| { | |
| "best_metric": 11.913727760314941, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.7421150278293135, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.029684601113172542, | |
| "grad_norm": 0.08440621197223663, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9231, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.029684601113172542, | |
| "eval_loss": 11.920661926269531, | |
| "eval_runtime": 0.1771, | |
| "eval_samples_per_second": 282.363, | |
| "eval_steps_per_second": 73.414, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.059369202226345084, | |
| "grad_norm": 0.07143169641494751, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9261, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.08905380333951762, | |
| "grad_norm": 0.07815750688314438, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 11.9269, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.11873840445269017, | |
| "grad_norm": 0.09560947865247726, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 11.9222, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.14842300556586271, | |
| "grad_norm": 0.0957864299416542, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 11.9285, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.17810760667903525, | |
| "grad_norm": 0.09346175938844681, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 11.934, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.2077922077922078, | |
| "grad_norm": 0.11279693245887756, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 11.9301, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.23747680890538034, | |
| "grad_norm": 0.11731767654418945, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 11.9298, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.26716141001855287, | |
| "grad_norm": 0.07877083867788315, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 11.9248, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.29684601113172543, | |
| "grad_norm": 0.045284539461135864, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 11.9318, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.32653061224489793, | |
| "grad_norm": 0.07036509364843369, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 11.9297, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.3562152133580705, | |
| "grad_norm": 0.07343818247318268, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 11.9276, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.38589981447124305, | |
| "grad_norm": 0.08361507207155228, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 11.9237, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.4155844155844156, | |
| "grad_norm": 0.10278163850307465, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 11.9262, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.4452690166975881, | |
| "grad_norm": 0.10730006545782089, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 11.9315, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.4749536178107607, | |
| "grad_norm": 0.11636124551296234, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 11.9271, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.5046382189239332, | |
| "grad_norm": 0.0831388458609581, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 11.9265, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.5343228200371057, | |
| "grad_norm": 0.06362044811248779, | |
| "learning_rate": 7.75e-05, | |
| "loss": 11.9248, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.5640074211502782, | |
| "grad_norm": 0.0942530408501625, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 11.9219, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.5936920222634509, | |
| "grad_norm": 0.0732453465461731, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 11.9212, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.6233766233766234, | |
| "grad_norm": 0.11220160126686096, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 11.9295, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.6530612244897959, | |
| "grad_norm": 0.10498771071434021, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 11.9278, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.6827458256029685, | |
| "grad_norm": 0.124515600502491, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 11.9253, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.712430426716141, | |
| "grad_norm": 0.1343991756439209, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 11.9325, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.7421150278293135, | |
| "grad_norm": 0.12157789617776871, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 11.9332, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.7421150278293135, | |
| "eval_loss": 11.913727760314941, | |
| "eval_runtime": 0.1789, | |
| "eval_samples_per_second": 279.536, | |
| "eval_steps_per_second": 72.679, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "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": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 521247129600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |