| { | |
| "best_metric": 2.1732585430145264, | |
| "best_model_checkpoint": "hBERTv1_no_pretrain_stsb/checkpoint-120", | |
| "epoch": 7.0, | |
| "global_step": 420, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3.9200000000000004e-05, | |
| "loss": 2.3601, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_combined_score": 0.10693021777425508, | |
| "eval_loss": 2.663867473602295, | |
| "eval_pearson": 0.10586092872855574, | |
| "eval_runtime": 7.035, | |
| "eval_samples_per_second": 213.218, | |
| "eval_spearmanr": 0.10799950681995443, | |
| "eval_steps_per_second": 2.274, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 3.8400000000000005e-05, | |
| "loss": 1.9983, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_combined_score": 0.2255738455165121, | |
| "eval_loss": 2.1732585430145264, | |
| "eval_pearson": 0.23743749639631304, | |
| "eval_runtime": 7.0377, | |
| "eval_samples_per_second": 213.137, | |
| "eval_spearmanr": 0.21371019463671115, | |
| "eval_steps_per_second": 2.273, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 3.76e-05, | |
| "loss": 1.7079, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_combined_score": 0.19197115777574508, | |
| "eval_loss": 2.500040292739868, | |
| "eval_pearson": 0.18722802160872423, | |
| "eval_runtime": 7.0344, | |
| "eval_samples_per_second": 213.238, | |
| "eval_spearmanr": 0.19671429394276596, | |
| "eval_steps_per_second": 2.275, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 3.680000000000001e-05, | |
| "loss": 1.3775, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_combined_score": 0.2214031712862335, | |
| "eval_loss": 3.1202645301818848, | |
| "eval_pearson": 0.21770063206447132, | |
| "eval_runtime": 7.0369, | |
| "eval_samples_per_second": 213.162, | |
| "eval_spearmanr": 0.2251057105079957, | |
| "eval_steps_per_second": 2.274, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 3.6e-05, | |
| "loss": 1.1218, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_combined_score": 0.26032775290992616, | |
| "eval_loss": 2.8260228633880615, | |
| "eval_pearson": 0.260850187966332, | |
| "eval_runtime": 7.0316, | |
| "eval_samples_per_second": 213.321, | |
| "eval_spearmanr": 0.25980531785352035, | |
| "eval_steps_per_second": 2.275, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 3.52e-05, | |
| "loss": 0.8882, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_combined_score": 0.3080700458055182, | |
| "eval_loss": 2.5413460731506348, | |
| "eval_pearson": 0.30994111366811594, | |
| "eval_runtime": 7.0382, | |
| "eval_samples_per_second": 213.124, | |
| "eval_spearmanr": 0.30619897794292045, | |
| "eval_steps_per_second": 2.273, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 3.44e-05, | |
| "loss": 0.728, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_combined_score": 0.3448220522198585, | |
| "eval_loss": 2.4024245738983154, | |
| "eval_pearson": 0.342872486433605, | |
| "eval_runtime": 7.0455, | |
| "eval_samples_per_second": 212.902, | |
| "eval_spearmanr": 0.34677161800611195, | |
| "eval_steps_per_second": 2.271, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "step": 420, | |
| "total_flos": 5959810973433856.0, | |
| "train_loss": 1.454549062819708, | |
| "train_runtime": 727.1833, | |
| "train_samples_per_second": 395.292, | |
| "train_steps_per_second": 4.126 | |
| } | |
| ], | |
| "max_steps": 3000, | |
| "num_train_epochs": 50, | |
| "total_flos": 5959810973433856.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |