| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 10554, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.763122986545386e-05, | |
| "loss": 3.8175, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.5262459730907715e-05, | |
| "loss": 2.8101, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 4.289368959636157e-05, | |
| "loss": 2.4786, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.052491946181542e-05, | |
| "loss": 2.3064, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 3.8156149327269285e-05, | |
| "loss": 2.1496, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 3.578737919272314e-05, | |
| "loss": 2.0646, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 3.3418609058177e-05, | |
| "loss": 1.9892, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 3.1049838923630854e-05, | |
| "loss": 1.7539, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 2.8681068789084707e-05, | |
| "loss": 1.7072, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 2.6312298654538564e-05, | |
| "loss": 1.6794, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 2.394352851999242e-05, | |
| "loss": 1.6592, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 2.1574758385446277e-05, | |
| "loss": 1.6435, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 1.9205988250900133e-05, | |
| "loss": 1.6038, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 1.683721811635399e-05, | |
| "loss": 1.5701, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 1.4468447981807845e-05, | |
| "loss": 1.3777, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 1.2099677847261701e-05, | |
| "loss": 1.3635, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 9.73090771271556e-06, | |
| "loss": 1.3521, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 7.362137578169415e-06, | |
| "loss": 1.3458, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 4.993367443623271e-06, | |
| "loss": 1.341, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 2.624597309077127e-06, | |
| "loss": 1.3338, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 2.558271745309835e-07, | |
| "loss": 1.3213, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 10554, | |
| "total_flos": 1.5129661596155904e+16, | |
| "train_loss": 1.8386345003643834, | |
| "train_runtime": 3266.2576, | |
| "train_samples_per_second": 32.311, | |
| "train_steps_per_second": 3.231 | |
| } | |
| ], | |
| "max_steps": 10554, | |
| "num_train_epochs": 3, | |
| "total_flos": 1.5129661596155904e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |