| { | |
| "best_metric": 11.931014060974121, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.1283497884344147, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.022566995768688293, | |
| "grad_norm": 0.017333844676613808, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9302, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.022566995768688293, | |
| "eval_loss": 11.933246612548828, | |
| "eval_runtime": 0.1725, | |
| "eval_samples_per_second": 289.865, | |
| "eval_steps_per_second": 75.365, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.045133991537376586, | |
| "grad_norm": 0.019053371623158455, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9316, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.06770098730606489, | |
| "grad_norm": 0.019754186272621155, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 11.9305, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.09026798307475317, | |
| "grad_norm": 0.01678977534174919, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 11.9307, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.11283497884344147, | |
| "grad_norm": 0.020915821194648743, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 11.9308, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.13540197461212977, | |
| "grad_norm": 0.02063576877117157, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 11.9315, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.15796897038081806, | |
| "grad_norm": 0.016847189515829086, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 11.9324, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.18053596614950634, | |
| "grad_norm": 0.019121292978525162, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 11.9334, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.20310296191819463, | |
| "grad_norm": 0.02240542322397232, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 11.9298, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.22566995768688294, | |
| "grad_norm": 0.024457793682813644, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 11.9324, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.24823695345557123, | |
| "grad_norm": 0.031559307128190994, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 11.9334, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.27080394922425954, | |
| "grad_norm": 0.018383698537945747, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 11.9298, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.2933709449929478, | |
| "grad_norm": 0.020455243065953255, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 11.9304, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.3159379407616361, | |
| "grad_norm": 0.02079765871167183, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 11.9296, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.3385049365303244, | |
| "grad_norm": 0.022732308134436607, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 11.9302, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.3610719322990127, | |
| "grad_norm": 0.01656685210764408, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 11.9313, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.383638928067701, | |
| "grad_norm": 0.024003805592656136, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 11.9312, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.40620592383638926, | |
| "grad_norm": 0.032477445900440216, | |
| "learning_rate": 7.75e-05, | |
| "loss": 11.93, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.4287729196050776, | |
| "grad_norm": 0.026340581476688385, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 11.9292, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.4513399153737659, | |
| "grad_norm": 0.025969544425606728, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 11.931, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.47390691114245415, | |
| "grad_norm": 0.02748195454478264, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 11.9331, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.49647390691114246, | |
| "grad_norm": 0.031438447535037994, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 11.9311, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.5190409026798307, | |
| "grad_norm": 0.026204247027635574, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 11.9301, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.5416078984485191, | |
| "grad_norm": 0.024893777444958687, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 11.9315, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.5641748942172073, | |
| "grad_norm": 0.02302592061460018, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 11.9299, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5641748942172073, | |
| "eval_loss": 11.931870460510254, | |
| "eval_runtime": 0.1671, | |
| "eval_samples_per_second": 299.204, | |
| "eval_steps_per_second": 77.793, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5867418899858956, | |
| "grad_norm": 0.032059792429208755, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 11.9294, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.609308885754584, | |
| "grad_norm": 0.028178269043564796, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 11.9301, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.6318758815232722, | |
| "grad_norm": 0.031542014330625534, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 11.9307, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.6544428772919605, | |
| "grad_norm": 0.029014427214860916, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 11.9318, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.6770098730606487, | |
| "grad_norm": 0.03503303602337837, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 11.9302, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.6995768688293371, | |
| "grad_norm": 0.03429326042532921, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 11.9303, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.7221438645980254, | |
| "grad_norm": 0.03715181350708008, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 11.9305, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.7447108603667136, | |
| "grad_norm": 0.038947250694036484, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 11.9309, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.767277856135402, | |
| "grad_norm": 0.030063152313232422, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 11.9303, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.7898448519040903, | |
| "grad_norm": 0.028033409267663956, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 11.9287, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.8124118476727785, | |
| "grad_norm": 0.028053291141986847, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 11.9305, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.8349788434414669, | |
| "grad_norm": 0.028353266417980194, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 11.9292, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.8575458392101551, | |
| "grad_norm": 0.03844644874334335, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 11.9292, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.8801128349788434, | |
| "grad_norm": 0.038593534380197525, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 11.9305, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.9026798307475318, | |
| "grad_norm": 0.03276919573545456, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 11.932, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.92524682651622, | |
| "grad_norm": 0.03799021989107132, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 11.9316, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.9478138222849083, | |
| "grad_norm": 0.03997742384672165, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 11.9304, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.9703808180535967, | |
| "grad_norm": 0.043088801205158234, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 11.9287, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.9929478138222849, | |
| "grad_norm": 0.04122375696897507, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 11.9302, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.0155148095909732, | |
| "grad_norm": 0.06158071011304855, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 21.1064, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.0380818053596614, | |
| "grad_norm": 0.029533565044403076, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 11.4006, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.0606488011283497, | |
| "grad_norm": 0.036127302795648575, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 11.6845, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.0832157968970382, | |
| "grad_norm": 0.03641054779291153, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 11.9889, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.1057827926657264, | |
| "grad_norm": 0.03584923967719078, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 11.8621, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.1283497884344147, | |
| "grad_norm": 0.04079252853989601, | |
| "learning_rate": 1e-05, | |
| "loss": 11.7881, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.1283497884344147, | |
| "eval_loss": 11.931014060974121, | |
| "eval_runtime": 0.1717, | |
| "eval_samples_per_second": 291.157, | |
| "eval_steps_per_second": 75.701, | |
| "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": 1043471597568.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |