skymizer/mistral-7b-v0.1-csft-open-orca-on-open-orca

base_model: Open-Orca/Mistral-7B-OpenOrca
model_type: AutoModelForCausalLM
tokenizer_config: Open-Orca/Mistral-7B-OpenOrca
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false
resize_token_embeddings_to_32x: true

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

load_in_8bit: false
load_in_4bit: false
strict: false

chat_template: chatml
datasets:
  - path: skymizer/open-orca-conversations
    type: chat_template
    field_messages: messages

hf_use_auth_token: true
dataset_prepared_path: pretokenized/open-orca
output_dir: ./outputs/out

sequence_len: 2048
sample_packing: true
pad_to_sequence_len: true

val_set_size: 0.005
eval_sample_packing: false
# eval_causal_lm_metrics: ["perplexity"]

wandb_project: "axolotl_mistral_sft"
wandb_entity:
wandb_watch:
wandb_name: "mistral-7B-v0.1-csft-open-orca-on-open-orca"
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 16
max_steps: 3000
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.000005 
weight_decay: 0.0
adam_beta1: 0.9
adam_beta2: 0.95
adam_eps: 0.000001
max_grad_norm: 1.0

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

hub_model_id: "skymizer/mistral-7b-v0.1-csft-open-orca-on-open-orca"
save_strategy: "steps"
save_steps: 1000

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_ratio: 0.03
eval_steps: 500
# evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128
debug:
deepspeed: deepspeed_configs/zero3_bf16.json
fsdp:
fsdp_config:

seed: 42