diff --git "a/last-checkpoint/trainer_state.json" "b/last-checkpoint/trainer_state.json" --- "a/last-checkpoint/trainer_state.json" +++ "b/last-checkpoint/trainer_state.json" @@ -1,9 +1,9 @@ { "best_metric": null, "best_model_checkpoint": null, - "epoch": 0.776925318053802, + "epoch": 0.9999028843352433, "eval_steps": 5, - "global_step": 3000, + "global_step": 3861, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, @@ -31224,6 +31224,8957 @@ "eval_samples_per_second": 2.986, "eval_steps_per_second": 0.136, "step": 3000 + }, + { + "epoch": 0.77718429315982, + "grad_norm": 3.063413913018199, + "learning_rate": 1.7967428508257653e-07, + "loss": 0.286, + "step": 3001 + }, + { + "epoch": 0.777443268265838, + "grad_norm": 3.8473608241469677, + "learning_rate": 1.7927789618289463e-07, + "loss": 0.3339, + "step": 3002 + }, + { + "epoch": 0.7777022433718559, + "grad_norm": 3.292994336016053, + "learning_rate": 1.788818717888586e-07, + "loss": 0.3252, + "step": 3003 + }, + { + "epoch": 0.7779612184778738, + "grad_norm": 8.606050746959276, + "learning_rate": 1.784862122243318e-07, + "loss": 0.3458, + "step": 3004 + }, + { + "epoch": 0.7782201935838917, + "grad_norm": 4.15084586160797, + "learning_rate": 1.780909178128793e-07, + "loss": 0.3716, + "step": 3005 + }, + { + "epoch": 0.7782201935838917, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8404924044002096, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.225625142455101, + "eval_runtime": 14.6687, + "eval_samples_per_second": 3.0, + "eval_steps_per_second": 0.136, + "step": 3005 + }, + { + "epoch": 0.7784791686899096, + "grad_norm": 8.14892489727702, + "learning_rate": 1.7769598887776768e-07, + "loss": 0.3613, + "step": 3006 + }, + { + "epoch": 0.7787381437959277, + "grad_norm": 4.113779303126627, + "learning_rate": 1.773014257419646e-07, + "loss": 0.2981, + "step": 3007 + }, + { + "epoch": 0.7789971189019456, + "grad_norm": 4.5002863178445045, + "learning_rate": 1.7690722872813863e-07, + "loss": 0.3161, + "step": 3008 + }, + { + "epoch": 0.7792560940079635, + "grad_norm": 5.141081748734731, + "learning_rate": 1.7651339815865885e-07, + "loss": 0.3137, + "step": 3009 + }, + { + "epoch": 0.7795150691139814, + "grad_norm": 3.49687353846544, + "learning_rate": 1.7611993435559485e-07, + "loss": 0.2933, + "step": 3010 + }, + { + "epoch": 0.7795150691139814, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8402304871660555, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22494862973690033, + "eval_runtime": 14.7055, + "eval_samples_per_second": 2.992, + "eval_steps_per_second": 0.136, + "step": 3010 + }, + { + "epoch": 0.7797740442199994, + "grad_norm": 4.525147961093864, + "learning_rate": 1.7572683764071577e-07, + "loss": 0.3237, + "step": 3011 + }, + { + "epoch": 0.7800330193260173, + "grad_norm": 3.0618279090759497, + "learning_rate": 1.7533410833549085e-07, + "loss": 0.3253, + "step": 3012 + }, + { + "epoch": 0.7802919944320352, + "grad_norm": 3.187192666794747, + "learning_rate": 1.7494174676108942e-07, + "loss": 0.2849, + "step": 3013 + }, + { + "epoch": 0.7805509695380531, + "grad_norm": 3.0432895321512174, + "learning_rate": 1.7454975323837936e-07, + "loss": 0.2829, + "step": 3014 + }, + { + "epoch": 0.780809944644071, + "grad_norm": 5.360131343034448, + "learning_rate": 1.7415812808792774e-07, + "loss": 0.3429, + "step": 3015 + }, + { + "epoch": 0.780809944644071, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8376113148245155, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.2252221554517746, + "eval_runtime": 14.747, + "eval_samples_per_second": 2.984, + "eval_steps_per_second": 0.136, + "step": 3015 + }, + { + "epoch": 0.7810689197500891, + "grad_norm": 3.409683517979357, + "learning_rate": 1.7376687163000053e-07, + "loss": 0.3276, + "step": 3016 + }, + { + "epoch": 0.781327894856107, + "grad_norm": 4.933182821100604, + "learning_rate": 1.7337598418456197e-07, + "loss": 0.3735, + "step": 3017 + }, + { + "epoch": 0.7815868699621249, + "grad_norm": 3.7704586038554684, + "learning_rate": 1.7298546607127494e-07, + "loss": 0.3244, + "step": 3018 + }, + { + "epoch": 0.7818458450681428, + "grad_norm": 3.261699169990043, + "learning_rate": 1.7259531760949953e-07, + "loss": 0.2765, + "step": 3019 + }, + { + "epoch": 0.7821048201741607, + "grad_norm": 4.5081068096019905, + "learning_rate": 1.7220553911829418e-07, + "loss": 0.3578, + "step": 3020 + }, + { + "epoch": 0.7821048201741607, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8386589837611316, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22578896582126617, + "eval_runtime": 15.107, + "eval_samples_per_second": 2.913, + "eval_steps_per_second": 0.132, + "step": 3020 + }, + { + "epoch": 0.7823637952801787, + "grad_norm": 3.642720174150836, + "learning_rate": 1.7181613091641472e-07, + "loss": 0.3428, + "step": 3021 + }, + { + "epoch": 0.7826227703861967, + "grad_norm": 3.2769131174028416, + "learning_rate": 1.714270933223139e-07, + "loss": 0.3084, + "step": 3022 + }, + { + "epoch": 0.7828817454922146, + "grad_norm": 2.871580677440366, + "learning_rate": 1.7103842665414135e-07, + "loss": 0.2744, + "step": 3023 + }, + { + "epoch": 0.7831407205982325, + "grad_norm": 3.649440014424122, + "learning_rate": 1.70650131229744e-07, + "loss": 0.3024, + "step": 3024 + }, + { + "epoch": 0.7833996957042504, + "grad_norm": 3.3966572072435737, + "learning_rate": 1.7026220736666447e-07, + "loss": 0.2833, + "step": 3025 + }, + { + "epoch": 0.7833996957042504, + "eval_PRM Accuracy": 0.8679245283018868, + "eval_PRM F1": 0.9135802469135802, + "eval_PRM F1 AUC": 0.8370874803562075, + "eval_PRM F1 AUC (fixed)": 0.8376113148245155, + "eval_PRM F1 Neg": 0.72, + "eval_PRM NPV": 0.6666666666666666, + "eval_PRM Precision": 0.9367088607594937, + "eval_PRM Recall": 0.891566265060241, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22521370649337769, + "eval_runtime": 14.9006, + "eval_samples_per_second": 2.953, + "eval_steps_per_second": 0.134, + "step": 3025 + }, + { + "epoch": 0.7836586708102684, + "grad_norm": 3.551364102153189, + "learning_rate": 1.698746553821419e-07, + "loss": 0.3126, + "step": 3026 + }, + { + "epoch": 0.7839176459162863, + "grad_norm": 5.047965204409711, + "learning_rate": 1.6948747559311086e-07, + "loss": 0.3495, + "step": 3027 + }, + { + "epoch": 0.7841766210223042, + "grad_norm": 4.996449188867915, + "learning_rate": 1.6910066831620207e-07, + "loss": 0.417, + "step": 3028 + }, + { + "epoch": 0.7844355961283221, + "grad_norm": 3.986789814086634, + "learning_rate": 1.6871423386774138e-07, + "loss": 0.2664, + "step": 3029 + }, + { + "epoch": 0.78469457123434, + "grad_norm": 5.557400122503032, + "learning_rate": 1.6832817256374978e-07, + "loss": 0.2476, + "step": 3030 + }, + { + "epoch": 0.78469457123434, + "eval_PRM Accuracy": 0.8679245283018868, + "eval_PRM F1": 0.9135802469135802, + "eval_PRM F1 AUC": 0.8370874803562075, + "eval_PRM F1 AUC (fixed)": 0.8360398114195915, + "eval_PRM F1 Neg": 0.72, + "eval_PRM NPV": 0.6666666666666666, + "eval_PRM Precision": 0.9367088607594937, + "eval_PRM Recall": 0.891566265060241, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22533774375915527, + "eval_runtime": 14.621, + "eval_samples_per_second": 3.009, + "eval_steps_per_second": 0.137, + "step": 3030 + }, + { + "epoch": 0.7849535463403581, + "grad_norm": 3.9640641304527695, + "learning_rate": 1.679424847199431e-07, + "loss": 0.3392, + "step": 3031 + }, + { + "epoch": 0.785212521446376, + "grad_norm": 3.5240211261699748, + "learning_rate": 1.6755717065173177e-07, + "loss": 0.2827, + "step": 3032 + }, + { + "epoch": 0.7854714965523939, + "grad_norm": 4.510321046297228, + "learning_rate": 1.6717223067422038e-07, + "loss": 0.2993, + "step": 3033 + }, + { + "epoch": 0.7857304716584118, + "grad_norm": 3.243998771764336, + "learning_rate": 1.6678766510220808e-07, + "loss": 0.3449, + "step": 3034 + }, + { + "epoch": 0.7859894467644297, + "grad_norm": 5.247798651020656, + "learning_rate": 1.664034742501875e-07, + "loss": 0.3453, + "step": 3035 + }, + { + "epoch": 0.7859894467644297, + "eval_PRM Accuracy": 0.8679245283018868, + "eval_PRM F1": 0.9135802469135802, + "eval_PRM F1 AUC": 0.8370874803562075, + "eval_PRM F1 AUC (fixed)": 0.8386589837611315, + "eval_PRM F1 Neg": 0.72, + "eval_PRM NPV": 0.6666666666666666, + "eval_PRM Precision": 0.9367088607594937, + "eval_PRM Recall": 0.891566265060241, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22425414621829987, + "eval_runtime": 14.9211, + "eval_samples_per_second": 2.949, + "eval_steps_per_second": 0.134, + "step": 3035 + }, + { + "epoch": 0.7862484218704477, + "grad_norm": 3.5074390253247225, + "learning_rate": 1.660196584323446e-07, + "loss": 0.3162, + "step": 3036 + }, + { + "epoch": 0.7865073969764657, + "grad_norm": 4.676266670241532, + "learning_rate": 1.656362179625589e-07, + "loss": 0.3826, + "step": 3037 + }, + { + "epoch": 0.7867663720824836, + "grad_norm": 3.295722956524875, + "learning_rate": 1.65253153154403e-07, + "loss": 0.3689, + "step": 3038 + }, + { + "epoch": 0.7870253471885015, + "grad_norm": 3.570468742916763, + "learning_rate": 1.6487046432114225e-07, + "loss": 0.3425, + "step": 3039 + }, + { + "epoch": 0.7872843222945194, + "grad_norm": 5.009717493531312, + "learning_rate": 1.6448815177573456e-07, + "loss": 0.3436, + "step": 3040 + }, + { + "epoch": 0.7872843222945194, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8360398114195915, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22432450950145721, + "eval_runtime": 15.0449, + "eval_samples_per_second": 2.925, + "eval_steps_per_second": 0.133, + "step": 3040 + }, + { + "epoch": 0.7875432974005374, + "grad_norm": 4.1789193330166166, + "learning_rate": 1.6410621583083007e-07, + "loss": 0.2745, + "step": 3041 + }, + { + "epoch": 0.7878022725065553, + "grad_norm": 3.5433453589448596, + "learning_rate": 1.637246567987709e-07, + "loss": 0.3093, + "step": 3042 + }, + { + "epoch": 0.7880612476125732, + "grad_norm": 6.137434156394761, + "learning_rate": 1.6334347499159104e-07, + "loss": 0.3676, + "step": 3043 + }, + { + "epoch": 0.7883202227185911, + "grad_norm": 5.156956777245463, + "learning_rate": 1.629626707210158e-07, + "loss": 0.333, + "step": 3044 + }, + { + "epoch": 0.7885791978246091, + "grad_norm": 5.784330100960781, + "learning_rate": 1.6258224429846204e-07, + "loss": 0.2847, + "step": 3045 + }, + { + "epoch": 0.7885791978246091, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8363017286537454, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22516365349292755, + "eval_runtime": 14.6872, + "eval_samples_per_second": 2.996, + "eval_steps_per_second": 0.136, + "step": 3045 + }, + { + "epoch": 0.7888381729306271, + "grad_norm": 4.506335458276582, + "learning_rate": 1.6220219603503742e-07, + "loss": 0.2925, + "step": 3046 + }, + { + "epoch": 0.789097148036645, + "grad_norm": 4.242863856497479, + "learning_rate": 1.6182252624154037e-07, + "loss": 0.3052, + "step": 3047 + }, + { + "epoch": 0.7893561231426629, + "grad_norm": 3.8363168711614706, + "learning_rate": 1.6144323522845977e-07, + "loss": 0.2972, + "step": 3048 + }, + { + "epoch": 0.7896150982486808, + "grad_norm": 5.669937742284619, + "learning_rate": 1.6106432330597493e-07, + "loss": 0.4139, + "step": 3049 + }, + { + "epoch": 0.7898740733546987, + "grad_norm": 3.4884395228241227, + "learning_rate": 1.6068579078395485e-07, + "loss": 0.256, + "step": 3050 + }, + { + "epoch": 0.7898740733546987, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8368255631220534, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22636336088180542, + "eval_runtime": 14.9392, + "eval_samples_per_second": 2.945, + "eval_steps_per_second": 0.134, + "step": 3050 + }, + { + "epoch": 0.7901330484607167, + "grad_norm": 8.331456865837293, + "learning_rate": 1.6030763797195857e-07, + "loss": 0.4064, + "step": 3051 + }, + { + "epoch": 0.7903920235667347, + "grad_norm": 5.0291371075428986, + "learning_rate": 1.599298651792344e-07, + "loss": 0.3923, + "step": 3052 + }, + { + "epoch": 0.7906509986727526, + "grad_norm": 3.057130056307773, + "learning_rate": 1.595524727147199e-07, + "loss": 0.249, + "step": 3053 + }, + { + "epoch": 0.7909099737787705, + "grad_norm": 2.9442653001523107, + "learning_rate": 1.5917546088704175e-07, + "loss": 0.333, + "step": 3054 + }, + { + "epoch": 0.7911689488847885, + "grad_norm": 3.898683692247379, + "learning_rate": 1.5879883000451512e-07, + "loss": 0.2937, + "step": 3055 + }, + { + "epoch": 0.7911689488847885, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8365636458878993, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22627776861190796, + "eval_runtime": 14.4651, + "eval_samples_per_second": 3.042, + "eval_steps_per_second": 0.138, + "step": 3055 + }, + { + "epoch": 0.7914279239908064, + "grad_norm": 4.586715193610282, + "learning_rate": 1.584225803751438e-07, + "loss": 0.3757, + "step": 3056 + }, + { + "epoch": 0.7916868990968243, + "grad_norm": 3.699001133143903, + "learning_rate": 1.5804671230661984e-07, + "loss": 0.3403, + "step": 3057 + }, + { + "epoch": 0.7919458742028422, + "grad_norm": 2.866994346554387, + "learning_rate": 1.5767122610632305e-07, + "loss": 0.2791, + "step": 3058 + }, + { + "epoch": 0.7922048493088601, + "grad_norm": 5.637341651118698, + "learning_rate": 1.5729612208132136e-07, + "loss": 0.2334, + "step": 3059 + }, + { + "epoch": 0.7924638244148782, + "grad_norm": 3.8090808011243826, + "learning_rate": 1.569214005383695e-07, + "loss": 0.3288, + "step": 3060 + }, + { + "epoch": 0.7924638244148782, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8376113148245155, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22738145291805267, + "eval_runtime": 14.3068, + "eval_samples_per_second": 3.075, + "eval_steps_per_second": 0.14, + "step": 3060 + }, + { + "epoch": 0.7927227995208961, + "grad_norm": 4.13457710597036, + "learning_rate": 1.5654706178390974e-07, + "loss": 0.368, + "step": 3061 + }, + { + "epoch": 0.792981774626914, + "grad_norm": 5.868660694024252, + "learning_rate": 1.5617310612407184e-07, + "loss": 0.3152, + "step": 3062 + }, + { + "epoch": 0.7932407497329319, + "grad_norm": 6.678385619854394, + "learning_rate": 1.557995338646716e-07, + "loss": 0.2686, + "step": 3063 + }, + { + "epoch": 0.7934997248389498, + "grad_norm": 7.683779303817856, + "learning_rate": 1.5542634531121135e-07, + "loss": 0.3267, + "step": 3064 + }, + { + "epoch": 0.7937586999449678, + "grad_norm": 3.2685967912793314, + "learning_rate": 1.5505354076887982e-07, + "loss": 0.3003, + "step": 3065 + }, + { + "epoch": 0.7937586999449678, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8370874803562074, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22620266675949097, + "eval_runtime": 14.461, + "eval_samples_per_second": 3.043, + "eval_steps_per_second": 0.138, + "step": 3065 + }, + { + "epoch": 0.7940176750509857, + "grad_norm": 2.836820711646679, + "learning_rate": 1.546811205425517e-07, + "loss": 0.2486, + "step": 3066 + }, + { + "epoch": 0.7942766501570037, + "grad_norm": 4.038480897554534, + "learning_rate": 1.5430908493678725e-07, + "loss": 0.3295, + "step": 3067 + }, + { + "epoch": 0.7945356252630216, + "grad_norm": 5.832788230955389, + "learning_rate": 1.539374342558325e-07, + "loss": 0.3394, + "step": 3068 + }, + { + "epoch": 0.7947946003690395, + "grad_norm": 6.749905153716121, + "learning_rate": 1.535661688036181e-07, + "loss": 0.2978, + "step": 3069 + }, + { + "epoch": 0.7950535754750575, + "grad_norm": 3.7646239090905764, + "learning_rate": 1.531952888837602e-07, + "loss": 0.3348, + "step": 3070 + }, + { + "epoch": 0.7950535754750575, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8394447354635934, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22611790895462036, + "eval_runtime": 14.4639, + "eval_samples_per_second": 3.042, + "eval_steps_per_second": 0.138, + "step": 3070 + }, + { + "epoch": 0.7953125505810754, + "grad_norm": 4.787920759409917, + "learning_rate": 1.5282479479955933e-07, + "loss": 0.3228, + "step": 3071 + }, + { + "epoch": 0.7955715256870933, + "grad_norm": 4.876688241079694, + "learning_rate": 1.5245468685400098e-07, + "loss": 0.372, + "step": 3072 + }, + { + "epoch": 0.7958305007931112, + "grad_norm": 3.4508314629346155, + "learning_rate": 1.5208496534975436e-07, + "loss": 0.3449, + "step": 3073 + }, + { + "epoch": 0.7960894758991292, + "grad_norm": 4.617203008880166, + "learning_rate": 1.517156305891729e-07, + "loss": 0.2731, + "step": 3074 + }, + { + "epoch": 0.7963484510051472, + "grad_norm": 4.635762082531109, + "learning_rate": 1.5134668287429356e-07, + "loss": 0.337, + "step": 3075 + }, + { + "epoch": 0.7963484510051472, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8363017286537455, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22483843564987183, + "eval_runtime": 14.5528, + "eval_samples_per_second": 3.023, + "eval_steps_per_second": 0.137, + "step": 3075 + }, + { + "epoch": 0.7966074261111651, + "grad_norm": 4.556853590649624, + "learning_rate": 1.509781225068372e-07, + "loss": 0.2857, + "step": 3076 + }, + { + "epoch": 0.796866401217183, + "grad_norm": 6.076231012352373, + "learning_rate": 1.5060994978820722e-07, + "loss": 0.3357, + "step": 3077 + }, + { + "epoch": 0.7971253763232009, + "grad_norm": 3.9661364457589445, + "learning_rate": 1.502421650194906e-07, + "loss": 0.3067, + "step": 3078 + }, + { + "epoch": 0.7973843514292188, + "grad_norm": 4.180657545866321, + "learning_rate": 1.4987476850145683e-07, + "loss": 0.3251, + "step": 3079 + }, + { + "epoch": 0.7976433265352368, + "grad_norm": 8.719142284309804, + "learning_rate": 1.4950776053455796e-07, + "loss": 0.3165, + "step": 3080 + }, + { + "epoch": 0.7976433265352368, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8378732320586695, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.2258179783821106, + "eval_runtime": 14.6192, + "eval_samples_per_second": 3.01, + "eval_steps_per_second": 0.137, + "step": 3080 + }, + { + "epoch": 0.7979023016412548, + "grad_norm": 3.3733373016902144, + "learning_rate": 1.4914114141892818e-07, + "loss": 0.2863, + "step": 3081 + }, + { + "epoch": 0.7981612767472727, + "grad_norm": 4.678216130638732, + "learning_rate": 1.4877491145438363e-07, + "loss": 0.3298, + "step": 3082 + }, + { + "epoch": 0.7984202518532906, + "grad_norm": 4.423993971881356, + "learning_rate": 1.4840907094042275e-07, + "loss": 0.2915, + "step": 3083 + }, + { + "epoch": 0.7986792269593085, + "grad_norm": 5.902942184330639, + "learning_rate": 1.4804362017622496e-07, + "loss": 0.3455, + "step": 3084 + }, + { + "epoch": 0.7989382020653265, + "grad_norm": 7.171137817687478, + "learning_rate": 1.4767855946065084e-07, + "loss": 0.403, + "step": 3085 + }, + { + "epoch": 0.7989382020653265, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8381351492928235, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22500590980052948, + "eval_runtime": 14.5711, + "eval_samples_per_second": 3.02, + "eval_steps_per_second": 0.137, + "step": 3085 + }, + { + "epoch": 0.7991971771713444, + "grad_norm": 4.86712286633565, + "learning_rate": 1.473138890922423e-07, + "loss": 0.3724, + "step": 3086 + }, + { + "epoch": 0.7994561522773623, + "grad_norm": 6.760809173787938, + "learning_rate": 1.4694960936922194e-07, + "loss": 0.3603, + "step": 3087 + }, + { + "epoch": 0.7997151273833802, + "grad_norm": 3.284939643692524, + "learning_rate": 1.46585720589493e-07, + "loss": 0.2588, + "step": 3088 + }, + { + "epoch": 0.7999741024893982, + "grad_norm": 4.67671853240067, + "learning_rate": 1.4622222305063882e-07, + "loss": 0.4205, + "step": 3089 + }, + { + "epoch": 0.8002330775954162, + "grad_norm": 5.345110970385336, + "learning_rate": 1.4585911704992294e-07, + "loss": 0.4929, + "step": 3090 + }, + { + "epoch": 0.8002330775954162, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8383970665269775, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.224909245967865, + "eval_runtime": 14.8238, + "eval_samples_per_second": 2.968, + "eval_steps_per_second": 0.135, + "step": 3090 + }, + { + "epoch": 0.8004920527014341, + "grad_norm": 3.4546943432630846, + "learning_rate": 1.454964028842886e-07, + "loss": 0.2634, + "step": 3091 + }, + { + "epoch": 0.800751027807452, + "grad_norm": 3.3655745729192996, + "learning_rate": 1.4513408085035846e-07, + "loss": 0.2538, + "step": 3092 + }, + { + "epoch": 0.8010100029134699, + "grad_norm": 3.2254857796024936, + "learning_rate": 1.4477215124443535e-07, + "loss": 0.2998, + "step": 3093 + }, + { + "epoch": 0.8012689780194879, + "grad_norm": 4.124644800001299, + "learning_rate": 1.444106143624998e-07, + "loss": 0.345, + "step": 3094 + }, + { + "epoch": 0.8015279531255058, + "grad_norm": 5.4090000885425775, + "learning_rate": 1.4404947050021227e-07, + "loss": 0.296, + "step": 3095 + }, + { + "epoch": 0.8015279531255058, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8376113148245155, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22668538987636566, + "eval_runtime": 14.6613, + "eval_samples_per_second": 3.001, + "eval_steps_per_second": 0.136, + "step": 3095 + }, + { + "epoch": 0.8017869282315238, + "grad_norm": 3.332477100057321, + "learning_rate": 1.4368871995291127e-07, + "loss": 0.3168, + "step": 3096 + }, + { + "epoch": 0.8020459033375417, + "grad_norm": 2.5996486925311166, + "learning_rate": 1.433283630156139e-07, + "loss": 0.2361, + "step": 3097 + }, + { + "epoch": 0.8023048784435596, + "grad_norm": 5.409189503940081, + "learning_rate": 1.4296839998301525e-07, + "loss": 0.3555, + "step": 3098 + }, + { + "epoch": 0.8025638535495776, + "grad_norm": 5.049019844494443, + "learning_rate": 1.4260883114948845e-07, + "loss": 0.3251, + "step": 3099 + }, + { + "epoch": 0.8028228286555955, + "grad_norm": 10.719990258680244, + "learning_rate": 1.4224965680908406e-07, + "loss": 0.3875, + "step": 3100 + }, + { + "epoch": 0.8028228286555955, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8383970665269775, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22511988878250122, + "eval_runtime": 14.8608, + "eval_samples_per_second": 2.961, + "eval_steps_per_second": 0.135, + "step": 3100 + }, + { + "epoch": 0.8030818037616134, + "grad_norm": 4.347877480378805, + "learning_rate": 1.418908772555301e-07, + "loss": 0.3546, + "step": 3101 + }, + { + "epoch": 0.8033407788676313, + "grad_norm": 3.761554703813863, + "learning_rate": 1.4153249278223173e-07, + "loss": 0.321, + "step": 3102 + }, + { + "epoch": 0.8035997539736492, + "grad_norm": 3.9064558442798014, + "learning_rate": 1.4117450368227113e-07, + "loss": 0.3719, + "step": 3103 + }, + { + "epoch": 0.8038587290796673, + "grad_norm": 7.113697099975123, + "learning_rate": 1.4081691024840694e-07, + "loss": 0.3344, + "step": 3104 + }, + { + "epoch": 0.8041177041856852, + "grad_norm": 3.440091756598331, + "learning_rate": 1.4045971277307447e-07, + "loss": 0.3255, + "step": 3105 + }, + { + "epoch": 0.8041177041856852, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8389209009952856, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22460676729679108, + "eval_runtime": 14.7959, + "eval_samples_per_second": 2.974, + "eval_steps_per_second": 0.135, + "step": 3105 + }, + { + "epoch": 0.8043766792917031, + "grad_norm": 3.673487570023885, + "learning_rate": 1.4010291154838497e-07, + "loss": 0.3469, + "step": 3106 + }, + { + "epoch": 0.804635654397721, + "grad_norm": 5.198761783713384, + "learning_rate": 1.3974650686612578e-07, + "loss": 0.3067, + "step": 3107 + }, + { + "epoch": 0.8048946295037389, + "grad_norm": 6.684141886639013, + "learning_rate": 1.3939049901776005e-07, + "loss": 0.3095, + "step": 3108 + }, + { + "epoch": 0.8051536046097569, + "grad_norm": 4.2798929995978385, + "learning_rate": 1.3903488829442631e-07, + "loss": 0.3929, + "step": 3109 + }, + { + "epoch": 0.8054125797157748, + "grad_norm": 3.6533286601307258, + "learning_rate": 1.3867967498693797e-07, + "loss": 0.2851, + "step": 3110 + }, + { + "epoch": 0.8054125797157748, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8376113148245155, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22461777925491333, + "eval_runtime": 14.7641, + "eval_samples_per_second": 2.98, + "eval_steps_per_second": 0.135, + "step": 3110 + }, + { + "epoch": 0.8056715548217928, + "grad_norm": 2.288780161233815, + "learning_rate": 1.3832485938578415e-07, + "loss": 0.2247, + "step": 3111 + }, + { + "epoch": 0.8059305299278107, + "grad_norm": 3.519189190121331, + "learning_rate": 1.3797044178112825e-07, + "loss": 0.3625, + "step": 3112 + }, + { + "epoch": 0.8061895050338286, + "grad_norm": 3.4262005567079914, + "learning_rate": 1.3761642246280827e-07, + "loss": 0.2713, + "step": 3113 + }, + { + "epoch": 0.8064484801398466, + "grad_norm": 5.807848612988007, + "learning_rate": 1.3726280172033653e-07, + "loss": 0.371, + "step": 3114 + }, + { + "epoch": 0.8067074552458645, + "grad_norm": 4.654482987368536, + "learning_rate": 1.3690957984289946e-07, + "loss": 0.3259, + "step": 3115 + }, + { + "epoch": 0.8067074552458645, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8357778941854375, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.2244022935628891, + "eval_runtime": 14.6581, + "eval_samples_per_second": 3.002, + "eval_steps_per_second": 0.136, + "step": 3115 + }, + { + "epoch": 0.8069664303518824, + "grad_norm": 6.677760279594266, + "learning_rate": 1.365567571193572e-07, + "loss": 0.4051, + "step": 3116 + }, + { + "epoch": 0.8072254054579003, + "grad_norm": 3.4039328099002235, + "learning_rate": 1.362043338382435e-07, + "loss": 0.2899, + "step": 3117 + }, + { + "epoch": 0.8074843805639182, + "grad_norm": 6.327243731165046, + "learning_rate": 1.3585231028776563e-07, + "loss": 0.2067, + "step": 3118 + }, + { + "epoch": 0.8077433556699363, + "grad_norm": 3.6966652503628192, + "learning_rate": 1.355006867558035e-07, + "loss": 0.2728, + "step": 3119 + }, + { + "epoch": 0.8080023307759542, + "grad_norm": 4.4630048179181765, + "learning_rate": 1.351494635299101e-07, + "loss": 0.3765, + "step": 3120 + }, + { + "epoch": 0.8080023307759542, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8386589837611315, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.2243594229221344, + "eval_runtime": 14.9133, + "eval_samples_per_second": 2.95, + "eval_steps_per_second": 0.134, + "step": 3120 + }, + { + "epoch": 0.8082613058819721, + "grad_norm": 5.585078070140554, + "learning_rate": 1.347986408973116e-07, + "loss": 0.3408, + "step": 3121 + }, + { + "epoch": 0.80852028098799, + "grad_norm": 3.0796542466944614, + "learning_rate": 1.344482191449059e-07, + "loss": 0.2649, + "step": 3122 + }, + { + "epoch": 0.8087792560940079, + "grad_norm": 7.192051449257777, + "learning_rate": 1.340981985592632e-07, + "loss": 0.3207, + "step": 3123 + }, + { + "epoch": 0.8090382312000259, + "grad_norm": 4.17964014272493, + "learning_rate": 1.3374857942662577e-07, + "loss": 0.3303, + "step": 3124 + }, + { + "epoch": 0.8092972063060438, + "grad_norm": 5.378015158527195, + "learning_rate": 1.3339936203290758e-07, + "loss": 0.3897, + "step": 3125 + }, + { + "epoch": 0.8092972063060438, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8352540597171294, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22555293142795563, + "eval_runtime": 14.3721, + "eval_samples_per_second": 3.061, + "eval_steps_per_second": 0.139, + "step": 3125 + }, + { + "epoch": 0.8095561814120618, + "grad_norm": 4.567213801644765, + "learning_rate": 1.3305054666369408e-07, + "loss": 0.3309, + "step": 3126 + }, + { + "epoch": 0.8098151565180797, + "grad_norm": 4.563219192763328, + "learning_rate": 1.3270213360424154e-07, + "loss": 0.3067, + "step": 3127 + }, + { + "epoch": 0.8100741316240976, + "grad_norm": 4.90789793762559, + "learning_rate": 1.3235412313947773e-07, + "loss": 0.3605, + "step": 3128 + }, + { + "epoch": 0.8103331067301156, + "grad_norm": 3.160901274703959, + "learning_rate": 1.3200651555400104e-07, + "loss": 0.3044, + "step": 3129 + }, + { + "epoch": 0.8105920818361335, + "grad_norm": 4.470423523557715, + "learning_rate": 1.3165931113208012e-07, + "loss": 0.2984, + "step": 3130 + }, + { + "epoch": 0.8105920818361335, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8349921424829754, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22475433349609375, + "eval_runtime": 14.61, + "eval_samples_per_second": 3.012, + "eval_steps_per_second": 0.137, + "step": 3130 + }, + { + "epoch": 0.8108510569421514, + "grad_norm": 3.8955145810333653, + "learning_rate": 1.3131251015765457e-07, + "loss": 0.2885, + "step": 3131 + }, + { + "epoch": 0.8111100320481693, + "grad_norm": 3.8301522085136637, + "learning_rate": 1.3096611291433344e-07, + "loss": 0.2855, + "step": 3132 + }, + { + "epoch": 0.8113690071541872, + "grad_norm": 4.56474854284993, + "learning_rate": 1.3062011968539582e-07, + "loss": 0.261, + "step": 3133 + }, + { + "epoch": 0.8116279822602053, + "grad_norm": 3.756937968072322, + "learning_rate": 1.302745307537906e-07, + "loss": 0.3561, + "step": 3134 + }, + { + "epoch": 0.8118869573662232, + "grad_norm": 8.389672208602333, + "learning_rate": 1.2992934640213547e-07, + "loss": 0.3888, + "step": 3135 + }, + { + "epoch": 0.8118869573662232, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8336825563122053, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22338654100894928, + "eval_runtime": 14.859, + "eval_samples_per_second": 2.961, + "eval_steps_per_second": 0.135, + "step": 3135 + }, + { + "epoch": 0.8121459324722411, + "grad_norm": 6.045296721565757, + "learning_rate": 1.2958456691271783e-07, + "loss": 0.3685, + "step": 3136 + }, + { + "epoch": 0.812404907578259, + "grad_norm": 3.2575007493958714, + "learning_rate": 1.2924019256749375e-07, + "loss": 0.3193, + "step": 3137 + }, + { + "epoch": 0.812663882684277, + "grad_norm": 2.969174698102353, + "learning_rate": 1.28896223648088e-07, + "loss": 0.2837, + "step": 3138 + }, + { + "epoch": 0.8129228577902949, + "grad_norm": 5.449678885023483, + "learning_rate": 1.2855266043579388e-07, + "loss": 0.2662, + "step": 3139 + }, + { + "epoch": 0.8131818328963129, + "grad_norm": 4.155946182197453, + "learning_rate": 1.282095032115728e-07, + "loss": 0.3551, + "step": 3140 + }, + { + "epoch": 0.8131818328963129, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8331587218438974, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22306251525878906, + "eval_runtime": 14.6842, + "eval_samples_per_second": 2.996, + "eval_steps_per_second": 0.136, + "step": 3140 + }, + { + "epoch": 0.8134408080023308, + "grad_norm": 3.1989756573789543, + "learning_rate": 1.27866752256054e-07, + "loss": 0.2632, + "step": 3141 + }, + { + "epoch": 0.8136997831083487, + "grad_norm": 5.374824118397931, + "learning_rate": 1.2752440784953518e-07, + "loss": 0.3487, + "step": 3142 + }, + { + "epoch": 0.8139587582143667, + "grad_norm": 5.140350533632939, + "learning_rate": 1.2718247027198087e-07, + "loss": 0.3871, + "step": 3143 + }, + { + "epoch": 0.8142177333203846, + "grad_norm": 3.466759545788073, + "learning_rate": 1.2684093980302292e-07, + "loss": 0.374, + "step": 3144 + }, + { + "epoch": 0.8144767084264025, + "grad_norm": 2.9777098889112867, + "learning_rate": 1.2649981672196048e-07, + "loss": 0.3048, + "step": 3145 + }, + { + "epoch": 0.8144767084264025, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8376113148245155, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22220945358276367, + "eval_runtime": 14.5693, + "eval_samples_per_second": 3.02, + "eval_steps_per_second": 0.137, + "step": 3145 + }, + { + "epoch": 0.8147356835324204, + "grad_norm": 4.0269240569764, + "learning_rate": 1.2615910130775956e-07, + "loss": 0.2838, + "step": 3146 + }, + { + "epoch": 0.8149946586384383, + "grad_norm": 3.5173318154889786, + "learning_rate": 1.2581879383905275e-07, + "loss": 0.2813, + "step": 3147 + }, + { + "epoch": 0.8152536337444564, + "grad_norm": 8.246408047389778, + "learning_rate": 1.254788945941389e-07, + "loss": 0.3619, + "step": 3148 + }, + { + "epoch": 0.8155126088504743, + "grad_norm": 4.209418843504564, + "learning_rate": 1.2513940385098324e-07, + "loss": 0.2787, + "step": 3149 + }, + { + "epoch": 0.8157715839564922, + "grad_norm": 5.538849921809308, + "learning_rate": 1.2480032188721673e-07, + "loss": 0.3493, + "step": 3150 + }, + { + "epoch": 0.8157715839564922, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8347302252488213, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22439557313919067, + "eval_runtime": 14.5339, + "eval_samples_per_second": 3.027, + "eval_steps_per_second": 0.138, + "step": 3150 + }, + { + "epoch": 0.8160305590625101, + "grad_norm": 4.253796826647627, + "learning_rate": 1.244616489801362e-07, + "loss": 0.2748, + "step": 3151 + }, + { + "epoch": 0.816289534168528, + "grad_norm": 3.5559438352739883, + "learning_rate": 1.241233854067038e-07, + "loss": 0.3228, + "step": 3152 + }, + { + "epoch": 0.816548509274546, + "grad_norm": 3.6626992533987472, + "learning_rate": 1.2378553144354704e-07, + "loss": 0.3448, + "step": 3153 + }, + { + "epoch": 0.8168074843805639, + "grad_norm": 3.547105408007252, + "learning_rate": 1.2344808736695837e-07, + "loss": 0.3277, + "step": 3154 + }, + { + "epoch": 0.8170664594865819, + "grad_norm": 3.0521699136487475, + "learning_rate": 1.2311105345289515e-07, + "loss": 0.3089, + "step": 3155 + }, + { + "epoch": 0.8170664594865819, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8347302252488213, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.2242182344198227, + "eval_runtime": 14.5826, + "eval_samples_per_second": 3.017, + "eval_steps_per_second": 0.137, + "step": 3155 + }, + { + "epoch": 0.8173254345925998, + "grad_norm": 3.040530752436925, + "learning_rate": 1.2277442997697932e-07, + "loss": 0.312, + "step": 3156 + }, + { + "epoch": 0.8175844096986177, + "grad_norm": 3.494665550459257, + "learning_rate": 1.22438217214497e-07, + "loss": 0.3003, + "step": 3157 + }, + { + "epoch": 0.8178433848046357, + "grad_norm": 3.3742381410931257, + "learning_rate": 1.221024154403986e-07, + "loss": 0.3646, + "step": 3158 + }, + { + "epoch": 0.8181023599106536, + "grad_norm": 3.623043834571127, + "learning_rate": 1.2176702492929834e-07, + "loss": 0.3108, + "step": 3159 + }, + { + "epoch": 0.8183613350166715, + "grad_norm": 4.38197614523558, + "learning_rate": 1.2143204595547424e-07, + "loss": 0.3815, + "step": 3160 + }, + { + "epoch": 0.8183613350166715, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8381351492928235, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22308219969272614, + "eval_runtime": 14.3162, + "eval_samples_per_second": 3.073, + "eval_steps_per_second": 0.14, + "step": 3160 + }, + { + "epoch": 0.8186203101226894, + "grad_norm": 4.507430086887117, + "learning_rate": 1.2109747879286752e-07, + "loss": 0.3908, + "step": 3161 + }, + { + "epoch": 0.8188792852287073, + "grad_norm": 3.2922128599615617, + "learning_rate": 1.2076332371508294e-07, + "loss": 0.2792, + "step": 3162 + }, + { + "epoch": 0.8191382603347254, + "grad_norm": 4.985052400589261, + "learning_rate": 1.20429580995388e-07, + "loss": 0.361, + "step": 3163 + }, + { + "epoch": 0.8193972354407433, + "grad_norm": 2.9795001128313654, + "learning_rate": 1.2009625090671314e-07, + "loss": 0.2796, + "step": 3164 + }, + { + "epoch": 0.8196562105467612, + "grad_norm": 3.5950376749594635, + "learning_rate": 1.1976333372165132e-07, + "loss": 0.3117, + "step": 3165 + }, + { + "epoch": 0.8196562105467612, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8360398114195915, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22432804107666016, + "eval_runtime": 14.4376, + "eval_samples_per_second": 3.048, + "eval_steps_per_second": 0.139, + "step": 3165 + }, + { + "epoch": 0.8199151856527791, + "grad_norm": 3.8837689376209177, + "learning_rate": 1.1943082971245772e-07, + "loss": 0.2848, + "step": 3166 + }, + { + "epoch": 0.820174160758797, + "grad_norm": 3.85110042339936, + "learning_rate": 1.190987391510498e-07, + "loss": 0.3537, + "step": 3167 + }, + { + "epoch": 0.820433135864815, + "grad_norm": 4.147281018993882, + "learning_rate": 1.1876706230900696e-07, + "loss": 0.3083, + "step": 3168 + }, + { + "epoch": 0.8206921109708329, + "grad_norm": 7.425239472199798, + "learning_rate": 1.1843579945756974e-07, + "loss": 0.4569, + "step": 3169 + }, + { + "epoch": 0.8209510860768509, + "grad_norm": 3.3945647674519392, + "learning_rate": 1.1810495086764088e-07, + "loss": 0.3544, + "step": 3170 + }, + { + "epoch": 0.8209510860768509, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8357778941854375, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22527550160884857, + "eval_runtime": 14.4903, + "eval_samples_per_second": 3.037, + "eval_steps_per_second": 0.138, + "step": 3170 + }, + { + "epoch": 0.8212100611828688, + "grad_norm": 7.703193550100602, + "learning_rate": 1.1777451680978386e-07, + "loss": 0.3732, + "step": 3171 + }, + { + "epoch": 0.8214690362888867, + "grad_norm": 4.535249386992737, + "learning_rate": 1.1744449755422334e-07, + "loss": 0.2744, + "step": 3172 + }, + { + "epoch": 0.8217280113949047, + "grad_norm": 3.159607628957131, + "learning_rate": 1.1711489337084464e-07, + "loss": 0.3217, + "step": 3173 + }, + { + "epoch": 0.8219869865009226, + "grad_norm": 4.094469303883063, + "learning_rate": 1.1678570452919376e-07, + "loss": 0.3373, + "step": 3174 + }, + { + "epoch": 0.8222459616069405, + "grad_norm": 2.8740138898146443, + "learning_rate": 1.1645693129847695e-07, + "loss": 0.2964, + "step": 3175 + }, + { + "epoch": 0.8222459616069405, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8355159769512834, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22569118440151215, + "eval_runtime": 14.695, + "eval_samples_per_second": 2.994, + "eval_steps_per_second": 0.136, + "step": 3175 + }, + { + "epoch": 0.8225049367129584, + "grad_norm": 3.8194753946169886, + "learning_rate": 1.1612857394756073e-07, + "loss": 0.2752, + "step": 3176 + }, + { + "epoch": 0.8227639118189763, + "grad_norm": 4.975676908575541, + "learning_rate": 1.1580063274497122e-07, + "loss": 0.4378, + "step": 3177 + }, + { + "epoch": 0.8230228869249944, + "grad_norm": 2.9423084641013597, + "learning_rate": 1.1547310795889444e-07, + "loss": 0.3768, + "step": 3178 + }, + { + "epoch": 0.8232818620310123, + "grad_norm": 4.29102835430554, + "learning_rate": 1.1514599985717564e-07, + "loss": 0.3652, + "step": 3179 + }, + { + "epoch": 0.8235408371370302, + "grad_norm": 6.797678493616764, + "learning_rate": 1.1481930870731995e-07, + "loss": 0.3116, + "step": 3180 + }, + { + "epoch": 0.8235408371370302, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8344683080146674, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22575873136520386, + "eval_runtime": 14.869, + "eval_samples_per_second": 2.959, + "eval_steps_per_second": 0.135, + "step": 3180 + }, + { + "epoch": 0.8237998122430481, + "grad_norm": 4.458636655408022, + "learning_rate": 1.1449303477649089e-07, + "loss": 0.3157, + "step": 3181 + }, + { + "epoch": 0.8240587873490661, + "grad_norm": 4.6200490531791365, + "learning_rate": 1.1416717833151091e-07, + "loss": 0.3708, + "step": 3182 + }, + { + "epoch": 0.824317762455084, + "grad_norm": 5.627128293966109, + "learning_rate": 1.1384173963886109e-07, + "loss": 0.2555, + "step": 3183 + }, + { + "epoch": 0.824576737561102, + "grad_norm": 3.0719330389581616, + "learning_rate": 1.1351671896468109e-07, + "loss": 0.3309, + "step": 3184 + }, + { + "epoch": 0.8248357126671199, + "grad_norm": 5.253415614672871, + "learning_rate": 1.1319211657476827e-07, + "loss": 0.4469, + "step": 3185 + }, + { + "epoch": 0.8248357126671199, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8347302252488213, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.2272109091281891, + "eval_runtime": 14.412, + "eval_samples_per_second": 3.053, + "eval_steps_per_second": 0.139, + "step": 3185 + }, + { + "epoch": 0.8250946877731378, + "grad_norm": 6.612044977157061, + "learning_rate": 1.1286793273457816e-07, + "loss": 0.3141, + "step": 3186 + }, + { + "epoch": 0.8253536628791558, + "grad_norm": 6.547230536086711, + "learning_rate": 1.1254416770922421e-07, + "loss": 0.4776, + "step": 3187 + }, + { + "epoch": 0.8256126379851737, + "grad_norm": 3.8024729421105516, + "learning_rate": 1.1222082176347702e-07, + "loss": 0.3652, + "step": 3188 + }, + { + "epoch": 0.8258716130911916, + "grad_norm": 3.3937459749162153, + "learning_rate": 1.1189789516176475e-07, + "loss": 0.2474, + "step": 3189 + }, + { + "epoch": 0.8261305881972095, + "grad_norm": 3.4153618441248135, + "learning_rate": 1.1157538816817227e-07, + "loss": 0.2584, + "step": 3190 + }, + { + "epoch": 0.8261305881972095, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8326348873755893, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.228841170668602, + "eval_runtime": 14.9547, + "eval_samples_per_second": 2.942, + "eval_steps_per_second": 0.134, + "step": 3190 + }, + { + "epoch": 0.8263895633032274, + "grad_norm": 5.904493247203295, + "learning_rate": 1.1125330104644193e-07, + "loss": 0.3946, + "step": 3191 + }, + { + "epoch": 0.8266485384092455, + "grad_norm": 3.358936600919463, + "learning_rate": 1.1093163405997226e-07, + "loss": 0.315, + "step": 3192 + }, + { + "epoch": 0.8269075135152634, + "grad_norm": 4.116907361549203, + "learning_rate": 1.1061038747181792e-07, + "loss": 0.3356, + "step": 3193 + }, + { + "epoch": 0.8271664886212813, + "grad_norm": 4.138048499578868, + "learning_rate": 1.1028956154469035e-07, + "loss": 0.286, + "step": 3194 + }, + { + "epoch": 0.8274254637272992, + "grad_norm": 6.1303510703640045, + "learning_rate": 1.0996915654095678e-07, + "loss": 0.2547, + "step": 3195 + }, + { + "epoch": 0.8274254637272992, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8370874803562074, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22799743711948395, + "eval_runtime": 14.6581, + "eval_samples_per_second": 3.002, + "eval_steps_per_second": 0.136, + "step": 3195 + }, + { + "epoch": 0.8276844388333171, + "grad_norm": 2.669708165312555, + "learning_rate": 1.0964917272264016e-07, + "loss": 0.3023, + "step": 3196 + }, + { + "epoch": 0.8279434139393351, + "grad_norm": 2.6882553683641497, + "learning_rate": 1.0932961035141895e-07, + "loss": 0.2665, + "step": 3197 + }, + { + "epoch": 0.828202389045353, + "grad_norm": 4.619996487067307, + "learning_rate": 1.0901046968862711e-07, + "loss": 0.2691, + "step": 3198 + }, + { + "epoch": 0.828461364151371, + "grad_norm": 4.659738372771947, + "learning_rate": 1.0869175099525363e-07, + "loss": 0.374, + "step": 3199 + }, + { + "epoch": 0.8287203392573889, + "grad_norm": 2.9964288796337515, + "learning_rate": 1.0837345453194231e-07, + "loss": 0.345, + "step": 3200 + }, + { + "epoch": 0.8287203392573889, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8334206390780514, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22903980314731598, + "eval_runtime": 14.5642, + "eval_samples_per_second": 3.021, + "eval_steps_per_second": 0.137, + "step": 3200 + }, + { + "epoch": 0.8289793143634068, + "grad_norm": 5.103977615798045, + "learning_rate": 1.0805558055899231e-07, + "loss": 0.2982, + "step": 3201 + }, + { + "epoch": 0.8292382894694248, + "grad_norm": 3.3570338955698458, + "learning_rate": 1.0773812933635615e-07, + "loss": 0.2958, + "step": 3202 + }, + { + "epoch": 0.8294972645754427, + "grad_norm": 8.114913119069808, + "learning_rate": 1.0742110112364153e-07, + "loss": 0.3098, + "step": 3203 + }, + { + "epoch": 0.8297562396814606, + "grad_norm": 2.80025645297437, + "learning_rate": 1.0710449618010987e-07, + "loss": 0.3152, + "step": 3204 + }, + { + "epoch": 0.8300152147874785, + "grad_norm": 4.218916408091627, + "learning_rate": 1.0678831476467651e-07, + "loss": 0.2989, + "step": 3205 + }, + { + "epoch": 0.8300152147874785, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8376113148245155, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22697149217128754, + "eval_runtime": 14.8568, + "eval_samples_per_second": 2.962, + "eval_steps_per_second": 0.135, + "step": 3205 + }, + { + "epoch": 0.8302741898934964, + "grad_norm": 6.456776696718716, + "learning_rate": 1.0647255713591043e-07, + "loss": 0.3777, + "step": 3206 + }, + { + "epoch": 0.8305331649995145, + "grad_norm": 4.642876985993794, + "learning_rate": 1.061572235520341e-07, + "loss": 0.2903, + "step": 3207 + }, + { + "epoch": 0.8307921401055324, + "grad_norm": 3.360250151483618, + "learning_rate": 1.0584231427092313e-07, + "loss": 0.297, + "step": 3208 + }, + { + "epoch": 0.8310511152115503, + "grad_norm": 4.834170428788455, + "learning_rate": 1.0552782955010616e-07, + "loss": 0.2816, + "step": 3209 + }, + { + "epoch": 0.8313100903175682, + "grad_norm": 3.2888737397663075, + "learning_rate": 1.0521376964676463e-07, + "loss": 0.3324, + "step": 3210 + }, + { + "epoch": 0.8313100903175682, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8344683080146673, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.2260277271270752, + "eval_runtime": 14.4018, + "eval_samples_per_second": 3.055, + "eval_steps_per_second": 0.139, + "step": 3210 + }, + { + "epoch": 0.8315690654235861, + "grad_norm": 4.622683902672736, + "learning_rate": 1.049001348177326e-07, + "loss": 0.3545, + "step": 3211 + }, + { + "epoch": 0.8318280405296041, + "grad_norm": 2.6641944582954493, + "learning_rate": 1.0458692531949644e-07, + "loss": 0.3128, + "step": 3212 + }, + { + "epoch": 0.832087015635622, + "grad_norm": 4.310937407923954, + "learning_rate": 1.0427414140819478e-07, + "loss": 0.34, + "step": 3213 + }, + { + "epoch": 0.83234599074164, + "grad_norm": 3.922701908255086, + "learning_rate": 1.0396178333961816e-07, + "loss": 0.4212, + "step": 3214 + }, + { + "epoch": 0.8326049658476579, + "grad_norm": 4.9585900596768955, + "learning_rate": 1.0364985136920892e-07, + "loss": 0.3451, + "step": 3215 + }, + { + "epoch": 0.8326049658476579, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8349921424829754, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.2246641218662262, + "eval_runtime": 14.7217, + "eval_samples_per_second": 2.989, + "eval_steps_per_second": 0.136, + "step": 3215 + }, + { + "epoch": 0.8328639409536758, + "grad_norm": 3.212863684839889, + "learning_rate": 1.0333834575206085e-07, + "loss": 0.2683, + "step": 3216 + }, + { + "epoch": 0.8331229160596938, + "grad_norm": 3.133994293985615, + "learning_rate": 1.0302726674291927e-07, + "loss": 0.3651, + "step": 3217 + }, + { + "epoch": 0.8333818911657117, + "grad_norm": 4.077068899929995, + "learning_rate": 1.0271661459618006e-07, + "loss": 0.3235, + "step": 3218 + }, + { + "epoch": 0.8336408662717296, + "grad_norm": 3.0881432615077458, + "learning_rate": 1.0240638956589083e-07, + "loss": 0.2356, + "step": 3219 + }, + { + "epoch": 0.8338998413777475, + "grad_norm": 5.295920901491226, + "learning_rate": 1.0209659190574949e-07, + "loss": 0.3788, + "step": 3220 + }, + { + "epoch": 0.8338998413777475, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8376113148245155, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.225033238530159, + "eval_runtime": 15.2765, + "eval_samples_per_second": 2.88, + "eval_steps_per_second": 0.131, + "step": 3220 + }, + { + "epoch": 0.8341588164837656, + "grad_norm": 3.987332880810263, + "learning_rate": 1.0178722186910441e-07, + "loss": 0.355, + "step": 3221 + }, + { + "epoch": 0.8344177915897835, + "grad_norm": 5.888103364821521, + "learning_rate": 1.0147827970895425e-07, + "loss": 0.3649, + "step": 3222 + }, + { + "epoch": 0.8346767666958014, + "grad_norm": 6.953586426062711, + "learning_rate": 1.0116976567794784e-07, + "loss": 0.3417, + "step": 3223 + }, + { + "epoch": 0.8349357418018193, + "grad_norm": 3.014322722612192, + "learning_rate": 1.0086168002838397e-07, + "loss": 0.2217, + "step": 3224 + }, + { + "epoch": 0.8351947169078372, + "grad_norm": 4.0908575472485085, + "learning_rate": 1.0055402301221095e-07, + "loss": 0.3787, + "step": 3225 + }, + { + "epoch": 0.8351947169078372, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8397066526977475, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22433432936668396, + "eval_runtime": 14.7048, + "eval_samples_per_second": 2.992, + "eval_steps_per_second": 0.136, + "step": 3225 + }, + { + "epoch": 0.8354536920138552, + "grad_norm": 3.1660494678650792, + "learning_rate": 1.0024679488102679e-07, + "loss": 0.3254, + "step": 3226 + }, + { + "epoch": 0.8357126671198731, + "grad_norm": 3.546917727497168, + "learning_rate": 9.993999588607827e-08, + "loss": 0.2763, + "step": 3227 + }, + { + "epoch": 0.835971642225891, + "grad_norm": 4.337922346001531, + "learning_rate": 9.963362627826157e-08, + "loss": 0.3077, + "step": 3228 + }, + { + "epoch": 0.836230617331909, + "grad_norm": 3.0814028269238167, + "learning_rate": 9.932768630812204e-08, + "loss": 0.3224, + "step": 3229 + }, + { + "epoch": 0.8364895924379269, + "grad_norm": 4.4501996697923225, + "learning_rate": 9.902217622585308e-08, + "loss": 0.3614, + "step": 3230 + }, + { + "epoch": 0.8364895924379269, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8363017286537454, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22447329759597778, + "eval_runtime": 14.73, + "eval_samples_per_second": 2.987, + "eval_steps_per_second": 0.136, + "step": 3230 + }, + { + "epoch": 0.8367485675439449, + "grad_norm": 3.523486521444904, + "learning_rate": 9.871709628129694e-08, + "loss": 0.2424, + "step": 3231 + }, + { + "epoch": 0.8370075426499628, + "grad_norm": 9.38716515921061, + "learning_rate": 9.84124467239439e-08, + "loss": 0.3985, + "step": 3232 + }, + { + "epoch": 0.8372665177559807, + "grad_norm": 2.5441215991283603, + "learning_rate": 9.81082278029323e-08, + "loss": 0.2407, + "step": 3233 + }, + { + "epoch": 0.8375254928619986, + "grad_norm": 4.515093182419461, + "learning_rate": 9.780443976704856e-08, + "loss": 0.3424, + "step": 3234 + }, + { + "epoch": 0.8377844679680165, + "grad_norm": 3.4613994023174177, + "learning_rate": 9.750108286472625e-08, + "loss": 0.2788, + "step": 3235 + }, + { + "epoch": 0.8377844679680165, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8336825563122054, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.2260800451040268, + "eval_runtime": 14.221, + "eval_samples_per_second": 3.094, + "eval_steps_per_second": 0.141, + "step": 3235 + }, + { + "epoch": 0.8380434430740346, + "grad_norm": 3.494656974841171, + "learning_rate": 9.71981573440467e-08, + "loss": 0.3075, + "step": 3236 + }, + { + "epoch": 0.8383024181800525, + "grad_norm": 4.409321576005133, + "learning_rate": 9.689566345273841e-08, + "loss": 0.3187, + "step": 3237 + }, + { + "epoch": 0.8385613932860704, + "grad_norm": 5.821066178378045, + "learning_rate": 9.65936014381768e-08, + "loss": 0.2959, + "step": 3238 + }, + { + "epoch": 0.8388203683920883, + "grad_norm": 4.037897922469876, + "learning_rate": 9.629197154738451e-08, + "loss": 0.4197, + "step": 3239 + }, + { + "epoch": 0.8390793434981062, + "grad_norm": 4.868964587487792, + "learning_rate": 9.599077402703021e-08, + "loss": 0.3332, + "step": 3240 + }, + { + "epoch": 0.8390793434981062, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8365636458878994, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22532673180103302, + "eval_runtime": 14.5694, + "eval_samples_per_second": 3.02, + "eval_steps_per_second": 0.137, + "step": 3240 + }, + { + "epoch": 0.8393383186041242, + "grad_norm": 3.988859996944219, + "learning_rate": 9.569000912342932e-08, + "loss": 0.3815, + "step": 3241 + }, + { + "epoch": 0.8395972937101421, + "grad_norm": 3.7646617188331746, + "learning_rate": 9.538967708254361e-08, + "loss": 0.3713, + "step": 3242 + }, + { + "epoch": 0.83985626881616, + "grad_norm": 12.983374167438368, + "learning_rate": 9.508977814998023e-08, + "loss": 0.4843, + "step": 3243 + }, + { + "epoch": 0.840115243922178, + "grad_norm": 4.8049101687868845, + "learning_rate": 9.47903125709928e-08, + "loss": 0.3383, + "step": 3244 + }, + { + "epoch": 0.8403742190281959, + "grad_norm": 4.919475651472781, + "learning_rate": 9.449128059048032e-08, + "loss": 0.3411, + "step": 3245 + }, + { + "epoch": 0.8403742190281959, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8334206390780513, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22586487233638763, + "eval_runtime": 14.8644, + "eval_samples_per_second": 2.96, + "eval_steps_per_second": 0.135, + "step": 3245 + }, + { + "epoch": 0.8406331941342139, + "grad_norm": 3.3355306040580404, + "learning_rate": 9.419268245298715e-08, + "loss": 0.3103, + "step": 3246 + }, + { + "epoch": 0.8408921692402318, + "grad_norm": 2.8266428438009776, + "learning_rate": 9.389451840270292e-08, + "loss": 0.2743, + "step": 3247 + }, + { + "epoch": 0.8411511443462497, + "grad_norm": 4.302602700561876, + "learning_rate": 9.359678868346219e-08, + "loss": 0.3559, + "step": 3248 + }, + { + "epoch": 0.8414101194522676, + "grad_norm": 4.424565835089334, + "learning_rate": 9.329949353874434e-08, + "loss": 0.3228, + "step": 3249 + }, + { + "epoch": 0.8416690945582855, + "grad_norm": 4.775069123929839, + "learning_rate": 9.300263321167367e-08, + "loss": 0.2827, + "step": 3250 + }, + { + "epoch": 0.8416690945582855, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8339444735463593, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.2263118326663971, + "eval_runtime": 14.2575, + "eval_samples_per_second": 3.086, + "eval_steps_per_second": 0.14, + "step": 3250 + }, + { + "epoch": 0.8419280696643036, + "grad_norm": 5.2192366959286085, + "learning_rate": 9.270620794501861e-08, + "loss": 0.2695, + "step": 3251 + }, + { + "epoch": 0.8421870447703215, + "grad_norm": 2.685766572229494, + "learning_rate": 9.241021798119157e-08, + "loss": 0.2374, + "step": 3252 + }, + { + "epoch": 0.8424460198763394, + "grad_norm": 4.920178240819252, + "learning_rate": 9.211466356224927e-08, + "loss": 0.3461, + "step": 3253 + }, + { + "epoch": 0.8427049949823573, + "grad_norm": 6.108691526658832, + "learning_rate": 9.18195449298924e-08, + "loss": 0.319, + "step": 3254 + }, + { + "epoch": 0.8429639700883752, + "grad_norm": 4.445759440164081, + "learning_rate": 9.152486232546492e-08, + "loss": 0.3121, + "step": 3255 + }, + { + "epoch": 0.8429639700883752, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8339444735463594, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22631831467151642, + "eval_runtime": 14.779, + "eval_samples_per_second": 2.977, + "eval_steps_per_second": 0.135, + "step": 3255 + }, + { + "epoch": 0.8432229451943932, + "grad_norm": 5.491988117433152, + "learning_rate": 9.123061598995439e-08, + "loss": 0.3035, + "step": 3256 + }, + { + "epoch": 0.8434819203004111, + "grad_norm": 4.561194119088811, + "learning_rate": 9.093680616399161e-08, + "loss": 0.3475, + "step": 3257 + }, + { + "epoch": 0.843740895406429, + "grad_norm": 5.054349794560757, + "learning_rate": 9.064343308785035e-08, + "loss": 0.2561, + "step": 3258 + }, + { + "epoch": 0.843999870512447, + "grad_norm": 5.543823644551007, + "learning_rate": 9.035049700144724e-08, + "loss": 0.3326, + "step": 3259 + }, + { + "epoch": 0.8442588456184649, + "grad_norm": 4.904142901789248, + "learning_rate": 9.005799814434162e-08, + "loss": 0.388, + "step": 3260 + }, + { + "epoch": 0.8442588456184649, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8347302252488213, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.2256801277399063, + "eval_runtime": 14.5786, + "eval_samples_per_second": 3.018, + "eval_steps_per_second": 0.137, + "step": 3260 + }, + { + "epoch": 0.8445178207244829, + "grad_norm": 5.2716926158789335, + "learning_rate": 8.976593675573506e-08, + "loss": 0.256, + "step": 3261 + }, + { + "epoch": 0.8447767958305008, + "grad_norm": 3.899842534053996, + "learning_rate": 8.947431307447157e-08, + "loss": 0.3469, + "step": 3262 + }, + { + "epoch": 0.8450357709365187, + "grad_norm": 4.586413063382779, + "learning_rate": 8.918312733903714e-08, + "loss": 0.2957, + "step": 3263 + }, + { + "epoch": 0.8452947460425366, + "grad_norm": 7.159650236801048, + "learning_rate": 8.88923797875596e-08, + "loss": 0.5405, + "step": 3264 + }, + { + "epoch": 0.8455537211485546, + "grad_norm": 6.628396235476007, + "learning_rate": 8.860207065780841e-08, + "loss": 0.3901, + "step": 3265 + }, + { + "epoch": 0.8455537211485546, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8357778941854375, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22570514678955078, + "eval_runtime": 14.6754, + "eval_samples_per_second": 2.998, + "eval_steps_per_second": 0.136, + "step": 3265 + }, + { + "epoch": 0.8458126962545726, + "grad_norm": 3.354292766403392, + "learning_rate": 8.831220018719465e-08, + "loss": 0.3562, + "step": 3266 + }, + { + "epoch": 0.8460716713605905, + "grad_norm": 3.8395229256770933, + "learning_rate": 8.802276861277049e-08, + "loss": 0.2705, + "step": 3267 + }, + { + "epoch": 0.8463306464666084, + "grad_norm": 3.244089014710345, + "learning_rate": 8.773377617122929e-08, + "loss": 0.2595, + "step": 3268 + }, + { + "epoch": 0.8465896215726263, + "grad_norm": 3.673451843170741, + "learning_rate": 8.744522309890522e-08, + "loss": 0.247, + "step": 3269 + }, + { + "epoch": 0.8468485966786443, + "grad_norm": 3.780857360770634, + "learning_rate": 8.71571096317731e-08, + "loss": 0.3436, + "step": 3270 + }, + { + "epoch": 0.8468485966786443, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8363017286537454, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22453927993774414, + "eval_runtime": 14.7741, + "eval_samples_per_second": 2.978, + "eval_steps_per_second": 0.135, + "step": 3270 + }, + { + "epoch": 0.8471075717846622, + "grad_norm": 3.452826917263798, + "learning_rate": 8.686943600544846e-08, + "loss": 0.3167, + "step": 3271 + }, + { + "epoch": 0.8473665468906801, + "grad_norm": 4.050679787874992, + "learning_rate": 8.658220245518684e-08, + "loss": 0.282, + "step": 3272 + }, + { + "epoch": 0.847625521996698, + "grad_norm": 5.408087536332757, + "learning_rate": 8.629540921588415e-08, + "loss": 0.2994, + "step": 3273 + }, + { + "epoch": 0.847884497102716, + "grad_norm": 6.093492217559335, + "learning_rate": 8.600905652207607e-08, + "loss": 0.2506, + "step": 3274 + }, + { + "epoch": 0.848143472208734, + "grad_norm": 3.7719636046517686, + "learning_rate": 8.572314460793804e-08, + "loss": 0.3027, + "step": 3275 + }, + { + "epoch": 0.848143472208734, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8357778941854375, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.2251819223165512, + "eval_runtime": 14.5014, + "eval_samples_per_second": 3.034, + "eval_steps_per_second": 0.138, + "step": 3275 + }, + { + "epoch": 0.8484024473147519, + "grad_norm": 4.186353286478501, + "learning_rate": 8.543767370728526e-08, + "loss": 0.3064, + "step": 3276 + }, + { + "epoch": 0.8486614224207698, + "grad_norm": 6.478245051239394, + "learning_rate": 8.515264405357146e-08, + "loss": 0.3878, + "step": 3277 + }, + { + "epoch": 0.8489203975267877, + "grad_norm": 3.653980736920043, + "learning_rate": 8.486805587989075e-08, + "loss": 0.2359, + "step": 3278 + }, + { + "epoch": 0.8491793726328056, + "grad_norm": 3.3040037738884087, + "learning_rate": 8.458390941897536e-08, + "loss": 0.2546, + "step": 3279 + }, + { + "epoch": 0.8494383477388237, + "grad_norm": 3.627417903706657, + "learning_rate": 8.430020490319643e-08, + "loss": 0.3104, + "step": 3280 + }, + { + "epoch": 0.8494383477388237, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8349921424829754, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22541767358779907, + "eval_runtime": 14.783, + "eval_samples_per_second": 2.976, + "eval_steps_per_second": 0.135, + "step": 3280 + }, + { + "epoch": 0.8496973228448416, + "grad_norm": 4.7075203293874575, + "learning_rate": 8.401694256456386e-08, + "loss": 0.3264, + "step": 3281 + }, + { + "epoch": 0.8499562979508595, + "grad_norm": 3.7086564679416627, + "learning_rate": 8.373412263472581e-08, + "loss": 0.2543, + "step": 3282 + }, + { + "epoch": 0.8502152730568774, + "grad_norm": 2.53148523480163, + "learning_rate": 8.345174534496875e-08, + "loss": 0.2683, + "step": 3283 + }, + { + "epoch": 0.8504742481628953, + "grad_norm": 3.217557976128564, + "learning_rate": 8.31698109262171e-08, + "loss": 0.3243, + "step": 3284 + }, + { + "epoch": 0.8507332232689133, + "grad_norm": 3.6096389256821144, + "learning_rate": 8.288831960903291e-08, + "loss": 0.3265, + "step": 3285 + }, + { + "epoch": 0.8507332232689133, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8386589837611316, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.2233910709619522, + "eval_runtime": 15.4944, + "eval_samples_per_second": 2.84, + "eval_steps_per_second": 0.129, + "step": 3285 + }, + { + "epoch": 0.8509921983749312, + "grad_norm": 3.051825436465324, + "learning_rate": 8.26072716236162e-08, + "loss": 0.3285, + "step": 3286 + }, + { + "epoch": 0.8512511734809491, + "grad_norm": 3.4332716896898283, + "learning_rate": 8.232666719980416e-08, + "loss": 0.3079, + "step": 3287 + }, + { + "epoch": 0.851510148586967, + "grad_norm": 4.821025330439831, + "learning_rate": 8.204650656707162e-08, + "loss": 0.2808, + "step": 3288 + }, + { + "epoch": 0.851769123692985, + "grad_norm": 8.008768251299683, + "learning_rate": 8.176678995453012e-08, + "loss": 0.3206, + "step": 3289 + }, + { + "epoch": 0.852028098799003, + "grad_norm": 5.142101815042363, + "learning_rate": 8.148751759092826e-08, + "loss": 0.2989, + "step": 3290 + }, + { + "epoch": 0.852028098799003, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8370874803562074, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22420667111873627, + "eval_runtime": 14.6057, + "eval_samples_per_second": 3.013, + "eval_steps_per_second": 0.137, + "step": 3290 + }, + { + "epoch": 0.8522870739050209, + "grad_norm": 3.257092546280958, + "learning_rate": 8.120868970465115e-08, + "loss": 0.306, + "step": 3291 + }, + { + "epoch": 0.8525460490110388, + "grad_norm": 3.8555536817938774, + "learning_rate": 8.093030652372089e-08, + "loss": 0.2362, + "step": 3292 + }, + { + "epoch": 0.8528050241170567, + "grad_norm": 4.228761956351373, + "learning_rate": 8.065236827579509e-08, + "loss": 0.3477, + "step": 3293 + }, + { + "epoch": 0.8530639992230746, + "grad_norm": 3.3416518491070057, + "learning_rate": 8.037487518816826e-08, + "loss": 0.2871, + "step": 3294 + }, + { + "epoch": 0.8533229743290927, + "grad_norm": 4.158923017320803, + "learning_rate": 8.009782748777048e-08, + "loss": 0.3417, + "step": 3295 + }, + { + "epoch": 0.8533229743290927, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8352540597171294, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22363168001174927, + "eval_runtime": 14.7024, + "eval_samples_per_second": 2.993, + "eval_steps_per_second": 0.136, + "step": 3295 + }, + { + "epoch": 0.8535819494351106, + "grad_norm": 3.7160442173803294, + "learning_rate": 7.982122540116779e-08, + "loss": 0.3432, + "step": 3296 + }, + { + "epoch": 0.8538409245411285, + "grad_norm": 4.565847202722701, + "learning_rate": 7.954506915456164e-08, + "loss": 0.3948, + "step": 3297 + }, + { + "epoch": 0.8540998996471464, + "grad_norm": 4.488042614970003, + "learning_rate": 7.926935897378883e-08, + "loss": 0.2622, + "step": 3298 + }, + { + "epoch": 0.8543588747531643, + "grad_norm": 3.8952046023985054, + "learning_rate": 7.899409508432183e-08, + "loss": 0.4124, + "step": 3299 + }, + { + "epoch": 0.8546178498591823, + "grad_norm": 3.183074779592404, + "learning_rate": 7.871927771126768e-08, + "loss": 0.3026, + "step": 3300 + }, + { + "epoch": 0.8546178498591823, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8328968046097434, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.2241465151309967, + "eval_runtime": 14.6868, + "eval_samples_per_second": 2.996, + "eval_steps_per_second": 0.136, + "step": 3300 + }, + { + "epoch": 0.8548768249652002, + "grad_norm": 4.225952332017539, + "learning_rate": 7.844490707936845e-08, + "loss": 0.2639, + "step": 3301 + }, + { + "epoch": 0.8551358000712181, + "grad_norm": 3.473049789305803, + "learning_rate": 7.81709834130006e-08, + "loss": 0.3108, + "step": 3302 + }, + { + "epoch": 0.855394775177236, + "grad_norm": 7.487597901490835, + "learning_rate": 7.789750693617536e-08, + "loss": 0.2771, + "step": 3303 + }, + { + "epoch": 0.8556537502832541, + "grad_norm": 3.428125472643825, + "learning_rate": 7.76244778725383e-08, + "loss": 0.2967, + "step": 3304 + }, + { + "epoch": 0.855912725389272, + "grad_norm": 2.787400183395411, + "learning_rate": 7.735189644536893e-08, + "loss": 0.2856, + "step": 3305 + }, + { + "epoch": 0.855912725389272, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8365636458878996, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22391477227210999, + "eval_runtime": 14.6352, + "eval_samples_per_second": 3.006, + "eval_steps_per_second": 0.137, + "step": 3305 + }, + { + "epoch": 0.8561717004952899, + "grad_norm": 2.867722466294111, + "learning_rate": 7.707976287758066e-08, + "loss": 0.3069, + "step": 3306 + }, + { + "epoch": 0.8564306756013078, + "grad_norm": 5.354932393127859, + "learning_rate": 7.680807739172076e-08, + "loss": 0.3163, + "step": 3307 + }, + { + "epoch": 0.8566896507073257, + "grad_norm": 4.128666762052998, + "learning_rate": 7.653684020996997e-08, + "loss": 0.2915, + "step": 3308 + }, + { + "epoch": 0.8569486258133437, + "grad_norm": 3.269925447609431, + "learning_rate": 7.626605155414281e-08, + "loss": 0.2967, + "step": 3309 + }, + { + "epoch": 0.8572076009193617, + "grad_norm": 3.5562709429176462, + "learning_rate": 7.599571164568629e-08, + "loss": 0.3083, + "step": 3310 + }, + { + "epoch": 0.8572076009193617, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8336825563122053, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22412022948265076, + "eval_runtime": 14.8512, + "eval_samples_per_second": 2.963, + "eval_steps_per_second": 0.135, + "step": 3310 + }, + { + "epoch": 0.8574665760253796, + "grad_norm": 6.694544573692518, + "learning_rate": 7.572582070568088e-08, + "loss": 0.3389, + "step": 3311 + }, + { + "epoch": 0.8577255511313975, + "grad_norm": 6.715718098230577, + "learning_rate": 7.545637895483994e-08, + "loss": 0.3437, + "step": 3312 + }, + { + "epoch": 0.8579845262374154, + "grad_norm": 5.271828595175152, + "learning_rate": 7.518738661350923e-08, + "loss": 0.2522, + "step": 3313 + }, + { + "epoch": 0.8582435013434334, + "grad_norm": 3.7476291757437035, + "learning_rate": 7.49188439016673e-08, + "loss": 0.333, + "step": 3314 + }, + { + "epoch": 0.8585024764494513, + "grad_norm": 3.683511138580593, + "learning_rate": 7.465075103892467e-08, + "loss": 0.3505, + "step": 3315 + }, + { + "epoch": 0.8585024764494513, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8342063907805135, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22429195046424866, + "eval_runtime": 14.8516, + "eval_samples_per_second": 2.963, + "eval_steps_per_second": 0.135, + "step": 3315 + }, + { + "epoch": 0.8587614515554692, + "grad_norm": 7.429214851373768, + "learning_rate": 7.438310824452427e-08, + "loss": 0.3864, + "step": 3316 + }, + { + "epoch": 0.8590204266614871, + "grad_norm": 3.0823477320251667, + "learning_rate": 7.41159157373407e-08, + "loss": 0.3576, + "step": 3317 + }, + { + "epoch": 0.8592794017675051, + "grad_norm": 4.4576618569663555, + "learning_rate": 7.384917373588062e-08, + "loss": 0.366, + "step": 3318 + }, + { + "epoch": 0.8595383768735231, + "grad_norm": 6.240735229303388, + "learning_rate": 7.358288245828196e-08, + "loss": 0.2449, + "step": 3319 + }, + { + "epoch": 0.859797351979541, + "grad_norm": 4.982536212034621, + "learning_rate": 7.331704212231436e-08, + "loss": 0.3324, + "step": 3320 + }, + { + "epoch": 0.859797351979541, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8376113148245155, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.2243414968252182, + "eval_runtime": 14.4372, + "eval_samples_per_second": 3.048, + "eval_steps_per_second": 0.139, + "step": 3320 + }, + { + "epoch": 0.8600563270855589, + "grad_norm": 3.253542636579658, + "learning_rate": 7.305165294537842e-08, + "loss": 0.3469, + "step": 3321 + }, + { + "epoch": 0.8603153021915768, + "grad_norm": 8.362355644370453, + "learning_rate": 7.278671514450594e-08, + "loss": 0.3842, + "step": 3322 + }, + { + "epoch": 0.8605742772975947, + "grad_norm": 4.227237158393191, + "learning_rate": 7.252222893635953e-08, + "loss": 0.3956, + "step": 3323 + }, + { + "epoch": 0.8608332524036127, + "grad_norm": 5.714150241299133, + "learning_rate": 7.225819453723255e-08, + "loss": 0.385, + "step": 3324 + }, + { + "epoch": 0.8610922275096307, + "grad_norm": 5.807975343114923, + "learning_rate": 7.199461216304896e-08, + "loss": 0.3153, + "step": 3325 + }, + { + "epoch": 0.8610922275096307, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8336825563122053, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22550290822982788, + "eval_runtime": 14.799, + "eval_samples_per_second": 2.973, + "eval_steps_per_second": 0.135, + "step": 3325 + }, + { + "epoch": 0.8613512026156486, + "grad_norm": 4.324532820502202, + "learning_rate": 7.173148202936255e-08, + "loss": 0.3622, + "step": 3326 + }, + { + "epoch": 0.8616101777216665, + "grad_norm": 7.32256322027147, + "learning_rate": 7.146880435135811e-08, + "loss": 0.4103, + "step": 3327 + }, + { + "epoch": 0.8618691528276844, + "grad_norm": 4.5125459703920265, + "learning_rate": 7.120657934384968e-08, + "loss": 0.4207, + "step": 3328 + }, + { + "epoch": 0.8621281279337024, + "grad_norm": 5.363054276145537, + "learning_rate": 7.094480722128157e-08, + "loss": 0.3731, + "step": 3329 + }, + { + "epoch": 0.8623871030397203, + "grad_norm": 3.1035007838566515, + "learning_rate": 7.068348819772753e-08, + "loss": 0.322, + "step": 3330 + }, + { + "epoch": 0.8623871030397203, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8315872184389732, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22568827867507935, + "eval_runtime": 14.7495, + "eval_samples_per_second": 2.983, + "eval_steps_per_second": 0.136, + "step": 3330 + }, + { + "epoch": 0.8626460781457382, + "grad_norm": 5.941251952695048, + "learning_rate": 7.042262248689078e-08, + "loss": 0.3062, + "step": 3331 + }, + { + "epoch": 0.8629050532517561, + "grad_norm": 2.770471874542337, + "learning_rate": 7.01622103021038e-08, + "loss": 0.2546, + "step": 3332 + }, + { + "epoch": 0.8631640283577741, + "grad_norm": 6.359835838869824, + "learning_rate": 6.990225185632832e-08, + "loss": 0.3288, + "step": 3333 + }, + { + "epoch": 0.8634230034637921, + "grad_norm": 3.8125968650243456, + "learning_rate": 6.964274736215498e-08, + "loss": 0.3223, + "step": 3334 + }, + { + "epoch": 0.86368197856981, + "grad_norm": 5.184330171275464, + "learning_rate": 6.938369703180292e-08, + "loss": 0.3991, + "step": 3335 + }, + { + "epoch": 0.86368197856981, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8347302252488213, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22495955228805542, + "eval_runtime": 14.676, + "eval_samples_per_second": 2.998, + "eval_steps_per_second": 0.136, + "step": 3335 + }, + { + "epoch": 0.8639409536758279, + "grad_norm": 4.089056715794528, + "learning_rate": 6.912510107712003e-08, + "loss": 0.3621, + "step": 3336 + }, + { + "epoch": 0.8641999287818458, + "grad_norm": 5.841564235946712, + "learning_rate": 6.886695970958299e-08, + "loss": 0.3946, + "step": 3337 + }, + { + "epoch": 0.8644589038878637, + "grad_norm": 3.7218538765850355, + "learning_rate": 6.860927314029618e-08, + "loss": 0.3914, + "step": 3338 + }, + { + "epoch": 0.8647178789938818, + "grad_norm": 4.844258583352906, + "learning_rate": 6.835204157999237e-08, + "loss": 0.3019, + "step": 3339 + }, + { + "epoch": 0.8649768540998997, + "grad_norm": 4.13387372212498, + "learning_rate": 6.80952652390321e-08, + "loss": 0.4041, + "step": 3340 + }, + { + "epoch": 0.8649768540998997, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8339444735463594, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22623926401138306, + "eval_runtime": 14.7654, + "eval_samples_per_second": 2.98, + "eval_steps_per_second": 0.135, + "step": 3340 + }, + { + "epoch": 0.8652358292059176, + "grad_norm": 5.594786617302885, + "learning_rate": 6.783894432740356e-08, + "loss": 0.3738, + "step": 3341 + }, + { + "epoch": 0.8654948043119355, + "grad_norm": 4.32116871414182, + "learning_rate": 6.758307905472293e-08, + "loss": 0.3241, + "step": 3342 + }, + { + "epoch": 0.8657537794179534, + "grad_norm": 5.341432262539577, + "learning_rate": 6.732766963023302e-08, + "loss": 0.2767, + "step": 3343 + }, + { + "epoch": 0.8660127545239714, + "grad_norm": 3.6160337693022715, + "learning_rate": 6.707271626280445e-08, + "loss": 0.3644, + "step": 3344 + }, + { + "epoch": 0.8662717296299893, + "grad_norm": 4.813248046746639, + "learning_rate": 6.681821916093477e-08, + "loss": 0.2992, + "step": 3345 + }, + { + "epoch": 0.8662717296299893, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8313253012048193, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22699524462223053, + "eval_runtime": 15.1737, + "eval_samples_per_second": 2.9, + "eval_steps_per_second": 0.132, + "step": 3345 + }, + { + "epoch": 0.8665307047360072, + "grad_norm": 5.117434892694729, + "learning_rate": 6.656417853274817e-08, + "loss": 0.28, + "step": 3346 + }, + { + "epoch": 0.8667896798420252, + "grad_norm": 4.0085445833668905, + "learning_rate": 6.631059458599597e-08, + "loss": 0.3508, + "step": 3347 + }, + { + "epoch": 0.8670486549480432, + "grad_norm": 3.4540669630499785, + "learning_rate": 6.605746752805571e-08, + "loss": 0.2839, + "step": 3348 + }, + { + "epoch": 0.8673076300540611, + "grad_norm": 4.905717292554045, + "learning_rate": 6.580479756593129e-08, + "loss": 0.3134, + "step": 3349 + }, + { + "epoch": 0.867566605160079, + "grad_norm": 5.996014991177582, + "learning_rate": 6.5552584906253e-08, + "loss": 0.3549, + "step": 3350 + }, + { + "epoch": 0.867566605160079, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8331587218438974, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22673730552196503, + "eval_runtime": 14.5787, + "eval_samples_per_second": 3.018, + "eval_steps_per_second": 0.137, + "step": 3350 + }, + { + "epoch": 0.8678255802660969, + "grad_norm": 4.536006949145603, + "learning_rate": 6.530082975527679e-08, + "loss": 0.4025, + "step": 3351 + }, + { + "epoch": 0.8680845553721148, + "grad_norm": 3.33049937934309, + "learning_rate": 6.504953231888476e-08, + "loss": 0.2726, + "step": 3352 + }, + { + "epoch": 0.8683435304781328, + "grad_norm": 5.38969880097761, + "learning_rate": 6.479869280258469e-08, + "loss": 0.2979, + "step": 3353 + }, + { + "epoch": 0.8686025055841508, + "grad_norm": 3.1208153992743006, + "learning_rate": 6.454831141150981e-08, + "loss": 0.2804, + "step": 3354 + }, + { + "epoch": 0.8688614806901687, + "grad_norm": 3.6040786356359633, + "learning_rate": 6.429838835041876e-08, + "loss": 0.2997, + "step": 3355 + }, + { + "epoch": 0.8688614806901687, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8349921424829754, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22681547701358795, + "eval_runtime": 14.7668, + "eval_samples_per_second": 2.98, + "eval_steps_per_second": 0.135, + "step": 3355 + }, + { + "epoch": 0.8691204557961866, + "grad_norm": 4.222064756454635, + "learning_rate": 6.404892382369521e-08, + "loss": 0.4086, + "step": 3356 + }, + { + "epoch": 0.8693794309022045, + "grad_norm": 5.012940298680437, + "learning_rate": 6.37999180353479e-08, + "loss": 0.2993, + "step": 3357 + }, + { + "epoch": 0.8696384060082225, + "grad_norm": 3.617921078905211, + "learning_rate": 6.355137118901074e-08, + "loss": 0.3455, + "step": 3358 + }, + { + "epoch": 0.8698973811142404, + "grad_norm": 2.5154193302417167, + "learning_rate": 6.330328348794199e-08, + "loss": 0.3233, + "step": 3359 + }, + { + "epoch": 0.8701563562202583, + "grad_norm": 3.2287220417255065, + "learning_rate": 6.305565513502428e-08, + "loss": 0.2971, + "step": 3360 + }, + { + "epoch": 0.8701563562202583, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8326348873755893, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22723431885242462, + "eval_runtime": 14.6225, + "eval_samples_per_second": 3.009, + "eval_steps_per_second": 0.137, + "step": 3360 + }, + { + "epoch": 0.8704153313262762, + "grad_norm": 4.278927301754888, + "learning_rate": 6.280848633276493e-08, + "loss": 0.2659, + "step": 3361 + }, + { + "epoch": 0.8706743064322942, + "grad_norm": 4.0710330143602995, + "learning_rate": 6.25617772832953e-08, + "loss": 0.3072, + "step": 3362 + }, + { + "epoch": 0.8709332815383122, + "grad_norm": 4.030706558418879, + "learning_rate": 6.231552818837077e-08, + "loss": 0.3186, + "step": 3363 + }, + { + "epoch": 0.8711922566443301, + "grad_norm": 4.399554568646487, + "learning_rate": 6.20697392493707e-08, + "loss": 0.3252, + "step": 3364 + }, + { + "epoch": 0.871451231750348, + "grad_norm": 4.576281890881114, + "learning_rate": 6.182441066729793e-08, + "loss": 0.3836, + "step": 3365 + }, + { + "epoch": 0.871451231750348, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8323729701414353, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22709430754184723, + "eval_runtime": 15.1839, + "eval_samples_per_second": 2.898, + "eval_steps_per_second": 0.132, + "step": 3365 + }, + { + "epoch": 0.8717102068563659, + "grad_norm": 7.341056088310733, + "learning_rate": 6.157954264277899e-08, + "loss": 0.3748, + "step": 3366 + }, + { + "epoch": 0.8719691819623838, + "grad_norm": 2.7762923056497044, + "learning_rate": 6.13351353760637e-08, + "loss": 0.2659, + "step": 3367 + }, + { + "epoch": 0.8722281570684018, + "grad_norm": 3.6798707831776203, + "learning_rate": 6.109118906702509e-08, + "loss": 0.3041, + "step": 3368 + }, + { + "epoch": 0.8724871321744198, + "grad_norm": 8.680586706457692, + "learning_rate": 6.084770391515914e-08, + "loss": 0.3065, + "step": 3369 + }, + { + "epoch": 0.8727461072804377, + "grad_norm": 2.8650899547675097, + "learning_rate": 6.060468011958497e-08, + "loss": 0.2309, + "step": 3370 + }, + { + "epoch": 0.8727461072804377, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8321110529072813, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.2274998128414154, + "eval_runtime": 14.4087, + "eval_samples_per_second": 3.054, + "eval_steps_per_second": 0.139, + "step": 3370 + }, + { + "epoch": 0.8730050823864556, + "grad_norm": 3.656661473351032, + "learning_rate": 6.036211787904409e-08, + "loss": 0.3015, + "step": 3371 + }, + { + "epoch": 0.8732640574924735, + "grad_norm": 5.230711194190608, + "learning_rate": 6.012001739190074e-08, + "loss": 0.3454, + "step": 3372 + }, + { + "epoch": 0.8735230325984915, + "grad_norm": 3.5615766809099454, + "learning_rate": 5.987837885614147e-08, + "loss": 0.3401, + "step": 3373 + }, + { + "epoch": 0.8737820077045094, + "grad_norm": 4.93953490721229, + "learning_rate": 5.963720246937511e-08, + "loss": 0.2681, + "step": 3374 + }, + { + "epoch": 0.8740409828105273, + "grad_norm": 4.185810396110995, + "learning_rate": 5.939648842883255e-08, + "loss": 0.3642, + "step": 3375 + }, + { + "epoch": 0.8740409828105273, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8339444735463594, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22736778855323792, + "eval_runtime": 14.4582, + "eval_samples_per_second": 3.043, + "eval_steps_per_second": 0.138, + "step": 3375 + }, + { + "epoch": 0.8742999579165452, + "grad_norm": 3.0339429895613805, + "learning_rate": 5.9156236931366545e-08, + "loss": 0.2356, + "step": 3376 + }, + { + "epoch": 0.8745589330225632, + "grad_norm": 3.5292656486556147, + "learning_rate": 5.8916448173451516e-08, + "loss": 0.3466, + "step": 3377 + }, + { + "epoch": 0.8748179081285812, + "grad_norm": 3.564397437297009, + "learning_rate": 5.86771223511836e-08, + "loss": 0.329, + "step": 3378 + }, + { + "epoch": 0.8750768832345991, + "grad_norm": 7.11095796760187, + "learning_rate": 5.843825966028026e-08, + "loss": 0.295, + "step": 3379 + }, + { + "epoch": 0.875335858340617, + "grad_norm": 3.2971345530493807, + "learning_rate": 5.819986029608031e-08, + "loss": 0.3275, + "step": 3380 + }, + { + "epoch": 0.875335858340617, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8355159769512834, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22721867263317108, + "eval_runtime": 14.3296, + "eval_samples_per_second": 3.071, + "eval_steps_per_second": 0.14, + "step": 3380 + }, + { + "epoch": 0.8755948334466349, + "grad_norm": 4.196557695056934, + "learning_rate": 5.7961924453543496e-08, + "loss": 0.317, + "step": 3381 + }, + { + "epoch": 0.8758538085526528, + "grad_norm": 2.818303138886244, + "learning_rate": 5.7724452327250696e-08, + "loss": 0.3206, + "step": 3382 + }, + { + "epoch": 0.8761127836586708, + "grad_norm": 3.9527281981536717, + "learning_rate": 5.7487444111403513e-08, + "loss": 0.3054, + "step": 3383 + }, + { + "epoch": 0.8763717587646888, + "grad_norm": 5.037496985577489, + "learning_rate": 5.7250899999824124e-08, + "loss": 0.2493, + "step": 3384 + }, + { + "epoch": 0.8766307338707067, + "grad_norm": 3.609678460688916, + "learning_rate": 5.7014820185954874e-08, + "loss": 0.3223, + "step": 3385 + }, + { + "epoch": 0.8766307338707067, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8339444735463595, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22724615037441254, + "eval_runtime": 14.484, + "eval_samples_per_second": 3.038, + "eval_steps_per_second": 0.138, + "step": 3385 + }, + { + "epoch": 0.8768897089767246, + "grad_norm": 3.52457786776594, + "learning_rate": 5.677920486285911e-08, + "loss": 0.2523, + "step": 3386 + }, + { + "epoch": 0.8771486840827425, + "grad_norm": 3.968655078464756, + "learning_rate": 5.6544054223219774e-08, + "loss": 0.3736, + "step": 3387 + }, + { + "epoch": 0.8774076591887605, + "grad_norm": 5.3450593888411575, + "learning_rate": 5.630936845934e-08, + "loss": 0.3464, + "step": 3388 + }, + { + "epoch": 0.8776666342947784, + "grad_norm": 4.1652413407589615, + "learning_rate": 5.6075147763142574e-08, + "loss": 0.3736, + "step": 3389 + }, + { + "epoch": 0.8779256094007963, + "grad_norm": 4.493051733585838, + "learning_rate": 5.584139232617025e-08, + "loss": 0.2606, + "step": 3390 + }, + { + "epoch": 0.8779256094007963, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8347302252488213, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22693084180355072, + "eval_runtime": 14.3553, + "eval_samples_per_second": 3.065, + "eval_steps_per_second": 0.139, + "step": 3390 + }, + { + "epoch": 0.8781845845068142, + "grad_norm": 5.31219463940011, + "learning_rate": 5.5608102339585054e-08, + "loss": 0.3644, + "step": 3391 + }, + { + "epoch": 0.8784435596128323, + "grad_norm": 3.838056818768345, + "learning_rate": 5.537527799416853e-08, + "loss": 0.4078, + "step": 3392 + }, + { + "epoch": 0.8787025347188502, + "grad_norm": 4.937281878345705, + "learning_rate": 5.514291948032123e-08, + "loss": 0.3676, + "step": 3393 + }, + { + "epoch": 0.8789615098248681, + "grad_norm": 5.067278140721961, + "learning_rate": 5.491102698806289e-08, + "loss": 0.2706, + "step": 3394 + }, + { + "epoch": 0.879220484930886, + "grad_norm": 4.59441785781205, + "learning_rate": 5.4679600707032015e-08, + "loss": 0.3536, + "step": 3395 + }, + { + "epoch": 0.879220484930886, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8339444735463594, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22761179506778717, + "eval_runtime": 14.6544, + "eval_samples_per_second": 3.003, + "eval_steps_per_second": 0.136, + "step": 3395 + }, + { + "epoch": 0.8794794600369039, + "grad_norm": 4.855603734246533, + "learning_rate": 5.444864082648625e-08, + "loss": 0.3736, + "step": 3396 + }, + { + "epoch": 0.8797384351429219, + "grad_norm": 4.320560782081386, + "learning_rate": 5.4218147535301384e-08, + "loss": 0.347, + "step": 3397 + }, + { + "epoch": 0.8799974102489398, + "grad_norm": 3.144235850260847, + "learning_rate": 5.3988121021971845e-08, + "loss": 0.2526, + "step": 3398 + }, + { + "epoch": 0.8802563853549578, + "grad_norm": 3.289834725293091, + "learning_rate": 5.3758561474610144e-08, + "loss": 0.3292, + "step": 3399 + }, + { + "epoch": 0.8805153604609757, + "grad_norm": 5.060999084961638, + "learning_rate": 5.352946908094729e-08, + "loss": 0.332, + "step": 3400 + }, + { + "epoch": 0.8805153604609757, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8331587218438974, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22727392613887787, + "eval_runtime": 15.0536, + "eval_samples_per_second": 2.923, + "eval_steps_per_second": 0.133, + "step": 3400 + }, + { + "epoch": 0.8807743355669936, + "grad_norm": 3.173642297373319, + "learning_rate": 5.330084402833169e-08, + "loss": 0.3306, + "step": 3401 + }, + { + "epoch": 0.8810333106730116, + "grad_norm": 3.621113206934202, + "learning_rate": 5.307268650373003e-08, + "loss": 0.3703, + "step": 3402 + }, + { + "epoch": 0.8812922857790295, + "grad_norm": 3.3814304736338108, + "learning_rate": 5.28449966937266e-08, + "loss": 0.3323, + "step": 3403 + }, + { + "epoch": 0.8815512608850474, + "grad_norm": 8.984830054134703, + "learning_rate": 5.261777478452301e-08, + "loss": 0.3615, + "step": 3404 + }, + { + "epoch": 0.8818102359910653, + "grad_norm": 3.177749015856064, + "learning_rate": 5.239102096193826e-08, + "loss": 0.2549, + "step": 3405 + }, + { + "epoch": 0.8818102359910653, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8347302252488215, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22614401578903198, + "eval_runtime": 14.7691, + "eval_samples_per_second": 2.979, + "eval_steps_per_second": 0.135, + "step": 3405 + }, + { + "epoch": 0.8820692110970833, + "grad_norm": 3.628281027044527, + "learning_rate": 5.2164735411408815e-08, + "loss": 0.3048, + "step": 3406 + }, + { + "epoch": 0.8823281862031013, + "grad_norm": 4.869520640152494, + "learning_rate": 5.1938918317988027e-08, + "loss": 0.3578, + "step": 3407 + }, + { + "epoch": 0.8825871613091192, + "grad_norm": 8.255791477329788, + "learning_rate": 5.171356986634596e-08, + "loss": 0.3894, + "step": 3408 + }, + { + "epoch": 0.8828461364151371, + "grad_norm": 3.0369310042358544, + "learning_rate": 5.148869024076984e-08, + "loss": 0.2446, + "step": 3409 + }, + { + "epoch": 0.883105111521155, + "grad_norm": 5.9814321229101175, + "learning_rate": 5.126427962516299e-08, + "loss": 0.3613, + "step": 3410 + }, + { + "epoch": 0.883105111521155, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8323729701414353, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22659160196781158, + "eval_runtime": 14.5983, + "eval_samples_per_second": 3.014, + "eval_steps_per_second": 0.137, + "step": 3410 + }, + { + "epoch": 0.8833640866271729, + "grad_norm": 5.170425251991757, + "learning_rate": 5.1040338203045544e-08, + "loss": 0.356, + "step": 3411 + }, + { + "epoch": 0.8836230617331909, + "grad_norm": 4.004557535039488, + "learning_rate": 5.0816866157553794e-08, + "loss": 0.3213, + "step": 3412 + }, + { + "epoch": 0.8838820368392089, + "grad_norm": 3.648178448765578, + "learning_rate": 5.05938636714403e-08, + "loss": 0.2247, + "step": 3413 + }, + { + "epoch": 0.8841410119452268, + "grad_norm": 3.900791476499685, + "learning_rate": 5.037133092707355e-08, + "loss": 0.3163, + "step": 3414 + }, + { + "epoch": 0.8843999870512447, + "grad_norm": 4.463380369033736, + "learning_rate": 5.014926810643784e-08, + "loss": 0.2942, + "step": 3415 + }, + { + "epoch": 0.8843999870512447, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8344683080146673, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.2269064337015152, + "eval_runtime": 15.0743, + "eval_samples_per_second": 2.919, + "eval_steps_per_second": 0.133, + "step": 3415 + }, + { + "epoch": 0.8846589621572626, + "grad_norm": 3.566993510010346, + "learning_rate": 4.992767539113305e-08, + "loss": 0.3414, + "step": 3416 + }, + { + "epoch": 0.8849179372632806, + "grad_norm": 7.086130145565575, + "learning_rate": 4.9706552962375256e-08, + "loss": 0.3562, + "step": 3417 + }, + { + "epoch": 0.8851769123692985, + "grad_norm": 4.997709973952491, + "learning_rate": 4.9485901000995014e-08, + "loss": 0.281, + "step": 3418 + }, + { + "epoch": 0.8854358874753164, + "grad_norm": 4.716666385412374, + "learning_rate": 4.926571968743868e-08, + "loss": 0.3773, + "step": 3419 + }, + { + "epoch": 0.8856948625813343, + "grad_norm": 5.4235924492331975, + "learning_rate": 4.9046009201767636e-08, + "loss": 0.363, + "step": 3420 + }, + { + "epoch": 0.8856948625813343, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8328968046097434, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22756090760231018, + "eval_runtime": 14.9078, + "eval_samples_per_second": 2.951, + "eval_steps_per_second": 0.134, + "step": 3420 + }, + { + "epoch": 0.8859538376873523, + "grad_norm": 7.4861517838113025, + "learning_rate": 4.88267697236583e-08, + "loss": 0.3254, + "step": 3421 + }, + { + "epoch": 0.8862128127933703, + "grad_norm": 3.3594508054174614, + "learning_rate": 4.8608001432401754e-08, + "loss": 0.3264, + "step": 3422 + }, + { + "epoch": 0.8864717878993882, + "grad_norm": 4.992402815633038, + "learning_rate": 4.8389704506903794e-08, + "loss": 0.3498, + "step": 3423 + }, + { + "epoch": 0.8867307630054061, + "grad_norm": 4.133523238532369, + "learning_rate": 4.817187912568473e-08, + "loss": 0.3602, + "step": 3424 + }, + { + "epoch": 0.886989738111424, + "grad_norm": 2.8699009921735033, + "learning_rate": 4.795452546687944e-08, + "loss": 0.2947, + "step": 3425 + }, + { + "epoch": 0.886989738111424, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8310633839706653, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22745627164840698, + "eval_runtime": 15.0718, + "eval_samples_per_second": 2.919, + "eval_steps_per_second": 0.133, + "step": 3425 + }, + { + "epoch": 0.8872487132174419, + "grad_norm": 3.670728102317825, + "learning_rate": 4.773764370823671e-08, + "loss": 0.3584, + "step": 3426 + }, + { + "epoch": 0.8875076883234599, + "grad_norm": 5.3463056251530805, + "learning_rate": 4.752123402711958e-08, + "loss": 0.3161, + "step": 3427 + }, + { + "epoch": 0.8877666634294779, + "grad_norm": 5.2357584441861444, + "learning_rate": 4.730529660050512e-08, + "loss": 0.3047, + "step": 3428 + }, + { + "epoch": 0.8880256385354958, + "grad_norm": 5.7567613526474375, + "learning_rate": 4.708983160498407e-08, + "loss": 0.3689, + "step": 3429 + }, + { + "epoch": 0.8882846136415137, + "grad_norm": 4.83561211798566, + "learning_rate": 4.687483921676089e-08, + "loss": 0.3674, + "step": 3430 + }, + { + "epoch": 0.8882846136415137, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8336825563122054, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.2279638797044754, + "eval_runtime": 15.0433, + "eval_samples_per_second": 2.925, + "eval_steps_per_second": 0.133, + "step": 3430 + }, + { + "epoch": 0.8885435887475317, + "grad_norm": 4.088741014514308, + "learning_rate": 4.666031961165343e-08, + "loss": 0.3217, + "step": 3431 + }, + { + "epoch": 0.8888025638535496, + "grad_norm": 3.700642326532076, + "learning_rate": 4.644627296509302e-08, + "loss": 0.3809, + "step": 3432 + }, + { + "epoch": 0.8890615389595675, + "grad_norm": 5.2266800549061525, + "learning_rate": 4.623269945212429e-08, + "loss": 0.2997, + "step": 3433 + }, + { + "epoch": 0.8893205140655854, + "grad_norm": 2.8361009784760416, + "learning_rate": 4.601959924740454e-08, + "loss": 0.3532, + "step": 3434 + }, + { + "epoch": 0.8895794891716033, + "grad_norm": 3.8258325381749656, + "learning_rate": 4.580697252520458e-08, + "loss": 0.3856, + "step": 3435 + }, + { + "epoch": 0.8895794891716033, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8315872184389733, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.2282646745443344, + "eval_runtime": 14.4923, + "eval_samples_per_second": 3.036, + "eval_steps_per_second": 0.138, + "step": 3435 + }, + { + "epoch": 0.8898384642776214, + "grad_norm": 3.5564436102710517, + "learning_rate": 4.559481945940768e-08, + "loss": 0.2962, + "step": 3436 + }, + { + "epoch": 0.8900974393836393, + "grad_norm": 2.5948956134920005, + "learning_rate": 4.5383140223509775e-08, + "loss": 0.258, + "step": 3437 + }, + { + "epoch": 0.8903564144896572, + "grad_norm": 5.118865342111697, + "learning_rate": 4.517193499061934e-08, + "loss": 0.3133, + "step": 3438 + }, + { + "epoch": 0.8906153895956751, + "grad_norm": 6.319989727863078, + "learning_rate": 4.496120393345724e-08, + "loss": 0.2501, + "step": 3439 + }, + { + "epoch": 0.890874364701693, + "grad_norm": 5.955218210989458, + "learning_rate": 4.475094722435659e-08, + "loss": 0.4424, + "step": 3440 + }, + { + "epoch": 0.890874364701693, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8305395495023573, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22824673354625702, + "eval_runtime": 14.646, + "eval_samples_per_second": 3.004, + "eval_steps_per_second": 0.137, + "step": 3440 + }, + { + "epoch": 0.891133339807711, + "grad_norm": 2.458689667002345, + "learning_rate": 4.454116503526243e-08, + "loss": 0.2353, + "step": 3441 + }, + { + "epoch": 0.891392314913729, + "grad_norm": 3.8724486709317905, + "learning_rate": 4.4331857537732104e-08, + "loss": 0.3459, + "step": 3442 + }, + { + "epoch": 0.8916512900197469, + "grad_norm": 2.650881392304277, + "learning_rate": 4.4123024902934175e-08, + "loss": 0.281, + "step": 3443 + }, + { + "epoch": 0.8919102651257648, + "grad_norm": 4.97374723325083, + "learning_rate": 4.3914667301649327e-08, + "loss": 0.3278, + "step": 3444 + }, + { + "epoch": 0.8921692402317827, + "grad_norm": 5.792223921301298, + "learning_rate": 4.37067849042698e-08, + "loss": 0.3285, + "step": 3445 + }, + { + "epoch": 0.8921692402317827, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8302776322682033, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22819185256958008, + "eval_runtime": 14.7893, + "eval_samples_per_second": 2.975, + "eval_steps_per_second": 0.135, + "step": 3445 + }, + { + "epoch": 0.8924282153378007, + "grad_norm": 5.004376975408014, + "learning_rate": 4.3499377880798985e-08, + "loss": 0.2243, + "step": 3446 + }, + { + "epoch": 0.8926871904438186, + "grad_norm": 5.214918211559507, + "learning_rate": 4.329244640085162e-08, + "loss": 0.3548, + "step": 3447 + }, + { + "epoch": 0.8929461655498365, + "grad_norm": 4.209616318596235, + "learning_rate": 4.3085990633653446e-08, + "loss": 0.2827, + "step": 3448 + }, + { + "epoch": 0.8932051406558544, + "grad_norm": 3.403275534408304, + "learning_rate": 4.288001074804142e-08, + "loss": 0.3404, + "step": 3449 + }, + { + "epoch": 0.8934641157618723, + "grad_norm": 3.4398753627779137, + "learning_rate": 4.26745069124631e-08, + "loss": 0.2185, + "step": 3450 + }, + { + "epoch": 0.8934641157618723, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8331587218438974, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22873058915138245, + "eval_runtime": 15.0449, + "eval_samples_per_second": 2.925, + "eval_steps_per_second": 0.133, + "step": 3450 + }, + { + "epoch": 0.8937230908678904, + "grad_norm": 5.582793498352874, + "learning_rate": 4.246947929497675e-08, + "loss": 0.2985, + "step": 3451 + }, + { + "epoch": 0.8939820659739083, + "grad_norm": 7.005716825533674, + "learning_rate": 4.226492806325124e-08, + "loss": 0.252, + "step": 3452 + }, + { + "epoch": 0.8942410410799262, + "grad_norm": 3.905013502634552, + "learning_rate": 4.2060853384565946e-08, + "loss": 0.3349, + "step": 3453 + }, + { + "epoch": 0.8945000161859441, + "grad_norm": 4.0105116150110245, + "learning_rate": 4.1857255425810306e-08, + "loss": 0.2801, + "step": 3454 + }, + { + "epoch": 0.894758991291962, + "grad_norm": 5.527027959985177, + "learning_rate": 4.1654134353484173e-08, + "loss": 0.3818, + "step": 3455 + }, + { + "epoch": 0.894758991291962, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8300157150340493, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.2288253903388977, + "eval_runtime": 14.8475, + "eval_samples_per_second": 2.963, + "eval_steps_per_second": 0.135, + "step": 3455 + }, + { + "epoch": 0.89501796639798, + "grad_norm": 4.862029379619393, + "learning_rate": 4.1451490333697314e-08, + "loss": 0.2651, + "step": 3456 + }, + { + "epoch": 0.895276941503998, + "grad_norm": 5.0369299734893165, + "learning_rate": 4.124932353216919e-08, + "loss": 0.382, + "step": 3457 + }, + { + "epoch": 0.8955359166100159, + "grad_norm": 3.9248789089215133, + "learning_rate": 4.104763411422935e-08, + "loss": 0.3658, + "step": 3458 + }, + { + "epoch": 0.8957948917160338, + "grad_norm": 4.7179779512290905, + "learning_rate": 4.0846422244816486e-08, + "loss": 0.3822, + "step": 3459 + }, + { + "epoch": 0.8960538668220517, + "grad_norm": 4.054957381575267, + "learning_rate": 4.06456880884791e-08, + "loss": 0.4453, + "step": 3460 + }, + { + "epoch": 0.8960538668220517, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8302776322682033, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.2287435531616211, + "eval_runtime": 14.8136, + "eval_samples_per_second": 2.97, + "eval_steps_per_second": 0.135, + "step": 3460 + }, + { + "epoch": 0.8963128419280697, + "grad_norm": 5.187373440473211, + "learning_rate": 4.044543180937492e-08, + "loss": 0.3847, + "step": 3461 + }, + { + "epoch": 0.8965718170340876, + "grad_norm": 6.022903626509619, + "learning_rate": 4.024565357127093e-08, + "loss": 0.251, + "step": 3462 + }, + { + "epoch": 0.8968307921401055, + "grad_norm": 6.731571879689912, + "learning_rate": 4.0046353537543106e-08, + "loss": 0.2898, + "step": 3463 + }, + { + "epoch": 0.8970897672461234, + "grad_norm": 3.8153282129111292, + "learning_rate": 3.984753187117642e-08, + "loss": 0.3437, + "step": 3464 + }, + { + "epoch": 0.8973487423521413, + "grad_norm": 5.590534565462717, + "learning_rate": 3.964918873476442e-08, + "loss": 0.225, + "step": 3465 + }, + { + "epoch": 0.8973487423521413, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8308014667365113, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.2275192141532898, + "eval_runtime": 14.6278, + "eval_samples_per_second": 3.008, + "eval_steps_per_second": 0.137, + "step": 3465 + }, + { + "epoch": 0.8976077174581594, + "grad_norm": 3.8962643939179693, + "learning_rate": 3.945132429050979e-08, + "loss": 0.3751, + "step": 3466 + }, + { + "epoch": 0.8978666925641773, + "grad_norm": 5.822090221612418, + "learning_rate": 3.9253938700223386e-08, + "loss": 0.3075, + "step": 3467 + }, + { + "epoch": 0.8981256676701952, + "grad_norm": 3.1700580495271606, + "learning_rate": 3.905703212532433e-08, + "loss": 0.3351, + "step": 3468 + }, + { + "epoch": 0.8983846427762131, + "grad_norm": 2.828506599831979, + "learning_rate": 3.886060472684042e-08, + "loss": 0.2798, + "step": 3469 + }, + { + "epoch": 0.898643617882231, + "grad_norm": 4.27169559920908, + "learning_rate": 3.866465666540725e-08, + "loss": 0.2888, + "step": 3470 + }, + { + "epoch": 0.898643617882231, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8318491356731272, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.2286653369665146, + "eval_runtime": 14.4883, + "eval_samples_per_second": 3.037, + "eval_steps_per_second": 0.138, + "step": 3470 + }, + { + "epoch": 0.898902592988249, + "grad_norm": 4.942244514459234, + "learning_rate": 3.8469188101268664e-08, + "loss": 0.3075, + "step": 3471 + }, + { + "epoch": 0.899161568094267, + "grad_norm": 4.30957478058587, + "learning_rate": 3.8274199194276234e-08, + "loss": 0.382, + "step": 3472 + }, + { + "epoch": 0.8994205432002849, + "grad_norm": 4.755214939128542, + "learning_rate": 3.8079690103889347e-08, + "loss": 0.3771, + "step": 3473 + }, + { + "epoch": 0.8996795183063028, + "grad_norm": 4.164950483901984, + "learning_rate": 3.788566098917486e-08, + "loss": 0.2911, + "step": 3474 + }, + { + "epoch": 0.8999384934123208, + "grad_norm": 4.0697054556196, + "learning_rate": 3.76921120088073e-08, + "loss": 0.252, + "step": 3475 + }, + { + "epoch": 0.8999384934123208, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8305395495023572, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22887569665908813, + "eval_runtime": 15.1033, + "eval_samples_per_second": 2.913, + "eval_steps_per_second": 0.132, + "step": 3475 + }, + { + "epoch": 0.9001974685183387, + "grad_norm": 4.394180248437739, + "learning_rate": 3.7499043321068475e-08, + "loss": 0.3131, + "step": 3476 + }, + { + "epoch": 0.9004564436243566, + "grad_norm": 3.0538595400122386, + "learning_rate": 3.7306455083847354e-08, + "loss": 0.3114, + "step": 3477 + }, + { + "epoch": 0.9007154187303745, + "grad_norm": 3.78932187593212, + "learning_rate": 3.7114347454640096e-08, + "loss": 0.2984, + "step": 3478 + }, + { + "epoch": 0.9009743938363924, + "grad_norm": 2.504834680991571, + "learning_rate": 3.692272059054973e-08, + "loss": 0.2649, + "step": 3479 + }, + { + "epoch": 0.9012333689424105, + "grad_norm": 4.037593300230576, + "learning_rate": 3.673157464828624e-08, + "loss": 0.2338, + "step": 3480 + }, + { + "epoch": 0.9012333689424105, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8318491356731272, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22841906547546387, + "eval_runtime": 15.1296, + "eval_samples_per_second": 2.908, + "eval_steps_per_second": 0.132, + "step": 3480 + }, + { + "epoch": 0.9014923440484284, + "grad_norm": 6.744938406151544, + "learning_rate": 3.654090978416618e-08, + "loss": 0.3676, + "step": 3481 + }, + { + "epoch": 0.9017513191544463, + "grad_norm": 3.3350418632622056, + "learning_rate": 3.635072615411281e-08, + "loss": 0.3201, + "step": 3482 + }, + { + "epoch": 0.9020102942604642, + "grad_norm": 5.126238895136223, + "learning_rate": 3.616102391365582e-08, + "loss": 0.3245, + "step": 3483 + }, + { + "epoch": 0.9022692693664821, + "grad_norm": 2.894133157682696, + "learning_rate": 3.5971803217931115e-08, + "loss": 0.3027, + "step": 3484 + }, + { + "epoch": 0.9025282444725001, + "grad_norm": 3.9977120681734273, + "learning_rate": 3.578306422168089e-08, + "loss": 0.317, + "step": 3485 + }, + { + "epoch": 0.9025282444725001, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8328968046097434, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22943733632564545, + "eval_runtime": 15.1743, + "eval_samples_per_second": 2.9, + "eval_steps_per_second": 0.132, + "step": 3485 + }, + { + "epoch": 0.902787219578518, + "grad_norm": 3.5557029325805023, + "learning_rate": 3.5594807079253475e-08, + "loss": 0.313, + "step": 3486 + }, + { + "epoch": 0.903046194684536, + "grad_norm": 4.46773382874172, + "learning_rate": 3.540703194460302e-08, + "loss": 0.3623, + "step": 3487 + }, + { + "epoch": 0.9033051697905539, + "grad_norm": 5.07113931505075, + "learning_rate": 3.521973897128953e-08, + "loss": 0.2694, + "step": 3488 + }, + { + "epoch": 0.9035641448965718, + "grad_norm": 3.400796448946861, + "learning_rate": 3.503292831247868e-08, + "loss": 0.2768, + "step": 3489 + }, + { + "epoch": 0.9038231200025898, + "grad_norm": 3.9318914984152826, + "learning_rate": 3.484660012094188e-08, + "loss": 0.2806, + "step": 3490 + }, + { + "epoch": 0.9038231200025898, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8308014667365113, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.2280009388923645, + "eval_runtime": 14.6788, + "eval_samples_per_second": 2.998, + "eval_steps_per_second": 0.136, + "step": 3490 + }, + { + "epoch": 0.9040820951086077, + "grad_norm": 3.7298316600768553, + "learning_rate": 3.4660754549055845e-08, + "loss": 0.3102, + "step": 3491 + }, + { + "epoch": 0.9043410702146256, + "grad_norm": 5.246589345384884, + "learning_rate": 3.447539174880263e-08, + "loss": 0.3309, + "step": 3492 + }, + { + "epoch": 0.9046000453206435, + "grad_norm": 3.0464128743217147, + "learning_rate": 3.429051187176929e-08, + "loss": 0.2423, + "step": 3493 + }, + { + "epoch": 0.9048590204266614, + "grad_norm": 5.341849206333132, + "learning_rate": 3.410611506914831e-08, + "loss": 0.3925, + "step": 3494 + }, + { + "epoch": 0.9051179955326795, + "grad_norm": 3.7308874812448445, + "learning_rate": 3.392220149173703e-08, + "loss": 0.2968, + "step": 3495 + }, + { + "epoch": 0.9051179955326795, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8313253012048193, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22804273664951324, + "eval_runtime": 14.4915, + "eval_samples_per_second": 3.036, + "eval_steps_per_second": 0.138, + "step": 3495 + }, + { + "epoch": 0.9053769706386974, + "grad_norm": 5.777622143796477, + "learning_rate": 3.373877128993744e-08, + "loss": 0.2887, + "step": 3496 + }, + { + "epoch": 0.9056359457447153, + "grad_norm": 3.1405435943019966, + "learning_rate": 3.3555824613756285e-08, + "loss": 0.2429, + "step": 3497 + }, + { + "epoch": 0.9058949208507332, + "grad_norm": 4.87773191088679, + "learning_rate": 3.337336161280507e-08, + "loss": 0.3116, + "step": 3498 + }, + { + "epoch": 0.9061538959567511, + "grad_norm": 6.11279450853698, + "learning_rate": 3.319138243629956e-08, + "loss": 0.3295, + "step": 3499 + }, + { + "epoch": 0.9064128710627691, + "grad_norm": 4.257108902348883, + "learning_rate": 3.300988723305997e-08, + "loss": 0.3419, + "step": 3500 + }, + { + "epoch": 0.9064128710627691, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8331587218438974, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22762753069400787, + "eval_runtime": 14.6621, + "eval_samples_per_second": 3.001, + "eval_steps_per_second": 0.136, + "step": 3500 + }, + { + "epoch": 0.906671846168787, + "grad_norm": 6.658332270150957, + "learning_rate": 3.2828876151510606e-08, + "loss": 0.2875, + "step": 3501 + }, + { + "epoch": 0.906930821274805, + "grad_norm": 3.7345365931748282, + "learning_rate": 3.2648349339679877e-08, + "loss": 0.3257, + "step": 3502 + }, + { + "epoch": 0.9071897963808229, + "grad_norm": 4.649697404488906, + "learning_rate": 3.246830694520031e-08, + "loss": 0.4247, + "step": 3503 + }, + { + "epoch": 0.9074487714868408, + "grad_norm": 5.874234925925666, + "learning_rate": 3.228874911530823e-08, + "loss": 0.3273, + "step": 3504 + }, + { + "epoch": 0.9077077465928588, + "grad_norm": 3.3006532882599395, + "learning_rate": 3.21096759968436e-08, + "loss": 0.2929, + "step": 3505 + }, + { + "epoch": 0.9077077465928588, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8323729701414353, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22911635041236877, + "eval_runtime": 15.5326, + "eval_samples_per_second": 2.833, + "eval_steps_per_second": 0.129, + "step": 3505 + }, + { + "epoch": 0.9079667216988767, + "grad_norm": 2.393300562292658, + "learning_rate": 3.193108773625012e-08, + "loss": 0.2453, + "step": 3506 + }, + { + "epoch": 0.9082256968048946, + "grad_norm": 4.169818750397308, + "learning_rate": 3.1752984479574836e-08, + "loss": 0.3245, + "step": 3507 + }, + { + "epoch": 0.9084846719109125, + "grad_norm": 4.184017161205753, + "learning_rate": 3.1575366372468346e-08, + "loss": 0.288, + "step": 3508 + }, + { + "epoch": 0.9087436470169304, + "grad_norm": 3.268075528452953, + "learning_rate": 3.139823356018423e-08, + "loss": 0.3516, + "step": 3509 + }, + { + "epoch": 0.9090026221229485, + "grad_norm": 3.581077190323426, + "learning_rate": 3.122158618757941e-08, + "loss": 0.3029, + "step": 3510 + }, + { + "epoch": 0.9090026221229485, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8305395495023573, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22939838469028473, + "eval_runtime": 14.6182, + "eval_samples_per_second": 3.01, + "eval_steps_per_second": 0.137, + "step": 3510 + }, + { + "epoch": 0.9092615972289664, + "grad_norm": 2.9573108723644164, + "learning_rate": 3.10454243991138e-08, + "loss": 0.2566, + "step": 3511 + }, + { + "epoch": 0.9095205723349843, + "grad_norm": 3.0211449409589597, + "learning_rate": 3.0869748338850234e-08, + "loss": 0.2753, + "step": 3512 + }, + { + "epoch": 0.9097795474410022, + "grad_norm": 3.3759931392023015, + "learning_rate": 3.069455815045405e-08, + "loss": 0.2631, + "step": 3513 + }, + { + "epoch": 0.9100385225470201, + "grad_norm": 3.686880334285989, + "learning_rate": 3.051985397719379e-08, + "loss": 0.2912, + "step": 3514 + }, + { + "epoch": 0.9102974976530381, + "grad_norm": 5.7418072730527445, + "learning_rate": 3.034563596194008e-08, + "loss": 0.2483, + "step": 3515 + }, + { + "epoch": 0.9102974976530381, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8334206390780514, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22764262557029724, + "eval_runtime": 14.9208, + "eval_samples_per_second": 2.949, + "eval_steps_per_second": 0.134, + "step": 3515 + }, + { + "epoch": 0.910556472759056, + "grad_norm": 3.684350149109675, + "learning_rate": 3.0171904247166057e-08, + "loss": 0.3419, + "step": 3516 + }, + { + "epoch": 0.910815447865074, + "grad_norm": 3.069741260114825, + "learning_rate": 2.9998658974947356e-08, + "loss": 0.3299, + "step": 3517 + }, + { + "epoch": 0.9110744229710919, + "grad_norm": 5.685431139471469, + "learning_rate": 2.98259002869615e-08, + "loss": 0.2979, + "step": 3518 + }, + { + "epoch": 0.9113333980771099, + "grad_norm": 4.02449355595937, + "learning_rate": 2.9653628324488316e-08, + "loss": 0.3045, + "step": 3519 + }, + { + "epoch": 0.9115923731831278, + "grad_norm": 9.369959898143184, + "learning_rate": 2.948184322840962e-08, + "loss": 0.444, + "step": 3520 + }, + { + "epoch": 0.9115923731831278, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8336825563122054, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22756633162498474, + "eval_runtime": 14.9801, + "eval_samples_per_second": 2.937, + "eval_steps_per_second": 0.134, + "step": 3520 + }, + { + "epoch": 0.9118513482891457, + "grad_norm": 4.31128382061578, + "learning_rate": 2.9310545139208876e-08, + "loss": 0.3437, + "step": 3521 + }, + { + "epoch": 0.9121103233951636, + "grad_norm": 3.591450336500356, + "learning_rate": 2.9139734196971456e-08, + "loss": 0.3539, + "step": 3522 + }, + { + "epoch": 0.9123692985011815, + "grad_norm": 5.45003884982312, + "learning_rate": 2.8969410541384302e-08, + "loss": 0.2814, + "step": 3523 + }, + { + "epoch": 0.9126282736071996, + "grad_norm": 4.074984447480573, + "learning_rate": 2.879957431173572e-08, + "loss": 0.3347, + "step": 3524 + }, + { + "epoch": 0.9128872487132175, + "grad_norm": 5.62413002679158, + "learning_rate": 2.8630225646915853e-08, + "loss": 0.3122, + "step": 3525 + }, + { + "epoch": 0.9128872487132175, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8349921424829754, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.2277001440525055, + "eval_runtime": 14.4339, + "eval_samples_per_second": 3.048, + "eval_steps_per_second": 0.139, + "step": 3525 + }, + { + "epoch": 0.9131462238192354, + "grad_norm": 3.743782660765499, + "learning_rate": 2.846136468541552e-08, + "loss": 0.2717, + "step": 3526 + }, + { + "epoch": 0.9134051989252533, + "grad_norm": 4.861760885279072, + "learning_rate": 2.8292991565327042e-08, + "loss": 0.3026, + "step": 3527 + }, + { + "epoch": 0.9136641740312712, + "grad_norm": 3.5247476679503524, + "learning_rate": 2.812510642434374e-08, + "loss": 0.2644, + "step": 3528 + }, + { + "epoch": 0.9139231491372892, + "grad_norm": 5.233895632566011, + "learning_rate": 2.795770939975989e-08, + "loss": 0.3155, + "step": 3529 + }, + { + "epoch": 0.9141821242433071, + "grad_norm": 3.4676345140269142, + "learning_rate": 2.7790800628470574e-08, + "loss": 0.3378, + "step": 3530 + }, + { + "epoch": 0.9141821242433071, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8331587218438974, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.2272835373878479, + "eval_runtime": 14.6201, + "eval_samples_per_second": 3.01, + "eval_steps_per_second": 0.137, + "step": 3530 + }, + { + "epoch": 0.914441099349325, + "grad_norm": 5.278927511443333, + "learning_rate": 2.7624380246971463e-08, + "loss": 0.3467, + "step": 3531 + }, + { + "epoch": 0.914700074455343, + "grad_norm": 4.469836647612876, + "learning_rate": 2.745844839135911e-08, + "loss": 0.3015, + "step": 3532 + }, + { + "epoch": 0.9149590495613609, + "grad_norm": 4.059744433278033, + "learning_rate": 2.7293005197330318e-08, + "loss": 0.3619, + "step": 3533 + }, + { + "epoch": 0.9152180246673789, + "grad_norm": 3.109433689246621, + "learning_rate": 2.712805080018234e-08, + "loss": 0.2944, + "step": 3534 + }, + { + "epoch": 0.9154769997733968, + "grad_norm": 4.4667667043265835, + "learning_rate": 2.696358533481276e-08, + "loss": 0.314, + "step": 3535 + }, + { + "epoch": 0.9154769997733968, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8318491356731272, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22725313901901245, + "eval_runtime": 14.7154, + "eval_samples_per_second": 2.99, + "eval_steps_per_second": 0.136, + "step": 3535 + }, + { + "epoch": 0.9157359748794147, + "grad_norm": 3.16911332055457, + "learning_rate": 2.6799608935719132e-08, + "loss": 0.3014, + "step": 3536 + }, + { + "epoch": 0.9159949499854326, + "grad_norm": 3.7315791663825055, + "learning_rate": 2.6636121736999324e-08, + "loss": 0.3464, + "step": 3537 + }, + { + "epoch": 0.9162539250914505, + "grad_norm": 3.30366300515193, + "learning_rate": 2.6473123872350902e-08, + "loss": 0.2869, + "step": 3538 + }, + { + "epoch": 0.9165129001974686, + "grad_norm": 3.3205785152317024, + "learning_rate": 2.631061547507141e-08, + "loss": 0.3464, + "step": 3539 + }, + { + "epoch": 0.9167718753034865, + "grad_norm": 4.561389471907303, + "learning_rate": 2.614859667805815e-08, + "loss": 0.3561, + "step": 3540 + }, + { + "epoch": 0.9167718753034865, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8334206390780513, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.2274029403924942, + "eval_runtime": 14.697, + "eval_samples_per_second": 2.994, + "eval_steps_per_second": 0.136, + "step": 3540 + }, + { + "epoch": 0.9170308504095044, + "grad_norm": 3.087318650785213, + "learning_rate": 2.5987067613807773e-08, + "loss": 0.2728, + "step": 3541 + }, + { + "epoch": 0.9172898255155223, + "grad_norm": 3.1481458054572307, + "learning_rate": 2.5826028414416767e-08, + "loss": 0.2881, + "step": 3542 + }, + { + "epoch": 0.9175488006215402, + "grad_norm": 4.211724744449585, + "learning_rate": 2.566547921158083e-08, + "loss": 0.3486, + "step": 3543 + }, + { + "epoch": 0.9178077757275582, + "grad_norm": 2.7537085859441626, + "learning_rate": 2.5505420136594933e-08, + "loss": 0.3234, + "step": 3544 + }, + { + "epoch": 0.9180667508335761, + "grad_norm": 3.2254052630465035, + "learning_rate": 2.5345851320353263e-08, + "loss": 0.2942, + "step": 3545 + }, + { + "epoch": 0.9180667508335761, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8326348873755893, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22719654440879822, + "eval_runtime": 14.9348, + "eval_samples_per_second": 2.946, + "eval_steps_per_second": 0.134, + "step": 3545 + }, + { + "epoch": 0.918325725939594, + "grad_norm": 4.002147896395684, + "learning_rate": 2.518677289334914e-08, + "loss": 0.3435, + "step": 3546 + }, + { + "epoch": 0.918584701045612, + "grad_norm": 3.356582446866656, + "learning_rate": 2.502818498567483e-08, + "loss": 0.2757, + "step": 3547 + }, + { + "epoch": 0.9188436761516299, + "grad_norm": 2.9925321774318085, + "learning_rate": 2.4870087727021304e-08, + "loss": 0.2423, + "step": 3548 + }, + { + "epoch": 0.9191026512576479, + "grad_norm": 4.493241726543325, + "learning_rate": 2.4712481246678547e-08, + "loss": 0.4105, + "step": 3549 + }, + { + "epoch": 0.9193616263636658, + "grad_norm": 4.004110546753917, + "learning_rate": 2.4555365673534988e-08, + "loss": 0.3138, + "step": 3550 + }, + { + "epoch": 0.9193616263636658, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8355159769512834, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22700929641723633, + "eval_runtime": 14.532, + "eval_samples_per_second": 3.028, + "eval_steps_per_second": 0.138, + "step": 3550 + }, + { + "epoch": 0.9196206014696837, + "grad_norm": 5.858679067704419, + "learning_rate": 2.4398741136077708e-08, + "loss": 0.3653, + "step": 3551 + }, + { + "epoch": 0.9198795765757016, + "grad_norm": 3.707217686876636, + "learning_rate": 2.4242607762391957e-08, + "loss": 0.3111, + "step": 3552 + }, + { + "epoch": 0.9201385516817195, + "grad_norm": 4.8212671897384105, + "learning_rate": 2.4086965680161916e-08, + "loss": 0.3859, + "step": 3553 + }, + { + "epoch": 0.9203975267877376, + "grad_norm": 3.1744152568105286, + "learning_rate": 2.3931815016669386e-08, + "loss": 0.2919, + "step": 3554 + }, + { + "epoch": 0.9206565018937555, + "grad_norm": 4.75990845618556, + "learning_rate": 2.3777155898794537e-08, + "loss": 0.2341, + "step": 3555 + }, + { + "epoch": 0.9206565018937555, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8310633839706653, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22753220796585083, + "eval_runtime": 15.0539, + "eval_samples_per_second": 2.923, + "eval_steps_per_second": 0.133, + "step": 3555 + }, + { + "epoch": 0.9209154769997734, + "grad_norm": 5.162344514222715, + "learning_rate": 2.3622988453015708e-08, + "loss": 0.3353, + "step": 3556 + }, + { + "epoch": 0.9211744521057913, + "grad_norm": 4.030530963049944, + "learning_rate": 2.346931280540879e-08, + "loss": 0.3381, + "step": 3557 + }, + { + "epoch": 0.9214334272118093, + "grad_norm": 6.039147740361125, + "learning_rate": 2.3316129081647905e-08, + "loss": 0.3835, + "step": 3558 + }, + { + "epoch": 0.9216924023178272, + "grad_norm": 3.424213109809178, + "learning_rate": 2.316343740700451e-08, + "loss": 0.2842, + "step": 3559 + }, + { + "epoch": 0.9219513774238451, + "grad_norm": 3.5733784726275917, + "learning_rate": 2.301123790634789e-08, + "loss": 0.3262, + "step": 3560 + }, + { + "epoch": 0.9219513774238451, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8323729701414353, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22674298286437988, + "eval_runtime": 14.671, + "eval_samples_per_second": 2.999, + "eval_steps_per_second": 0.136, + "step": 3560 + }, + { + "epoch": 0.922210352529863, + "grad_norm": 6.08548742034888, + "learning_rate": 2.2859530704144802e-08, + "loss": 0.3458, + "step": 3561 + }, + { + "epoch": 0.922469327635881, + "grad_norm": 4.723417007479406, + "learning_rate": 2.2708315924459268e-08, + "loss": 0.3791, + "step": 3562 + }, + { + "epoch": 0.922728302741899, + "grad_norm": 4.065500132720788, + "learning_rate": 2.255759369095299e-08, + "loss": 0.3135, + "step": 3563 + }, + { + "epoch": 0.9229872778479169, + "grad_norm": 3.5282554424241663, + "learning_rate": 2.2407364126884464e-08, + "loss": 0.2973, + "step": 3564 + }, + { + "epoch": 0.9232462529539348, + "grad_norm": 2.8924772234860554, + "learning_rate": 2.225762735510943e-08, + "loss": 0.2564, + "step": 3565 + }, + { + "epoch": 0.9232462529539348, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8323729701414353, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22608961164951324, + "eval_runtime": 14.3267, + "eval_samples_per_second": 3.071, + "eval_steps_per_second": 0.14, + "step": 3565 + }, + { + "epoch": 0.9235052280599527, + "grad_norm": 4.773785627481292, + "learning_rate": 2.2108383498080713e-08, + "loss": 0.3317, + "step": 3566 + }, + { + "epoch": 0.9237642031659706, + "grad_norm": 5.306235133336425, + "learning_rate": 2.1959632677847898e-08, + "loss": 0.3685, + "step": 3567 + }, + { + "epoch": 0.9240231782719887, + "grad_norm": 4.1947069354381945, + "learning_rate": 2.1811375016057428e-08, + "loss": 0.2931, + "step": 3568 + }, + { + "epoch": 0.9242821533780066, + "grad_norm": 3.0183950530763712, + "learning_rate": 2.166361063395253e-08, + "loss": 0.2779, + "step": 3569 + }, + { + "epoch": 0.9245411284840245, + "grad_norm": 3.8721823618920004, + "learning_rate": 2.1516339652372932e-08, + "loss": 0.3618, + "step": 3570 + }, + { + "epoch": 0.9245411284840245, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8336825563122054, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.2277008444070816, + "eval_runtime": 14.5843, + "eval_samples_per_second": 3.017, + "eval_steps_per_second": 0.137, + "step": 3570 + }, + { + "epoch": 0.9248001035900424, + "grad_norm": 3.490438640340912, + "learning_rate": 2.1369562191754857e-08, + "loss": 0.2871, + "step": 3571 + }, + { + "epoch": 0.9250590786960603, + "grad_norm": 4.278304200275105, + "learning_rate": 2.122327837213091e-08, + "loss": 0.3156, + "step": 3572 + }, + { + "epoch": 0.9253180538020783, + "grad_norm": 3.3146489795592284, + "learning_rate": 2.107748831313032e-08, + "loss": 0.312, + "step": 3573 + }, + { + "epoch": 0.9255770289080962, + "grad_norm": 4.090001614021699, + "learning_rate": 2.0932192133978e-08, + "loss": 0.2771, + "step": 3574 + }, + { + "epoch": 0.9258360040141141, + "grad_norm": 4.2532762037766325, + "learning_rate": 2.0787389953495497e-08, + "loss": 0.3529, + "step": 3575 + }, + { + "epoch": 0.9258360040141141, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8313253012048193, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22716179490089417, + "eval_runtime": 14.545, + "eval_samples_per_second": 3.025, + "eval_steps_per_second": 0.138, + "step": 3575 + }, + { + "epoch": 0.9260949791201321, + "grad_norm": 4.124462776338432, + "learning_rate": 2.064308189009996e-08, + "loss": 0.3632, + "step": 3576 + }, + { + "epoch": 0.92635395422615, + "grad_norm": 4.983420753621755, + "learning_rate": 2.0499268061804563e-08, + "loss": 0.4111, + "step": 3577 + }, + { + "epoch": 0.926612929332168, + "grad_norm": 3.68678896687096, + "learning_rate": 2.035594858621842e-08, + "loss": 0.304, + "step": 3578 + }, + { + "epoch": 0.9268719044381859, + "grad_norm": 8.041891781853636, + "learning_rate": 2.021312358054639e-08, + "loss": 0.3698, + "step": 3579 + }, + { + "epoch": 0.9271308795442038, + "grad_norm": 5.191464748540226, + "learning_rate": 2.007079316158872e-08, + "loss": 0.3478, + "step": 3580 + }, + { + "epoch": 0.9271308795442038, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8373493975903615, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22711549699306488, + "eval_runtime": 14.7953, + "eval_samples_per_second": 2.974, + "eval_steps_per_second": 0.135, + "step": 3580 + }, + { + "epoch": 0.9273898546502217, + "grad_norm": 4.274988026760934, + "learning_rate": 1.992895744574147e-08, + "loss": 0.4131, + "step": 3581 + }, + { + "epoch": 0.9276488297562396, + "grad_norm": 5.689321691038787, + "learning_rate": 1.9787616548995956e-08, + "loss": 0.3988, + "step": 3582 + }, + { + "epoch": 0.9279078048622577, + "grad_norm": 3.0574317118636998, + "learning_rate": 1.964677058693888e-08, + "loss": 0.3665, + "step": 3583 + }, + { + "epoch": 0.9281667799682756, + "grad_norm": 4.134628262816393, + "learning_rate": 1.950641967475228e-08, + "loss": 0.4059, + "step": 3584 + }, + { + "epoch": 0.9284257550742935, + "grad_norm": 4.624065396147654, + "learning_rate": 1.936656392721316e-08, + "loss": 0.3754, + "step": 3585 + }, + { + "epoch": 0.9284257550742935, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8334206390780513, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.227674663066864, + "eval_runtime": 14.7461, + "eval_samples_per_second": 2.984, + "eval_steps_per_second": 0.136, + "step": 3585 + }, + { + "epoch": 0.9286847301803114, + "grad_norm": 5.137808813024803, + "learning_rate": 1.9227203458693847e-08, + "loss": 0.3636, + "step": 3586 + }, + { + "epoch": 0.9289437052863293, + "grad_norm": 3.222327637306318, + "learning_rate": 1.9088338383161376e-08, + "loss": 0.3098, + "step": 3587 + }, + { + "epoch": 0.9292026803923473, + "grad_norm": 5.927392377926643, + "learning_rate": 1.894996881417782e-08, + "loss": 0.392, + "step": 3588 + }, + { + "epoch": 0.9294616554983652, + "grad_norm": 3.5165172169165353, + "learning_rate": 1.881209486489996e-08, + "loss": 0.3329, + "step": 3589 + }, + { + "epoch": 0.9297206306043831, + "grad_norm": 6.516823166304788, + "learning_rate": 1.8674716648079336e-08, + "loss": 0.3496, + "step": 3590 + }, + { + "epoch": 0.9297206306043831, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8302776322682033, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.227274090051651, + "eval_runtime": 14.3975, + "eval_samples_per_second": 3.056, + "eval_steps_per_second": 0.139, + "step": 3590 + }, + { + "epoch": 0.9299796057104011, + "grad_norm": 5.922768274899525, + "learning_rate": 1.8537834276061984e-08, + "loss": 0.2827, + "step": 3591 + }, + { + "epoch": 0.930238580816419, + "grad_norm": 2.8301109604673926, + "learning_rate": 1.8401447860788568e-08, + "loss": 0.2884, + "step": 3592 + }, + { + "epoch": 0.930497555922437, + "grad_norm": 3.0466015183948483, + "learning_rate": 1.826555751379397e-08, + "loss": 0.277, + "step": 3593 + }, + { + "epoch": 0.9307565310284549, + "grad_norm": 3.8659035294387833, + "learning_rate": 1.8130163346207694e-08, + "loss": 0.2763, + "step": 3594 + }, + { + "epoch": 0.9310155061344728, + "grad_norm": 5.409756793029833, + "learning_rate": 1.7995265468753117e-08, + "loss": 0.3672, + "step": 3595 + }, + { + "epoch": 0.9310155061344728, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8326348873755893, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22807078063488007, + "eval_runtime": 14.2448, + "eval_samples_per_second": 3.089, + "eval_steps_per_second": 0.14, + "step": 3595 + }, + { + "epoch": 0.9312744812404907, + "grad_norm": 3.3580634540459955, + "learning_rate": 1.7860863991748106e-08, + "loss": 0.3042, + "step": 3596 + }, + { + "epoch": 0.9315334563465086, + "grad_norm": 5.403727553932612, + "learning_rate": 1.7726959025104254e-08, + "loss": 0.3017, + "step": 3597 + }, + { + "epoch": 0.9317924314525267, + "grad_norm": 5.193886068044656, + "learning_rate": 1.7593550678327437e-08, + "loss": 0.3335, + "step": 3598 + }, + { + "epoch": 0.9320514065585446, + "grad_norm": 3.0647235150129606, + "learning_rate": 1.746063906051705e-08, + "loss": 0.2854, + "step": 3599 + }, + { + "epoch": 0.9323103816645625, + "grad_norm": 3.968021756350638, + "learning_rate": 1.7328224280366708e-08, + "loss": 0.321, + "step": 3600 + }, + { + "epoch": 0.9323103816645625, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8336825563122053, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22722715139389038, + "eval_runtime": 14.6184, + "eval_samples_per_second": 3.01, + "eval_steps_per_second": 0.137, + "step": 3600 + }, + { + "epoch": 0.9325693567705804, + "grad_norm": 3.9452167384345915, + "learning_rate": 1.7196306446163185e-08, + "loss": 0.3286, + "step": 3601 + }, + { + "epoch": 0.9328283318765984, + "grad_norm": 3.2308210486558733, + "learning_rate": 1.7064885665787346e-08, + "loss": 0.2979, + "step": 3602 + }, + { + "epoch": 0.9330873069826163, + "grad_norm": 2.745806577598325, + "learning_rate": 1.6933962046713284e-08, + "loss": 0.2485, + "step": 3603 + }, + { + "epoch": 0.9333462820886342, + "grad_norm": 3.1195401424870375, + "learning_rate": 1.680353569600862e-08, + "loss": 0.295, + "step": 3604 + }, + { + "epoch": 0.9336052571946521, + "grad_norm": 4.238435100489242, + "learning_rate": 1.6673606720334356e-08, + "loss": 0.4098, + "step": 3605 + }, + { + "epoch": 0.9336052571946521, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8318491356731273, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22748208045959473, + "eval_runtime": 14.6859, + "eval_samples_per_second": 2.996, + "eval_steps_per_second": 0.136, + "step": 3605 + }, + { + "epoch": 0.9338642323006701, + "grad_norm": 4.295255199344785, + "learning_rate": 1.654417522594459e-08, + "loss": 0.3146, + "step": 3606 + }, + { + "epoch": 0.9341232074066881, + "grad_norm": 3.5133202132490506, + "learning_rate": 1.6415241318686742e-08, + "loss": 0.2644, + "step": 3607 + }, + { + "epoch": 0.934382182512706, + "grad_norm": 5.206264683165435, + "learning_rate": 1.6286805104001325e-08, + "loss": 0.3704, + "step": 3608 + }, + { + "epoch": 0.9346411576187239, + "grad_norm": 2.822308458072882, + "learning_rate": 1.615886668692161e-08, + "loss": 0.2831, + "step": 3609 + }, + { + "epoch": 0.9349001327247418, + "grad_norm": 5.469320167009498, + "learning_rate": 1.603142617207405e-08, + "loss": 0.2378, + "step": 3610 + }, + { + "epoch": 0.9349001327247418, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8344683080146673, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.2271704524755478, + "eval_runtime": 14.7283, + "eval_samples_per_second": 2.987, + "eval_steps_per_second": 0.136, + "step": 3610 + }, + { + "epoch": 0.9351591078307597, + "grad_norm": 7.760724638894671, + "learning_rate": 1.5904483663677776e-08, + "loss": 0.3738, + "step": 3611 + }, + { + "epoch": 0.9354180829367778, + "grad_norm": 5.503304716626157, + "learning_rate": 1.577803926554475e-08, + "loss": 0.3037, + "step": 3612 + }, + { + "epoch": 0.9356770580427957, + "grad_norm": 5.56800313067715, + "learning_rate": 1.565209308107947e-08, + "loss": 0.3643, + "step": 3613 + }, + { + "epoch": 0.9359360331488136, + "grad_norm": 4.98279214313769, + "learning_rate": 1.5526645213279137e-08, + "loss": 0.4438, + "step": 3614 + }, + { + "epoch": 0.9361950082548315, + "grad_norm": 2.8677893032491575, + "learning_rate": 1.5401695764733284e-08, + "loss": 0.248, + "step": 3615 + }, + { + "epoch": 0.9361950082548315, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8339444735463595, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22812624275684357, + "eval_runtime": 14.4244, + "eval_samples_per_second": 3.05, + "eval_steps_per_second": 0.139, + "step": 3615 + }, + { + "epoch": 0.9364539833608494, + "grad_norm": 3.5848299177250365, + "learning_rate": 1.5277244837623996e-08, + "loss": 0.2688, + "step": 3616 + }, + { + "epoch": 0.9367129584668674, + "grad_norm": 3.519182697138096, + "learning_rate": 1.515329253372555e-08, + "loss": 0.4097, + "step": 3617 + }, + { + "epoch": 0.9369719335728853, + "grad_norm": 3.752513120205663, + "learning_rate": 1.5029838954404436e-08, + "loss": 0.2678, + "step": 3618 + }, + { + "epoch": 0.9372309086789032, + "grad_norm": 3.1973235136342213, + "learning_rate": 1.4906884200619477e-08, + "loss": 0.3155, + "step": 3619 + }, + { + "epoch": 0.9374898837849212, + "grad_norm": 2.658567115141049, + "learning_rate": 1.478442837292135e-08, + "loss": 0.2971, + "step": 3620 + }, + { + "epoch": 0.9374898837849212, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8347302252488213, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22747349739074707, + "eval_runtime": 14.6444, + "eval_samples_per_second": 3.005, + "eval_steps_per_second": 0.137, + "step": 3620 + }, + { + "epoch": 0.9377488588909391, + "grad_norm": 2.6452860267581277, + "learning_rate": 1.46624715714528e-08, + "loss": 0.2661, + "step": 3621 + }, + { + "epoch": 0.9380078339969571, + "grad_norm": 3.451612601603736, + "learning_rate": 1.4541013895948557e-08, + "loss": 0.2963, + "step": 3622 + }, + { + "epoch": 0.938266809102975, + "grad_norm": 2.959860948020173, + "learning_rate": 1.4420055445735146e-08, + "loss": 0.3483, + "step": 3623 + }, + { + "epoch": 0.9385257842089929, + "grad_norm": 6.990443224067317, + "learning_rate": 1.4299596319730727e-08, + "loss": 0.3502, + "step": 3624 + }, + { + "epoch": 0.9387847593150108, + "grad_norm": 6.416562624520446, + "learning_rate": 1.4179636616445252e-08, + "loss": 0.3409, + "step": 3625 + }, + { + "epoch": 0.9387847593150108, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8318491356731272, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22689169645309448, + "eval_runtime": 14.7981, + "eval_samples_per_second": 2.973, + "eval_steps_per_second": 0.135, + "step": 3625 + }, + { + "epoch": 0.9390437344210287, + "grad_norm": 2.845831953597317, + "learning_rate": 1.4060176433980042e-08, + "loss": 0.2816, + "step": 3626 + }, + { + "epoch": 0.9393027095270468, + "grad_norm": 6.55400743039207, + "learning_rate": 1.3941215870028058e-08, + "loss": 0.5005, + "step": 3627 + }, + { + "epoch": 0.9395616846330647, + "grad_norm": 4.238681202484355, + "learning_rate": 1.3822755021873844e-08, + "loss": 0.3544, + "step": 3628 + }, + { + "epoch": 0.9398206597390826, + "grad_norm": 3.423640236159824, + "learning_rate": 1.3704793986392961e-08, + "loss": 0.3512, + "step": 3629 + }, + { + "epoch": 0.9400796348451005, + "grad_norm": 3.38759270711965, + "learning_rate": 1.3587332860052482e-08, + "loss": 0.3358, + "step": 3630 + }, + { + "epoch": 0.9400796348451005, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8357778941854374, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.2271747589111328, + "eval_runtime": 14.8215, + "eval_samples_per_second": 2.969, + "eval_steps_per_second": 0.135, + "step": 3630 + }, + { + "epoch": 0.9403386099511184, + "grad_norm": 4.6321380785611375, + "learning_rate": 1.3470371738910498e-08, + "loss": 0.3834, + "step": 3631 + }, + { + "epoch": 0.9405975850571364, + "grad_norm": 3.2391006151356603, + "learning_rate": 1.3353910718616192e-08, + "loss": 0.3453, + "step": 3632 + }, + { + "epoch": 0.9408565601631543, + "grad_norm": 4.331542674736102, + "learning_rate": 1.3237949894410115e-08, + "loss": 0.3668, + "step": 3633 + }, + { + "epoch": 0.9411155352691722, + "grad_norm": 4.577358989805272, + "learning_rate": 1.3122489361123286e-08, + "loss": 0.3768, + "step": 3634 + }, + { + "epoch": 0.9413745103751902, + "grad_norm": 3.3202295071741843, + "learning_rate": 1.3007529213177813e-08, + "loss": 0.3403, + "step": 3635 + }, + { + "epoch": 0.9413745103751902, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8336825563122053, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22670255601406097, + "eval_runtime": 14.445, + "eval_samples_per_second": 3.046, + "eval_steps_per_second": 0.138, + "step": 3635 + }, + { + "epoch": 0.9416334854812081, + "grad_norm": 7.161620463670725, + "learning_rate": 1.289306954458662e-08, + "loss": 0.3715, + "step": 3636 + }, + { + "epoch": 0.9418924605872261, + "grad_norm": 2.881021719740321, + "learning_rate": 1.2779110448953302e-08, + "loss": 0.3178, + "step": 3637 + }, + { + "epoch": 0.942151435693244, + "grad_norm": 4.504864763033837, + "learning_rate": 1.2665652019472133e-08, + "loss": 0.3687, + "step": 3638 + }, + { + "epoch": 0.9424104107992619, + "grad_norm": 3.454434033795404, + "learning_rate": 1.2552694348927919e-08, + "loss": 0.2869, + "step": 3639 + }, + { + "epoch": 0.9426693859052798, + "grad_norm": 3.465183900159842, + "learning_rate": 1.2440237529695864e-08, + "loss": 0.2999, + "step": 3640 + }, + { + "epoch": 0.9426693859052798, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8313253012048193, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22781075537204742, + "eval_runtime": 14.7632, + "eval_samples_per_second": 2.98, + "eval_steps_per_second": 0.135, + "step": 3640 + }, + { + "epoch": 0.9429283610112978, + "grad_norm": 5.573515978843369, + "learning_rate": 1.232828165374178e-08, + "loss": 0.2685, + "step": 3641 + }, + { + "epoch": 0.9431873361173158, + "grad_norm": 6.330031825249047, + "learning_rate": 1.2216826812621595e-08, + "loss": 0.3372, + "step": 3642 + }, + { + "epoch": 0.9434463112233337, + "grad_norm": 3.281072435287292, + "learning_rate": 1.2105873097481707e-08, + "loss": 0.23, + "step": 3643 + }, + { + "epoch": 0.9437052863293516, + "grad_norm": 4.739224247561069, + "learning_rate": 1.199542059905856e-08, + "loss": 0.379, + "step": 3644 + }, + { + "epoch": 0.9439642614353695, + "grad_norm": 3.236673708214439, + "learning_rate": 1.188546940767872e-08, + "loss": 0.3059, + "step": 3645 + }, + { + "epoch": 0.9439642614353695, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8331587218438973, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22814516723155975, + "eval_runtime": 15.1701, + "eval_samples_per_second": 2.9, + "eval_steps_per_second": 0.132, + "step": 3645 + }, + { + "epoch": 0.9442232365413875, + "grad_norm": 3.8527012586315568, + "learning_rate": 1.1776019613258873e-08, + "loss": 0.3674, + "step": 3646 + }, + { + "epoch": 0.9444822116474054, + "grad_norm": 3.130703326786509, + "learning_rate": 1.1667071305305547e-08, + "loss": 0.2355, + "step": 3647 + }, + { + "epoch": 0.9447411867534233, + "grad_norm": 6.606572545575242, + "learning_rate": 1.1558624572915247e-08, + "loss": 0.2979, + "step": 3648 + }, + { + "epoch": 0.9450001618594412, + "grad_norm": 3.4110722928748696, + "learning_rate": 1.1450679504774326e-08, + "loss": 0.3292, + "step": 3649 + }, + { + "epoch": 0.9452591369654592, + "grad_norm": 4.883485349943146, + "learning_rate": 1.1343236189158766e-08, + "loss": 0.3343, + "step": 3650 + }, + { + "epoch": 0.9452591369654592, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8347302252488213, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22717644274234772, + "eval_runtime": 14.6814, + "eval_samples_per_second": 2.997, + "eval_steps_per_second": 0.136, + "step": 3650 + }, + { + "epoch": 0.9455181120714772, + "grad_norm": 6.093587649764905, + "learning_rate": 1.1236294713934322e-08, + "loss": 0.4174, + "step": 3651 + }, + { + "epoch": 0.9457770871774951, + "grad_norm": 4.900178274353927, + "learning_rate": 1.112985516655632e-08, + "loss": 0.2602, + "step": 3652 + }, + { + "epoch": 0.946036062283513, + "grad_norm": 3.6097861423893463, + "learning_rate": 1.1023917634069639e-08, + "loss": 0.3119, + "step": 3653 + }, + { + "epoch": 0.9462950373895309, + "grad_norm": 5.997349656410146, + "learning_rate": 1.0918482203108593e-08, + "loss": 0.326, + "step": 3654 + }, + { + "epoch": 0.9465540124955488, + "grad_norm": 4.952459512351431, + "learning_rate": 1.081354895989685e-08, + "loss": 0.4361, + "step": 3655 + }, + { + "epoch": 0.9465540124955488, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8339444735463594, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22808776795864105, + "eval_runtime": 14.7704, + "eval_samples_per_second": 2.979, + "eval_steps_per_second": 0.135, + "step": 3655 + }, + { + "epoch": 0.9468129876015668, + "grad_norm": 3.2543892282724363, + "learning_rate": 1.0709117990247431e-08, + "loss": 0.2327, + "step": 3656 + }, + { + "epoch": 0.9470719627075848, + "grad_norm": 4.906965288762532, + "learning_rate": 1.0605189379562578e-08, + "loss": 0.3769, + "step": 3657 + }, + { + "epoch": 0.9473309378136027, + "grad_norm": 3.8822330664335114, + "learning_rate": 1.0501763212833817e-08, + "loss": 0.2727, + "step": 3658 + }, + { + "epoch": 0.9475899129196206, + "grad_norm": 3.679605321331663, + "learning_rate": 1.039883957464169e-08, + "loss": 0.3607, + "step": 3659 + }, + { + "epoch": 0.9478488880256385, + "grad_norm": 3.7683308062075676, + "learning_rate": 1.0296418549155598e-08, + "loss": 0.2859, + "step": 3660 + }, + { + "epoch": 0.9478488880256385, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8339444735463594, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22781690955162048, + "eval_runtime": 14.8505, + "eval_samples_per_second": 2.963, + "eval_steps_per_second": 0.135, + "step": 3660 + }, + { + "epoch": 0.9481078631316565, + "grad_norm": 3.0408844107256643, + "learning_rate": 1.019450022013438e-08, + "loss": 0.2901, + "step": 3661 + }, + { + "epoch": 0.9483668382376744, + "grad_norm": 4.15093791924597, + "learning_rate": 1.0093084670925318e-08, + "loss": 0.2966, + "step": 3662 + }, + { + "epoch": 0.9486258133436923, + "grad_norm": 4.760587632539664, + "learning_rate": 9.992171984464782e-09, + "loss": 0.3728, + "step": 3663 + }, + { + "epoch": 0.9488847884497102, + "grad_norm": 4.799007590382829, + "learning_rate": 9.89176224327787e-09, + "loss": 0.3337, + "step": 3664 + }, + { + "epoch": 0.9491437635557282, + "grad_norm": 4.284545288916356, + "learning_rate": 9.7918555294782e-09, + "loss": 0.3317, + "step": 3665 + }, + { + "epoch": 0.9491437635557282, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8336825563122053, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.227735698223114, + "eval_runtime": 14.7362, + "eval_samples_per_second": 2.986, + "eval_steps_per_second": 0.136, + "step": 3665 + }, + { + "epoch": 0.9494027386617462, + "grad_norm": 3.700305729264088, + "learning_rate": 9.692451924768337e-09, + "loss": 0.327, + "step": 3666 + }, + { + "epoch": 0.9496617137677641, + "grad_norm": 3.485250927323631, + "learning_rate": 9.593551510439086e-09, + "loss": 0.371, + "step": 3667 + }, + { + "epoch": 0.949920688873782, + "grad_norm": 3.8891845150984246, + "learning_rate": 9.495154367369988e-09, + "loss": 0.3345, + "step": 3668 + }, + { + "epoch": 0.9501796639797999, + "grad_norm": 5.266785350354726, + "learning_rate": 9.397260576028897e-09, + "loss": 0.3656, + "step": 3669 + }, + { + "epoch": 0.9504386390858178, + "grad_norm": 4.19726798214639, + "learning_rate": 9.299870216471982e-09, + "loss": 0.3255, + "step": 3670 + }, + { + "epoch": 0.9504386390858178, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8334206390780514, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22928597033023834, + "eval_runtime": 14.6032, + "eval_samples_per_second": 3.013, + "eval_steps_per_second": 0.137, + "step": 3670 + }, + { + "epoch": 0.9506976141918358, + "grad_norm": 3.150761364774726, + "learning_rate": 9.202983368343938e-09, + "loss": 0.3362, + "step": 3671 + }, + { + "epoch": 0.9509565892978538, + "grad_norm": 4.019792395061327, + "learning_rate": 9.106600110877495e-09, + "loss": 0.2536, + "step": 3672 + }, + { + "epoch": 0.9512155644038717, + "grad_norm": 5.430353855647166, + "learning_rate": 9.010720522893562e-09, + "loss": 0.3438, + "step": 3673 + }, + { + "epoch": 0.9514745395098896, + "grad_norm": 5.510726597932946, + "learning_rate": 8.915344682801224e-09, + "loss": 0.3183, + "step": 3674 + }, + { + "epoch": 0.9517335146159075, + "grad_norm": 3.3330579305486374, + "learning_rate": 8.820472668597674e-09, + "loss": 0.2971, + "step": 3675 + }, + { + "epoch": 0.9517335146159075, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8323729701414353, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.2276269942522049, + "eval_runtime": 14.4447, + "eval_samples_per_second": 3.046, + "eval_steps_per_second": 0.138, + "step": 3675 + }, + { + "epoch": 0.9519924897219255, + "grad_norm": 3.985966541788916, + "learning_rate": 8.726104557867862e-09, + "loss": 0.3329, + "step": 3676 + }, + { + "epoch": 0.9522514648279434, + "grad_norm": 3.615222717025619, + "learning_rate": 8.63224042778478e-09, + "loss": 0.2912, + "step": 3677 + }, + { + "epoch": 0.9525104399339613, + "grad_norm": 5.193279886366126, + "learning_rate": 8.538880355109386e-09, + "loss": 0.3448, + "step": 3678 + }, + { + "epoch": 0.9527694150399793, + "grad_norm": 3.4948326163212404, + "learning_rate": 8.44602441619019e-09, + "loss": 0.3331, + "step": 3679 + }, + { + "epoch": 0.9530283901459972, + "grad_norm": 3.4194463731118447, + "learning_rate": 8.353672686963604e-09, + "loss": 0.2203, + "step": 3680 + }, + { + "epoch": 0.9530283901459972, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8297537977998952, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.2282119244337082, + "eval_runtime": 14.7193, + "eval_samples_per_second": 2.989, + "eval_steps_per_second": 0.136, + "step": 3680 + }, + { + "epoch": 0.9532873652520152, + "grad_norm": 3.9646986433077935, + "learning_rate": 8.261825242953658e-09, + "loss": 0.3663, + "step": 3681 + }, + { + "epoch": 0.9535463403580331, + "grad_norm": 3.140522571461789, + "learning_rate": 8.170482159272005e-09, + "loss": 0.2661, + "step": 3682 + }, + { + "epoch": 0.953805315464051, + "grad_norm": 2.9541415159565783, + "learning_rate": 8.079643510617852e-09, + "loss": 0.3071, + "step": 3683 + }, + { + "epoch": 0.9540642905700689, + "grad_norm": 3.498775149571394, + "learning_rate": 7.989309371277745e-09, + "loss": 0.3482, + "step": 3684 + }, + { + "epoch": 0.9543232656760869, + "grad_norm": 4.41473833769433, + "learning_rate": 7.899479815125718e-09, + "loss": 0.3149, + "step": 3685 + }, + { + "epoch": 0.9543232656760869, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8336825563122053, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22721882164478302, + "eval_runtime": 14.6839, + "eval_samples_per_second": 2.996, + "eval_steps_per_second": 0.136, + "step": 3685 + }, + { + "epoch": 0.9545822407821049, + "grad_norm": 2.7152741070471076, + "learning_rate": 7.810154915623286e-09, + "loss": 0.2517, + "step": 3686 + }, + { + "epoch": 0.9548412158881228, + "grad_norm": 5.0393714415819, + "learning_rate": 7.721334745819168e-09, + "loss": 0.3529, + "step": 3687 + }, + { + "epoch": 0.9551001909941407, + "grad_norm": 3.7219905765665886, + "learning_rate": 7.633019378349218e-09, + "loss": 0.3266, + "step": 3688 + }, + { + "epoch": 0.9553591661001586, + "grad_norm": 5.743693729861512, + "learning_rate": 7.545208885436778e-09, + "loss": 0.3422, + "step": 3689 + }, + { + "epoch": 0.9556181412061766, + "grad_norm": 3.810487918632539, + "learning_rate": 7.457903338891904e-09, + "loss": 0.2911, + "step": 3690 + }, + { + "epoch": 0.9556181412061766, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8315872184389733, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22763410210609436, + "eval_runtime": 14.337, + "eval_samples_per_second": 3.069, + "eval_steps_per_second": 0.139, + "step": 3690 + }, + { + "epoch": 0.9558771163121945, + "grad_norm": 4.172877753358404, + "learning_rate": 7.371102810111997e-09, + "loss": 0.317, + "step": 3691 + }, + { + "epoch": 0.9561360914182124, + "grad_norm": 4.925705148641474, + "learning_rate": 7.2848073700814565e-09, + "loss": 0.339, + "step": 3692 + }, + { + "epoch": 0.9563950665242303, + "grad_norm": 3.547438914577523, + "learning_rate": 7.199017089371402e-09, + "loss": 0.2954, + "step": 3693 + }, + { + "epoch": 0.9566540416302483, + "grad_norm": 5.762074302601659, + "learning_rate": 7.1137320381401555e-09, + "loss": 0.2298, + "step": 3694 + }, + { + "epoch": 0.9569130167362663, + "grad_norm": 3.280828522725003, + "learning_rate": 7.028952286132554e-09, + "loss": 0.3035, + "step": 3695 + }, + { + "epoch": 0.9569130167362663, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8357778941854374, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.2275650054216385, + "eval_runtime": 15.0644, + "eval_samples_per_second": 2.921, + "eval_steps_per_second": 0.133, + "step": 3695 + }, + { + "epoch": 0.9571719918422842, + "grad_norm": 3.0340223418938397, + "learning_rate": 6.944677902680428e-09, + "loss": 0.2715, + "step": 3696 + }, + { + "epoch": 0.9574309669483021, + "grad_norm": 3.3386098829540236, + "learning_rate": 6.860908956702328e-09, + "loss": 0.3203, + "step": 3697 + }, + { + "epoch": 0.95768994205432, + "grad_norm": 4.074998036867272, + "learning_rate": 6.777645516703249e-09, + "loss": 0.3399, + "step": 3698 + }, + { + "epoch": 0.9579489171603379, + "grad_norm": 6.771010689228516, + "learning_rate": 6.694887650775042e-09, + "loss": 0.4097, + "step": 3699 + }, + { + "epoch": 0.9582078922663559, + "grad_norm": 3.079360208487848, + "learning_rate": 6.612635426595931e-09, + "loss": 0.3141, + "step": 3700 + }, + { + "epoch": 0.9582078922663559, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8344683080146674, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.2266630232334137, + "eval_runtime": 14.5869, + "eval_samples_per_second": 3.016, + "eval_steps_per_second": 0.137, + "step": 3700 + }, + { + "epoch": 0.9584668673723739, + "grad_norm": 4.456097269209638, + "learning_rate": 6.530888911430722e-09, + "loss": 0.3924, + "step": 3701 + }, + { + "epoch": 0.9587258424783918, + "grad_norm": 3.7553526719156136, + "learning_rate": 6.44964817213066e-09, + "loss": 0.2914, + "step": 3702 + }, + { + "epoch": 0.9589848175844097, + "grad_norm": 5.505254793585942, + "learning_rate": 6.3689132751332264e-09, + "loss": 0.2897, + "step": 3703 + }, + { + "epoch": 0.9592437926904276, + "grad_norm": 3.7949148083013644, + "learning_rate": 6.288684286462551e-09, + "loss": 0.3231, + "step": 3704 + }, + { + "epoch": 0.9595027677964456, + "grad_norm": 2.599105743953544, + "learning_rate": 6.208961271728722e-09, + "loss": 0.2557, + "step": 3705 + }, + { + "epoch": 0.9595027677964456, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8342063907805135, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22650884091854095, + "eval_runtime": 14.5108, + "eval_samples_per_second": 3.032, + "eval_steps_per_second": 0.138, + "step": 3705 + }, + { + "epoch": 0.9597617429024635, + "grad_norm": 3.394154597985728, + "learning_rate": 6.1297442961281285e-09, + "loss": 0.2731, + "step": 3706 + }, + { + "epoch": 0.9600207180084814, + "grad_norm": 10.64117146668317, + "learning_rate": 6.051033424443464e-09, + "loss": 0.4123, + "step": 3707 + }, + { + "epoch": 0.9602796931144993, + "grad_norm": 6.07669549891729, + "learning_rate": 5.9728287210434474e-09, + "loss": 0.3431, + "step": 3708 + }, + { + "epoch": 0.9605386682205173, + "grad_norm": 3.264665085608003, + "learning_rate": 5.895130249882683e-09, + "loss": 0.2953, + "step": 3709 + }, + { + "epoch": 0.9607976433265353, + "grad_norm": 8.38842775323875, + "learning_rate": 5.81793807450208e-09, + "loss": 0.402, + "step": 3710 + }, + { + "epoch": 0.9607976433265353, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8342063907805134, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22796091437339783, + "eval_runtime": 14.8886, + "eval_samples_per_second": 2.955, + "eval_steps_per_second": 0.134, + "step": 3710 + }, + { + "epoch": 0.9610566184325532, + "grad_norm": 3.4071940350766674, + "learning_rate": 5.741252258028435e-09, + "loss": 0.323, + "step": 3711 + }, + { + "epoch": 0.9613155935385711, + "grad_norm": 3.571517818320127, + "learning_rate": 5.6650728631742896e-09, + "loss": 0.3433, + "step": 3712 + }, + { + "epoch": 0.961574568644589, + "grad_norm": 3.9394341298746456, + "learning_rate": 5.589399952238214e-09, + "loss": 0.366, + "step": 3713 + }, + { + "epoch": 0.9618335437506069, + "grad_norm": 3.281159472074768, + "learning_rate": 5.514233587104456e-09, + "loss": 0.3055, + "step": 3714 + }, + { + "epoch": 0.962092518856625, + "grad_norm": 5.729235677423284, + "learning_rate": 5.43957382924315e-09, + "loss": 0.2705, + "step": 3715 + }, + { + "epoch": 0.962092518856625, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8326348873755893, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22735975682735443, + "eval_runtime": 14.3659, + "eval_samples_per_second": 3.063, + "eval_steps_per_second": 0.139, + "step": 3715 + }, + { + "epoch": 0.9623514939626429, + "grad_norm": 3.0130755699795575, + "learning_rate": 5.365420739710039e-09, + "loss": 0.2444, + "step": 3716 + }, + { + "epoch": 0.9626104690686608, + "grad_norm": 3.183823040446827, + "learning_rate": 5.291774379146478e-09, + "loss": 0.3404, + "step": 3717 + }, + { + "epoch": 0.9628694441746787, + "grad_norm": 5.335522046586569, + "learning_rate": 5.218634807779496e-09, + "loss": 0.356, + "step": 3718 + }, + { + "epoch": 0.9631284192806966, + "grad_norm": 3.045649201648641, + "learning_rate": 5.146002085421667e-09, + "loss": 0.2646, + "step": 3719 + }, + { + "epoch": 0.9633873943867146, + "grad_norm": 3.405316814321279, + "learning_rate": 5.07387627147117e-09, + "loss": 0.3006, + "step": 3720 + }, + { + "epoch": 0.9633873943867146, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8336825563122054, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22643962502479553, + "eval_runtime": 14.5783, + "eval_samples_per_second": 3.018, + "eval_steps_per_second": 0.137, + "step": 3720 + }, + { + "epoch": 0.9636463694927325, + "grad_norm": 4.195197718854826, + "learning_rate": 5.00225742491145e-09, + "loss": 0.294, + "step": 3721 + }, + { + "epoch": 0.9639053445987504, + "grad_norm": 3.5452224151997456, + "learning_rate": 4.931145604311419e-09, + "loss": 0.316, + "step": 3722 + }, + { + "epoch": 0.9641643197047683, + "grad_norm": 3.957524446131255, + "learning_rate": 4.860540867825531e-09, + "loss": 0.3097, + "step": 3723 + }, + { + "epoch": 0.9644232948107863, + "grad_norm": 4.563974754994355, + "learning_rate": 4.790443273193293e-09, + "loss": 0.2524, + "step": 3724 + }, + { + "epoch": 0.9646822699168043, + "grad_norm": 7.280776733389496, + "learning_rate": 4.720852877739615e-09, + "loss": 0.328, + "step": 3725 + }, + { + "epoch": 0.9646822699168043, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8331587218438974, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22683392465114594, + "eval_runtime": 14.6242, + "eval_samples_per_second": 3.009, + "eval_steps_per_second": 0.137, + "step": 3725 + }, + { + "epoch": 0.9649412450228222, + "grad_norm": 4.4609944581138965, + "learning_rate": 4.651769738374598e-09, + "loss": 0.3757, + "step": 3726 + }, + { + "epoch": 0.9652002201288401, + "grad_norm": 4.760852219296557, + "learning_rate": 4.583193911593536e-09, + "loss": 0.3492, + "step": 3727 + }, + { + "epoch": 0.965459195234858, + "grad_norm": 3.509804003108367, + "learning_rate": 4.515125453476779e-09, + "loss": 0.2711, + "step": 3728 + }, + { + "epoch": 0.965718170340876, + "grad_norm": 3.2258563654692485, + "learning_rate": 4.447564419689868e-09, + "loss": 0.2726, + "step": 3729 + }, + { + "epoch": 0.965977145446894, + "grad_norm": 4.427505757522188, + "learning_rate": 4.380510865483328e-09, + "loss": 0.3936, + "step": 3730 + }, + { + "epoch": 0.965977145446894, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8328968046097434, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22673159837722778, + "eval_runtime": 14.5111, + "eval_samples_per_second": 3.032, + "eval_steps_per_second": 0.138, + "step": 3730 + }, + { + "epoch": 0.9662361205529119, + "grad_norm": 5.0158474266864035, + "learning_rate": 4.313964845692672e-09, + "loss": 0.4353, + "step": 3731 + }, + { + "epoch": 0.9664950956589298, + "grad_norm": 5.374006941640815, + "learning_rate": 4.247926414738326e-09, + "loss": 0.285, + "step": 3732 + }, + { + "epoch": 0.9667540707649477, + "grad_norm": 4.404456224426791, + "learning_rate": 4.182395626625702e-09, + "loss": 0.3099, + "step": 3733 + }, + { + "epoch": 0.9670130458709657, + "grad_norm": 3.652535138453535, + "learning_rate": 4.117372534944916e-09, + "loss": 0.3506, + "step": 3734 + }, + { + "epoch": 0.9672720209769836, + "grad_norm": 6.814473031283584, + "learning_rate": 4.052857192871074e-09, + "loss": 0.3143, + "step": 3735 + }, + { + "epoch": 0.9672720209769836, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8326348873755893, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22613172233104706, + "eval_runtime": 14.6059, + "eval_samples_per_second": 3.012, + "eval_steps_per_second": 0.137, + "step": 3735 + }, + { + "epoch": 0.9675309960830015, + "grad_norm": 4.202762943256565, + "learning_rate": 3.988849653163915e-09, + "loss": 0.3544, + "step": 3736 + }, + { + "epoch": 0.9677899711890194, + "grad_norm": 3.9810099537743717, + "learning_rate": 3.925349968167957e-09, + "loss": 0.2999, + "step": 3737 + }, + { + "epoch": 0.9680489462950373, + "grad_norm": 3.2665330073439858, + "learning_rate": 3.862358189812496e-09, + "loss": 0.2718, + "step": 3738 + }, + { + "epoch": 0.9683079214010554, + "grad_norm": 6.014518094227009, + "learning_rate": 3.7998743696112535e-09, + "loss": 0.2698, + "step": 3739 + }, + { + "epoch": 0.9685668965070733, + "grad_norm": 4.477211307322106, + "learning_rate": 3.737898558662731e-09, + "loss": 0.3943, + "step": 3740 + }, + { + "epoch": 0.9685668965070733, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8323729701414353, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.2278762012720108, + "eval_runtime": 14.3348, + "eval_samples_per_second": 3.069, + "eval_steps_per_second": 0.14, + "step": 3740 + }, + { + "epoch": 0.9688258716130912, + "grad_norm": 3.4812788985580743, + "learning_rate": 3.6764308076499972e-09, + "loss": 0.345, + "step": 3741 + }, + { + "epoch": 0.9690848467191091, + "grad_norm": 4.207006822777574, + "learning_rate": 3.6154711668404118e-09, + "loss": 0.3131, + "step": 3742 + }, + { + "epoch": 0.969343821825127, + "grad_norm": 3.687882801837316, + "learning_rate": 3.5550196860861114e-09, + "loss": 0.3012, + "step": 3743 + }, + { + "epoch": 0.969602796931145, + "grad_norm": 3.2237093873628635, + "learning_rate": 3.495076414823384e-09, + "loss": 0.2854, + "step": 3744 + }, + { + "epoch": 0.969861772037163, + "grad_norm": 3.555020493419626, + "learning_rate": 3.435641402073156e-09, + "loss": 0.3129, + "step": 3745 + }, + { + "epoch": 0.969861772037163, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8339444735463594, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22751933336257935, + "eval_runtime": 14.9947, + "eval_samples_per_second": 2.934, + "eval_steps_per_second": 0.133, + "step": 3745 + }, + { + "epoch": 0.9701207471431809, + "grad_norm": 3.1104580945588776, + "learning_rate": 3.376714696440575e-09, + "loss": 0.393, + "step": 3746 + }, + { + "epoch": 0.9703797222491988, + "grad_norm": 3.0005649157449192, + "learning_rate": 3.3182963461150798e-09, + "loss": 0.3341, + "step": 3747 + }, + { + "epoch": 0.9706386973552167, + "grad_norm": 4.636979262479428, + "learning_rate": 3.2603863988703995e-09, + "loss": 0.3275, + "step": 3748 + }, + { + "epoch": 0.9708976724612347, + "grad_norm": 4.161710816302581, + "learning_rate": 3.2029849020646237e-09, + "loss": 0.2648, + "step": 3749 + }, + { + "epoch": 0.9711566475672526, + "grad_norm": 7.525252717634673, + "learning_rate": 3.1460919026398555e-09, + "loss": 0.3553, + "step": 3750 + }, + { + "epoch": 0.9711566475672526, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8347302252488213, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22600655257701874, + "eval_runtime": 14.4939, + "eval_samples_per_second": 3.036, + "eval_steps_per_second": 0.138, + "step": 3750 + }, + { + "epoch": 0.9714156226732705, + "grad_norm": 2.9320847994639023, + "learning_rate": 3.089707447122489e-09, + "loss": 0.2556, + "step": 3751 + }, + { + "epoch": 0.9716745977792884, + "grad_norm": 3.3623826891926805, + "learning_rate": 3.0338315816229313e-09, + "loss": 0.3555, + "step": 3752 + }, + { + "epoch": 0.9719335728853064, + "grad_norm": 3.00191844900484, + "learning_rate": 2.978464351835811e-09, + "loss": 0.3261, + "step": 3753 + }, + { + "epoch": 0.9721925479913244, + "grad_norm": 3.151081764616473, + "learning_rate": 2.923605803039631e-09, + "loss": 0.2822, + "step": 3754 + }, + { + "epoch": 0.9724515230973423, + "grad_norm": 2.898759924831491, + "learning_rate": 2.8692559800970464e-09, + "loss": 0.2791, + "step": 3755 + }, + { + "epoch": 0.9724515230973423, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8336825563122054, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.2281143069267273, + "eval_runtime": 14.3427, + "eval_samples_per_second": 3.068, + "eval_steps_per_second": 0.139, + "step": 3755 + }, + { + "epoch": 0.9727104982033602, + "grad_norm": 5.261916492906041, + "learning_rate": 2.815414927454588e-09, + "loss": 0.3642, + "step": 3756 + }, + { + "epoch": 0.9729694733093781, + "grad_norm": 7.654674605231565, + "learning_rate": 2.7620826891427284e-09, + "loss": 0.3933, + "step": 3757 + }, + { + "epoch": 0.973228448415396, + "grad_norm": 2.950243791713008, + "learning_rate": 2.709259308775955e-09, + "loss": 0.3097, + "step": 3758 + }, + { + "epoch": 0.973487423521414, + "grad_norm": 2.8988696408898194, + "learning_rate": 2.6569448295524907e-09, + "loss": 0.2696, + "step": 3759 + }, + { + "epoch": 0.973746398627432, + "grad_norm": 4.0300610398540915, + "learning_rate": 2.6051392942543635e-09, + "loss": 0.2906, + "step": 3760 + }, + { + "epoch": 0.973746398627432, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8308014667365112, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.2276378571987152, + "eval_runtime": 14.4333, + "eval_samples_per_second": 3.049, + "eval_steps_per_second": 0.139, + "step": 3760 + }, + { + "epoch": 0.9740053737334499, + "grad_norm": 3.5572309917694094, + "learning_rate": 2.553842745247545e-09, + "loss": 0.3028, + "step": 3761 + }, + { + "epoch": 0.9742643488394678, + "grad_norm": 2.648093419725573, + "learning_rate": 2.5030552244816737e-09, + "loss": 0.2417, + "step": 3762 + }, + { + "epoch": 0.9745233239454857, + "grad_norm": 3.6428337799856525, + "learning_rate": 2.4527767734899844e-09, + "loss": 0.3488, + "step": 3763 + }, + { + "epoch": 0.9747822990515037, + "grad_norm": 3.9619057384524763, + "learning_rate": 2.4030074333897256e-09, + "loss": 0.3595, + "step": 3764 + }, + { + "epoch": 0.9750412741575216, + "grad_norm": 4.847054032559317, + "learning_rate": 2.353747244881466e-09, + "loss": 0.3012, + "step": 3765 + }, + { + "epoch": 0.9750412741575216, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8294918805657412, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22683225572109222, + "eval_runtime": 14.1507, + "eval_samples_per_second": 3.109, + "eval_steps_per_second": 0.141, + "step": 3765 + }, + { + "epoch": 0.9753002492635395, + "grad_norm": 2.9574261623983977, + "learning_rate": 2.3049962482495773e-09, + "loss": 0.3233, + "step": 3766 + }, + { + "epoch": 0.9755592243695574, + "grad_norm": 3.2277209530147064, + "learning_rate": 2.2567544833619616e-09, + "loss": 0.2596, + "step": 3767 + }, + { + "epoch": 0.9758181994755755, + "grad_norm": 3.493629270449725, + "learning_rate": 2.2090219896701153e-09, + "loss": 0.2415, + "step": 3768 + }, + { + "epoch": 0.9760771745815934, + "grad_norm": 5.43675057896812, + "learning_rate": 2.1617988062089953e-09, + "loss": 0.4408, + "step": 3769 + }, + { + "epoch": 0.9763361496876113, + "grad_norm": 3.5401517999956225, + "learning_rate": 2.1150849715972226e-09, + "loss": 0.3153, + "step": 3770 + }, + { + "epoch": 0.9763361496876113, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8355159769512834, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.2271132916212082, + "eval_runtime": 14.9537, + "eval_samples_per_second": 2.942, + "eval_steps_per_second": 0.134, + "step": 3770 + }, + { + "epoch": 0.9765951247936292, + "grad_norm": 4.609390580002042, + "learning_rate": 2.068880524036601e-09, + "loss": 0.3074, + "step": 3771 + }, + { + "epoch": 0.9768540998996471, + "grad_norm": 3.838724351318659, + "learning_rate": 2.0231855013126688e-09, + "loss": 0.2909, + "step": 3772 + }, + { + "epoch": 0.9771130750056651, + "grad_norm": 4.788558188607948, + "learning_rate": 1.9779999407940757e-09, + "loss": 0.3706, + "step": 3773 + }, + { + "epoch": 0.977372050111683, + "grad_norm": 4.017167634491476, + "learning_rate": 1.9333238794329996e-09, + "loss": 0.3114, + "step": 3774 + }, + { + "epoch": 0.977631025217701, + "grad_norm": 4.07888562081562, + "learning_rate": 1.889157353765006e-09, + "loss": 0.2142, + "step": 3775 + }, + { + "epoch": 0.977631025217701, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8344683080146673, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22764945030212402, + "eval_runtime": 14.3285, + "eval_samples_per_second": 3.071, + "eval_steps_per_second": 0.14, + "step": 3775 + }, + { + "epoch": 0.9778900003237189, + "grad_norm": 4.813240343450575, + "learning_rate": 1.8455003999088422e-09, + "loss": 0.2666, + "step": 3776 + }, + { + "epoch": 0.9781489754297368, + "grad_norm": 5.969145708907028, + "learning_rate": 1.802353053566644e-09, + "loss": 0.2992, + "step": 3777 + }, + { + "epoch": 0.9784079505357548, + "grad_norm": 3.1276215129346316, + "learning_rate": 1.7597153500235887e-09, + "loss": 0.2965, + "step": 3778 + }, + { + "epoch": 0.9786669256417727, + "grad_norm": 2.8367646584880064, + "learning_rate": 1.7175873241484509e-09, + "loss": 0.2677, + "step": 3779 + }, + { + "epoch": 0.9789259007477906, + "grad_norm": 3.613997421863165, + "learning_rate": 1.6759690103927694e-09, + "loss": 0.2568, + "step": 3780 + }, + { + "epoch": 0.9789259007477906, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8339444735463594, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22727273404598236, + "eval_runtime": 14.7671, + "eval_samples_per_second": 2.98, + "eval_steps_per_second": 0.135, + "step": 3780 + }, + { + "epoch": 0.9791848758538085, + "grad_norm": 3.1768749839991903, + "learning_rate": 1.6348604427916109e-09, + "loss": 0.2787, + "step": 3781 + }, + { + "epoch": 0.9794438509598264, + "grad_norm": 3.2120106928360026, + "learning_rate": 1.5942616549628754e-09, + "loss": 0.2456, + "step": 3782 + }, + { + "epoch": 0.9797028260658445, + "grad_norm": 4.1973769152624865, + "learning_rate": 1.5541726801078517e-09, + "loss": 0.3376, + "step": 3783 + }, + { + "epoch": 0.9799618011718624, + "grad_norm": 3.6737570040496847, + "learning_rate": 1.5145935510106624e-09, + "loss": 0.3491, + "step": 3784 + }, + { + "epoch": 0.9802207762778803, + "grad_norm": 5.38680653872221, + "learning_rate": 1.4755243000386804e-09, + "loss": 0.3061, + "step": 3785 + }, + { + "epoch": 0.9802207762778803, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8355159769512834, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22653593122959137, + "eval_runtime": 14.3727, + "eval_samples_per_second": 3.061, + "eval_steps_per_second": 0.139, + "step": 3785 + }, + { + "epoch": 0.9804797513838982, + "grad_norm": 3.7835316941078907, + "learning_rate": 1.4369649591421814e-09, + "loss": 0.367, + "step": 3786 + }, + { + "epoch": 0.9807387264899161, + "grad_norm": 3.344834933570689, + "learning_rate": 1.3989155598544828e-09, + "loss": 0.32, + "step": 3787 + }, + { + "epoch": 0.9809977015959341, + "grad_norm": 4.8682190984287335, + "learning_rate": 1.3613761332918058e-09, + "loss": 0.4202, + "step": 3788 + }, + { + "epoch": 0.981256676701952, + "grad_norm": 4.0554611275364, + "learning_rate": 1.3243467101535513e-09, + "loss": 0.2856, + "step": 3789 + }, + { + "epoch": 0.98151565180797, + "grad_norm": 3.3288311029913604, + "learning_rate": 1.2878273207218155e-09, + "loss": 0.3525, + "step": 3790 + }, + { + "epoch": 0.98151565180797, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8339444735463595, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.2278343290090561, + "eval_runtime": 15.1689, + "eval_samples_per_second": 2.901, + "eval_steps_per_second": 0.132, + "step": 3790 + }, + { + "epoch": 0.9817746269139879, + "grad_norm": 3.459587386891869, + "learning_rate": 1.2518179948616677e-09, + "loss": 0.3536, + "step": 3791 + }, + { + "epoch": 0.9820336020200058, + "grad_norm": 4.643758571881619, + "learning_rate": 1.2163187620210792e-09, + "loss": 0.3149, + "step": 3792 + }, + { + "epoch": 0.9822925771260238, + "grad_norm": 4.883486340237557, + "learning_rate": 1.1813296512307864e-09, + "loss": 0.3639, + "step": 3793 + }, + { + "epoch": 0.9825515522320417, + "grad_norm": 4.393586588908449, + "learning_rate": 1.1468506911045674e-09, + "loss": 0.3375, + "step": 3794 + }, + { + "epoch": 0.9828105273380596, + "grad_norm": 4.732433723411681, + "learning_rate": 1.1128819098386868e-09, + "loss": 0.3954, + "step": 3795 + }, + { + "epoch": 0.9828105273380596, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8342063907805134, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22779884934425354, + "eval_runtime": 14.2777, + "eval_samples_per_second": 3.082, + "eval_steps_per_second": 0.14, + "step": 3795 + }, + { + "epoch": 0.9830695024440775, + "grad_norm": 3.3725155309739288, + "learning_rate": 1.079423335212451e-09, + "loss": 0.3051, + "step": 3796 + }, + { + "epoch": 0.9833284775500954, + "grad_norm": 3.8223729504108035, + "learning_rate": 1.0464749945878622e-09, + "loss": 0.2497, + "step": 3797 + }, + { + "epoch": 0.9835874526561135, + "grad_norm": 6.151024812245598, + "learning_rate": 1.0140369149096164e-09, + "loss": 0.3414, + "step": 3798 + }, + { + "epoch": 0.9838464277621314, + "grad_norm": 3.3182062558343497, + "learning_rate": 9.82109122705105e-10, + "loss": 0.3497, + "step": 3799 + }, + { + "epoch": 0.9841054028681493, + "grad_norm": 3.288946257871186, + "learning_rate": 9.506916440845532e-10, + "loss": 0.2347, + "step": 3800 + }, + { + "epoch": 0.9841054028681493, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8334206390780514, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.2275124490261078, + "eval_runtime": 14.8795, + "eval_samples_per_second": 2.957, + "eval_steps_per_second": 0.134, + "step": 3800 + }, + { + "epoch": 0.9843643779741672, + "grad_norm": 5.791584606424794, + "learning_rate": 9.197845047406034e-10, + "loss": 0.2604, + "step": 3801 + }, + { + "epoch": 0.9846233530801851, + "grad_norm": 5.343549355531095, + "learning_rate": 8.893877299488707e-10, + "loss": 0.3209, + "step": 3802 + }, + { + "epoch": 0.9848823281862031, + "grad_norm": 5.275102932130712, + "learning_rate": 8.595013445673178e-10, + "loss": 0.2754, + "step": 3803 + }, + { + "epoch": 0.985141303292221, + "grad_norm": 3.05840143184376, + "learning_rate": 8.301253730367415e-10, + "loss": 0.2999, + "step": 3804 + }, + { + "epoch": 0.985400278398239, + "grad_norm": 3.412730369936823, + "learning_rate": 8.012598393802862e-10, + "loss": 0.3124, + "step": 3805 + }, + { + "epoch": 0.985400278398239, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8292299633315872, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22656263411045074, + "eval_runtime": 14.7188, + "eval_samples_per_second": 2.989, + "eval_steps_per_second": 0.136, + "step": 3805 + }, + { + "epoch": 0.9856592535042569, + "grad_norm": 4.1174842482325005, + "learning_rate": 7.729047672039302e-10, + "loss": 0.3096, + "step": 3806 + }, + { + "epoch": 0.9859182286102748, + "grad_norm": 3.5398067724955977, + "learning_rate": 7.450601796960693e-10, + "loss": 0.3457, + "step": 3807 + }, + { + "epoch": 0.9861772037162928, + "grad_norm": 3.5796836338468836, + "learning_rate": 7.177260996275165e-10, + "loss": 0.3503, + "step": 3808 + }, + { + "epoch": 0.9864361788223107, + "grad_norm": 4.1349858744830925, + "learning_rate": 6.909025493518489e-10, + "loss": 0.3274, + "step": 3809 + }, + { + "epoch": 0.9866951539283286, + "grad_norm": 5.545670996001833, + "learning_rate": 6.645895508049227e-10, + "loss": 0.3212, + "step": 3810 + }, + { + "epoch": 0.9866951539283286, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8347302252488213, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22643357515335083, + "eval_runtime": 14.3767, + "eval_samples_per_second": 3.06, + "eval_steps_per_second": 0.139, + "step": 3810 + }, + { + "epoch": 0.9869541290343465, + "grad_norm": 3.5861053308982878, + "learning_rate": 6.387871255052886e-10, + "loss": 0.2693, + "step": 3811 + }, + { + "epoch": 0.9872131041403646, + "grad_norm": 5.365354261520226, + "learning_rate": 6.134952945536371e-10, + "loss": 0.2981, + "step": 3812 + }, + { + "epoch": 0.9874720792463825, + "grad_norm": 2.92775771692027, + "learning_rate": 5.887140786334928e-10, + "loss": 0.2266, + "step": 3813 + }, + { + "epoch": 0.9877310543524004, + "grad_norm": 2.690765708543126, + "learning_rate": 5.644434980104501e-10, + "loss": 0.258, + "step": 3814 + }, + { + "epoch": 0.9879900294584183, + "grad_norm": 6.763959755676743, + "learning_rate": 5.406835725327298e-10, + "loss": 0.2936, + "step": 3815 + }, + { + "epoch": 0.9879900294584183, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8326348873755893, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.2280174195766449, + "eval_runtime": 14.9601, + "eval_samples_per_second": 2.941, + "eval_steps_per_second": 0.134, + "step": 3815 + }, + { + "epoch": 0.9882490045644362, + "grad_norm": 4.433695465586773, + "learning_rate": 5.174343216308996e-10, + "loss": 0.3677, + "step": 3816 + }, + { + "epoch": 0.9885079796704542, + "grad_norm": 6.509805211160363, + "learning_rate": 4.946957643178763e-10, + "loss": 0.3703, + "step": 3817 + }, + { + "epoch": 0.9887669547764721, + "grad_norm": 5.334204827112618, + "learning_rate": 4.72467919188993e-10, + "loss": 0.2354, + "step": 3818 + }, + { + "epoch": 0.98902592988249, + "grad_norm": 4.838284527515975, + "learning_rate": 4.507508044217929e-10, + "loss": 0.3443, + "step": 3819 + }, + { + "epoch": 0.989284904988508, + "grad_norm": 5.3529792741958895, + "learning_rate": 4.295444377763053e-10, + "loss": 0.3691, + "step": 3820 + }, + { + "epoch": 0.989284904988508, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8331587218438974, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22712968289852142, + "eval_runtime": 14.8632, + "eval_samples_per_second": 2.96, + "eval_steps_per_second": 0.135, + "step": 3820 + }, + { + "epoch": 0.9895438800945259, + "grad_norm": 4.7657055107525155, + "learning_rate": 4.088488365948384e-10, + "loss": 0.356, + "step": 3821 + }, + { + "epoch": 0.9898028552005439, + "grad_norm": 3.1438215994844505, + "learning_rate": 3.88664017801979e-10, + "loss": 0.3136, + "step": 3822 + }, + { + "epoch": 0.9900618303065618, + "grad_norm": 4.392969525615217, + "learning_rate": 3.6898999790452304e-10, + "loss": 0.3131, + "step": 3823 + }, + { + "epoch": 0.9903208054125797, + "grad_norm": 4.9359097835147825, + "learning_rate": 3.4982679299168376e-10, + "loss": 0.3199, + "step": 3824 + }, + { + "epoch": 0.9905797805185976, + "grad_norm": 3.3480551974054253, + "learning_rate": 3.3117441873488365e-10, + "loss": 0.2809, + "step": 3825 + }, + { + "epoch": 0.9905797805185976, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8336825563122053, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22777841985225677, + "eval_runtime": 14.4757, + "eval_samples_per_second": 3.04, + "eval_steps_per_second": 0.138, + "step": 3825 + }, + { + "epoch": 0.9908387556246155, + "grad_norm": 3.1112028748040705, + "learning_rate": 3.130328903878238e-10, + "loss": 0.3223, + "step": 3826 + }, + { + "epoch": 0.9910977307306336, + "grad_norm": 4.515051358563836, + "learning_rate": 2.9540222278627574e-10, + "loss": 0.3458, + "step": 3827 + }, + { + "epoch": 0.9913567058366515, + "grad_norm": 3.688031204242464, + "learning_rate": 2.7828243034849767e-10, + "loss": 0.3676, + "step": 3828 + }, + { + "epoch": 0.9916156809426694, + "grad_norm": 6.299857244292773, + "learning_rate": 2.616735270747489e-10, + "loss": 0.2734, + "step": 3829 + }, + { + "epoch": 0.9918746560486873, + "grad_norm": 2.7200752559752894, + "learning_rate": 2.4557552654763674e-10, + "loss": 0.263, + "step": 3830 + }, + { + "epoch": 0.9918746560486873, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8339444735463594, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22735093533992767, + "eval_runtime": 14.0768, + "eval_samples_per_second": 3.126, + "eval_steps_per_second": 0.142, + "step": 3830 + }, + { + "epoch": 0.9921336311547052, + "grad_norm": 3.4253653354400764, + "learning_rate": 2.2998844193190816e-10, + "loss": 0.2896, + "step": 3831 + }, + { + "epoch": 0.9923926062607232, + "grad_norm": 4.836729051087595, + "learning_rate": 2.1491228597438074e-10, + "loss": 0.3938, + "step": 3832 + }, + { + "epoch": 0.9926515813667411, + "grad_norm": 4.3835875472916905, + "learning_rate": 2.0034707100415052e-10, + "loss": 0.411, + "step": 3833 + }, + { + "epoch": 0.992910556472759, + "grad_norm": 4.030759305603927, + "learning_rate": 1.8629280893252276e-10, + "loss": 0.2884, + "step": 3834 + }, + { + "epoch": 0.993169531578777, + "grad_norm": 5.22701626735598, + "learning_rate": 1.727495112528732e-10, + "loss": 0.2528, + "step": 3835 + }, + { + "epoch": 0.993169531578777, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8378732320586695, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22664810717105865, + "eval_runtime": 14.7042, + "eval_samples_per_second": 2.992, + "eval_steps_per_second": 0.136, + "step": 3835 + }, + { + "epoch": 0.9934285066847949, + "grad_norm": 6.493532087510634, + "learning_rate": 1.597171890407173e-10, + "loss": 0.3467, + "step": 3836 + }, + { + "epoch": 0.9936874817908129, + "grad_norm": 3.767028127642761, + "learning_rate": 1.4719585295364102e-10, + "loss": 0.2771, + "step": 3837 + }, + { + "epoch": 0.9939464568968308, + "grad_norm": 4.368815822103052, + "learning_rate": 1.3518551323157825e-10, + "loss": 0.3366, + "step": 3838 + }, + { + "epoch": 0.9942054320028487, + "grad_norm": 3.8465277486450606, + "learning_rate": 1.2368617969632512e-10, + "loss": 0.3043, + "step": 3839 + }, + { + "epoch": 0.9944644071088666, + "grad_norm": 9.325157464249818, + "learning_rate": 1.1269786175188702e-10, + "loss": 0.3202, + "step": 3840 + }, + { + "epoch": 0.9944644071088666, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8313253012048193, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.2281055599451065, + "eval_runtime": 14.3631, + "eval_samples_per_second": 3.063, + "eval_steps_per_second": 0.139, + "step": 3840 + }, + { + "epoch": 0.9947233822148845, + "grad_norm": 5.641531180918843, + "learning_rate": 1.0222056838440908e-10, + "loss": 0.3469, + "step": 3841 + }, + { + "epoch": 0.9949823573209026, + "grad_norm": 4.101151977591374, + "learning_rate": 9.22543081620375e-11, + "loss": 0.29, + "step": 3842 + }, + { + "epoch": 0.9952413324269205, + "grad_norm": 4.891817142955838, + "learning_rate": 8.279908923505831e-11, + "loss": 0.32, + "step": 3843 + }, + { + "epoch": 0.9955003075329384, + "grad_norm": 7.535098460321248, + "learning_rate": 7.38549193358279e-11, + "loss": 0.3266, + "step": 3844 + }, + { + "epoch": 0.9957592826389563, + "grad_norm": 4.312420699285119, + "learning_rate": 6.54218057788425e-11, + "loss": 0.3664, + "step": 3845 + }, + { + "epoch": 0.9957592826389563, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8331587218438974, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22716383635997772, + "eval_runtime": 14.6696, + "eval_samples_per_second": 2.999, + "eval_steps_per_second": 0.136, + "step": 3845 + }, + { + "epoch": 0.9960182577449742, + "grad_norm": 4.741186844985929, + "learning_rate": 5.7499755460460605e-11, + "loss": 0.3828, + "step": 3846 + }, + { + "epoch": 0.9962772328509922, + "grad_norm": 3.4879528750383226, + "learning_rate": 5.008877485931929e-11, + "loss": 0.2539, + "step": 3847 + }, + { + "epoch": 0.9965362079570101, + "grad_norm": 5.232229838784004, + "learning_rate": 4.3188870035987264e-11, + "loss": 0.36, + "step": 3848 + }, + { + "epoch": 0.9967951830630281, + "grad_norm": 4.322538922475531, + "learning_rate": 3.680004663317305e-11, + "loss": 0.3159, + "step": 3849 + }, + { + "epoch": 0.997054158169046, + "grad_norm": 4.525830981996262, + "learning_rate": 3.092230987544742e-11, + "loss": 0.2828, + "step": 3850 + }, + { + "epoch": 0.997054158169046, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8342063907805135, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22756601870059967, + "eval_runtime": 14.18, + "eval_samples_per_second": 3.103, + "eval_steps_per_second": 0.141, + "step": 3850 + }, + { + "epoch": 0.997313133275064, + "grad_norm": 6.105729108580667, + "learning_rate": 2.5555664569659744e-11, + "loss": 0.3476, + "step": 3851 + }, + { + "epoch": 0.9975721083810819, + "grad_norm": 4.5474908436043595, + "learning_rate": 2.0700115104591022e-11, + "loss": 0.3325, + "step": 3852 + }, + { + "epoch": 0.9978310834870998, + "grad_norm": 4.071704000877237, + "learning_rate": 1.6355665450953907e-11, + "loss": 0.3664, + "step": 3853 + }, + { + "epoch": 0.9980900585931177, + "grad_norm": 3.9717802184138074, + "learning_rate": 1.2522319161600848e-11, + "loss": 0.2919, + "step": 3854 + }, + { + "epoch": 0.9983490336991356, + "grad_norm": 8.039000729858921, + "learning_rate": 9.200079371454729e-12, + "loss": 0.3699, + "step": 3855 + }, + { + "epoch": 0.9983490336991356, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8331587218438974, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22770334780216217, + "eval_runtime": 14.3208, + "eval_samples_per_second": 3.072, + "eval_steps_per_second": 0.14, + "step": 3855 + }, + { + "epoch": 0.9986080088051537, + "grad_norm": 4.902294905980206, + "learning_rate": 6.388948797370065e-12, + "loss": 0.3163, + "step": 3856 + }, + { + "epoch": 0.9988669839111716, + "grad_norm": 5.209523923474209, + "learning_rate": 4.0889297382024075e-12, + "loss": 0.3926, + "step": 3857 + }, + { + "epoch": 0.9991259590171895, + "grad_norm": 2.739620647333535, + "learning_rate": 2.300024074947116e-12, + "loss": 0.2317, + "step": 3858 + }, + { + "epoch": 0.9993849341232074, + "grad_norm": 3.361231885723997, + "learning_rate": 1.0222332705311921e-12, + "loss": 0.3661, + "step": 3859 + }, + { + "epoch": 0.9996439092292253, + "grad_norm": 3.6074290799983157, + "learning_rate": 2.5555836988266915e-13, + "loss": 0.3282, + "step": 3860 + }, + { + "epoch": 0.9996439092292253, + "eval_PRM Accuracy": 0.8773584905660378, + "eval_PRM F1": 0.9202453987730062, + "eval_PRM F1 AUC": 0.8431115767417497, + "eval_PRM F1 AUC (fixed)": 0.8313253012048193, + "eval_PRM F1 Neg": 0.7346938775510204, + "eval_PRM NPV": 0.6923076923076923, + "eval_PRM Precision": 0.9375, + "eval_PRM Recall": 0.9036144578313253, + "eval_PRM Specificty": 0.782608695652174, + "eval_loss": 0.22751803696155548, + "eval_runtime": 14.717, + "eval_samples_per_second": 2.99, + "eval_steps_per_second": 0.136, + "step": 3860 + }, + { + "epoch": 0.9999028843352433, + "grad_norm": 2.8710946206932113, + "learning_rate": 0.0, + "loss": 0.2203, + "step": 3861 } ], "logging_steps": 1, @@ -31238,12 +40189,12 @@ "should_evaluate": false, "should_log": false, "should_save": true, - "should_training_stop": false + "should_training_stop": true }, "attributes": {} } }, - "total_flos": 253587145543680.0, + "total_flos": 326368491245568.0, "train_batch_size": 2, "trial_name": null, "trial_params": null