deepseek-coder-6.7b-instruct_finetuned_manim_pile_context_FIM_1024

This model is a fine-tuned version of deepseek-ai/deepseek-coder-6.7b-instruct on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.6405

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	462	1.6572
1.6976	2.0	925	1.6421
1.63	3.0	1387	1.6406
1.6295	4.0	1850	1.6405
1.6256	4.99	2310	1.6405

Framework versions

• Transformers 4.38.2
• Pytorch 2.1.0+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2