| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.2340425531914896, |
| "global_step": 188, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.05, |
| "learning_rate": 0.00015789473684210524, |
| "loss": 0.7328, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.11, |
| "learning_rate": 0.00029822485207100586, |
| "loss": 0.6679, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.16, |
| "learning_rate": 0.0002804733727810651, |
| "loss": 0.5821, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.21, |
| "learning_rate": 0.00026272189349112423, |
| "loss": 0.5167, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.25, |
| "eval_accuracy": 0.8396584440227703, |
| "eval_loss": 0.4641830027103424, |
| "eval_runtime": 815.2421, |
| "eval_samples_per_second": 1.293, |
| "eval_steps_per_second": 0.021, |
| "step": 47 |
| }, |
| { |
| "epoch": 1.01, |
| "learning_rate": 0.0002449704142011834, |
| "loss": 0.4418, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.06, |
| "learning_rate": 0.00022721893491124259, |
| "loss": 0.4147, |
| "step": 60 |
| }, |
| { |
| "epoch": 1.12, |
| "learning_rate": 0.00020946745562130177, |
| "loss": 0.3811, |
| "step": 70 |
| }, |
| { |
| "epoch": 1.17, |
| "learning_rate": 0.00019171597633136094, |
| "loss": 0.3601, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.22, |
| "learning_rate": 0.0001739644970414201, |
| "loss": 0.3341, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.24, |
| "eval_accuracy": 0.8823529411764706, |
| "eval_loss": 0.363214373588562, |
| "eval_runtime": 789.1022, |
| "eval_samples_per_second": 1.336, |
| "eval_steps_per_second": 0.022, |
| "step": 94 |
| }, |
| { |
| "epoch": 2.02, |
| "learning_rate": 0.00015621301775147929, |
| "loss": 0.3092, |
| "step": 100 |
| }, |
| { |
| "epoch": 2.07, |
| "learning_rate": 0.00013846153846153845, |
| "loss": 0.3099, |
| "step": 110 |
| }, |
| { |
| "epoch": 2.13, |
| "learning_rate": 0.00012071005917159762, |
| "loss": 0.3077, |
| "step": 120 |
| }, |
| { |
| "epoch": 2.18, |
| "learning_rate": 0.00010295857988165678, |
| "loss": 0.3326, |
| "step": 130 |
| }, |
| { |
| "epoch": 2.23, |
| "learning_rate": 8.520710059171597e-05, |
| "loss": 0.2945, |
| "step": 140 |
| }, |
| { |
| "epoch": 2.24, |
| "eval_accuracy": 0.8946869070208728, |
| "eval_loss": 0.3224978744983673, |
| "eval_runtime": 802.0516, |
| "eval_samples_per_second": 1.314, |
| "eval_steps_per_second": 0.021, |
| "step": 141 |
| }, |
| { |
| "epoch": 3.03, |
| "learning_rate": 6.745562130177515e-05, |
| "loss": 0.2907, |
| "step": 150 |
| }, |
| { |
| "epoch": 3.09, |
| "learning_rate": 4.9704142011834316e-05, |
| "loss": 0.2774, |
| "step": 160 |
| }, |
| { |
| "epoch": 3.14, |
| "learning_rate": 3.195266272189349e-05, |
| "loss": 0.289, |
| "step": 170 |
| }, |
| { |
| "epoch": 3.19, |
| "learning_rate": 1.4201183431952662e-05, |
| "loss": 0.2909, |
| "step": 180 |
| }, |
| { |
| "epoch": 3.23, |
| "eval_accuracy": 0.8975332068311196, |
| "eval_loss": 0.31426551938056946, |
| "eval_runtime": 814.9805, |
| "eval_samples_per_second": 1.293, |
| "eval_steps_per_second": 0.021, |
| "step": 188 |
| }, |
| { |
| "epoch": 3.23, |
| "step": 188, |
| "total_flos": 1.4951529009071456e+19, |
| "train_loss": 0.3928315411222742, |
| "train_runtime": 11312.6208, |
| "train_samples_per_second": 1.064, |
| "train_steps_per_second": 0.017 |
| } |
| ], |
| "max_steps": 188, |
| "num_train_epochs": 9223372036854775807, |
| "total_flos": 1.4951529009071456e+19, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
