| { | |
| "best_metric": 1.138919711112976, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.1869436201780414, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02373887240356083, | |
| "grad_norm": 1.8149988651275635, | |
| "learning_rate": 5e-05, | |
| "loss": 2.3628, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02373887240356083, | |
| "eval_loss": 4.49245548248291, | |
| "eval_runtime": 3.8602, | |
| "eval_samples_per_second": 12.953, | |
| "eval_steps_per_second": 3.368, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04747774480712166, | |
| "grad_norm": 1.940530776977539, | |
| "learning_rate": 0.0001, | |
| "loss": 2.6657, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0712166172106825, | |
| "grad_norm": 2.166443109512329, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 2.7295, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.09495548961424333, | |
| "grad_norm": 2.5491065979003906, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 2.7157, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.11869436201780416, | |
| "grad_norm": 2.428069591522217, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 2.5142, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.142433234421365, | |
| "grad_norm": 2.2948455810546875, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2.4517, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.1661721068249258, | |
| "grad_norm": 2.072003126144409, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 2.5398, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.18991097922848665, | |
| "grad_norm": 2.7198984622955322, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 2.6305, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.21364985163204747, | |
| "grad_norm": 2.0513155460357666, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 2.4877, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.23738872403560832, | |
| "grad_norm": 2.4049549102783203, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 2.6521, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.26112759643916916, | |
| "grad_norm": 3.4100911617279053, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.8284, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.28486646884273, | |
| "grad_norm": 2.2710535526275635, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.8157, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.3086053412462908, | |
| "grad_norm": 1.7425583600997925, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.7151, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.3323442136498516, | |
| "grad_norm": 1.1660573482513428, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.7164, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.3560830860534125, | |
| "grad_norm": 1.1513049602508545, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 1.5474, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.3798219584569733, | |
| "grad_norm": 1.3932960033416748, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.7311, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.4035608308605341, | |
| "grad_norm": 1.4897091388702393, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.6791, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.42729970326409494, | |
| "grad_norm": 1.5472290515899658, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.8346, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.45103857566765576, | |
| "grad_norm": 1.7270818948745728, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.8753, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.47477744807121663, | |
| "grad_norm": 1.8078877925872803, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.978, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.49851632047477745, | |
| "grad_norm": 2.4212305545806885, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 2.1005, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.5222551928783383, | |
| "grad_norm": 2.1638898849487305, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.3877, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.5459940652818991, | |
| "grad_norm": 1.6141053438186646, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 1.3306, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.56973293768546, | |
| "grad_norm": 1.411310076713562, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.2576, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.5934718100890207, | |
| "grad_norm": 1.2712687253952026, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 1.2808, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5934718100890207, | |
| "eval_loss": 1.657345175743103, | |
| "eval_runtime": 3.4793, | |
| "eval_samples_per_second": 14.371, | |
| "eval_steps_per_second": 3.736, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.6172106824925816, | |
| "grad_norm": 1.33504056930542, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 1.285, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.6409495548961425, | |
| "grad_norm": 1.3836376667022705, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 1.3445, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.6646884272997032, | |
| "grad_norm": 1.4555468559265137, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 1.3612, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.6884272997032641, | |
| "grad_norm": 1.595334529876709, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 1.4551, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.712166172106825, | |
| "grad_norm": 1.677962064743042, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 1.1477, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.7359050445103857, | |
| "grad_norm": 2.268947124481201, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 1.4105, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.7596439169139466, | |
| "grad_norm": 1.8075306415557861, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 1.1708, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.7833827893175074, | |
| "grad_norm": 1.3961358070373535, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 1.051, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.8071216617210683, | |
| "grad_norm": 1.2634520530700684, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 1.0955, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.8308605341246291, | |
| "grad_norm": 1.3281856775283813, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.9206, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.8545994065281899, | |
| "grad_norm": 1.541483998298645, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 1.0296, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.8783382789317508, | |
| "grad_norm": 1.5500856637954712, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 1.1397, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.9020771513353115, | |
| "grad_norm": 1.671694278717041, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 1.0177, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.9258160237388724, | |
| "grad_norm": 1.5672807693481445, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 1.0509, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.9495548961424333, | |
| "grad_norm": 1.7088992595672607, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.9209, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.973293768545994, | |
| "grad_norm": 2.0631930828094482, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 1.0925, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.9970326409495549, | |
| "grad_norm": 3.0031752586364746, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 1.3225, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.0207715133531157, | |
| "grad_norm": 5.280531406402588, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 2.201, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.0445103857566767, | |
| "grad_norm": 1.4850263595581055, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.9308, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.0682492581602374, | |
| "grad_norm": 1.2865294218063354, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.8719, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.0919881305637982, | |
| "grad_norm": 1.3108830451965332, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.8323, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.115727002967359, | |
| "grad_norm": 1.5480964183807373, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.9578, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.13946587537092, | |
| "grad_norm": 1.6136928796768188, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.9948, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.1632047477744807, | |
| "grad_norm": 1.52801513671875, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.8489, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.1869436201780414, | |
| "grad_norm": 1.6096166372299194, | |
| "learning_rate": 1e-05, | |
| "loss": 0.9536, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.1869436201780414, | |
| "eval_loss": 1.138919711112976, | |
| "eval_runtime": 3.4871, | |
| "eval_samples_per_second": 14.338, | |
| "eval_steps_per_second": 3.728, | |
| "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": 5.968083617316864e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |