| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 14.06060606060606, | |
| "eval_steps": 500, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0, | |
| "eval_loss": 2.495208501815796, | |
| "eval_runtime": 2.6893, | |
| "eval_samples_per_second": 87.012, | |
| "eval_steps_per_second": 2.975, | |
| "step": 0 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.000299794430213186, | |
| "loss": 2.5615, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "eval_loss": 2.527021646499634, | |
| "eval_runtime": 2.6142, | |
| "eval_samples_per_second": 89.512, | |
| "eval_steps_per_second": 3.06, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "eval_loss": 2.5362284183502197, | |
| "eval_runtime": 2.7127, | |
| "eval_samples_per_second": 86.26, | |
| "eval_steps_per_second": 2.949, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "eval_loss": 2.5337562561035156, | |
| "eval_runtime": 2.65, | |
| "eval_samples_per_second": 88.303, | |
| "eval_steps_per_second": 3.019, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "eval_loss": 2.273432493209839, | |
| "eval_runtime": 2.6565, | |
| "eval_samples_per_second": 88.087, | |
| "eval_steps_per_second": 3.012, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "eval_loss": 2.3209340572357178, | |
| "eval_runtime": 2.6548, | |
| "eval_samples_per_second": 88.143, | |
| "eval_steps_per_second": 3.013, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 6.06, | |
| "eval_loss": 2.102634906768799, | |
| "eval_runtime": 2.6553, | |
| "eval_samples_per_second": 88.127, | |
| "eval_steps_per_second": 3.013, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 7.15, | |
| "learning_rate": 0.0002948888739433602, | |
| "loss": 2.3634, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 7.15, | |
| "eval_loss": 2.0141050815582275, | |
| "eval_runtime": 2.6618, | |
| "eval_samples_per_second": 87.911, | |
| "eval_steps_per_second": 3.005, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 7.15, | |
| "eval_loss": 2.0772061347961426, | |
| "eval_runtime": 2.6548, | |
| "eval_samples_per_second": 88.141, | |
| "eval_steps_per_second": 3.013, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 9.09, | |
| "eval_loss": 1.9678362607955933, | |
| "eval_runtime": 2.6714, | |
| "eval_samples_per_second": 87.596, | |
| "eval_steps_per_second": 2.995, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 9.09, | |
| "eval_loss": 1.8939728736877441, | |
| "eval_runtime": 2.6704, | |
| "eval_samples_per_second": 87.627, | |
| "eval_steps_per_second": 2.996, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 11.03, | |
| "eval_loss": 1.812046766281128, | |
| "eval_runtime": 2.6479, | |
| "eval_samples_per_second": 88.374, | |
| "eval_steps_per_second": 3.021, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 12.12, | |
| "eval_loss": 1.8151631355285645, | |
| "eval_runtime": 2.6396, | |
| "eval_samples_per_second": 88.651, | |
| "eval_steps_per_second": 3.031, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 12.12, | |
| "eval_loss": 1.7991279363632202, | |
| "eval_runtime": 2.6349, | |
| "eval_samples_per_second": 88.807, | |
| "eval_steps_per_second": 3.036, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 14.06, | |
| "eval_loss": 1.7646088600158691, | |
| "eval_runtime": 2.6455, | |
| "eval_samples_per_second": 88.453, | |
| "eval_steps_per_second": 3.024, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 14.06, | |
| "step": 9, | |
| "total_flos": 2602157207453696.0, | |
| "train_loss": 2.256301376554701, | |
| "train_runtime": 1141.7556, | |
| "train_samples_per_second": 27.55, | |
| "train_steps_per_second": 0.053 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 60, | |
| "num_train_epochs": 15, | |
| "save_steps": 500, | |
| "total_flos": 2602157207453696.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |