base_model: microsoft/phi-2
model_revision: 834565c  # pin model repo to the previous architecture
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

hub_model_id: satpalsr/phi2-filter2
hf_use_auth_token: true

datasets:
  - path: satpalsr/phifilter
    type: completion

dataset_prepared_path:
val_set_size: 0.0
output_dir: ./phi2-filter2

sequence_len: 2048
sample_packing: false  # currently unsupported
pad_to_sequence_len:

adapter:
lora_model_dir:
lora_r: 16
lora_alpha: 32
lora_dropout: 0.1
lora_target_linear: true
lora_fan_in_fan_out:
lora_modules_to_save:
  - embd
  - lm_head

wandb_project: phi2transfilter
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 16
num_epochs: 16
optimizer: paged_adamw_8bit
adam_beta2: 0.95
adam_epsilon: 0.00001
max_grad_norm: 1.0
lr_scheduler: cosine
learning_rate: 1e-5

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

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: false

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

phi2-filter2

This model is a fine-tuned version of microsoft/phi-2 on the None dataset.

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: 1e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 100
num_epochs: 16

Training results

Framework versions

Transformers 4.37.0.dev0
Pytorch 2.1.1+cu118
Datasets 2.16.1
Tokenizers 0.15.0