Tokenizers 0.22.1
Downloads last month
1
Safetensors
Model size
1B params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for contemmcm/a176e17ab6c6863c4ff58dc7764affa0

Finetuned
(1594)
this model