Training in progress, step 1400

checkpoint-1000/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0932a52d6b4c3c4e337093c02f9394882fd78cb430dfee8e6137095d3a658a4
+oid sha256:d16254a48573454a8dffae99fcbd6facc8e1dca2bf52789182b5e7ffbad5179a
 size 1762416361

checkpoint-1000/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b04cceee17b6116ba5f2ffd85407a818511ee6b6e3ffd8931e166c1418fd4035
+oid sha256:b4bb89adf143aa0a397ba7e79218873ad2170511c5f037bb21ebe0ea55a0c28d
 size 440628841

checkpoint-1000/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5342227bdca42f48673c49ca7187615e8bf1f2709576bbd5f67511c70ef56bd4
+oid sha256:3b519090df16ae3dcd0f23b27a096fb05dd73809b346f1b29dc9e93a9ef43485
 size 623

checkpoint-1000/trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.9211038961038961,
-  "best_model_checkpoint": "mpnet-metric/checkpoint-400",
+  "best_metric": 0.9272727272727272,
+  "best_model_checkpoint": "mpnet-metric/checkpoint-1000",
   "epoch": 22.727272727272727,
   "global_step": 1000,
   "is_hyper_param_search": false,
@@ -9,124 +9,124 @@
   "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
     }
   ],

checkpoint-1000/training_args.bin

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

checkpoint-1200/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54ed0fcb2389858b7855c944023c8e3ff020e6f969f19607f172901e1886177a
+oid sha256:cad7a596c052a08c8db42cb10447227e29d8d4455fa0120644eb6f0abbeca42b
 size 1762416361

checkpoint-1200/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d3db71b604d12783ac359b4cd32eb2805fb088b687932d56bbb4f2ff0faca7a
+oid sha256:853cf6bedc3356ef5f29d6a357ce047e768610621694b599958a43dc01be5e96
 size 440628841

checkpoint-1200/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ea043fe05817e85fc2adb93cb12dbca9d33b85f743bb3863f0b42b136916122
+oid sha256:7bf8bc9c432358c961802485cb2ea69ee42a10de898d17b0f4a70a83244098ad
 size 623

checkpoint-1200/trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.9211038961038961,
-  "best_model_checkpoint": "mpnet-metric/checkpoint-400",
+  "best_metric": 0.9272727272727272,
+  "best_model_checkpoint": "mpnet-metric/checkpoint-1000",
   "epoch": 27.272727272727273,
   "global_step": 1200,
   "is_hyper_param_search": false,
@@ -9,146 +9,146 @@
   "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
     }
   ],

checkpoint-1200/training_args.bin

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

checkpoint-1400/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:775d813f827646f85ebd3ca36b0bc0da9eb27804242e56e23178633dc35442b5
+oid sha256:94026c22fd60a9f8a7247d40dba810569ef7aa21c7e93a1e96b33fb855b16390
 size 1762416361

checkpoint-1400/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3ccbd2180207084cad5f0ce95ded2f74a4445182758f26982a02d94bcdade15
+oid sha256:9ce7476ae37df65c46ba296e4e3f2f220f1c120049ff857a57fcf3eb534a1524
 size 440628841

checkpoint-1400/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:871c7c5e2e075b82a9c9e1d4c608b227353621b5e190c395954a23f9cafc754f
+oid sha256:b84ba2c6df8c4934f46ec1bcbeaaa46cf4dc96e81696db393fe490fee1b7bf23
 size 623

checkpoint-1400/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.9217532467532468,
+  "best_metric": 0.9282467532467532,
   "best_model_checkpoint": "mpnet-metric/checkpoint-1400",
   "epoch": 31.818181818181817,
   "global_step": 1400,
@@ -9,168 +9,168 @@
   "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
     }
   ],

checkpoint-1400/training_args.bin

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

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38381380b182a449c1fe36f43009070e415f0b58b89f24f7c894800dbebb0e0b
+oid sha256:9ce7476ae37df65c46ba296e4e3f2f220f1c120049ff857a57fcf3eb534a1524
 size 440628841