This model is a fine-tuned version of Qwen/Qwen2.5-3B on the assimilation_strict_json_v2 dataset.
It achieves the following results on the evaluation set:
Loss: 0.1501
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: 0.00015
train_batch_size: 16
eval_batch_size: 4
seed: 11
distributed_type: multi-GPU
num_devices: 8
total_train_batch_size: 128
total_eval_batch_size: 32
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
