---
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: burkelibbey/colors
    type:
      field_instruction: color
      field_output: description
    conversation: chatml
chat_template: chatml

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:

wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

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>

# 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: 1.2375

## 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 |
|:-------------:|:------:|:----:|:---------------:|
| 2.7509        | 0.0204 | 1    | 2.6902          |
| 1.8064        | 0.2653 | 13   | 1.6735          |
| 1.5513        | 0.5306 | 26   | 1.4832          |
| 1.482         | 0.7959 | 39   | 1.4111          |
| 1.392         | 1.0408 | 52   | 1.3677          |
| 1.3414        | 1.3061 | 65   | 1.3319          |
| 1.3213        | 1.5714 | 78   | 1.3029          |
| 1.3028        | 1.8367 | 91   | 1.2795          |
| 1.2761        | 2.0816 | 104  | 1.2697          |
| 1.2509        | 2.3469 | 117  | 1.2587          |
| 1.2884        | 2.6122 | 130  | 1.2472          |
| 1.254         | 2.8776 | 143  | 1.2410          |
| 1.2523        | 3.1224 | 156  | 1.2403          |
| 1.2468        | 3.3878 | 169  | 1.2385          |
| 1.2476        | 3.6531 | 182  | 1.2370          |
| 1.2366        | 3.9184 | 195  | 1.2375          |


### Framework versions

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