alsokit/eLM-Phi3-mini-128K-it-LoRA

See axolotl config

axolotl version: 0.4.1

base_model: microsoft/Phi-3-mini-128k-instruct
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false

datasets:
  - path: alsokit/alpaca_vtb_train_and_eval_25K
    type: alpaca
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./outputs/out

sequence_len: 8192
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: qlora
lora_model_dir:
lora_r: 32
lora_alpha: 64
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: 1
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.0002

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: true

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
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:
special_tokens:

outputs/out

This model is a fine-tuned version of microsoft/Phi-3-mini-128k-instruct on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1984

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
• gradient_accumulation_steps: 4
• total_train_batch_size: 4
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 10
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
3.4523	0.0018	1	2.7465
0.3199	0.2512	142	0.3300
0.2857	0.5024	284	0.2663
0.2264	0.7536	426	0.2466
0.246	1.0049	568	0.2292
0.2419	1.2472	710	0.2197
0.2099	1.4985	852	0.2147
0.2111	1.7497	994	0.2065
0.1662	2.0009	1136	0.2005
0.173	2.2366	1278	0.1999
0.1633	2.4878	1420	0.1986
0.169	2.7391	1562	0.1984

Framework versions

• PEFT 0.11.1
• Transformers 4.42.3
• Pytorch 2.1.2+cu118
• Datasets 2.19.1
• Tokenizers 0.19.1