---
base_model: unsloth/Mistral-Nemo-Base-2407
library_name: peft
license: apache-2.0
tags:
- axolotl
- generated_from_trainer
model-index:
- name: adventure-nemo-ws
  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
# python -m axolotl.cli.preprocess adventure-nemo.yml
# accelerate launch -m axolotl.cli.train adventure-nemo.yml
# python -m axolotl.cli.merge_lora adventure-nemo.yml

base_model: unsloth/Mistral-Nemo-Base-2407
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: true
strict: false
sequence_len: 8192 # 99% vram
bf16: auto
fp16:
tf32: false
flash_attention: true
special_tokens:

# Data
dataset_prepared_path: last_run_prepared
datasets:
  - path: ColumbidAI/adventure-8k
    type: completion
warmup_steps: 10
shuffle_merged_datasets: true

save_safetensors: true
saves_per_epoch: 4
save_total_limit: 2

# WandB
wandb_project: Nemo-A
wandb_entity:

# Iterations
num_epochs: 1

# Output
output_dir: ./adventure-command-r-workspace
hub_model_id: ToastyPigeon/adventure-nemo-ws
hub_strategy: "all_checkpoints"

# Sampling
sample_packing: true
pad_to_sequence_len: true

# Batching
gradient_accumulation_steps: 1
micro_batch_size: 4
gradient_checkpointing: 'unsloth'
gradient_checkpointing_kwargs:
   use_reentrant: true

#unsloth_cross_entropy_loss: true
#unsloth_lora_mlp: true
#unsloth_lora_qkv: true
#unsloth_lora_o: true

# Evaluation
val_set_size: 0.005
evals_per_epoch: 5
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false
eval_batch_size: 1

# LoRA
adapter: qlora
lora_model_dir:
lora_r: 64
lora_alpha: 32
lora_dropout: 0.125
lora_target_linear: 
lora_fan_in_fan_out:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:

# Optimizer
optimizer: paged_adamw_8bit # adamw_8bit
lr_scheduler: cosine
learning_rate: 0.00025
lr_scheduler: cosine_with_min_lr
lr_scheduler_kwargs:
    min_lr: 0.000025
weight_decay: 0.01
max_grad_norm: 20.0

# Misc
train_on_inputs: false
group_by_length: false
early_stopping_patience:
local_rank:
logging_steps: 1
xformers_attention:
debug:
#deepspeed: /workspace/axolotl/deepspeed_configs/zero3.json # previously blank
fsdp:
fsdp_config:


plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_swiglu: true
liger_fused_linear_cross_entropy: true
```

</details><br>

# adventure-nemo-ws

This model is a fine-tuned version of [unsloth/Mistral-Nemo-Base-2407](https://huggingface.co/unsloth/Mistral-Nemo-Base-2407) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 2.1587

## 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: 0.00025
- train_batch_size: 4
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine_with_min_lr
- lr_scheduler_warmup_steps: 10
- num_epochs: 1

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 1.9422        | 0.0011 | 1    | 2.3948          |
| 1.8427        | 0.2011 | 189  | 2.2440          |
| 1.6786        | 0.4021 | 378  | 2.2143          |
| 1.9847        | 0.6032 | 567  | 2.1799          |
| 1.8358        | 0.8043 | 756  | 2.1587          |


### Framework versions

- PEFT 0.12.0
- Transformers 4.45.0.dev0
- Pytorch 2.3.1+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1