| { | |
| "best_metric": 0.8612245046067181, | |
| "best_model_checkpoint": "/home/sh0416/checkpoints/20211030_171530/checkpoint-2000", | |
| "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": 0.8416441611818962, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 3.6922124167827844e-05, | |
| "loss": 0.7311, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_stsb_spearman": 0.8525851534565596, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_stsb_spearman": 0.847019460255557, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 3.38256696082985e-05, | |
| "loss": 0.5362, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_stsb_spearman": 0.8544025934514893, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_stsb_spearman": 0.8555246108692984, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 3.072921504876916e-05, | |
| "loss": 0.4894, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_stsb_spearman": 0.8554197418384588, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_stsb_spearman": 0.8551499711901335, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 2.763276048923982e-05, | |
| "loss": 0.4658, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_stsb_spearman": 0.8612245046067181, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "eval_stsb_spearman": 0.8514790736455403, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 2.4536305929710486e-05, | |
| "loss": 0.3763, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "eval_stsb_spearman": 0.8549840867343126, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "eval_stsb_spearman": 0.8577538840145208, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 2.1439851370181147e-05, | |
| "loss": 0.3323, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "eval_stsb_spearman": 0.8570612483064401, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "eval_stsb_spearman": 0.8527018164800769, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 1.8343396810651805e-05, | |
| "loss": 0.3324, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "eval_stsb_spearman": 0.8548207475240701, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "eval_stsb_spearman": 0.8561597832731205, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 1.5246942251122465e-05, | |
| "loss": 0.3231, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "eval_stsb_spearman": 0.8588956837328435, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "eval_stsb_spearman": 0.8571489288440057, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 1.2150487691593128e-05, | |
| "loss": 0.2859, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "eval_stsb_spearman": 0.8603596705056781, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "eval_stsb_spearman": 0.8593167996810743, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 9.054033132063787e-06, | |
| "loss": 0.2412, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "eval_stsb_spearman": 0.856394199804584, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "eval_stsb_spearman": 0.8587140989619012, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 5.957578572534448e-06, | |
| "loss": 0.2444, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "eval_stsb_spearman": 0.8586584921620097, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "eval_stsb_spearman": 0.8591725059874461, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 2.8611240130051095e-06, | |
| "loss": 0.2441, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "eval_stsb_spearman": 0.8577426224409327, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "eval_stsb_spearman": 0.8575225991578108, | |
| "step": 6250 | |
| } | |
| ], | |
| "max_steps": 6459, | |
| "num_train_epochs": 3, | |
| "total_flos": 0.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |