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

load_in_8bit: false
load_in_4bit: true
strict: false

datasets:
  - path: mhenrichsen/alpaca_2k_test
    type: alpaca
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: Jambalpaca-v0.1
wandb_log_model:

adapter: qlora
lora_r: 32
lora_alpha: 64
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:

out

This model is a fine-tuned version of ai21labs/Jamba-v0.1 on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.9899

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: 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
0.9332	0.17	1	1.0365
0.9677	0.35	2	1.0337
0.9337	0.7	4	0.9899

Framework versions

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

mlabonne/Jambalpaca-v0.1

out

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

mlabonne/
Jambalpaca-v0.1