Create axolotl_config/config.yml

axolotl_config/config.yml

@@ -0,0 +1,70 @@
+base_model: Qwen/Qwen2-72B-Instruct
+model_type: AutoModelForCausalLM
+tokenizer_type: AutoTokenizer
+
+trust_remote_code: true
+
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+datasets:
+  - path: data/data.json
+    type: sharegpt
+    conversation: chatml
+chat_template: chatml
+dataset_prepared_path:
+val_set_size: 0.0
+output_dir: ./qwen2-72b-instruct
+
+sequence_len: 8192
+sample_packing: true
+eval_sample_packing: false
+pad_to_sequence_len:
+
+adapter:
+lora_model_dir:
+lora_r:
+lora_alpha:
+lora_dropout:
+lora_target_linear:
+lora_fan_in_fan_out:
+
+wandb_project: qwen2-72b-opus-v0.1
+wandb_entity:
+wandb_watch:
+wandb_name: attempt-3
+wandb_log_model:
+
+gradient_accumulation_steps: 2
+micro_batch_size: 1
+num_epochs: 4
+optimizer: paged_adamw_8bit
+lr_scheduler: cosine
+learning_rate: 0.000001
+
+train_on_inputs: false
+group_by_length: false
+bf16: auto
+fp16:
+tf32: false
+
+gradient_checkpointing: unsloth
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+
+warmup_steps: 10
+evals_per_epoch:
+eval_table_size:
+eval_max_new_tokens:
+saves_per_epoch: 4
+debug:
+deepspeed: deepspeed_configs/zero3_bf16.json
+weight_decay: 0.0
+fsdp:
+fsdp_config:
+special_tokens: