| { | |
| "best_metric": 0.10530552268028259, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.556420233463035, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0311284046692607, | |
| "grad_norm": 9.926247596740723, | |
| "learning_rate": 5e-05, | |
| "loss": 5.2342, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0311284046692607, | |
| "eval_loss": 5.72003173828125, | |
| "eval_runtime": 3.8173, | |
| "eval_samples_per_second": 13.098, | |
| "eval_steps_per_second": 3.406, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0622568093385214, | |
| "grad_norm": 10.351175308227539, | |
| "learning_rate": 0.0001, | |
| "loss": 5.3259, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0933852140077821, | |
| "grad_norm": 9.876289367675781, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 4.906, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1245136186770428, | |
| "grad_norm": 6.973885536193848, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 3.1993, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.1556420233463035, | |
| "grad_norm": 6.595519542694092, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 2.0786, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1867704280155642, | |
| "grad_norm": 7.392065048217773, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.1917, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.2178988326848249, | |
| "grad_norm": 5.252386569976807, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 0.502, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.2490272373540856, | |
| "grad_norm": 3.8015263080596924, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.2918, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.2801556420233463, | |
| "grad_norm": 6.925857067108154, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.4391, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.311284046692607, | |
| "grad_norm": 5.934936046600342, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.4491, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3424124513618677, | |
| "grad_norm": 3.8128702640533447, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.3788, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.3735408560311284, | |
| "grad_norm": 2.8401427268981934, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.3058, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.4046692607003891, | |
| "grad_norm": 2.2815659046173096, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.2793, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.4357976653696498, | |
| "grad_norm": 1.993712306022644, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.2575, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.4669260700389105, | |
| "grad_norm": 2.533045530319214, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.2593, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.4980544747081712, | |
| "grad_norm": 2.374345302581787, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.2229, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.5291828793774319, | |
| "grad_norm": 2.1960155963897705, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.2379, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.5603112840466926, | |
| "grad_norm": 1.8646379709243774, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.2132, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.5914396887159533, | |
| "grad_norm": 1.9866734743118286, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.2288, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.622568093385214, | |
| "grad_norm": 1.3293571472167969, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.1679, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.6536964980544747, | |
| "grad_norm": 1.063161849975586, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.1783, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.6848249027237354, | |
| "grad_norm": 1.157092571258545, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.1473, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.7159533073929961, | |
| "grad_norm": 1.2641205787658691, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.17, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.7470817120622568, | |
| "grad_norm": 1.6932222843170166, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.2098, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.7782101167315175, | |
| "grad_norm": 2.0876078605651855, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.1764, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.7782101167315175, | |
| "eval_loss": 0.14145001769065857, | |
| "eval_runtime": 3.4979, | |
| "eval_samples_per_second": 14.294, | |
| "eval_steps_per_second": 3.716, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.8093385214007782, | |
| "grad_norm": 2.2419772148132324, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.1745, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.8404669260700389, | |
| "grad_norm": 1.8178470134735107, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.1717, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.8715953307392996, | |
| "grad_norm": 1.2768809795379639, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.1504, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.9027237354085603, | |
| "grad_norm": 0.9017437696456909, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.159, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.933852140077821, | |
| "grad_norm": 1.263572096824646, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.1653, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.9649805447470817, | |
| "grad_norm": 1.1224571466445923, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.1611, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.9961089494163424, | |
| "grad_norm": 1.5271551609039307, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.1742, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.027237354085603, | |
| "grad_norm": 2.334810733795166, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.228, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.0583657587548638, | |
| "grad_norm": 0.7964612245559692, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.1209, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.0894941634241244, | |
| "grad_norm": 0.8177843689918518, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.1245, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.1206225680933852, | |
| "grad_norm": 0.7340578436851501, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.1294, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.1517509727626458, | |
| "grad_norm": 0.859123170375824, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.1388, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.1828793774319066, | |
| "grad_norm": 0.758919358253479, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.1088, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.2140077821011672, | |
| "grad_norm": 0.7981888651847839, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.1256, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.245136186770428, | |
| "grad_norm": 0.8933906555175781, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.1213, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.2762645914396886, | |
| "grad_norm": 0.7495871186256409, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.0941, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.3073929961089494, | |
| "grad_norm": 0.6591278910636902, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.0954, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.3385214007782102, | |
| "grad_norm": 0.6582584381103516, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.0985, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.3696498054474708, | |
| "grad_norm": 0.6135019063949585, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.1084, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.4007782101167314, | |
| "grad_norm": 0.857144296169281, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.0981, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.4319066147859922, | |
| "grad_norm": 1.0293967723846436, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.1399, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.463035019455253, | |
| "grad_norm": 0.947338879108429, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.1457, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.4941634241245136, | |
| "grad_norm": 1.044509768486023, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.1132, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.5252918287937742, | |
| "grad_norm": 0.7475258708000183, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.0992, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.556420233463035, | |
| "grad_norm": 0.8056252002716064, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0983, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.556420233463035, | |
| "eval_loss": 0.10530552268028259, | |
| "eval_runtime": 3.4776, | |
| "eval_samples_per_second": 14.378, | |
| "eval_steps_per_second": 3.738, | |
| "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 | |
| } | |