This model is a fine-tuned version of deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B on the open_thoughts_19K dataset. It achieves the following results on the evaluation set:

Loss: 0.5804

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: 1e-05
train_batch_size: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 2
total_train_batch_size: 2
total_eval_batch_size: 2
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 1.0

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0870	2	0.6561
No log	0.1739	4	0.6379
No log	0.2609	6	0.6213
No log	0.3478	8	0.6110
No log	0.4348	10	0.5980
No log	0.5217	12	0.5886
No log	0.6087	14	0.5854
No log	0.6957	16	0.5828
No log	0.7826	18	0.5815
No log	0.8696	20	0.5806
No log	0.9565	22	0.5804

Framework versions

Transformers 4.50.0
Pytorch 2.6.0+cu124
Datasets 3.3.2
Tokenizers 0.21.0

realYinkaIyiola/Deepseek-R1-Distill-1.5B-Code-test

code_finetune

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

realYinkaIyiola/
Deepseek-R1-Distill-1.5B-Code-test