Hugging Face's logo

amphora
/
l3kpm2-lora

PEFT
Safetensors
llama
Generated from Trainer
8-bit precision
bitsandbytes
Model card Files Community
l3kpm2-lora / README.md
amphora's picture
amphora
Upload folder using huggingface_hub
c351ff0 verified
preview code
|
raw
history blame contribute delete
4.07 kB
metadata
base_model: NousResearch/Meta-Llama-3-8B-Instruct
library_name: peft
license: other
tags:
  - generated_from_trainer
model-index:
  - name: outputs/lora-out
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

base_model: NousResearch/Meta-Llama-3-8B-Instruct
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: true
load_in_4bit: false
strict: false

chat_template: llama3
datasets:
  - path: absolute-feedback-long.jsonl
    type: chat_template
    chat_template: llama3
    field_messages: messages
    message_field_role: role
    message_field_content: content
    roles:
      user:
        - user
      assistant:
        - assistant
val_set_size: 0.01
output_dir: ./outputs/lora-out

sequence_len: 4096
sample_packing: false
pad_to_sequence_len: false

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: fincode
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 32
micro_batch_size: 12
num_epochs: 3
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
s2_attention:
deepspeed: deepspeed_configs/zero1.json

warmup_steps: 20
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 3
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  pad_token: <|end_of_text|>

Visualize in Weights & Biases

outputs/lora-out

This model is a fine-tuned version of NousResearch/Meta-Llama-3-8B-Instruct on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.0461

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: 12
  • eval_batch_size: 12
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 8
  • gradient_accumulation_steps: 32
  • total_train_batch_size: 3072
  • total_eval_batch_size: 96
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 20
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss
1.8935 0.0311 1 1.8884
1.6965 0.2490 8 1.5971
1.3733 0.4981 16 1.3446
1.2466 0.7471 24 1.2463
1.1852 0.9961 32 1.1822
1.1444 1.2451 40 1.1379
1.0986 1.4942 48 1.1052
1.0774 1.7432 56 1.0816
1.065 1.9922 64 1.0657
1.055 2.2412 72 1.0551
1.0438 2.4903 80 1.0484
1.0394 2.7393 88 1.0463
1.0466 2.9883 96 1.0461

Framework versions

  • PEFT 0.11.1
  • Transformers 4.42.3
  • Pytorch 2.1.2
  • Datasets 2.19.1
  • Tokenizers 0.19.1