| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.5644402634054563, |
| "eval_steps": 500, |
| "global_step": 600, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0, |
| "eval/E1/acc_on_CONSISTENT": 0.16435185185185186, |
| "eval/E1/acc_on_INCONSISTENT": 0.9875, |
| "eval/E1/accuracy": 0.29296875, |
| "eval/E1/f1_INC": 0.3038461538461539, |
| "eval/E1/precision_INC": 0.17954545454545454, |
| "eval/E1/recall_INC": 0.9875, |
| "eval/E2/acc_on_CONSISTENT": 0.6785714285714286, |
| "eval/E2/acc_on_INCONSISTENT": 0.9594594594594594, |
| "eval/E2/accuracy": 0.759765625, |
| "eval/E2/f1_INC": 0.6977886977886979, |
| "eval/E2/precision_INC": 0.5482625482625483, |
| "eval/E2/recall_INC": 0.9594594594594594, |
| "eval/E3/acc_on_CONSISTENT": 0.07098765432098765, |
| "eval/E3/acc_on_INCONSISTENT": 0.9680851063829787, |
| "eval/E3/accuracy": 0.400390625, |
| "eval/E3/f1_INC": 0.5424739195230999, |
| "eval/E3/precision_INC": 0.37681159420289856, |
| "eval/E3/recall_INC": 0.9680851063829787, |
| "eval/E4/acc_on_CONSISTENT": 0.0529595015576324, |
| "eval/E4/acc_on_INCONSISTENT": 0.9476439790575916, |
| "eval/E4/accuracy": 0.38671875, |
| "eval/E4/f1_INC": 0.5355029585798816, |
| "eval/E4/precision_INC": 0.3731958762886598, |
| "eval/E4/recall_INC": 0.9476439790575916, |
| "eval/edge_macro_accuracy": 0.4599609375, |
| "eval/malformed_rate": 0.0, |
| "eval/n_eval": 512.0, |
| "eval/overall/acc_on_CONSISTENT": 0.08133971291866028, |
| "eval/overall/acc_on_INCONSISTENT": 0.966996699669967, |
| "eval/overall/accuracy": 0.60546875, |
| "eval/overall/f1_INC": 0.7436548223350254, |
| "eval/overall/precision_INC": 0.6041237113402061, |
| "eval/overall/recall_INC": 0.966996699669967, |
| "eval/overall_exact_match": 0.064453125, |
| "eval_label": "start", |
| "step": 0 |
| }, |
| { |
| "epoch": 0.01881467544684854, |
| "grad_norm": 0.13588111102581024, |
| "learning_rate": 5.9375e-05, |
| "loss": 0.0936, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.03762935089369708, |
| "grad_norm": 0.15987196564674377, |
| "learning_rate": 9.932104752667314e-05, |
| "loss": 0.0348, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.05644402634054563, |
| "grad_norm": 0.14962074160575867, |
| "learning_rate": 9.73811833171678e-05, |
| "loss": 0.0273, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.07525870178739416, |
| "grad_norm": 0.1912640929222107, |
| "learning_rate": 9.544131910766246e-05, |
| "loss": 0.0248, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.09407337723424271, |
| "eval/E1/acc_on_CONSISTENT": 0.8819444444444444, |
| "eval/E1/acc_on_INCONSISTENT": 0.4625, |
| "eval/E1/accuracy": 0.81640625, |
| "eval/E1/f1_INC": 0.44047619047619047, |
| "eval/E1/precision_INC": 0.42045454545454547, |
| "eval/E1/recall_INC": 0.4625, |
| "eval/E2/acc_on_CONSISTENT": 0.9752747252747253, |
| "eval/E2/acc_on_INCONSISTENT": 0.8243243243243243, |
| "eval/E2/accuracy": 0.931640625, |
| "eval/E2/f1_INC": 0.8745519713261649, |
| "eval/E2/precision_INC": 0.9312977099236641, |
| "eval/E2/recall_INC": 0.8243243243243243, |
| "eval/E3/acc_on_CONSISTENT": 0.8179012345679012, |
| "eval/E3/acc_on_INCONSISTENT": 0.6968085106382979, |
| "eval/E3/accuracy": 0.7734375, |
| "eval/E3/f1_INC": 0.6931216931216931, |
| "eval/E3/precision_INC": 0.6894736842105263, |
| "eval/E3/recall_INC": 0.6968085106382979, |
| "eval/E4/acc_on_CONSISTENT": 0.8629283489096573, |
| "eval/E4/acc_on_INCONSISTENT": 0.7068062827225131, |
| "eval/E4/accuracy": 0.8046875, |
| "eval/E4/f1_INC": 0.7297297297297297, |
| "eval/E4/precision_INC": 0.7541899441340782, |
| "eval/E4/recall_INC": 0.7068062827225131, |
| "eval/edge_macro_accuracy": 0.83154296875, |
| "eval/malformed_rate": 0.0, |
| "eval/n_eval": 512.0, |
| "eval/overall/acc_on_CONSISTENT": 0.8325358851674641, |
| "eval/overall/acc_on_INCONSISTENT": 0.7887788778877888, |
| "eval/overall/accuracy": 0.806640625, |
| "eval/overall/f1_INC": 0.82842287694974, |
| "eval/overall/precision_INC": 0.8722627737226277, |
| "eval/overall/recall_INC": 0.7887788778877888, |
| "eval/overall_exact_match": 0.576171875, |
| "eval_label": "step_100", |
| "step": 100 |
| }, |
| { |
| "epoch": 0.09407337723424271, |
| "grad_norm": 0.10156096518039703, |
| "learning_rate": 9.350145489815713e-05, |
| "loss": 0.0248, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.11288805268109126, |
| "grad_norm": 0.15984299778938293, |
| "learning_rate": 9.15615906886518e-05, |
| "loss": 0.0241, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.1317027281279398, |
| "grad_norm": 0.14268864691257477, |
| "learning_rate": 8.962172647914647e-05, |
| "loss": 0.0222, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.15051740357478832, |
| "grad_norm": 0.09480800479650497, |
| "learning_rate": 8.768186226964112e-05, |
| "loss": 0.022, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.16933207902163688, |
| "grad_norm": 0.09908359497785568, |
| "learning_rate": 8.57419980601358e-05, |
| "loss": 0.0205, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.18814675446848542, |
| "eval/E1/acc_on_CONSISTENT": 0.9236111111111112, |
| "eval/E1/acc_on_INCONSISTENT": 0.4125, |
| "eval/E1/accuracy": 0.84375, |
| "eval/E1/f1_INC": 0.4520547945205479, |
| "eval/E1/precision_INC": 0.5, |
| "eval/E1/recall_INC": 0.4125, |
| "eval/E2/acc_on_CONSISTENT": 0.945054945054945, |
| "eval/E2/acc_on_INCONSISTENT": 0.9391891891891891, |
| "eval/E2/accuracy": 0.943359375, |
| "eval/E2/f1_INC": 0.9055374592833876, |
| "eval/E2/precision_INC": 0.8742138364779874, |
| "eval/E2/recall_INC": 0.9391891891891891, |
| "eval/E3/acc_on_CONSISTENT": 0.8703703703703703, |
| "eval/E3/acc_on_INCONSISTENT": 0.8191489361702128, |
| "eval/E3/accuracy": 0.8515625, |
| "eval/E3/f1_INC": 0.8020833333333333, |
| "eval/E3/precision_INC": 0.7857142857142857, |
| "eval/E3/recall_INC": 0.8191489361702128, |
| "eval/E4/acc_on_CONSISTENT": 0.8411214953271028, |
| "eval/E4/acc_on_INCONSISTENT": 0.7905759162303665, |
| "eval/E4/accuracy": 0.822265625, |
| "eval/E4/f1_INC": 0.7684478371501273, |
| "eval/E4/precision_INC": 0.7475247524752475, |
| "eval/E4/recall_INC": 0.7905759162303665, |
| "eval/edge_macro_accuracy": 0.865234375, |
| "eval/malformed_rate": 0.0, |
| "eval/n_eval": 512.0, |
| "eval/overall/acc_on_CONSISTENT": 0.7559808612440191, |
| "eval/overall/acc_on_INCONSISTENT": 0.8712871287128713, |
| "eval/overall/accuracy": 0.82421875, |
| "eval/overall/f1_INC": 0.854368932038835, |
| "eval/overall/precision_INC": 0.8380952380952381, |
| "eval/overall/recall_INC": 0.8712871287128713, |
| "eval/overall_exact_match": 0.63671875, |
| "eval_label": "step_200", |
| "step": 200 |
| }, |
| { |
| "epoch": 0.18814675446848542, |
| "grad_norm": 0.1302443891763687, |
| "learning_rate": 8.380213385063046e-05, |
| "loss": 0.0211, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.20696142991533395, |
| "grad_norm": 0.14304408431053162, |
| "learning_rate": 8.186226964112513e-05, |
| "loss": 0.0187, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.2257761053621825, |
| "grad_norm": 0.20394913852214813, |
| "learning_rate": 7.99224054316198e-05, |
| "loss": 0.0208, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.24459078080903104, |
| "grad_norm": 0.11161988973617554, |
| "learning_rate": 7.798254122211446e-05, |
| "loss": 0.019, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.2634054562558796, |
| "grad_norm": 0.11904545873403549, |
| "learning_rate": 7.604267701260912e-05, |
| "loss": 0.0204, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.28222013170272814, |
| "eval/E1/acc_on_CONSISTENT": 0.9652777777777778, |
| "eval/E1/acc_on_INCONSISTENT": 0.3375, |
| "eval/E1/accuracy": 0.8671875, |
| "eval/E1/f1_INC": 0.4426229508196722, |
| "eval/E1/precision_INC": 0.6428571428571429, |
| "eval/E1/recall_INC": 0.3375, |
| "eval/E2/acc_on_CONSISTENT": 0.967032967032967, |
| "eval/E2/acc_on_INCONSISTENT": 0.9324324324324325, |
| "eval/E2/accuracy": 0.95703125, |
| "eval/E2/f1_INC": 0.9261744966442953, |
| "eval/E2/precision_INC": 0.92, |
| "eval/E2/recall_INC": 0.9324324324324325, |
| "eval/E3/acc_on_CONSISTENT": 0.9382716049382716, |
| "eval/E3/acc_on_INCONSISTENT": 0.8138297872340425, |
| "eval/E3/accuracy": 0.892578125, |
| "eval/E3/f1_INC": 0.8476454293628809, |
| "eval/E3/precision_INC": 0.884393063583815, |
| "eval/E3/recall_INC": 0.8138297872340425, |
| "eval/E4/acc_on_CONSISTENT": 0.8940809968847352, |
| "eval/E4/acc_on_INCONSISTENT": 0.8010471204188482, |
| "eval/E4/accuracy": 0.859375, |
| "eval/E4/f1_INC": 0.8095238095238095, |
| "eval/E4/precision_INC": 0.8181818181818182, |
| "eval/E4/recall_INC": 0.8010471204188482, |
| "eval/edge_macro_accuracy": 0.89404296875, |
| "eval/malformed_rate": 0.0, |
| "eval/n_eval": 512.0, |
| "eval/overall/acc_on_CONSISTENT": 0.8851674641148325, |
| "eval/overall/acc_on_INCONSISTENT": 0.8448844884488449, |
| "eval/overall/accuracy": 0.861328125, |
| "eval/overall/f1_INC": 0.8782161234991424, |
| "eval/overall/precision_INC": 0.9142857142857143, |
| "eval/overall/recall_INC": 0.8448844884488449, |
| "eval/overall_exact_match": 0.697265625, |
| "eval_label": "step_300", |
| "step": 300 |
| }, |
| { |
| "epoch": 0.28222013170272814, |
| "grad_norm": 0.1075235903263092, |
| "learning_rate": 7.410281280310378e-05, |
| "loss": 0.0212, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.30103480714957664, |
| "grad_norm": 0.08106118440628052, |
| "learning_rate": 7.216294859359845e-05, |
| "loss": 0.0177, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.3198494825964252, |
| "grad_norm": 0.07731106132268906, |
| "learning_rate": 7.022308438409312e-05, |
| "loss": 0.0182, |
| "step": 340 |
| }, |
| { |
| "epoch": 0.33866415804327377, |
| "grad_norm": 0.1482355296611786, |
| "learning_rate": 6.828322017458779e-05, |
| "loss": 0.0178, |
| "step": 360 |
| }, |
| { |
| "epoch": 0.35747883349012227, |
| "grad_norm": 0.07897721230983734, |
| "learning_rate": 6.634335596508244e-05, |
| "loss": 0.018, |
| "step": 380 |
| }, |
| { |
| "epoch": 0.37629350893697083, |
| "eval/E1/acc_on_CONSISTENT": 0.9722222222222222, |
| "eval/E1/acc_on_INCONSISTENT": 0.45, |
| "eval/E1/accuracy": 0.890625, |
| "eval/E1/f1_INC": 0.5625000000000001, |
| "eval/E1/precision_INC": 0.75, |
| "eval/E1/recall_INC": 0.45, |
| "eval/E2/acc_on_CONSISTENT": 0.9697802197802198, |
| "eval/E2/acc_on_INCONSISTENT": 0.9324324324324325, |
| "eval/E2/accuracy": 0.958984375, |
| "eval/E2/f1_INC": 0.9292929292929293, |
| "eval/E2/precision_INC": 0.9261744966442953, |
| "eval/E2/recall_INC": 0.9324324324324325, |
| "eval/E3/acc_on_CONSISTENT": 0.9598765432098766, |
| "eval/E3/acc_on_INCONSISTENT": 0.8138297872340425, |
| "eval/E3/accuracy": 0.90625, |
| "eval/E3/f1_INC": 0.8644067796610171, |
| "eval/E3/precision_INC": 0.9216867469879518, |
| "eval/E3/recall_INC": 0.8138297872340425, |
| "eval/E4/acc_on_CONSISTENT": 0.9096573208722741, |
| "eval/E4/acc_on_INCONSISTENT": 0.806282722513089, |
| "eval/E4/accuracy": 0.87109375, |
| "eval/E4/f1_INC": 0.823529411764706, |
| "eval/E4/precision_INC": 0.8415300546448088, |
| "eval/E4/recall_INC": 0.806282722513089, |
| "eval/edge_macro_accuracy": 0.90673828125, |
| "eval/malformed_rate": 0.0, |
| "eval/n_eval": 512.0, |
| "eval/overall/acc_on_CONSISTENT": 0.9282296650717703, |
| "eval/overall/acc_on_INCONSISTENT": 0.8481848184818482, |
| "eval/overall/accuracy": 0.880859375, |
| "eval/overall/f1_INC": 0.8939130434782608, |
| "eval/overall/precision_INC": 0.9448529411764706, |
| "eval/overall/recall_INC": 0.8481848184818482, |
| "eval/overall_exact_match": 0.728515625, |
| "eval_label": "step_400", |
| "step": 400 |
| }, |
| { |
| "epoch": 0.37629350893697083, |
| "grad_norm": 0.1120094284415245, |
| "learning_rate": 6.440349175557712e-05, |
| "loss": 0.0168, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.3951081843838194, |
| "grad_norm": 0.16071178019046783, |
| "learning_rate": 6.246362754607178e-05, |
| "loss": 0.016, |
| "step": 420 |
| }, |
| { |
| "epoch": 0.4139228598306679, |
| "grad_norm": 0.10165177285671234, |
| "learning_rate": 6.0523763336566445e-05, |
| "loss": 0.0159, |
| "step": 440 |
| }, |
| { |
| "epoch": 0.43273753527751646, |
| "grad_norm": 0.08946932107210159, |
| "learning_rate": 5.8583899127061106e-05, |
| "loss": 0.0167, |
| "step": 460 |
| }, |
| { |
| "epoch": 0.451552210724365, |
| "grad_norm": 0.07830841839313507, |
| "learning_rate": 5.664403491755578e-05, |
| "loss": 0.016, |
| "step": 480 |
| }, |
| { |
| "epoch": 0.4703668861712135, |
| "eval/E1/acc_on_CONSISTENT": 0.9444444444444444, |
| "eval/E1/acc_on_INCONSISTENT": 0.575, |
| "eval/E1/accuracy": 0.88671875, |
| "eval/E1/f1_INC": 0.6133333333333333, |
| "eval/E1/precision_INC": 0.6571428571428571, |
| "eval/E1/recall_INC": 0.575, |
| "eval/E2/acc_on_CONSISTENT": 0.9285714285714286, |
| "eval/E2/acc_on_INCONSISTENT": 0.9594594594594594, |
| "eval/E2/accuracy": 0.9375, |
| "eval/E2/f1_INC": 0.8987341772151899, |
| "eval/E2/precision_INC": 0.8452380952380952, |
| "eval/E2/recall_INC": 0.9594594594594594, |
| "eval/E3/acc_on_CONSISTENT": 0.8919753086419753, |
| "eval/E3/acc_on_INCONSISTENT": 0.8882978723404256, |
| "eval/E3/accuracy": 0.890625, |
| "eval/E3/f1_INC": 0.8564102564102564, |
| "eval/E3/precision_INC": 0.8267326732673267, |
| "eval/E3/recall_INC": 0.8882978723404256, |
| "eval/E4/acc_on_CONSISTENT": 0.8847352024922118, |
| "eval/E4/acc_on_INCONSISTENT": 0.8638743455497382, |
| "eval/E4/accuracy": 0.876953125, |
| "eval/E4/f1_INC": 0.8396946564885497, |
| "eval/E4/precision_INC": 0.8168316831683168, |
| "eval/E4/recall_INC": 0.8638743455497382, |
| "eval/edge_macro_accuracy": 0.89794921875, |
| "eval/malformed_rate": 0.0, |
| "eval/n_eval": 512.0, |
| "eval/overall/acc_on_CONSISTENT": 0.8325358851674641, |
| "eval/overall/acc_on_INCONSISTENT": 0.8976897689768977, |
| "eval/overall/accuracy": 0.87109375, |
| "eval/overall/f1_INC": 0.8918032786885246, |
| "eval/overall/precision_INC": 0.8859934853420195, |
| "eval/overall/recall_INC": 0.8976897689768977, |
| "eval/overall_exact_match": 0.71484375, |
| "eval_label": "step_500", |
| "step": 500 |
| }, |
| { |
| "epoch": 0.4703668861712135, |
| "grad_norm": 0.23986610770225525, |
| "learning_rate": 5.470417070805044e-05, |
| "loss": 0.0168, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.4891815616180621, |
| "grad_norm": 0.07184334099292755, |
| "learning_rate": 5.27643064985451e-05, |
| "loss": 0.0169, |
| "step": 520 |
| }, |
| { |
| "epoch": 0.5079962370649106, |
| "grad_norm": 0.0486169196665287, |
| "learning_rate": 5.0824442289039763e-05, |
| "loss": 0.0148, |
| "step": 540 |
| }, |
| { |
| "epoch": 0.5268109125117592, |
| "grad_norm": 0.11095824092626572, |
| "learning_rate": 4.888457807953444e-05, |
| "loss": 0.0173, |
| "step": 560 |
| }, |
| { |
| "epoch": 0.5456255879586077, |
| "grad_norm": 0.11410392075777054, |
| "learning_rate": 4.69447138700291e-05, |
| "loss": 0.0149, |
| "step": 580 |
| }, |
| { |
| "epoch": 0.5644402634054563, |
| "eval/E1/acc_on_CONSISTENT": 0.9722222222222222, |
| "eval/E1/acc_on_INCONSISTENT": 0.4375, |
| "eval/E1/accuracy": 0.888671875, |
| "eval/E1/f1_INC": 0.5511811023622046, |
| "eval/E1/precision_INC": 0.7446808510638298, |
| "eval/E1/recall_INC": 0.4375, |
| "eval/E2/acc_on_CONSISTENT": 0.978021978021978, |
| "eval/E2/acc_on_INCONSISTENT": 0.9391891891891891, |
| "eval/E2/accuracy": 0.966796875, |
| "eval/E2/f1_INC": 0.9423728813559321, |
| "eval/E2/precision_INC": 0.9455782312925171, |
| "eval/E2/recall_INC": 0.9391891891891891, |
| "eval/E3/acc_on_CONSISTENT": 0.9691358024691358, |
| "eval/E3/acc_on_INCONSISTENT": 0.75, |
| "eval/E3/accuracy": 0.888671875, |
| "eval/E3/f1_INC": 0.831858407079646, |
| "eval/E3/precision_INC": 0.9337748344370861, |
| "eval/E3/recall_INC": 0.75, |
| "eval/E4/acc_on_CONSISTENT": 0.956386292834891, |
| "eval/E4/acc_on_INCONSISTENT": 0.7801047120418848, |
| "eval/E4/accuracy": 0.890625, |
| "eval/E4/f1_INC": 0.8418079096045198, |
| "eval/E4/precision_INC": 0.9141104294478528, |
| "eval/E4/recall_INC": 0.7801047120418848, |
| "eval/edge_macro_accuracy": 0.90869140625, |
| "eval/malformed_rate": 0.0, |
| "eval/n_eval": 512.0, |
| "eval/overall/acc_on_CONSISTENT": 0.9473684210526315, |
| "eval/overall/acc_on_INCONSISTENT": 0.8118811881188119, |
| "eval/overall/accuracy": 0.8671875, |
| "eval/overall/f1_INC": 0.8785714285714287, |
| "eval/overall/precision_INC": 0.9571984435797666, |
| "eval/overall/recall_INC": 0.8118811881188119, |
| "eval/overall_exact_match": 0.728515625, |
| "eval_label": "step_600", |
| "step": 600 |
| }, |
| { |
| "epoch": 0.5644402634054563, |
| "grad_norm": 0.13476960361003876, |
| "learning_rate": 4.500484966052377e-05, |
| "loss": 0.0159, |
| "step": 600 |
| } |
| ], |
| "logging_steps": 20, |
| "max_steps": 1063, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 300, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 8.738632608964936e+17, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
