f355998d-ef8a-4f68-8682-75a3cc55a87b

This model is a fine-tuned version of Artples/L-MChat-7b on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.4884

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: 180
• 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	0.0002	1	1.0816
1.4226	0.0094	50	0.8103
1.4682	0.0188	100	0.8389
1.4409	0.0282	150	0.7858
1.3102	0.0376	200	0.7526
1.8441	0.0470	250	0.6848
1.2096	0.0564	300	0.6182
1.1151	0.0658	350	0.5677
1.1581	0.0752	400	0.5256
1.0032	0.0846	450	0.4944
1.0026	0.0940	500	0.4884

Framework versions

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