c6408b72-cd12-4b07-b8eb-fe88f8a9f545

This model is a fine-tuned version of berkeley-nest/Starling-LM-7B-alpha on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.7585

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: 0.000203
• train_batch_size: 4
• eval_batch_size: 4
• seed: 30
• 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	0.9447
1.6243	0.0224	50	0.8770
1.8883	0.0449	100	0.8966
1.7804	0.0673	150	0.8885
1.8887	0.0897	200	0.8706
1.7703	0.1122	250	0.8369
1.8232	0.1346	300	0.8097
1.7332	0.1570	350	0.7869
1.675	0.1795	400	0.7682
1.6311	0.2019	450	0.7584
1.813	0.2243	500	0.7585

Framework versions

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