---
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: Lambent/cosmoem-4x1b
model-index:
- name: 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: Lambent/cosmoem-4x1b
model_type: AutoModelForCausalLM
tokenizer_type: LlamaTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: HuggingFaceTB/cosmopedia-100k
    type: completion
  - path: Vezora/Tested-22k-Python-Alpaca
    type: alpaca
dataset_prepared_path: prepared-cosmoem
val_set_size: 0.05
output_dir: ./lora-out

sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.1
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: cosmoem-cosmo100
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 16
num_epochs: 1
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.001

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

loss_watchdog_threshold: 2.0
loss_watchdog_patience: 3

warmup_steps: 10
evals_per_epoch: 4
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.002
fsdp:
fsdp_config:
special_tokens:

```

</details><br>

# lora-out

This model is a fine-tuned version of [Lambent/cosmoem-4x1b](https://huggingface.co/Lambent/cosmoem-4x1b) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9382

## 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: 0.001
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 0.9599        | 0.0   | 1    | 0.9550          |
| 0.9077        | 0.25  | 672  | 0.9459          |
| 0.919         | 0.5   | 1344 | 0.9439          |
| 0.9228        | 0.75  | 2016 | 0.9391          |
| 0.9236        | 1.0   | 2688 | 0.9382          |


### Framework versions

- PEFT 0.9.0
- Transformers 4.40.0.dev0
- Pytorch 2.1.2+cu118
- Datasets 2.18.0
- Tokenizers 0.15.0