fee64bbd-67ea-4710-9d4f-a87a35a95a31

This model is a fine-tuned version of OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.9083

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: 0.000218
• 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	3.2918
6.1834	0.0030	50	3.0175
6.0544	0.0060	100	2.9833
5.9209	0.0090	150	2.9660
5.8253	0.0120	200	2.9501
5.8927	0.0150	250	2.9330
5.7712	0.0180	300	2.9226
5.8339	0.0210	350	2.9178
5.8031	0.0240	400	2.9119
5.8225	0.0270	450	2.9104
5.913	0.0300	500	2.9083

Framework versions

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