a37c1f28-b2d6-48e6-a0fa-cb63b8166b18

This model is a fine-tuned version of HuggingFaceH4/zephyr-7b-beta on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0300

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: 0.000206
• train_batch_size: 4
• eval_batch_size: 4
• seed: 60
• 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	0.0001	1	2.2663
0.3198	0.0069	50	0.1729
0.3058	0.0138	100	0.1171
0.7569	0.0207	150	0.1385
0.5144	0.0275	200	0.2068
0.2928	0.0344	250	0.0967
0.2777	0.0413	300	0.1127
0.1516	0.0482	350	0.0782
0.0612	0.0551	400	0.0566
0.0398	0.0620	450	0.0349
0.0575	0.0688	500	0.0300

Framework versions

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