Lambent / cosmo-1b-lisa-pythontest

huggingface.co
Total runs: 15
24-hour runs: -1
7-day runs: -2
30-day runs: 7
Model's Last Updated: April 17 2024
text-generation

Introduction of cosmo-1b-lisa-pythontest

Model Details of cosmo-1b-lisa-pythontest

Catastrophic forgetting test results:

Initial evaluation loss on 1k subset of HuggingFaceTB/cosmopedia-100k dataset was 1.217. 100 steps of LISA training reduced this to 1.153.

Comparison to control: cosmo-1b started out with 1.003 loss on (a different subset of) dataset, increasing to 1.024 at 100 steps.

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: false
load_in_4bit: false
strict: false

datasets:
  - path: Vezora/Tested-22k-Python-Alpaca
    type: alpaca
dataset_prepared_path: prepared-qlora
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: 4
lisa_step_interval: 10
lisa_layers_attribute: model.layers

wandb_project: cosmo-python-lisa
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: 0.0005

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:

lisa-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: 0.2534
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
  • 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
0.6299 0.0 1 0.6469
0.4249 0.25 217 0.4382
0.3487 0.5 434 0.3111
0.3918 0.75 651 0.2534
Framework versions
  • Transformers 4.40.0.dev0
  • Pytorch 2.1.2+cu118
  • Datasets 2.18.0
  • Tokenizers 0.15.0

Runs of Lambent cosmo-1b-lisa-pythontest on huggingface.co

15
Total runs
-1
24-hour runs
-3
3-day runs
-2
7-day runs
7
30-day runs

More Information About cosmo-1b-lisa-pythontest huggingface.co Model

More cosmo-1b-lisa-pythontest license Visit here:

https://choosealicense.com/licenses/apache-2.0

cosmo-1b-lisa-pythontest huggingface.co

cosmo-1b-lisa-pythontest huggingface.co is an AI model on huggingface.co that provides cosmo-1b-lisa-pythontest's model effect (), which can be used instantly with this Lambent cosmo-1b-lisa-pythontest model. huggingface.co supports a free trial of the cosmo-1b-lisa-pythontest model, and also provides paid use of the cosmo-1b-lisa-pythontest. Support call cosmo-1b-lisa-pythontest model through api, including Node.js, Python, http.

cosmo-1b-lisa-pythontest huggingface.co Url

https://huggingface.co/Lambent/cosmo-1b-lisa-pythontest

Lambent cosmo-1b-lisa-pythontest online free

cosmo-1b-lisa-pythontest huggingface.co is an online trial and call api platform, which integrates cosmo-1b-lisa-pythontest's modeling effects, including api services, and provides a free online trial of cosmo-1b-lisa-pythontest, you can try cosmo-1b-lisa-pythontest online for free by clicking the link below.

Lambent cosmo-1b-lisa-pythontest online free url in huggingface.co:

https://huggingface.co/Lambent/cosmo-1b-lisa-pythontest

cosmo-1b-lisa-pythontest install

cosmo-1b-lisa-pythontest is an open source model from GitHub that offers a free installation service, and any user can find cosmo-1b-lisa-pythontest on GitHub to install. At the same time, huggingface.co provides the effect of cosmo-1b-lisa-pythontest install, users can directly use cosmo-1b-lisa-pythontest installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

cosmo-1b-lisa-pythontest install url in huggingface.co:

https://huggingface.co/Lambent/cosmo-1b-lisa-pythontest

Url of cosmo-1b-lisa-pythontest

cosmo-1b-lisa-pythontest huggingface.co Url

Provider of cosmo-1b-lisa-pythontest huggingface.co

Lambent
ORGANIZATIONS

Other API from Lambent

huggingface.co

Total runs: 109
Run Growth: 42
Growth Rate: 38.53%
Updated:March 16 2024
huggingface.co

Total runs: 40
Run Growth: 18
Growth Rate: 45.00%
Updated:March 17 2026
huggingface.co

Total runs: 26
Run Growth: 12
Growth Rate: 46.15%
Updated:March 26 2026
huggingface.co

Total runs: 12
Run Growth: -16
Growth Rate: -133.33%
Updated:March 09 2026