| { | |
| "best_metric": 0.7862407862407862, | |
| "best_model_checkpoint": "finetune_results/omarmomen/structformer_s1_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": 0.6736658215522766, | |
| "eval_f1": 0.7146136189747514, | |
| "eval_loss": 0.5989475250244141, | |
| "eval_mcc": 0.3425894886466018, | |
| "eval_runtime": 4.4241, | |
| "eval_samples_per_second": 516.72, | |
| "eval_steps_per_second": 64.646, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 4.316939890710383e-05, | |
| "loss": 0.6481, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "eval_accuracy": 0.7349081635475159, | |
| "eval_f1": 0.72579185520362, | |
| "eval_loss": 0.5559495091438293, | |
| "eval_mcc": 0.4829898982899456, | |
| "eval_runtime": 4.4215, | |
| "eval_samples_per_second": 517.013, | |
| "eval_steps_per_second": 64.683, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 3.633879781420765e-05, | |
| "loss": 0.5099, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "eval_accuracy": 0.751968502998352, | |
| "eval_f1": 0.7618647627047459, | |
| "eval_loss": 0.555103063583374, | |
| "eval_mcc": 0.5037717283176012, | |
| "eval_runtime": 4.4181, | |
| "eval_samples_per_second": 517.421, | |
| "eval_steps_per_second": 64.734, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 4.1, | |
| "learning_rate": 2.9508196721311478e-05, | |
| "loss": 0.3245, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 4.37, | |
| "eval_accuracy": 0.7755905389785767, | |
| "eval_f1": 0.7782101167315174, | |
| "eval_loss": 0.6722451448440552, | |
| "eval_mcc": 0.5551932955703639, | |
| "eval_runtime": 4.4196, | |
| "eval_samples_per_second": 517.245, | |
| "eval_steps_per_second": 64.712, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 5.46, | |
| "learning_rate": 2.2677595628415303e-05, | |
| "loss": 0.1577, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 5.46, | |
| "eval_accuracy": 0.7716535329818726, | |
| "eval_f1": 0.7862407862407862, | |
| "eval_loss": 0.8745389580726624, | |
| "eval_mcc": 0.5412131716827608, | |
| "eval_runtime": 4.4197, | |
| "eval_samples_per_second": 517.228, | |
| "eval_steps_per_second": 64.71, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 6.56, | |
| "eval_accuracy": 0.7677165269851685, | |
| "eval_f1": 0.7777312683131016, | |
| "eval_loss": 0.9956287741661072, | |
| "eval_mcc": 0.5349834947951929, | |
| "eval_runtime": 4.4246, | |
| "eval_samples_per_second": 516.662, | |
| "eval_steps_per_second": 64.639, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 6.83, | |
| "learning_rate": 1.5846994535519128e-05, | |
| "loss": 0.0887, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 7.65, | |
| "eval_accuracy": 0.7672790884971619, | |
| "eval_f1": 0.7745762711864408, | |
| "eval_loss": 1.1708937883377075, | |
| "eval_mcc": 0.5355122905220886, | |
| "eval_runtime": 4.4191, | |
| "eval_samples_per_second": 517.303, | |
| "eval_steps_per_second": 64.719, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 8.2, | |
| "learning_rate": 9.016393442622952e-06, | |
| "loss": 0.045, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 8.74, | |
| "eval_accuracy": 0.778215229511261, | |
| "eval_f1": 0.7823100042936882, | |
| "eval_loss": 1.3273141384124756, | |
| "eval_mcc": 0.5593191626279744, | |
| "eval_runtime": 4.4227, | |
| "eval_samples_per_second": 516.884, | |
| "eval_steps_per_second": 64.667, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 9.56, | |
| "learning_rate": 2.185792349726776e-06, | |
| "loss": 0.0253, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 9.84, | |
| "eval_accuracy": 0.7808399200439453, | |
| "eval_f1": 0.7839586028460542, | |
| "eval_loss": 1.4356170892715454, | |
| "eval_mcc": 0.565280259416071, | |
| "eval_runtime": 4.4184, | |
| "eval_samples_per_second": 517.385, | |
| "eval_steps_per_second": 64.73, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 3660, | |
| "total_flos": 3.665914093619712e+16, | |
| "train_loss": 0.24654610430608032, | |
| "train_runtime": 2153.3841, | |
| "train_samples_per_second": 203.944, | |
| "train_steps_per_second": 1.7 | |
| } | |
| ], | |
| "max_steps": 3660, | |
| "num_train_epochs": 10, | |
| "total_flos": 3.665914093619712e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |