| { | |
| "best_metric": 0.88732, | |
| "best_model_checkpoint": "checkpoint/bert-base/imdb_42/checkpoint-7820", | |
| "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": 0.885, | |
| "eval_loss": 0.2771714925765991, | |
| "eval_runtime": 15.7601, | |
| "eval_samples_per_second": 1586.288, | |
| "eval_steps_per_second": 6.218, | |
| "step": 782 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 4.360613810741688e-05, | |
| "loss": 0.3091, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.88332, | |
| "eval_loss": 0.3185863494873047, | |
| "eval_runtime": 14.8791, | |
| "eval_samples_per_second": 1680.206, | |
| "eval_steps_per_second": 6.586, | |
| "step": 1564 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 3.721227621483376e-05, | |
| "loss": 0.1446, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.88372, | |
| "eval_loss": 0.4319324493408203, | |
| "eval_runtime": 15.634, | |
| "eval_samples_per_second": 1599.077, | |
| "eval_steps_per_second": 6.268, | |
| "step": 2346 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 3.081841432225064e-05, | |
| "loss": 0.0654, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.88224, | |
| "eval_loss": 0.527112603187561, | |
| "eval_runtime": 15.5935, | |
| "eval_samples_per_second": 1603.233, | |
| "eval_steps_per_second": 6.285, | |
| "step": 3128 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.882, | |
| "eval_loss": 0.7103033065795898, | |
| "eval_runtime": 15.6832, | |
| "eval_samples_per_second": 1594.061, | |
| "eval_steps_per_second": 6.249, | |
| "step": 3910 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "learning_rate": 2.442455242966752e-05, | |
| "loss": 0.0255, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.88156, | |
| "eval_loss": 0.7340117692947388, | |
| "eval_runtime": 15.5378, | |
| "eval_samples_per_second": 1608.978, | |
| "eval_steps_per_second": 6.307, | |
| "step": 4692 | |
| }, | |
| { | |
| "epoch": 6.39, | |
| "learning_rate": 1.80306905370844e-05, | |
| "loss": 0.0144, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.88624, | |
| "eval_loss": 0.8043656945228577, | |
| "eval_runtime": 15.5601, | |
| "eval_samples_per_second": 1606.673, | |
| "eval_steps_per_second": 6.298, | |
| "step": 5474 | |
| }, | |
| { | |
| "epoch": 7.67, | |
| "learning_rate": 1.163682864450128e-05, | |
| "loss": 0.0106, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.88544, | |
| "eval_loss": 0.8684703707695007, | |
| "eval_runtime": 15.6281, | |
| "eval_samples_per_second": 1599.681, | |
| "eval_steps_per_second": 6.271, | |
| "step": 6256 | |
| }, | |
| { | |
| "epoch": 8.95, | |
| "learning_rate": 5.242966751918159e-06, | |
| "loss": 0.0049, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.88596, | |
| "eval_loss": 0.8513516187667847, | |
| "eval_runtime": 15.5688, | |
| "eval_samples_per_second": 1605.772, | |
| "eval_steps_per_second": 6.295, | |
| "step": 7038 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.88732, | |
| "eval_loss": 0.8893799185752869, | |
| "eval_runtime": 15.6721, | |
| "eval_samples_per_second": 1595.191, | |
| "eval_steps_per_second": 6.253, | |
| "step": 7820 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 7820, | |
| "total_flos": 1.644444096e+16, | |
| "train_loss": 0.07364957506394447, | |
| "train_runtime": 797.6475, | |
| "train_samples_per_second": 313.422, | |
| "train_steps_per_second": 9.804 | |
| } | |
| ], | |
| "max_steps": 7820, | |
| "num_train_epochs": 10, | |
| "total_flos": 1.644444096e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |