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

# Store the training logs in weights and biases
wandb_entity: byvuong-org
wandb_project: tinyllama-1.1B_alpaca_2k_lora

# The rest of this config stays the same:
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:

tinyllama-1.1B_alpaca_2k_lora

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: 1.2133

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
1.4613	0.0784	1	1.4899
1.385	0.2353	3	1.4862
1.3665	0.4706	6	1.4402
1.2691	0.7059	9	1.3409
1.2269	0.9412	12	1.2944
1.2531	1.1569	15	1.2793
1.2266	1.3922	18	1.2552
1.136	1.6275	21	1.2342
1.2704	1.8627	24	1.2297
1.1491	2.0784	27	1.2232
1.1515	2.3137	30	1.2230
1.195	2.5490	33	1.2190
1.1126	2.7843	36	1.2178
1.1511	3.0196	39	1.2138
1.1888	3.2353	42	1.2105
1.1008	3.4706	45	1.2118
1.1896	3.7059	48	1.2133

Framework versions

PEFT 0.13.2
Transformers 4.45.2
Pytorch 2.3.1+cu121
Datasets 3.0.1
Tokenizers 0.20.1