| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 3380, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.4792899408284024, | |
| "grad_norm": 3.84375, | |
| "learning_rate": 8.520710059171599e-05, | |
| "loss": 0.6478, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.4792899408284024, | |
| "eval_accuracy": 0.8455031356898518, | |
| "eval_f1": 0.012843946055426568, | |
| "eval_loss": 0.4867057204246521, | |
| "eval_precision": 0.010016179983049541, | |
| "eval_recall": 0.01789647577092511, | |
| "eval_runtime": 95.5701, | |
| "eval_samples_per_second": 6.278, | |
| "eval_steps_per_second": 0.785, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.9585798816568047, | |
| "grad_norm": 4.09375, | |
| "learning_rate": 7.041420118343195e-05, | |
| "loss": 0.5008, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.9585798816568047, | |
| "eval_accuracy": 0.8540407639680729, | |
| "eval_f1": 0.016587026967649805, | |
| "eval_loss": 0.4580599069595337, | |
| "eval_precision": 0.013798775472905053, | |
| "eval_recall": 0.020787444933920703, | |
| "eval_runtime": 95.5633, | |
| "eval_samples_per_second": 6.279, | |
| "eval_steps_per_second": 0.785, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.437869822485207, | |
| "grad_norm": 4.125, | |
| "learning_rate": 5.562130177514793e-05, | |
| "loss": 0.4718, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 4.437869822485207, | |
| "eval_accuracy": 0.8557155074116306, | |
| "eval_f1": 0.01738934056007227, | |
| "eval_loss": 0.44876301288604736, | |
| "eval_precision": 0.014739663093415008, | |
| "eval_recall": 0.021200440528634363, | |
| "eval_runtime": 95.5719, | |
| "eval_samples_per_second": 6.278, | |
| "eval_steps_per_second": 0.785, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.9171597633136095, | |
| "grad_norm": 5.0, | |
| "learning_rate": 4.0828402366863904e-05, | |
| "loss": 0.4697, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 5.9171597633136095, | |
| "eval_accuracy": 0.8567702394526796, | |
| "eval_f1": 0.016934408165632433, | |
| "eval_loss": 0.44674479961395264, | |
| "eval_precision": 0.01463072452149514, | |
| "eval_recall": 0.020099118942731278, | |
| "eval_runtime": 95.576, | |
| "eval_samples_per_second": 6.278, | |
| "eval_steps_per_second": 0.785, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 7.396449704142012, | |
| "grad_norm": 5.3125, | |
| "learning_rate": 2.6035502958579882e-05, | |
| "loss": 0.4663, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 7.396449704142012, | |
| "eval_accuracy": 0.8562428734321551, | |
| "eval_f1": 0.017444150582409543, | |
| "eval_loss": 0.4421093761920929, | |
| "eval_precision": 0.01475207004853907, | |
| "eval_recall": 0.021338105726872246, | |
| "eval_runtime": 95.5992, | |
| "eval_samples_per_second": 6.276, | |
| "eval_steps_per_second": 0.785, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 8.875739644970414, | |
| "grad_norm": 6.0, | |
| "learning_rate": 1.1242603550295859e-05, | |
| "loss": 0.4614, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 8.875739644970414, | |
| "eval_accuracy": 0.8567559863169898, | |
| "eval_f1": 0.01658185144948253, | |
| "eval_loss": 0.4435156285762787, | |
| "eval_precision": 0.014180929095354523, | |
| "eval_recall": 0.01996145374449339, | |
| "eval_runtime": 95.7263, | |
| "eval_samples_per_second": 6.268, | |
| "eval_steps_per_second": 0.783, | |
| "step": 3000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 3380, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "total_flos": 2.351623317247311e+18, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |