| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 2.4489102363586426, | |
| "learning_rate": 2e-05, | |
| "loss": 1.8047, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 1.8422876596450806, | |
| "learning_rate": 1.9396926207859085e-05, | |
| "loss": 1.3832, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 3.1532328128814697, | |
| "learning_rate": 1.766044443118978e-05, | |
| "loss": 1.1404, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 1.9095581769943237, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 1.068, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 2.4410550594329834, | |
| "learning_rate": 1.1736481776669307e-05, | |
| "loss": 1.014, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 2.7899439334869385, | |
| "learning_rate": 8.263518223330698e-06, | |
| "loss": 1.1168, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 2.6681783199310303, | |
| "learning_rate": 5.000000000000003e-06, | |
| "loss": 0.9987, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 2.2320525646209717, | |
| "learning_rate": 2.339555568810221e-06, | |
| "loss": 1.198, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 1.1953657865524292, | |
| "learning_rate": 6.030737921409169e-07, | |
| "loss": 1.0336, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 2.67486572265625, | |
| "learning_rate": 0.0, | |
| "loss": 1.0806, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 100, | |
| "total_flos": 1253709718659072.0, | |
| "train_loss": 1.1837843036651612, | |
| "train_runtime": 1511.658, | |
| "train_samples_per_second": 0.066, | |
| "train_steps_per_second": 0.066 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 1000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1253709718659072.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |