| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.2938090241343127, | |
| "global_step": 2800, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "eval_accuracy": 0.7687216869069928, | |
| "eval_f1": 0.7665424923390772, | |
| "eval_loss": 0.9364227652549744, | |
| "eval_runtime": 684.6631, | |
| "eval_samples_per_second": 197.963, | |
| "eval_steps_per_second": 0.774, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.994774396642183e-06, | |
| "loss": 1.2511, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_accuracy": 0.8296492496569228, | |
| "eval_f1": 0.8293241244922317, | |
| "eval_loss": 0.8166272044181824, | |
| "eval_runtime": 684.0816, | |
| "eval_samples_per_second": 198.131, | |
| "eval_steps_per_second": 0.775, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.989538300104932e-06, | |
| "loss": 0.8696, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_accuracy": 0.846795732562086, | |
| "eval_f1": 0.8476031571339556, | |
| "eval_loss": 0.7674374580383301, | |
| "eval_runtime": 684.9072, | |
| "eval_samples_per_second": 197.892, | |
| "eval_steps_per_second": 0.774, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.98429171038825e-06, | |
| "loss": 0.8001, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_accuracy": 0.8562469565730644, | |
| "eval_f1": 0.8555885462291756, | |
| "eval_loss": 0.7412897348403931, | |
| "eval_runtime": 685.4288, | |
| "eval_samples_per_second": 197.742, | |
| "eval_steps_per_second": 0.773, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 9.97906610703043e-06, | |
| "loss": 0.7653, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_accuracy": 0.8584087119479408, | |
| "eval_f1": 0.8589656756888883, | |
| "eval_loss": 0.7346311807632446, | |
| "eval_runtime": 1253.8639, | |
| "eval_samples_per_second": 108.096, | |
| "eval_steps_per_second": 0.423, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_accuracy": 0.8606590033791262, | |
| "eval_f1": 0.8613764873641668, | |
| "eval_loss": 0.7210016846656799, | |
| "eval_runtime": 749.1336, | |
| "eval_samples_per_second": 180.926, | |
| "eval_steps_per_second": 0.707, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 9.973840503672613e-06, | |
| "loss": 0.7517, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_accuracy": 0.8668491493160589, | |
| "eval_f1": 0.8662439909072627, | |
| "eval_loss": 0.7115087509155273, | |
| "eval_runtime": 748.5848, | |
| "eval_samples_per_second": 181.059, | |
| "eval_steps_per_second": 0.708, | |
| "step": 2800 | |
| } | |
| ], | |
| "max_steps": 953000, | |
| "num_train_epochs": 100, | |
| "total_flos": 1.1748750372701952e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |