fine_tuned_per_domain_balanced

This model is a fine-tuned version of Qwen/Qwen2-1.5B on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1209
  • Accuracy: 0.9540

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: 2e-05
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 42
  • 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
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.5664 0.0203 100 0.2706 0.8890
0.2871 0.0406 200 0.2891 0.8871
0.2495 0.0608 300 0.2310 0.9026
0.2414 0.0811 400 0.1710 0.9290
0.1983 0.1014 500 0.1614 0.9332
0.198 0.1217 600 0.1482 0.9394
0.2112 0.1419 700 0.1545 0.9443
0.1791 0.1622 800 0.1303 0.9501
0.1707 0.1825 900 0.1822 0.9340
0.1663 0.2028 1000 0.1297 0.9511
0.1657 0.2230 1100 0.1433 0.9492
0.1467 0.2433 1200 0.1107 0.9590
0.1519 0.2636 1300 0.1250 0.9548
0.1474 0.2839 1400 0.1045 0.9613
0.1509 0.3041 1500 0.1180 0.9593
0.147 0.3244 1600 0.1076 0.9588
0.1308 0.3447 1700 0.1209 0.9540

Framework versions

  • Transformers 4.49.0
  • Pytorch 2.6.0+cu126
  • Datasets 3.3.2
  • Tokenizers 0.21.0
Downloads last month
12
Safetensors
Model size
1.54B params
Tensor type
F32
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for EndOfLe/fine_tuned_per_domain_balanced

Base model

Qwen/Qwen2-1.5B
Finetuned
(47)
this model