See axolotl config

axolotl version: 0.4.1

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
  - path: yahma/alpaca-cleaned
    type: alpaca
dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/alpaca-cleaned-tiny-llama
hub_model_id: ahmedsamirio/alpaca-cleaned-tiny-llama

sequence_len: 4096
sample_packing: true
eval_sample_packing: true
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:

wandb_project: alpaca-tiny-llama
wandb_entity: ahmedsamirio
wandb_watch:
wandb_name:
wandb_log_model:

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:

alpaca-cleaned-tiny-llama

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: 1.1115

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
1.3435	0.0029	1	1.4128
1.1926	0.2498	85	1.1723
1.1275	0.4996	170	1.1518
1.1153	0.7494	255	1.1410
1.1289	0.9993	340	1.1312
1.1267	1.2278	425	1.1276
1.1053	1.4776	510	1.1220
1.1261	1.7274	595	1.1172
1.0991	1.9772	680	1.1144
1.0295	2.2057	765	1.1157
1.086	2.4555	850	1.1131
1.029	2.7054	935	1.1114
1.019	2.9552	1020	1.1108
1.0158	3.1830	1105	1.1113
1.0297	3.4328	1190	1.1123
1.0571	3.6826	1275	1.1116
1.0306	3.9324	1360	1.1115

Framework versions

• PEFT 0.11.1
• Transformers 4.41.1
• Pytorch 2.1.2+cu118
• Datasets 2.19.1
• Tokenizers 0.19.1