---
license: apache-2.0
library_name: peft
tags:
- axolotl
- generated_from_trainer
base_model: cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser
model-index:
- name: cheater-7b
  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: cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser
model_type: MistralForCausalLM
tokenizer_type: LlamaTokenizer

load_in_8bit: true
load_in_4bit: false
strict: false

datasets:
  - path: ./julia/data.jsonl
    type: sharegpt
    conversation: chatml
dataset_prepared_path: ./julia/prepared_data
chat_template: chatml
val_set_size: 0.05
output_dir: ./julia/lora-out
hub_model_id: animmina/cheater-7b
hub_strategy: every_save
hf_use_auth_token: true

sequence_len: 2048
sample_packing: true
pad_to_sequence_len: true
eval_sample_packing: false

adapter: lora
lora_model_dir:
lora_r: 8
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj

wandb_project: cheater-7b
wandb_entity:
wandb_watch:
wandb_name: v02
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 4
num_epochs: 4
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.00003

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
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  unk_token: "<unk>"

```

</details><br>

# cheater-7b

This model is a fine-tuned version of [cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser](https://huggingface.co/cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser) on 11 test cases from the [Julia LLM Leaderboard](https://github.com/svilupp/Julia-LLM-Leaderboard).
It achieves the following results on the evaluation set:
- Loss: 0.5741

## Model description

Simple LORA adapter (rank: 8).

## 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: 3e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 0.554         | 0.04  | 1    | 0.6521          |
| 0.4152        | 0.26  | 7    | 0.6499          |
| 0.3984        | 0.52  | 14   | 0.6283          |
| 0.4133        | 0.78  | 21   | 0.6140          |
| 0.3772        | 1.04  | 28   | 0.5951          |
| 0.3855        | 1.22  | 35   | 0.5869          |
| 0.4077        | 1.48  | 42   | 0.5840          |
| 0.3104        | 1.74  | 49   | 0.5793          |
| 0.3345        | 2.0   | 56   | 0.5776          |
| 0.3207        | 2.19  | 63   | 0.5761          |
| 0.3679        | 2.44  | 70   | 0.5784          |
| 0.3593        | 2.7   | 77   | 0.5781          |
| 0.2391        | 2.96  | 84   | 0.5761          |
| 0.3329        | 3.15  | 91   | 0.5743          |
| 0.2636        | 3.41  | 98   | 0.5744          |
| 0.3114        | 3.67  | 105  | 0.5741          |


### Framework versions

- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.1.2+cu121
- Datasets 2.18.0
- Tokenizers 0.15.0