9cb1dbea-a414-43d2-a9f2-09640c7a5a46

This model is a fine-tuned version of Qwen/Qwen1.5-0.5B on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1078

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: 0.000202
• train_batch_size: 4
• eval_batch_size: 4
• seed: 20
• 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	0.0002	1	0.9728
0.1344	0.0115	50	0.1209
0.1264	0.0229	100	0.1194
0.1248	0.0344	150	0.1140
0.1195	0.0459	200	0.1195
0.1022	0.0573	250	0.1120
0.1081	0.0688	300	0.1146
0.1008	0.0803	350	0.1090
0.1011	0.0917	400	0.1081
0.0998	0.1032	450	0.1086
0.0967	0.1147	500	0.1078

Framework versions

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