| { | |
| "best_metric": 0.678784966468811, | |
| "best_model_checkpoint": "mobilebert_sa_GLUE_Experiment_logit_kd_cola/checkpoint-268", | |
| "epoch": 9.0, | |
| "global_step": 603, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 4.9e-05, | |
| "loss": 0.8105, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.6861336827278137, | |
| "eval_matthews_correlation": 0.0, | |
| "eval_runtime": 2.5122, | |
| "eval_samples_per_second": 415.174, | |
| "eval_steps_per_second": 3.583, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 4.8e-05, | |
| "loss": 0.7967, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.6866122484207153, | |
| "eval_matthews_correlation": 0.0, | |
| "eval_runtime": 2.4907, | |
| "eval_samples_per_second": 418.752, | |
| "eval_steps_per_second": 3.613, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 4.7e-05, | |
| "loss": 0.7956, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.6835572719573975, | |
| "eval_matthews_correlation": 0.0, | |
| "eval_runtime": 2.5643, | |
| "eval_samples_per_second": 406.732, | |
| "eval_steps_per_second": 3.51, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 4.600000000000001e-05, | |
| "loss": 0.791, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.678784966468811, | |
| "eval_matthews_correlation": 0.0, | |
| "eval_runtime": 2.4862, | |
| "eval_samples_per_second": 419.52, | |
| "eval_steps_per_second": 3.62, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.7253, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.7158414721488953, | |
| "eval_matthews_correlation": 0.08211733464812727, | |
| "eval_runtime": 2.4873, | |
| "eval_samples_per_second": 419.333, | |
| "eval_steps_per_second": 3.618, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 4.4000000000000006e-05, | |
| "loss": 0.6322, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.6941786408424377, | |
| "eval_matthews_correlation": 0.06499224719567617, | |
| "eval_runtime": 2.5194, | |
| "eval_samples_per_second": 413.986, | |
| "eval_steps_per_second": 3.572, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 4.3e-05, | |
| "loss": 0.5874, | |
| "step": 469 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 0.7295144200325012, | |
| "eval_matthews_correlation": 0.08034386400319438, | |
| "eval_runtime": 2.4991, | |
| "eval_samples_per_second": 417.355, | |
| "eval_steps_per_second": 3.601, | |
| "step": 469 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 4.2e-05, | |
| "loss": 0.556, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.7735297679901123, | |
| "eval_matthews_correlation": 0.083300560463545, | |
| "eval_runtime": 2.4978, | |
| "eval_samples_per_second": 417.565, | |
| "eval_steps_per_second": 3.603, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 4.1e-05, | |
| "loss": 0.5308, | |
| "step": 603 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 0.7790567278862, | |
| "eval_matthews_correlation": 0.09696758932386995, | |
| "eval_runtime": 2.4939, | |
| "eval_samples_per_second": 418.229, | |
| "eval_steps_per_second": 3.609, | |
| "step": 603 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "step": 603, | |
| "total_flos": 2412992519995392.0, | |
| "train_loss": 0.6917202445009653, | |
| "train_runtime": 629.6796, | |
| "train_samples_per_second": 678.996, | |
| "train_steps_per_second": 5.32 | |
| } | |
| ], | |
| "max_steps": 3350, | |
| "num_train_epochs": 50, | |
| "total_flos": 2412992519995392.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |