lemexp-task1-min_symbols_template_small-deepseek-coder-1.3b-base-fsdp

This model is a fine-tuned version of deepseek-ai/deepseek-coder-1.3b-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.1984

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: 0.0002
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• total_train_batch_size: 16
• total_eval_batch_size: 16
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 2
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.4383	0.2001	629	0.3292
0.322	0.4001	1258	0.2787
0.2868	0.6002	1887	0.2509
0.2489	0.8003	2516	0.2356
0.2363	1.0003	3145	0.2278
0.2192	1.2004	3774	0.2188
0.2116	1.4004	4403	0.2094
0.1985	1.6005	5032	0.2042
0.1961	1.8006	5661	0.1984

Framework versions

• PEFT 0.14.0
• Transformers 4.47.0
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0