| { | |
| "best_metric": 1.146162748336792, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.4071246819338422, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008142493638676845, | |
| "grad_norm": 0.7831802368164062, | |
| "learning_rate": 5e-05, | |
| "loss": 2.1777, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008142493638676845, | |
| "eval_loss": 2.6585562229156494, | |
| "eval_runtime": 3.179, | |
| "eval_samples_per_second": 15.728, | |
| "eval_steps_per_second": 4.089, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01628498727735369, | |
| "grad_norm": 0.9065176248550415, | |
| "learning_rate": 0.0001, | |
| "loss": 2.1561, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.024427480916030534, | |
| "grad_norm": 0.9400052428245544, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 2.1895, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03256997455470738, | |
| "grad_norm": 1.0230543613433838, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 2.0533, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04071246819338423, | |
| "grad_norm": 0.9375590085983276, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 1.7889, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.04885496183206107, | |
| "grad_norm": 0.684062659740448, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.5627, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.056997455470737916, | |
| "grad_norm": 0.6688232421875, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.324, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.06513994910941476, | |
| "grad_norm": 0.7182115912437439, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.2985, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0732824427480916, | |
| "grad_norm": 0.5141118764877319, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.1464, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.08142493638676845, | |
| "grad_norm": 0.495283305644989, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.158, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08956743002544529, | |
| "grad_norm": 0.5461936593055725, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.0639, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.09770992366412214, | |
| "grad_norm": 0.6632602214813232, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.9866, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.10585241730279898, | |
| "grad_norm": 0.5742640495300293, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.4373, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.11399491094147583, | |
| "grad_norm": 0.6885349750518799, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.4673, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.12213740458015267, | |
| "grad_norm": 0.5408735871315002, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 1.366, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.13027989821882952, | |
| "grad_norm": 0.4258224070072174, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.3541, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.13842239185750635, | |
| "grad_norm": 0.47161340713500977, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.3002, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.1465648854961832, | |
| "grad_norm": 0.4001603126525879, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.2064, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.15470737913486005, | |
| "grad_norm": 0.5180523991584778, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.2031, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.1628498727735369, | |
| "grad_norm": 0.4585513472557068, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.1297, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.17099236641221374, | |
| "grad_norm": 0.42557641863822937, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 1.1331, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.17913486005089058, | |
| "grad_norm": 0.36922454833984375, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.1081, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.18727735368956744, | |
| "grad_norm": 0.3761698007583618, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 1.0548, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.19541984732824427, | |
| "grad_norm": 0.4325619637966156, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.99, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2035623409669211, | |
| "grad_norm": 0.4425663352012634, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.7986, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2035623409669211, | |
| "eval_loss": 1.1732544898986816, | |
| "eval_runtime": 3.2358, | |
| "eval_samples_per_second": 15.452, | |
| "eval_steps_per_second": 4.018, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.21170483460559797, | |
| "grad_norm": 0.47239935398101807, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 1.4729, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.2198473282442748, | |
| "grad_norm": 0.5448411703109741, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 1.4152, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.22798982188295167, | |
| "grad_norm": 0.4144279658794403, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 1.3087, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.2361323155216285, | |
| "grad_norm": 0.43465501070022583, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 1.2266, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.24427480916030533, | |
| "grad_norm": 0.3278026282787323, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 1.1868, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.25241730279898217, | |
| "grad_norm": 0.32642263174057007, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 1.178, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.26055979643765903, | |
| "grad_norm": 0.30465167760849, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 1.2446, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.2687022900763359, | |
| "grad_norm": 0.3416752815246582, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 1.0719, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.2768447837150127, | |
| "grad_norm": 0.34141701459884644, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 1.0569, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.28498727735368956, | |
| "grad_norm": 0.417844295501709, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 1.022, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.2931297709923664, | |
| "grad_norm": 0.4493633806705475, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 1.0213, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.30127226463104323, | |
| "grad_norm": 0.5586698055267334, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.8832, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.3094147582697201, | |
| "grad_norm": 0.3204140067100525, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 1.3685, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.31755725190839695, | |
| "grad_norm": 0.24755215644836426, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 1.3834, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.3256997455470738, | |
| "grad_norm": 0.2518017888069153, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 1.3252, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3338422391857506, | |
| "grad_norm": 0.2561423182487488, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 1.2411, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.3419847328244275, | |
| "grad_norm": 0.2716136872768402, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 1.2071, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.35012722646310435, | |
| "grad_norm": 0.2563495337963104, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 1.1695, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.35826972010178115, | |
| "grad_norm": 0.2868095934391022, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 1.2058, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.366412213740458, | |
| "grad_norm": 0.30007317662239075, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 1.125, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.3745547073791349, | |
| "grad_norm": 0.29985371232032776, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 1.0624, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.3826972010178117, | |
| "grad_norm": 0.31994521617889404, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 1.0312, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.39083969465648855, | |
| "grad_norm": 0.32543620467185974, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.9651, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.3989821882951654, | |
| "grad_norm": 0.3547946512699127, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.8825, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.4071246819338422, | |
| "grad_norm": 0.38324517011642456, | |
| "learning_rate": 1e-05, | |
| "loss": 0.8323, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4071246819338422, | |
| "eval_loss": 1.146162748336792, | |
| "eval_runtime": 3.2267, | |
| "eval_samples_per_second": 15.496, | |
| "eval_steps_per_second": 4.029, | |
| "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": 5.624057810649088e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |