---
license: other
library_name: peft
tags:
- axolotl
- generated_from_trainer
base_model: deepseek-ai/deepseek-coder-6.7b-instruct
model-index:
- name: diff-deepseek-code-ir
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
<details><summary>See axolotl config</summary>

axolotl version: `0.4.0`
```yaml
base_model: deepseek-ai/deepseek-coder-6.7b-instruct
model_type: LlamaForCausalLM
tokenizer_type: LlamaTokenizerFast

load_in_8bit: true
load_in_4bit: false
strict: false

datasets:
  - path: vdaita/editpackft_inst_code
    split: train
    type: oasst
dataset_prepared_path:

test_datasets:
  - path: vdaita/editpackft_inst_code
    split: test
    type: oasst

output_dir: ./outputs/dscoder-code-ir-4

sequence_len: 4096
sample_packing: true
pad_to_sequence_len: true

eval_sample_packing: false

adapter: lora
lora_model_dir:
lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: huggingface
wandb_log_model: axolotl-dscoder-code-3

hub_model_id: vdaita/diff-deepseek-code-ir
hub_strategy: every_save

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 1
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0002

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 10
evals_per_epoch: 4
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:

special_tokens:
  bos_token: "<|begin_of_sentence|>"
  eos_token: "<|end_of_sentence|>"
  pad_token: "<|end_of_sentence|>"

```

</details><br>

# diff-deepseek-code-ir

This model is a fine-tuned version of [deepseek-ai/deepseek-coder-6.7b-instruct](https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-instruct) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2549

## 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: 2
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- total_eval_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- num_epochs: 1

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.5233        | 0.02  | 1    | 0.5554          |
| 0.3976        | 0.25  | 13   | 0.3534          |
| 0.3354        | 0.51  | 26   | 0.2805          |
| 0.2759        | 0.76  | 39   | 0.2549          |


### Framework versions

- PEFT 0.10.0
- Transformers 4.40.0.dev0
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.15.0