Hugging Face's logo

mlabonne
/
Jambatypus-v0.1

Text Generation
Transformers
Safetensors
English
jamba
axolotl
conversational
custom_code
Inference Endpoints
4-bit precision
bitsandbytes
Model card Files Community
Jambatypus-v0.1 / README.md
mlabonne's picture
mlabonne
Update README.md
705e567 verified
preview code
|
raw
history blame
3.1 kB
metadata
license: apache-2.0
language:
  - en
dataset:
  - chargoddard/Open-Platypus-Chat
tags:
  - axolotl
base_model: ai21labs/Jamba-v0.1

image/webp

Jambatypus-v0.1

This model is a fine-tuned version of ai21labs/Jamba-v0.1 on the chargoddard/Open-Platypus-Chat dataset.

It has been trained on 2xA100 80 GB using my LazyAxolotl - Jamba notebook.

Built with Axolotl

See axolotl config

axolotl version: 0.4.0


base_model: ai21labs/Jamba-v0.1
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false

datasets:
  - path: chargoddard/Open-Platypus-Chat
    type: sharegpt
chat_template: chatml
dataset_prepared_path:
val_set_size: 0.01
output_dir: ./out

sequence_len: 4096
sample_packing: true
pad_to_sequence_len: true
eval_sample_packing: false

use_wandb: true
wandb_project: axolotl
wandb_entity:
wandb_watch:
wandb_name: Jambatypus-v0.1
wandb_log_model:

adapter: qlora
lora_r: 16
lora_alpha: 32
lora_dropout: 0.05
lora_target_linear: true

low_cpu_mem_usage: true
gradient_accumulation_steps: 8
micro_batch_size: 1
num_epochs: 1
optimizer: adamw_bnb_8bit
adam_beta2: 0.95
adam_epsilon: 0.00001
max_grad_norm: 1.0
lr_scheduler: cosine
learning_rate: 0.0002

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
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: 4
save_total_limit: 2
debug:
deepspeed:
weight_decay: 0.0
special_tokens:

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 0.0002
  • train_batch_size: 1
  • eval_batch_size: 1
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 2
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 16
  • total_eval_batch_size: 2
  • optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 10
  • num_epochs: 1

Training results

Training Loss Epoch Step Validation Loss
0.6274 0.01 1 1.0298
0.44 0.25 42 0.9770
0.4406 0.5 84 0.9653
0.4445 0.75 126 0.9645
0.4609 1.0 168 0.9641

Framework versions

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