| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 260, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.38461538461538464, | |
| "grad_norm": 2.784594774246216, | |
| "learning_rate": 0.00015384615384615385, | |
| "loss": 0.9669, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.7692307692307693, | |
| "grad_norm": 0.7259019017219543, | |
| "learning_rate": 0.00019960391807762463, | |
| "loss": 0.2826, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.1538461538461537, | |
| "grad_norm": 0.6641652584075928, | |
| "learning_rate": 0.00019767147448363366, | |
| "loss": 0.1705, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.5384615384615383, | |
| "grad_norm": 0.6633732318878174, | |
| "learning_rate": 0.00019416109981763526, | |
| "loss": 0.1269, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.9230769230769231, | |
| "grad_norm": 0.8556098937988281, | |
| "learning_rate": 0.0001891295059219472, | |
| "loss": 0.1146, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.3076923076923075, | |
| "grad_norm": 0.72641521692276, | |
| "learning_rate": 0.00018265798068939294, | |
| "loss": 0.1052, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.6923076923076925, | |
| "grad_norm": 0.6073856949806213, | |
| "learning_rate": 0.00017485107481711012, | |
| "loss": 0.093, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 3.076923076923077, | |
| "grad_norm": 0.7456368207931519, | |
| "learning_rate": 0.00016583491273822765, | |
| "loss": 0.082, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.4615384615384617, | |
| "grad_norm": 0.7613458037376404, | |
| "learning_rate": 0.00015575515501914668, | |
| "loss": 0.0777, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.8461538461538463, | |
| "grad_norm": 0.24724791944026947, | |
| "learning_rate": 0.00014477464514090743, | |
| "loss": 0.0752, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 4.230769230769231, | |
| "grad_norm": 0.5276409983634949, | |
| "learning_rate": 0.00013307077868205487, | |
| "loss": 0.0668, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.615384615384615, | |
| "grad_norm": 0.4655822217464447, | |
| "learning_rate": 0.00012083263740515765, | |
| "loss": 0.0662, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 0.33128008246421814, | |
| "learning_rate": 0.00010825793454723325, | |
| "loss": 0.056, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 5.384615384615385, | |
| "grad_norm": 0.2525981068611145, | |
| "learning_rate": 9.5549820664426e-05, | |
| "loss": 0.0591, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 5.769230769230769, | |
| "grad_norm": 0.44852906465530396, | |
| "learning_rate": 8.291360163409978e-05, | |
| "loss": 0.0613, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 6.153846153846154, | |
| "grad_norm": 0.3840689957141876, | |
| "learning_rate": 7.05534218366488e-05, | |
| "loss": 0.0548, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 6.538461538461538, | |
| "grad_norm": 0.35870087146759033, | |
| "learning_rate": 5.8668966101867005e-05, | |
| "loss": 0.0499, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 6.923076923076923, | |
| "grad_norm": 0.4101502597332001, | |
| "learning_rate": 4.745223370156797e-05, | |
| "loss": 0.0441, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 7.3076923076923075, | |
| "grad_norm": 0.20243866741657257, | |
| "learning_rate": 3.708443650620206e-05, | |
| "loss": 0.0492, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 7.6923076923076925, | |
| "grad_norm": 0.24904510378837585, | |
| "learning_rate": 2.773307141728867e-05, | |
| "loss": 0.0476, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 8.076923076923077, | |
| "grad_norm": 0.24507194757461548, | |
| "learning_rate": 1.9549214371968004e-05, | |
| "loss": 0.0496, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 8.461538461538462, | |
| "grad_norm": 0.19474808871746063, | |
| "learning_rate": 1.2665079636369969e-05, | |
| "loss": 0.0472, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 8.846153846153847, | |
| "grad_norm": 0.28991830348968506, | |
| "learning_rate": 7.191883818625189e-06, | |
| "loss": 0.0452, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 9.23076923076923, | |
| "grad_norm": 0.25674358010292053, | |
| "learning_rate": 3.2180491094465415e-06, | |
| "loss": 0.045, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 9.615384615384615, | |
| "grad_norm": 0.22138427197933197, | |
| "learning_rate": 8.077747778200473e-07, | |
| "loss": 0.0405, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 0.26071739196777344, | |
| "learning_rate": 0.0, | |
| "loss": 0.0449, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 260, | |
| "total_flos": 3.84172166657952e+16, | |
| "train_loss": 0.11238977611064911, | |
| "train_runtime": 340.1603, | |
| "train_samples_per_second": 48.918, | |
| "train_steps_per_second": 0.764 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 260, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 10000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.84172166657952e+16, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |