7b377ecd-7e77-465c-afcc-cba370b9c5e5

This model is a fine-tuned version of jingyeom/seal3.1.6n_7b on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.8523

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: 0.000214
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 50
• training_steps: 500

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0006	1	1.9465
0.8747	0.0293	50	1.2186
0.8156	0.0586	100	1.1785
0.8325	0.0880	150	1.0621
0.7726	0.1173	200	1.0214
0.7815	0.1466	250	0.9988
0.8154	0.1759	300	0.9346
0.6438	0.2052	350	0.8879
0.7983	0.2345	400	0.8639
0.6763	0.2639	450	0.8545
0.7375	0.2932	500	0.8523

Framework versions

• PEFT 0.13.2
• Transformers 4.46.0
• Pytorch 2.5.0+cu124
• Datasets 3.0.1
• Tokenizers 0.20.1