| { |
| "best_metric": 0.9582504965178059, |
| "best_model_checkpoint": "../out/onto_final/ner-roberta-spanclass-dice/checkpoints/checkpoint-22000", |
| "epoch": 17.200938232994528, |
| "global_step": 22000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.7818608287724785, |
| "learning_rate": 9.973937972374251e-06, |
| "loss": 0.5397671508789063, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.7818608287724785, |
| "eval_loss": 0.22605788707733154, |
| "eval_micro_f1": 0.9477679373274942, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.5637216575449568, |
| "learning_rate": 9.947875944748501e-06, |
| "loss": 0.1624965362548828, |
| "step": 2000 |
| }, |
| { |
| "epoch": 1.5637216575449568, |
| "eval_loss": 0.21387435495853424, |
| "eval_micro_f1": 0.9516537135790754, |
| "step": 2000 |
| }, |
| { |
| "epoch": 2.3455824863174355, |
| "learning_rate": 9.921813917122753e-06, |
| "loss": 0.12110142517089843, |
| "step": 3000 |
| }, |
| { |
| "epoch": 2.3455824863174355, |
| "eval_loss": 0.21980492770671844, |
| "eval_micro_f1": 0.953822518928795, |
| "step": 3000 |
| }, |
| { |
| "epoch": 3.127443315089914, |
| "learning_rate": 9.895751889497005e-06, |
| "loss": 0.10264362335205078, |
| "step": 4000 |
| }, |
| { |
| "epoch": 3.127443315089914, |
| "eval_loss": 0.2117234468460083, |
| "eval_micro_f1": 0.9575275614012327, |
| "step": 4000 |
| }, |
| { |
| "epoch": 3.9093041438623923, |
| "learning_rate": 9.869689861871255e-06, |
| "loss": 0.0832140121459961, |
| "step": 5000 |
| }, |
| { |
| "epoch": 3.9093041438623923, |
| "eval_loss": 0.22679875791072845, |
| "eval_micro_f1": 0.9530092169226502, |
| "step": 5000 |
| }, |
| { |
| "epoch": 4.691164972634871, |
| "learning_rate": 9.843627834245505e-06, |
| "loss": 0.06584241485595703, |
| "step": 6000 |
| }, |
| { |
| "epoch": 4.691164972634871, |
| "eval_loss": 0.23657391965389252, |
| "eval_micro_f1": 0.9532803175913651, |
| "step": 6000 |
| }, |
| { |
| "epoch": 5.473025801407349, |
| "learning_rate": 9.817565806619755e-06, |
| "loss": 0.05782469177246094, |
| "step": 7000 |
| }, |
| { |
| "epoch": 5.473025801407349, |
| "eval_loss": 0.25745341181755066, |
| "eval_micro_f1": 0.9544550871557965, |
| "step": 7000 |
| }, |
| { |
| "epoch": 6.254886630179828, |
| "learning_rate": 9.791503778994007e-06, |
| "loss": 0.04978230285644531, |
| "step": 8000 |
| }, |
| { |
| "epoch": 6.254886630179828, |
| "eval_loss": 0.2867651581764221, |
| "eval_micro_f1": 0.9527381162539351, |
| "step": 8000 |
| }, |
| { |
| "epoch": 7.0367474589523065, |
| "learning_rate": 9.765441751368257e-06, |
| "loss": 0.043348209381103515, |
| "step": 9000 |
| }, |
| { |
| "epoch": 7.0367474589523065, |
| "eval_loss": 0.30041876435279846, |
| "eval_micro_f1": 0.949394541339784, |
| "step": 9000 |
| }, |
| { |
| "epoch": 7.818608287724785, |
| "learning_rate": 9.739379723742509e-06, |
| "loss": 0.03466781616210937, |
| "step": 10000 |
| }, |
| { |
| "epoch": 7.818608287724785, |
| "eval_loss": 0.30916619300842285, |
| "eval_micro_f1": 0.9520151811373619, |
| "step": 10000 |
| }, |
| { |
| "epoch": 8.600469116497264, |
| "learning_rate": 9.713317696116759e-06, |
| "loss": 0.030826730728149412, |
| "step": 11000 |
| }, |
| { |
| "epoch": 8.600469116497264, |
| "eval_loss": 0.309920072555542, |
| "eval_micro_f1": 0.9503885771250722, |
| "step": 11000 |
| }, |
| { |
| "epoch": 9.382329945269742, |
| "learning_rate": 9.687255668491009e-06, |
| "loss": 0.027759357452392577, |
| "step": 12000 |
| }, |
| { |
| "epoch": 9.382329945269742, |
| "eval_loss": 0.3114129900932312, |
| "eval_micro_f1": 0.9543647202662249, |
| "step": 12000 |
| }, |
| { |
| "epoch": 10.16419077404222, |
| "learning_rate": 9.661193640865259e-06, |
| "loss": 0.026107059478759766, |
| "step": 13000 |
| }, |
| { |
| "epoch": 10.16419077404222, |
| "eval_loss": 0.3399326205253601, |
| "eval_micro_f1": 0.9531899507017935, |
| "step": 13000 |
| }, |
| { |
| "epoch": 10.946051602814698, |
| "learning_rate": 9.635131613239511e-06, |
| "loss": 0.019590240478515625, |
| "step": 14000 |
| }, |
| { |
| "epoch": 10.946051602814698, |
| "eval_loss": 0.337801992893219, |
| "eval_micro_f1": 0.9550876553827982, |
| "step": 14000 |
| }, |
| { |
| "epoch": 11.727912431587178, |
| "learning_rate": 9.609069585613761e-06, |
| "loss": 0.016569852828979492, |
| "step": 15000 |
| }, |
| { |
| "epoch": 11.727912431587178, |
| "eval_loss": 0.3670026957988739, |
| "eval_micro_f1": 0.9524670155852202, |
| "step": 15000 |
| }, |
| { |
| "epoch": 12.509773260359657, |
| "learning_rate": 9.583007557988013e-06, |
| "loss": 0.016996849060058595, |
| "step": 16000 |
| }, |
| { |
| "epoch": 12.509773260359657, |
| "eval_loss": 0.35762009024620056, |
| "eval_micro_f1": 0.9553587560515131, |
| "step": 16000 |
| }, |
| { |
| "epoch": 13.291634089132135, |
| "learning_rate": 9.556945530362263e-06, |
| "loss": 0.012570078849792481, |
| "step": 17000 |
| }, |
| { |
| "epoch": 13.291634089132135, |
| "eval_loss": 0.39511236548423767, |
| "eval_micro_f1": 0.9543647202662249, |
| "step": 17000 |
| }, |
| { |
| "epoch": 14.073494917904613, |
| "learning_rate": 9.530883502736513e-06, |
| "loss": 0.01412732219696045, |
| "step": 18000 |
| }, |
| { |
| "epoch": 14.073494917904613, |
| "eval_loss": 0.37808138132095337, |
| "eval_micro_f1": 0.9533706844809368, |
| "step": 18000 |
| }, |
| { |
| "epoch": 14.855355746677091, |
| "learning_rate": 9.504821475110765e-06, |
| "loss": 0.01403067398071289, |
| "step": 19000 |
| }, |
| { |
| "epoch": 14.855355746677091, |
| "eval_loss": 0.3788624405860901, |
| "eval_micro_f1": 0.9541839864870816, |
| "step": 19000 |
| }, |
| { |
| "epoch": 15.63721657544957, |
| "learning_rate": 9.478759447485015e-06, |
| "loss": 0.011390049934387208, |
| "step": 20000 |
| }, |
| { |
| "epoch": 15.63721657544957, |
| "eval_loss": 0.3904345631599426, |
| "eval_micro_f1": 0.9565335256159445, |
| "step": 20000 |
| }, |
| { |
| "epoch": 16.419077404222048, |
| "learning_rate": 9.452697419859265e-06, |
| "loss": 0.01300933837890625, |
| "step": 21000 |
| }, |
| { |
| "epoch": 16.419077404222048, |
| "eval_loss": 0.39750251173973083, |
| "eval_micro_f1": 0.9537321520392233, |
| "step": 21000 |
| }, |
| { |
| "epoch": 17.200938232994528, |
| "learning_rate": 9.426635392233517e-06, |
| "loss": 0.011849085807800292, |
| "step": 22000 |
| }, |
| { |
| "epoch": 17.200938232994528, |
| "eval_loss": 0.36782628297805786, |
| "eval_micro_f1": 0.9582504965178059, |
| "step": 22000 |
| } |
| ], |
| "max_steps": 383700, |
| "num_train_epochs": 300, |
| "total_flos": 152916752018322864, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
