| { | |
| "best_metric": 6.908915996551514, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.024680693527488123, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004936138705497624, | |
| "grad_norm": 0.12607267498970032, | |
| "learning_rate": 5e-05, | |
| "loss": 6.9388, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004936138705497624, | |
| "eval_loss": 6.934563159942627, | |
| "eval_runtime": 0.379, | |
| "eval_samples_per_second": 131.939, | |
| "eval_steps_per_second": 34.304, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009872277410995249, | |
| "grad_norm": 0.13222505152225494, | |
| "learning_rate": 0.0001, | |
| "loss": 6.938, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0014808416116492873, | |
| "grad_norm": 0.1434653252363205, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 6.9388, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0019744554821990497, | |
| "grad_norm": 0.14161203801631927, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 6.9361, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.002468069352748812, | |
| "grad_norm": 0.13810838758945465, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 6.9376, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0029616832232985746, | |
| "grad_norm": 0.13990676403045654, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 6.9353, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.003455297093848337, | |
| "grad_norm": 0.13130301237106323, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 6.9334, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0039489109643980995, | |
| "grad_norm": 0.13105778396129608, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 6.9349, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004442524834947862, | |
| "grad_norm": 0.1305726319551468, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 6.9327, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004936138705497624, | |
| "grad_norm": 0.13379615545272827, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 6.9335, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005429752576047387, | |
| "grad_norm": 0.13082166016101837, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 6.9336, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.005923366446597149, | |
| "grad_norm": 0.1423841416835785, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 6.9306, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.006416980317146912, | |
| "grad_norm": 0.13897782564163208, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 6.9309, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.006910594187696674, | |
| "grad_norm": 0.1373441517353058, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 6.9296, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.007404208058246437, | |
| "grad_norm": 0.1404893398284912, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 6.9305, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.007897821928796199, | |
| "grad_norm": 0.14130637049674988, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 6.9299, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.008391435799345962, | |
| "grad_norm": 0.14290094375610352, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 6.9256, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.008885049669895725, | |
| "grad_norm": 0.14205792546272278, | |
| "learning_rate": 7.75e-05, | |
| "loss": 6.9287, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.009378663540445486, | |
| "grad_norm": 0.1310996413230896, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 6.9288, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.009872277410995249, | |
| "grad_norm": 0.13495320081710815, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 6.926, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.010365891281545012, | |
| "grad_norm": 0.14342084527015686, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 6.9235, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.010859505152094774, | |
| "grad_norm": 0.1481991857290268, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 6.9218, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.011353119022644536, | |
| "grad_norm": 0.14943259954452515, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 6.9231, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.011846732893194298, | |
| "grad_norm": 0.14566724002361298, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 6.9232, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.012340346763744061, | |
| "grad_norm": 0.15683439373970032, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 6.9184, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.012340346763744061, | |
| "eval_loss": 6.916877269744873, | |
| "eval_runtime": 0.0741, | |
| "eval_samples_per_second": 674.775, | |
| "eval_steps_per_second": 175.441, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.012833960634293824, | |
| "grad_norm": 0.13884158432483673, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 6.9225, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.013327574504843585, | |
| "grad_norm": 0.1499403864145279, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 6.9219, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.013821188375393348, | |
| "grad_norm": 0.1470962017774582, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 6.9218, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.014314802245943111, | |
| "grad_norm": 0.15731434524059296, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 6.9193, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.014808416116492874, | |
| "grad_norm": 0.14495715498924255, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 6.9224, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.015302029987042635, | |
| "grad_norm": 0.15400440990924835, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 6.9177, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.015795643857592398, | |
| "grad_norm": 0.15128593146800995, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 6.9184, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.01628925772814216, | |
| "grad_norm": 0.14144425094127655, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 6.9201, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.016782871598691924, | |
| "grad_norm": 0.1577358841896057, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 6.9144, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.017276485469241685, | |
| "grad_norm": 0.14602337777614594, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 6.9174, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.01777009933979145, | |
| "grad_norm": 0.16055308282375336, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 6.9148, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.01826371321034121, | |
| "grad_norm": 0.1566527783870697, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 6.9134, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.01875732708089097, | |
| "grad_norm": 0.150618776679039, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 6.9186, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.019250940951440736, | |
| "grad_norm": 0.1551329344511032, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 6.9181, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.019744554821990497, | |
| "grad_norm": 0.15703345835208893, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 6.9167, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.020238168692540262, | |
| "grad_norm": 0.1670963615179062, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 6.9153, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.020731782563090023, | |
| "grad_norm": 0.15504442155361176, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 6.9155, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.021225396433639784, | |
| "grad_norm": 0.1557377576828003, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 6.9165, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.02171901030418955, | |
| "grad_norm": 0.15476340055465698, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 6.9163, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.02221262417473931, | |
| "grad_norm": 0.16276222467422485, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 6.9113, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.02270623804528907, | |
| "grad_norm": 0.15289202332496643, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 6.9168, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.023199851915838836, | |
| "grad_norm": 0.1528581827878952, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 6.9146, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.023693465786388597, | |
| "grad_norm": 0.15851595997810364, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 6.9168, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.02418707965693836, | |
| "grad_norm": 0.16302946209907532, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 6.9156, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.024680693527488123, | |
| "grad_norm": 0.16977712512016296, | |
| "learning_rate": 1e-05, | |
| "loss": 6.9121, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.024680693527488123, | |
| "eval_loss": 6.908915996551514, | |
| "eval_runtime": 0.0709, | |
| "eval_samples_per_second": 705.333, | |
| "eval_steps_per_second": 183.387, | |
| "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": 5705957376000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |