See axolotl config

axolotl version: 0.3.0

base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
model_type: LlamaForCausalLM
tokenizer_type: LlamaTokenizer
is_llama_derived_model: true
hub_model_id: TinyLlamusk

load_in_8bit: false
load_in_4bit: true
strict: false

datasets:
  - path: lcama/elon-tweets
    type: completion
dataset_prepared_path:
val_set_size: 0.02
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-tinyllama
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 1
num_epochs: 4
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:

TinyLlamusk

This model is a fine-tuned version of TinyLlama/TinyLlama-1.1B-Chat-v1.0 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 4.7587

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: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 2
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 10
• num_epochs: 4
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
6.8915	0.07	1	6.5485
6.1595	0.53	8	5.8708
5.361	1.03	16	5.2979
4.8874	1.57	24	5.0493
4.7517	2.07	32	4.9304
4.6544	2.6	40	4.8450
4.544	3.1	48	4.7767
4.4482	3.63	56	4.7587

Framework versions

• PEFT 0.7.2.dev0
• Transformers 4.37.0.dev0
• Pytorch 2.0.1+cu117
• Datasets 2.16.1
• Tokenizers 0.15.0