| { | |
| "best_metric": 0.0008296275627799332, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.5979073243647235, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02391629297458894, | |
| "grad_norm": 0.5000861883163452, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0601, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02391629297458894, | |
| "eval_loss": 0.1901516318321228, | |
| "eval_runtime": 4.4167, | |
| "eval_samples_per_second": 11.321, | |
| "eval_steps_per_second": 2.943, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04783258594917788, | |
| "grad_norm": 0.9140944480895996, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0932, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.07174887892376682, | |
| "grad_norm": 0.46170955896377563, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 0.0591, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.09566517189835576, | |
| "grad_norm": 0.21453425288200378, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 0.0169, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.11958146487294469, | |
| "grad_norm": 0.10587561875581741, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 0.016, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.14349775784753363, | |
| "grad_norm": 0.10676142573356628, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 0.0105, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.16741405082212257, | |
| "grad_norm": 0.09449061751365662, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 0.0077, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.19133034379671152, | |
| "grad_norm": 0.12052935361862183, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.0112, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.21524663677130046, | |
| "grad_norm": 0.08228503167629242, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.0058, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.23916292974588937, | |
| "grad_norm": 0.11513187736272812, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.0068, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.26307922272047835, | |
| "grad_norm": 0.09261412918567657, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.0168, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.28699551569506726, | |
| "grad_norm": 0.051280997693538666, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.0034, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.3109118086696562, | |
| "grad_norm": 0.03256010264158249, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.0031, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.33482810164424515, | |
| "grad_norm": 0.04068237543106079, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.0025, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.35874439461883406, | |
| "grad_norm": 0.03880110755562782, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.0025, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.38266068759342303, | |
| "grad_norm": 0.025225255638360977, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.0019, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.40657698056801195, | |
| "grad_norm": 0.045391716063022614, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.002, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.4304932735426009, | |
| "grad_norm": 0.03613187372684479, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.0014, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.45440956651718983, | |
| "grad_norm": 0.03006964921951294, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.0013, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.47832585949177875, | |
| "grad_norm": 0.039465390145778656, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.0016, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.5022421524663677, | |
| "grad_norm": 0.05139923840761185, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.0051, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.5261584454409567, | |
| "grad_norm": 0.03245363384485245, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.001, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.5500747384155455, | |
| "grad_norm": 0.023098977282643318, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.0009, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.5739910313901345, | |
| "grad_norm": 0.02532481960952282, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.0008, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.5979073243647235, | |
| "grad_norm": 0.022385241463780403, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.0008, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5979073243647235, | |
| "eval_loss": 0.0008296275627799332, | |
| "eval_runtime": 4.5093, | |
| "eval_samples_per_second": 11.088, | |
| "eval_steps_per_second": 2.883, | |
| "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": 3.390293917554442e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |