Hugging Face's logo

Lambent
/
CosmoAlpacaLight-1b

PEFT
PyTorch
llama
Generated from Trainer
8-bit precision
bitsandbytes
Model card Files Community
CosmoAlpacaLight-1b / README.md
Lambent's picture
Lambent
Update README.md
e871327 verified
preview code
|
raw
history blame contribute delete
2.81 kB
metadata
license: cc
library_name: peft
tags:
  - generated_from_trainer
base_model: HuggingFaceTB/cosmo-1b
model-index:
  - name: lora-out
    results: []
datasets:
  - vicgalle/alpaca-gpt4

Built with Axolotl

See axolotl config

axolotl version: 0.4.0

base_model: HuggingFaceTB/cosmo-1b
model_type: LlamaForCausalLM
tokenizer_type: LlamaTokenizer

load_in_8bit: true
load_in_4bit: false
strict: false

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

sequence_len: 2048
sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 64
lora_alpha: 16
lora_dropout: 0.1
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: CosmoAlpacaLight-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: 0.0002

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:

lora-out

This model is a fine-tuned version of HuggingFaceTB/cosmo-1b on the alpaca-gpt4 dataset. It achieves the following results on the evaluation set:

  • Loss: 1.0717

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: 0.0002
  • 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
1.0447 1.0 662 1.0717

Framework versions

  • PEFT 0.8.2
  • Transformers 4.39.0.dev0
  • Pytorch 2.1.2+cu118
  • Datasets 2.17.1
  • Tokenizers 0.15.0