| { | |
| "best_metric": 0.872036678543347, | |
| "best_model_checkpoint": "/home/sh0416/checkpoints/20211030_190826/checkpoint-4500", | |
| "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": 0.8654053981781068, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 3.691593125870878e-05, | |
| "loss": 0.6824, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_stsb_spearman": 0.8630942150925814, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_stsb_spearman": 0.8647722892013918, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 3.381947669917944e-05, | |
| "loss": 0.5019, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_stsb_spearman": 0.863924300829715, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_stsb_spearman": 0.865832672493566, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 3.07230221396501e-05, | |
| "loss": 0.4588, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_stsb_spearman": 0.8697838762809251, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_stsb_spearman": 0.8663751095801148, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 2.7626567580120764e-05, | |
| "loss": 0.4315, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_stsb_spearman": 0.8675459975163204, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "eval_stsb_spearman": 0.8623516779814553, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 2.4536305929710486e-05, | |
| "loss": 0.3605, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "eval_stsb_spearman": 0.8661447456621129, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "eval_stsb_spearman": 0.8630883894657957, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 2.1439851370181147e-05, | |
| "loss": 0.3204, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "eval_stsb_spearman": 0.8676861417409001, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "eval_stsb_spearman": 0.8663622547086287, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 1.8343396810651805e-05, | |
| "loss": 0.3192, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "eval_stsb_spearman": 0.8681967674192711, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "eval_stsb_spearman": 0.8680997292141981, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 1.5246942251122465e-05, | |
| "loss": 0.3082, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "eval_stsb_spearman": 0.8704183945112793, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "eval_stsb_spearman": 0.8694464515546018, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 1.2150487691593128e-05, | |
| "loss": 0.2717, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "eval_stsb_spearman": 0.872036678543347, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "eval_stsb_spearman": 0.8696657587618986, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 9.054033132063787e-06, | |
| "loss": 0.2319, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "eval_stsb_spearman": 0.8693052602931151, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "eval_stsb_spearman": 0.8693374738384204, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 5.957578572534448e-06, | |
| "loss": 0.2373, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "eval_stsb_spearman": 0.8716913178704958, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "eval_stsb_spearman": 0.8712393132258108, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 2.867316922124168e-06, | |
| "loss": 0.2324, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "eval_stsb_spearman": 0.8697257054223788, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "eval_stsb_spearman": 0.8694333564666972, | |
| "step": 6250 | |
| } | |
| ], | |
| "max_steps": 6459, | |
| "num_train_epochs": 3, | |
| "total_flos": 0.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |