| { | |
| "best_metric": 1.9435697793960571, | |
| "best_model_checkpoint": "output/little-big/checkpoint-38", | |
| "epoch": 2.0, | |
| "global_step": 38, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00011506151581352585, | |
| "loss": 1.9259, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 6.293505690059801e-05, | |
| "loss": 2.0874, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.4464961055407408e-05, | |
| "loss": 1.9273, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.967223048210144, | |
| "eval_runtime": 1.1752, | |
| "eval_samples_per_second": 21.274, | |
| "eval_steps_per_second": 3.404, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 9.35614586573241e-07, | |
| "loss": 1.9037, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 3.1079356352801514e-05, | |
| "loss": 1.7917, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 8.54403044178588e-05, | |
| "loss": 1.6825, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 0.00012893189933276512, | |
| "loss": 1.6975, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.9435697793960571, | |
| "eval_runtime": 1.1861, | |
| "eval_samples_per_second": 21.078, | |
| "eval_steps_per_second": 3.373, | |
| "step": 38 | |
| } | |
| ], | |
| "max_steps": 38, | |
| "num_train_epochs": 2, | |
| "total_flos": 39455096832000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |