| { | |
| "best_metric": 0.05693262815475464, | |
| "best_model_checkpoint": "./models/microsoft/deberta-base_1668615764.565312/checkpoint-9400", | |
| "epoch": 3.0, | |
| "global_step": 14100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.9341843971631205e-05, | |
| "loss": 0.2396, | |
| "step": 469 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.8676595744680853e-05, | |
| "loss": 0.0934, | |
| "step": 938 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.8011347517730498e-05, | |
| "loss": 0.076, | |
| "step": 1407 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1.7346099290780143e-05, | |
| "loss": 0.0742, | |
| "step": 1876 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.6680851063829788e-05, | |
| "loss": 0.0697, | |
| "step": 2345 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 1.6015602836879433e-05, | |
| "loss": 0.0612, | |
| "step": 2814 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1.5350354609929078e-05, | |
| "loss": 0.0645, | |
| "step": 3283 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.4685106382978724e-05, | |
| "loss": 0.0558, | |
| "step": 3752 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 1.401985815602837e-05, | |
| "loss": 0.0559, | |
| "step": 4221 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.3354609929078016e-05, | |
| "loss": 0.0533, | |
| "step": 4690 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9835180063569192, | |
| "eval_f1": 0.8845294916144851, | |
| "eval_loss": 0.05832871422171593, | |
| "eval_precision": 0.8721934369602763, | |
| "eval_recall": 0.8972195078617748, | |
| "eval_runtime": 22.9422, | |
| "eval_samples_per_second": 413.168, | |
| "eval_steps_per_second": 25.848, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 1.268936170212766e-05, | |
| "loss": 0.0432, | |
| "step": 5159 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 1.2024113475177306e-05, | |
| "loss": 0.0426, | |
| "step": 5628 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 1.135886524822695e-05, | |
| "loss": 0.0416, | |
| "step": 6097 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 1.0693617021276597e-05, | |
| "loss": 0.042, | |
| "step": 6566 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 1.0028368794326242e-05, | |
| "loss": 0.0413, | |
| "step": 7035 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 9.363120567375887e-06, | |
| "loss": 0.0388, | |
| "step": 7504 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 8.697872340425533e-06, | |
| "loss": 0.0369, | |
| "step": 7973 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 8.032624113475178e-06, | |
| "loss": 0.039, | |
| "step": 8442 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 7.367375886524823e-06, | |
| "loss": 0.036, | |
| "step": 8911 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 6.702127659574469e-06, | |
| "loss": 0.0397, | |
| "step": 9380 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9839366902741495, | |
| "eval_f1": 0.8953622417309568, | |
| "eval_loss": 0.05693262815475464, | |
| "eval_precision": 0.8937771089669824, | |
| "eval_recall": 0.8969530070178555, | |
| "eval_runtime": 22.8104, | |
| "eval_samples_per_second": 415.555, | |
| "eval_steps_per_second": 25.997, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 6.036879432624114e-06, | |
| "loss": 0.0263, | |
| "step": 9849 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 5.37163120567376e-06, | |
| "loss": 0.0252, | |
| "step": 10318 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 4.707801418439717e-06, | |
| "loss": 0.0254, | |
| "step": 10787 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 4.042553191489362e-06, | |
| "loss": 0.028, | |
| "step": 11256 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 3.377304964539007e-06, | |
| "loss": 0.0256, | |
| "step": 11725 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 2.7120567375886527e-06, | |
| "loss": 0.0242, | |
| "step": 12194 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 2.046808510638298e-06, | |
| "loss": 0.0287, | |
| "step": 12663 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 1.3815602836879433e-06, | |
| "loss": 0.0242, | |
| "step": 13132 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 7.177304964539007e-07, | |
| "loss": 0.025, | |
| "step": 13601 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 5.248226950354611e-08, | |
| "loss": 0.0266, | |
| "step": 14070 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9848035428915137, | |
| "eval_f1": 0.902634593356243, | |
| "eval_loss": 0.06115942820906639, | |
| "eval_precision": 0.8953762782973517, | |
| "eval_recall": 0.9100115483699032, | |
| "eval_runtime": 22.4809, | |
| "eval_samples_per_second": 421.647, | |
| "eval_steps_per_second": 26.378, | |
| "step": 14100 | |
| } | |
| ], | |
| "max_steps": 14100, | |
| "num_train_epochs": 3, | |
| "total_flos": 7109576555415114.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |