| { | |
| "best_metric": 0.2748616780165325, | |
| "best_model_checkpoint": "../checkpoint2/roberta_beit/checkpoint-1560", | |
| "epoch": 5.0, | |
| "global_step": 1560, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 4e-05, | |
| "loss": 5.0468, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_acc": 0.1351242983159583, | |
| "eval_f1": 0.006434080129098572, | |
| "eval_loss": 4.231764316558838, | |
| "eval_runtime": 132.0946, | |
| "eval_samples_per_second": 18.88, | |
| "eval_steps_per_second": 0.59, | |
| "eval_wups": 0.17304510572251913, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 3e-05, | |
| "loss": 4.1988, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_acc": 0.19847634322373697, | |
| "eval_f1": 0.013303627810448783, | |
| "eval_loss": 3.8960349559783936, | |
| "eval_runtime": 143.358, | |
| "eval_samples_per_second": 17.397, | |
| "eval_steps_per_second": 0.544, | |
| "eval_wups": 0.2244747719547611, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 2e-05, | |
| "loss": 3.8346, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_acc": 0.23616680032076984, | |
| "eval_f1": 0.024459827814494416, | |
| "eval_loss": 3.7291460037231445, | |
| "eval_runtime": 140.9534, | |
| "eval_samples_per_second": 17.694, | |
| "eval_steps_per_second": 0.553, | |
| "eval_wups": 0.2609480790042663, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 1e-05, | |
| "loss": 3.5694, | |
| "step": 1248 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_acc": 0.24979951884522855, | |
| "eval_f1": 0.029650383091193284, | |
| "eval_loss": 3.598897933959961, | |
| "eval_runtime": 144.0499, | |
| "eval_samples_per_second": 17.313, | |
| "eval_steps_per_second": 0.541, | |
| "eval_wups": 0.27255059088292083, | |
| "step": 1248 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.0, | |
| "loss": 3.3582, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_acc": 0.25100240577385724, | |
| "eval_f1": 0.030046165522131196, | |
| "eval_loss": 3.566617250442505, | |
| "eval_runtime": 142.9069, | |
| "eval_samples_per_second": 17.452, | |
| "eval_steps_per_second": 0.546, | |
| "eval_wups": 0.2748616780165325, | |
| "step": 1560 | |
| } | |
| ], | |
| "max_steps": 1560, | |
| "num_train_epochs": 5, | |
| "total_flos": 0.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |