---
license: apache-2.0
base_model: mhenrichsen/danskgpt-tiny
tags:
- generated_from_trainer
model-index:
- name: tiny-chat
  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/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
<details><summary>See axolotl config</summary>

axolotl version: `0.3.0`
```yaml
base_model: mhenrichsen/danskgpt-tiny

model_type: LlamaForCausalLM
tokenizer_type: LlamaTokenizer
is_llama_derived_model: true

load_in_8bit: false
load_in_4bit: false
strict: false

#pretraining_dataset: mhenrichsen/terra

datasets:
  - path: mhenrichsen/rag-qa-sharegpt
    type: sharegpt
    conversation: chatml
  - path: mhenrichsen/creator
    type: sharegpt
    conversation: chatml
  - path: mhenrichsen/puffin-sharegpt-fix
    type: sharegpt
    conversation: chatml
  - path: mhenrichsen/orcaslim-sharegpt-fix
    type: sharegpt
    conversation: chatml
  - path: mhenrichsen/dansk-tekst-sharegpt
    type: sharegpt
    conversation: chatml

chat_template: chatml

dataset_prepared_path:
val_set_size: 0.001
output_dir: ./tiny-chat

sequence_len: 2048
sample_packing: true
pad_to_sequence_len: true

wandb_project: tiny-danskgpt-chat
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 16
num_epochs: 3
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.00005

train_on_inputs: false
group_by_length: false
bf16: true
fp16: false
tf32: false

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

warmup_steps: 10
evals_per_epoch: 4
eval_table_size:
saves_per_epoch: 2
debug:
deepspeed: deepspeed/zero2.json
weight_decay: 0.1
fsdp:
fsdp_config:
special_tokens:
  eos_token: "<|im_end|>"
tokens:
  - "<|im_start|>"

```

</details><br>

# tiny-chat

This model is a fine-tuned version of [mhenrichsen/danskgpt-tiny](https://huggingface.co/mhenrichsen/danskgpt-tiny) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7168

## 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: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 4
- total_train_batch_size: 256
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- num_epochs: 3

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.3599        | 0.0   | 1    | 1.4118          |
| 0.7896        | 0.25  | 136  | 0.7813          |
| 0.7339        | 0.5   | 272  | 0.7490          |
| 0.7378        | 0.75  | 408  | 0.7285          |
| 0.7112        | 1.0   | 544  | 0.7146          |
| 0.6377        | 1.23  | 680  | 0.7135          |
| 0.6192        | 1.49  | 816  | 0.7133          |
| 0.5985        | 1.74  | 952  | 0.7073          |
| 0.6067        | 1.99  | 1088 | 0.7026          |
| 0.5139        | 2.22  | 1224 | 0.7167          |
| 0.5099        | 2.47  | 1360 | 0.7193          |
| 0.5217        | 2.72  | 1496 | 0.7168          |


### Framework versions

- Transformers 4.37.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.16.1
- Tokenizers 0.15.0