| { | |
| "best_metric": 0.7943262411347518, | |
| "best_model_checkpoint": "finetune_results/omarmomen/structformer_s2_final_with_pos/qnli/checkpoint-2000", | |
| "epoch": 10.0, | |
| "global_step": 3660, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.09, | |
| "eval_accuracy": 0.6596675515174866, | |
| "eval_f1": 0.6291706387035272, | |
| "eval_loss": 0.6406663060188293, | |
| "eval_mcc": 0.3433284175764004, | |
| "eval_runtime": 4.4117, | |
| "eval_samples_per_second": 518.173, | |
| "eval_steps_per_second": 64.828, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 4.316939890710383e-05, | |
| "loss": 0.6418, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "eval_accuracy": 0.7646543979644775, | |
| "eval_f1": 0.762157382847038, | |
| "eval_loss": 0.5161377191543579, | |
| "eval_mcc": 0.5375627310785333, | |
| "eval_runtime": 4.4115, | |
| "eval_samples_per_second": 518.188, | |
| "eval_steps_per_second": 64.83, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 3.633879781420765e-05, | |
| "loss": 0.4738, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "eval_accuracy": 0.7786526679992676, | |
| "eval_f1": 0.7898671096345513, | |
| "eval_loss": 0.5230312347412109, | |
| "eval_mcc": 0.5561856987463696, | |
| "eval_runtime": 4.4087, | |
| "eval_samples_per_second": 518.52, | |
| "eval_steps_per_second": 64.872, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 4.1, | |
| "learning_rate": 2.9508196721311478e-05, | |
| "loss": 0.3208, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 4.37, | |
| "eval_accuracy": 0.764216959476471, | |
| "eval_f1": 0.7594823739402053, | |
| "eval_loss": 0.6839817762374878, | |
| "eval_mcc": 0.538776423502748, | |
| "eval_runtime": 4.4102, | |
| "eval_samples_per_second": 518.35, | |
| "eval_steps_per_second": 64.85, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 5.46, | |
| "learning_rate": 2.2677595628415303e-05, | |
| "loss": 0.1862, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 5.46, | |
| "eval_accuracy": 0.784339427947998, | |
| "eval_f1": 0.7943262411347518, | |
| "eval_loss": 0.7829149961471558, | |
| "eval_mcc": 0.5679876594318457, | |
| "eval_runtime": 4.4082, | |
| "eval_samples_per_second": 518.58, | |
| "eval_steps_per_second": 64.879, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 6.56, | |
| "eval_accuracy": 0.7825896739959717, | |
| "eval_f1": 0.7912641747165058, | |
| "eval_loss": 0.8158888220787048, | |
| "eval_mcc": 0.56514836827955, | |
| "eval_runtime": 4.4092, | |
| "eval_samples_per_second": 518.463, | |
| "eval_steps_per_second": 64.865, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 6.83, | |
| "learning_rate": 1.5846994535519128e-05, | |
| "loss": 0.1181, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 7.65, | |
| "eval_accuracy": 0.7790901064872742, | |
| "eval_f1": 0.7880822492656315, | |
| "eval_loss": 0.9320896863937378, | |
| "eval_mcc": 0.5580439426682389, | |
| "eval_runtime": 4.4085, | |
| "eval_samples_per_second": 518.548, | |
| "eval_steps_per_second": 64.875, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 8.2, | |
| "learning_rate": 9.016393442622952e-06, | |
| "loss": 0.0707, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 8.74, | |
| "eval_accuracy": 0.7650918364524841, | |
| "eval_f1": 0.7647831800262813, | |
| "eval_loss": 1.1550036668777466, | |
| "eval_mcc": 0.5365366134864961, | |
| "eval_runtime": 4.4071, | |
| "eval_samples_per_second": 518.705, | |
| "eval_steps_per_second": 64.895, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 9.56, | |
| "learning_rate": 2.185792349726776e-06, | |
| "loss": 0.0451, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 9.84, | |
| "eval_accuracy": 0.7760279774665833, | |
| "eval_f1": 0.7795004306632213, | |
| "eval_loss": 1.2090375423431396, | |
| "eval_mcc": 0.5554180529142885, | |
| "eval_runtime": 4.4056, | |
| "eval_samples_per_second": 518.888, | |
| "eval_steps_per_second": 64.918, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 3660, | |
| "total_flos": 3.665910855707136e+16, | |
| "train_loss": 0.25508030907052465, | |
| "train_runtime": 2018.5569, | |
| "train_samples_per_second": 217.566, | |
| "train_steps_per_second": 1.813 | |
| } | |
| ], | |
| "max_steps": 3660, | |
| "num_train_epochs": 10, | |
| "total_flos": 3.665910855707136e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |