| { | |
| "best_metric": 1.2206299304962158, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-30", | |
| "epoch": 0.01843884449907806, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006146281499692685, | |
| "eval_loss": 1.6310069561004639, | |
| "eval_runtime": 45.8666, | |
| "eval_samples_per_second": 14.935, | |
| "eval_steps_per_second": 7.478, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0018438844499078057, | |
| "grad_norm": 0.46550798416137695, | |
| "learning_rate": 0.00012, | |
| "loss": 1.2911, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003073140749846343, | |
| "eval_loss": 1.5613337755203247, | |
| "eval_runtime": 44.3666, | |
| "eval_samples_per_second": 15.44, | |
| "eval_steps_per_second": 7.731, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0036877688998156115, | |
| "grad_norm": 0.4773057699203491, | |
| "learning_rate": 0.0001992114701314478, | |
| "loss": 1.1367, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005531653349723417, | |
| "grad_norm": 0.8123539090156555, | |
| "learning_rate": 0.00018763066800438636, | |
| "loss": 1.3804, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006146281499692686, | |
| "eval_loss": 1.3972467184066772, | |
| "eval_runtime": 44.3624, | |
| "eval_samples_per_second": 15.441, | |
| "eval_steps_per_second": 7.732, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007375537799631223, | |
| "grad_norm": 0.5950524210929871, | |
| "learning_rate": 0.000163742398974869, | |
| "loss": 1.1126, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00921942224953903, | |
| "grad_norm": 0.7039989829063416, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.0127, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00921942224953903, | |
| "eval_loss": 1.302493929862976, | |
| "eval_runtime": 44.531, | |
| "eval_samples_per_second": 15.383, | |
| "eval_steps_per_second": 7.702, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.011063306699446834, | |
| "grad_norm": 0.684798002243042, | |
| "learning_rate": 9.372094804706867e-05, | |
| "loss": 0.9299, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.012292562999385371, | |
| "eval_loss": 1.247101902961731, | |
| "eval_runtime": 44.4753, | |
| "eval_samples_per_second": 15.402, | |
| "eval_steps_per_second": 7.712, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01290719114935464, | |
| "grad_norm": 0.596222996711731, | |
| "learning_rate": 5.7422070843492734e-05, | |
| "loss": 1.1096, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.014751075599262446, | |
| "grad_norm": 0.5047256946563721, | |
| "learning_rate": 2.7103137257858868e-05, | |
| "loss": 1.1311, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.015365703749231715, | |
| "eval_loss": 1.2259085178375244, | |
| "eval_runtime": 44.5912, | |
| "eval_samples_per_second": 15.362, | |
| "eval_steps_per_second": 7.692, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.016594960049170254, | |
| "grad_norm": 0.8928716778755188, | |
| "learning_rate": 7.022351411174866e-06, | |
| "loss": 0.8738, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.01843884449907806, | |
| "grad_norm": 0.6247184872627258, | |
| "learning_rate": 0.0, | |
| "loss": 1.3205, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01843884449907806, | |
| "eval_loss": 1.2206299304962158, | |
| "eval_runtime": 44.5161, | |
| "eval_samples_per_second": 15.388, | |
| "eval_steps_per_second": 7.705, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.2426611999637504e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |