| { | |
| "best_metric": 10.344432830810547, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.6986899563318777, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.013973799126637555, | |
| "grad_norm": 0.11506249755620956, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3724, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013973799126637555, | |
| "eval_loss": 10.36445426940918, | |
| "eval_runtime": 0.0996, | |
| "eval_samples_per_second": 501.859, | |
| "eval_steps_per_second": 130.483, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02794759825327511, | |
| "grad_norm": 0.1338982731103897, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3681, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04192139737991266, | |
| "grad_norm": 0.14040330052375793, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 10.3664, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05589519650655022, | |
| "grad_norm": 0.1615523397922516, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 10.3676, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06986899563318777, | |
| "grad_norm": 0.17175965011119843, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 10.3638, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08384279475982533, | |
| "grad_norm": 0.176798477768898, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 10.3652, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.09781659388646288, | |
| "grad_norm": 0.18990817666053772, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 10.36, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.11179039301310044, | |
| "grad_norm": 0.198957622051239, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 10.3572, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.125764192139738, | |
| "grad_norm": 0.20558711886405945, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 10.3549, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.13973799126637554, | |
| "grad_norm": 0.21933849155902863, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 10.3524, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1537117903930131, | |
| "grad_norm": 0.2439589649438858, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 10.3508, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.16768558951965065, | |
| "grad_norm": 0.29382824897766113, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 10.3456, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.18165938864628822, | |
| "grad_norm": 0.12970881164073944, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 10.36, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.19563318777292577, | |
| "grad_norm": 0.12605752050876617, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 10.3648, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.2096069868995633, | |
| "grad_norm": 0.14213746786117554, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 10.3612, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.22358078602620088, | |
| "grad_norm": 0.14566223323345184, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 10.3568, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.23755458515283842, | |
| "grad_norm": 0.16291500627994537, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 10.356, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.251528384279476, | |
| "grad_norm": 0.15950094163417816, | |
| "learning_rate": 7.75e-05, | |
| "loss": 10.3543, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.26550218340611353, | |
| "grad_norm": 0.16793178021907806, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 10.3551, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2794759825327511, | |
| "grad_norm": 0.17009131610393524, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 10.3509, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2934497816593886, | |
| "grad_norm": 0.18983396887779236, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 10.3512, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.3074235807860262, | |
| "grad_norm": 0.19557395577430725, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 10.3461, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.32139737991266376, | |
| "grad_norm": 0.23050399124622345, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 10.3408, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.3353711790393013, | |
| "grad_norm": 0.22350473701953888, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 10.3383, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.34934497816593885, | |
| "grad_norm": 0.3139852285385132, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 10.3252, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.34934497816593885, | |
| "eval_loss": 10.34911823272705, | |
| "eval_runtime": 0.1045, | |
| "eval_samples_per_second": 478.469, | |
| "eval_steps_per_second": 124.402, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.36331877729257644, | |
| "grad_norm": 0.11566270887851715, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 10.3624, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.377292576419214, | |
| "grad_norm": 0.12949135899543762, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 10.358, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.39126637554585153, | |
| "grad_norm": 0.140901580452919, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 10.3559, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.4052401746724891, | |
| "grad_norm": 0.14029686152935028, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 10.3539, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.4192139737991266, | |
| "grad_norm": 0.15310536324977875, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 10.3534, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4331877729257642, | |
| "grad_norm": 0.13963443040847778, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 10.3492, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.44716157205240176, | |
| "grad_norm": 0.15991738438606262, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 10.3449, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.4611353711790393, | |
| "grad_norm": 0.16402499377727509, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 10.3439, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.47510917030567684, | |
| "grad_norm": 0.17659306526184082, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 10.3394, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.4890829694323144, | |
| "grad_norm": 0.19355088472366333, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 10.3369, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.503056768558952, | |
| "grad_norm": 0.19989122450351715, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 10.331, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5170305676855895, | |
| "grad_norm": 0.267549604177475, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 10.3273, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5310043668122271, | |
| "grad_norm": 0.11852973699569702, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 10.3526, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5449781659388646, | |
| "grad_norm": 0.11729513853788376, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 10.3553, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5589519650655022, | |
| "grad_norm": 0.11852356791496277, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 10.3543, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5729257641921397, | |
| "grad_norm": 0.12188510596752167, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 10.3498, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.5868995633187772, | |
| "grad_norm": 0.12156735360622406, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 10.353, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.6008733624454149, | |
| "grad_norm": 0.1305505484342575, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 10.3478, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.6148471615720524, | |
| "grad_norm": 0.15021030604839325, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 10.3479, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.62882096069869, | |
| "grad_norm": 0.13688212633132935, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 10.3464, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6427947598253275, | |
| "grad_norm": 0.16216903924942017, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 10.3426, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.6567685589519651, | |
| "grad_norm": 0.15822577476501465, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 10.3397, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.6707423580786026, | |
| "grad_norm": 0.18622951209545135, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 10.336, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.6847161572052402, | |
| "grad_norm": 0.2275187373161316, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 10.3309, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.6986899563318777, | |
| "grad_norm": 0.29126372933387756, | |
| "learning_rate": 1e-05, | |
| "loss": 10.3213, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6986899563318777, | |
| "eval_loss": 10.344432830810547, | |
| "eval_runtime": 0.0972, | |
| "eval_samples_per_second": 514.324, | |
| "eval_steps_per_second": 133.724, | |
| "step": 50 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 42768059596800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |