---
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
library_name: peft
license: llama3.1
tags:
- generated_from_trainer
model-index:
- name: world_model_training/outputs/qlora_llama_8b_desc_with_tao_webarena_16k
  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/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
<details><summary>See axolotl config</summary>

axolotl version: `0.4.1`
```yaml
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
tokenizer_type: AutoTokenizer

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_swiglu: true
liger_fused_linear_cross_entropy: true

load_in_4bit: true
strict: false

datasets:
  - path: DLI-Lab/world_model_for_wa_desc_with_tao_formatted_w_cot
    type: alpaca
dataset_prepared_path: last_run_prepared
val_set_size: 0.0
output_dir: world_model_training/outputs/qlora_llama_8b_desc_with_tao_webarena_16k
save_safetensors: true

adapter: qlora

sequence_len: 16000
sample_packing: true
pad_to_sequence_len: true

lora_r: 16
lora_alpha: 16
lora_dropout: 0.05
lora_target_modules:
lora_target_linear: true

wandb_project: world_model
wandb_entity: tutoring-convei
wandb_watch: 
wandb_name: qlora_llama_8b_desc_with_tao_webarena_16k
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 2
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00001

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

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: true
logging_steps: 1
flash_attention: true

warmup_steps: 10
evals_per_epoch: 4
saves_per_epoch: 2
weight_decay: 0.0
fsdp:
  - full_shard
  - auto_wrap
fsdp_config:
  fsdp_limit_all_gathers: true
  fsdp_sync_module_states: true
  fsdp_offload_params: true
  fsdp_use_orig_params: false
  fsdp_cpu_ram_efficient_loading: true
  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
  fsdp_transformer_layer_cls_to_wrap: LlamaDecoderLayer
  fsdp_state_dict_type: FULL_STATE_DICT
  fsdp_sharding_strategy: FULL_SHARD
special_tokens:
  pad_token: <|finetune_right_pad_id|>
```

</details><br>

# world_model_training/outputs/qlora_llama_8b_desc_with_tao_webarena_16k

This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co./meta-llama/Meta-Llama-3.1-8B-Instruct) on the None dataset.

## 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: 1e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- total_train_batch_size: 8
- total_eval_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: 2

### Training results



### Framework versions

- PEFT 0.12.0
- Transformers 4.45.0.dev0
- Pytorch 2.4.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1