metadata
license: apache-2.0
library_name: peft
tags:
- axolotl
- generated_from_trainer
base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
model-index:
- name: pytiny-hf
results: []
See axolotl config
axolotl version: 0.3.0
base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
model_type: LlamaForCausalLM
tokenizer_type: LlamaTokenizer
is_llama_derived_model: true
hub_model_id: pytiny-hf
load_in_8bit: false
load_in_4bit: true
strict: false
datasets:
- path: mhenrichsen/alpaca_2k_test
type: alpaca
dataset_prepared_path:
val_set_size: 0.05
output_dir: ./qlora-out
adapter: qlora
lora_model_dir:
sequence_len: 2048
sample_packing: true
pad_to_sequence_len: true
lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_modules:
lora_target_linear: true
lora_fan_in_fan_out:
wandb_project: axolotl-pytiny-hf
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 3
optimizer: paged_adamw_32bit
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:
flash_attention: false
warmup_steps: 10
evals_per_epoch: 2
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
pytiny-hf
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: 3.7089
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: 3
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
6.8735 | 0.04 | 1 | 6.7693 |
5.594 | 0.5 | 13 | 5.4061 |
4.7525 | 1.0 | 26 | 4.6806 |
4.404 | 1.46 | 39 | 4.3381 |
4.0121 | 1.96 | 52 | 3.9443 |
3.7604 | 2.42 | 65 | 3.7493 |
3.6504 | 2.92 | 78 | 3.7089 |
Framework versions
- PEFT 0.7.2.dev0
- Transformers 4.37.0
- Pytorch 2.0.1+cu117
- Datasets 2.16.1
- Tokenizers 0.15.0