| { | |
| "best_metric": 0.29731500148773193, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.3109211037699184, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006218422075398368, | |
| "grad_norm": 0.22229772806167603, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3638, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006218422075398368, | |
| "eval_loss": 0.6265063285827637, | |
| "eval_runtime": 1.401, | |
| "eval_samples_per_second": 35.689, | |
| "eval_steps_per_second": 9.279, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.012436844150796735, | |
| "grad_norm": 0.34933504462242126, | |
| "learning_rate": 0.0001, | |
| "loss": 0.4261, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.018655266226195105, | |
| "grad_norm": 0.3780006766319275, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 0.3986, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.02487368830159347, | |
| "grad_norm": 0.3268946707248688, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 0.3963, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03109211037699184, | |
| "grad_norm": 0.36501720547676086, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 0.3709, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03731053245239021, | |
| "grad_norm": 0.3809024691581726, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 0.3323, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.04352895452778857, | |
| "grad_norm": 0.3877021074295044, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 0.3416, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.04974737660318694, | |
| "grad_norm": 0.29683631658554077, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.3326, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.05596579867858531, | |
| "grad_norm": 0.49793848395347595, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.3584, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.06218422075398368, | |
| "grad_norm": 0.4865315854549408, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.3416, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06840264282938205, | |
| "grad_norm": 0.5153951048851013, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.4089, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.07462106490478042, | |
| "grad_norm": 0.45801788568496704, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.4065, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.08083948698017877, | |
| "grad_norm": 0.09606501460075378, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.3175, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.08705790905557714, | |
| "grad_norm": 0.12753839790821075, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.315, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.09327633113097551, | |
| "grad_norm": 0.2014089673757553, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.3216, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.09949475320637388, | |
| "grad_norm": 0.1620405614376068, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.282, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.10571317528177225, | |
| "grad_norm": 0.12604041397571564, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.2787, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.11193159735717062, | |
| "grad_norm": 0.1285071223974228, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.2843, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.11815001943256899, | |
| "grad_norm": 0.10579027980566025, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.28, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.12436844150796736, | |
| "grad_norm": 0.13292458653450012, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.2943, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.13058686358336571, | |
| "grad_norm": 0.11772623658180237, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.268, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1368052856587641, | |
| "grad_norm": 0.1446559578180313, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.3321, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.14302370773416245, | |
| "grad_norm": 0.18193776905536652, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.3311, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.14924212980956084, | |
| "grad_norm": 0.22447001934051514, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.3661, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.1554605518849592, | |
| "grad_norm": 0.45850419998168945, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.3917, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1554605518849592, | |
| "eval_loss": 0.3052322566509247, | |
| "eval_runtime": 0.6619, | |
| "eval_samples_per_second": 75.543, | |
| "eval_steps_per_second": 19.641, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.16167897396035755, | |
| "grad_norm": 0.05467255786061287, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.3056, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.16789739603575593, | |
| "grad_norm": 0.07083805650472641, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.2749, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.17411581811115429, | |
| "grad_norm": 0.07528531551361084, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.2818, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.18033424018655267, | |
| "grad_norm": 0.09004832059144974, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.2856, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.18655266226195102, | |
| "grad_norm": 0.10006168484687805, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.2992, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1927710843373494, | |
| "grad_norm": 0.10617878288030624, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.2736, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.19898950641274776, | |
| "grad_norm": 0.10531214624643326, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.251, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.20520792848814615, | |
| "grad_norm": 0.12280702590942383, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.2671, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.2114263505635445, | |
| "grad_norm": 0.13969354331493378, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.2841, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.21764477263894286, | |
| "grad_norm": 0.1534193456172943, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.3061, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.22386319471434124, | |
| "grad_norm": 0.17459821701049805, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.3199, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.2300816167897396, | |
| "grad_norm": 0.20583975315093994, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.3434, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.23630003886513798, | |
| "grad_norm": 0.06656050682067871, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.3414, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.24251846094053633, | |
| "grad_norm": 0.06291203200817108, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.2861, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.24873688301593472, | |
| "grad_norm": 0.07160060852766037, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.275, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2549553050913331, | |
| "grad_norm": 0.08236276358366013, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.3031, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.26117372716673143, | |
| "grad_norm": 0.16188380122184753, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.2749, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.2673921492421298, | |
| "grad_norm": 0.0924171581864357, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.2471, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.2736105713175282, | |
| "grad_norm": 0.11398671567440033, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.2917, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.27982899339292655, | |
| "grad_norm": 0.11780249327421188, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.273, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.2860474154683249, | |
| "grad_norm": 0.13337303698062897, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.2713, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.29226583754372326, | |
| "grad_norm": 0.12880964577198029, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.3067, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.2984842596191217, | |
| "grad_norm": 0.14828264713287354, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.3396, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.30470268169452003, | |
| "grad_norm": 0.15794625878334045, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.3561, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.3109211037699184, | |
| "grad_norm": 0.23790889978408813, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3821, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3109211037699184, | |
| "eval_loss": 0.29731500148773193, | |
| "eval_runtime": 0.6608, | |
| "eval_samples_per_second": 75.67, | |
| "eval_steps_per_second": 19.674, | |
| "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": 1.0618540886956442e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |