{ "best_metric": 2.117478132247925, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.08787346221441125, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0017574692442882249, "grad_norm": 8.155097961425781, "learning_rate": 5e-05, "loss": 41.6019, "step": 1 }, { "epoch": 0.0017574692442882249, "eval_loss": 2.6723787784576416, "eval_runtime": 3.3022, "eval_samples_per_second": 15.142, "eval_steps_per_second": 3.937, "step": 1 }, { "epoch": 0.0035149384885764497, "grad_norm": 8.102839469909668, "learning_rate": 0.0001, "loss": 41.7807, "step": 2 }, { "epoch": 0.005272407732864675, "grad_norm": 7.643195629119873, "learning_rate": 9.990365154573717e-05, "loss": 41.4355, "step": 3 }, { "epoch": 0.007029876977152899, "grad_norm": 6.929295539855957, "learning_rate": 9.961501876182148e-05, "loss": 41.4712, "step": 4 }, { "epoch": 0.008787346221441126, "grad_norm": 6.217116355895996, "learning_rate": 9.913533761814537e-05, "loss": 40.7428, "step": 5 }, { "epoch": 0.01054481546572935, "grad_norm": 6.357845306396484, "learning_rate": 9.846666218300807e-05, "loss": 40.2373, "step": 6 }, { "epoch": 0.012302284710017574, "grad_norm": 7.052750110626221, "learning_rate": 9.761185582727977e-05, "loss": 40.0276, "step": 7 }, { "epoch": 0.014059753954305799, "grad_norm": 6.3859453201293945, "learning_rate": 9.657457896300791e-05, "loss": 39.3341, "step": 8 }, { "epoch": 0.015817223198594025, "grad_norm": 5.650634765625, "learning_rate": 9.535927336897098e-05, "loss": 38.5342, "step": 9 }, { "epoch": 0.01757469244288225, "grad_norm": 5.400217056274414, "learning_rate": 9.397114317029975e-05, "loss": 39.4071, "step": 10 }, { "epoch": 0.019332161687170474, "grad_norm": 5.9621782302856445, "learning_rate": 9.241613255361455e-05, "loss": 38.2531, "step": 11 }, { "epoch": 0.0210896309314587, "grad_norm": 6.27240514755249, "learning_rate": 9.070090031310558e-05, "loss": 37.0957, "step": 12 }, { "epoch": 0.022847100175746926, "grad_norm": 7.232273101806641, "learning_rate": 8.883279133655399e-05, "loss": 37.3327, "step": 13 }, { "epoch": 0.02460456942003515, "grad_norm": 6.111523151397705, "learning_rate": 8.681980515339464e-05, "loss": 36.9622, "step": 14 }, { "epoch": 0.026362038664323375, "grad_norm": 5.189523696899414, "learning_rate": 8.467056167950311e-05, "loss": 36.7707, "step": 15 }, { "epoch": 0.028119507908611598, "grad_norm": 4.849571704864502, "learning_rate": 8.239426430539243e-05, "loss": 36.6955, "step": 16 }, { "epoch": 0.029876977152899824, "grad_norm": 4.863271236419678, "learning_rate": 8.000066048588211e-05, "loss": 36.8177, "step": 17 }, { "epoch": 0.03163444639718805, "grad_norm": 4.815723896026611, "learning_rate": 7.75e-05, "loss": 36.0512, "step": 18 }, { "epoch": 0.033391915641476276, "grad_norm": 4.641097545623779, "learning_rate": 7.490299105985507e-05, "loss": 36.3713, "step": 19 }, { "epoch": 0.0351493848857645, "grad_norm": 4.852198600769043, "learning_rate": 7.222075445642904e-05, "loss": 35.6233, "step": 20 }, { "epoch": 0.03690685413005272, "grad_norm": 5.490119934082031, "learning_rate": 6.946477593864228e-05, "loss": 35.9335, "step": 21 }, { "epoch": 0.03866432337434095, "grad_norm": 4.903435230255127, "learning_rate": 6.664685702961344e-05, "loss": 35.3752, "step": 22 }, { "epoch": 0.040421792618629174, "grad_norm": 4.8363165855407715, "learning_rate": 6.377906449072578e-05, "loss": 35.7809, "step": 23 }, { "epoch": 0.0421792618629174, "grad_norm": 4.949439525604248, "learning_rate": 6.087367864990233e-05, "loss": 35.3121, "step": 24 }, { "epoch": 0.043936731107205626, "grad_norm": 7.111607551574707, "learning_rate": 5.794314081535644e-05, "loss": 34.1224, "step": 25 }, { "epoch": 0.043936731107205626, "eval_loss": 2.1845593452453613, "eval_runtime": 3.3662, "eval_samples_per_second": 14.854, "eval_steps_per_second": 3.862, "step": 25 }, { "epoch": 0.04569420035149385, "grad_norm": 6.5634565353393555, "learning_rate": 5.500000000000001e-05, "loss": 35.1202, "step": 26 }, { "epoch": 0.04745166959578207, "grad_norm": 5.575784206390381, "learning_rate": 5.205685918464356e-05, "loss": 34.9999, "step": 27 }, { "epoch": 0.0492091388400703, "grad_norm": 5.333949089050293, "learning_rate": 4.912632135009769e-05, "loss": 34.6598, "step": 28 }, { "epoch": 0.050966608084358524, "grad_norm": 5.233462810516357, "learning_rate": 4.6220935509274235e-05, "loss": 35.3394, "step": 29 }, { "epoch": 0.05272407732864675, "grad_norm": 4.848039627075195, "learning_rate": 4.3353142970386564e-05, "loss": 34.6306, "step": 30 }, { "epoch": 0.054481546572934976, "grad_norm": 4.672798156738281, "learning_rate": 4.053522406135775e-05, "loss": 34.26, "step": 31 }, { "epoch": 0.056239015817223195, "grad_norm": 5.004295825958252, "learning_rate": 3.777924554357096e-05, "loss": 35.2661, "step": 32 }, { "epoch": 0.05799648506151142, "grad_norm": 4.774494647979736, "learning_rate": 3.509700894014496e-05, "loss": 34.3399, "step": 33 }, { "epoch": 0.05975395430579965, "grad_norm": 5.3914713859558105, "learning_rate": 3.250000000000001e-05, "loss": 33.8915, "step": 34 }, { "epoch": 0.061511423550087874, "grad_norm": 5.224306583404541, "learning_rate": 2.9999339514117912e-05, "loss": 34.217, "step": 35 }, { "epoch": 0.0632688927943761, "grad_norm": 5.110523700714111, "learning_rate": 2.760573569460757e-05, "loss": 34.3804, "step": 36 }, { "epoch": 0.06502636203866433, "grad_norm": 6.0106201171875, "learning_rate": 2.53294383204969e-05, "loss": 34.0626, "step": 37 }, { "epoch": 0.06678383128295255, "grad_norm": 6.163959980010986, "learning_rate": 2.3180194846605367e-05, "loss": 34.2085, "step": 38 }, { "epoch": 0.06854130052724078, "grad_norm": 5.352950572967529, "learning_rate": 2.1167208663446025e-05, "loss": 34.3615, "step": 39 }, { "epoch": 0.070298769771529, "grad_norm": 5.185631275177002, "learning_rate": 1.9299099686894423e-05, "loss": 33.6859, "step": 40 }, { "epoch": 0.07205623901581722, "grad_norm": 4.927276134490967, "learning_rate": 1.758386744638546e-05, "loss": 34.1852, "step": 41 }, { "epoch": 0.07381370826010544, "grad_norm": 4.6272172927856445, "learning_rate": 1.602885682970026e-05, "loss": 33.955, "step": 42 }, { "epoch": 0.07557117750439367, "grad_norm": 4.516628265380859, "learning_rate": 1.464072663102903e-05, "loss": 34.2475, "step": 43 }, { "epoch": 0.0773286467486819, "grad_norm": 4.3881731033325195, "learning_rate": 1.3425421036992098e-05, "loss": 34.2023, "step": 44 }, { "epoch": 0.07908611599297012, "grad_norm": 4.675719738006592, "learning_rate": 1.2388144172720251e-05, "loss": 34.3724, "step": 45 }, { "epoch": 0.08084358523725835, "grad_norm": 4.657413005828857, "learning_rate": 1.1533337816991932e-05, "loss": 33.9527, "step": 46 }, { "epoch": 0.08260105448154657, "grad_norm": 5.37712287902832, "learning_rate": 1.0864662381854632e-05, "loss": 34.4192, "step": 47 }, { "epoch": 0.0843585237258348, "grad_norm": 5.268314361572266, "learning_rate": 1.0384981238178534e-05, "loss": 34.3434, "step": 48 }, { "epoch": 0.08611599297012303, "grad_norm": 5.414996147155762, "learning_rate": 1.0096348454262845e-05, "loss": 33.6508, "step": 49 }, { "epoch": 0.08787346221441125, "grad_norm": 7.697075366973877, "learning_rate": 1e-05, "loss": 33.6944, "step": 50 }, { "epoch": 0.08787346221441125, "eval_loss": 2.117478132247925, "eval_runtime": 3.3457, "eval_samples_per_second": 14.945, "eval_steps_per_second": 3.886, "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": 2.967137622687744e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }