Delete data/configs_hc.yml

data/configs_hc.yml

@@ -1,91 +0,0 @@
-base_model: mistralai/Mistral-7B-v0.1
-model_type: MistralForCausalLM
-tokenizer_type: LlamaTokenizer
-is_mistral_derived_model: true
-
-load_in_8bit: false
-load_in_4bit: true
-strict: false
-
-lora_fan_in_fan_out: false
-data_seed: 49
-seed: 49
-
-datasets:
-  - path: /teamspace/studios/this_studio/axolotl/finetune_maven/hc-mistral-alpaca/data/alpaca_synth_queries_healed.jsonl
-    type: sharegpt
-    conversation: alpaca
-dataset_prepared_path: last_run_prepared
-val_set_size: 0.1
-output_dir: ./qlora-alpaca-out
-hub_model_id: valLabsz/clssfcn-naming
-#hub_model_id: hamel/hc-mistral-alpaca
-
-
-adapter: qlora
-lora_model_dir:
-
-sequence_len: 896
-sample_packing: false
-pad_to_sequence_len: true
-
-lora_r: 32
-lora_alpha: 16
-lora_dropout: 0.05
-lora_target_linear: true
-lora_fan_in_fan_out:
-lora_target_modules:
-  - gate_proj
-  - down_proj
-  - up_proj
-  - q_proj
-  - v_proj
-  - k_proj
-  - o_proj
-
-#wandb_project: hc-axolotl-mistral
-#wandb_entity: hamelsmu
-
-gradient_accumulation_steps: 4
-micro_batch_size: 16
-eval_batch_size: 16
-num_epochs: 3
-optimizer: adamw_bnb_8bit
-lr_scheduler: cosine
-learning_rate: 0.0002
-max_grad_norm: 1.0
-adam_beta2: 0.95
-adam_epsilon: 0.00001
-save_total_limit: 12
-
-train_on_inputs: false
-group_by_length: false
-bf16: true
-fp16: false
-tf32: false
-
-gradient_checkpointing: true
-early_stopping_patience:
-resume_from_checkpoint:
-local_rank:
-logging_steps: 1
-xformers_attention:
-flash_attention: true
-
-loss_watchdog_threshold: 5.0
-loss_watchdog_patience: 3
-
-warmup_steps: 20
-evals_per_epoch: 4
-eval_table_size:
-eval_table_max_new_tokens: 128
-saves_per_epoch: 6
-debug:
-weight_decay: 0.0
-fsdp:
-fsdp_config:
-special_tokens:
-  bos_token: "<s>"
-  eos_token: "</s>"
-  unk_token: "<unk>"
-save_safetensors: true