864d6721-df21-443d-94f2-54be93f26420

This model is a fine-tuned version of Qwen/Qwen1.5-14B-Chat on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.3564

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: 0.000211
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 50
• training_steps: 500

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0004	1	4.3035
1.4447	0.0184	50	1.6585
1.4389	0.0368	100	1.5589
1.3404	0.0552	150	1.5202
1.3406	0.0736	200	1.4983
1.2893	0.0920	250	1.4556
1.2337	0.1104	300	1.4263
1.2765	0.1287	350	1.3965
1.2918	0.1471	400	1.3673
1.2669	0.1655	450	1.3584
1.2717	0.1839	500	1.3564

Framework versions

• PEFT 0.13.2
• Transformers 4.46.0
• Pytorch 2.5.0+cu124
• Datasets 3.0.1
• Tokenizers 0.20.1