| { | |
| "best_metric": 4.068567795911804e-05, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.882515168229454, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01765030336458908, | |
| "grad_norm": 106.18191528320312, | |
| "learning_rate": 5e-05, | |
| "loss": 13.2432, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01765030336458908, | |
| "eval_loss": 13.094860076904297, | |
| "eval_runtime": 0.5907, | |
| "eval_samples_per_second": 84.65, | |
| "eval_steps_per_second": 22.009, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03530060672917816, | |
| "grad_norm": 116.89754486083984, | |
| "learning_rate": 0.0001, | |
| "loss": 13.1542, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.052950910093767234, | |
| "grad_norm": 108.49707794189453, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 10.0312, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.07060121345835632, | |
| "grad_norm": 86.93528747558594, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 4.5454, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0882515168229454, | |
| "grad_norm": 74.98580932617188, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 2.2552, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.10590182018753447, | |
| "grad_norm": 31.74031639099121, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 0.3477, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.12355212355212356, | |
| "grad_norm": 2.792018413543701, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 0.0292, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.14120242691671264, | |
| "grad_norm": 1.0474987030029297, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.0235, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.1588527302813017, | |
| "grad_norm": 2.290456771850586, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.0261, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1765030336458908, | |
| "grad_norm": 11.507671356201172, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.1286, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.19415333701047988, | |
| "grad_norm": 9.126189231872559, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.0862, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.21180364037506894, | |
| "grad_norm": 5.316036224365234, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.0683, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.22945394373965802, | |
| "grad_norm": 0.5275075435638428, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.0042, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.2471042471042471, | |
| "grad_norm": 0.12385106831789017, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.0007, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.26475455046883617, | |
| "grad_norm": 0.009042929857969284, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.0001, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2824048538334253, | |
| "grad_norm": 0.013975061476230621, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.0001, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.30005515719801434, | |
| "grad_norm": 0.037294093519449234, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.0001, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.3177054605626034, | |
| "grad_norm": 0.009404132142663002, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.0001, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.3353557639271925, | |
| "grad_norm": 0.0055360570549964905, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.0001, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.3530060672917816, | |
| "grad_norm": 0.005744273774325848, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.0001, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.37065637065637064, | |
| "grad_norm": 0.008507120423018932, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.0001, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.38830667402095975, | |
| "grad_norm": 0.01138891838490963, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.0001, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.4059569773855488, | |
| "grad_norm": 0.010977202095091343, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.0001, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.42360728075013787, | |
| "grad_norm": 0.5794980525970459, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.0023, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.441257584114727, | |
| "grad_norm": 0.013314218260347843, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.0002, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.441257584114727, | |
| "eval_loss": 4.068567795911804e-05, | |
| "eval_runtime": 0.5672, | |
| "eval_samples_per_second": 88.158, | |
| "eval_steps_per_second": 22.921, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.45890788747931605, | |
| "grad_norm": 0.0008449350716546178, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.4765581908439051, | |
| "grad_norm": 0.0008811301086097956, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.4942084942084942, | |
| "grad_norm": 0.0009417127585038543, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.5118587975730833, | |
| "grad_norm": 0.0010093341115862131, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.5295091009376723, | |
| "grad_norm": 0.001085045631043613, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5471594043022614, | |
| "grad_norm": 0.0011195273837074637, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.5648097076668506, | |
| "grad_norm": 0.001229833927936852, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.5824600110314396, | |
| "grad_norm": 0.0019689970649778843, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.6001103143960287, | |
| "grad_norm": 0.019161324948072433, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.0001, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.6177606177606177, | |
| "grad_norm": 0.04453014209866524, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.0001, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.6354109211252068, | |
| "grad_norm": 1.2612073421478271, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.0019, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.6530612244897959, | |
| "grad_norm": 0.002591792494058609, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.0001, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.670711527854385, | |
| "grad_norm": 0.0017153579974547029, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.6883618312189741, | |
| "grad_norm": 0.0007801396423019469, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.7060121345835632, | |
| "grad_norm": 0.0008483222918584943, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.7236624379481522, | |
| "grad_norm": 0.0008646952919661999, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.7413127413127413, | |
| "grad_norm": 0.0009732348844408989, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.7589630446773304, | |
| "grad_norm": 0.0009822549764066935, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.7766133480419195, | |
| "grad_norm": 0.0009263743413612247, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.7942636514065086, | |
| "grad_norm": 0.0009933272376656532, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.8119139547710976, | |
| "grad_norm": 0.0011112219654023647, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.8295642581356867, | |
| "grad_norm": 0.001772879739291966, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.8472145615002757, | |
| "grad_norm": 0.004433015361428261, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.0001, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.8648648648648649, | |
| "grad_norm": 0.009279930032789707, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.0001, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.882515168229454, | |
| "grad_norm": 0.008922255598008633, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0001, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.882515168229454, | |
| "eval_loss": 4.58928661828395e-05, | |
| "eval_runtime": 0.5848, | |
| "eval_samples_per_second": 85.493, | |
| "eval_steps_per_second": 22.228, | |
| "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": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.953470533435392e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |