Hugging Face's logo

kamrr
/
tinyllama-1.1B_alpaca_2k_lora

PEFT
Safetensors
llama
axolotl
Generated from Trainer
8-bit precision
bitsandbytes
Model card Files Community
tinyllama-1.1B_alpaca_2k_lora / README.md
Kareem Amr
Training in progress, step 12
49be7fc verified
preview code
|
raw
history blame
3.93 kB
metadata
license: apache-2.0
library_name: peft
tags:
  - generated_from_trainer
base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
model-index:
  - name: outputs/lora-out
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.0

# # Upload the final model to Huggingface
# hub_model_id: kareemamrr/tinyllama-1.1B_alpaca_2k_lora

# # Store the training logs in weights and biases
# wandb_entity: kamr54
# wandb_project: tinyllama-1.1B_alpaca_2k_lora
# wandb_name: lora-run

base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
model_type: LlamaForCausalLM
tokenizer_type: LlamaTokenizer

load_in_8bit: true
load_in_4bit: false
strict: false

datasets:
  - path: mhenrichsen/alpaca_2k_test
    type: alpaca
dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/lora-out

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

adapter: lora
lora_model_dir:
lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 4
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:

outputs/lora-out

This model is a fine-tuned version of TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.2118

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: 4

Training results

Training Loss Epoch Step Validation Loss
1.4615 0.08 1 1.4899
1.385 0.24 3 1.4883
1.3675 0.48 6 1.4370
1.2691 0.72 9 1.3388
1.2268 0.96 12 1.2973
1.2526 1.16 15 1.2808
1.2261 1.4 18 1.2527
1.135 1.6400 21 1.2343
1.2694 1.88 24 1.2301
1.149 2.08 27 1.2242
1.1515 2.32 30 1.2208
1.195 2.56 33 1.2196
1.1129 2.8 36 1.2151
1.1518 3.04 39 1.2133
1.1887 3.24 42 1.2115
1.1002 3.48 45 1.2104
1.189 3.7200 48 1.2118

Framework versions

  • PEFT 0.10.0
  • Transformers 4.40.2
  • Pytorch 2.1.2+cu118
  • Datasets 2.19.1
  • Tokenizers 0.19.1