| { | |
| "best_metric": 0.8242009132420092, | |
| "best_model_checkpoint": "tmp/tst-translation352/checkpoint-1050", | |
| "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": 0.3470319634703196, | |
| "eval_loss": 0.373898446559906, | |
| "eval_runtime": 6.3352, | |
| "eval_samples_per_second": 69.138, | |
| "eval_steps_per_second": 5.84, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.4680365296803653, | |
| "eval_loss": 0.2931307554244995, | |
| "eval_runtime": 6.311, | |
| "eval_samples_per_second": 69.402, | |
| "eval_steps_per_second": 5.863, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.6118721461187214, | |
| "eval_loss": 0.23119673132896423, | |
| "eval_runtime": 5.6506, | |
| "eval_samples_per_second": 77.513, | |
| "eval_steps_per_second": 6.548, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.6917808219178082, | |
| "eval_loss": 0.1783980280160904, | |
| "eval_runtime": 10.3121, | |
| "eval_samples_per_second": 42.474, | |
| "eval_steps_per_second": 3.588, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 4.76, | |
| "learning_rate": 2.6190476190476192e-05, | |
| "loss": 0.4892, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.7648401826484018, | |
| "eval_loss": 0.16749408841133118, | |
| "eval_runtime": 6.1421, | |
| "eval_samples_per_second": 71.312, | |
| "eval_steps_per_second": 6.024, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.776255707762557, | |
| "eval_loss": 0.16153858602046967, | |
| "eval_runtime": 11.6144, | |
| "eval_samples_per_second": 37.712, | |
| "eval_steps_per_second": 3.186, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.7899543378995434, | |
| "eval_loss": 0.1554407775402069, | |
| "eval_runtime": 7.3539, | |
| "eval_samples_per_second": 59.561, | |
| "eval_steps_per_second": 5.031, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.8105022831050228, | |
| "eval_loss": 0.16994284093379974, | |
| "eval_runtime": 6.2215, | |
| "eval_samples_per_second": 70.401, | |
| "eval_steps_per_second": 5.947, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.815068493150685, | |
| "eval_loss": 0.17339114844799042, | |
| "eval_runtime": 6.998, | |
| "eval_samples_per_second": 62.589, | |
| "eval_steps_per_second": 5.287, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 9.52, | |
| "learning_rate": 2.3809523809523808e-06, | |
| "loss": 0.1412, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.8242009132420092, | |
| "eval_loss": 0.16242149472236633, | |
| "eval_runtime": 6.0509, | |
| "eval_samples_per_second": 72.385, | |
| "eval_steps_per_second": 6.115, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 1050, | |
| "total_flos": 2385811380510720.0, | |
| "train_loss": 0.3063449269249326, | |
| "train_runtime": 361.9602, | |
| "train_samples_per_second": 34.645, | |
| "train_steps_per_second": 2.901 | |
| } | |
| ], | |
| "max_steps": 1050, | |
| "num_train_epochs": 10, | |
| "total_flos": 2385811380510720.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |