| { | |
| "best_metric": 1.0014017820358276, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.1510791366906474, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02302158273381295, | |
| "grad_norm": 51.27009582519531, | |
| "learning_rate": 5e-05, | |
| "loss": 59.5547, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02302158273381295, | |
| "eval_loss": 4.219150543212891, | |
| "eval_runtime": 1.4656, | |
| "eval_samples_per_second": 34.115, | |
| "eval_steps_per_second": 8.87, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0460431654676259, | |
| "grad_norm": 52.14596939086914, | |
| "learning_rate": 0.0001, | |
| "loss": 66.9514, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.06906474820143885, | |
| "grad_norm": 73.6473159790039, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 88.7822, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0920863309352518, | |
| "grad_norm": 76.42533111572266, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 105.8788, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.11510791366906475, | |
| "grad_norm": 88.7105941772461, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 102.5182, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1381294964028777, | |
| "grad_norm": 101.5471420288086, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 89.6244, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.16115107913669063, | |
| "grad_norm": 119.08177185058594, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 71.6918, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.1841726618705036, | |
| "grad_norm": 113.49226379394531, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 52.1182, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.20719424460431654, | |
| "grad_norm": 64.88825225830078, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 37.5966, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.2302158273381295, | |
| "grad_norm": 67.97850799560547, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 34.7204, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.25323741007194245, | |
| "grad_norm": 80.26464080810547, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 37.317, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.2762589928057554, | |
| "grad_norm": 30.27471160888672, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 50.8477, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.2992805755395683, | |
| "grad_norm": 34.09827423095703, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 42.7292, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.32230215827338127, | |
| "grad_norm": 35.786705017089844, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 44.7788, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.34532374100719426, | |
| "grad_norm": 32.19075012207031, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 36.2925, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.3683453237410072, | |
| "grad_norm": 33.80173873901367, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 34.3814, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.39136690647482014, | |
| "grad_norm": 34.994361877441406, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 34.2221, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.4143884892086331, | |
| "grad_norm": 30.99186897277832, | |
| "learning_rate": 7.75e-05, | |
| "loss": 33.6055, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.437410071942446, | |
| "grad_norm": 50.038936614990234, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 28.7858, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.460431654676259, | |
| "grad_norm": 25.917606353759766, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 28.09, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.48345323741007196, | |
| "grad_norm": 29.549970626831055, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 32.0602, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.5064748201438849, | |
| "grad_norm": 23.611438751220703, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 38.0321, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.5294964028776978, | |
| "grad_norm": 15.553833961486816, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 42.3021, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.5525179856115108, | |
| "grad_norm": 19.091585159301758, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 38.3939, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.5755395683453237, | |
| "grad_norm": 18.050025939941406, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 36.5805, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5755395683453237, | |
| "eval_loss": 1.0759358406066895, | |
| "eval_runtime": 1.4586, | |
| "eval_samples_per_second": 34.279, | |
| "eval_steps_per_second": 8.913, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5985611510791367, | |
| "grad_norm": 19.713987350463867, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 32.3912, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.6215827338129496, | |
| "grad_norm": 18.734251022338867, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 33.0844, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.6446043165467625, | |
| "grad_norm": 23.264362335205078, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 30.0175, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.6676258992805756, | |
| "grad_norm": 21.15528106689453, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 28.8613, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.6906474820143885, | |
| "grad_norm": 21.473705291748047, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 26.4456, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.7136690647482015, | |
| "grad_norm": 22.020238876342773, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 26.6504, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.7366906474820144, | |
| "grad_norm": 23.917692184448242, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 26.535, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.7597122302158273, | |
| "grad_norm": 16.099769592285156, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 38.9816, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.7827338129496403, | |
| "grad_norm": 13.968155860900879, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 38.2441, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.8057553956834532, | |
| "grad_norm": 16.24407196044922, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 34.9773, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.8287769784172662, | |
| "grad_norm": 18.08936882019043, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 31.861, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.8517985611510791, | |
| "grad_norm": 17.8543643951416, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 28.9791, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.874820143884892, | |
| "grad_norm": 20.712501525878906, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 31.5953, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.897841726618705, | |
| "grad_norm": 21.663637161254883, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 26.2142, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.920863309352518, | |
| "grad_norm": 20.295846939086914, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 29.1029, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.943884892086331, | |
| "grad_norm": 21.162328720092773, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 23.3831, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.9669064748201439, | |
| "grad_norm": 24.621768951416016, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 26.9917, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.9899280575539569, | |
| "grad_norm": 33.076759338378906, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 26.055, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.0129496402877698, | |
| "grad_norm": 16.25497055053711, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 39.5755, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.0359712230215827, | |
| "grad_norm": 11.067312240600586, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 40.9644, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.0589928057553957, | |
| "grad_norm": 13.398911476135254, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 36.1482, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.0820143884892086, | |
| "grad_norm": 15.000913619995117, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 36.1772, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.1050359712230216, | |
| "grad_norm": 15.171695709228516, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 28.492, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.1280575539568345, | |
| "grad_norm": 17.97978973388672, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 28.6112, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.1510791366906474, | |
| "grad_norm": 19.472795486450195, | |
| "learning_rate": 1e-05, | |
| "loss": 28.4342, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.1510791366906474, | |
| "eval_loss": 1.0014017820358276, | |
| "eval_runtime": 1.4573, | |
| "eval_samples_per_second": 34.31, | |
| "eval_steps_per_second": 8.92, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 5.259156315439104e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |