| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.0, | |
| "global_step": 1150, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 0.544, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7328431372549019, | |
| "eval_combined_score": 0.7813981676914135, | |
| "eval_f1": 0.8299531981279251, | |
| "eval_loss": 0.5272471308708191, | |
| "eval_runtime": 2.9626, | |
| "eval_samples_per_second": 137.716, | |
| "eval_steps_per_second": 17.215, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.2e-05, | |
| "loss": 0.4034, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7254901960784313, | |
| "eval_combined_score": 0.7776387150604923, | |
| "eval_f1": 0.8297872340425533, | |
| "eval_loss": 0.6210632920265198, | |
| "eval_runtime": 2.9625, | |
| "eval_samples_per_second": 137.721, | |
| "eval_steps_per_second": 17.215, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.2602, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.7230392156862745, | |
| "eval_combined_score": 0.7768119616662257, | |
| "eval_f1": 0.830584707646177, | |
| "eval_loss": 0.9109526872634888, | |
| "eval_runtime": 2.9562, | |
| "eval_samples_per_second": 138.014, | |
| "eval_steps_per_second": 17.252, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.1688, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.7696078431372549, | |
| "eval_combined_score": 0.8092412206039973, | |
| "eval_f1": 0.8488745980707396, | |
| "eval_loss": 0.8639819622039795, | |
| "eval_runtime": 2.9721, | |
| "eval_samples_per_second": 137.276, | |
| "eval_steps_per_second": 17.16, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.0913, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.7720588235294118, | |
| "eval_combined_score": 0.8111501847115659, | |
| "eval_f1": 0.8502415458937198, | |
| "eval_loss": 0.9652777314186096, | |
| "eval_runtime": 2.962, | |
| "eval_samples_per_second": 137.745, | |
| "eval_steps_per_second": 17.218, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "step": 1150, | |
| "total_flos": 3261567627386880.0, | |
| "train_loss": 0.2935443347433339, | |
| "train_runtime": 468.0335, | |
| "train_samples_per_second": 39.185, | |
| "train_steps_per_second": 2.457 | |
| } | |
| ], | |
| "max_steps": 1150, | |
| "num_train_epochs": 5, | |
| "total_flos": 3261567627386880.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |