qwen14b-multi-turn-R2

This model is a fine-tuned version of RezolveAI/brainpowa-general-conversational-M-v1 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1976

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: 0.0002
  • train_batch_size: 1
  • eval_batch_size: 1
  • seed: 42
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 8
  • optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT 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
0.6472 0.1647 200 0.6514
0.5717 0.3295 400 0.5779
0.5236 0.4942 600 0.5135
0.4373 0.6590 800 0.4592
0.4455 0.8237 1000 0.4062
0.4116 0.9885 1200 0.3598
0.2866 1.1532 1400 0.3276
0.2412 1.3180 1600 0.3039
0.2561 1.4827 1800 0.2785
0.2001 1.6474 2000 0.2585
0.1716 1.8122 2200 0.2400
0.1872 1.9769 2400 0.2259
0.1347 2.1417 2600 0.2231
0.153 2.3064 2800 0.2168
0.1281 2.4712 3000 0.2102
0.1226 2.6359 3200 0.2051
0.1298 2.8007 3400 0.1993
0.1161 2.9654 3600 0.1976

Framework versions

  • PEFT 0.17.1
  • Transformers 4.56.2
  • Pytorch 2.6.0+cu124
  • Datasets 4.1.1
  • Tokenizers 0.22.1
Downloads last month
-
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for c-mohanraj/qwen14b-multi-turn-R2

Adapter
(2)
this model

Evaluation results