| { |
| "best_global_step": 1350, |
| "best_metric": 0.015210631303489208, |
| "best_model_checkpoint": "/content/drive/MyDrive/model/Roberta_Squad/roberta_qa_squad/checkpoint-1350", |
| "epoch": 1.4060009376465072, |
| "eval_steps": 150, |
| "global_step": 1500, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0009376465072667605, |
| "grad_norm": 8.176928520202637, |
| "learning_rate": 0.0, |
| "loss": 1.5108, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.04688232536333802, |
| "grad_norm": 8.130581855773926, |
| "learning_rate": 3.6738519212746023e-07, |
| "loss": 1.5054, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.09376465072667604, |
| "grad_norm": 8.648624420166016, |
| "learning_rate": 7.422680412371135e-07, |
| "loss": 1.4071, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.14064697609001406, |
| "grad_norm": 6.109848976135254, |
| "learning_rate": 1.1096532333645738e-06, |
| "loss": 0.8935, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.14064697609001406, |
| "eval_accuracy": 0.9943728018757327, |
| "eval_f1": 0.9915671414895327, |
| "eval_loss": 0.2591439187526703, |
| "eval_runtime": 81.2934, |
| "eval_samples_per_second": 104.929, |
| "eval_steps_per_second": 3.284, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.1875293014533521, |
| "grad_norm": 0.5893043875694275, |
| "learning_rate": 1.484536082474227e-06, |
| "loss": 0.1302, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.23441162681669012, |
| "grad_norm": 0.6598557233810425, |
| "learning_rate": 1.8594189315838805e-06, |
| "loss": 0.0508, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.2812939521800281, |
| "grad_norm": 0.34134793281555176, |
| "learning_rate": 2.2343017806935337e-06, |
| "loss": 0.0445, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.2812939521800281, |
| "eval_accuracy": 0.9943728018757327, |
| "eval_f1": 0.9915671414895327, |
| "eval_loss": 0.03849140182137489, |
| "eval_runtime": 81.554, |
| "eval_samples_per_second": 104.593, |
| "eval_steps_per_second": 3.274, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.32817627754336615, |
| "grad_norm": 2.4221816062927246, |
| "learning_rate": 2.6091846298031867e-06, |
| "loss": 0.0543, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.3750586029067042, |
| "grad_norm": 0.2128182053565979, |
| "learning_rate": 2.98406747891284e-06, |
| "loss": 0.039, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.4219409282700422, |
| "grad_norm": 0.5770402550697327, |
| "learning_rate": 3.3589503280224936e-06, |
| "loss": 0.0376, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.4219409282700422, |
| "eval_accuracy": 0.9943728018757327, |
| "eval_f1": 0.9915671414895327, |
| "eval_loss": 0.026231080293655396, |
| "eval_runtime": 82.0333, |
| "eval_samples_per_second": 103.982, |
| "eval_steps_per_second": 3.255, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.46882325363338023, |
| "grad_norm": 2.9004955291748047, |
| "learning_rate": 3.7338331771321466e-06, |
| "loss": 0.0395, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.5157055789967182, |
| "grad_norm": 0.609539806842804, |
| "learning_rate": 4.1087160262418e-06, |
| "loss": 0.0352, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.5625879043600562, |
| "grad_norm": 2.1714508533477783, |
| "learning_rate": 4.4835988753514534e-06, |
| "loss": 0.0255, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.5625879043600562, |
| "eval_accuracy": 0.9943728018757327, |
| "eval_f1": 0.9915671414895327, |
| "eval_loss": 0.022847361862659454, |
| "eval_runtime": 81.5699, |
| "eval_samples_per_second": 104.573, |
| "eval_steps_per_second": 3.273, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.6094702297233943, |
| "grad_norm": 8.338334083557129, |
| "learning_rate": 4.8584817244611065e-06, |
| "loss": 0.0239, |
| "step": 650 |
| }, |
| { |
| "epoch": 0.6563525550867323, |
| "grad_norm": 1.456930160522461, |
| "learning_rate": 5.2333645735707595e-06, |
| "loss": 0.0297, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.7032348804500703, |
| "grad_norm": 0.043082769960165024, |
| "learning_rate": 5.608247422680413e-06, |
| "loss": 0.015, |
| "step": 750 |
| }, |
| { |
| "epoch": 0.7032348804500703, |
| "eval_accuracy": 0.9947245017584995, |
| "eval_f1": 0.9924296993488696, |
| "eval_loss": 0.026663808152079582, |
| "eval_runtime": 81.4503, |
| "eval_samples_per_second": 104.726, |
| "eval_steps_per_second": 3.278, |
| "step": 750 |
| }, |
| { |
| "epoch": 0.7501172058134083, |
| "grad_norm": 0.6943381428718567, |
| "learning_rate": 5.983130271790066e-06, |
| "loss": 0.0251, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.7969995311767464, |
| "grad_norm": 1.7227779626846313, |
| "learning_rate": 6.35801312089972e-06, |
| "loss": 0.0316, |
| "step": 850 |
| }, |
| { |
| "epoch": 0.8438818565400844, |
| "grad_norm": 3.4432597160339355, |
| "learning_rate": 6.72539831302718e-06, |
| "loss": 0.0302, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.8438818565400844, |
| "eval_accuracy": 0.9955451348182884, |
| "eval_f1": 0.9942699931547789, |
| "eval_loss": 0.0194783266633749, |
| "eval_runtime": 81.3456, |
| "eval_samples_per_second": 104.861, |
| "eval_steps_per_second": 3.282, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.8907641819034224, |
| "grad_norm": 0.03146049380302429, |
| "learning_rate": 7.100281162136833e-06, |
| "loss": 0.013, |
| "step": 950 |
| }, |
| { |
| "epoch": 0.9376465072667605, |
| "grad_norm": 0.04733593761920929, |
| "learning_rate": 7.4751640112464875e-06, |
| "loss": 0.0149, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.9845288326300985, |
| "grad_norm": 6.861303806304932, |
| "learning_rate": 7.85004686035614e-06, |
| "loss": 0.0172, |
| "step": 1050 |
| }, |
| { |
| "epoch": 0.9845288326300985, |
| "eval_accuracy": 0.9961313012895663, |
| "eval_f1": 0.9951308645351936, |
| "eval_loss": 0.015716344118118286, |
| "eval_runtime": 81.9547, |
| "eval_samples_per_second": 104.082, |
| "eval_steps_per_second": 3.258, |
| "step": 1050 |
| }, |
| { |
| "epoch": 1.030942334739803, |
| "grad_norm": 0.7189509272575378, |
| "learning_rate": 8.224929709465793e-06, |
| "loss": 0.0149, |
| "step": 1100 |
| }, |
| { |
| "epoch": 1.0778246601031412, |
| "grad_norm": 0.05800914764404297, |
| "learning_rate": 8.599812558575446e-06, |
| "loss": 0.0258, |
| "step": 1150 |
| }, |
| { |
| "epoch": 1.124706985466479, |
| "grad_norm": 0.05400075018405914, |
| "learning_rate": 8.9746954076851e-06, |
| "loss": 0.0184, |
| "step": 1200 |
| }, |
| { |
| "epoch": 1.124706985466479, |
| "eval_accuracy": 0.9964830011723329, |
| "eval_f1": 0.9955277447884284, |
| "eval_loss": 0.016378656029701233, |
| "eval_runtime": 81.207, |
| "eval_samples_per_second": 105.04, |
| "eval_steps_per_second": 3.288, |
| "step": 1200 |
| }, |
| { |
| "epoch": 1.1715893108298172, |
| "grad_norm": 0.014752120710909367, |
| "learning_rate": 9.349578256794754e-06, |
| "loss": 0.008, |
| "step": 1250 |
| }, |
| { |
| "epoch": 1.2184716361931551, |
| "grad_norm": 0.07657089084386826, |
| "learning_rate": 9.724461105904407e-06, |
| "loss": 0.0322, |
| "step": 1300 |
| }, |
| { |
| "epoch": 1.2653539615564933, |
| "grad_norm": 0.028269890695810318, |
| "learning_rate": 1.009934395501406e-05, |
| "loss": 0.0277, |
| "step": 1350 |
| }, |
| { |
| "epoch": 1.2653539615564933, |
| "eval_accuracy": 0.9955451348182884, |
| "eval_f1": 0.9946868955524881, |
| "eval_loss": 0.015210631303489208, |
| "eval_runtime": 81.384, |
| "eval_samples_per_second": 104.812, |
| "eval_steps_per_second": 3.281, |
| "step": 1350 |
| }, |
| { |
| "epoch": 1.3122362869198312, |
| "grad_norm": 0.05029395967721939, |
| "learning_rate": 1.0474226804123713e-05, |
| "loss": 0.0162, |
| "step": 1400 |
| }, |
| { |
| "epoch": 1.3591186122831693, |
| "grad_norm": 0.013746126554906368, |
| "learning_rate": 1.0849109653233366e-05, |
| "loss": 0.007, |
| "step": 1450 |
| }, |
| { |
| "epoch": 1.4060009376465072, |
| "grad_norm": 0.14504247903823853, |
| "learning_rate": 1.122399250234302e-05, |
| "loss": 0.0204, |
| "step": 1500 |
| }, |
| { |
| "epoch": 1.4060009376465072, |
| "eval_accuracy": 0.9951934349355217, |
| "eval_f1": 0.994607890208291, |
| "eval_loss": 0.01869564689695835, |
| "eval_runtime": 81.4744, |
| "eval_samples_per_second": 104.696, |
| "eval_steps_per_second": 3.277, |
| "step": 1500 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 10670, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "save_steps": 150, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 4, |
| "early_stopping_threshold": 0.001 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 3 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2.524671200570573e+16, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
