| 2025-08-19 06:36:27,594 INFO MainThread:1898 [wandb_setup.py:_flush():80] Current SDK version is 0.21.1 |
| 2025-08-19 06:36:27,594 INFO MainThread:1898 [wandb_setup.py:_flush():80] Configure stats pid to 1898 |
| 2025-08-19 06:36:27,594 INFO MainThread:1898 [wandb_setup.py:_flush():80] Loading settings from /root/.config/wandb/settings |
| 2025-08-19 06:36:27,594 INFO MainThread:1898 [wandb_setup.py:_flush():80] Loading settings from /notebooks/toy_models/models/gelu_2l_v6_200m_subset/wandb/settings |
| 2025-08-19 06:36:27,594 INFO MainThread:1898 [wandb_setup.py:_flush():80] Loading settings from environment variables |
| 2025-08-19 06:36:27,594 INFO MainThread:1898 [wandb_init.py:setup_run_log_directory():703] Logging user logs to /notebooks/toy_models/models/gelu_2l_v6_200m_subset/wandb/run-20250819_063627-4rs47wj5/logs/debug.log |
| 2025-08-19 06:36:27,594 INFO MainThread:1898 [wandb_init.py:setup_run_log_directory():704] Logging internal logs to /notebooks/toy_models/models/gelu_2l_v6_200m_subset/wandb/run-20250819_063627-4rs47wj5/logs/debug-internal.log |
| 2025-08-19 06:36:27,594 INFO MainThread:1898 [wandb_init.py:init():830] calling init triggers |
| 2025-08-19 06:36:27,594 INFO MainThread:1898 [wandb_init.py:init():835] wandb.init called with sweep_config: {} |
| config: {'model_name': 'gelu_2l_v5_random_above_15000', 'n_layers': 2, 'd_model': 512, 'd_mlp': 2048, 'd_head': 64, 'n_heads': 8, 'attn_only': False, 'layer_norm_eps': 1e-05, 'init_range': 0.02, 'n_ctx': 1024, 'd_vocab': 48262, 'dataset_name': 'eoinf/unprocessed-c4-code-test', 'tokenizer_name': 'NeelNanda/gpt-neox-tokenizer-digits', 'seed': 10, 'device': 'cuda', 'use_bfloat16_matmul': False, 'batch_size_per_device': 32, 'n_devices': 1, 'batches_per_step': 1, 'max_tokens': 200000000, 'lr_hidden': 0.002, 'lr_vector': 0.001, 'lr_schedule': 'constant_with_warmup', 'warmup_tokens': 30000000, 'weight_decay': 0.05, 'grad_norm_clip': 1.0, 'train_loss_moving_average_beta': 0.99, 'log_interval': 25, 'save_checkpoints': True, 'checkpoint_interval': 500, 'checkpoint_interval_ratio': 1.08, 'save_log_checkpoints': True, 'use_wandb': True, 'batch_size': 32, 'tokens_per_step': 32768, 'warmup_steps': 915, 'max_steps': 6103, '_wandb': {}} |
| 2025-08-19 06:36:27,594 INFO MainThread:1898 [wandb_init.py:init():871] starting backend |
| 2025-08-19 06:36:27,801 INFO MainThread:1898 [wandb_init.py:init():874] sending inform_init request |
| 2025-08-19 06:36:27,804 INFO MainThread:1898 [wandb_init.py:init():882] backend started and connected |
| 2025-08-19 06:36:27,806 INFO MainThread:1898 [wandb_init.py:init():953] updated telemetry |
| 2025-08-19 06:36:27,809 INFO MainThread:1898 [wandb_init.py:init():977] communicating run to backend with 90.0 second timeout |
| 2025-08-19 06:36:28,120 INFO MainThread:1898 [wandb_init.py:init():1029] starting run threads in backend |
| 2025-08-19 06:36:28,215 INFO MainThread:1898 [wandb_run.py:_console_start():2494] atexit reg |
| 2025-08-19 06:36:28,215 INFO MainThread:1898 [wandb_run.py:_redirect():2342] redirect: wrap_raw |
| 2025-08-19 06:36:28,215 INFO MainThread:1898 [wandb_run.py:_redirect():2411] Wrapping output streams. |
| 2025-08-19 06:36:28,216 INFO MainThread:1898 [wandb_run.py:_redirect():2434] Redirects installed. |
| 2025-08-19 06:36:28,218 INFO MainThread:1898 [wandb_init.py:init():1075] run started, returning control to user process |
| 2025-08-19 07:45:26,690 INFO MainThread:1898 [wandb_run.py:_finish():2260] finishing run eoin/toy-transformer-replication/4rs47wj5 |
| 2025-08-19 07:45:26,697 INFO MainThread:1898 [wandb_run.py:_atexit_cleanup():2459] got exitcode: 0 |
| 2025-08-19 07:45:26,697 INFO MainThread:1898 [wandb_run.py:_restore():2441] restore |
| 2025-08-19 07:45:26,698 INFO MainThread:1898 [wandb_run.py:_restore():2447] restore done |
| 2025-08-19 07:45:27,278 INFO MainThread:1898 [wandb_run.py:_footer_history_summary_info():3895] rendering history |
| 2025-08-19 07:45:27,278 INFO MainThread:1898 [wandb_run.py:_footer_history_summary_info():3927] rendering summary |
| 2025-08-19 07:45:27,279 INFO MainThread:1898 [wandb_run.py:_footer_sync_info():3856] logging synced files |
|
|