Modelpublic

sahanes/TinyLlamaB_alpaca_2k

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face

0likes9downloads

Model Card

<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/> <details><summary>See axolotl config</summary>

axolotl version: 0.4.0

yaml

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/simple-lora-out/
hub_model_id: sahanes/TinyLlamaB_alpaca_2k

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:

wandb_project:
wandb_entity:
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:

</details><br>

TinyLlamaBalpaca2k

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: 1.2124

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
—trainbatchsize: 2
—evalbatchsize: 2
—seed: 42
—gradientaccumulationsteps: 4
—totaltrainbatch_size: 8
—optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
—lrschedulertype: cosine
—lrschedulerwarmup_steps: 10
—num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss
1.4615	0.08	1	1.4899
1.3853	0.24	3	1.4862
1.3665	0.48	6	1.4396
1.2677	0.72	9	1.3393
1.2261	0.96	12	1.2967
1.2513	1.16	15	1.2810
1.2266	1.4	18	1.2557
1.1349	1.6400	21	1.2344
1.2688	1.88	24	1.2275
1.1477	2.08	27	1.2242
1.1524	2.32	30	1.2217
1.1944	2.56	33	1.2198
1.1123	2.8	36	1.2134
1.1523	3.04	39	1.2126
1.1897	3.24	42	1.2102
1.1006	3.48	45	1.2143
1.1894	3.7200	48	1.2124

Framework versions

—PEFT 0.10.0
—Transformers 4.40.2
—Pytorch 2.1.2+cu118
—Datasets 2.19.1
—Tokenizers 0.19.1