| { | |
| "best_metric": 1.0610356330871582, | |
| "best_model_checkpoint": "mobilebert_add_GLUE_Experiment_logit_kd_qnli/checkpoint-3276", | |
| "epoch": 9.0, | |
| "global_step": 7371, | |
| "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": 1.1397, | |
| "step": 819 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.5053999633900788, | |
| "eval_loss": 1.0611544847488403, | |
| "eval_runtime": 12.0737, | |
| "eval_samples_per_second": 452.471, | |
| "eval_steps_per_second": 3.561, | |
| "step": 819 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 4.8e-05, | |
| "loss": 1.1394, | |
| "step": 1638 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.5053999633900788, | |
| "eval_loss": 1.0610606670379639, | |
| "eval_runtime": 12.0421, | |
| "eval_samples_per_second": 453.657, | |
| "eval_steps_per_second": 3.571, | |
| "step": 1638 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 4.7e-05, | |
| "loss": 1.1393, | |
| "step": 2457 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.5053999633900788, | |
| "eval_loss": 1.0616439580917358, | |
| "eval_runtime": 12.0412, | |
| "eval_samples_per_second": 453.691, | |
| "eval_steps_per_second": 3.571, | |
| "step": 2457 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 4.600000000000001e-05, | |
| "loss": 1.1393, | |
| "step": 3276 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.5053999633900788, | |
| "eval_loss": 1.0610356330871582, | |
| "eval_runtime": 12.2467, | |
| "eval_samples_per_second": 446.079, | |
| "eval_steps_per_second": 3.511, | |
| "step": 3276 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 4.5e-05, | |
| "loss": 1.1394, | |
| "step": 4095 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.5053999633900788, | |
| "eval_loss": 1.0612379312515259, | |
| "eval_runtime": 12.0192, | |
| "eval_samples_per_second": 454.522, | |
| "eval_steps_per_second": 3.578, | |
| "step": 4095 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 4.4000000000000006e-05, | |
| "loss": 1.1393, | |
| "step": 4914 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.5053999633900788, | |
| "eval_loss": 1.0612590312957764, | |
| "eval_runtime": 12.209, | |
| "eval_samples_per_second": 447.458, | |
| "eval_steps_per_second": 3.522, | |
| "step": 4914 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 4.3e-05, | |
| "loss": 1.1393, | |
| "step": 5733 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.5053999633900788, | |
| "eval_loss": 1.0614322423934937, | |
| "eval_runtime": 12.0416, | |
| "eval_samples_per_second": 453.678, | |
| "eval_steps_per_second": 3.571, | |
| "step": 5733 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 4.2e-05, | |
| "loss": 1.1393, | |
| "step": 6552 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.5053999633900788, | |
| "eval_loss": 1.0612900257110596, | |
| "eval_runtime": 12.028, | |
| "eval_samples_per_second": 454.19, | |
| "eval_steps_per_second": 3.575, | |
| "step": 6552 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 4.1e-05, | |
| "loss": 1.1392, | |
| "step": 7371 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.5053999633900788, | |
| "eval_loss": 1.0610575675964355, | |
| "eval_runtime": 12.0528, | |
| "eval_samples_per_second": 453.258, | |
| "eval_steps_per_second": 3.568, | |
| "step": 7371 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "step": 7371, | |
| "total_flos": 2.788502631402701e+16, | |
| "train_loss": 1.139348039535214, | |
| "train_runtime": 5578.6907, | |
| "train_samples_per_second": 938.778, | |
| "train_steps_per_second": 7.34 | |
| } | |
| ], | |
| "max_steps": 40950, | |
| "num_train_epochs": 50, | |
| "total_flos": 2.788502631402701e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |