| { | |
| "best_metric": 1.8483147621154785, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.3109211037699184, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.012436844150796735, | |
| "grad_norm": 4.334837913513184, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 4.2908, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.012436844150796735, | |
| "eval_loss": 6.697080135345459, | |
| "eval_runtime": 4.4995, | |
| "eval_samples_per_second": 11.112, | |
| "eval_steps_per_second": 2.889, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02487368830159347, | |
| "grad_norm": 4.578608512878418, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 4.86, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03731053245239021, | |
| "grad_norm": 4.818152904510498, | |
| "learning_rate": 0.0001, | |
| "loss": 4.925, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.04974737660318694, | |
| "grad_norm": 5.355129241943359, | |
| "learning_rate": 9.99571699711836e-05, | |
| "loss": 4.5105, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06218422075398368, | |
| "grad_norm": 5.519801616668701, | |
| "learning_rate": 9.982876141412856e-05, | |
| "loss": 3.597, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.07462106490478042, | |
| "grad_norm": 4.105515480041504, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 2.9274, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.08705790905557714, | |
| "grad_norm": 3.8129172325134277, | |
| "learning_rate": 9.931634888554937e-05, | |
| "loss": 2.7116, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.09949475320637388, | |
| "grad_norm": 3.111717939376831, | |
| "learning_rate": 9.893332032039701e-05, | |
| "loss": 2.4759, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.11193159735717062, | |
| "grad_norm": 3.8541200160980225, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2.2602, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.12436844150796736, | |
| "grad_norm": 3.1858394145965576, | |
| "learning_rate": 9.791726278367022e-05, | |
| "loss": 2.1403, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1368052856587641, | |
| "grad_norm": 2.9167511463165283, | |
| "learning_rate": 9.728616793536588e-05, | |
| "loss": 1.8919, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.14924212980956084, | |
| "grad_norm": 6.798462390899658, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.6077, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.16167897396035755, | |
| "grad_norm": 11.831518173217773, | |
| "learning_rate": 9.578385041664925e-05, | |
| "loss": 3.0053, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.17411581811115429, | |
| "grad_norm": 9.798856735229492, | |
| "learning_rate": 9.491548749301997e-05, | |
| "loss": 2.8547, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.18655266226195102, | |
| "grad_norm": 4.359902858734131, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 2.5411, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.19898950641274776, | |
| "grad_norm": 2.2944040298461914, | |
| "learning_rate": 9.295261506157986e-05, | |
| "loss": 2.3035, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.2114263505635445, | |
| "grad_norm": 2.36320424079895, | |
| "learning_rate": 9.186184199300464e-05, | |
| "loss": 2.1875, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.22386319471434124, | |
| "grad_norm": 2.428184986114502, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 2.1433, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.23630003886513798, | |
| "grad_norm": 2.2989890575408936, | |
| "learning_rate": 8.947199994035401e-05, | |
| "loss": 2.1427, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.24873688301593472, | |
| "grad_norm": 2.1419265270233154, | |
| "learning_rate": 8.817748015645558e-05, | |
| "loss": 1.9281, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.26117372716673143, | |
| "grad_norm": 1.9683345556259155, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.7075, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.2736105713175282, | |
| "grad_norm": 1.7316274642944336, | |
| "learning_rate": 8.540155934270471e-05, | |
| "loss": 1.7915, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.2860474154683249, | |
| "grad_norm": 1.917214035987854, | |
| "learning_rate": 8.392544243589427e-05, | |
| "loss": 1.6485, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.2984842596191217, | |
| "grad_norm": 1.8824145793914795, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.3475, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.3109211037699184, | |
| "grad_norm": 8.887231826782227, | |
| "learning_rate": 8.081093963579707e-05, | |
| "loss": 0.772, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3109211037699184, | |
| "eval_loss": 1.8483147621154785, | |
| "eval_runtime": 4.4758, | |
| "eval_samples_per_second": 11.171, | |
| "eval_steps_per_second": 2.905, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.984041808658432e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |