Training in progress, step 200

checkpoint-1600/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6761a96f04a5d144ad5d0d1ab485d43821b19b46c9d6286724902d1c41c4313
+oid sha256:227ed66293bdd92a98aef33e2bea6e0cf714b5f3de2221070e85c0fd928b6de6
 size 1762416361

checkpoint-1600/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:454b5dc90f671b802f85ebdc3659a415c2e5c4fa951d2545a102c97fb2cc9744
+oid sha256:6554b9968a07507c9ad3a7768e4bf306b17d8dc60069999b186a9c02dd47c9dd
 size 440628841

checkpoint-1600/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c96f06838e7ed125bc66cd3258abcf5211608962ce711b5854cc010d4f3f765
+oid sha256:f308c18e470c73b6a08f647ea7fbf34e8681f5877eba1262e1d03e5323d4a478
 size 623

checkpoint-1600/trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.923051948051948,
-  "best_model_checkpoint": "mpnet-metric/checkpoint-1600",
+  "best_metric": 0.9282467532467532,
+  "best_model_checkpoint": "mpnet-metric/checkpoint-1400",
   "epoch": 36.36363636363637,
   "global_step": 1600,
   "is_hyper_param_search": false,
@@ -9,196 +9,196 @@
   "log_history": [
     {
       "epoch": 2.27,
-      "eval_accuracy": 0.811038961038961,
-      "eval_f1": 0.7439023537501395,
-      "eval_loss": 1.5588715076446533,
-      "eval_matthews_correlation": 0.8092922570286504,
-      "eval_runtime": 2.19,
-      "eval_samples_per_second": 1406.404,
-      "eval_steps_per_second": 9.132,
+      "eval_accuracy": 0.8194805194805195,
+      "eval_f1": 0.7656701166780793,
+      "eval_loss": 1.9282063245773315,
+      "eval_matthews_correlation": 0.8177401806097793,
+      "eval_runtime": 2.1248,
+      "eval_samples_per_second": 1449.542,
+      "eval_steps_per_second": 9.413,
       "step": 100
     },
     {
       "epoch": 4.55,
-      "eval_accuracy": 0.9022727272727272,
-      "eval_f1": 0.8954269843626451,
-      "eval_loss": 1.4355967044830322,
-      "eval_matthews_correlation": 0.9009908755361663,
-      "eval_runtime": 2.1598,
-      "eval_samples_per_second": 1426.032,
-      "eval_steps_per_second": 9.26,
+      "eval_accuracy": 0.8603896103896104,
+      "eval_f1": 0.8221385737164676,
+      "eval_loss": 1.785994529724121,
+      "eval_matthews_correlation": 0.8588446795045349,
+      "eval_runtime": 2.1571,
+      "eval_samples_per_second": 1427.834,
+      "eval_steps_per_second": 9.272,
       "step": 200
     },
     {
       "epoch": 6.82,
-      "eval_accuracy": 0.9087662337662338,
-      "eval_f1": 0.9085810469063416,
-      "eval_loss": 1.4876813888549805,
-      "eval_matthews_correlation": 0.9075986799590098,
-      "eval_runtime": 2.5367,
-      "eval_samples_per_second": 1214.181,
-      "eval_steps_per_second": 7.884,
+      "eval_accuracy": 0.8831168831168831,
+      "eval_f1": 0.8503152420049573,
+      "eval_loss": 1.703816533088684,
+      "eval_matthews_correlation": 0.8817033568232515,
+      "eval_runtime": 2.2955,
+      "eval_samples_per_second": 1341.777,
+      "eval_steps_per_second": 8.713,
       "step": 300
     },
     {
       "epoch": 9.09,
-      "eval_accuracy": 0.9211038961038961,
-      "eval_f1": 0.9201538821364931,
-      "eval_loss": 1.5697877407073975,
-      "eval_matthews_correlation": 0.9200518104822324,
-      "eval_runtime": 2.1855,
-      "eval_samples_per_second": 1409.265,
-      "eval_steps_per_second": 9.151,
+      "eval_accuracy": 0.8948051948051948,
+      "eval_f1": 0.8658511061420076,
+      "eval_loss": 1.5578949451446533,
+      "eval_matthews_correlation": 0.893469940479661,
+      "eval_runtime": 2.1159,
+      "eval_samples_per_second": 1455.648,
+      "eval_steps_per_second": 9.452,
       "step": 400
     },
     {
       "epoch": 11.36,
-      "learning_rate": 4.966670829549896e-05,
-      "loss": 1.1589,
+      "learning_rate": 2.91576008814464e-05,
+      "loss": 1.3674,
       "step": 500
     },
     {
       "epoch": 11.36,
-      "eval_accuracy": 0.9136363636363637,
-      "eval_f1": 0.9151636464610898,
-      "eval_loss": 1.5979810953140259,
-      "eval_matthews_correlation": 0.9124994144840757,
-      "eval_runtime": 2.0901,
-      "eval_samples_per_second": 1473.643,
-      "eval_steps_per_second": 9.569,
+      "eval_accuracy": 0.9084415584415585,
+      "eval_f1": 0.8884952022189863,
+      "eval_loss": 1.6358195543289185,
+      "eval_matthews_correlation": 0.9072261203467101,
+      "eval_runtime": 2.0369,
+      "eval_samples_per_second": 1512.102,
+      "eval_steps_per_second": 9.819,
       "step": 500
     },
     {
       "epoch": 13.64,
-      "eval_accuracy": 0.9107142857142857,
-      "eval_f1": 0.9107863922881503,
-      "eval_loss": 1.6872682571411133,
-      "eval_matthews_correlation": 0.9095190428978093,
-      "eval_runtime": 2.0448,
-      "eval_samples_per_second": 1506.257,
-      "eval_steps_per_second": 9.781,
+      "eval_accuracy": 0.9191558441558442,
+      "eval_f1": 0.9087017801267994,
+      "eval_loss": 1.6092149019241333,
+      "eval_matthews_correlation": 0.9180607280357055,
+      "eval_runtime": 2.2317,
+      "eval_samples_per_second": 1380.116,
+      "eval_steps_per_second": 8.962,
       "step": 600
     },
     {
       "epoch": 15.91,
-      "eval_accuracy": 0.9188311688311688,
-      "eval_f1": 0.9186833383887418,
-      "eval_loss": 1.6089478731155396,
-      "eval_matthews_correlation": 0.9177598370690575,
-      "eval_runtime": 2.3373,
-      "eval_samples_per_second": 1317.752,
-      "eval_steps_per_second": 8.557,
+      "eval_accuracy": 0.9237012987012987,
+      "eval_f1": 0.9173470137032593,
+      "eval_loss": 1.6759223937988281,
+      "eval_matthews_correlation": 0.92267900847975,
+      "eval_runtime": 2.1403,
+      "eval_samples_per_second": 1439.027,
+      "eval_steps_per_second": 9.344,
       "step": 700
     },
     {
       "epoch": 18.18,
-      "eval_accuracy": 0.9165584415584416,
-      "eval_f1": 0.9161751570564223,
-      "eval_loss": 1.7232335805892944,
-      "eval_matthews_correlation": 0.9154263192161151,
-      "eval_runtime": 2.0505,
-      "eval_samples_per_second": 1502.065,
-      "eval_steps_per_second": 9.754,
+      "eval_accuracy": 0.922077922077922,
+      "eval_f1": 0.9224956919233739,
+      "eval_loss": 1.7042781114578247,
+      "eval_matthews_correlation": 0.9210156723561079,
+      "eval_runtime": 2.1182,
+      "eval_samples_per_second": 1454.06,
+      "eval_steps_per_second": 9.442,
       "step": 800
     },
     {
       "epoch": 20.45,
-      "eval_accuracy": 0.9191558441558442,
-      "eval_f1": 0.9178254962063602,
-      "eval_loss": 1.7106611728668213,
-      "eval_matthews_correlation": 0.9180443672283,
-      "eval_runtime": 2.0231,
-      "eval_samples_per_second": 1522.42,
-      "eval_steps_per_second": 9.886,
+      "eval_accuracy": 0.9256493506493506,
+      "eval_f1": 0.9250031430609338,
+      "eval_loss": 1.618914246559143,
+      "eval_matthews_correlation": 0.9246330543218574,
+      "eval_runtime": 2.1102,
+      "eval_samples_per_second": 1459.597,
+      "eval_steps_per_second": 9.478,
       "step": 900
     },
     {
       "epoch": 22.73,
-      "learning_rate": 2.9957697067126356e-05,
-      "loss": 0.4659,
+      "learning_rate": 1.758712434118989e-05,
+      "loss": 0.4113,
       "step": 1000
     },
     {
       "epoch": 22.73,
-      "eval_accuracy": 0.9207792207792208,
-      "eval_f1": 0.9206063339961166,
-      "eval_loss": 1.7829617261886597,
-      "eval_matthews_correlation": 0.9196922723503571,
-      "eval_runtime": 2.1571,
-      "eval_samples_per_second": 1427.815,
-      "eval_steps_per_second": 9.272,
+      "eval_accuracy": 0.9272727272727272,
+      "eval_f1": 0.9262478178442993,
+      "eval_loss": 1.6726940870285034,
+      "eval_matthews_correlation": 0.9262802775880362,
+      "eval_runtime": 2.3947,
+      "eval_samples_per_second": 1286.193,
+      "eval_steps_per_second": 8.352,
       "step": 1000
     },
     {
       "epoch": 25.0,
-      "eval_accuracy": 0.9207792207792208,
-      "eval_f1": 0.920614925829126,
-      "eval_loss": 1.790487289428711,
-      "eval_matthews_correlation": 0.9196988176170032,
-      "eval_runtime": 2.4658,
-      "eval_samples_per_second": 1249.096,
-      "eval_steps_per_second": 8.111,
+      "eval_accuracy": 0.9282467532467532,
+      "eval_f1": 0.9285902214751346,
+      "eval_loss": 1.7208188772201538,
+      "eval_matthews_correlation": 0.9272760959410294,
+      "eval_runtime": 2.0547,
+      "eval_samples_per_second": 1498.986,
+      "eval_steps_per_second": 9.734,
       "step": 1100
     },
     {
       "epoch": 27.27,
-      "eval_accuracy": 0.9204545454545454,
-      "eval_f1": 0.9188404387742339,
-      "eval_loss": 1.8175984621047974,
-      "eval_matthews_correlation": 0.9193738592421591,
-      "eval_runtime": 2.1608,
-      "eval_samples_per_second": 1425.368,
-      "eval_steps_per_second": 9.256,
+      "eval_accuracy": 0.9272727272727272,
+      "eval_f1": 0.9269182576494233,
+      "eval_loss": 1.7480313777923584,
+      "eval_matthews_correlation": 0.9262735351894748,
+      "eval_runtime": 2.0774,
+      "eval_samples_per_second": 1482.597,
+      "eval_steps_per_second": 9.627,
       "step": 1200
     },
     {
       "epoch": 29.55,
-      "eval_accuracy": 0.9233766233766234,
-      "eval_f1": 0.9229582864798324,
-      "eval_loss": 1.8081684112548828,
-      "eval_matthews_correlation": 0.9223426539336737,
-      "eval_runtime": 2.2566,
-      "eval_samples_per_second": 1364.887,
-      "eval_steps_per_second": 8.863,
+      "eval_accuracy": 0.9262987012987013,
+      "eval_f1": 0.9262601189689171,
+      "eval_loss": 1.7753738164901733,
+      "eval_matthews_correlation": 0.9252925536787239,
+      "eval_runtime": 2.1885,
+      "eval_samples_per_second": 1407.348,
+      "eval_steps_per_second": 9.139,
       "step": 1300
     },
     {
       "epoch": 31.82,
-      "eval_accuracy": 0.9217532467532468,
-      "eval_f1": 0.9198895876658407,
-      "eval_loss": 1.8111428022384644,
-      "eval_matthews_correlation": 0.920686764000696,
-      "eval_runtime": 2.0686,
-      "eval_samples_per_second": 1488.895,
-      "eval_steps_per_second": 9.668,
+      "eval_accuracy": 0.9282467532467532,
+      "eval_f1": 0.9278794105174281,
+      "eval_loss": 1.790648341178894,
+      "eval_matthews_correlation": 0.9272619193360061,
+      "eval_runtime": 2.0054,
+      "eval_samples_per_second": 1535.842,
+      "eval_steps_per_second": 9.973,
       "step": 1400
     },
     {
       "epoch": 34.09,
-      "learning_rate": 1.0248685838753754e-05,
-      "loss": 0.1136,
+      "learning_rate": 6.0166478009333844e-06,
+      "loss": 0.0733,
       "step": 1500
     },
     {
       "epoch": 34.09,
-      "eval_accuracy": 0.9227272727272727,
-      "eval_f1": 0.9203460178662468,
-      "eval_loss": 1.8586403131484985,
-      "eval_matthews_correlation": 0.9216675520951976,
-      "eval_runtime": 2.1851,
-      "eval_samples_per_second": 1409.565,
-      "eval_steps_per_second": 9.153,
+      "eval_accuracy": 0.9262987012987013,
+      "eval_f1": 0.9263368444227621,
+      "eval_loss": 1.805496335029602,
+      "eval_matthews_correlation": 0.9252900896996127,
+      "eval_runtime": 2.1349,
+      "eval_samples_per_second": 1442.709,
+      "eval_steps_per_second": 9.368,
       "step": 1500
     },
     {
       "epoch": 36.36,
-      "eval_accuracy": 0.923051948051948,
-      "eval_f1": 0.9210405985603535,
-      "eval_loss": 1.838761329650879,
-      "eval_matthews_correlation": 0.9219970795291079,
-      "eval_runtime": 2.0604,
-      "eval_samples_per_second": 1494.867,
-      "eval_steps_per_second": 9.707,
+      "eval_accuracy": 0.9282467532467532,
+      "eval_f1": 0.9281799745185059,
+      "eval_loss": 1.7787483930587769,
+      "eval_matthews_correlation": 0.9272691959664779,
+      "eval_runtime": 2.095,
+      "eval_samples_per_second": 1470.152,
+      "eval_steps_per_second": 9.546,
       "step": 1600
     }
   ],

checkpoint-1600/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8e3513e5e545ce3f937f4f40e29e495b42c30f38865af855a93457c5772aab8
+oid sha256:7326a47c8357d75e8dc38a799f439aecb77a23c1cf207d4544566ffb7195bf20
 size 2927

checkpoint-200/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:514f00db63f43cccb0a7e4a1fef217b54223a75fc5e2ef41ada8d7e4e690eddb
+oid sha256:95664306a52cf37346b2133150bff5f406e03144bb7e191777e6f980bcdba362
 size 1762415977

checkpoint-200/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99c143c9585c7f07018d33924a44f6dbd15721d85d334140a508253f417f7ce7
+oid sha256:202672afbab4f365ee802555ddd19f2fe07221ba090113c7189effcc8556a01e
 size 440628841

checkpoint-200/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95fde9002ee6cf571ae7d4c3d2c21a6aa5e3c1314fd5310d771dc0a17f698cae
+oid sha256:2c07c734078251f359366effbc444dbdd5d4b936fe8a7081914086f6465cb641
 size 623

checkpoint-200/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.8603896103896104,
+  "best_metric": 0.9042207792207793,
   "best_model_checkpoint": "mpnet-metric/checkpoint-200",
   "epoch": 4.545454545454545,
   "global_step": 200,
@@ -9,24 +9,24 @@
   "log_history": [
     {
       "epoch": 2.27,
-      "eval_accuracy": 0.8194805194805195,
-      "eval_f1": 0.7656701166780793,
-      "eval_loss": 1.9282063245773315,
-      "eval_matthews_correlation": 0.8177401806097793,
-      "eval_runtime": 2.1248,
-      "eval_samples_per_second": 1449.542,
-      "eval_steps_per_second": 9.413,
+      "eval_accuracy": 0.8418831168831169,
+      "eval_f1": 0.8027962745185904,
+      "eval_loss": 1.4791860580444336,
+      "eval_matthews_correlation": 0.8403536839300481,
+      "eval_runtime": 2.0893,
+      "eval_samples_per_second": 1474.144,
+      "eval_steps_per_second": 9.572,
       "step": 100
     },
     {
       "epoch": 4.55,
-      "eval_accuracy": 0.8603896103896104,
-      "eval_f1": 0.8221385737164676,
-      "eval_loss": 1.785994529724121,
-      "eval_matthews_correlation": 0.8588446795045349,
-      "eval_runtime": 2.1571,
-      "eval_samples_per_second": 1427.834,
-      "eval_steps_per_second": 9.272,
+      "eval_accuracy": 0.9042207792207793,
+      "eval_f1": 0.9047628877989691,
+      "eval_loss": 1.487802267074585,
+      "eval_matthews_correlation": 0.9030870359405524,
+      "eval_runtime": 2.1548,
+      "eval_samples_per_second": 1429.39,
+      "eval_steps_per_second": 9.282,
       "step": 200
     }
   ],

checkpoint-200/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7326a47c8357d75e8dc38a799f439aecb77a23c1cf207d4544566ffb7195bf20
+oid sha256:292e7a8288c43b303abd31559aec885616dd7d87f70adfd70022f96ffad2e087
 size 2927

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ce7476ae37df65c46ba296e4e3f2f220f1c120049ff857a57fcf3eb534a1524
+oid sha256:202672afbab4f365ee802555ddd19f2fe07221ba090113c7189effcc8556a01e
 size 440628841

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7326a47c8357d75e8dc38a799f439aecb77a23c1cf207d4544566ffb7195bf20
+oid sha256:292e7a8288c43b303abd31559aec885616dd7d87f70adfd70022f96ffad2e087
 size 2927