---
library_name: peft
license: apache-2.0
base_model: unsloth/zephyr-sft
tags:
- axolotl
- generated_from_trainer
model-index:
- name: f9d386bf-0d6f-4e46-93f1-4f8ecb8e3dc4
  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: unsloth/zephyr-sft
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 23d42f343676655f_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/23d42f343676655f_train_data.json
  type:
    field_instruction: prompt
    field_output: chosen
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: null
eval_max_new_tokens: 128
eval_table_size: null
evals_per_epoch: 4
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
gradient_clipping: 1.0
group_by_length: false
hub_model_id: leixa/f9d386bf-0d6f-4e46-93f1-4f8ecb8e3dc4
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0001
load_in_4bit: false
load_in_8bit: false
local_rank: 0
logging_steps: 3
lora_alpha: 32
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 16
lora_target_linear: true
lr_scheduler: cosine
max_steps: 200
micro_batch_size: 8
mlflow_experiment_name: /tmp/23d42f343676655f_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
saves_per_epoch: 4
sequence_len: 1024
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: techspear-hub
wandb_mode: online
wandb_name: 6247deab-a9bf-440c-a8f4-ae717545d668
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 6247deab-a9bf-440c-a8f4-ae717545d668
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

```

</details><br>

# f9d386bf-0d6f-4e46-93f1-4f8ecb8e3dc4

This model is a fine-tuned version of [unsloth/zephyr-sft](https://huggingface.co/unsloth/zephyr-sft) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9702

## 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: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- 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: 200

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| No log        | 0.0104 | 1    | 1.5250          |
| 4.718         | 0.1771 | 17   | 1.1565          |
| 4.4312        | 0.3542 | 34   | 1.0752          |
| 4.2179        | 0.5312 | 51   | 1.0343          |
| 4.0932        | 0.7083 | 68   | 1.0110          |
| 3.9669        | 0.8854 | 85   | 0.9922          |
| 3.3631        | 1.0625 | 102  | 0.9912          |
| 3.436         | 1.2396 | 119  | 0.9816          |
| 3.3189        | 1.4167 | 136  | 0.9781          |
| 3.4449        | 1.5938 | 153  | 0.9719          |
| 3.4252        | 1.7708 | 170  | 0.9709          |
| 3.3787        | 1.9479 | 187  | 0.9702          |


### Framework versions

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