echarif/qwen_lora_adapter

models

This model is a fine-tuned version of Qwen/Qwen2.5-1.5B-Instruct on the chatbot_enseignement_train dataset. It achieves the following results on the evaluation set:

• Loss: 0.0036

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: 2
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 8
• 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: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.0205	0.9524	100	0.0302
0.0114	1.9048	200	0.0088
0.0025	2.8571	300	0.0038
0.003	3.8095	400	0.0035
0.0042	4.7619	500	0.0036

Framework versions

• PEFT 0.15.2
• Transformers 4.51.3
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.21.1