| { | |
| "best_metric": 1.0433918237686157, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.9093078758949882, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03818615751789976, | |
| "grad_norm": 0.598337709903717, | |
| "learning_rate": 5e-05, | |
| "loss": 1.3305, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03818615751789976, | |
| "eval_loss": 1.3011970520019531, | |
| "eval_runtime": 3.8681, | |
| "eval_samples_per_second": 12.926, | |
| "eval_steps_per_second": 3.361, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07637231503579953, | |
| "grad_norm": 0.63288813829422, | |
| "learning_rate": 0.0001, | |
| "loss": 1.3475, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.11455847255369929, | |
| "grad_norm": 0.5574071407318115, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 1.2604, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.15274463007159905, | |
| "grad_norm": 0.5159134268760681, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 1.1942, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.1909307875894988, | |
| "grad_norm": 0.6356820464134216, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 1.2512, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.22911694510739858, | |
| "grad_norm": 0.37804216146469116, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.2074, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.26730310262529833, | |
| "grad_norm": 0.3053663969039917, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.2112, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.3054892601431981, | |
| "grad_norm": 0.2931787073612213, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.1615, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.3436754176610978, | |
| "grad_norm": 0.25367945432662964, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.1396, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3818615751789976, | |
| "grad_norm": 0.20709821581840515, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.0884, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4200477326968974, | |
| "grad_norm": 0.21825897693634033, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.1018, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.45823389021479716, | |
| "grad_norm": 0.23478585481643677, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.1477, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.4964200477326969, | |
| "grad_norm": 0.2821744382381439, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.2513, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5346062052505967, | |
| "grad_norm": 0.3008337616920471, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.1062, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5727923627684964, | |
| "grad_norm": 0.26872631907463074, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 1.0936, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6109785202863962, | |
| "grad_norm": 0.22524605691432953, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.0977, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.649164677804296, | |
| "grad_norm": 0.2258208841085434, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.0668, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.6873508353221957, | |
| "grad_norm": 0.23417900502681732, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.1043, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.7255369928400954, | |
| "grad_norm": 0.26141414046287537, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.1187, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7637231503579952, | |
| "grad_norm": 0.2536011040210724, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.1744, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.801909307875895, | |
| "grad_norm": 0.20398104190826416, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 1.0902, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.8400954653937948, | |
| "grad_norm": 0.2584631145000458, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.1053, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.8782816229116945, | |
| "grad_norm": 0.24347423017024994, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 1.0866, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.9164677804295943, | |
| "grad_norm": 0.25506117939949036, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.1008, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.954653937947494, | |
| "grad_norm": 0.21184368431568146, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 1.1233, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.954653937947494, | |
| "eval_loss": 1.0651795864105225, | |
| "eval_runtime": 3.4914, | |
| "eval_samples_per_second": 14.321, | |
| "eval_steps_per_second": 3.723, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.9928400954653938, | |
| "grad_norm": 0.22500985860824585, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 1.0603, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.0310262529832936, | |
| "grad_norm": 0.4766336977481842, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 2.0533, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.0692124105011933, | |
| "grad_norm": 0.2036180943250656, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 1.0609, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.107398568019093, | |
| "grad_norm": 0.1957828253507614, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 1.0562, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.1455847255369929, | |
| "grad_norm": 0.199952632188797, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 1.0406, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.1837708830548925, | |
| "grad_norm": 0.20388226211071014, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 1.0644, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.2219570405727924, | |
| "grad_norm": 0.21528272330760956, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 1.0359, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.260143198090692, | |
| "grad_norm": 0.21346765756607056, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 1.0727, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.2983293556085918, | |
| "grad_norm": 0.2118886560201645, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 1.0475, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.3365155131264916, | |
| "grad_norm": 0.2171202301979065, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 1.0706, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.3747016706443915, | |
| "grad_norm": 0.2041509449481964, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 1.0409, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.4128878281622912, | |
| "grad_norm": 0.19373871386051178, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 1.0167, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.4510739856801909, | |
| "grad_norm": 0.2035079449415207, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 1.0841, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.4892601431980907, | |
| "grad_norm": 0.22423155605793, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 1.0604, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.5274463007159904, | |
| "grad_norm": 0.19593113660812378, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 1.0352, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.5656324582338903, | |
| "grad_norm": 0.19927962124347687, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 1.0087, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.60381861575179, | |
| "grad_norm": 0.19032032787799835, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 1.0021, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.6420047732696896, | |
| "grad_norm": 0.2027662694454193, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.9654, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.6801909307875895, | |
| "grad_norm": 0.20297980308532715, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 1.035, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.7183770883054894, | |
| "grad_norm": 0.23470035195350647, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 1.0552, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.756563245823389, | |
| "grad_norm": 0.22237010300159454, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 1.0851, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.7947494033412887, | |
| "grad_norm": 0.2051822692155838, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 1.0682, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.8329355608591884, | |
| "grad_norm": 0.19624276459217072, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 1.0594, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.8711217183770883, | |
| "grad_norm": 0.19812841713428497, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 1.0042, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.9093078758949882, | |
| "grad_norm": 0.1921299695968628, | |
| "learning_rate": 1e-05, | |
| "loss": 1.0595, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.9093078758949882, | |
| "eval_loss": 1.0433918237686157, | |
| "eval_runtime": 3.5223, | |
| "eval_samples_per_second": 14.195, | |
| "eval_steps_per_second": 3.691, | |
| "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": 5.968083617316864e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |