| { | |
| "best_metric": 0.8749827232758327, | |
| "best_model_checkpoint": "/home/sh0416/checkpoints/20211030_191325/checkpoint-4000", | |
| "epoch": 2.9029261495587555, | |
| "global_step": 6250, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.12, | |
| "eval_stsb_spearman": 0.8672622126234729, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 4.614491407338598e-05, | |
| "loss": 0.6229, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_stsb_spearman": 0.8686220872249998, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_stsb_spearman": 0.8713530161510513, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 4.22743458739743e-05, | |
| "loss": 0.4539, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_stsb_spearman": 0.8703891151316948, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_stsb_spearman": 0.8704823686386852, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 3.840377767456263e-05, | |
| "loss": 0.4148, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_stsb_spearman": 0.8739520357336363, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_stsb_spearman": 0.8733650442263879, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3.453320947515095e-05, | |
| "loss": 0.387, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_stsb_spearman": 0.8746502426199291, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "eval_stsb_spearman": 0.8683478201322982, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 3.0662641275739276e-05, | |
| "loss": 0.3273, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "eval_stsb_spearman": 0.8707791741190464, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "eval_stsb_spearman": 0.8717106836570322, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 2.6792073076327606e-05, | |
| "loss": 0.292, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "eval_stsb_spearman": 0.8694230308368138, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "eval_stsb_spearman": 0.8712383460280487, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 2.2921504876915932e-05, | |
| "loss": 0.2914, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "eval_stsb_spearman": 0.8724842589226055, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "eval_stsb_spearman": 0.8724524457334477, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 1.905093667750426e-05, | |
| "loss": 0.2816, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "eval_stsb_spearman": 0.8749827232758327, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "eval_stsb_spearman": 0.8713456193488069, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 1.5180368478092586e-05, | |
| "loss": 0.2479, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "eval_stsb_spearman": 0.8707441171554137, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "eval_stsb_spearman": 0.8747425362777639, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 1.1309800278680912e-05, | |
| "loss": 0.2137, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "eval_stsb_spearman": 0.8688566710163649, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "eval_stsb_spearman": 0.8699787446260961, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 7.439232079269237e-06, | |
| "loss": 0.2157, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "eval_stsb_spearman": 0.8721395238098683, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "eval_stsb_spearman": 0.8728644709280902, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 3.5764050162563865e-06, | |
| "loss": 0.2129, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "eval_stsb_spearman": 0.8704374372290133, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "eval_stsb_spearman": 0.8703125990647913, | |
| "step": 6250 | |
| } | |
| ], | |
| "max_steps": 6459, | |
| "num_train_epochs": 3, | |
| "total_flos": 0.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |