---
license: bigcode-openrail-m
library_name: peft
tags:
- generated_from_trainer
base_model: bigcode/starcoder
model-index:
- name: lora-out
  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: bigcode/starcoder # this can be swapped for mdel model when the model is released
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
is_llama_derived_model: false

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: /workspace/axolotl-mdel/mtg.txt # change this to where your dataset is
    type: completion # change this to 'alpaca' if you are using alpaca

lora_modules_to_save:
  - embed_tokens
  - lm_head

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./lora-out

sequence_len: 4096 # this can be tweaked for efficiency
sample_packing: true
pad_to_sequence_len: true

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

wandb_project: mtg-starcoder-experiement-cleaner # give this a name
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 2 # this can be tweaked for efficiency
micro_batch_size: 1 # this can be tweaked for efficiency
num_epochs: 1 # this can be experimented with
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0002

train_on_inputs: true
group_by_length: false
bf16: true
fp16: false
tf32: false

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

warmup_steps: 10 # this can be tweaked for efficiency
evals_per_epoch: 10 # this can be tweaked for efficiency
eval_table_size:
eval_table_max_new_tokens: 128
saves_per_epoch: 1 
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  pad_token: "<|endoftext|>" # I need to talk with Huu/Taishi about this
  eos_token: "<|endoftext|>"

```

</details><br>

# lora-out

This model is a fine-tuned version of [bigcode/starcoder](https://huggingface.co/bigcode/starcoder) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7371

## 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: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 2
- 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 4.0386        | 0.0   | 1    | 3.7331          |
| 1.8941        | 0.1   | 25   | 1.6178          |
| 1.0615        | 0.21  | 50   | 0.9739          |
| 0.9228        | 0.31  | 75   | 0.8470          |
| 0.8614        | 0.41  | 100  | 0.8104          |
| 0.8562        | 0.52  | 125  | 0.7776          |
| 0.7939        | 0.62  | 150  | 0.7530          |
| 0.7714        | 0.73  | 175  | 0.7430          |
| 0.7999        | 0.83  | 200  | 0.7389          |
| 0.8647        | 0.93  | 225  | 0.7371          |


### Framework versions

- PEFT 0.7.1
- Transformers 4.37.0
- Pytorch 2.1.2+cu118
- Datasets 2.16.1
- Tokenizers 0.15.0