| { | |
| "best_metric": 0.06400035321712494, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.03067837558001304, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006135675116002607, | |
| "grad_norm": 0.7583703994750977, | |
| "learning_rate": 5e-05, | |
| "loss": 0.7206, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006135675116002607, | |
| "eval_loss": 1.1403805017471313, | |
| "eval_runtime": 4.3679, | |
| "eval_samples_per_second": 11.447, | |
| "eval_steps_per_second": 2.976, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012271350232005214, | |
| "grad_norm": 0.8787322640419006, | |
| "learning_rate": 0.0001, | |
| "loss": 0.8522, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0018407025348007823, | |
| "grad_norm": 0.8613839745521545, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 0.8327, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002454270046401043, | |
| "grad_norm": 0.821357250213623, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 0.6956, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003067837558001304, | |
| "grad_norm": 0.695791482925415, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 0.6351, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0036814050696015645, | |
| "grad_norm": 0.6424224972724915, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 0.4879, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004294972581201826, | |
| "grad_norm": 0.7815857529640198, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 0.4486, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.004908540092802086, | |
| "grad_norm": 0.8228691816329956, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.4152, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005522107604402347, | |
| "grad_norm": 0.6749762892723083, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.3557, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006135675116002608, | |
| "grad_norm": 0.5336638689041138, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.3013, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006749242627602868, | |
| "grad_norm": 0.5431511402130127, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.297, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.007362810139203129, | |
| "grad_norm": 0.5695570111274719, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.2957, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00797637765080339, | |
| "grad_norm": 0.647546112537384, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.2095, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.008589945162403651, | |
| "grad_norm": 0.502677857875824, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.1585, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.009203512674003912, | |
| "grad_norm": 0.4411288797855377, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.1422, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.009817080185604172, | |
| "grad_norm": 0.35536736249923706, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.1201, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.010430647697204433, | |
| "grad_norm": 0.28933218121528625, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.1229, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.011044215208804694, | |
| "grad_norm": 0.30381715297698975, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.125, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.011657782720404955, | |
| "grad_norm": 0.31191951036453247, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.1141, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.012271350232005216, | |
| "grad_norm": 0.31290727853775024, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.112, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.012884917743605477, | |
| "grad_norm": 0.3080437481403351, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.1185, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.013498485255205736, | |
| "grad_norm": 0.26505807042121887, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.1071, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.014112052766805997, | |
| "grad_norm": 0.3317841589450836, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.1331, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.014725620278406258, | |
| "grad_norm": 0.29665809869766235, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.1352, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01533918779000652, | |
| "grad_norm": 0.4122360646724701, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.1553, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01533918779000652, | |
| "eval_loss": 0.09947963058948517, | |
| "eval_runtime": 4.407, | |
| "eval_samples_per_second": 11.346, | |
| "eval_steps_per_second": 2.95, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01595275530160678, | |
| "grad_norm": 0.25747811794281006, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.0904, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.01656632281320704, | |
| "grad_norm": 0.23223653435707092, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.067, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.017179890324807302, | |
| "grad_norm": 0.18984195590019226, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.0735, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.017793457836407563, | |
| "grad_norm": 0.2101801037788391, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.0738, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.018407025348007824, | |
| "grad_norm": 0.21006661653518677, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.0833, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.019020592859608085, | |
| "grad_norm": 0.1932811439037323, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.0652, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.019634160371208343, | |
| "grad_norm": 0.19555415213108063, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.0696, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.020247727882808604, | |
| "grad_norm": 0.24109168350696564, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.0879, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.020861295394408865, | |
| "grad_norm": 0.22455033659934998, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.0833, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.021474862906009126, | |
| "grad_norm": 0.25285103917121887, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.0943, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.022088430417609387, | |
| "grad_norm": 0.2642708718776703, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.0727, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.022701997929209648, | |
| "grad_norm": 0.29292234778404236, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.0934, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.02331556544080991, | |
| "grad_norm": 0.20500828325748444, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.0737, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.02392913295241017, | |
| "grad_norm": 0.14348016679286957, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.049, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.02454270046401043, | |
| "grad_norm": 0.17976398766040802, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.066, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.025156267975610692, | |
| "grad_norm": 0.1790475845336914, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.0617, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.025769835487210953, | |
| "grad_norm": 0.17942076921463013, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.0621, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.026383402998811215, | |
| "grad_norm": 0.15874969959259033, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.0568, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.026996970510411472, | |
| "grad_norm": 0.17187748849391937, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.0622, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.027610538022011733, | |
| "grad_norm": 0.18186913430690765, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.067, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.028224105533611994, | |
| "grad_norm": 0.2198343127965927, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.0678, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.028837673045212255, | |
| "grad_norm": 0.22388826310634613, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.0699, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.029451240556812516, | |
| "grad_norm": 0.21301940083503723, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.0719, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.030064808068412777, | |
| "grad_norm": 0.2947802245616913, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.0896, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.03067837558001304, | |
| "grad_norm": 0.3046525716781616, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0936, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03067837558001304, | |
| "eval_loss": 0.06400035321712494, | |
| "eval_runtime": 4.4283, | |
| "eval_samples_per_second": 11.291, | |
| "eval_steps_per_second": 2.936, | |
| "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": 2.654149397184512e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |