| { | |
| "best_metric": 0.00033007311867550015, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.031773770752244024, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0012709508300897609, | |
| "grad_norm": 1.0162434577941895, | |
| "learning_rate": 5e-05, | |
| "loss": 0.2522, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012709508300897609, | |
| "eval_loss": 1.392747402191162, | |
| "eval_runtime": 2.0621, | |
| "eval_samples_per_second": 24.247, | |
| "eval_steps_per_second": 6.304, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0025419016601795218, | |
| "grad_norm": 1.3236790895462036, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3358, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.003812852490269283, | |
| "grad_norm": 1.2251592874526978, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 0.3311, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0050838033203590436, | |
| "grad_norm": 0.8695217967033386, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 0.2192, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006354754150448804, | |
| "grad_norm": 0.9969640970230103, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 0.1351, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.007625704980538566, | |
| "grad_norm": 0.34964844584465027, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 0.0776, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.008896655810628326, | |
| "grad_norm": 0.9730827212333679, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 0.0748, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.010167606640718087, | |
| "grad_norm": 0.7326748371124268, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.0509, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.011438557470807848, | |
| "grad_norm": 0.33750614523887634, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.0453, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.012709508300897608, | |
| "grad_norm": 0.5372080206871033, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.0347, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01398045913098737, | |
| "grad_norm": 0.6136100888252258, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.0412, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.015251409961077132, | |
| "grad_norm": 0.21363592147827148, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.0122, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.016522360791166892, | |
| "grad_norm": 0.497074693441391, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.0329, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.017793311621256653, | |
| "grad_norm": 0.2652136981487274, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.0223, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.019064262451346414, | |
| "grad_norm": 0.23249875009059906, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.0084, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.020335213281436174, | |
| "grad_norm": 0.09723572432994843, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.0037, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.021606164111525935, | |
| "grad_norm": 0.17268534004688263, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.0052, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.022877114941615696, | |
| "grad_norm": 0.09277069568634033, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.0019, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.024148065771705456, | |
| "grad_norm": 0.0783044844865799, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.0016, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.025419016601795217, | |
| "grad_norm": 0.14670029282569885, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.0014, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.026689967431884978, | |
| "grad_norm": 0.3589989244937897, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.0018, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.02796091826197474, | |
| "grad_norm": 0.15043768286705017, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.002, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.029231869092064502, | |
| "grad_norm": 0.03329368680715561, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.0007, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.030502819922154263, | |
| "grad_norm": 0.23992179334163666, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.004, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.031773770752244024, | |
| "grad_norm": 0.16787421703338623, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.003, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.031773770752244024, | |
| "eval_loss": 0.00033007311867550015, | |
| "eval_runtime": 2.0826, | |
| "eval_samples_per_second": 24.008, | |
| "eval_steps_per_second": 6.242, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8.1240447254528e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |