| { | |
| "best_metric": 0.81132042094234, | |
| "best_model_checkpoint": "result/dfm-sentence-encoder-medium-v4", | |
| "epoch": 1.0, | |
| "global_step": 49345, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 9.89867261120681e-06, | |
| "loss": 0.551, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_avg_sts": 0.7288716035836427, | |
| "eval_sickr_spearman": 0.6917684187734319, | |
| "eval_stsb_spearman": 0.7659747883938535, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.797345222413618e-06, | |
| "loss": 0.4721, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_avg_sts": 0.7351199653659765, | |
| "eval_sickr_spearman": 0.6964072145192234, | |
| "eval_stsb_spearman": 0.7738327162127295, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 9.696017833620428e-06, | |
| "loss": 0.4607, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_avg_sts": 0.7423278666926523, | |
| "eval_sickr_spearman": 0.6978035266691308, | |
| "eval_stsb_spearman": 0.7868522067161736, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 9.594690444827237e-06, | |
| "loss": 0.4586, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_avg_sts": 0.7441749546870178, | |
| "eval_sickr_spearman": 0.6987989232153342, | |
| "eval_stsb_spearman": 0.7895509861587012, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.493363056034047e-06, | |
| "loss": 0.4627, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_avg_sts": 0.7445984460802536, | |
| "eval_sickr_spearman": 0.69917351777545, | |
| "eval_stsb_spearman": 0.7900233743850572, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.392035667240856e-06, | |
| "loss": 0.4686, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_avg_sts": 0.7510002108817091, | |
| "eval_sickr_spearman": 0.7075781920294968, | |
| "eval_stsb_spearman": 0.7944222297339215, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.290708278447666e-06, | |
| "loss": 0.4686, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_avg_sts": 0.7477270819237568, | |
| "eval_sickr_spearman": 0.7019111464641181, | |
| "eval_stsb_spearman": 0.7935430173833955, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 9.189380889654475e-06, | |
| "loss": 0.454, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_avg_sts": 0.7419612954851657, | |
| "eval_sickr_spearman": 0.6941440850816625, | |
| "eval_stsb_spearman": 0.7897785058886688, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.088053500861283e-06, | |
| "loss": 0.4649, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_avg_sts": 0.7418233576604656, | |
| "eval_sickr_spearman": 0.6867260657133575, | |
| "eval_stsb_spearman": 0.7969206496075738, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 8.986726112068093e-06, | |
| "loss": 0.467, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_avg_sts": 0.7446135457895653, | |
| "eval_sickr_spearman": 0.6906753269669034, | |
| "eval_stsb_spearman": 0.7985517646122272, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 8.885398723274902e-06, | |
| "loss": 0.468, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_avg_sts": 0.7410856251082112, | |
| "eval_sickr_spearman": 0.6825309332515498, | |
| "eval_stsb_spearman": 0.7996403169648725, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 8.78407133448171e-06, | |
| "loss": 0.4614, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_avg_sts": 0.7509672954480082, | |
| "eval_sickr_spearman": 0.6987787501527303, | |
| "eval_stsb_spearman": 0.8031558407432862, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 8.68274394568852e-06, | |
| "loss": 0.4596, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_avg_sts": 0.7500520514398668, | |
| "eval_sickr_spearman": 0.6982613591280389, | |
| "eval_stsb_spearman": 0.8018427437516946, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 8.58141655689533e-06, | |
| "loss": 0.4494, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_avg_sts": 0.741497727059482, | |
| "eval_sickr_spearman": 0.6884413524079153, | |
| "eval_stsb_spearman": 0.7945541017110487, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 8.480089168102139e-06, | |
| "loss": 0.4535, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_avg_sts": 0.7464036949270956, | |
| "eval_sickr_spearman": 0.696571288761736, | |
| "eval_stsb_spearman": 0.796236101092455, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 8.378761779308948e-06, | |
| "loss": 0.452, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_avg_sts": 0.7481634305513074, | |
| "eval_sickr_spearman": 0.6957231555725417, | |
| "eval_stsb_spearman": 0.8006037055300731, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 8.277434390515758e-06, | |
| "loss": 0.4627, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_avg_sts": 0.7469738693319797, | |
| "eval_sickr_spearman": 0.6922042529878814, | |
| "eval_stsb_spearman": 0.8017434856760781, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 8.176107001722566e-06, | |
| "loss": 0.4579, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_avg_sts": 0.7445587366747802, | |
| "eval_sickr_spearman": 0.689870373737902, | |
| "eval_stsb_spearman": 0.7992470996116584, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 8.074779612929375e-06, | |
| "loss": 0.4631, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_avg_sts": 0.7415088027050005, | |
| "eval_sickr_spearman": 0.6845037627120188, | |
| "eval_stsb_spearman": 0.7985138426979821, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 7.973452224136185e-06, | |
| "loss": 0.4584, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_avg_sts": 0.7471105530073405, | |
| "eval_sickr_spearman": 0.6933327917472712, | |
| "eval_stsb_spearman": 0.8008883142674098, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 7.872124835342994e-06, | |
| "loss": 0.4589, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_avg_sts": 0.745595984233087, | |
| "eval_sickr_spearman": 0.6923495470697317, | |
| "eval_stsb_spearman": 0.7988424213964425, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 7.770797446549802e-06, | |
| "loss": 0.4587, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_avg_sts": 0.7466024940300805, | |
| "eval_sickr_spearman": 0.692575533401998, | |
| "eval_stsb_spearman": 0.800629454658163, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 7.669470057756611e-06, | |
| "loss": 0.4661, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_avg_sts": 0.7517425175405497, | |
| "eval_sickr_spearman": 0.6975225927568193, | |
| "eval_stsb_spearman": 0.8059624423242799, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 7.568142668963422e-06, | |
| "loss": 0.4621, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_avg_sts": 0.7477990028501873, | |
| "eval_sickr_spearman": 0.6881468256938967, | |
| "eval_stsb_spearman": 0.8074511800064779, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 7.466815280170231e-06, | |
| "loss": 0.4572, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_avg_sts": 0.7490645066698164, | |
| "eval_sickr_spearman": 0.690311203186901, | |
| "eval_stsb_spearman": 0.8078178101527318, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 7.36548789137704e-06, | |
| "loss": 0.4505, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_avg_sts": 0.7488632831459506, | |
| "eval_sickr_spearman": 0.6918468535620804, | |
| "eval_stsb_spearman": 0.8058797127298208, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 7.264160502583849e-06, | |
| "loss": 0.4587, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_avg_sts": 0.7492004417544827, | |
| "eval_sickr_spearman": 0.6910344555123561, | |
| "eval_stsb_spearman": 0.8073664279966094, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 7.162833113790658e-06, | |
| "loss": 0.4567, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_avg_sts": 0.7515448270625236, | |
| "eval_sickr_spearman": 0.6936582024595145, | |
| "eval_stsb_spearman": 0.8094314516655328, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 7.061505724997467e-06, | |
| "loss": 0.4543, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_avg_sts": 0.7513387605617963, | |
| "eval_sickr_spearman": 0.6940377922541799, | |
| "eval_stsb_spearman": 0.8086397288694127, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 6.9601783362042765e-06, | |
| "loss": 0.4523, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_avg_sts": 0.7500897857354842, | |
| "eval_sickr_spearman": 0.6939183389049033, | |
| "eval_stsb_spearman": 0.8062612325660653, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 6.858850947411085e-06, | |
| "loss": 0.4564, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_avg_sts": 0.7472002180219787, | |
| "eval_sickr_spearman": 0.6905755663692164, | |
| "eval_stsb_spearman": 0.803824869674741, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 6.757523558617895e-06, | |
| "loss": 0.4646, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_avg_sts": 0.7507948330729827, | |
| "eval_sickr_spearman": 0.6941705502185548, | |
| "eval_stsb_spearman": 0.8074191159274106, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 6.656196169824705e-06, | |
| "loss": 0.4492, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_avg_sts": 0.7529879565790001, | |
| "eval_sickr_spearman": 0.6971369030122712, | |
| "eval_stsb_spearman": 0.8088390101457289, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 6.554868781031514e-06, | |
| "loss": 0.4575, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_avg_sts": 0.7518569042679815, | |
| "eval_sickr_spearman": 0.6972905545057717, | |
| "eval_stsb_spearman": 0.8064232540301913, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 6.453541392238322e-06, | |
| "loss": 0.4637, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_avg_sts": 0.7498519912345287, | |
| "eval_sickr_spearman": 0.6938069547806683, | |
| "eval_stsb_spearman": 0.8058970276883892, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 6.352214003445132e-06, | |
| "loss": 0.4583, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_avg_sts": 0.7516061405002821, | |
| "eval_sickr_spearman": 0.6938626708583365, | |
| "eval_stsb_spearman": 0.8093496101422275, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 6.250886614651941e-06, | |
| "loss": 0.4645, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_avg_sts": 0.7534092039150044, | |
| "eval_sickr_spearman": 0.6986008429530034, | |
| "eval_stsb_spearman": 0.8082175648770055, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 6.14955922585875e-06, | |
| "loss": 0.4525, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_avg_sts": 0.7495273023794997, | |
| "eval_sickr_spearman": 0.6942551329881874, | |
| "eval_stsb_spearman": 0.8047994717708119, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 6.048231837065559e-06, | |
| "loss": 0.4616, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_avg_sts": 0.7498676062871128, | |
| "eval_sickr_spearman": 0.6946699295802069, | |
| "eval_stsb_spearman": 0.8050652829940186, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 5.946904448272368e-06, | |
| "loss": 0.4607, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_avg_sts": 0.7500055698075132, | |
| "eval_sickr_spearman": 0.6939670904728629, | |
| "eval_stsb_spearman": 0.8060440491421634, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 5.845577059479177e-06, | |
| "loss": 0.4548, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_avg_sts": 0.7494506896871379, | |
| "eval_sickr_spearman": 0.6917624148857522, | |
| "eval_stsb_spearman": 0.8071389644885236, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 5.744249670685987e-06, | |
| "loss": 0.4596, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_avg_sts": 0.7491829900995786, | |
| "eval_sickr_spearman": 0.6914101067567036, | |
| "eval_stsb_spearman": 0.8069558734424537, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 5.642922281892796e-06, | |
| "loss": 0.4484, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_avg_sts": 0.7496264233935017, | |
| "eval_sickr_spearman": 0.692096231040747, | |
| "eval_stsb_spearman": 0.8071566157462565, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 5.541594893099606e-06, | |
| "loss": 0.4604, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_avg_sts": 0.7475317779125041, | |
| "eval_sickr_spearman": 0.6897084608949542, | |
| "eval_stsb_spearman": 0.8053550949300541, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 5.440267504306414e-06, | |
| "loss": 0.4661, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_avg_sts": 0.749782311685921, | |
| "eval_sickr_spearman": 0.6907351256881937, | |
| "eval_stsb_spearman": 0.8088294976836483, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 5.338940115513224e-06, | |
| "loss": 0.4629, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_avg_sts": 0.7493434059552446, | |
| "eval_sickr_spearman": 0.6895577873297428, | |
| "eval_stsb_spearman": 0.8091290245807464, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 5.2376127267200325e-06, | |
| "loss": 0.46, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_avg_sts": 0.7494797845962304, | |
| "eval_sickr_spearman": 0.6888344389420848, | |
| "eval_stsb_spearman": 0.810125130250376, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 5.136285337926842e-06, | |
| "loss": 0.457, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_avg_sts": 0.7481539489426248, | |
| "eval_sickr_spearman": 0.6876096938865144, | |
| "eval_stsb_spearman": 0.808698203998735, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 5.034957949133651e-06, | |
| "loss": 0.4591, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_avg_sts": 0.7487851537577938, | |
| "eval_sickr_spearman": 0.6880744428240295, | |
| "eval_stsb_spearman": 0.809495864691558, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 4.93363056034046e-06, | |
| "loss": 0.4595, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_avg_sts": 0.749808924875282, | |
| "eval_sickr_spearman": 0.6898596147711799, | |
| "eval_stsb_spearman": 0.8097582349793842, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 4.83230317154727e-06, | |
| "loss": 0.4623, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_avg_sts": 0.7498742734395706, | |
| "eval_sickr_spearman": 0.6910954550111825, | |
| "eval_stsb_spearman": 0.8086530918679586, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 4.730975782754078e-06, | |
| "loss": 0.461, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_avg_sts": 0.74840720780684, | |
| "eval_sickr_spearman": 0.6880080158107407, | |
| "eval_stsb_spearman": 0.8088063998029394, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.629648393960888e-06, | |
| "loss": 0.4602, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_avg_sts": 0.7495470437599494, | |
| "eval_sickr_spearman": 0.6893540874285438, | |
| "eval_stsb_spearman": 0.8097400000913552, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.5283210051676975e-06, | |
| "loss": 0.4494, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_avg_sts": 0.7498239634592918, | |
| "eval_sickr_spearman": 0.6894677290145463, | |
| "eval_stsb_spearman": 0.8101801979040372, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.426993616374506e-06, | |
| "loss": 0.4621, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_avg_sts": 0.751903069869123, | |
| "eval_sickr_spearman": 0.692736149405207, | |
| "eval_stsb_spearman": 0.8110699903330391, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.325666227581316e-06, | |
| "loss": 0.4589, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_avg_sts": 0.7525324676455694, | |
| "eval_sickr_spearman": 0.6937445143487988, | |
| "eval_stsb_spearman": 0.81132042094234, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.224338838788124e-06, | |
| "loss": 0.4627, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_avg_sts": 0.7538511183199736, | |
| "eval_sickr_spearman": 0.696754047102708, | |
| "eval_stsb_spearman": 0.8109481895372391, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.123011449994934e-06, | |
| "loss": 0.4564, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_avg_sts": 0.7515831116726858, | |
| "eval_sickr_spearman": 0.6939315954889002, | |
| "eval_stsb_spearman": 0.8092346278564714, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.021684061201743e-06, | |
| "loss": 0.455, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_avg_sts": 0.7533852057891757, | |
| "eval_sickr_spearman": 0.6955959692159336, | |
| "eval_stsb_spearman": 0.8111744423624179, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 3.920356672408552e-06, | |
| "loss": 0.4632, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_avg_sts": 0.7518159970200462, | |
| "eval_sickr_spearman": 0.6946737720683219, | |
| "eval_stsb_spearman": 0.8089582219717706, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.819029283615362e-06, | |
| "loss": 0.4611, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_avg_sts": 0.7533598766129962, | |
| "eval_sickr_spearman": 0.6974833513469443, | |
| "eval_stsb_spearman": 0.8092364018790481, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.7177018948221703e-06, | |
| "loss": 0.4534, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_avg_sts": 0.7526633199575018, | |
| "eval_sickr_spearman": 0.6965692714554756, | |
| "eval_stsb_spearman": 0.808757368459528, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.6163745060289802e-06, | |
| "loss": 0.449, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_avg_sts": 0.7523877050131327, | |
| "eval_sickr_spearman": 0.6958016383922917, | |
| "eval_stsb_spearman": 0.8089737716339735, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.5150471172357893e-06, | |
| "loss": 0.4634, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_avg_sts": 0.7514477132225694, | |
| "eval_sickr_spearman": 0.6954868425534663, | |
| "eval_stsb_spearman": 0.8074085838916726, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 3.4137197284425984e-06, | |
| "loss": 0.4598, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_avg_sts": 0.7515196489317053, | |
| "eval_sickr_spearman": 0.697347375298773, | |
| "eval_stsb_spearman": 0.8056919225646377, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.312392339649407e-06, | |
| "loss": 0.4499, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_avg_sts": 0.7531240484791469, | |
| "eval_sickr_spearman": 0.7002055620520509, | |
| "eval_stsb_spearman": 0.806042534906243, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 3.211064950856217e-06, | |
| "loss": 0.4618, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_avg_sts": 0.7543101399622849, | |
| "eval_sickr_spearman": 0.701310901789446, | |
| "eval_stsb_spearman": 0.8073093781351238, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 3.109737562063026e-06, | |
| "loss": 0.4622, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_avg_sts": 0.7535012273240942, | |
| "eval_sickr_spearman": 0.6987900374615681, | |
| "eval_stsb_spearman": 0.8082124171866202, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 3.0084101732698353e-06, | |
| "loss": 0.4654, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_avg_sts": 0.7528923913364809, | |
| "eval_sickr_spearman": 0.698313232717592, | |
| "eval_stsb_spearman": 0.8074715499553696, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 2.907082784476644e-06, | |
| "loss": 0.4577, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_avg_sts": 0.7508251788488477, | |
| "eval_sickr_spearman": 0.6952676286065028, | |
| "eval_stsb_spearman": 0.8063827290911926, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 2.805755395683453e-06, | |
| "loss": 0.4506, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_avg_sts": 0.7509892106103371, | |
| "eval_sickr_spearman": 0.6953001456621763, | |
| "eval_stsb_spearman": 0.8066782755584977, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 2.704428006890263e-06, | |
| "loss": 0.4613, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_avg_sts": 0.7503441697836055, | |
| "eval_sickr_spearman": 0.6956849228157971, | |
| "eval_stsb_spearman": 0.8050034167514141, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 2.603100618097072e-06, | |
| "loss": 0.4639, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_avg_sts": 0.7496733652176951, | |
| "eval_sickr_spearman": 0.6941632014600347, | |
| "eval_stsb_spearman": 0.8051835289753555, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 2.501773229303881e-06, | |
| "loss": 0.4637, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_avg_sts": 0.7492569767417572, | |
| "eval_sickr_spearman": 0.6940407221513675, | |
| "eval_stsb_spearman": 0.8044732313321468, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 2.4004458405106903e-06, | |
| "loss": 0.4523, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_avg_sts": 0.7480946141530285, | |
| "eval_sickr_spearman": 0.6926867254018273, | |
| "eval_stsb_spearman": 0.8035025029042295, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 2.2991184517174994e-06, | |
| "loss": 0.4547, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_avg_sts": 0.7484090650166574, | |
| "eval_sickr_spearman": 0.6932337035850045, | |
| "eval_stsb_spearman": 0.8035844264483103, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 2.1977910629243085e-06, | |
| "loss": 0.4598, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "eval_avg_sts": 0.7474650473627502, | |
| "eval_sickr_spearman": 0.6918610707681061, | |
| "eval_stsb_spearman": 0.8030690239573942, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 2.0964636741311176e-06, | |
| "loss": 0.4601, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_avg_sts": 0.7474876355051218, | |
| "eval_sickr_spearman": 0.6911482411916631, | |
| "eval_stsb_spearman": 0.8038270298185805, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.9951362853379267e-06, | |
| "loss": 0.4582, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_avg_sts": 0.749122521812451, | |
| "eval_sickr_spearman": 0.6930461587670631, | |
| "eval_stsb_spearman": 0.8051988848578389, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.8938088965447363e-06, | |
| "loss": 0.4589, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_avg_sts": 0.747485970375817, | |
| "eval_sickr_spearman": 0.6916881107718275, | |
| "eval_stsb_spearman": 0.8032838299798064, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 1.7924815077515454e-06, | |
| "loss": 0.4494, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_avg_sts": 0.7484522252119146, | |
| "eval_sickr_spearman": 0.6921244733283927, | |
| "eval_stsb_spearman": 0.8047799770954366, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 1.6911541189583547e-06, | |
| "loss": 0.4692, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_avg_sts": 0.7489686533203876, | |
| "eval_sickr_spearman": 0.6921774036021774, | |
| "eval_stsb_spearman": 0.8057599030385979, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 1.5898267301651638e-06, | |
| "loss": 0.4512, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_avg_sts": 0.7486704913862867, | |
| "eval_sickr_spearman": 0.6929249596649603, | |
| "eval_stsb_spearman": 0.8044160231076133, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 1.4884993413719729e-06, | |
| "loss": 0.4569, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_avg_sts": 0.7481669304082241, | |
| "eval_sickr_spearman": 0.691963905356285, | |
| "eval_stsb_spearman": 0.8043699554601632, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 1.3871719525787822e-06, | |
| "loss": 0.4543, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "eval_avg_sts": 0.7481576956303677, | |
| "eval_sickr_spearman": 0.6925726515359116, | |
| "eval_stsb_spearman": 0.8037427397248238, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 1.2858445637855913e-06, | |
| "loss": 0.4556, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "eval_avg_sts": 0.7478866338195715, | |
| "eval_sickr_spearman": 0.6912525647439866, | |
| "eval_stsb_spearman": 0.8045207028951564, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 1.1845171749924006e-06, | |
| "loss": 0.4593, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_avg_sts": 0.7482308793293835, | |
| "eval_sickr_spearman": 0.6917689951466491, | |
| "eval_stsb_spearman": 0.8046927635121179, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 1.0831897861992097e-06, | |
| "loss": 0.4578, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "eval_avg_sts": 0.7487411634362362, | |
| "eval_sickr_spearman": 0.6923790381660146, | |
| "eval_stsb_spearman": 0.8051032887064578, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 9.818623974060188e-07, | |
| "loss": 0.4617, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_avg_sts": 0.7495089794416554, | |
| "eval_sickr_spearman": 0.6935791912976488, | |
| "eval_stsb_spearman": 0.8054387675856621, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 8.80535008612828e-07, | |
| "loss": 0.4534, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "eval_avg_sts": 0.7495111256181921, | |
| "eval_sickr_spearman": 0.6928939315734312, | |
| "eval_stsb_spearman": 0.806128319662953, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 7.792076198196374e-07, | |
| "loss": 0.4546, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "eval_avg_sts": 0.748989011722548, | |
| "eval_sickr_spearman": 0.6924577611412717, | |
| "eval_stsb_spearman": 0.8055202623038241, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 6.778802310264466e-07, | |
| "loss": 0.4613, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_avg_sts": 0.7489659458032893, | |
| "eval_sickr_spearman": 0.6927594444894045, | |
| "eval_stsb_spearman": 0.8051724471171742, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 5.765528422332558e-07, | |
| "loss": 0.4594, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_avg_sts": 0.7486440766299414, | |
| "eval_sickr_spearman": 0.6924414305667828, | |
| "eval_stsb_spearman": 0.8048467226930999, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 4.752254534400649e-07, | |
| "loss": 0.4584, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "eval_avg_sts": 0.7490758878100736, | |
| "eval_sickr_spearman": 0.6929523854238814, | |
| "eval_stsb_spearman": 0.805199390196266, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 3.738980646468741e-07, | |
| "loss": 0.4496, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_avg_sts": 0.7489021602575776, | |
| "eval_sickr_spearman": 0.6924429195309273, | |
| "eval_stsb_spearman": 0.8053614009842279, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 2.725706758536833e-07, | |
| "loss": 0.4521, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_avg_sts": 0.7486292878627302, | |
| "eval_sickr_spearman": 0.6919387850902329, | |
| "eval_stsb_spearman": 0.8053197906352275, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 1.7124328706049245e-07, | |
| "loss": 0.4618, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "eval_avg_sts": 0.7487302574375756, | |
| "eval_sickr_spearman": 0.6921317740558113, | |
| "eval_stsb_spearman": 0.80532874081934, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 6.991589826730166e-08, | |
| "loss": 0.4501, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_avg_sts": 0.748655762950658, | |
| "eval_sickr_spearman": 0.6920557408222348, | |
| "eval_stsb_spearman": 0.8052557850790812, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 49345, | |
| "train_runtime": 47384.4879, | |
| "train_samples_per_second": 1.041 | |
| } | |
| ], | |
| "max_steps": 49345, | |
| "num_train_epochs": 1, | |
| "total_flos": 1976154204533723136, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |