| { | |
| "best_metric": 10.567898750305176, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.020857776039629773, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00041715552079259546, | |
| "grad_norm": 16.225372314453125, | |
| "learning_rate": 5e-05, | |
| "loss": 177.4848, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00041715552079259546, | |
| "eval_loss": 11.107605934143066, | |
| "eval_runtime": 0.5672, | |
| "eval_samples_per_second": 88.157, | |
| "eval_steps_per_second": 22.921, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008343110415851909, | |
| "grad_norm": 19.649044036865234, | |
| "learning_rate": 0.0001, | |
| "loss": 177.5286, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0012514665623777864, | |
| "grad_norm": 19.702499389648438, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 177.519, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0016686220831703819, | |
| "grad_norm": 20.22748374938965, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 177.2245, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0020857776039629773, | |
| "grad_norm": 19.653493881225586, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 176.9257, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0025029331247555728, | |
| "grad_norm": 20.355478286743164, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 176.6786, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0029200886455481682, | |
| "grad_norm": 20.59766387939453, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 176.4899, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0033372441663407637, | |
| "grad_norm": 20.92879295349121, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 176.0992, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0037543996871333596, | |
| "grad_norm": 18.95726776123047, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 175.9636, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004171555207925955, | |
| "grad_norm": 19.476179122924805, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 175.6026, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00458871072871855, | |
| "grad_norm": 19.132965087890625, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 175.3802, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0050058662495111456, | |
| "grad_norm": 19.804948806762695, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 175.5304, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.005423021770303741, | |
| "grad_norm": 16.1426944732666, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 175.3834, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0058401772910963365, | |
| "grad_norm": 17.41680908203125, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 174.5042, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.006257332811888932, | |
| "grad_norm": 19.615482330322266, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 173.7562, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.006674488332681527, | |
| "grad_norm": 20.319902420043945, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 173.3591, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.007091643853474124, | |
| "grad_norm": 20.526622772216797, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 172.9324, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.007508799374266719, | |
| "grad_norm": 19.18339729309082, | |
| "learning_rate": 7.75e-05, | |
| "loss": 172.9094, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.007925954895059314, | |
| "grad_norm": 19.07183837890625, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 172.7227, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.00834311041585191, | |
| "grad_norm": 18.749589920043945, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 172.5453, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.008760265936644505, | |
| "grad_norm": 19.284332275390625, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 172.0866, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0091774214574371, | |
| "grad_norm": 17.55962562561035, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 172.4816, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.009594576978229696, | |
| "grad_norm": 17.24770736694336, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 172.2674, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.010011732499022291, | |
| "grad_norm": 18.669254302978516, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 171.6859, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.010428888019814887, | |
| "grad_norm": 19.6612548828125, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 172.3712, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.010428888019814887, | |
| "eval_loss": 10.703987121582031, | |
| "eval_runtime": 0.0837, | |
| "eval_samples_per_second": 597.656, | |
| "eval_steps_per_second": 155.391, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.010846043540607482, | |
| "grad_norm": 15.183359146118164, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 172.194, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.011263199061400078, | |
| "grad_norm": 17.194549560546875, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 170.835, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.011680354582192673, | |
| "grad_norm": 16.776403427124023, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 170.8668, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.012097510102985268, | |
| "grad_norm": 17.39474105834961, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 170.3105, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.012514665623777864, | |
| "grad_norm": 17.14206886291504, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 170.1634, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01293182114457046, | |
| "grad_norm": 16.973140716552734, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 170.1308, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.013348976665363055, | |
| "grad_norm": 16.690622329711914, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 170.1685, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.01376613218615565, | |
| "grad_norm": 17.22452163696289, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 169.8173, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.014183287706948247, | |
| "grad_norm": 16.15555191040039, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 170.0619, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.014600443227740843, | |
| "grad_norm": 15.78242015838623, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 170.3394, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.015017598748533438, | |
| "grad_norm": 16.192392349243164, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 169.9828, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.015434754269326034, | |
| "grad_norm": 16.889453887939453, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 170.1619, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.015851909790118628, | |
| "grad_norm": 14.697663307189941, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 171.5415, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.016269065310911223, | |
| "grad_norm": 14.812946319580078, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 170.041, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.01668622083170382, | |
| "grad_norm": 15.579548835754395, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 169.3603, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.017103376352496414, | |
| "grad_norm": 15.448450088500977, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 169.2855, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.01752053187328901, | |
| "grad_norm": 15.2275390625, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 169.3168, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.017937687394081605, | |
| "grad_norm": 15.755297660827637, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 168.8581, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0183548429148742, | |
| "grad_norm": 15.333876609802246, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 169.1523, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.018771998435666796, | |
| "grad_norm": 15.545121192932129, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 169.1059, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.01918915395645939, | |
| "grad_norm": 15.434908866882324, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 169.0822, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.019606309477251987, | |
| "grad_norm": 14.696342468261719, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 169.5559, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.020023464998044582, | |
| "grad_norm": 15.240139961242676, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 169.6834, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.020440620518837178, | |
| "grad_norm": 16.353404998779297, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 169.1321, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.020857776039629773, | |
| "grad_norm": 18.517147064208984, | |
| "learning_rate": 1e-05, | |
| "loss": 170.0445, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.020857776039629773, | |
| "eval_loss": 10.567898750305176, | |
| "eval_runtime": 0.0956, | |
| "eval_samples_per_second": 523.206, | |
| "eval_steps_per_second": 136.034, | |
| "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": 38111123865600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |