---
base_model: mistralai/Mistral-7B-v0.1
library_name: peft
license: apache-2.0
tags:
- axolotl
- generated_from_trainer
model-index:
- name: mistral-test-alpaca
  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
base_model: mistralai/Mistral-7B-v0.1
model_type: MistralForCausalLM
tokenizer_type: LlamaTokenizer
is_mistral_derived_model: true

load_in_8bit: false
load_in_4bit: true
strict: false

lora_fan_in_fan_out: false
data_seed: 49
seed: 49

datasets:
  - path: sample_data/alpaca_synth_queries.jsonl
    type: sharegpt
    conversation: alpaca

dataset_prepared_path: last_run_prepared
val_set_size: 0.1
output_dir: ./ft-v1
hub_model_id: mahendra0203/mistral-test-alpaca

adapter: qlora
lora_model_dir:
sequence_len: 512  # Reduced from 896
sample_packing: true  # Enable sample packing
eval_sample_packing: false
pad_to_sequence_len: false  # Changed to false

lora_r: 16  # Reduced from 32
lora_alpha: 32
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj

wandb_project: ft-alpaca-mistral-hc
wandb_entity: mahendra0203

gradient_accumulation_steps: 8  # Increased from 4
micro_batch_size: 4  # Reduced from 16
eval_batch_size: 4  # Reduced from 16
num_epochs: 2
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0002
max_grad_norm: 1.0
adam_beta2: 0.95
adam_epsilon: 0.00001
save_total_limit: 3  # Reduced from 12

train_on_inputs: false
group_by_length: true  # Changed to true
bf16: true  # Changed to false
fp16: false  # Changed to true
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention: false
flash_attention: false  

loss_watchdog_threshold: 5.0
loss_watchdog_patience: 3

warmup_steps: 20
evals_per_epoch: 2  # Reduced from 4
eval_table_size:
eval_table_max_new_tokens: 128
saves_per_epoch: 2  # Reduced from 6
debug:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<s>"
  eos_token: "</s>"
  unk_token: "<unk>"
save_safetensors: true
```

</details><br>

[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/mahendra0203/ft-alpaca-mistral-hc/runs/yp7zk4y6)
# mistral-test-alpaca

This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.3238

## 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: 49
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 20
- num_epochs: 2

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 1.3818        | 0.6667 | 1    | 1.3490          |
| 1.3841        | 1.1667 | 2    | 1.3238          |


### Framework versions

- PEFT 0.11.1
- Transformers 4.42.3
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1