---
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
model-index:
- name: outputs/lora-out
  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: `0.4.0`
```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-4.5k
    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: 4
lora_alpha: 16
lora_dropout: 0.8
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: tinyllama-dolly-axolotl
wandb_entity: kamr54

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 4
optimizer: adamw_bnb_8bit
lr_scheduler:
learning_rate: 0.0008

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>

# outputs/lora-out

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 the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.7742

## 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: 0.0008
- 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 |
|:-------------:|:------:|:----:|:---------------:|
| 1.8146        | 0.0317 | 1    | 2.1074          |
| 1.767         | 0.2540 | 8    | 1.8264          |
| 2.0003        | 0.5079 | 16   | 1.7782          |
| 1.7691        | 0.7619 | 24   | 1.7640          |
| 1.8407        | 1.0159 | 32   | 1.7693          |
| 1.7637        | 1.2460 | 40   | 1.7650          |
| 1.7748        | 1.5    | 48   | 1.7724          |
| 1.773         | 1.7540 | 56   | 1.7669          |
| 1.7533        | 2.0079 | 64   | 1.7599          |
| 1.5889        | 2.2381 | 72   | 1.7678          |
| 1.591         | 2.4921 | 80   | 1.7741          |
| 1.7303        | 2.7460 | 88   | 1.7669          |
| 1.5035        | 3.0    | 96   | 1.7666          |
| 1.4954        | 3.2222 | 104  | 1.7715          |
| 1.6623        | 3.4762 | 112  | 1.7708          |
| 1.7277        | 3.7302 | 120  | 1.7742          |


### Framework versions

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