| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.292993630573248, | |
| "eval_steps": 100, | |
| "global_step": 1616, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 2e-05, | |
| "loss": 1.1355, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 1.157366156578064, | |
| "eval_runtime": 30.4555, | |
| "eval_samples_per_second": 65.67, | |
| "eval_steps_per_second": 1.051, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 2e-05, | |
| "loss": 0.881, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "eval_loss": 1.3262789249420166, | |
| "eval_runtime": 29.1383, | |
| "eval_samples_per_second": 68.638, | |
| "eval_steps_per_second": 1.098, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 2e-05, | |
| "loss": 0.5496, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "eval_loss": 1.3176809549331665, | |
| "eval_runtime": 28.8909, | |
| "eval_samples_per_second": 69.226, | |
| "eval_steps_per_second": 1.108, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2597, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "eval_loss": 1.5806535482406616, | |
| "eval_runtime": 29.1193, | |
| "eval_samples_per_second": 68.683, | |
| "eval_steps_per_second": 1.099, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 2e-05, | |
| "loss": 0.1877, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "eval_loss": 1.7526657581329346, | |
| "eval_runtime": 29.1196, | |
| "eval_samples_per_second": 68.682, | |
| "eval_steps_per_second": 1.099, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 2e-05, | |
| "loss": 0.1158, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "eval_loss": 1.7486767768859863, | |
| "eval_runtime": 29.2706, | |
| "eval_samples_per_second": 68.328, | |
| "eval_steps_per_second": 1.093, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 4.46, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0855, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 4.46, | |
| "eval_loss": 1.873838186264038, | |
| "eval_runtime": 29.2292, | |
| "eval_samples_per_second": 68.425, | |
| "eval_steps_per_second": 1.095, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 5.1, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0645, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 5.1, | |
| "eval_loss": 1.9275007247924805, | |
| "eval_runtime": 29.013, | |
| "eval_samples_per_second": 68.935, | |
| "eval_steps_per_second": 1.103, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 5.73, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0518, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 5.73, | |
| "eval_loss": 1.9070993661880493, | |
| "eval_runtime": 30.5536, | |
| "eval_samples_per_second": 65.459, | |
| "eval_steps_per_second": 1.047, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 6.37, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0464, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 6.37, | |
| "eval_loss": 1.9601927995681763, | |
| "eval_runtime": 28.9827, | |
| "eval_samples_per_second": 69.007, | |
| "eval_steps_per_second": 1.104, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0367, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "eval_loss": 1.973179817199707, | |
| "eval_runtime": 29.0672, | |
| "eval_samples_per_second": 68.806, | |
| "eval_steps_per_second": 1.101, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 7.64, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0288, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 7.64, | |
| "eval_loss": 2.0399632453918457, | |
| "eval_runtime": 29.0049, | |
| "eval_samples_per_second": 68.954, | |
| "eval_steps_per_second": 1.103, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 8.28, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0265, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 8.28, | |
| "eval_loss": 2.0276734828948975, | |
| "eval_runtime": 28.9115, | |
| "eval_samples_per_second": 69.177, | |
| "eval_steps_per_second": 1.107, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 8.92, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0287, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 8.92, | |
| "eval_loss": 2.049071788787842, | |
| "eval_runtime": 29.0231, | |
| "eval_samples_per_second": 68.911, | |
| "eval_steps_per_second": 1.103, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 9.55, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0195, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 9.55, | |
| "eval_loss": 2.043515205383301, | |
| "eval_runtime": 29.1891, | |
| "eval_samples_per_second": 68.519, | |
| "eval_steps_per_second": 1.096, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 10.19, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0215, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 10.19, | |
| "eval_loss": 2.101804733276367, | |
| "eval_runtime": 28.9478, | |
| "eval_samples_per_second": 69.09, | |
| "eval_steps_per_second": 1.105, | |
| "step": 1600 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 1616, | |
| "num_train_epochs": 11, | |
| "save_steps": 808, | |
| "total_flos": 0.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |