| { | |
| "best_metric": 0.5056634304207119, | |
| "best_model_checkpoint": "./results/C5/checkpoint-139", | |
| "epoch": 5.978494623655914, | |
| "eval_steps": 500, | |
| "global_step": 139, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.989247311827957, | |
| "eval_HDIV": 0.18461538461538463, | |
| "eval_QWK": 0.13293330256173552, | |
| "eval_RMSE": 68.86627696168932, | |
| "eval_accuracy": 0.18974358974358974, | |
| "eval_loss": 1.7435897588729858, | |
| "eval_runtime": 223.5722, | |
| "eval_samples_per_second": 0.872, | |
| "eval_steps_per_second": 0.438, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.978494623655914, | |
| "eval_HDIV": 0.07179487179487176, | |
| "eval_QWK": 0.35492010092514725, | |
| "eval_RMSE": 58.21269576920441, | |
| "eval_accuracy": 0.3128205128205128, | |
| "eval_loss": 1.6234976053237915, | |
| "eval_runtime": 223.4808, | |
| "eval_samples_per_second": 0.873, | |
| "eval_steps_per_second": 0.439, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.967741935483871, | |
| "eval_HDIV": 0.10769230769230764, | |
| "eval_QWK": 0.4539788636979496, | |
| "eval_RMSE": 61.76879969195302, | |
| "eval_accuracy": 0.3282051282051282, | |
| "eval_loss": 1.6040664911270142, | |
| "eval_runtime": 223.4382, | |
| "eval_samples_per_second": 0.873, | |
| "eval_steps_per_second": 0.439, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_HDIV": 0.09743589743589742, | |
| "eval_QWK": 0.4958661417322835, | |
| "eval_RMSE": 56.85789754133117, | |
| "eval_accuracy": 0.3435897435897436, | |
| "eval_loss": 1.5939502716064453, | |
| "eval_runtime": 223.4891, | |
| "eval_samples_per_second": 0.873, | |
| "eval_steps_per_second": 0.439, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 4.301075268817204, | |
| "grad_norm": 10.25, | |
| "learning_rate": 3.3082706766917295e-05, | |
| "loss": 1.6435, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 4.989247311827957, | |
| "eval_HDIV": 0.1282051282051282, | |
| "eval_QWK": 0.4161535675479898, | |
| "eval_RMSE": 63.794542005908234, | |
| "eval_accuracy": 0.3333333333333333, | |
| "eval_loss": 1.5479767322540283, | |
| "eval_runtime": 223.3063, | |
| "eval_samples_per_second": 0.873, | |
| "eval_steps_per_second": 0.439, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 5.978494623655914, | |
| "eval_HDIV": 0.07179487179487176, | |
| "eval_QWK": 0.5056634304207119, | |
| "eval_RMSE": 55.543930407635045, | |
| "eval_accuracy": 0.35384615384615387, | |
| "eval_loss": 1.623157024383545, | |
| "eval_runtime": 223.264, | |
| "eval_samples_per_second": 0.873, | |
| "eval_steps_per_second": 0.439, | |
| "step": 139 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 276, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 12, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.3029657030611436e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |