| { | |
| "best_metric": 10.95541000366211, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-75", | |
| "epoch": 0.6500541711809318, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00866738894907909, | |
| "grad_norm": 10.811844825744629, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 355.0012, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00866738894907909, | |
| "eval_loss": 11.097260475158691, | |
| "eval_runtime": 0.0681, | |
| "eval_samples_per_second": 734.456, | |
| "eval_steps_per_second": 190.959, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01733477789815818, | |
| "grad_norm": 11.61693000793457, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 354.9903, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02600216684723727, | |
| "grad_norm": 13.614788055419922, | |
| "learning_rate": 0.0001, | |
| "loss": 355.01, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03466955579631636, | |
| "grad_norm": 13.563213348388672, | |
| "learning_rate": 9.99571699711836e-05, | |
| "loss": 354.9338, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04333694474539545, | |
| "grad_norm": 15.03657054901123, | |
| "learning_rate": 9.982876141412856e-05, | |
| "loss": 354.8098, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05200433369447454, | |
| "grad_norm": 11.799213409423828, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 354.743, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.06067172264355363, | |
| "grad_norm": 13.64436149597168, | |
| "learning_rate": 9.931634888554937e-05, | |
| "loss": 354.6391, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.06933911159263272, | |
| "grad_norm": 14.219197273254395, | |
| "learning_rate": 9.893332032039701e-05, | |
| "loss": 354.4811, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0780065005417118, | |
| "grad_norm": 15.872390747070312, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 354.2897, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0866738894907909, | |
| "grad_norm": 19.295272827148438, | |
| "learning_rate": 9.791726278367022e-05, | |
| "loss": 354.0125, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09534127843986999, | |
| "grad_norm": 22.49827766418457, | |
| "learning_rate": 9.728616793536588e-05, | |
| "loss": 353.5613, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.10400866738894908, | |
| "grad_norm": 26.195762634277344, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 353.1424, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.11267605633802817, | |
| "grad_norm": 19.691654205322266, | |
| "learning_rate": 9.578385041664925e-05, | |
| "loss": 353.5012, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.12134344528710726, | |
| "grad_norm": 10.785454750061035, | |
| "learning_rate": 9.491548749301997e-05, | |
| "loss": 354.0385, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.13001083423618634, | |
| "grad_norm": 12.652568817138672, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 353.7744, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.13867822318526543, | |
| "grad_norm": 11.43913745880127, | |
| "learning_rate": 9.295261506157986e-05, | |
| "loss": 353.8282, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.14734561213434452, | |
| "grad_norm": 11.863940238952637, | |
| "learning_rate": 9.186184199300464e-05, | |
| "loss": 353.5572, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.1560130010834236, | |
| "grad_norm": 9.942915916442871, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 353.7301, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1646803900325027, | |
| "grad_norm": 10.467239379882812, | |
| "learning_rate": 8.947199994035401e-05, | |
| "loss": 353.5835, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.1733477789815818, | |
| "grad_norm": 10.793790817260742, | |
| "learning_rate": 8.817748015645558e-05, | |
| "loss": 353.3143, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1820151679306609, | |
| "grad_norm": 12.102933883666992, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 353.1421, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.19068255687973998, | |
| "grad_norm": 12.968494415283203, | |
| "learning_rate": 8.540155934270471e-05, | |
| "loss": 352.8263, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.19934994582881907, | |
| "grad_norm": 15.78851318359375, | |
| "learning_rate": 8.392544243589427e-05, | |
| "loss": 352.1595, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.20801733477789816, | |
| "grad_norm": 19.05240249633789, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 351.4413, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.21668472372697725, | |
| "grad_norm": 22.709346771240234, | |
| "learning_rate": 8.081093963579707e-05, | |
| "loss": 350.7502, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.21668472372697725, | |
| "eval_loss": 11.008831977844238, | |
| "eval_runtime": 0.0672, | |
| "eval_samples_per_second": 744.468, | |
| "eval_steps_per_second": 193.562, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.22535211267605634, | |
| "grad_norm": 8.14040756225586, | |
| "learning_rate": 7.917848237560709e-05, | |
| "loss": 353.3572, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.23401950162513543, | |
| "grad_norm": 8.944589614868164, | |
| "learning_rate": 7.75e-05, | |
| "loss": 353.0698, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.24268689057421453, | |
| "grad_norm": 9.255316734313965, | |
| "learning_rate": 7.577868759557654e-05, | |
| "loss": 352.8857, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.2513542795232936, | |
| "grad_norm": 9.936644554138184, | |
| "learning_rate": 7.401782177833148e-05, | |
| "loss": 352.7039, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.2600216684723727, | |
| "grad_norm": 9.272581100463867, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 352.7361, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.26868905742145177, | |
| "grad_norm": 8.569504737854004, | |
| "learning_rate": 7.03909064496551e-05, | |
| "loss": 352.7864, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.27735644637053086, | |
| "grad_norm": 8.665220260620117, | |
| "learning_rate": 6.853176097769229e-05, | |
| "loss": 352.6284, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.28602383531960995, | |
| "grad_norm": 9.216779708862305, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 352.4148, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.29469122426868904, | |
| "grad_norm": 10.269509315490723, | |
| "learning_rate": 6.473978262721463e-05, | |
| "loss": 352.075, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.30335861321776814, | |
| "grad_norm": 11.437735557556152, | |
| "learning_rate": 6.281416799501188e-05, | |
| "loss": 351.5313, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.3120260021668472, | |
| "grad_norm": 14.813851356506348, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 350.6866, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.3206933911159263, | |
| "grad_norm": 17.97544288635254, | |
| "learning_rate": 5.8922008423644624e-05, | |
| "loss": 349.869, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.3293607800650054, | |
| "grad_norm": 13.719532012939453, | |
| "learning_rate": 5.696287243144013e-05, | |
| "loss": 351.0155, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.3380281690140845, | |
| "grad_norm": 8.143577575683594, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 352.5081, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.3466955579631636, | |
| "grad_norm": 8.626445770263672, | |
| "learning_rate": 5.303712756855988e-05, | |
| "loss": 352.2322, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3553629469122427, | |
| "grad_norm": 8.909131050109863, | |
| "learning_rate": 5.107799157635538e-05, | |
| "loss": 351.9501, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.3640303358613218, | |
| "grad_norm": 8.486912727355957, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 352.0607, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.37269772481040087, | |
| "grad_norm": 8.207656860351562, | |
| "learning_rate": 4.718583200498814e-05, | |
| "loss": 352.0579, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.38136511375947996, | |
| "grad_norm": 8.082942008972168, | |
| "learning_rate": 4.526021737278538e-05, | |
| "loss": 352.0917, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.39003250270855905, | |
| "grad_norm": 8.122820854187012, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 351.9533, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.39869989165763814, | |
| "grad_norm": 8.681859016418457, | |
| "learning_rate": 4.146823902230772e-05, | |
| "loss": 351.7365, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.40736728060671723, | |
| "grad_norm": 10.082976341247559, | |
| "learning_rate": 3.960909355034491e-05, | |
| "loss": 351.1706, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.4160346695557963, | |
| "grad_norm": 12.920576095581055, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 350.3184, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.4247020585048754, | |
| "grad_norm": 16.692523956298828, | |
| "learning_rate": 3.598217822166854e-05, | |
| "loss": 349.401, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.4333694474539545, | |
| "grad_norm": 21.548805236816406, | |
| "learning_rate": 3.422131240442349e-05, | |
| "loss": 348.674, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4333694474539545, | |
| "eval_loss": 10.967840194702148, | |
| "eval_runtime": 0.0672, | |
| "eval_samples_per_second": 743.642, | |
| "eval_steps_per_second": 193.347, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4420368364030336, | |
| "grad_norm": 7.347636699676514, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 352.377, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.4507042253521127, | |
| "grad_norm": 8.223448753356934, | |
| "learning_rate": 3.082151762439293e-05, | |
| "loss": 351.9161, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.4593716143011918, | |
| "grad_norm": 8.413117408752441, | |
| "learning_rate": 2.9189060364202943e-05, | |
| "loss": 351.7371, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.46803900325027087, | |
| "grad_norm": 8.33215618133545, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 351.5685, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.47670639219934996, | |
| "grad_norm": 7.779220104217529, | |
| "learning_rate": 2.6074557564105727e-05, | |
| "loss": 351.7665, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.48537378114842905, | |
| "grad_norm": 7.201082706451416, | |
| "learning_rate": 2.459844065729529e-05, | |
| "loss": 351.9603, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.49404117009750814, | |
| "grad_norm": 7.1011128425598145, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 352.0007, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.5027085590465872, | |
| "grad_norm": 8.327539443969727, | |
| "learning_rate": 2.1822519843544424e-05, | |
| "loss": 351.3857, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.5113759479956663, | |
| "grad_norm": 8.971449851989746, | |
| "learning_rate": 2.0528000059645997e-05, | |
| "loss": 351.2054, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.5200433369447454, | |
| "grad_norm": 10.882966995239258, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 350.5195, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.5287107258938245, | |
| "grad_norm": 14.518791198730469, | |
| "learning_rate": 1.8138158006995364e-05, | |
| "loss": 349.3605, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.5373781148429035, | |
| "grad_norm": 18.91132354736328, | |
| "learning_rate": 1.7047384938420154e-05, | |
| "loss": 348.531, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.5460455037919827, | |
| "grad_norm": 13.490793228149414, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 350.0132, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.5547128927410617, | |
| "grad_norm": 7.963681697845459, | |
| "learning_rate": 1.5084512506980026e-05, | |
| "loss": 351.9526, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.5633802816901409, | |
| "grad_norm": 9.159059524536133, | |
| "learning_rate": 1.4216149583350754e-05, | |
| "loss": 351.1215, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.5720476706392199, | |
| "grad_norm": 8.50036334991455, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 351.3712, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.580715059588299, | |
| "grad_norm": 8.025604248046875, | |
| "learning_rate": 1.2713832064634126e-05, | |
| "loss": 351.5546, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.5893824485373781, | |
| "grad_norm": 7.468068599700928, | |
| "learning_rate": 1.2082737216329794e-05, | |
| "loss": 351.6381, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.5980498374864572, | |
| "grad_norm": 7.055534839630127, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 351.767, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.6067172264355363, | |
| "grad_norm": 7.515651226043701, | |
| "learning_rate": 1.1066679679603e-05, | |
| "loss": 351.5, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.6153846153846154, | |
| "grad_norm": 8.22630500793457, | |
| "learning_rate": 1.0683651114450641e-05, | |
| "loss": 351.2801, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.6240520043336945, | |
| "grad_norm": 9.437993049621582, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 350.7368, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.6327193932827736, | |
| "grad_norm": 11.552631378173828, | |
| "learning_rate": 1.017123858587145e-05, | |
| "loss": 349.9885, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.6413867822318526, | |
| "grad_norm": 16.06629180908203, | |
| "learning_rate": 1.00428300288164e-05, | |
| "loss": 348.9134, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.6500541711809318, | |
| "grad_norm": 22.20697021484375, | |
| "learning_rate": 1e-05, | |
| "loss": 347.9704, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.6500541711809318, | |
| "eval_loss": 10.95541000366211, | |
| "eval_runtime": 0.0671, | |
| "eval_samples_per_second": 745.545, | |
| "eval_steps_per_second": 193.842, | |
| "step": 75 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "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": 6321112350720.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |