| { | |
| "best_metric": 3.582388401031494, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.007033430775655537, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00014066861551311076, | |
| "grad_norm": 0.9427841305732727, | |
| "learning_rate": 5e-05, | |
| "loss": 2.2525, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00014066861551311076, | |
| "eval_loss": 5.381374359130859, | |
| "eval_runtime": 4.305, | |
| "eval_samples_per_second": 11.614, | |
| "eval_steps_per_second": 3.02, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00028133723102622153, | |
| "grad_norm": 1.4493043422698975, | |
| "learning_rate": 0.0001, | |
| "loss": 3.0518, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00042200584653933227, | |
| "grad_norm": 1.8600473403930664, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 3.6448, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0005626744620524431, | |
| "grad_norm": 2.302962303161621, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 4.4023, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0007033430775655537, | |
| "grad_norm": 3.376417875289917, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 4.6614, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0008440116930786645, | |
| "grad_norm": 3.2473976612091064, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 4.4394, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0009846803085917753, | |
| "grad_norm": 2.340790033340454, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 4.2634, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0011253489241048861, | |
| "grad_norm": 2.2660000324249268, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 4.3473, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0012660175396179967, | |
| "grad_norm": 2.196218729019165, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 4.26, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0014066861551311075, | |
| "grad_norm": 2.6228277683258057, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 4.171, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0015473547706442183, | |
| "grad_norm": 3.1706738471984863, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 4.4074, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.001688023386157329, | |
| "grad_norm": 4.587759494781494, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 4.6637, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0018286920016704399, | |
| "grad_norm": 2.9576611518859863, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 2.4479, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0019693606171835507, | |
| "grad_norm": 3.024545907974243, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 2.8594, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0021100292326966612, | |
| "grad_norm": 2.2302956581115723, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 2.9605, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0022506978482097722, | |
| "grad_norm": 1.8585838079452515, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 3.3364, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.002391366463722883, | |
| "grad_norm": 2.91164493560791, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 3.79, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0025320350792359934, | |
| "grad_norm": 2.227503538131714, | |
| "learning_rate": 7.75e-05, | |
| "loss": 3.743, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0026727036947491044, | |
| "grad_norm": 1.9422775506973267, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 3.9933, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.002813372310262215, | |
| "grad_norm": 1.9657392501831055, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 3.963, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.002954040925775326, | |
| "grad_norm": 2.104684591293335, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 3.8063, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0030947095412884366, | |
| "grad_norm": 2.2109615802764893, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 4.0589, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0032353781568015476, | |
| "grad_norm": 2.330768585205078, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 3.9557, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.003376046772314658, | |
| "grad_norm": 2.38495135307312, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 4.3077, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0035167153878277687, | |
| "grad_norm": 3.6864495277404785, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 4.858, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0035167153878277687, | |
| "eval_loss": 3.688027858734131, | |
| "eval_runtime": 4.3449, | |
| "eval_samples_per_second": 11.508, | |
| "eval_steps_per_second": 2.992, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0036573840033408797, | |
| "grad_norm": 0.7148618698120117, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 1.8397, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0037980526188539903, | |
| "grad_norm": 0.7965158224105835, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 2.5025, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.003938721234367101, | |
| "grad_norm": 0.8529465198516846, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 2.9173, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0040793898498802115, | |
| "grad_norm": 1.0659992694854736, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 3.4396, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0042200584653933225, | |
| "grad_norm": 1.1692177057266235, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 3.6577, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0043607270809064335, | |
| "grad_norm": 1.3070368766784668, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 3.7179, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0045013956964195445, | |
| "grad_norm": 1.3615529537200928, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 3.6686, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.004642064311932655, | |
| "grad_norm": 1.3193974494934082, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 3.7734, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.004782732927445766, | |
| "grad_norm": 1.5574662685394287, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 3.7865, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.004923401542958877, | |
| "grad_norm": 1.6892421245574951, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 3.9089, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.005064070158471987, | |
| "grad_norm": 1.7540158033370972, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 4.0583, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.005204738773985098, | |
| "grad_norm": 2.6319198608398438, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 4.4668, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.005345407389498209, | |
| "grad_norm": 0.6882954835891724, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 1.892, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.00548607600501132, | |
| "grad_norm": 0.6292988657951355, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 2.3763, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.00562674462052443, | |
| "grad_norm": 0.8061068654060364, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 2.7793, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.005767413236037541, | |
| "grad_norm": 0.9110883474349976, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 3.047, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.005908081851550652, | |
| "grad_norm": 1.0115941762924194, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 3.51, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.006048750467063762, | |
| "grad_norm": 1.0895260572433472, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 3.5791, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.006189419082576873, | |
| "grad_norm": 1.222615122795105, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 3.7129, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.006330087698089984, | |
| "grad_norm": 1.33371901512146, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 3.7673, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.006470756313603095, | |
| "grad_norm": 1.4590684175491333, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 3.6255, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.006611424929116205, | |
| "grad_norm": 1.6010714769363403, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 3.5992, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.006752093544629316, | |
| "grad_norm": 2.1239309310913086, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 3.9121, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.006892762160142427, | |
| "grad_norm": 2.1113851070404053, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 4.0347, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.007033430775655537, | |
| "grad_norm": 3.646865129470825, | |
| "learning_rate": 1e-05, | |
| "loss": 4.6202, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.007033430775655537, | |
| "eval_loss": 3.582388401031494, | |
| "eval_runtime": 4.4168, | |
| "eval_samples_per_second": 11.32, | |
| "eval_steps_per_second": 2.943, | |
| "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": 5.968083617316864e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |