Aris-375M

This model is a fine-tuned version of joseph-ai/Aris-375M on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 3.7763

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: 5e-05
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• distributed_type: multi-GPU
• num_devices: 2
• gradient_accumulation_steps: 16
• total_train_batch_size: 64
• total_eval_batch_size: 4
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 200
• training_steps: 7630

Training results

Training Loss	Epoch	Step	Validation Loss
3.8660	0.0655	500	3.9581
3.7762	0.1311	1000	3.8790
3.7488	0.1966	1500	3.8372
3.7214	0.2621	2000	3.8135
3.6299	0.3277	2500	3.7986
3.7139	0.3932	3000	3.7894
3.7061	0.4587	3500	3.7832
3.7101	0.5242	4000	3.7798
3.7447	0.5898	4500	3.7778
3.7484	0.6553	5000	3.7768
3.7037	0.7208	5500	3.7765
3.7168	0.7864	6000	3.7763
3.7784	0.8519	6500	3.7762
3.6824	0.9174	7000	3.7762
3.6204	0.9830	7500	3.7762
3.7134	1.0	7630	3.7763

Framework versions

• Transformers 5.12.1
• Pytorch 2.4.1+cu124
• Datasets 5.0.0
• Tokenizers 0.22.2