You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Log in or Sign Up to review the conditions and access this model content.

dense_isl_100m_mult

This model is a fine-tuned version of on the arrow dataset. It achieves the following results on the evaluation set:

  • Loss: 4.7708

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: 0.0001
  • train_batch_size: 8
  • eval_batch_size: 32
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 32
  • optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-06 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 25299
  • training_steps: 252992
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
6.8389 0.3953 10000 6.7793
5.4301 0.7905 20000 5.4051
4.9618 1.1858 30000 4.9770
4.7451 1.5811 40000 4.7354
4.5748 1.9763 50000 4.5824
4.3215 2.3716 60000 4.4992
4.3104 2.7669 70000 4.4252
3.9934 3.1622 80000 4.3939
4.0323 3.5574 90000 4.3534
4.0436 3.9527 100000 4.3117
3.7358 4.3480 110000 4.3456
3.7637 4.7433 120000 4.3139
3.4001 5.1385 130000 4.3703
3.485 5.5338 140000 4.3637
3.5164 5.9291 150000 4.3389
3.179 6.3244 160000 4.4476
3.2661 6.7196 170000 4.4353
2.8494 7.1149 180000 4.5269
2.9443 7.5102 190000 4.5534
2.9868 7.9054 200000 4.5482
2.6395 8.3007 210000 4.6645
2.6918 8.6960 220000 4.6763
2.3959 9.0913 230000 4.7391
2.4431 9.4865 240000 4.7673
2.4452 9.8818 250000 4.7704

Framework versions

  • Transformers 4.51.0
  • Pytorch 2.7.0+cu126
  • Datasets 3.6.0
  • Tokenizers 0.21.1
Downloads last month
-
Safetensors
Model size
0.2B params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support