| { | |
| "best_metric": 0.8033109903335571, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-500", | |
| "epoch": 0.18412815319462345, | |
| "eval_steps": 50, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003682563063892469, | |
| "eval_loss": 2.228027582168579, | |
| "eval_runtime": 105.1707, | |
| "eval_samples_per_second": 10.878, | |
| "eval_steps_per_second": 2.719, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0036825630638924692, | |
| "grad_norm": 3.64420485496521, | |
| "learning_rate": 4.0600000000000004e-05, | |
| "loss": 4.2977, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0073651261277849385, | |
| "grad_norm": 1.8111019134521484, | |
| "learning_rate": 8.120000000000001e-05, | |
| "loss": 3.6581, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.011047689191677408, | |
| "grad_norm": 2.067847728729248, | |
| "learning_rate": 0.00012179999999999999, | |
| "loss": 3.1829, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.014730252255569877, | |
| "grad_norm": 1.6672817468643188, | |
| "learning_rate": 0.00016240000000000002, | |
| "loss": 2.8307, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.018412815319462345, | |
| "grad_norm": 1.8722939491271973, | |
| "learning_rate": 0.000203, | |
| "loss": 2.597, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.018412815319462345, | |
| "eval_loss": 1.3078378438949585, | |
| "eval_runtime": 104.9597, | |
| "eval_samples_per_second": 10.899, | |
| "eval_steps_per_second": 2.725, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.022095378383354815, | |
| "grad_norm": 1.3702597618103027, | |
| "learning_rate": 0.00020275275110137215, | |
| "loss": 2.5237, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.025777941447247283, | |
| "grad_norm": 1.518210768699646, | |
| "learning_rate": 0.00020201220897726938, | |
| "loss": 2.4878, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.029460504511139754, | |
| "grad_norm": 1.3466520309448242, | |
| "learning_rate": 0.00020078198147448128, | |
| "loss": 2.3046, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.03314306757503222, | |
| "grad_norm": 1.2383614778518677, | |
| "learning_rate": 0.00019906806213773937, | |
| "loss": 2.3387, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.03682563063892469, | |
| "grad_norm": 1.4980638027191162, | |
| "learning_rate": 0.0001968788010097697, | |
| "loss": 2.0506, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.03682563063892469, | |
| "eval_loss": 1.1180486679077148, | |
| "eval_runtime": 105.0543, | |
| "eval_samples_per_second": 10.89, | |
| "eval_steps_per_second": 2.722, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.040508193702817163, | |
| "grad_norm": 1.1839851140975952, | |
| "learning_rate": 0.00019422486395072398, | |
| "loss": 2.1824, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.04419075676670963, | |
| "grad_norm": 1.347690224647522, | |
| "learning_rate": 0.0001911191806751811, | |
| "loss": 2.1568, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.0478733198306021, | |
| "grad_norm": 1.2591941356658936, | |
| "learning_rate": 0.00018757688175987723, | |
| "loss": 2.142, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.051555882894494566, | |
| "grad_norm": 1.2574785947799683, | |
| "learning_rate": 0.00018361522492905716, | |
| "loss": 2.0817, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.05523844595838704, | |
| "grad_norm": 1.4502058029174805, | |
| "learning_rate": 0.00017925351097657625, | |
| "loss": 1.9292, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.05523844595838704, | |
| "eval_loss": 1.0143712759017944, | |
| "eval_runtime": 105.2365, | |
| "eval_samples_per_second": 10.871, | |
| "eval_steps_per_second": 2.718, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.05892100902227951, | |
| "grad_norm": 1.2236560583114624, | |
| "learning_rate": 0.00017451298973437308, | |
| "loss": 2.1045, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.06260357208617198, | |
| "grad_norm": 1.1792196035385132, | |
| "learning_rate": 0.0001694167565454241, | |
| "loss": 2.0273, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.06628613515006444, | |
| "grad_norm": 1.1047189235687256, | |
| "learning_rate": 0.0001639896397455543, | |
| "loss": 2.0091, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.06996869821395692, | |
| "grad_norm": 1.1556135416030884, | |
| "learning_rate": 0.0001582580797022808, | |
| "loss": 1.9671, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.07365126127784938, | |
| "grad_norm": 1.5440864562988281, | |
| "learning_rate": 0.00015225, | |
| "loss": 1.8005, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.07365126127784938, | |
| "eval_loss": 0.9690786600112915, | |
| "eval_runtime": 104.9771, | |
| "eval_samples_per_second": 10.898, | |
| "eval_steps_per_second": 2.724, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.07733382434174185, | |
| "grad_norm": 1.745725154876709, | |
| "learning_rate": 0.00014599467139909136, | |
| "loss": 1.9487, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.08101638740563433, | |
| "grad_norm": 1.1734682321548462, | |
| "learning_rate": 0.0001395225692317151, | |
| "loss": 1.9076, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.08469895046952679, | |
| "grad_norm": 1.083282709121704, | |
| "learning_rate": 0.00013286522492905717, | |
| "loss": 1.9023, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.08838151353341926, | |
| "grad_norm": 1.1208113431930542, | |
| "learning_rate": 0.00012605507240336626, | |
| "loss": 1.8028, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.09206407659731172, | |
| "grad_norm": 1.5673129558563232, | |
| "learning_rate": 0.00011912529003319345, | |
| "loss": 1.5755, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.09206407659731172, | |
| "eval_loss": 0.914474606513977, | |
| "eval_runtime": 105.0575, | |
| "eval_samples_per_second": 10.889, | |
| "eval_steps_per_second": 2.722, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.0957466396612042, | |
| "grad_norm": 1.1317609548568726, | |
| "learning_rate": 0.00011210963902166683, | |
| "loss": 1.867, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.09942920272509667, | |
| "grad_norm": 1.1235476732254028, | |
| "learning_rate": 0.00010504229891530386, | |
| "loss": 1.8936, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.10311176578898913, | |
| "grad_norm": 1.1461458206176758, | |
| "learning_rate": 9.795770108469618e-05, | |
| "loss": 1.8071, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.1067943288528816, | |
| "grad_norm": 1.1431809663772583, | |
| "learning_rate": 9.08903609783332e-05, | |
| "loss": 1.8178, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.11047689191677408, | |
| "grad_norm": 1.3735449314117432, | |
| "learning_rate": 8.387470996680658e-05, | |
| "loss": 1.6099, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.11047689191677408, | |
| "eval_loss": 0.8697930574417114, | |
| "eval_runtime": 104.9151, | |
| "eval_samples_per_second": 10.904, | |
| "eval_steps_per_second": 2.726, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.11415945498066654, | |
| "grad_norm": 0.9413533210754395, | |
| "learning_rate": 7.694492759663374e-05, | |
| "loss": 1.767, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.11784201804455902, | |
| "grad_norm": 1.0218007564544678, | |
| "learning_rate": 7.013477507094284e-05, | |
| "loss": 1.6817, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.12152458110845148, | |
| "grad_norm": 1.0082601308822632, | |
| "learning_rate": 6.347743076828492e-05, | |
| "loss": 1.7117, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.12520714417234396, | |
| "grad_norm": 1.0002052783966064, | |
| "learning_rate": 5.700532860090863e-05, | |
| "loss": 1.6825, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.1288897072362364, | |
| "grad_norm": 1.2524888515472412, | |
| "learning_rate": 5.075000000000002e-05, | |
| "loss": 1.4342, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.1288897072362364, | |
| "eval_loss": 0.8377587795257568, | |
| "eval_runtime": 104.9194, | |
| "eval_samples_per_second": 10.904, | |
| "eval_steps_per_second": 2.726, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.13257227030012889, | |
| "grad_norm": 1.0344349145889282, | |
| "learning_rate": 4.4741920297719214e-05, | |
| "loss": 1.7175, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.13625483336402136, | |
| "grad_norm": 1.1708482503890991, | |
| "learning_rate": 3.901036025444568e-05, | |
| "loss": 1.692, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.13993739642791383, | |
| "grad_norm": 1.0002044439315796, | |
| "learning_rate": 3.358324345457592e-05, | |
| "loss": 1.6282, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.1436199594918063, | |
| "grad_norm": 1.103905439376831, | |
| "learning_rate": 2.8487010265626928e-05, | |
| "loss": 1.6997, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.14730252255569876, | |
| "grad_norm": 1.3405430316925049, | |
| "learning_rate": 2.3746489023423744e-05, | |
| "loss": 1.5467, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.14730252255569876, | |
| "eval_loss": 0.8156729936599731, | |
| "eval_runtime": 105.1156, | |
| "eval_samples_per_second": 10.883, | |
| "eval_steps_per_second": 2.721, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.15098508561959123, | |
| "grad_norm": 0.9257370233535767, | |
| "learning_rate": 1.9384775070942844e-05, | |
| "loss": 1.6284, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.1546676486834837, | |
| "grad_norm": 1.1275734901428223, | |
| "learning_rate": 1.5423118240122765e-05, | |
| "loss": 1.6474, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.15835021174737618, | |
| "grad_norm": 1.0271503925323486, | |
| "learning_rate": 1.188081932481891e-05, | |
| "loss": 1.5823, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.16203277481126865, | |
| "grad_norm": 0.9594849944114685, | |
| "learning_rate": 8.775136049276001e-06, | |
| "loss": 1.6091, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.1657153378751611, | |
| "grad_norm": 1.3645907640457153, | |
| "learning_rate": 6.121198990230306e-06, | |
| "loss": 1.4868, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.1657153378751611, | |
| "eval_loss": 0.8050962686538696, | |
| "eval_runtime": 105.3167, | |
| "eval_samples_per_second": 10.862, | |
| "eval_steps_per_second": 2.716, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.16939790093905358, | |
| "grad_norm": 1.1936448812484741, | |
| "learning_rate": 3.931937862260632e-06, | |
| "loss": 1.6886, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.17308046400294605, | |
| "grad_norm": 1.1452791690826416, | |
| "learning_rate": 2.2180185255187225e-06, | |
| "loss": 1.6843, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.17676302706683852, | |
| "grad_norm": 1.0918186902999878, | |
| "learning_rate": 9.877910227306082e-07, | |
| "loss": 1.6394, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.180445590130731, | |
| "grad_norm": 0.9549961686134338, | |
| "learning_rate": 2.472488986278439e-07, | |
| "loss": 1.7196, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.18412815319462345, | |
| "grad_norm": 1.2962521314620972, | |
| "learning_rate": 0.0, | |
| "loss": 1.5057, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.18412815319462345, | |
| "eval_loss": 0.8033109903335571, | |
| "eval_runtime": 105.0396, | |
| "eval_samples_per_second": 10.891, | |
| "eval_steps_per_second": 2.723, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "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": 1.5092811439276032e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |