Hugging Face's logo

Fischerboot
/
sophie-1epoch

PEFT
llama
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files Community
sophie-1epoch / README.md
Fischerboot's picture
Fischerboot
Upload 7 files
1ca8bbb verified
preview code
|
raw
history blame
3.48 kB
metadata
base_model: Fischerboot/LLama3-Lexi-Aura-3Some-SLERP-SLERP-ql-merge
library_name: peft
tags:
  - generated_from_trainer
model-index:
  - name: outputs/128-rank-1-epoch
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

base_model: Fischerboot/LLama3-Lexi-Aura-3Some-SLERP-SLERP-ql-merge
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: true
strict: false

chat_template: llama3
datasets:
  - path: Fischerboot/newnewdataset-sophie
    type: sharegpt
  - path: PJMixers/grimulkan_theory-of-mind-ShareGPT
    type: sharegpt
    conversation: llama3
dataset_prepared_path: last_run_prepared
val_set_size: 0.1
output_dir: ./outputs/128-rank-1-epoch

adapter: qlora
lora_model_dir:

sequence_len: 128
sample_packing: false
pad_to_sequence_len: true

lora_r: 128
lora_alpha: 64
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj

wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 1
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

loss_watchdog_threshold: 8.0
loss_watchdog_patience: 3

eval_sample_packing: false
warmup_steps: 10
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|begin_of_text|>"
  eos_token: "<|end_of_text|>"
  pad_token: "<|end_of_text|>"

outputs/128-rank-1-epoch

This model is a fine-tuned version of Fischerboot/LLama3-Lexi-Aura-3Some-SLERP-SLERP-ql-merge on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3392

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
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 10
  • num_epochs: 1

Training results

Training Loss Epoch Step Validation Loss
6.1066 0.0034 1 6.0671
0.2353 0.2526 74 0.5415
0.2449 0.5051 148 0.3903
0.2361 0.7577 222 0.3392

Framework versions

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