Dans-DiscountModels/7b-m-dans-optimizersweeps-repremover-1-ademamix-b1_0.9-b2_0.999-b3_0.999-a15

base_model: Dans-DiscountModels/7b-m-dans-personalityengine-v1.2.1-rc-2
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code:

# wandb configuration
wandb_project: 7b-m-dans-optimizersweeps
wandb_watch:

wandb_run_id: repremover-1-1-ademamix-b1_0.9-b2_0.999-b3_0.999-a15
wandb_log_model:

# push checkpoints to hub
hub_model_id: Dans-DiscountModels/7b-m-dans-optimizersweeps-repremover-1-ademamix-b1_0.9-b2_0.999-b3_0.999-a15
# how to push checkpoints to hub
# https://huggingface.co/docs/transformers/v4.31.0/en/main_classes/trainer#transformers.TrainingArguments.hub_strategy
hub_strategy: "every_save"
# Whether to use hf `use_auth_token` for loading datasets. Useful for fetching private datasets
# Required to be true when used in combination with `push_dataset_to_hub`
hf_use_auth_token: true

# where to save the finished model to
output_dir: ./7b-m-dans-optimizersweeps

# where to save the dataset to
dataset_prepared_path: ./7b-m-dans-optimizersweeps-data

save_safetensors: true

# dataset settings (local or huggingface repo)
datasets:
  - path: Dans-DiscountModels/pretokenization-test-3
    ds_type: parquet
    type:

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true

load_in_8bit: false
load_in_4bit: false
strict: false

adapter:
lora_model_dir:

val_set_size: 0.01
sequence_len: 8192

sample_packing: false
eval_sample_packing: false

pad_to_sequence_len: true

gradient_checkpointing: true
# gradient_checkpointing_kwargs:
# use_reentrant: false

gradient_accumulation_steps: 1
micro_batch_size: 4

num_epochs: 3

optimizer: ademamix
optim_args: "beta1=0.9,beta2=0.999,beta3=0.999,alpha=15"

lr_scheduler: rex
learning_rate: 0.0000001
cosine_min_lr_ratio:

# weight_decay: 0.03
max_grad_norm: 0.001

train_on_inputs: false
group_by_length: true

bf16: true
fp16: false
tf32: false

early_stopping_patience:

resume_from_checkpoint:
auto_resume_from_checkpoints: false

local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_ratio: 0.1

evals_per_epoch: 24
eval_table_size:
eval_max_new_tokens:

saves_per_epoch: 8
save_total_limit: 2

debug: false

deepspeed: deepspeed_configs/zero3_bf16.json

fsdp:
fsdp_config:

special_tokens: