CoolFace
Modelpublic

Lambent/cosmo-1b-qdora-pythontest

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face
0likes
Model Card

<!-- 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"/> <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: true
strict: false

datasets:
  - path: Vezora/Tested-22k-Python-Alpaca
    type: alpaca
dataset_prepared_path: prepared-qlora
val_set_size: 0.05
output_dir: ./qlora-out

sequence_len: 2048
sample_packing: true
pad_to_sequence_len: true

adapter: qlora
lora_model_dir:
lora_r: 256
lora_alpha: 256
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_dora: true

wandb_project: cosmo-python-qlora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 1
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.0005

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>

qlora-out

This model is a fine-tuned version of HuggingFaceTB/cosmo-1b on the None dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.2055

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: 0.0005
  • —trainbatchsize: 2
  • —evalbatchsize: 2
  • —seed: 42
  • —gradientaccumulationsteps: 4
  • —totaltrainbatch_size: 8
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: cosine
  • —lrschedulerwarmup_steps: 10
  • —num_epochs: 1

Training results

Training LossEpochStepValidation Loss
0.64580.010.6657
0.39690.252170.4062
0.3270.54340.2912
0.3560.756510.2055

Framework versions

  • —PEFT 0.10.0
  • —Transformers 4.40.0.dev0
  • —Pytorch 2.1.2+cu118
  • —Datasets 2.18.0
  • —Tokenizers 0.15.0