---
license: cc
base_model: HuggingFaceTB/cosmo-1b
tags:
- generated_from_trainer
model-index:
- name: lisa-out
  results: []
---

Trying out some LISA training.
A few too many numbers changed to be quite directly comparable, but here's the nous-eval comparisons with the CosmoAlpacaLight using LORA:

|                                 Model                                 |AGIEval|GPT4All|TruthfulQA|Bigbench|Average|
|-----------------------------------------------------------------------|------:|------:|---------:|-------:|------:|
|[CosmoAlpacaLisa-1b](https://huggingface.co/Lambent/CosmoAlpacaLisa-1b)|  23.89|  51.93|     39.93|   28.68|  36.11|

|                                  Model                                  |AGIEval|GPT4All|TruthfulQA|Bigbench|Average|
|-------------------------------------------------------------------------|------:|------:|---------:|-------:|------:|
|[CosmoAlpacaLight-1b](https://huggingface.co/Lambent/CosmoAlpacaLight-1b)|  24.28|  51.31|     40.33|   29.47|  36.35|

|                          Model                          |AGIEval|GPT4All|TruthfulQA|Bigbench|Average|
|---------------------------------------------------------|------:|------:|---------:|-------:|------:|
|[cosmo-1b](https://huggingface.co/HuggingFaceTB/cosmo-1b)|  22.97|  52.01|     38.02|   28.73|  35.43|


[<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: HuggingFaceTB/cosmo-1b
model_type: LlamaForCausalLM
tokenizer_type: LlamaTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: vicgalle/alpaca-gpt4
    type: alpaca
dataset_prepared_path:
val_set_size: 0.05
output_dir: ./lisa-out

sequence_len: 2048
sample_packing: true
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear:
lora_fan_in_fan_out:

lisa_n_layers: 8
lisa_step_interval: 10
lisa_layers_attribute: model.layers

wandb_project: CosmoAlpacaLisa-1b-v0.1
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 1
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 5e-5

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>

# lisa-out

This model is a fine-tuned version of [HuggingFaceTB/cosmo-1b](https://huggingface.co/HuggingFaceTB/cosmo-1b) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.0634

## 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: 5e-05
- 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: 1

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.2281        | 0.0   | 1    | 1.2636          |
| 1.0796        | 0.25  | 166  | 1.0695          |
| 1.0272        | 0.5   | 332  | 1.0644          |
| 1.0471        | 0.75  | 498  | 1.0634          |


### Framework versions

- Transformers 4.40.0.dev0
- Pytorch 2.1.2+cu118
- Datasets 2.18.0
- Tokenizers 0.15.0