This is the Instruction Fine Tuned version of Tiny Llama on @Teknium1's openhermes dataset.
"The TinyLlama project aims to pretrain a 1.1B Llama model on 3 trillion tokens. With some proper optimization, we can achieve this within a span of "just" 90 days using 16 A100-40G GPUs 🚀🚀. The training has started on 2023-09-01."
See axolotl config
axolotl version: 0.3.0
base_model: ./TinyLlama-1.1B-intermediate-step-1431k-3T
model_type: LlamaForCausalLM
tokenizer_type: LlamaTokenizer
is_llama_derived_model: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: ./openhermes
type: alpaca
dataset_prepared_path:
val_set_size: 0.05
output_dir: ./out
sequence_len: 4096
sample_packing: false
adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear:
lora_fan_in_fan_out:
wandb_project: tinyllama-openhermes
wandb_entity: tensoic
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 2
micro_batch_size: 8
num_epochs: 1
optimizer: adamw_bnb_8bit
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: false
fp16: true
tf32: false
gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention: true
flash_attention:
warmup_steps: 100
evals_per_epoch: 4
eval_table_size:
saves_per_epoch: 1
debug:
deepspeed: zero2.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
bos_token: "<s>"
eos_token: "</s>"
unk_token: "<unk>"
The model achieves the following loss:
- Loss: 1.3647
The loss exploded after a couple hundred steps. As suggested by winglian, we set the following values in the config file:
adam_epsilon: 0.00001
max_grad_norm: 1.0
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 2
- total_train_batch_size: 128
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-05
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- num_epochs: 1
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
3.0006 | 0.0 | 1 | 1.6838 |
0.8195 | 0.25 | 451 | 1.4620 |
0.6836 | 0.5 | 902 | 1.4158 |
0.6811 | 0.75 | 1353 | 1.3647 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.0.1+cu117
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 10
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.