| { | |
| "best_metric": 11.683328628540039, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.535833891493637, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.010716677829872739, | |
| "grad_norm": 0.3579203486442566, | |
| "learning_rate": 5e-05, | |
| "loss": 11.7499, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010716677829872739, | |
| "eval_loss": 11.747014999389648, | |
| "eval_runtime": 0.1165, | |
| "eval_samples_per_second": 429.239, | |
| "eval_steps_per_second": 111.602, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.021433355659745478, | |
| "grad_norm": 0.2880854308605194, | |
| "learning_rate": 0.0001, | |
| "loss": 11.7526, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.032150033489618215, | |
| "grad_norm": 0.2896791398525238, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 11.7576, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.042866711319490956, | |
| "grad_norm": 0.28422674536705017, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 11.7435, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0535833891493637, | |
| "grad_norm": 0.29379916191101074, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 11.7397, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.06430006697923643, | |
| "grad_norm": 0.28467515110969543, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 11.7416, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.07501674480910918, | |
| "grad_norm": 0.3610594570636749, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 11.7316, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.08573342263898191, | |
| "grad_norm": 0.33949601650238037, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 11.7317, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.09645010046885466, | |
| "grad_norm": 0.3650335371494293, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 11.7378, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1071667782987274, | |
| "grad_norm": 0.38304686546325684, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 11.7273, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.11788345612860013, | |
| "grad_norm": 0.4165284335613251, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 11.725, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.12860013395847286, | |
| "grad_norm": 0.4531891345977783, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 11.7345, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.13931681178834562, | |
| "grad_norm": 0.42262741923332214, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 11.7358, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.15003348961821836, | |
| "grad_norm": 0.368812620639801, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 11.7445, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.1607501674480911, | |
| "grad_norm": 0.32296884059906006, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 11.7322, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.17146684527796383, | |
| "grad_norm": 0.4163282513618469, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 11.732, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.18218352310783656, | |
| "grad_norm": 0.4484187364578247, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 11.726, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.19290020093770932, | |
| "grad_norm": 0.3976253867149353, | |
| "learning_rate": 7.75e-05, | |
| "loss": 11.7251, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.20361687876758205, | |
| "grad_norm": 0.4430258870124817, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 11.7191, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2143335565974548, | |
| "grad_norm": 0.49592018127441406, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 11.7165, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.22505023442732752, | |
| "grad_norm": 0.5270517468452454, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 11.701, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.23576691225720026, | |
| "grad_norm": 0.4895842373371124, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 11.7047, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.24648359008707302, | |
| "grad_norm": 0.5824676752090454, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 11.7079, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.2572002679169457, | |
| "grad_norm": 0.65845787525177, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 11.6986, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2679169457468185, | |
| "grad_norm": 0.6766319870948792, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 11.7086, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2679169457468185, | |
| "eval_loss": 11.707274436950684, | |
| "eval_runtime": 0.1144, | |
| "eval_samples_per_second": 437.25, | |
| "eval_steps_per_second": 113.685, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.27863362357669125, | |
| "grad_norm": 0.6378116011619568, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 11.7108, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.289350301406564, | |
| "grad_norm": 0.5049313902854919, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 11.7114, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.3000669792364367, | |
| "grad_norm": 0.48692914843559265, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 11.7181, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.31078365706630945, | |
| "grad_norm": 0.4770529270172119, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 11.705, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.3215003348961822, | |
| "grad_norm": 0.5465254187583923, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 11.6971, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3322170127260549, | |
| "grad_norm": 0.5846957564353943, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 11.688, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.34293369055592765, | |
| "grad_norm": 0.6031647324562073, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 11.6896, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.3536503683858004, | |
| "grad_norm": 0.593400776386261, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 11.6974, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.3643670462156731, | |
| "grad_norm": 0.653511106967926, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 11.6989, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.3750837240455459, | |
| "grad_norm": 0.6714555621147156, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 11.6787, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.38580040187541864, | |
| "grad_norm": 0.6866130828857422, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 11.6906, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.3965170797052914, | |
| "grad_norm": 0.7554149031639099, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 11.6774, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.4072337575351641, | |
| "grad_norm": 0.6247978210449219, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 11.6914, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.41795043536503684, | |
| "grad_norm": 0.6444849967956543, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 11.6864, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.4286671131949096, | |
| "grad_norm": 0.5599631667137146, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 11.7007, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4393837910247823, | |
| "grad_norm": 0.5610001683235168, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 11.7048, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.45010046885465504, | |
| "grad_norm": 0.6208688616752625, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 11.6906, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.4608171466845278, | |
| "grad_norm": 0.589806854724884, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 11.6843, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.4715338245144005, | |
| "grad_norm": 0.6590961217880249, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 11.6723, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.4822505023442733, | |
| "grad_norm": 0.6476118564605713, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 11.686, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.49296718017414604, | |
| "grad_norm": 0.7357048988342285, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 11.6814, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.5036838580040187, | |
| "grad_norm": 0.6685858964920044, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 11.684, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.5144005358338914, | |
| "grad_norm": 0.7207851409912109, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 11.677, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.5251172136637642, | |
| "grad_norm": 0.7620865702629089, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 11.6855, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.535833891493637, | |
| "grad_norm": 0.8084555268287659, | |
| "learning_rate": 1e-05, | |
| "loss": 11.6791, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.535833891493637, | |
| "eval_loss": 11.683328628540039, | |
| "eval_runtime": 0.1143, | |
| "eval_samples_per_second": 437.419, | |
| "eval_steps_per_second": 113.729, | |
| "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": 163886137344000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |