| { | |
| "best_metric": 0.1114240512251854, | |
| "best_model_checkpoint": "/kaggle/working/BERT-BASE-harsh/checkpoint-4468", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 8936, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.8880931065353626e-05, | |
| "loss": 0.151, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.7761862130707253e-05, | |
| "loss": 0.1135, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1.6642793196060877e-05, | |
| "loss": 0.1061, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1.5523724261414504e-05, | |
| "loss": 0.1125, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 1.4404655326768131e-05, | |
| "loss": 0.1068, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1.3285586392121757e-05, | |
| "loss": 0.0979, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.2166517457475382e-05, | |
| "loss": 0.0952, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 1.1047448522829008e-05, | |
| "loss": 0.1026, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9645255147717099, | |
| "eval_loss": 0.1114240512251854, | |
| "eval_runtime": 219.6711, | |
| "eval_samples_per_second": 81.358, | |
| "eval_steps_per_second": 5.085, | |
| "step": 4468 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 9.928379588182634e-06, | |
| "loss": 0.0949, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 8.809310653536257e-06, | |
| "loss": 0.0605, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 7.690241718889885e-06, | |
| "loss": 0.0595, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 6.57117278424351e-06, | |
| "loss": 0.0658, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 5.452103849597136e-06, | |
| "loss": 0.0622, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 4.3330349149507615e-06, | |
| "loss": 0.0639, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 3.213965980304387e-06, | |
| "loss": 0.0611, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 2.0948970456580127e-06, | |
| "loss": 0.0554, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 9.758281110116385e-07, | |
| "loss": 0.0625, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9682743957027753, | |
| "eval_loss": 0.11515786498785019, | |
| "eval_runtime": 219.7688, | |
| "eval_samples_per_second": 81.322, | |
| "eval_steps_per_second": 5.083, | |
| "step": 8936 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 8936, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "total_flos": 2.592649627027338e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |