Phi 1.5 multi-gpu config (Axolotl)

phi15_test_wizzard_vicuna.yml

#only changed self.vocab_size = vocab_size in configuration_mixformer_sequential.py, as suggested by @NanoBit
base_model: /workspace/models/phi-1_5
base_model_config: /workspace/models/phi-1_5
trust_remote_code: true
base_model_ignore_patterns:
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
is_llama_derived_model: false

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: ehartford/wizard_vicuna_70k_unfiltered
    type: sharegpt:chat
dataset_prepared_path: /workspace/tmp/last_run_prepared
val_set_size: 0.03
output_dir: /workspace/models/phi_wizard_vicuna_uncensored
resume_from_checkpoint:

adapter:
lora_model_dir:

sequence_len: 2048
sample_packing: true

lora_r:
lora_alpha:
lora_dropout:
lora_target_modules:
lora_target_linear: true
lora_fan_in_fan_out:

relora_steps:
relora_warmup_steps:
relora_cpu_offload:

wandb_project: phi_wizard_vicuna
wandb_entity:
wandb_watch:
wandb_run_id: test2
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 3
optimizer: adamw_bnb_8bit
#paged_adamw_32bit
lr_scheduler: cosine
learning_rate: 0.00005

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

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

warmup_steps: 10
eval_steps: 125
save_steps: 250
save_total_limit: 3
debug:
#standard zero2.json from axolotl/deepspeed without any changes
deepspeed: zero2.json
weight_decay:
fsdp:
fsdp_config:
special_tokens:
  pad_token: "<|endoftext|>"

#500 schon done
resize_token_embeddings_to_32x: true