| { | |
| "best_metric": 0.6790423036479818, | |
| "best_model_checkpoint": "final_models/glue_models/structroberta_s2_50ep//finetune/main_verb_relative_token_position/checkpoint-1200", | |
| "epoch": 10.0, | |
| "global_step": 1280, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.56, | |
| "eval_accuracy": 0.6725444793701172, | |
| "eval_f1": 0.6708902691511387, | |
| "eval_loss": 2.7541887760162354, | |
| "eval_mcc": 0.34507245422899463, | |
| "eval_runtime": 51.6941, | |
| "eval_samples_per_second": 469.531, | |
| "eval_steps_per_second": 58.691, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "eval_accuracy": 0.6740688681602478, | |
| "eval_f1": 0.6786889240891921, | |
| "eval_loss": 3.085253953933716, | |
| "eval_mcc": 0.3485066175729402, | |
| "eval_runtime": 51.5994, | |
| "eval_samples_per_second": 470.393, | |
| "eval_steps_per_second": 58.799, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "learning_rate": 3.0468750000000002e-05, | |
| "loss": 0.0171, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 4.69, | |
| "eval_accuracy": 0.6735745072364807, | |
| "eval_f1": 0.6789057750759878, | |
| "eval_loss": 3.2460763454437256, | |
| "eval_mcc": 0.3475948939016053, | |
| "eval_runtime": 51.6143, | |
| "eval_samples_per_second": 470.258, | |
| "eval_steps_per_second": 58.782, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 6.25, | |
| "eval_accuracy": 0.673368513584137, | |
| "eval_f1": 0.6789763524457402, | |
| "eval_loss": 3.3441622257232666, | |
| "eval_mcc": 0.34721462917043855, | |
| "eval_runtime": 51.4134, | |
| "eval_samples_per_second": 472.095, | |
| "eval_steps_per_second": 59.012, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 7.81, | |
| "learning_rate": 1.09375e-05, | |
| "loss": 0.0, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 7.81, | |
| "eval_accuracy": 0.6730800867080688, | |
| "eval_f1": 0.6789918686030989, | |
| "eval_loss": 3.403488874435425, | |
| "eval_mcc": 0.34667361274175734, | |
| "eval_runtime": 51.612, | |
| "eval_samples_per_second": 470.278, | |
| "eval_steps_per_second": 58.785, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 9.38, | |
| "eval_accuracy": 0.673038899898529, | |
| "eval_f1": 0.6790423036479818, | |
| "eval_loss": 3.4321446418762207, | |
| "eval_mcc": 0.34660241883503, | |
| "eval_runtime": 51.4782, | |
| "eval_samples_per_second": 471.501, | |
| "eval_steps_per_second": 58.938, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 1280, | |
| "total_flos": 7490460859315200.0, | |
| "train_loss": 0.006709893904917408, | |
| "train_runtime": 745.4139, | |
| "train_samples_per_second": 109.697, | |
| "train_steps_per_second": 1.717 | |
| } | |
| ], | |
| "max_steps": 1280, | |
| "num_train_epochs": 10, | |
| "total_flos": 7490460859315200.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |