Mixtral_8x7B_instruct_A100_5k_Finetuned

This model is a fine-tuned version of mistralai/Mixtral-8x7B-Instruct-v0.1 on the generator dataset. It achieves the following results on the evaluation set:

• Loss: 0.4457

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: 2.5e-05
• train_batch_size: 4
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 0.03
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss
0.5452	1.0	201	0.4897
0.4473	2.0	402	0.4591
0.4865	3.0	603	0.4506
0.3804	4.0	804	0.4467
0.4376	5.0	1005	0.4457

Framework versions

• PEFT 0.9.0
• Transformers 4.38.1
• Pytorch 2.2.1+cu121
• Datasets 2.17.1
• Tokenizers 0.15.2