| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.089058524173028, | |
| "global_step": 4000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 2.625e-05, | |
| "loss": 1.5969, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "eval_accuracy": 0.2975871313672922, | |
| "eval_loss": 1.9108707904815674, | |
| "eval_runtime": 414.1526, | |
| "eval_samples_per_second": 3.603, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 2.2423469387755103e-05, | |
| "loss": 0.6315, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "eval_accuracy": 0.7607238605898123, | |
| "eval_loss": 0.705723762512207, | |
| "eval_runtime": 417.2946, | |
| "eval_samples_per_second": 3.575, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 1.8596938775510206e-05, | |
| "loss": 0.2271, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "eval_accuracy": 0.7774798927613941, | |
| "eval_loss": 0.7536256909370422, | |
| "eval_runtime": 427.7625, | |
| "eval_samples_per_second": 3.488, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 5.09, | |
| "learning_rate": 1.4770408163265308e-05, | |
| "loss": 0.089, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 5.09, | |
| "eval_accuracy": 0.8378016085790885, | |
| "eval_loss": 0.7497373819351196, | |
| "eval_runtime": 419.2295, | |
| "eval_samples_per_second": 3.559, | |
| "step": 4000 | |
| } | |
| ], | |
| "max_steps": 7860, | |
| "num_train_epochs": 10, | |
| "total_flos": 3.882544084944e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |