dcft-orca-agentinstruct-1M-v1-cleaned_mistral

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the mlfoundations-dev/dcft-orca-agentinstruct-1M-v1-cleaned dataset. It achieves the following results on the evaluation set:

• Loss: 0.4468

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: 5e-06
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 32
• gradient_accumulation_steps: 2
• total_train_batch_size: 512
• total_eval_batch_size: 256
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant
• lr_scheduler_warmup_ratio: 0.1
• lr_scheduler_warmup_steps: 1738
• num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.417	0.9995	1035	0.4187
0.326	2.0	2071	0.4136
0.2213	2.9986	3105	0.4468

Framework versions

• Transformers 4.45.2
• Pytorch 2.3.0
• Datasets 2.21.0
• Tokenizers 0.20.3