| { | |
| "best_metric": 2.8287272453308105, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-400", | |
| "epoch": 0.007723741090543968, | |
| "eval_steps": 50, | |
| "global_step": 400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.930935272635992e-05, | |
| "eval_loss": 3.0496411323547363, | |
| "eval_runtime": 573.4498, | |
| "eval_samples_per_second": 76.052, | |
| "eval_steps_per_second": 38.026, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007723741090543968, | |
| "grad_norm": 65.50666809082031, | |
| "learning_rate": 5e-05, | |
| "loss": 22.4683, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.000965467636317996, | |
| "eval_loss": 2.974703311920166, | |
| "eval_runtime": 577.5766, | |
| "eval_samples_per_second": 75.509, | |
| "eval_steps_per_second": 37.754, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0015447482181087937, | |
| "grad_norm": 55.97782516479492, | |
| "learning_rate": 0.0001, | |
| "loss": 23.412, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.001930935272635992, | |
| "eval_loss": 2.952493190765381, | |
| "eval_runtime": 573.673, | |
| "eval_samples_per_second": 76.022, | |
| "eval_steps_per_second": 38.011, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0023171223271631907, | |
| "grad_norm": 59.9059944152832, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 23.6834, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.002896402908953988, | |
| "eval_loss": 2.91841459274292, | |
| "eval_runtime": 572.3213, | |
| "eval_samples_per_second": 76.202, | |
| "eval_steps_per_second": 38.101, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.0030894964362175874, | |
| "grad_norm": 48.64730453491211, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 23.6425, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.003861870545271984, | |
| "grad_norm": 130.77362060546875, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 24.0095, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.003861870545271984, | |
| "eval_loss": 2.88468599319458, | |
| "eval_runtime": 572.0345, | |
| "eval_samples_per_second": 76.24, | |
| "eval_steps_per_second": 38.12, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.004634244654326381, | |
| "grad_norm": 58.31185531616211, | |
| "learning_rate": 5e-05, | |
| "loss": 21.6947, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.0048273381815899805, | |
| "eval_loss": 2.858558416366577, | |
| "eval_runtime": 574.8235, | |
| "eval_samples_per_second": 75.87, | |
| "eval_steps_per_second": 37.935, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.005406618763380778, | |
| "grad_norm": 42.24747848510742, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 22.0998, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.005792805817907976, | |
| "eval_loss": 2.838266372680664, | |
| "eval_runtime": 573.2821, | |
| "eval_samples_per_second": 76.074, | |
| "eval_steps_per_second": 38.037, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.006178992872435175, | |
| "grad_norm": 36.9980354309082, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 23.1427, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.006758273454225972, | |
| "eval_loss": 2.8305675983428955, | |
| "eval_runtime": 571.9896, | |
| "eval_samples_per_second": 76.246, | |
| "eval_steps_per_second": 38.123, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.0069513669814895715, | |
| "grad_norm": 34.094635009765625, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 23.7975, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.007723741090543968, | |
| "grad_norm": 126.58602142333984, | |
| "learning_rate": 0.0, | |
| "loss": 23.1161, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.007723741090543968, | |
| "eval_loss": 2.8287272453308105, | |
| "eval_runtime": 571.1268, | |
| "eval_samples_per_second": 76.361, | |
| "eval_steps_per_second": 38.181, | |
| "step": 400 | |
| } | |
| ], | |
| "logging_steps": 40, | |
| "max_steps": 400, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "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": 8354189109362688.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |