---
license: apache-2.0
library_name: peft
tags:
- axolotl
- generated_from_trainer
base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
model-index:
- name: tinyllama-1.1B_dolly-3k_lora
  results: []
---

[<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: `0.4.0`
```yaml
base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
model_type: LlamaForCausalLM
tokenizer_type: LlamaTokenizer

load_in_8bit: true
load_in_4bit: false
strict: false

datasets:
  - path: kareemamrr/databricks-dolly-3k
    type: alpaca
dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/lora-out

sequence_len: 4096
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

hub_model_id: kareemamrr/tinyllama-1.1B_dolly-3k_lora

wandb_project: tinyllama-1.1B_dolly-3k
wandb_entity: kamr54
wandb_name: lora

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 4
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0002

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
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
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:

```

</details><br>

# tinyllama-1.1B_dolly-3k_lora

This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T) on a subset of the [Databricks Dolly dataset](https://huggingface.co/datasets/kareemamrr/databricks-dolly-3k).
It achieves the following results on the evaluation set:
- Loss: 1.7510

## 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: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- num_epochs: 4

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 1.9375        | 0.0476 | 1    | 2.1187          |
| 1.9297        | 0.2857 | 6    | 2.0186          |
| 1.8257        | 0.5714 | 12   | 1.8111          |
| 1.7285        | 0.8571 | 18   | 1.7862          |
| 1.752         | 1.1071 | 24   | 1.7848          |
| 1.8686        | 1.3929 | 30   | 1.7808          |
| 1.6451        | 1.6786 | 36   | 1.7594          |
| 1.7861        | 1.9643 | 42   | 1.7582          |
| 1.6606        | 2.2024 | 48   | 1.7536          |
| 1.6168        | 2.4881 | 54   | 1.7543          |
| 1.7087        | 2.7738 | 60   | 1.7527          |
| 1.7276        | 3.0119 | 66   | 1.7525          |
| 1.8117        | 3.2976 | 72   | 1.7487          |
| 1.6897        | 3.5833 | 78   | 1.7502          |
| 1.7861        | 3.8690 | 84   | 1.7510          |


### Framework versions

- PEFT 0.10.0
- Transformers 4.40.2
- Pytorch 2.1.2+cu118
- Datasets 2.19.1
- Tokenizers 0.19.1