You can deploy this model and start earning money today!

ngdangkhanh/
deepseek-finetuned

Name: deepseek-finetuned
Availability: InStock

peft

tensorboard

safetensors

generated_from_trainer

deepseek-ai/deepseek-coder-1.3b-base

adapter

other

Views

No views yet

deepseek-finetuned

This model is a fine-tuned version of deepseek-ai/deepseek-coder-1.3b-base on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.0036

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: 2e-05
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 8
optimizer: Use 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: 9

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	471	0.0046
0.041	2.0	942	0.0042
0.0342	3.0	1413	0.0039
0.0319	4.0	1884	0.0038
0.0304	5.0	2355	0.0038
0.0292	6.0	2826	0.0037
0.0279	7.0	3297	0.0036
0.027	8.0	3768	0.0037
0.0265	8.9827	4230	0.0036

Framework versions

PEFT 0.14.0
Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

ngdangkhanh/deepseek-finetuned

deepseek-finetuned

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

ngdangkhanh/
deepseek-finetuned