base_model: microsoft/phi-1_5
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: true
strict: false

datasets:
  - path: garage-bAInd/Open-Platypus
    type: alpaca

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/phi-sft-out

sequence_len: 1024
sample_packing: true
pad_to_sequence_len: true

adapter: qlora
lora_model_dir:
lora_r: 64
lora_alpha: 32
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: 1
micro_batch_size: 1
num_epochs: 1
optimizer: adamw_torch
adam_beta2: 0.95
adam_epsilon: 0.00001
max_grad_norm: 1.0
lr_scheduler: cosine
learning_rate: 0.000003

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: True
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: false

warmup_steps: 100
evals_per_epoch: 1
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.1
fsdp:
fsdp_config:
resize_token_embeddings_to_32x: true
special_tokens:
  pad_token: "<|endoftext|>"

hub_model_id: AdamRTomkins/phi-kal 
hub_strategy: end
max_steps: 2

# Setting to enable pre-ampere cards!
bf16: auto
fp16: false

phi-kal

This model is a fine-tuned version of microsoft/phi-1_5 on the None dataset. It achieves the following results on the evaluation set:

Loss: 2.4120

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: 3e-06
train_batch_size: 1
eval_batch_size: 1
seed: 42
optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 100
training_steps: 2

Training results

Training Loss	Epoch	Step	Validation Loss
6.3765	0.0	2	2.4120

Framework versions

PEFT 0.8.2
Transformers 4.39.0.dev0
Pytorch 2.0.1+cu118
Datasets 2.17.1
Tokenizers 0.15.0