| { | |
| "best_metric": 0.28261637687683105, | |
| "best_model_checkpoint": "/home/fbravo/data/all_results/pawsx/roberta_base_bne/epochs_3_bs_64_lr_3e-5/checkpoint-900", | |
| "epoch": 3.0, | |
| "global_step": 2316, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.39, | |
| "eval_accuracy": 0.8794999718666077, | |
| "eval_loss": 0.30226433277130127, | |
| "eval_runtime": 0.8479, | |
| "eval_samples_per_second": 2358.837, | |
| "eval_steps_per_second": 37.741, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 2.3523316062176165e-05, | |
| "loss": 0.318, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "eval_accuracy": 0.8740000128746033, | |
| "eval_loss": 0.33601614832878113, | |
| "eval_runtime": 0.8536, | |
| "eval_samples_per_second": 2343.133, | |
| "eval_steps_per_second": 37.49, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "eval_accuracy": 0.8949999809265137, | |
| "eval_loss": 0.28261637687683105, | |
| "eval_runtime": 0.8516, | |
| "eval_samples_per_second": 2348.387, | |
| "eval_steps_per_second": 37.574, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 1.705958549222798e-05, | |
| "loss": 0.1498, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "eval_accuracy": 0.8949999809265137, | |
| "eval_loss": 0.3580223321914673, | |
| "eval_runtime": 0.8515, | |
| "eval_samples_per_second": 2348.84, | |
| "eval_steps_per_second": 37.581, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 1.0582901554404146e-05, | |
| "loss": 0.101, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "eval_accuracy": 0.8899999856948853, | |
| "eval_loss": 0.33210474252700806, | |
| "eval_runtime": 0.8482, | |
| "eval_samples_per_second": 2357.924, | |
| "eval_steps_per_second": 37.727, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "eval_accuracy": 0.8939999938011169, | |
| "eval_loss": 0.4253285527229309, | |
| "eval_runtime": 0.8518, | |
| "eval_samples_per_second": 2347.886, | |
| "eval_steps_per_second": 37.566, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 4.106217616580311e-06, | |
| "loss": 0.0505, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "eval_accuracy": 0.8985000252723694, | |
| "eval_loss": 0.39427509903907776, | |
| "eval_runtime": 0.8509, | |
| "eval_samples_per_second": 2350.514, | |
| "eval_steps_per_second": 37.608, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 2316, | |
| "total_flos": 8004352140640256.0, | |
| "train_loss": 0.14005086088427607, | |
| "train_runtime": 226.3922, | |
| "train_samples_per_second": 654.629, | |
| "train_steps_per_second": 10.23 | |
| } | |
| ], | |
| "max_steps": 2316, | |
| "num_train_epochs": 3, | |
| "total_flos": 8004352140640256.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |