| { | |
| "best_metric": 0.5886988639831543, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.6597510373443982, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03319502074688797, | |
| "grad_norm": 70.7431869506836, | |
| "learning_rate": 5e-05, | |
| "loss": 23.395, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03319502074688797, | |
| "eval_loss": 1.9604383707046509, | |
| "eval_runtime": 2.3021, | |
| "eval_samples_per_second": 21.719, | |
| "eval_steps_per_second": 5.647, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.06639004149377593, | |
| "grad_norm": 70.47954559326172, | |
| "learning_rate": 0.0001, | |
| "loss": 26.4463, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0995850622406639, | |
| "grad_norm": 81.28753662109375, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 24.136, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.13278008298755187, | |
| "grad_norm": 50.497074127197266, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 18.192, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.16597510373443983, | |
| "grad_norm": 55.77435302734375, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 15.9813, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1991701244813278, | |
| "grad_norm": 58.78676986694336, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 14.8981, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.23236514522821577, | |
| "grad_norm": 44.817684173583984, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 13.3566, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.26556016597510373, | |
| "grad_norm": 33.3582878112793, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 11.3925, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.2987551867219917, | |
| "grad_norm": 22.51363182067871, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 10.1493, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.33195020746887965, | |
| "grad_norm": 26.438974380493164, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 12.8564, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3651452282157676, | |
| "grad_norm": 25.190418243408203, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 12.1554, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.3983402489626556, | |
| "grad_norm": 24.64148712158203, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 12.3792, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.4315352697095436, | |
| "grad_norm": 21.904518127441406, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 12.9168, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.46473029045643155, | |
| "grad_norm": 23.861278533935547, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 11.9802, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.4979253112033195, | |
| "grad_norm": 26.47911262512207, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 12.5379, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.5311203319502075, | |
| "grad_norm": 15.533278465270996, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 7.2533, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.5643153526970954, | |
| "grad_norm": 19.37247657775879, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 9.8797, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.5975103734439834, | |
| "grad_norm": 25.750633239746094, | |
| "learning_rate": 7.75e-05, | |
| "loss": 11.3919, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.6307053941908713, | |
| "grad_norm": 19.59122657775879, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 10.1852, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.6639004149377593, | |
| "grad_norm": 19.977712631225586, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 11.1681, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.6970954356846473, | |
| "grad_norm": 21.2073974609375, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 9.8191, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.7302904564315352, | |
| "grad_norm": 22.94188117980957, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 11.3084, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.7634854771784232, | |
| "grad_norm": 19.7695369720459, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 9.4558, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.7966804979253111, | |
| "grad_norm": 17.488155364990234, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 8.7173, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.8298755186721992, | |
| "grad_norm": 17.16431999206543, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 9.8648, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.8298755186721992, | |
| "eval_loss": 0.6225014328956604, | |
| "eval_runtime": 2.3004, | |
| "eval_samples_per_second": 21.735, | |
| "eval_steps_per_second": 5.651, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.8630705394190872, | |
| "grad_norm": 18.56083869934082, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 10.6655, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.8962655601659751, | |
| "grad_norm": 19.938758850097656, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 9.9155, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.9294605809128631, | |
| "grad_norm": 19.842655181884766, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 11.0424, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.9626556016597511, | |
| "grad_norm": 21.709352493286133, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 11.3728, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.995850622406639, | |
| "grad_norm": 19.83875846862793, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 10.4444, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.0290456431535269, | |
| "grad_norm": 13.077057838439941, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 7.1556, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.062240663900415, | |
| "grad_norm": 14.586568832397461, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 7.0525, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.095435684647303, | |
| "grad_norm": 16.82367706298828, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 9.054, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.1286307053941909, | |
| "grad_norm": 16.17471694946289, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 8.8449, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.161825726141079, | |
| "grad_norm": 15.477469444274902, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 7.4922, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.1950207468879668, | |
| "grad_norm": 18.815563201904297, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 8.4511, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.2282157676348548, | |
| "grad_norm": 20.505046844482422, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 8.0047, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.2614107883817427, | |
| "grad_norm": 20.1456298828125, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 6.5811, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.2946058091286308, | |
| "grad_norm": 16.05089569091797, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 7.1053, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.3278008298755186, | |
| "grad_norm": 18.20804214477539, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 8.6375, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.3609958506224067, | |
| "grad_norm": 17.102148056030273, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 7.8548, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.3941908713692945, | |
| "grad_norm": 20.641029357910156, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 9.3321, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.4273858921161826, | |
| "grad_norm": 18.592660903930664, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 7.6553, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.4605809128630705, | |
| "grad_norm": 21.39291763305664, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 8.5863, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.4937759336099585, | |
| "grad_norm": 19.604318618774414, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 7.3111, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.5269709543568464, | |
| "grad_norm": 14.294530868530273, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 6.0329, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.5601659751037344, | |
| "grad_norm": 16.12917709350586, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 7.6304, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.5933609958506225, | |
| "grad_norm": 16.4742431640625, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 8.4643, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.6265560165975104, | |
| "grad_norm": 17.05834197998047, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 7.9585, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.6597510373443982, | |
| "grad_norm": 17.139780044555664, | |
| "learning_rate": 1e-05, | |
| "loss": 7.7306, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.6597510373443982, | |
| "eval_loss": 0.5886988639831543, | |
| "eval_runtime": 2.3016, | |
| "eval_samples_per_second": 21.724, | |
| "eval_steps_per_second": 5.648, | |
| "step": 50 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.658021338284032e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |