| { | |
| "best_metric": 0.8043988943099976, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.4195250659630607, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.028144239226033423, | |
| "grad_norm": 41.251258850097656, | |
| "learning_rate": 5e-05, | |
| "loss": 10.8713, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.028144239226033423, | |
| "eval_loss": 11.611474990844727, | |
| "eval_runtime": 5.2477, | |
| "eval_samples_per_second": 9.528, | |
| "eval_steps_per_second": 2.477, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.056288478452066845, | |
| "grad_norm": 42.86891555786133, | |
| "learning_rate": 0.0001, | |
| "loss": 11.2666, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.08443271767810026, | |
| "grad_norm": 30.683080673217773, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 8.4065, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.11257695690413369, | |
| "grad_norm": 17.567529678344727, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 3.7922, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.14072119613016712, | |
| "grad_norm": 10.173680305480957, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 2.0552, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.16886543535620052, | |
| "grad_norm": 4.438224792480469, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.3103, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.19700967458223395, | |
| "grad_norm": 3.33147931098938, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.0359, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.22515391380826738, | |
| "grad_norm": 2.65921688079834, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.0297, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.2532981530343008, | |
| "grad_norm": 1.5921533107757568, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.9496, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.28144239226033424, | |
| "grad_norm": 2.4922847747802734, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.8046, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3095866314863676, | |
| "grad_norm": 1.0983978509902954, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.7705, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.33773087071240104, | |
| "grad_norm": 0.9080610871315002, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.8037, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.3658751099384345, | |
| "grad_norm": 0.7231888175010681, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.7878, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.3940193491644679, | |
| "grad_norm": 0.5231512784957886, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.7821, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.42216358839050133, | |
| "grad_norm": 0.5364855527877808, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.8491, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.45030782761653476, | |
| "grad_norm": 0.7105052471160889, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.803, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.47845206684256814, | |
| "grad_norm": 0.5208602547645569, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.8514, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.5065963060686016, | |
| "grad_norm": 0.7129954099655151, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.7448, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.534740545294635, | |
| "grad_norm": 0.45417389273643494, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.7259, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.5628847845206685, | |
| "grad_norm": 0.29068127274513245, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.7371, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.5910290237467019, | |
| "grad_norm": 0.7438077926635742, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.776, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.6191732629727352, | |
| "grad_norm": 0.5736115574836731, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.7734, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.6473175021987687, | |
| "grad_norm": 0.9464084506034851, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.8445, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.6754617414248021, | |
| "grad_norm": 0.3483090102672577, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.7999, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.7036059806508356, | |
| "grad_norm": 0.36117613315582275, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.8521, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.7036059806508356, | |
| "eval_loss": 0.8159880042076111, | |
| "eval_runtime": 5.0985, | |
| "eval_samples_per_second": 9.807, | |
| "eval_steps_per_second": 2.55, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.731750219876869, | |
| "grad_norm": 1.0224896669387817, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.809, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.7598944591029023, | |
| "grad_norm": 0.7973669171333313, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.7901, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.7880386983289358, | |
| "grad_norm": 0.9329594969749451, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.746, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.8161829375549692, | |
| "grad_norm": 0.45507898926734924, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.7476, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.8443271767810027, | |
| "grad_norm": 0.4434109926223755, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.7383, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.872471416007036, | |
| "grad_norm": 0.5660054087638855, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.8037, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.9006156552330695, | |
| "grad_norm": 0.256831556558609, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.754, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.9287598944591029, | |
| "grad_norm": 0.424334853887558, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.7718, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.9569041336851363, | |
| "grad_norm": 0.6750025749206543, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.8117, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.9850483729111698, | |
| "grad_norm": 0.5063544511795044, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.7905, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.0255057167985928, | |
| "grad_norm": 0.7037585377693176, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 1.3675, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.0536499560246262, | |
| "grad_norm": 0.29729217290878296, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.6966, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.0817941952506596, | |
| "grad_norm": 0.1905137151479721, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.7452, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.109938434476693, | |
| "grad_norm": 0.3099241852760315, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.7634, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.1380826737027265, | |
| "grad_norm": 0.35693028569221497, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.7997, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.16622691292876, | |
| "grad_norm": 0.22667019069194794, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.7956, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.1943711521547933, | |
| "grad_norm": 0.3850700259208679, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.7755, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.2225153913808267, | |
| "grad_norm": 0.2817460596561432, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.8038, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.2506596306068603, | |
| "grad_norm": 0.30248430371284485, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.8167, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.2788038698328936, | |
| "grad_norm": 0.28060272336006165, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.6941, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.306948109058927, | |
| "grad_norm": 0.2564436197280884, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.7092, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.3350923482849604, | |
| "grad_norm": 0.23669637739658356, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.7473, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.3632365875109937, | |
| "grad_norm": 0.2533303499221802, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.7641, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.3913808267370273, | |
| "grad_norm": 0.33936166763305664, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.8011, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.4195250659630607, | |
| "grad_norm": 0.2788606882095337, | |
| "learning_rate": 1e-05, | |
| "loss": 0.7872, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.4195250659630607, | |
| "eval_loss": 0.8043988943099976, | |
| "eval_runtime": 5.2242, | |
| "eval_samples_per_second": 9.571, | |
| "eval_steps_per_second": 2.488, | |
| "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": 6.631381723512832e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |