Training in progress, step 800

checkpoint-400/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb45e00cb1c5b9ecf60eeedb8af78da73df4b2ee20aee4452f7630d4b9febe9a
+oid sha256:36a0cde7e77ae54ea8021805718368375fd26d905cd69b8fd6f553cfd1058038
 size 1762416361

checkpoint-400/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:611d4de6d8a6bf0229abe9befaa8bbad95b347b0eee54e290bfed02c072d5e77
+oid sha256:f6e114ec5549d08c13a52583e67328396e4933b5a53e27736567aed5b10bcf21
 size 440628841

checkpoint-400/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2099ac0a1cdd4fde866ef3793a599cc750698c84322030e65b9848212a4d6dd9
+oid sha256:67e5f799b0b4206fefbf9952152651fc5628fd103e86cea62fbf24b4452bdfac
 size 623

checkpoint-400/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.8948051948051948,
+  "best_metric": 0.9123376623376623,
   "best_model_checkpoint": "mpnet-metric/checkpoint-400",
   "epoch": 9.090909090909092,
   "global_step": 400,
@@ -9,46 +9,46 @@
   "log_history": [
     {
       "epoch": 2.27,
-      "eval_accuracy": 0.8194805194805195,
-      "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
     },
     {
       "epoch": 6.82,
-      "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,
+      "eval_accuracy": 0.9172077922077922,
+      "eval_f1": 0.9169016425995938,
+      "eval_loss": 1.6755403280258179,
+      "eval_matthews_correlation": 0.9161647270846853,
+      "eval_runtime": 2.1745,
+      "eval_samples_per_second": 1416.389,
+      "eval_steps_per_second": 9.197,
       "step": 300
     },
     {
       "epoch": 9.09,
-      "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,
+      "eval_accuracy": 0.9123376623376623,
+      "eval_f1": 0.9128534869153119,
+      "eval_loss": 1.6229037046432495,
+      "eval_matthews_correlation": 0.9111753584333115,
+      "eval_runtime": 2.0543,
+      "eval_samples_per_second": 1499.327,
+      "eval_steps_per_second": 9.736,
       "step": 400
     }
   ],

checkpoint-400/training_args.bin

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

checkpoint-600/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10dba73cdb8afb35d810ae2871ab0b4b1dddbc46096c049498285cb41aa3f237
+oid sha256:a244d82bf504bf9eb5ea45085bba9c1ab44373557cd844e2599fd44863ad6cfb
 size 1762416361

checkpoint-600/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7dd6d481df71f7927f8fe008dc4c65e326d5e94cd4a24971354a568312d47d9
+oid sha256:aa069392f424595854deef81b65aba19f2d1fd9545400a788b6dcf9da2eb6a77
 size 440628841

checkpoint-600/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a85e57600a4ef0a0b430eac3da601ce6876ac26939d4c94a02851379d83c6e8
+oid sha256:9e85af04e0e01345489f741d3a89df39a6f798a81f84b495375d306c3469f088
 size 623

checkpoint-600/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.9191558441558442,
+  "best_metric": 0.9211038961038961,
   "best_model_checkpoint": "mpnet-metric/checkpoint-600",
   "epoch": 13.636363636363637,
   "global_step": 600,
@@ -9,74 +9,74 @@
   "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
     },
     {
       "epoch": 6.82,
-      "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,
+      "eval_accuracy": 0.9172077922077922,
+      "eval_f1": 0.9169016425995938,
+      "eval_loss": 1.6755403280258179,
+      "eval_matthews_correlation": 0.9161647270846853,
+      "eval_runtime": 2.1745,
+      "eval_samples_per_second": 1416.389,
+      "eval_steps_per_second": 9.197,
       "step": 300
     },
     {
       "epoch": 9.09,
-      "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,
+      "eval_accuracy": 0.9123376623376623,
+      "eval_f1": 0.9128534869153119,
+      "eval_loss": 1.6229037046432495,
+      "eval_matthews_correlation": 0.9111753584333115,
+      "eval_runtime": 2.0543,
+      "eval_samples_per_second": 1499.327,
+      "eval_steps_per_second": 9.736,
       "step": 400
     },
     {
       "epoch": 11.36,
-      "learning_rate": 2.91576008814464e-05,
-      "loss": 1.3674,
+      "learning_rate": 5.2705340156346366e-05,
+      "loss": 1.1094,
       "step": 500
     },
     {
       "epoch": 11.36,
-      "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,
+      "eval_accuracy": 0.9172077922077922,
+      "eval_f1": 0.9150003521466267,
+      "eval_loss": 1.6902168989181519,
+      "eval_matthews_correlation": 0.916107308697779,
+      "eval_runtime": 2.1005,
+      "eval_samples_per_second": 1466.292,
+      "eval_steps_per_second": 9.521,
       "step": 500
     },
     {
       "epoch": 13.64,
-      "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,
+      "eval_accuracy": 0.9211038961038961,
+      "eval_f1": 0.9217190641997036,
+      "eval_loss": 1.809704065322876,
+      "eval_matthews_correlation": 0.9200266092875187,
+      "eval_runtime": 2.1893,
+      "eval_samples_per_second": 1406.863,
+      "eval_steps_per_second": 9.135,
       "step": 600
     }
   ],

checkpoint-600/training_args.bin

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

checkpoint-800/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54d6ded1fa1a96a2a46d0dc73ac0e5ca8c81efed36bfe60baab913f9e24ac052
+oid sha256:117c5421a2944e02d968033d53689d2ba0e51f904a3189a552703709c06d20d3
 size 1762416361

checkpoint-800/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38381380b182a449c1fe36f43009070e415f0b58b89f24f7c894800dbebb0e0b
+oid sha256:0e0e9c1bbfb0937072ea7f1cb5828117a85dc743eed73ea052bebc67cbd335b3
 size 440628841

checkpoint-800/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe1f7a1c3765672d101e10eb945c26cb679bef8cba252cf5bde3cfcb069d2e66
+oid sha256:bdb056e85e9694c7727758b97fd834637b8aac63ce43dcfeb23986ae5f2a1534
 size 623

checkpoint-800/trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.922077922077922,
-  "best_model_checkpoint": "mpnet-metric/checkpoint-800",
+  "best_metric": 0.9211038961038961,
+  "best_model_checkpoint": "mpnet-metric/checkpoint-600",
   "epoch": 18.181818181818183,
   "global_step": 800,
   "is_hyper_param_search": false,
@@ -9,96 +9,96 @@
   "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
     },
     {
       "epoch": 6.82,
-      "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,
+      "eval_accuracy": 0.9172077922077922,
+      "eval_f1": 0.9169016425995938,
+      "eval_loss": 1.6755403280258179,
+      "eval_matthews_correlation": 0.9161647270846853,
+      "eval_runtime": 2.1745,
+      "eval_samples_per_second": 1416.389,
+      "eval_steps_per_second": 9.197,
       "step": 300
     },
     {
       "epoch": 9.09,
-      "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,
+      "eval_accuracy": 0.9123376623376623,
+      "eval_f1": 0.9128534869153119,
+      "eval_loss": 1.6229037046432495,
+      "eval_matthews_correlation": 0.9111753584333115,
+      "eval_runtime": 2.0543,
+      "eval_samples_per_second": 1499.327,
+      "eval_steps_per_second": 9.736,
       "step": 400
     },
     {
       "epoch": 11.36,
-      "learning_rate": 2.91576008814464e-05,
-      "loss": 1.3674,
+      "learning_rate": 5.2705340156346366e-05,
+      "loss": 1.1094,
       "step": 500
     },
     {
       "epoch": 11.36,
-      "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,
+      "eval_accuracy": 0.9172077922077922,
+      "eval_f1": 0.9150003521466267,
+      "eval_loss": 1.6902168989181519,
+      "eval_matthews_correlation": 0.916107308697779,
+      "eval_runtime": 2.1005,
+      "eval_samples_per_second": 1466.292,
+      "eval_steps_per_second": 9.521,
       "step": 500
     },
     {
       "epoch": 13.64,
-      "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,
+      "eval_accuracy": 0.9211038961038961,
+      "eval_f1": 0.9217190641997036,
+      "eval_loss": 1.809704065322876,
+      "eval_matthews_correlation": 0.9200266092875187,
+      "eval_runtime": 2.1893,
+      "eval_samples_per_second": 1406.863,
+      "eval_steps_per_second": 9.135,
       "step": 600
     },
     {
       "epoch": 15.91,
-      "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,
+      "eval_accuracy": 0.9256493506493506,
+      "eval_f1": 0.9258906800234634,
+      "eval_loss": 1.767533779144287,
+      "eval_matthews_correlation": 0.9246460003797943,
+      "eval_runtime": 2.1499,
+      "eval_samples_per_second": 1432.599,
+      "eval_steps_per_second": 9.303,
       "step": 700
     },
     {
       "epoch": 18.18,
-      "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,
+      "eval_accuracy": 0.9188311688311688,
+      "eval_f1": 0.9200483431183891,
+      "eval_loss": 1.8722023963928223,
+      "eval_matthews_correlation": 0.917724204986671,
+      "eval_runtime": 2.0585,
+      "eval_samples_per_second": 1496.224,
+      "eval_steps_per_second": 9.716,
       "step": 800
     }
   ],

checkpoint-800/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 sha256:202672afbab4f365ee802555ddd19f2fe07221ba090113c7189effcc8556a01e
+oid sha256:0e0e9c1bbfb0937072ea7f1cb5828117a85dc743eed73ea052bebc67cbd335b3
 size 440628841