| { |
| "best_metric": 0.678714859437751, |
| "best_model_checkpoint": "./nlu_finetuned_models/rte/bert-base-uncased_lr1e-05/checkpoint-846", |
| "epoch": 10.0, |
| "eval_steps": 500, |
| "global_step": 1410, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.5140562248995983, |
| "eval_loss": 0.6864989995956421, |
| "eval_runtime": 0.2465, |
| "eval_samples_per_second": 1010.112, |
| "eval_steps_per_second": 64.907, |
| "step": 141 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.6144578313253012, |
| "eval_loss": 0.6658010482788086, |
| "eval_runtime": 0.2411, |
| "eval_samples_per_second": 1032.975, |
| "eval_steps_per_second": 66.376, |
| "step": 282 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.642570281124498, |
| "eval_loss": 0.7156305909156799, |
| "eval_runtime": 0.2406, |
| "eval_samples_per_second": 1035.061, |
| "eval_steps_per_second": 66.51, |
| "step": 423 |
| }, |
| { |
| "epoch": 3.546099290780142, |
| "grad_norm": 11.888811111450195, |
| "learning_rate": 6.867924528301887e-06, |
| "loss": 0.5575, |
| "step": 500 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.6385542168674698, |
| "eval_loss": 0.8045499920845032, |
| "eval_runtime": 0.2541, |
| "eval_samples_per_second": 979.981, |
| "eval_steps_per_second": 62.971, |
| "step": 564 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.6465863453815262, |
| "eval_loss": 1.0082933902740479, |
| "eval_runtime": 0.2462, |
| "eval_samples_per_second": 1011.391, |
| "eval_steps_per_second": 64.989, |
| "step": 705 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.678714859437751, |
| "eval_loss": 1.0545072555541992, |
| "eval_runtime": 0.2429, |
| "eval_samples_per_second": 1025.251, |
| "eval_steps_per_second": 65.88, |
| "step": 846 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_accuracy": 0.6706827309236948, |
| "eval_loss": 1.2696497440338135, |
| "eval_runtime": 0.2394, |
| "eval_samples_per_second": 1039.968, |
| "eval_steps_per_second": 66.825, |
| "step": 987 |
| }, |
| { |
| "epoch": 7.092198581560283, |
| "grad_norm": 14.514544486999512, |
| "learning_rate": 3.0943396226415094e-06, |
| "loss": 0.1723, |
| "step": 1000 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_accuracy": 0.6666666666666666, |
| "eval_loss": 1.419777512550354, |
| "eval_runtime": 0.2419, |
| "eval_samples_per_second": 1029.393, |
| "eval_steps_per_second": 66.146, |
| "step": 1128 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_accuracy": 0.6546184738955824, |
| "eval_loss": 1.497279405593872, |
| "eval_runtime": 0.2373, |
| "eval_samples_per_second": 1049.212, |
| "eval_steps_per_second": 67.419, |
| "step": 1269 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_accuracy": 0.6586345381526104, |
| "eval_loss": 1.5089062452316284, |
| "eval_runtime": 0.2374, |
| "eval_samples_per_second": 1049.047, |
| "eval_steps_per_second": 67.409, |
| "step": 1410 |
| }, |
| { |
| "epoch": 10.0, |
| "step": 1410, |
| "total_flos": 1449010137410880.0, |
| "train_loss": 0.2757559431360123, |
| "train_runtime": 115.2955, |
| "train_samples_per_second": 194.37, |
| "train_steps_per_second": 12.229 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 1410, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1449010137410880.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
