| { | |
| "best_metric": 1.0981897115707397, | |
| "best_model_checkpoint": "hBERTv1_no_pretrain_mnli/checkpoint-12272", | |
| "epoch": 9.0, | |
| "global_step": 27612, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.000490006518904824, | |
| "loss": 1.1069, | |
| "step": 3068 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.3544574630667346, | |
| "eval_loss": 1.0985444784164429, | |
| "eval_runtime": 17.187, | |
| "eval_samples_per_second": 571.071, | |
| "eval_steps_per_second": 4.48, | |
| "step": 3068 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.000480006518904824, | |
| "loss": 1.0987, | |
| "step": 6136 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.31818644931227713, | |
| "eval_loss": 1.0985891819000244, | |
| "eval_runtime": 17.1415, | |
| "eval_samples_per_second": 572.587, | |
| "eval_steps_per_second": 4.492, | |
| "step": 6136 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 0.000470006518904824, | |
| "loss": 1.0986, | |
| "step": 9204 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.3273560876209883, | |
| "eval_loss": 1.0984275341033936, | |
| "eval_runtime": 17.1414, | |
| "eval_samples_per_second": 572.589, | |
| "eval_steps_per_second": 4.492, | |
| "step": 9204 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 0.000460009778357236, | |
| "loss": 1.0986, | |
| "step": 12272 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.3544574630667346, | |
| "eval_loss": 1.0981897115707397, | |
| "eval_runtime": 17.1872, | |
| "eval_samples_per_second": 571.065, | |
| "eval_steps_per_second": 4.48, | |
| "step": 12272 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.00045001629726206, | |
| "loss": 1.0986, | |
| "step": 15340 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.3544574630667346, | |
| "eval_loss": 1.0984472036361694, | |
| "eval_runtime": 17.1683, | |
| "eval_samples_per_second": 571.695, | |
| "eval_steps_per_second": 4.485, | |
| "step": 15340 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 0.00044056714471968713, | |
| "loss": 1.0985, | |
| "step": 18408 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.3544574630667346, | |
| "eval_loss": NaN, | |
| "eval_runtime": 17.1388, | |
| "eval_samples_per_second": 572.677, | |
| "eval_steps_per_second": 4.493, | |
| "step": 18408 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 0.0004305671447196871, | |
| "loss": 0.0, | |
| "step": 21476 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.3544574630667346, | |
| "eval_loss": NaN, | |
| "eval_runtime": 17.1475, | |
| "eval_samples_per_second": 572.388, | |
| "eval_steps_per_second": 4.49, | |
| "step": 21476 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 0.0004205671447196871, | |
| "loss": 0.0, | |
| "step": 24544 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.3544574630667346, | |
| "eval_loss": NaN, | |
| "eval_runtime": 17.2161, | |
| "eval_samples_per_second": 570.106, | |
| "eval_steps_per_second": 4.473, | |
| "step": 24544 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 0.0004105671447196871, | |
| "loss": 0.0, | |
| "step": 27612 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.3544574630667346, | |
| "eval_loss": NaN, | |
| "eval_runtime": 17.1444, | |
| "eval_samples_per_second": 572.491, | |
| "eval_steps_per_second": 4.491, | |
| "step": 27612 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "step": 27612, | |
| "total_flos": 5.2342526347680154e+17, | |
| "train_loss": 0.7333283836765944, | |
| "train_runtime": 17892.0454, | |
| "train_samples_per_second": 1097.421, | |
| "train_steps_per_second": 8.574 | |
| } | |
| ], | |
| "max_steps": 153400, | |
| "num_train_epochs": 50, | |
| "total_flos": 5.2342526347680154e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |