| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.796812749003984, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01593625498007968, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01593625498007968, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.8925, | |
| "eval_samples_per_second": 12.845, | |
| "eval_steps_per_second": 3.34, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03187250996015936, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04780876494023904, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.06374501992031872, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.99571699711836e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0796812749003984, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.982876141412856e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.09561752988047809, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.11155378486055777, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.931634888554937e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.12749003984063745, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.893332032039701e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.14342629482071714, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1593625498007968, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.791726278367022e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1752988047808765, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.728616793536588e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.19123505976095617, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.20717131474103587, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.578385041664925e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.22310756972111553, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.491548749301997e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.23904382470119523, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2549800796812749, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.295261506157986e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.27091633466135456, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.186184199300464e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.2868525896414343, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.30278884462151395, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.947199994035401e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.3187250996015936, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.817748015645558e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3346613545816733, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.350597609561753, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.540155934270471e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.3665338645418327, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.392544243589427e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.38247011952191234, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.398406374501992, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.081093963579707e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.398406374501992, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.9367, | |
| "eval_samples_per_second": 12.701, | |
| "eval_steps_per_second": 3.302, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.41434262948207173, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.917848237560709e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.4302788844621514, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.44621513944223107, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.577868759557654e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.46215139442231074, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.401782177833148e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.47808764940239046, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4940239043824701, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.03909064496551e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.5099601593625498, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.853176097769229e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.5258964143426295, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.5418326693227091, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.473978262721463e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.5577689243027888, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.281416799501188e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.5737051792828686, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5896414342629482, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.8922008423644624e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.6055776892430279, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.696287243144013e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.6215139442231076, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.6374501992031872, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.303712756855988e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6533864541832669, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.107799157635538e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.6693227091633466, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.6852589641434262, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.718583200498814e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.701195219123506, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.526021737278538e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.7171314741035857, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.7330677290836654, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.146823902230772e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.749003984063745, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.960909355034491e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.7649402390438247, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.7808764940239044, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.598217822166854e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.796812749003984, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.422131240442349e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.796812749003984, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.8692, | |
| "eval_samples_per_second": 12.923, | |
| "eval_steps_per_second": 3.36, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.624057810649088e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |