| { | |
| "best_metric": 1.1384953260421753, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.012809120093506576, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00025618240187013155, | |
| "grad_norm": 1.071194052696228, | |
| "learning_rate": 5e-05, | |
| "loss": 2.8962, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00025618240187013155, | |
| "eval_loss": 3.3106155395507812, | |
| "eval_runtime": 1.5318, | |
| "eval_samples_per_second": 32.641, | |
| "eval_steps_per_second": 8.487, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005123648037402631, | |
| "grad_norm": 3.6906981468200684, | |
| "learning_rate": 0.0001, | |
| "loss": 2.9813, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0007685472056103946, | |
| "grad_norm": 2.532313346862793, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 2.9669, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0010247296074805262, | |
| "grad_norm": 2.5956337451934814, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 2.7056, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0012809120093506578, | |
| "grad_norm": 3.1904337406158447, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 2.4204, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001537094411220789, | |
| "grad_norm": 2.82814359664917, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2.215, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0017932768130909207, | |
| "grad_norm": 3.5345301628112793, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.9954, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0020494592149610524, | |
| "grad_norm": 59.07939147949219, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 2.0185, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.002305641616831184, | |
| "grad_norm": 16.29257583618164, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.7905, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0025618240187013155, | |
| "grad_norm": 5.184337139129639, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.5229, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0028180064205714467, | |
| "grad_norm": 4.18256139755249, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.3243, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.003074188822441578, | |
| "grad_norm": 3.7885982990264893, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.1763, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0033303712243117098, | |
| "grad_norm": 1.2441407442092896, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 2.6535, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0035865536261818413, | |
| "grad_norm": 3.06207537651062, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 2.3862, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.003842736028051973, | |
| "grad_norm": 1.6543389558792114, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 2.098, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004098918429922105, | |
| "grad_norm": 1.6060925722122192, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.6376, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.004355100831792236, | |
| "grad_norm": 1.698676586151123, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.3906, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.004611283233662368, | |
| "grad_norm": 1.3441932201385498, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.3307, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0048674656355324995, | |
| "grad_norm": 1.2712708711624146, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.1243, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.005123648037402631, | |
| "grad_norm": 1.1341032981872559, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.0344, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005379830439272763, | |
| "grad_norm": 0.7267351150512695, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.9158, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.005636012841142893, | |
| "grad_norm": 0.7292860150337219, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.8949, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.005892195243013025, | |
| "grad_norm": 0.8306976556777954, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.8188, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.006148377644883156, | |
| "grad_norm": 2.029994487762451, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.9764, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.006404560046753288, | |
| "grad_norm": 2.321648120880127, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 1.0235, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.006404560046753288, | |
| "eval_loss": 1.201508641242981, | |
| "eval_runtime": 1.5222, | |
| "eval_samples_per_second": 32.847, | |
| "eval_steps_per_second": 8.54, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0066607424486234195, | |
| "grad_norm": 0.7317392826080322, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 2.7792, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.006916924850493551, | |
| "grad_norm": 1.2366492748260498, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 2.0891, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.007173107252363683, | |
| "grad_norm": 1.2961385250091553, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 1.6581, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.007429289654233814, | |
| "grad_norm": 1.205391764640808, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 1.2327, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.007685472056103946, | |
| "grad_norm": 1.108265995979309, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 1.1861, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.007941654457974078, | |
| "grad_norm": 0.9121682047843933, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 1.156, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.00819783685984421, | |
| "grad_norm": 0.7840728759765625, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 1.0705, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.008454019261714341, | |
| "grad_norm": 0.7209661602973938, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 1.0062, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.008710201663584473, | |
| "grad_norm": 0.5964431166648865, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.9278, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.008966384065454604, | |
| "grad_norm": 0.5967997312545776, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.8185, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.009222566467324736, | |
| "grad_norm": 0.5782707929611206, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.7699, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.009478748869194868, | |
| "grad_norm": 1.7378571033477783, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 1.0288, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.009734931271064999, | |
| "grad_norm": 0.5410066843032837, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 2.7, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.00999111367293513, | |
| "grad_norm": 0.7376120686531067, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 2.2896, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.010247296074805262, | |
| "grad_norm": 0.8110925555229187, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 1.8188, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.010503478476675394, | |
| "grad_norm": 0.7669232487678528, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 1.3056, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.010759660878545525, | |
| "grad_norm": 0.7149698734283447, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 1.138, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.011015843280415655, | |
| "grad_norm": 0.6171885132789612, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 1.1505, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.011272025682285787, | |
| "grad_norm": 0.5427089333534241, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 1.0181, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.011528208084155918, | |
| "grad_norm": 0.41735145449638367, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.9324, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.01178439048602605, | |
| "grad_norm": 0.4027903079986572, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.9263, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.012040572887896181, | |
| "grad_norm": 0.41988879442214966, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.8873, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.012296755289766313, | |
| "grad_norm": 0.45334821939468384, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.8117, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.012552937691636444, | |
| "grad_norm": 0.7448716759681702, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.9191, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.012809120093506576, | |
| "grad_norm": 1.5897629261016846, | |
| "learning_rate": 1e-05, | |
| "loss": 0.9977, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.012809120093506576, | |
| "eval_loss": 1.1384953260421753, | |
| "eval_runtime": 1.5387, | |
| "eval_samples_per_second": 32.495, | |
| "eval_steps_per_second": 8.449, | |
| "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": 2.95300912644096e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |