| { | |
| "best_metric": 0.9534415899175958, | |
| "best_model_checkpoint": "./results/checkpoint-1000", | |
| "epoch": 0.1547269070091289, | |
| "eval_steps": 500, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01547269070091289, | |
| "grad_norm": 2257314.0, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6363, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.03094538140182578, | |
| "grad_norm": 3129538.0, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4287, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.04641807210273867, | |
| "grad_norm": 3898528.75, | |
| "learning_rate": 3e-05, | |
| "loss": 0.3508, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.06189076280365156, | |
| "grad_norm": 1689890.875, | |
| "learning_rate": 4e-05, | |
| "loss": 0.4636, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.07736345350456444, | |
| "grad_norm": 2084754.375, | |
| "learning_rate": 5e-05, | |
| "loss": 0.268, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.07736345350456444, | |
| "eval_accuracy": 0.9384707581369304, | |
| "eval_f1": 0.9266550339028704, | |
| "eval_loss": 0.16631442308425903, | |
| "eval_precision": 0.877639751552795, | |
| "eval_recall": 0.9814690779191784, | |
| "eval_roc_auc": 0.945872962460679, | |
| "eval_runtime": 764.2798, | |
| "eval_samples_per_second": 266.366, | |
| "eval_steps_per_second": 1.042, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.09283614420547734, | |
| "grad_norm": 2382709.75, | |
| "learning_rate": 4.916149589132987e-05, | |
| "loss": 0.2394, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.10830883490639022, | |
| "grad_norm": 936833.5, | |
| "learning_rate": 4.832299178265974e-05, | |
| "loss": 0.2343, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.12378152560730311, | |
| "grad_norm": 1470909.625, | |
| "learning_rate": 4.7484487673989605e-05, | |
| "loss": 0.1875, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.139254216308216, | |
| "grad_norm": 1565031.125, | |
| "learning_rate": 4.664598356531947e-05, | |
| "loss": 0.1592, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.1547269070091289, | |
| "grad_norm": 450809.3125, | |
| "learning_rate": 4.580747945664934e-05, | |
| "loss": 0.1575, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.1547269070091289, | |
| "eval_accuracy": 0.9622552535146234, | |
| "eval_f1": 0.9534415899175958, | |
| "eval_loss": 0.11282139271497726, | |
| "eval_precision": 0.9320050226255064, | |
| "eval_recall": 0.9758874748827864, | |
| "eval_roc_auc": 0.9646020542376454, | |
| "eval_runtime": 752.2615, | |
| "eval_samples_per_second": 270.621, | |
| "eval_steps_per_second": 1.058, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 6463, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.5502169563136e+18, | |
| "train_batch_size": 128, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |