{ "best_metric": 1.733738899230957, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.44543429844098, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.008908685968819599, "grad_norm": 0.18823038041591644, "learning_rate": 5e-05, "loss": 1.7416, "step": 1 }, { "epoch": 0.008908685968819599, "eval_loss": 3.0787603855133057, "eval_runtime": 2.9044, "eval_samples_per_second": 17.215, "eval_steps_per_second": 4.476, "step": 1 }, { "epoch": 0.017817371937639197, "grad_norm": 0.3004969656467438, "learning_rate": 0.0001, "loss": 1.9615, "step": 2 }, { "epoch": 0.026726057906458798, "grad_norm": 0.353916734457016, "learning_rate": 9.990365154573717e-05, "loss": 1.9986, "step": 3 }, { "epoch": 0.035634743875278395, "grad_norm": 0.5635604858398438, "learning_rate": 9.961501876182148e-05, "loss": 2.1622, "step": 4 }, { "epoch": 0.044543429844097995, "grad_norm": 0.9342576265335083, "learning_rate": 9.913533761814537e-05, "loss": 2.1846, "step": 5 }, { "epoch": 0.053452115812917596, "grad_norm": 0.8338181376457214, "learning_rate": 9.846666218300807e-05, "loss": 2.1917, "step": 6 }, { "epoch": 0.062360801781737196, "grad_norm": 0.8374766707420349, "learning_rate": 9.761185582727977e-05, "loss": 2.2393, "step": 7 }, { "epoch": 0.07126948775055679, "grad_norm": 1.0305372476577759, "learning_rate": 9.657457896300791e-05, "loss": 2.0463, "step": 8 }, { "epoch": 0.0801781737193764, "grad_norm": 1.6088753938674927, "learning_rate": 9.535927336897098e-05, "loss": 2.0633, "step": 9 }, { "epoch": 0.08908685968819599, "grad_norm": 2.118065595626831, "learning_rate": 9.397114317029975e-05, "loss": 2.0922, "step": 10 }, { "epoch": 0.09799554565701558, "grad_norm": 3.5291800498962402, "learning_rate": 9.241613255361455e-05, "loss": 2.1087, "step": 11 }, { "epoch": 0.10690423162583519, "grad_norm": 5.3907341957092285, "learning_rate": 9.070090031310558e-05, "loss": 2.435, "step": 12 }, { "epoch": 0.11581291759465479, "grad_norm": 1.941472053527832, "learning_rate": 8.883279133655399e-05, "loss": 1.8809, "step": 13 }, { "epoch": 0.12472160356347439, "grad_norm": 2.509364128112793, "learning_rate": 8.681980515339464e-05, "loss": 1.8533, "step": 14 }, { "epoch": 0.133630289532294, "grad_norm": 2.623279571533203, "learning_rate": 8.467056167950311e-05, "loss": 1.9515, "step": 15 }, { "epoch": 0.14253897550111358, "grad_norm": 2.138512134552002, "learning_rate": 8.239426430539243e-05, "loss": 1.9534, "step": 16 }, { "epoch": 0.1514476614699332, "grad_norm": 0.8622003793716431, "learning_rate": 8.000066048588211e-05, "loss": 2.0927, "step": 17 }, { "epoch": 0.1603563474387528, "grad_norm": 0.9450668096542358, "learning_rate": 7.75e-05, "loss": 1.9761, "step": 18 }, { "epoch": 0.16926503340757237, "grad_norm": 1.4933154582977295, "learning_rate": 7.490299105985507e-05, "loss": 2.032, "step": 19 }, { "epoch": 0.17817371937639198, "grad_norm": 1.7936705350875854, "learning_rate": 7.222075445642904e-05, "loss": 1.9708, "step": 20 }, { "epoch": 0.1870824053452116, "grad_norm": 1.8577200174331665, "learning_rate": 6.946477593864228e-05, "loss": 1.8581, "step": 21 }, { "epoch": 0.19599109131403117, "grad_norm": 2.2038028240203857, "learning_rate": 6.664685702961344e-05, "loss": 1.722, "step": 22 }, { "epoch": 0.20489977728285078, "grad_norm": 3.3114798069000244, "learning_rate": 6.377906449072578e-05, "loss": 1.9172, "step": 23 }, { "epoch": 0.21380846325167038, "grad_norm": 3.0929205417633057, "learning_rate": 6.087367864990233e-05, "loss": 1.5001, "step": 24 }, { "epoch": 0.22271714922049, "grad_norm": 12.224762916564941, "learning_rate": 5.794314081535644e-05, "loss": 2.6672, "step": 25 }, { "epoch": 0.22271714922049, "eval_loss": 1.867378830909729, "eval_runtime": 0.8491, "eval_samples_per_second": 58.887, "eval_steps_per_second": 15.311, "step": 25 }, { "epoch": 0.23162583518930957, "grad_norm": 0.33165210485458374, "learning_rate": 5.500000000000001e-05, "loss": 1.5981, "step": 26 }, { "epoch": 0.24053452115812918, "grad_norm": 0.7488612532615662, "learning_rate": 5.205685918464356e-05, "loss": 1.6941, "step": 27 }, { "epoch": 0.24944320712694878, "grad_norm": 0.861705482006073, "learning_rate": 4.912632135009769e-05, "loss": 1.9993, "step": 28 }, { "epoch": 0.2583518930957684, "grad_norm": 1.0878539085388184, "learning_rate": 4.6220935509274235e-05, "loss": 1.8833, "step": 29 }, { "epoch": 0.267260579064588, "grad_norm": 0.8501808047294617, "learning_rate": 4.3353142970386564e-05, "loss": 1.9919, "step": 30 }, { "epoch": 0.27616926503340755, "grad_norm": 0.669116735458374, "learning_rate": 4.053522406135775e-05, "loss": 2.0127, "step": 31 }, { "epoch": 0.28507795100222716, "grad_norm": 0.5088751316070557, "learning_rate": 3.777924554357096e-05, "loss": 1.9827, "step": 32 }, { "epoch": 0.29398663697104677, "grad_norm": 0.4590938687324524, "learning_rate": 3.509700894014496e-05, "loss": 1.8001, "step": 33 }, { "epoch": 0.3028953229398664, "grad_norm": 0.6814666986465454, "learning_rate": 3.250000000000001e-05, "loss": 1.8414, "step": 34 }, { "epoch": 0.311804008908686, "grad_norm": 0.9811885356903076, "learning_rate": 2.9999339514117912e-05, "loss": 1.7625, "step": 35 }, { "epoch": 0.3207126948775056, "grad_norm": 1.4614307880401611, "learning_rate": 2.760573569460757e-05, "loss": 1.6748, "step": 36 }, { "epoch": 0.32962138084632514, "grad_norm": 3.0398764610290527, "learning_rate": 2.53294383204969e-05, "loss": 1.637, "step": 37 }, { "epoch": 0.33853006681514475, "grad_norm": 0.33289289474487305, "learning_rate": 2.3180194846605367e-05, "loss": 1.6686, "step": 38 }, { "epoch": 0.34743875278396436, "grad_norm": 0.26579251885414124, "learning_rate": 2.1167208663446025e-05, "loss": 1.4826, "step": 39 }, { "epoch": 0.35634743875278396, "grad_norm": 0.3095352053642273, "learning_rate": 1.9299099686894423e-05, "loss": 1.7352, "step": 40 }, { "epoch": 0.36525612472160357, "grad_norm": 0.3182210922241211, "learning_rate": 1.758386744638546e-05, "loss": 1.7885, "step": 41 }, { "epoch": 0.3741648106904232, "grad_norm": 0.26366835832595825, "learning_rate": 1.602885682970026e-05, "loss": 1.9453, "step": 42 }, { "epoch": 0.3830734966592428, "grad_norm": 0.3004477620124817, "learning_rate": 1.464072663102903e-05, "loss": 1.8818, "step": 43 }, { "epoch": 0.39198218262806234, "grad_norm": 0.33916527032852173, "learning_rate": 1.3425421036992098e-05, "loss": 1.9296, "step": 44 }, { "epoch": 0.40089086859688194, "grad_norm": 0.3385569453239441, "learning_rate": 1.2388144172720251e-05, "loss": 1.8835, "step": 45 }, { "epoch": 0.40979955456570155, "grad_norm": 0.38246041536331177, "learning_rate": 1.1533337816991932e-05, "loss": 1.8184, "step": 46 }, { "epoch": 0.41870824053452116, "grad_norm": 0.5052685737609863, "learning_rate": 1.0864662381854632e-05, "loss": 1.7671, "step": 47 }, { "epoch": 0.42761692650334077, "grad_norm": 0.7465808987617493, "learning_rate": 1.0384981238178534e-05, "loss": 1.8135, "step": 48 }, { "epoch": 0.4365256124721604, "grad_norm": 1.7329742908477783, "learning_rate": 1.0096348454262845e-05, "loss": 1.6015, "step": 49 }, { "epoch": 0.44543429844098, "grad_norm": 4.2306718826293945, "learning_rate": 1e-05, "loss": 2.0812, "step": 50 }, { "epoch": 0.44543429844098, "eval_loss": 1.733738899230957, "eval_runtime": 0.8419, "eval_samples_per_second": 59.39, "eval_steps_per_second": 15.441, "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": 1.0621851957775565e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }