6f471b47-5f6a-44f8-8dfd-866a050f04fd

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: 0.0876

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: 0.000211
• 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	0.0017	1	2.4939
1.0851	0.0832	50	0.8332
0.8432	0.1664	100	0.5534
0.6258	0.2496	150	0.3854
0.5229	0.3328	200	0.3013
0.5443	0.4160	250	0.2291
0.2781	0.4992	300	0.1655
0.2913	0.5824	350	0.1253
0.2725	0.6656	400	0.1006
0.1846	0.7488	450	0.0898
0.2189	0.8319	500	0.0876

Framework versions

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