| { | |
| "best_metric": 0.90888, | |
| "best_model_checkpoint": "checkpoint/electra-base/imdb_42/checkpoint-7038", | |
| "epoch": 10.0, | |
| "global_step": 7820, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.90536, | |
| "eval_loss": 0.23193472623825073, | |
| "eval_runtime": 14.9471, | |
| "eval_samples_per_second": 1672.56, | |
| "eval_steps_per_second": 6.556, | |
| "step": 782 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 4.360613810741688e-05, | |
| "loss": 0.2699, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.90432, | |
| "eval_loss": 0.2524752616882324, | |
| "eval_runtime": 14.5935, | |
| "eval_samples_per_second": 1713.094, | |
| "eval_steps_per_second": 6.715, | |
| "step": 1564 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 3.721227621483376e-05, | |
| "loss": 0.1432, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.90284, | |
| "eval_loss": 0.4573332369327545, | |
| "eval_runtime": 14.9943, | |
| "eval_samples_per_second": 1667.297, | |
| "eval_steps_per_second": 6.536, | |
| "step": 2346 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 3.081841432225064e-05, | |
| "loss": 0.072, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8994, | |
| "eval_loss": 0.411539226770401, | |
| "eval_runtime": 14.9739, | |
| "eval_samples_per_second": 1669.577, | |
| "eval_steps_per_second": 6.545, | |
| "step": 3128 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.9038, | |
| "eval_loss": 0.45995330810546875, | |
| "eval_runtime": 14.943, | |
| "eval_samples_per_second": 1673.022, | |
| "eval_steps_per_second": 6.558, | |
| "step": 3910 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "learning_rate": 2.442455242966752e-05, | |
| "loss": 0.0384, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.9056, | |
| "eval_loss": 0.47831761837005615, | |
| "eval_runtime": 15.0585, | |
| "eval_samples_per_second": 1660.194, | |
| "eval_steps_per_second": 6.508, | |
| "step": 4692 | |
| }, | |
| { | |
| "epoch": 6.39, | |
| "learning_rate": 1.80306905370844e-05, | |
| "loss": 0.0227, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.90184, | |
| "eval_loss": 0.5771753787994385, | |
| "eval_runtime": 15.0276, | |
| "eval_samples_per_second": 1663.606, | |
| "eval_steps_per_second": 6.521, | |
| "step": 5474 | |
| }, | |
| { | |
| "epoch": 7.67, | |
| "learning_rate": 1.163682864450128e-05, | |
| "loss": 0.0144, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.90868, | |
| "eval_loss": 0.5959281921386719, | |
| "eval_runtime": 14.9693, | |
| "eval_samples_per_second": 1670.087, | |
| "eval_steps_per_second": 6.547, | |
| "step": 6256 | |
| }, | |
| { | |
| "epoch": 8.95, | |
| "learning_rate": 5.242966751918159e-06, | |
| "loss": 0.01, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.90888, | |
| "eval_loss": 0.6276312470436096, | |
| "eval_runtime": 14.9974, | |
| "eval_samples_per_second": 1666.955, | |
| "eval_steps_per_second": 6.534, | |
| "step": 7038 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.90888, | |
| "eval_loss": 0.6741125583648682, | |
| "eval_runtime": 14.9871, | |
| "eval_samples_per_second": 1668.106, | |
| "eval_steps_per_second": 6.539, | |
| "step": 7820 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 7820, | |
| "total_flos": 1.644444096e+16, | |
| "train_loss": 0.0733462499535602, | |
| "train_runtime": 793.1279, | |
| "train_samples_per_second": 315.208, | |
| "train_steps_per_second": 9.86 | |
| } | |
| ], | |
| "max_steps": 7820, | |
| "num_train_epochs": 10, | |
| "total_flos": 1.644444096e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |