| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.46920821114369504, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0093841642228739, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0093841642228739, | |
| "eval_loss": NaN, | |
| "eval_runtime": 14.5374, | |
| "eval_samples_per_second": 98.78, | |
| "eval_steps_per_second": 6.191, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0187683284457478, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0281524926686217, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0375366568914956, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0469208211143695, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0563049853372434, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.997266286704631e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0656891495601173, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.989068136093873e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0750733137829912, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.975414512725057e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0844574780058651, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.956320346634876e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.093841642228739, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1032258064516129, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.901899829374047e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.1126099706744868, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.86663298624003e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.1219941348973607, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.826044551386744e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1313782991202346, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.780178907671789e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.14076246334310852, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1501466275659824, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.672822322997305e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.15953079178885632, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.611448774886924e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.1689149560117302, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.545032675245813e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.17829912023460412, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.473646649103818e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.187683284457478, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.19706744868035192, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.316282404787871e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.2064516129032258, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.230476262104677e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.21583577712609972, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.140044155740101e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.2252199413489736, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.23460410557184752, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.23460410557184752, | |
| "eval_loss": NaN, | |
| "eval_runtime": 14.5302, | |
| "eval_samples_per_second": 98.829, | |
| "eval_steps_per_second": 6.194, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2439882697947214, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.842005554284296e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.2533724340175953, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.73410738492077e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.2627565982404692, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.622126023955446e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.2721407624633431, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.506183921362443e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.28152492668621704, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.386407858128706e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2909090909090909, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.262928807620843e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.3002932551319648, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.135881792367686e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.3096774193548387, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.005405736415126e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.31906158357771264, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.871643313414718e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.3284457478005865, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.734740790612136e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.3378299120234604, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.594847868906076e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.3472140762463343, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.452117519152542e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.35659824046920824, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.30670581489344e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.3659824046920821, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.158771761692464e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.375366568914956, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.008477123264848e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3847507331378299, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.855986244591104e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.39413489736070384, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.701465872208216e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.4035190615835777, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.4129032258064516, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.387014543809223e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.4222873900293255, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.227427435703997e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.43167155425219944, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.066498153718735e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.4410557184750733, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.90440267166055e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.4504398826979472, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.74131823855921e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.45982404692082113, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.577423184847932e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.46920821114369504, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.4128967273616625e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.46920821114369504, | |
| "eval_loss": NaN, | |
| "eval_runtime": 14.5301, | |
| "eval_samples_per_second": 98.829, | |
| "eval_steps_per_second": 6.194, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "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": 2.119072707772416e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |