| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.041322314049587, | |
| "eval_steps": 25, | |
| "global_step": 46, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06611570247933884, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.06611570247933884, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.1652, | |
| "eval_samples_per_second": 617.527, | |
| "eval_steps_per_second": 78.704, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1322314049586777, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.19834710743801653, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.987260573051269e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.2644628099173554, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.949107209404665e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.3305785123966942, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.885734329855798e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.39669421487603307, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.797464868072488e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.4628099173553719, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.68474862499881e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.5289256198347108, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.548159976772592e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5950413223140496, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.388394947836279e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.6611570247933884, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.206267664155907e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.7272727272727273, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.002706204621803e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.7933884297520661, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.778747871771292e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.859504132231405, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.9256198347107438, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.274303669726426e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.9917355371900827, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.996388332556735e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.0578512396694215, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.703204087277988e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.1239669421487604, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.396244933600285e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.1900826446280992, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.077075065009433e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.256198347107438, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.747320897995493e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.322314049586777, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.408662784207149e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.3884297520661157, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.062826447764883e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.4545454545454546, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.7115741913664264e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.5206611570247934, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.3566959159961615e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.5867768595041323, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.6528925619834711, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.643304084003839e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.6528925619834711, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.1845, | |
| "eval_samples_per_second": 552.928, | |
| "eval_steps_per_second": 70.471, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.71900826446281, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.288425808633575e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.7851239669421488, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.937173552235117e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.8512396694214877, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.591337215792852e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.9173553719008265, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.2526791020045086e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.9834710743801653, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9229249349905684e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.049586776859504, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.603755066399718e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.115702479338843, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.296795912722014e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.1818181818181817, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0036116674432654e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.2479338842975207, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.725696330273575e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.3140495867768593, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.3801652892561984, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2212521282287092e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.446280991735537, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.972937953781986e-06, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.512396694214876, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.937323358440935e-06, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.5785123966942147, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.116050521637218e-06, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.644628099173554, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.5184002322740785e-06, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.7107438016528924, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.1525137500119207e-06, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.7768595041322315, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0253513192751373e-06, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.84297520661157, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1426567014420297e-06, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.909090909090909, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.089279059533658e-07, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.975206611570248, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2739426948732424e-07, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 3.041322314049587, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 46 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 46, | |
| "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": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3225781090123776.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |