Hugging Face's logo

NeuralNovel
/
Valor-7B-v0.1

PEFT
Safetensors
mistral
Generated from Trainer
Model card Files Community
5
Valor-7B-v0.1 / README.md
NeuralNovel's picture
NeuralNovel
Update README.md
aa5b4b1 verified
preview code
|
raw
history blame
3.44 kB
metadata
license: apache-2.0
datasets:
  - NeuralNovel/Neural-Story-v1
library_name: peft
tags:
  - generated_from_trainer
base_model: alnrg2arg/blockchainlabs_7B_merged_test2_4
model-index:
  - name: qlora-out
    results: []

image/jpeg

Valor-7B-v0.1

Valor speaks louder than words.

This is a qlora finetune of blockchainlabs_7B_merged_test2_4 with NeuralStory dataset, with the intention of increasing creativity and writing ability.

base_model: alnrg2arg/blockchainlabs_7B_merged_test2_4
model_type: MistralForCausalLM
tokenizer_type: LlamaTokenizer
is_mistral_derived_model: true

load_in_8bit: false
load_in_4bit: true
strict: false

datasets:
  - path: NeuralNovel/Neural-Story-v1
    type: completion
dataset_prepared_path: last_run_prepared
val_set_size: 0.1
output_dir: ./qlora-out

adapter: qlora
lora_model_dir:

sequence_len: 8192
sample_packing: false
pad_to_sequence_len: true

lora_r: 32
lora_alpha: 16
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: 4
micro_batch_size: 2
num_epochs: 1
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0002

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

loss_watchdog_threshold: 5.0
loss_watchdog_patience: 3

warmup_steps: 10
evals_per_epoch: 4
eval_table_size:
eval_table_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<s>"
  eos_token: "</s>"
  unk_token: "<unk>"

qlora-out

This model is a fine-tuned version of alnrg2arg/blockchainlabs_7B_merged_test2_4 on the Neural-Story-v1. It achieves the following results on the evaluation set:

  • Loss: 2.1411

axolotl version: 0.3.0

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: 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: 1

Training results

Training Loss Epoch Step Validation Loss
2.3251 0.06 1 2.8409
2.5318 0.25 4 2.7634
1.7316 0.51 8 2.3662
1.5196 0.76 12 2.1411

Framework versions

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