9a5227b2-dcef-4b7c-ac36-d9dd382dd889

This model is a fine-tuned version of TinyLlama/TinyLlama_v1.1 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.6620

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:

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0001	1	7.4703
2.7397	0.0098	150	3.1231
2.6817	0.0196	300	2.8731
2.6155	0.0294	450	2.7856
2.64	0.0392	600	2.7420
2.5454	0.0490	750	2.7196
2.6233	0.0588	900	2.7128
2.4938	0.0686	1050	2.6984
2.5522	0.0784	1200	2.6876
2.5508	0.0882	1350	2.6807
2.5735	0.0980	1500	2.6732
2.5116	0.1078	1650	2.6669
2.5012	0.1176	1800	2.6641
2.5599	0.1274	1950	2.6620

Framework versions

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