| { | |
| "best_metric": 0.3470727503299713, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.746268656716418, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.014925373134328358, | |
| "grad_norm": 64.46163177490234, | |
| "learning_rate": 5e-06, | |
| "loss": 14.5135, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.014925373134328358, | |
| "eval_loss": 13.512981414794922, | |
| "eval_runtime": 2.1601, | |
| "eval_samples_per_second": 52.313, | |
| "eval_steps_per_second": 6.944, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.029850746268656716, | |
| "grad_norm": 69.60806274414062, | |
| "learning_rate": 1e-05, | |
| "loss": 13.3071, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04477611940298507, | |
| "grad_norm": 79.73008728027344, | |
| "learning_rate": 1.5e-05, | |
| "loss": 13.0762, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05970149253731343, | |
| "grad_norm": 73.28142547607422, | |
| "learning_rate": 2e-05, | |
| "loss": 13.2359, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.07462686567164178, | |
| "grad_norm": 83.07388305664062, | |
| "learning_rate": 2.5e-05, | |
| "loss": 11.9312, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08955223880597014, | |
| "grad_norm": 145.44117736816406, | |
| "learning_rate": 3e-05, | |
| "loss": 8.7698, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.1044776119402985, | |
| "grad_norm": 138.7646942138672, | |
| "learning_rate": 3.5e-05, | |
| "loss": 7.7651, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.11940298507462686, | |
| "grad_norm": 104.47525024414062, | |
| "learning_rate": 4e-05, | |
| "loss": 4.8383, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.13432835820895522, | |
| "grad_norm": 77.86751556396484, | |
| "learning_rate": 4.5e-05, | |
| "loss": 2.5665, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.14925373134328357, | |
| "grad_norm": 65.10105895996094, | |
| "learning_rate": 5e-05, | |
| "loss": 2.3387, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.16417910447761194, | |
| "grad_norm": 91.4745101928711, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 1.1481, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.1791044776119403, | |
| "grad_norm": 81.2979965209961, | |
| "learning_rate": 6e-05, | |
| "loss": 1.0484, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.19402985074626866, | |
| "grad_norm": 148.3818817138672, | |
| "learning_rate": 6.500000000000001e-05, | |
| "loss": 1.5095, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.208955223880597, | |
| "grad_norm": 47.15331268310547, | |
| "learning_rate": 7e-05, | |
| "loss": 0.9277, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.22388059701492538, | |
| "grad_norm": 22.466577529907227, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.4809, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.23880597014925373, | |
| "grad_norm": 40.23644256591797, | |
| "learning_rate": 8e-05, | |
| "loss": 0.6376, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.2537313432835821, | |
| "grad_norm": 29.990840911865234, | |
| "learning_rate": 8.5e-05, | |
| "loss": 0.4307, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.26865671641791045, | |
| "grad_norm": 32.61766052246094, | |
| "learning_rate": 9e-05, | |
| "loss": 0.6899, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2835820895522388, | |
| "grad_norm": 17.3817081451416, | |
| "learning_rate": 9.5e-05, | |
| "loss": 0.4744, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.29850746268656714, | |
| "grad_norm": 11.87378978729248, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3952, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.31343283582089554, | |
| "grad_norm": 15.681315422058105, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 0.5161, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.3283582089552239, | |
| "grad_norm": 8.95601749420166, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 0.4197, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.34328358208955223, | |
| "grad_norm": 6.909678936004639, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.3946, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.3582089552238806, | |
| "grad_norm": 11.765785217285156, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 0.4364, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.373134328358209, | |
| "grad_norm": 8.819604873657227, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.5176, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.373134328358209, | |
| "eval_loss": 0.3588247001171112, | |
| "eval_runtime": 1.7784, | |
| "eval_samples_per_second": 63.541, | |
| "eval_steps_per_second": 8.435, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3880597014925373, | |
| "grad_norm": 2.579695701599121, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.3718, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.40298507462686567, | |
| "grad_norm": 5.7628350257873535, | |
| "learning_rate": 8.715724127386972e-05, | |
| "loss": 0.3655, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.417910447761194, | |
| "grad_norm": 6.77158784866333, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 0.3935, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.43283582089552236, | |
| "grad_norm": 8.212152481079102, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 0.4286, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.44776119402985076, | |
| "grad_norm": 2.4192326068878174, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.349, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4626865671641791, | |
| "grad_norm": 1.9714003801345825, | |
| "learning_rate": 7.033683215379002e-05, | |
| "loss": 0.3515, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.47761194029850745, | |
| "grad_norm": 13.655623435974121, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.4861, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.4925373134328358, | |
| "grad_norm": 6.084580421447754, | |
| "learning_rate": 6.0395584540887963e-05, | |
| "loss": 0.3744, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.5074626865671642, | |
| "grad_norm": 10.576855659484863, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 0.456, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.5223880597014925, | |
| "grad_norm": 9.503621101379395, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4167, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.5373134328358209, | |
| "grad_norm": 3.3242833614349365, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 0.3957, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5522388059701493, | |
| "grad_norm": 9.451889038085938, | |
| "learning_rate": 3.960441545911204e-05, | |
| "loss": 0.3948, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5671641791044776, | |
| "grad_norm": 6.181709289550781, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.3618, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.582089552238806, | |
| "grad_norm": 6.71756649017334, | |
| "learning_rate": 2.9663167846209998e-05, | |
| "loss": 0.4049, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5970149253731343, | |
| "grad_norm": 4.298834800720215, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.3805, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6119402985074627, | |
| "grad_norm": 3.9876883029937744, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 0.358, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.6268656716417911, | |
| "grad_norm": 6.614153861999512, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 0.3695, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.6417910447761194, | |
| "grad_norm": 0.9489629864692688, | |
| "learning_rate": 1.2842758726130283e-05, | |
| "loss": 0.339, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.6567164179104478, | |
| "grad_norm": 6.705099105834961, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.3795, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.6716417910447762, | |
| "grad_norm": 3.4202003479003906, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.3362, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6865671641791045, | |
| "grad_norm": 1.3196394443511963, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 0.3458, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.7014925373134329, | |
| "grad_norm": 3.5369057655334473, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 0.3614, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.7164179104477612, | |
| "grad_norm": 2.6016862392425537, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 0.3561, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.7313432835820896, | |
| "grad_norm": 3.1364588737487793, | |
| "learning_rate": 2.7390523158633554e-07, | |
| "loss": 0.3334, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.746268656716418, | |
| "grad_norm": 3.0390493869781494, | |
| "learning_rate": 0.0, | |
| "loss": 0.3539, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.746268656716418, | |
| "eval_loss": 0.3470727503299713, | |
| "eval_runtime": 1.7732, | |
| "eval_samples_per_second": 63.725, | |
| "eval_steps_per_second": 8.459, | |
| "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": 3864241215897600.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |