Delete train_2025-08-07-09-00-30

train_2025-08-07-09-00-30/llamaboard_config.yaml

@@ -1,85 +0,0 @@
-top.booster: auto
-top.checkpoint_path: []
-top.finetuning_type: lora
-top.model_name: Llama-3.1-70B
-top.quantization_bit: none
-top.quantization_method: bnb
-top.rope_scaling: none
-top.template: default
-train.additional_target: ''
-train.apollo_rank: 16
-train.apollo_scale: 32
-train.apollo_target: all
-train.apollo_update_interval: 200
-train.badam_mode: layer
-train.badam_switch_interval: 50
-train.badam_switch_mode: ascending
-train.badam_update_ratio: 0.05
-train.batch_size: 1
-train.compute_type: bf16
-train.create_new_adapter: false
-train.cutoff_len: 2048
-train.dataset:
-- ASC_CORPUS
-train.dataset_dir: data
-train.ds_offload: false
-train.ds_stage: '3'
-train.enable_thinking: true
-train.extra_args: '{"optim": "adamw_torch"}'
-train.freeze_extra_modules: ''
-train.freeze_language_model: false
-train.freeze_multi_modal_projector: true
-train.freeze_trainable_layers: 2
-train.freeze_trainable_modules: all
-train.freeze_vision_tower: true
-train.galore_rank: 16
-train.galore_scale: 2
-train.galore_target: all
-train.galore_update_interval: 200
-train.gradient_accumulation_steps: 8
-train.image_max_pixels: 768*768
-train.image_min_pixels: 32*32
-train.learning_rate: 5e-5
-train.logging_steps: 1
-train.lora_alpha: 16
-train.lora_dropout: 0.05
-train.lora_rank: 8
-train.lora_target: ''
-train.loraplus_lr_ratio: 0
-train.lr_scheduler_type: cosine
-train.mask_history: false
-train.max_grad_norm: '1.0'
-train.max_samples: '100000'
-train.neat_packing: false
-train.neftune_alpha: 0
-train.num_train_epochs: '10.0'
-train.packing: true
-train.ppo_score_norm: false
-train.ppo_whiten_rewards: false
-train.pref_beta: 0.1
-train.pref_ftx: 0
-train.pref_loss: sigmoid
-train.report_to: wandb
-train.resize_vocab: false
-train.reward_model: []
-train.save_steps: 100
-train.swanlab_api_key: ''
-train.swanlab_link: ''
-train.swanlab_mode: cloud
-train.swanlab_project: llamafactory
-train.swanlab_run_name: ''
-train.swanlab_workspace: ''
-train.train_on_prompt: false
-train.training_stage: Pre-Training
-train.use_apollo: false
-train.use_badam: false
-train.use_dora: false
-train.use_galore: false
-train.use_llama_pro: false
-train.use_pissa: false
-train.use_rslora: false
-train.use_swanlab: false
-train.val_size: 0
-train.video_max_pixels: 256*256
-train.video_min_pixels: 16*16
-train.warmup_steps: 0

train_2025-08-07-09-00-30/running_log.txt

@@ -1,46 +0,0 @@
-[INFO|2025-08-07 09:03:42] configuration_utils.py:750 >> loading configuration file /workspace/meta-llama/Llama-3.1-70B/config.json
-[INFO|2025-08-07 09:03:42] configuration_utils.py:817 >> Model config LlamaConfig {
-  "architectures": [
-    "LlamaForCausalLM"
-  ],
-  "attention_bias": false,
-  "attention_dropout": 0.0,
-  "bos_token_id": 128000,
-  "eos_token_id": 128001,
-  "head_dim": 128,
-  "hidden_act": "silu",
-  "hidden_size": 8192,
-  "initializer_range": 0.02,
-  "intermediate_size": 28672,
-  "max_position_embeddings": 131072,
-  "mlp_bias": false,
-  "model_type": "llama",
-  "num_attention_heads": 64,
-  "num_hidden_layers": 80,
-  "num_key_value_heads": 8,
-  "pretraining_tp": 1,
-  "rms_norm_eps": 1e-05,
-  "rope_scaling": {
-    "factor": 8.0,
-    "high_freq_factor": 4.0,
-    "low_freq_factor": 1.0,
-    "original_max_position_embeddings": 8192,
-    "rope_type": "llama3"
-  },
-  "rope_theta": 500000.0,
-  "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.55.0",
-  "use_cache": true,
-  "vocab_size": 128256
-}
-
-[INFO|2025-08-07 09:03:42] logging.py:143 >> KV cache is disabled during training.
-[INFO|2025-08-07 09:03:42] modeling_utils.py:1305 >> loading weights file /workspace/meta-llama/Llama-3.1-70B/model.safetensors.index.json
-[INFO|2025-08-07 09:03:42] modeling_utils.py:4363 >> Detected DeepSpeed ZeRO-3: activating zero.init() for this model
-[INFO|2025-08-07 09:03:42] configuration_utils.py:1098 >> Generate config GenerationConfig {
-  "bos_token_id": 128000,
-  "eos_token_id": 128001,
-  "use_cache": false
-}
-

train_2025-08-07-09-00-30/training_args.yaml

@@ -1,35 +0,0 @@
-bf16: true
-cutoff_len: 2048
-dataset: ASC_CORPUS
-dataset_dir: data
-ddp_timeout: 180000000
-deepspeed: cache/ds_z3_config.json
-do_train: true
-enable_thinking: true
-finetuning_type: lora
-flash_attn: auto
-gradient_accumulation_steps: 8
-include_num_input_tokens_seen: true
-learning_rate: 5.0e-05
-logging_steps: 1
-lora_alpha: 16
-lora_dropout: 0.05
-lora_rank: 8
-lora_target: all
-lr_scheduler_type: cosine
-max_grad_norm: 1.0
-max_samples: 100000
-model_name_or_path: /workspace/meta-llama/Llama-3.1-70B
-num_train_epochs: 10.0
-optim: adamw_torch
-output_dir: saves/Llama-3.1-70B/lora/train_2025-08-07-09-00-30
-packing: true
-per_device_train_batch_size: 1
-plot_loss: true
-preprocessing_num_workers: 16
-report_to: wandb
-save_steps: 100
-stage: pt
-template: default
-trust_remote_code: true
-warmup_steps: 0