---
library_name: peft
base_model: jhflow/mistral7b-lora-multi-turn-v2
tags:
- axolotl
- generated_from_trainer
model-index:
- name: 5401ffa9-6e3d-478c-aac2-e3aff6d7efc7
  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: `0.10.0.dev0`
```yaml
adapter: lora
base_model: jhflow/mistral7b-lora-multi-turn-v2
bf16: true
chat_template: llama3
datasets:
- data_files:
  - 073ecb803828cfed_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/
  type:
    field_input: input
    field_instruction: instruct
    field_output: output
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
eval_max_new_tokens: 256
evals_per_epoch: 2
flash_attention: false
fp16: false
gradient_accumulation_steps: 1
gradient_checkpointing: true
group_by_length: true
hub_model_id: apriasmoro/5401ffa9-6e3d-478c-aac2-e3aff6d7efc7
learning_rate: 0.0002
logging_steps: 10
lora_alpha: 16
lora_dropout: 0.05
lora_fan_in_fan_out: false
lora_r: 8
lora_target_linear: true
lr_scheduler: cosine
max_steps: 269
micro_batch_size: 4
mlflow_experiment_name: /tmp/073ecb803828cfed_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
sample_packing: false
save_steps: 67
sequence_len: 2048
tf32: true
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: 589dc2a5-c919-4731-be25-e0afc45a1708
wandb_project: Gradients-On-Demand
wandb_run: apriasmoro
wandb_runid: 589dc2a5-c919-4731-be25-e0afc45a1708
warmup_steps: 100
weight_decay: 0.01

```

</details><br>

# 5401ffa9-6e3d-478c-aac2-e3aff6d7efc7

This model is a fine-tuned version of [jhflow/mistral7b-lora-multi-turn-v2](https://huggingface.co/jhflow/mistral7b-lora-multi-turn-v2) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5244

## 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
- distributed_type: multi-GPU
- num_devices: 8
- total_train_batch_size: 32
- total_eval_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: 100
- training_steps: 269

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| No log        | 0.0045 | 1    | 0.9024          |
| 0.6584        | 0.2036 | 45   | 0.6136          |
| 0.5876        | 0.4072 | 90   | 0.5672          |
| 0.5148        | 0.6109 | 135  | 0.5598          |
| 0.4828        | 0.8145 | 180  | 0.5327          |
| 0.5225        | 1.0181 | 225  | 0.5244          |


### Framework versions

- PEFT 0.15.2
- Transformers 4.51.3
- Pytorch 2.5.1+cu124
- Datasets 3.5.1
- Tokenizers 0.21.1