9e61baa4-11fe-4a95-8391-b9fcc2fbac0b

This model is a fine-tuned version of llamafactory/tiny-random-Llama-3 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 11.7028

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: 0.000204
• 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	0.0000	1	11.7644
11.7398	0.0005	50	11.7357
11.7306	0.0011	100	11.7275
11.7217	0.0016	150	11.7195
11.7127	0.0022	200	11.7121
11.7055	0.0027	250	11.7077
11.7079	0.0033	300	11.7053
11.7036	0.0038	350	11.7039
11.7024	0.0043	400	11.7031
11.7	0.0049	450	11.7029
11.7042	0.0054	500	11.7028

Framework versions

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