| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 2.4023845007451565, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04769001490312966, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04769001490312966, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.5091, | |
| "eval_samples_per_second": 98.215, | |
| "eval_steps_per_second": 25.536, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.09538002980625931, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.14307004470938897, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.19076005961251863, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.993832906395583e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.23845007451564829, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.97534852915723e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.28614008941877794, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.94459753267812e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.33383010432190763, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.901664203302126e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.38152011922503726, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.42921013412816694, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.779754323328192e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.47690014903129657, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.701111919237408e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.5245901639344263, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.610954559391703e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.5722801788375559, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.509529358847655e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.6199701937406855, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.6676602086438153, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.274017555754408e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.7153502235469449, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.140576474687264e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.7630402384500745, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.99715682655637e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.8107302533532041, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.844151714648274e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.8584202682563339, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.9061102831594635, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.511087728614862e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.9538002980625931, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.33194175972427e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.0104321907600595, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.14503363531613e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.0581222056631894, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.950875657567623e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.105812220566319, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.1535022354694486, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.542957248827961e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.2011922503725783, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.330314893841101e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.2011922503725783, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.5068, | |
| "eval_samples_per_second": 98.657, | |
| "eval_steps_per_second": 25.651, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.248882265275708, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.11265577295385e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.2965722801788375, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.890576474687263e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.3442622950819672, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.391952309985097, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.435602608679918e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.4396423248882266, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.203955092681039e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.4873323397913563, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.970378084704441e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.535022354694486, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.735511803093249e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.5827123695976155, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.6304023845007451, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.264488196906753e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.6780923994038748, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.0296219152955604e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.7257824143070044, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.7960449073189606e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.773472429210134, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.564397391320084e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.8211624441132637, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.8688524590163933, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.109423525312738e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.9165424739195231, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.887344227046149e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.9642324888226528, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.6696851061589e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.020864381520119, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.45704275117204e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.0685543964232487, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.1162444113263787, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.0491243424323785e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.1639344262295084, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.854966364683872e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.211624441132638, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6680582402757327e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.2593144560357676, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4889122713851394e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.3070044709388973, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.354694485842027, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1558482853517257e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.4023845007451565, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.002843173443631e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.4023845007451565, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.5089, | |
| "eval_samples_per_second": 98.244, | |
| "eval_steps_per_second": 25.543, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 63, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "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": 2.954393347424256e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |