| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 25.0, | |
| "eval_steps": 500, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 1.4377137422561646, | |
| "learning_rate": 9.6e-05, | |
| "loss": 1.3893, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 1.0715755224227905, | |
| "learning_rate": 9.200000000000001e-05, | |
| "loss": 1.3208, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 1.3223804235458374, | |
| "learning_rate": 8.800000000000001e-05, | |
| "loss": 1.2325, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 1.0086308717727661, | |
| "learning_rate": 8.4e-05, | |
| "loss": 1.1514, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 0.9249104261398315, | |
| "learning_rate": 8e-05, | |
| "loss": 1.0826, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 0.9513036012649536, | |
| "learning_rate": 7.6e-05, | |
| "loss": 1.02, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "grad_norm": 1.0480144023895264, | |
| "learning_rate": 7.2e-05, | |
| "loss": 0.9592, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 1.1185643672943115, | |
| "learning_rate": 6.800000000000001e-05, | |
| "loss": 0.8972, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "grad_norm": 1.1805726289749146, | |
| "learning_rate": 6.400000000000001e-05, | |
| "loss": 0.8332, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 1.2669492959976196, | |
| "learning_rate": 6e-05, | |
| "loss": 0.7677, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "grad_norm": 1.3598390817642212, | |
| "learning_rate": 5.6000000000000006e-05, | |
| "loss": 0.7044, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "grad_norm": 1.8499770164489746, | |
| "learning_rate": 5.2000000000000004e-05, | |
| "loss": 0.6446, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "grad_norm": 1.916239857673645, | |
| "learning_rate": 4.8e-05, | |
| "loss": 0.5817, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "grad_norm": 1.4864529371261597, | |
| "learning_rate": 4.4000000000000006e-05, | |
| "loss": 0.5206, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "grad_norm": 1.3958476781845093, | |
| "learning_rate": 4e-05, | |
| "loss": 0.469, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "grad_norm": 1.4041638374328613, | |
| "learning_rate": 3.6e-05, | |
| "loss": 0.4259, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "grad_norm": 1.3738752603530884, | |
| "learning_rate": 3.2000000000000005e-05, | |
| "loss": 0.3871, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "grad_norm": 1.2662386894226074, | |
| "learning_rate": 2.8000000000000003e-05, | |
| "loss": 0.353, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "grad_norm": 1.2382030487060547, | |
| "learning_rate": 2.4e-05, | |
| "loss": 0.325, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "grad_norm": 1.215654969215393, | |
| "learning_rate": 2e-05, | |
| "loss": 0.302, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "grad_norm": 1.1050209999084473, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 0.2824, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "grad_norm": 1.004746675491333, | |
| "learning_rate": 1.2e-05, | |
| "loss": 0.2666, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "grad_norm": 0.944015622138977, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.2544, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "grad_norm": 0.8987796902656555, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.2456, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "grad_norm": 0.8577855825424194, | |
| "learning_rate": 0.0, | |
| "loss": 0.2397, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 25, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.57758680064e+16, | |
| "train_batch_size": 100, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |