Hugging Face's logo

jeiku
/
Everything_v3_128_StableLM

PEFT
stablelm_epoch
Generated from Trainer
custom_code
4-bit precision
bitsandbytes
Model card Files Community
Everything_v3_128_StableLM / README.md
jeiku's picture
jeiku
Upload 8 files
b34d11d verified
preview code
|
raw
history blame contribute delete
3.65 kB
metadata
license: cc-by-sa-4.0
library_name: peft
tags:
  - generated_from_trainer
base_model: stabilityai/stablelm-3b-4e1t
model-index:
  - name: everything
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.3.0

base_model: stabilityai/stablelm-3b-4e1t
base_model_config: stabilityai/stablelm-3b-4e1t
trust_remote_code: true
model_type: AutoModelForCausalLM
tokenizer_type: GPTNeoXTokenizerFast

load_in_8bit: false
load_in_4bit: true
strict: false

datasets:
  - path: totally-not-an-llm/EverythingLM-data-V3
    type: alpaca

dataset_prepared_path:
val_set_size: 0.005
output_dir: ./everything

adapter: qlora

sequence_len: 1024
sample_packing: false
pad_to_sequence_len: true
save_safetensors: false

lora_r: 128
lora_alpha: 256
lora_dropout: 0.05
lora_target_linear: false
lora_fan_in_fan_out:
lora_modules_to_save:
  - embed_tokens
  - lm_head
lora_target_modules:
  - q_proj
  - v_proj

gradient_accumulation_steps: 1
micro_batch_size: 16
num_epochs: 5
optimizer: paged_adamw_32bit
lr_scheduler: cosine
learning_rate: 0.00005

train_on_inputs: false
group_by_length: false
bf16: true
fp16: false
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: 1
eval_table_size:
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|endoftext|>"
  eos_token: "<|im_end|>"
  unk_token: "<|endoftext|>"
tokens:
  - "<|im_start|>"
  - "<|im_end|>"

everything

This model is a fine-tuned version of stabilityai/stablelm-3b-4e1t on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.8096

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

The following bitsandbytes quantization config was used during training:

  • quant_method: bitsandbytes
  • load_in_8bit: False
  • load_in_4bit: True
  • llm_int8_threshold: 6.0
  • llm_int8_skip_modules: None
  • llm_int8_enable_fp32_cpu_offload: False
  • llm_int8_has_fp16_weight: False
  • bnb_4bit_quant_type: nf4
  • bnb_4bit_use_double_quant: True
  • bnb_4bit_compute_dtype: bfloat16

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 5e-05
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 10
  • num_epochs: 5

Training results

Training Loss Epoch Step Validation Loss
1.3873 0.02 1 1.6256
1.1399 1.0 60 0.8263
1.5717 2.0 120 0.8054
0.6861 3.0 180 0.8149
0.9527 4.0 240 0.8036
0.5738 5.0 300 0.8096

Framework versions

  • PEFT 0.7.0
  • Transformers 4.37.0.dev0
  • Pytorch 2.0.1+cu117
  • Datasets 2.16.1
  • Tokenizers 0.15.0