af16e712-59b8-4484-a2c6-9900e8c81c2c

This model is a fine-tuned version of NousResearch/Yarn-Llama-2-7b-64k on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.7993

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: 0.000214
• 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	0.0004	1	2.2280
2.5862	0.0184	50	1.3052
2.0547	0.0368	100	1.1151
1.9385	0.0552	150	1.0113
1.8092	0.0737	200	0.9592
1.5752	0.0921	250	0.9132
1.6061	0.1105	300	0.8682
1.4298	0.1289	350	0.8344
1.547	0.1473	400	0.8120
1.4848	0.1657	450	0.8011
1.5003	0.1841	500	0.7993

Framework versions

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