This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.1 on an unknown dataset.
It achieves the following results on the evaluation set:
eval_loss: 0.4493
eval_runtime: 67.3998
eval_samples_per_second: 0.519
eval_steps_per_second: 0.519
epoch: 1.0
step: 165
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: 0.0002
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 4
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
