| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.012, | |
| "eval_steps": 1000, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4e-05, | |
| "loss": 2.2234, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 8e-05, | |
| "loss": 2.1174, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00012, | |
| "loss": 1.9241, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00016, | |
| "loss": 2.141, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9293, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00019789473684210526, | |
| "loss": 2.5304, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00019578947368421054, | |
| "loss": 2.6989, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.0001936842105263158, | |
| "loss": 1.6002, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00019157894736842104, | |
| "loss": 2.1035, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00018947368421052632, | |
| "loss": 2.1115, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.0001873684210526316, | |
| "loss": 1.8284, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00018526315789473685, | |
| "loss": 2.1256, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0001831578947368421, | |
| "loss": 1.8958, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00018105263157894739, | |
| "loss": 1.8952, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00017894736842105264, | |
| "loss": 1.9093, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0001768421052631579, | |
| "loss": 1.6703, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00017473684210526317, | |
| "loss": 1.8382, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00017263157894736842, | |
| "loss": 2.6312, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0001705263157894737, | |
| "loss": 1.6544, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00016842105263157895, | |
| "loss": 2.0619, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00016631578947368423, | |
| "loss": 2.1024, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00016421052631578948, | |
| "loss": 1.8859, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00016210526315789473, | |
| "loss": 1.8444, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00016, | |
| "loss": 2.0529, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00015789473684210527, | |
| "loss": 1.6784, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00015578947368421052, | |
| "loss": 1.9135, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0001536842105263158, | |
| "loss": 1.5979, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00015157894736842108, | |
| "loss": 1.6566, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00014947368421052633, | |
| "loss": 1.766, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00014736842105263158, | |
| "loss": 1.6827, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "total_flos": 2104744175566848.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |