| { | |
| "best_metric": 0.7034921608463985, | |
| "best_model_checkpoint": "omarmomen/sf_babylm_1/finetune/control_raising_relative_token_position/checkpoint-800", | |
| "epoch": 10.0, | |
| "global_step": 1280, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.56, | |
| "eval_accuracy": 0.6759610176086426, | |
| "eval_f1": 0.6656290750010516, | |
| "eval_loss": 2.702744722366333, | |
| "eval_mcc": 0.3517766360451299, | |
| "eval_runtime": 31.4433, | |
| "eval_samples_per_second": 780.167, | |
| "eval_steps_per_second": 97.541, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "eval_accuracy": 0.673270583152771, | |
| "eval_f1": 0.6733504503403024, | |
| "eval_loss": 3.024230718612671, | |
| "eval_mcc": 0.3467492602821547, | |
| "eval_runtime": 31.5737, | |
| "eval_samples_per_second": 776.943, | |
| "eval_steps_per_second": 97.138, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "learning_rate": 3.0468750000000002e-05, | |
| "loss": 0.035, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 4.69, | |
| "eval_accuracy": 0.6791814565658569, | |
| "eval_f1": 0.6623476917796465, | |
| "eval_loss": 3.0073440074920654, | |
| "eval_mcc": 0.35869913049024865, | |
| "eval_runtime": 31.455, | |
| "eval_samples_per_second": 779.876, | |
| "eval_steps_per_second": 97.504, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 6.25, | |
| "eval_accuracy": 0.684684693813324, | |
| "eval_f1": 0.7034921608463985, | |
| "eval_loss": 3.041003942489624, | |
| "eval_mcc": 0.37473206132796, | |
| "eval_runtime": 31.3563, | |
| "eval_samples_per_second": 782.33, | |
| "eval_steps_per_second": 97.811, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 7.81, | |
| "learning_rate": 1.09375e-05, | |
| "loss": 0.0002, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 7.81, | |
| "eval_accuracy": 0.6741673946380615, | |
| "eval_f1": 0.6745388655889898, | |
| "eval_loss": 3.2542927265167236, | |
| "eval_mcc": 0.34857354071039653, | |
| "eval_runtime": 31.5138, | |
| "eval_samples_per_second": 778.42, | |
| "eval_steps_per_second": 97.322, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 9.38, | |
| "eval_accuracy": 0.6747788786888123, | |
| "eval_f1": 0.6763751419763102, | |
| "eval_loss": 3.2722206115722656, | |
| "eval_mcc": 0.34993760586669787, | |
| "eval_runtime": 31.3294, | |
| "eval_samples_per_second": 783.002, | |
| "eval_steps_per_second": 97.895, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 1280, | |
| "total_flos": 2092658450872320.0, | |
| "train_loss": 0.013747621335642179, | |
| "train_runtime": 397.5816, | |
| "train_samples_per_second": 205.392, | |
| "train_steps_per_second": 3.219 | |
| } | |
| ], | |
| "max_steps": 1280, | |
| "num_train_epochs": 10, | |
| "total_flos": 2092658450872320.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |