ayousanz/japanese-mistral-150m-recipe

checkpoints-mistral-150M-FA2

This model is a fine-tuned version of None on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 8.3607

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

graelo/wikipedia 20230901 jp only

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0006
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• distributed_type: multi-GPU
• gradient_accumulation_steps: 256
• total_train_batch_size: 4096
• optimizer: Adam with betas=(0.9,0.95) and epsilon=0.0001
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 1000
• training_steps: 100
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
8.361	2.87	100	8.3607

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.14.5
• Tokenizers 0.14.1