b698d03a-d284-4547-8e5a-c495d98f0c21

This model is a fine-tuned version of databricks/dolly-v2-3b on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.6243

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: 0.000208
• 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	0.0001	1	1.1150
0.7157	0.0073	50	0.9892
0.6547	0.0147	100	0.8532
0.2665	0.0220	150	0.7850
0.4048	0.0294	200	0.7096
0.4216	0.0367	250	0.6720
0.4735	0.0441	300	0.6513
0.5275	0.0514	350	0.6376
0.7545	0.0588	400	0.6299
0.3793	0.0661	450	0.6250
0.3498	0.0735	500	0.6243

Framework versions

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