| { | |
| "best_metric": 0.7785388127853882, | |
| "best_model_checkpoint": "tmp/tst-translation355/checkpoint-840", | |
| "epoch": 10.0, | |
| "global_step": 1050, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.2054794520547945, | |
| "eval_loss": 0.2730105221271515, | |
| "eval_runtime": 13.9745, | |
| "eval_samples_per_second": 31.343, | |
| "eval_steps_per_second": 2.648, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.4132420091324201, | |
| "eval_loss": 0.2166765183210373, | |
| "eval_runtime": 13.9525, | |
| "eval_samples_per_second": 31.392, | |
| "eval_steps_per_second": 2.652, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.6598173515981736, | |
| "eval_loss": 0.16653937101364136, | |
| "eval_runtime": 16.3239, | |
| "eval_samples_per_second": 26.832, | |
| "eval_steps_per_second": 2.267, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.6940639269406392, | |
| "eval_loss": 0.1442675143480301, | |
| "eval_runtime": 13.707, | |
| "eval_samples_per_second": 31.954, | |
| "eval_steps_per_second": 2.699, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 4.76, | |
| "learning_rate": 2.6190476190476192e-05, | |
| "loss": 0.3779, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.7146118721461188, | |
| "eval_loss": 0.1320880502462387, | |
| "eval_runtime": 14.2394, | |
| "eval_samples_per_second": 30.76, | |
| "eval_steps_per_second": 2.598, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.7579908675799086, | |
| "eval_loss": 0.11835604161024094, | |
| "eval_runtime": 14.2589, | |
| "eval_samples_per_second": 30.718, | |
| "eval_steps_per_second": 2.595, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.7579908675799086, | |
| "eval_loss": 0.119329072535038, | |
| "eval_runtime": 14.1651, | |
| "eval_samples_per_second": 30.921, | |
| "eval_steps_per_second": 2.612, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.7785388127853882, | |
| "eval_loss": 0.14183764159679413, | |
| "eval_runtime": 14.017, | |
| "eval_samples_per_second": 31.248, | |
| "eval_steps_per_second": 2.64, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.7602739726027398, | |
| "eval_loss": 0.1450866013765335, | |
| "eval_runtime": 14.0858, | |
| "eval_samples_per_second": 31.095, | |
| "eval_steps_per_second": 2.627, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 9.52, | |
| "learning_rate": 2.3809523809523808e-06, | |
| "loss": 0.0787, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.7625570776255708, | |
| "eval_loss": 0.148654505610466, | |
| "eval_runtime": 15.3383, | |
| "eval_samples_per_second": 28.556, | |
| "eval_steps_per_second": 2.412, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 1050, | |
| "total_flos": 8482350845952000.0, | |
| "train_loss": 0.2194767295746576, | |
| "train_runtime": 810.0029, | |
| "train_samples_per_second": 15.481, | |
| "train_steps_per_second": 1.296 | |
| } | |
| ], | |
| "max_steps": 1050, | |
| "num_train_epochs": 10, | |
| "total_flos": 8482350845952000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |