---
library_name: peft
license: mit
base_model: fxmarty/tiny-dummy-qwen2
tags:
- axolotl
- generated_from_trainer
model-index:
- name: c8d47522-2e04-42a0-93ed-59f3e5699aa8
  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/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
<details><summary>See axolotl config</summary>

axolotl version: `0.4.1`
```yaml
adapter: lora
base_model: fxmarty/tiny-dummy-qwen2
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - bce164773e1650b3_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/bce164773e1650b3_train_data.json
  type:
    field_input: input
    field_instruction: instruction
    field_output: output
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
device_map:
  ? ''
  : 0,1,2,3,4,5,6,7
early_stopping_patience: 2
eval_max_new_tokens: 128
eval_steps: 100
eval_table_size: null
flash_attention: true
gradient_accumulation_steps: 8
gradient_checkpointing: true
group_by_length: false
hub_model_id: Alphatao/c8d47522-2e04-42a0-93ed-59f3e5699aa8
hub_repo: null
hub_strategy: null
hub_token: null
learning_rate: 0.0002
load_best_model_at_end: true
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 128
lora_dropout: 0.1
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 64
lora_target_linear: true
lora_target_modules:
- q_proj
- k_proj
- v_proj
- o_proj
lr_scheduler: cosine
max_grad_norm: 1.0
max_steps: 27590
micro_batch_size: 4
mlflow_experiment_name: /tmp/bce164773e1650b3_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 2
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 100
sequence_len: 1024
strict: false
tf32: true
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.044897409419476494
wandb_entity: null
wandb_mode: online
wandb_name: 68810631-1dc7-4768-b968-076e11ca27ee
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 68810631-1dc7-4768-b968-076e11ca27ee
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

```

</details><br>

# c8d47522-2e04-42a0-93ed-59f3e5699aa8

This model is a fine-tuned version of [fxmarty/tiny-dummy-qwen2](https://huggingface.co/fxmarty/tiny-dummy-qwen2) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 11.9078

## 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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- training_steps: 6648

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 11.9323       | 0.0003 | 1    | 11.9318         |
| 11.9185       | 0.0301 | 100  | 11.9185         |
| 11.9162       | 0.0602 | 200  | 11.9145         |
| 11.9141       | 0.0903 | 300  | 11.9125         |
| 11.912        | 0.1203 | 400  | 11.9115         |
| 11.9113       | 0.1504 | 500  | 11.9110         |
| 11.9139       | 0.1805 | 600  | 11.9106         |
| 11.9124       | 0.2106 | 700  | 11.9103         |
| 11.9113       | 0.2407 | 800  | 11.9100         |
| 11.9132       | 0.2708 | 900  | 11.9098         |
| 11.912        | 0.3008 | 1000 | 11.9096         |
| 11.9128       | 0.3309 | 1100 | 11.9094         |
| 11.9124       | 0.3610 | 1200 | 11.9091         |
| 11.9111       | 0.3911 | 1300 | 11.9091         |
| 11.9124       | 0.4212 | 1400 | 11.9090         |
| 11.9113       | 0.4513 | 1500 | 11.9090         |
| 11.91         | 0.4813 | 1600 | 11.9087         |
| 11.9134       | 0.5114 | 1700 | 11.9086         |
| 11.91         | 0.5415 | 1800 | 11.9087         |
| 11.9115       | 0.5716 | 1900 | 11.9085         |
| 11.9112       | 0.6017 | 2000 | 11.9084         |
| 11.9103       | 0.6318 | 2100 | 11.9084         |
| 11.9095       | 0.6619 | 2200 | 11.9084         |
| 11.9113       | 0.6919 | 2300 | 11.9082         |
| 11.9129       | 0.7220 | 2400 | 11.9082         |
| 11.9107       | 0.7521 | 2500 | 11.9081         |
| 11.9145       | 0.7822 | 2600 | 11.9081         |
| 11.9089       | 0.8123 | 2700 | 11.9081         |
| 11.9105       | 0.8424 | 2800 | 11.9080         |
| 11.9093       | 0.8724 | 2900 | 11.9079         |
| 11.9079       | 0.9025 | 3000 | 11.9078         |
| 11.9111       | 0.9326 | 3100 | 11.9077         |
| 11.9104       | 0.9627 | 3200 | 11.9078         |
| 11.9129       | 0.9928 | 3300 | 11.9078         |


### Framework versions

- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1