clinno/eightwords-241113-mt2

sft

This model is a fine-tuned version of clinno/eightwords-241112-mt on the identity and the eightwords-20241113-alapaca datasets. It achieves the following results on the evaluation set:

• Loss: 3.0098

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: 1e-05
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 8
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 64.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.2795	12.5196	1000	2.0127
0.0784	25.0391	2000	2.3600
0.0037	37.5587	3000	2.7559
0.0016	50.0782	4000	2.9700
0.0013	62.5978	5000	3.0162

Framework versions

• Transformers 4.46.1
• Pytorch 2.5.1+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3