Training in progress, step 800

checkpoint-400/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea612b45cc7b7560dfaa34705b65983e89e6076f6315781d01cfde65d382fb3f
+oid sha256:cb45e00cb1c5b9ecf60eeedb8af78da73df4b2ee20aee4452f7630d4b9febe9a
 size 1762416361

checkpoint-400/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d3a61a2da9c7b73f1887898e4cb0300043d05c1557518fd709559d96b8080b4
+oid sha256:611d4de6d8a6bf0229abe9befaa8bbad95b347b0eee54e290bfed02c072d5e77
 size 440628841

checkpoint-400/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2dbc2046c53454073f6195a1fe4497d0952b044c6d7fa8487af05ea95fdea641
+oid sha256:2099ac0a1cdd4fde866ef3793a599cc750698c84322030e65b9848212a4d6dd9
 size 623

checkpoint-400/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.9211038961038961,
+  "best_metric": 0.8948051948051948,
   "best_model_checkpoint": "mpnet-metric/checkpoint-400",
   "epoch": 9.090909090909092,
   "global_step": 400,
@@ -9,46 +9,46 @@
   "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
     }
   ],

checkpoint-400/training_args.bin

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

checkpoint-600/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57397a55e3e207d177100783c9bea043367897810d373f2b53b0dfdb059200d4
+oid sha256:10dba73cdb8afb35d810ae2871ab0b4b1dddbc46096c049498285cb41aa3f237
 size 1762416361

checkpoint-600/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4dda37daa04128c87e4dee23b3044a855aa93c7c9e81111318c4d8fffa28bc82
+oid sha256:e7dd6d481df71f7927f8fe008dc4c65e326d5e94cd4a24971354a568312d47d9
 size 440628841

checkpoint-600/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7f6a1005bab922360d372b72d71902fde1e25b40b68559074f346908f87d1c1
+oid sha256:7a85e57600a4ef0a0b430eac3da601ce6876ac26939d4c94a02851379d83c6e8
 size 623

checkpoint-600/trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.9211038961038961,
-  "best_model_checkpoint": "mpnet-metric/checkpoint-400",
+  "best_metric": 0.9191558441558442,
+  "best_model_checkpoint": "mpnet-metric/checkpoint-600",
   "epoch": 13.636363636363637,
   "global_step": 600,
   "is_hyper_param_search": false,
@@ -9,74 +9,74 @@
   "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
     }
   ],

checkpoint-600/training_args.bin

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

checkpoint-800/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6373658e7aa9f00ef1368297b036f2e3c4ecd620e156b0988e626c6a4cec096a
+oid sha256:54d6ded1fa1a96a2a46d0dc73ac0e5ca8c81efed36bfe60baab913f9e24ac052
 size 1762416361

checkpoint-800/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74bd5a8904ee46ca53d83f7d5fd02fcc0670567ac7b7276ae1f1bdb7e206b6b4
+oid sha256:38381380b182a449c1fe36f43009070e415f0b58b89f24f7c894800dbebb0e0b
 size 440628841

checkpoint-800/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d91e3eff1500d66f8c5210afdbb0fa40efe0e49c401fa82508ac2d11c44d0652
+oid sha256:fe1f7a1c3765672d101e10eb945c26cb679bef8cba252cf5bde3cfcb069d2e66
 size 623

checkpoint-800/trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.9211038961038961,
-  "best_model_checkpoint": "mpnet-metric/checkpoint-400",
+  "best_metric": 0.922077922077922,
+  "best_model_checkpoint": "mpnet-metric/checkpoint-800",
   "epoch": 18.181818181818183,
   "global_step": 800,
   "is_hyper_param_search": false,
@@ -9,96 +9,96 @@
   "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
     }
   ],

checkpoint-800/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 sha256:99c143c9585c7f07018d33924a44f6dbd15721d85d334140a508253f417f7ce7
+oid sha256:38381380b182a449c1fe36f43009070e415f0b58b89f24f7c894800dbebb0e0b
 size 440628841