---
base_model: EleutherAI/pythia-160m-deduped
library_name: peft
license: apache-2.0
tags:
- axolotl
- relora
- generated_from_trainer
model-index:
- name: pythia-160m-storytelling
  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: `0.4.1`
```yaml
base_model: EleutherAI/pythia-160m-deduped
load_in_8bit: 
datasets:
  - path: jtatman/storywriting_combined_instruct
    type: alpaca
dataset_prepared_path: ds-storytelling
chat_template: inst
val_set_size: 0.01
adapter: lora
lora_model_dir: 
sequence_len: 2048
lora_r: 16
lora_alpha: 32
lora_dropout: 0.05
lora_target_modules:
  - query_key_value
lora_target_linear: true
lora_fan_in_fan_out: true  # pythia/GPTNeoX lora specific
lora_modules_to_save:
  - embed_tokens
  - lm_head
lora_on_cpu: false
# ReLoRA configuration
# # Must use either 'lora' or 'qlora' adapter, and does not support fsdp or deepspeed
# relora_steps: # Number of steps per ReLoRA restart
# relora_warmup_steps: # Number of per-restart warmup steps
# relora_anneal_steps: # Number of anneal steps for each relora cycle
# relora_prune_ratio: # threshold for optimizer magnitude when pruning
# relora_cpu_offload:  # True to perform lora weight merges on cpu during restarts, for modest gpu memory savings
relora_steps: 200
relora_warmup_steps: 10
relora_cpu_offload: false
wandb_project: pythia
wandb_entity:
wandb_watch:
wandb_name: pythia-160m-storytelling
wandb_log_model:
output_dir: ./outputs/lora-alpaca-pythia-160m-storytelling
gradient_accumulation_steps: 16
micro_batch_size: 1
num_epochs: 1
learning_rate: 0.0006
lr_scheduler: cosine_with_restarts
#cosine_min_lr_ratio: 0.1
train_on_inputs: false
group_by_length: false
#bf16: auto
#fp16: true
#tf32: false
float16: true
flash_attn: 
xformers_attention: true
optimizer: paged_adamw_8bit
gpu_memory_limit: 8GiB
hub_model_id: jtatman/pythia-160m-storytelling 
early_stopping_patience: 2
#resume_from_checkpoint: outputs/lora-alpaca-pythia-125m/checkpoint-51040
auto_resume_from_checkpoints: true
local_rank:
weight_decay: 0.0
#evals_per_epoch: 4
eval_steps: 200
logging_steps: 1
save_steps: 200
save_total_limit: 5
warmup_steps: 100

```

</details><br>

# pythia-160m-storytelling

This model is a fine-tuned version of [EleutherAI/pythia-160m-deduped](https://huggingface.co/EleutherAI/pythia-160m-deduped) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 2.8975

## 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: 0.0006
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine_with_restarts
- lr_scheduler_warmup_steps: 100
- num_epochs: 1

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 5.5185        | 0.0012 | 1    | 4.8333          |
| 3.7004        | 0.2348 | 200  | 3.2693          |
| 3.52          | 0.4696 | 400  | 3.3535          |
| 3.7836        | 0.7043 | 600  | 2.9896          |
| 3.3058        | 0.9391 | 800  | 2.8975          |


### Framework versions

- PEFT 0.11.1
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1