---
license: llama2
library_name: peft
tags:
- generated_from_trainer
base_model: codellama/CodeLlama-34b-hf
model-index:
- name: maverick34b
  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: codellama/CodeLlama-34b-hf
model_type: LlamaForCausalLM
tokenizer_type: CodeLlamaTokenizer
is_llama_derived_model: true

load_in_8bit: false
load_in_4bit: true
strict: false

datasets:
  - path: iamtarun/code_instructions_120k_alpaca
    type: alpaca
dataset_prepared_path:
val_set_size: 0.05
output_dir: ./maverick34b

adapter: qlora
lora_model_dir:

sequence_len: 4096
sample_packing: true
pad_to_sequence_len: true

lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_modules:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 4
optimizer: paged_adamw_32bit
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

warmup_steps: 10
evals_per_epoch: 4
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<s>"
  eos_token: "</s>"
  unk_token: "<unk>"

```

</details><br>

# maverick34b

This model is a fine-tuned version of [codellama/CodeLlama-34b-hf](https://huggingface.co/codellama/CodeLlama-34b-hf) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3391

## 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: 7
- gradient_accumulation_steps: 4
- total_train_batch_size: 56
- total_eval_batch_size: 14
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- num_epochs: 4

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.5065        | 0.01  | 1    | 0.5089          |
| 0.3477        | 0.25  | 29   | 0.3561          |
| 0.3593        | 0.51  | 58   | 0.3461          |
| 0.3329        | 0.76  | 87   | 0.3423          |
| 0.3607        | 1.0   | 116  | 0.3404          |
| 0.3336        | 1.26  | 145  | 0.3395          |
| 0.3449        | 1.51  | 174  | 0.3386          |
| 0.3187        | 1.77  | 203  | 0.3377          |
| 0.3216        | 2.0   | 232  | 0.3371          |
| 0.2961        | 2.26  | 261  | 0.3380          |
| 0.3117        | 2.51  | 290  | 0.3381          |
| 0.3207        | 2.77  | 319  | 0.3379          |
| 0.3047        | 3.01  | 348  | 0.3376          |
| 0.3096        | 3.26  | 377  | 0.3391          |
| 0.3148        | 3.52  | 406  | 0.3391          |
| 0.3116        | 3.77  | 435  | 0.3391          |


### Framework versions

- PEFT 0.8.2
- Transformers 4.38.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.17.0
- Tokenizers 0.15.0