NEW RUN 2024-03-22-12-52-51 {'load_model': '', 'model_path': '/workspace/VisualRWKV/models/rwkv3b-vitl336p14-577token_mix665k_8gpu_visual.pth', 'wandb': '', 'proj_dir': 'out/mod-rwkv3b', 'random_seed': -1, 'data_file': '/workspace/VisualRWKV/dataset/mod-rwkv-paper-image/lspd_instruct_300k.json', 'data_type': 'json', 'vocab_size': 65536, 'ctx_len': 1024, 'epoch_steps': 1000, 'epoch_count': 84, 'epoch_begin': 0, 'epoch_save': 10, 'micro_bsz': 1, 'n_layer': 32, 'n_embd': 2560, 'dim_att': 2560, 'dim_ffn': 8960, 'pre_ffn': 0, 'head_size_a': 64, 'head_size_divisor': 8, 'lr_init': 2e-05, 'lr_final': 2e-05, 'warmup_steps': 0, 'beta1': 0.9, 'beta2': 0.99, 'adam_eps': 1e-08, 'grad_cp': 0, 'dropout': 0, 'weight_decay': 0, 'weight_decay_final': -1, 'ds_bucket_mb': 200, 'vision_tower_name': 'openai/clip-vit-large-patch14-336', 'image_folder': '/workspace/VisualRWKV/dataset/mod-rwkv-paper-image/images/', 'grid_size': -1, 'detail': 'low', 'freeze_rwkv': 0, 'freeze_proj': 0, 'image_position': 'first', 'logger': False, 'enable_checkpointing': False, 'default_root_dir': None, 'gradient_clip_val': 1.0, 'gradient_clip_algorithm': None, 'num_nodes': 1, 'num_processes': None, 'devices': '8', 'gpus': None, 'auto_select_gpus': None, 'tpu_cores': None, 'ipus': None, 'enable_progress_bar': True, 'overfit_batches': 0.0, 'track_grad_norm': -1, 'check_val_every_n_epoch': 100000000000000000000, 'fast_dev_run': False, 'accumulate_grad_batches': 16, 'max_epochs': 84, 'min_epochs': None, 'max_steps': -1, 'min_steps': None, 'max_time': None, 'limit_train_batches': None, 'limit_val_batches': None, 'limit_test_batches': None, 'limit_predict_batches': None, 'val_check_interval': None, 'log_every_n_steps': 100000000000000000000, 'accelerator': 'gpu', 'strategy': 'deepspeed_stage_1', 'sync_batchnorm': False, 'precision': 'bf16', 'enable_model_summary': True, 'num_sanity_val_steps': 0, 'resume_from_checkpoint': None, 'profiler': None, 'benchmark': None, 'reload_dataloaders_every_n_epochs': 0, 'auto_lr_find': False, 'replace_sampler_ddp': False, 'detect_anomaly': False, 'auto_scale_batch_size': False, 'plugins': None, 'amp_backend': None, 'amp_level': None, 'move_metrics_to_cpu': False, 'multiple_trainloader_mode': 'max_size_cycle', 'inference_mode': True, 'my_timestamp': '2024-03-22-12-52-51', 'betas': (0.9, 0.99), 'real_bsz': 8, 'run_name': '65536 ctx1024 L32 D2560', 'tokenizer': , 'image_processor': CLIPImageProcessor { "_valid_processor_keys": [ "images", "do_resize", "size", "resample", "do_center_crop", "crop_size", "do_rescale", "rescale_factor", "do_normalize", "image_mean", "image_std", "do_convert_rgb", "return_tensors", "data_format", "input_data_format" ], "crop_size": { "height": 336, "width": 336 }, "do_center_crop": true, "do_convert_rgb": true, "do_normalize": true, "do_rescale": true, "do_resize": true, "image_mean": [ 0.48145466, 0.4578275, 0.40821073 ], "image_processor_type": "CLIPImageProcessor", "image_std": [ 0.26862954, 0.26130258, 0.27577711 ], "resample": 3, "rescale_factor": 0.00392156862745098, "size": { "shortest_edge": 336 } } } {'zero_allow_untested_optimizer': True, 'zero_optimization': {'stage': 1, 'contiguous_gradients': True, 'overlap_comm': True, 'allgather_partitions': True, 'reduce_scatter': True, 'allgather_bucket_size': 200000000, 'reduce_bucket_size': 200000000, 'sub_group_size': 1000000000000}, 'activation_checkpointing': {'partition_activations': False, 'cpu_checkpointing': False, 'contiguous_memory_optimization': False, 'synchronize_checkpoint_boundary': False}, 'aio': {'block_size': 1048576, 'queue_depth': 8, 'single_submit': False, 'overlap_events': True, 'thread_count': 1}, 'gradient_accumulation_steps': 16, 'train_micro_batch_size_per_gpu': 1, 'gradient_clipping': 1.0, 'bf16': {'enabled': True}} NEW RUN 2024-03-22-12-59-25 {'load_model': '/workspace/VisualRWKV/models/rwkv3b-vitl336p14-577token_mix665k_8gpu_rwkv.pth', 'model_path': '/workspace/VisualRWKV/models/rwkv3b-vitl336p14-577token_mix665k_8gpu_visual.pth', 'wandb': '', 'proj_dir': 'out/mod-rwkv3b', 'random_seed': -1, 'data_file': '/workspace/VisualRWKV/dataset/mod-rwkv-paper-image/lspd_instruct_300k.json', 'data_type': 'json', 'vocab_size': 65536, 'ctx_len': 1024, 'epoch_steps': 1000, 'epoch_count': 84, 'epoch_begin': 0, 'epoch_save': 10, 'micro_bsz': 1, 'n_layer': 32, 'n_embd': 2560, 'dim_att': 2560, 'dim_ffn': 8960, 'pre_ffn': 0, 'head_size_a': 64, 'head_size_divisor': 8, 'lr_init': 2e-05, 'lr_final': 2e-05, 'warmup_steps': 0, 'beta1': 0.9, 'beta2': 0.99, 'adam_eps': 1e-08, 'grad_cp': 0, 'dropout': 0, 'weight_decay': 0, 'weight_decay_final': -1, 'ds_bucket_mb': 200, 'vision_tower_name': 'openai/clip-vit-large-patch14-336', 'image_folder': '/workspace/VisualRWKV/dataset/mod-rwkv-paper-image/images/', 'grid_size': -1, 'detail': 'low', 'freeze_rwkv': 0, 'freeze_proj': 0, 'image_position': 'first', 'logger': False, 'enable_checkpointing': False, 'default_root_dir': None, 'gradient_clip_val': 1.0, 'gradient_clip_algorithm': None, 'num_nodes': 1, 'num_processes': None, 'devices': '8', 'gpus': None, 'auto_select_gpus': None, 'tpu_cores': None, 'ipus': None, 'enable_progress_bar': True, 'overfit_batches': 0.0, 'track_grad_norm': -1, 'check_val_every_n_epoch': 100000000000000000000, 'fast_dev_run': False, 'accumulate_grad_batches': 16, 'max_epochs': 84, 'min_epochs': None, 'max_steps': -1, 'min_steps': None, 'max_time': None, 'limit_train_batches': None, 'limit_val_batches': None, 'limit_test_batches': None, 'limit_predict_batches': None, 'val_check_interval': None, 'log_every_n_steps': 100000000000000000000, 'accelerator': 'gpu', 'strategy': 'deepspeed_stage_1', 'sync_batchnorm': False, 'precision': 'bf16', 'enable_model_summary': True, 'num_sanity_val_steps': 0, 'resume_from_checkpoint': None, 'profiler': None, 'benchmark': None, 'reload_dataloaders_every_n_epochs': 0, 'auto_lr_find': False, 'replace_sampler_ddp': False, 'detect_anomaly': False, 'auto_scale_batch_size': False, 'plugins': None, 'amp_backend': None, 'amp_level': None, 'move_metrics_to_cpu': False, 'multiple_trainloader_mode': 'max_size_cycle', 'inference_mode': True, 'my_timestamp': '2024-03-22-12-59-25', 'betas': (0.9, 0.99), 'real_bsz': 8, 'run_name': '65536 ctx1024 L32 D2560', 'tokenizer': , 'image_processor': CLIPImageProcessor { "_valid_processor_keys": [ "images", "do_resize", "size", "resample", "do_center_crop", "crop_size", "do_rescale", "rescale_factor", "do_normalize", "image_mean", "image_std", "do_convert_rgb", "return_tensors", "data_format", "input_data_format" ], "crop_size": { "height": 336, "width": 336 }, "do_center_crop": true, "do_convert_rgb": true, "do_normalize": true, "do_rescale": true, "do_resize": true, "image_mean": [ 0.48145466, 0.4578275, 0.40821073 ], "image_processor_type": "CLIPImageProcessor", "image_std": [ 0.26862954, 0.26130258, 0.27577711 ], "resample": 3, "rescale_factor": 0.00392156862745098, "size": { "shortest_edge": 336 } } } {'zero_allow_untested_optimizer': True, 'zero_optimization': {'stage': 1, 'contiguous_gradients': True, 'overlap_comm': True, 'allgather_partitions': True, 'reduce_scatter': True, 'allgather_bucket_size': 200000000, 'reduce_bucket_size': 200000000, 'sub_group_size': 1000000000000}, 'activation_checkpointing': {'partition_activations': False, 'cpu_checkpointing': False, 'contiguous_memory_optimization': False, 'synchronize_checkpoint_boundary': False}, 'aio': {'block_size': 1048576, 'queue_depth': 8, 'single_submit': False, 'overlap_events': True, 'thread_count': 1}, 'gradient_accumulation_steps': 16, 'train_micro_batch_size_per_gpu': 1, 'gradient_clipping': 1.0, 'bf16': {'enabled': True}} NEW RUN 2024-03-22-13-07-04 {'load_model': '/workspace/VisualRWKV/models/rwkv3b-vitl336p14-577token_mix665k_8gpu_rwkv.pth', 'model_path': '/workspace/VisualRWKV/models/rwkv3b-vitl336p14-577token_mix665k_8gpu_visual.pth', 'wandb': 'mod-visionrwkv', 'proj_dir': 'out/mod-rwkv3b', 'random_seed': -1, 'data_file': '/workspace/VisualRWKV/dataset/mod-rwkv-paper-image/lspd_instruct_300k.json', 'data_type': 'json', 'vocab_size': 65536, 'ctx_len': 1024, 'epoch_steps': 1000, 'epoch_count': 84, 'epoch_begin': 0, 'epoch_save': 10, 'micro_bsz': 1, 'n_layer': 32, 'n_embd': 2560, 'dim_att': 2560, 'dim_ffn': 8960, 'pre_ffn': 0, 'head_size_a': 64, 'head_size_divisor': 8, 'lr_init': 2e-05, 'lr_final': 2e-05, 'warmup_steps': 0, 'beta1': 0.9, 'beta2': 0.99, 'adam_eps': 1e-08, 'grad_cp': 0, 'dropout': 0, 'weight_decay': 0, 'weight_decay_final': -1, 'ds_bucket_mb': 200, 'vision_tower_name': 'openai/clip-vit-large-patch14-336', 'image_folder': '/workspace/VisualRWKV/dataset/mod-rwkv-paper-image/images/', 'grid_size': -1, 'detail': 'low', 'freeze_rwkv': 0, 'freeze_proj': 0, 'image_position': 'first', 'logger': False, 'enable_checkpointing': False, 'default_root_dir': None, 'gradient_clip_val': 1.0, 'gradient_clip_algorithm': None, 'num_nodes': 1, 'num_processes': None, 'devices': '8', 'gpus': None, 'auto_select_gpus': None, 'tpu_cores': None, 'ipus': None, 'enable_progress_bar': True, 'overfit_batches': 0.0, 'track_grad_norm': -1, 'check_val_every_n_epoch': 100000000000000000000, 'fast_dev_run': False, 'accumulate_grad_batches': 16, 'max_epochs': 84, 'min_epochs': None, 'max_steps': -1, 'min_steps': None, 'max_time': None, 'limit_train_batches': None, 'limit_val_batches': None, 'limit_test_batches': None, 'limit_predict_batches': None, 'val_check_interval': None, 'log_every_n_steps': 100000000000000000000, 'accelerator': 'gpu', 'strategy': 'deepspeed_stage_1', 'sync_batchnorm': False, 'precision': 'bf16', 'enable_model_summary': True, 'num_sanity_val_steps': 0, 'resume_from_checkpoint': None, 'profiler': None, 'benchmark': None, 'reload_dataloaders_every_n_epochs': 0, 'auto_lr_find': False, 'replace_sampler_ddp': False, 'detect_anomaly': False, 'auto_scale_batch_size': False, 'plugins': None, 'amp_backend': None, 'amp_level': None, 'move_metrics_to_cpu': False, 'multiple_trainloader_mode': 'max_size_cycle', 'inference_mode': True, 'my_timestamp': '2024-03-22-13-07-04', 'betas': (0.9, 0.99), 'real_bsz': 8, 'run_name': '65536 ctx1024 L32 D2560', 'tokenizer': , 'image_processor': CLIPImageProcessor { "_valid_processor_keys": [ "images", "do_resize", "size", "resample", "do_center_crop", "crop_size", "do_rescale", "rescale_factor", "do_normalize", "image_mean", "image_std", "do_convert_rgb", "return_tensors", "data_format", "input_data_format" ], "crop_size": { "height": 336, "width": 336 }, "do_center_crop": true, "do_convert_rgb": true, "do_normalize": true, "do_rescale": true, "do_resize": true, "image_mean": [ 0.48145466, 0.4578275, 0.40821073 ], "image_processor_type": "CLIPImageProcessor", "image_std": [ 0.26862954, 0.26130258, 0.27577711 ], "resample": 3, "rescale_factor": 0.00392156862745098, "size": { "shortest_edge": 336 } } } {'zero_allow_untested_optimizer': True, 'zero_optimization': {'stage': 1, 'contiguous_gradients': True, 'overlap_comm': True, 'allgather_partitions': True, 'reduce_scatter': True, 'allgather_bucket_size': 200000000, 'reduce_bucket_size': 200000000, 'sub_group_size': 1000000000000}, 'activation_checkpointing': {'partition_activations': False, 'cpu_checkpointing': False, 'contiguous_memory_optimization': False, 'synchronize_checkpoint_boundary': False}, 'aio': {'block_size': 1048576, 'queue_depth': 8, 'single_submit': False, 'overlap_events': True, 'thread_count': 1}, 'gradient_accumulation_steps': 16, 'train_micro_batch_size_per_gpu': 1, 'gradient_clipping': 1.0, 'bf16': {'enabled': True}} 0 0.746040 2.1086 0.00002000 2024-03-22 13:19:43.537517 0 1 0.548254 1.7302 0.00002000 2024-03-22 13:26:36.346264 1 2 0.512289 1.6691 0.00002000 2024-03-22 13:33:34.708854 2 3 0.488853 1.6304 0.00002000 2024-03-22 13:40:27.546320 3 4 0.473739 1.6060 0.00002000 2024-03-22 13:47:24.732973 4 5 0.462538 1.5881 0.00002000 2024-03-22 13:56:23.787183 5 6 0.452319 1.5720 0.00002000 2024-03-22 14:14:45.871084 6 7 0.445833 1.5618 0.00002000 2024-03-22 14:28:19.761131 7 8 0.442095 1.5560 0.00002000 2024-03-22 14:35:13.433437 8 9 0.438205 1.5499 0.00002000 2024-03-22 14:42:05.641207 9 10 0.430697 1.5383 0.00002000 2024-03-22 14:49:09.052478 10 11 0.427149 1.5329 0.00002000 2024-03-22 14:56:00.841882 11 12 0.422073 1.5251 0.00002000 2024-03-22 15:02:52.957633 12 13 0.419680 1.5215 0.00002000 2024-03-22 15:09:46.643417 13 14 0.415501 1.5151 0.00002000 2024-03-22 15:16:39.635809 14 15 0.414843 1.5141 0.00002000 2024-03-22 15:23:55.234766 15 16 0.407996 1.5038 0.00002000 2024-03-22 15:37:45.479784 16 17 0.408106 1.5040 0.00002000 2024-03-22 15:47:39.039546 17 18 0.406108 1.5010 0.00002000 2024-03-22 15:54:31.434503 18 19 0.404124 1.4980 0.00002000 2024-03-22 16:01:23.939296 19 20 0.401706 1.4944 0.00002000 2024-03-22 16:08:29.167253 20