Training in progress, step 200

checkpoint-1600/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8549827c39f256fa65d4b955ed42e6d77c1fd20cfbb17a0a84115fe638e3a0a0
+oid sha256:f99f8fb7c73670d80d8cc6d29ca47a57f7929620b60fffa9c12270693009da1f
 size 1762416361

checkpoint-1600/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a638aa8cc2855f0e8a9591f823deffe1fe8c5e35818ea7b749e15a79f2f86f0
+oid sha256:076fb7da75c7fc9411b439fe9db3b923ea11215fb369ed78288730f8a31d9db6
 size 440628841

checkpoint-1600/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c22b6d6b37248f66e0c6074a6481164923d4a29fb30615ebea2319468dfcfdfa
+oid sha256:42675db5200e73fa678e06a55ec798b1343886dd432c1c010c01820915b0ff17
 size 623

checkpoint-1600/trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.9311688311688312,
-  "best_model_checkpoint": "mpnet-metric/checkpoint-1600",
+  "best_metric": 0.9353896103896104,
+  "best_model_checkpoint": "mpnet-metric/checkpoint-1200",
   "epoch": 36.36363636363637,
   "global_step": 1600,
   "is_hyper_param_search": false,
@@ -9,196 +9,196 @@
   "log_history": [
     {
       "epoch": 2.27,
-      "eval_accuracy": 0.8198051948051948,
-      "eval_f1": 0.7450777417744769,
-      "eval_loss": 1.6592037677764893,
-      "eval_matthews_correlation": 0.8181083957290356,
-      "eval_runtime": 2.026,
-      "eval_samples_per_second": 1520.244,
-      "eval_steps_per_second": 9.872,
+      "eval_accuracy": 0.8159090909090909,
+      "eval_f1": 0.7511226652087337,
+      "eval_loss": 1.8484668731689453,
+      "eval_matthews_correlation": 0.8141220226006439,
+      "eval_runtime": 2.002,
+      "eval_samples_per_second": 1538.49,
+      "eval_steps_per_second": 9.99,
       "step": 100
     },
     {
       "epoch": 4.55,
-      "eval_accuracy": 0.8948051948051948,
-      "eval_f1": 0.8613149877764686,
-      "eval_loss": 1.4898205995559692,
-      "eval_matthews_correlation": 0.8934414020272823,
-      "eval_runtime": 1.9768,
-      "eval_samples_per_second": 1558.086,
-      "eval_steps_per_second": 10.117,
+      "eval_accuracy": 0.8551948051948052,
+      "eval_f1": 0.8020942917039883,
+      "eval_loss": 1.7144999504089355,
+      "eval_matthews_correlation": 0.8536409556631633,
+      "eval_runtime": 1.9896,
+      "eval_samples_per_second": 1548.081,
+      "eval_steps_per_second": 10.052,
       "step": 200
     },
     {
       "epoch": 6.82,
-      "eval_accuracy": 0.912987012987013,
-      "eval_f1": 0.9000423517675215,
-      "eval_loss": 1.4527192115783691,
-      "eval_matthews_correlation": 0.9118564052150951,
-      "eval_runtime": 2.57,
-      "eval_samples_per_second": 1198.465,
-      "eval_steps_per_second": 7.782,
+      "eval_accuracy": 0.8941558441558441,
+      "eval_f1": 0.8555110496639062,
+      "eval_loss": 1.7012308835983276,
+      "eval_matthews_correlation": 0.8928022091998309,
+      "eval_runtime": 2.0442,
+      "eval_samples_per_second": 1506.723,
+      "eval_steps_per_second": 9.784,
       "step": 300
     },
     {
       "epoch": 9.09,
-      "eval_accuracy": 0.9126623376623376,
-      "eval_f1": 0.908645696234123,
-      "eval_loss": 1.4831421375274658,
-      "eval_matthews_correlation": 0.9114895555845098,
-      "eval_runtime": 2.0848,
-      "eval_samples_per_second": 1477.333,
-      "eval_steps_per_second": 9.593,
+      "eval_accuracy": 0.9103896103896104,
+      "eval_f1": 0.8897197560299775,
+      "eval_loss": 1.6050169467926025,
+      "eval_matthews_correlation": 0.9092143006403555,
+      "eval_runtime": 2.1871,
+      "eval_samples_per_second": 1408.229,
+      "eval_steps_per_second": 9.144,
       "step": 400
     },
     {
       "epoch": 11.36,
-      "learning_rate": 5.415550623870174e-05,
-      "loss": 1.1899,
+      "learning_rate": 2.7063895051946938e-05,
+      "loss": 1.2946,
       "step": 500
     },
     {
       "epoch": 11.36,
-      "eval_accuracy": 0.9211038961038961,
-      "eval_f1": 0.9193943764927279,
-      "eval_loss": 1.5991318225860596,
-      "eval_matthews_correlation": 0.9200481714694354,
-      "eval_runtime": 2.063,
-      "eval_samples_per_second": 1492.975,
-      "eval_steps_per_second": 9.695,
+      "eval_accuracy": 0.9201298701298701,
+      "eval_f1": 0.9074369761816372,
+      "eval_loss": 1.6444977521896362,
+      "eval_matthews_correlation": 0.9190647083577843,
+      "eval_runtime": 2.0173,
+      "eval_samples_per_second": 1526.787,
+      "eval_steps_per_second": 9.914,
       "step": 500
     },
     {
       "epoch": 13.64,
-      "eval_accuracy": 0.926948051948052,
-      "eval_f1": 0.9278896493203828,
-      "eval_loss": 1.7099632024765015,
-      "eval_matthews_correlation": 0.9259681965773313,
-      "eval_runtime": 2.0449,
-      "eval_samples_per_second": 1506.181,
-      "eval_steps_per_second": 9.78,
+      "eval_accuracy": 0.9211038961038961,
+      "eval_f1": 0.9084577913023288,
+      "eval_loss": 1.663888692855835,
+      "eval_matthews_correlation": 0.9200604781411976,
+      "eval_runtime": 2.3853,
+      "eval_samples_per_second": 1291.224,
+      "eval_steps_per_second": 8.385,
       "step": 600
     },
     {
       "epoch": 15.91,
-      "eval_accuracy": 0.9262987012987013,
-      "eval_f1": 0.9266016706124925,
-      "eval_loss": 1.7617793083190918,
-      "eval_matthews_correlation": 0.9253075892589753,
-      "eval_runtime": 2.1189,
-      "eval_samples_per_second": 1453.585,
-      "eval_steps_per_second": 9.439,
+      "eval_accuracy": 0.923051948051948,
+      "eval_f1": 0.9136896227660865,
+      "eval_loss": 1.6868306398391724,
+      "eval_matthews_correlation": 0.9220235796156276,
+      "eval_runtime": 2.1585,
+      "eval_samples_per_second": 1426.921,
+      "eval_steps_per_second": 9.266,
       "step": 700
     },
     {
       "epoch": 18.18,
-      "eval_accuracy": 0.926948051948052,
-      "eval_f1": 0.9272992530361166,
-      "eval_loss": 1.6870428323745728,
-      "eval_matthews_correlation": 0.9259701871862133,
-      "eval_runtime": 2.0846,
-      "eval_samples_per_second": 1477.509,
-      "eval_steps_per_second": 9.594,
+      "eval_accuracy": 0.9295454545454546,
+      "eval_f1": 0.9301664771201281,
+      "eval_loss": 1.6475751399993896,
+      "eval_matthews_correlation": 0.9285897200356921,
+      "eval_runtime": 2.0719,
+      "eval_samples_per_second": 1486.591,
+      "eval_steps_per_second": 9.653,
       "step": 800
     },
     {
       "epoch": 20.45,
-      "eval_accuracy": 0.9311688311688312,
-      "eval_f1": 0.9325870183951288,
-      "eval_loss": 1.6581286191940308,
-      "eval_matthews_correlation": 0.930240830781528,
-      "eval_runtime": 2.1161,
-      "eval_samples_per_second": 1455.523,
-      "eval_steps_per_second": 9.451,
+      "eval_accuracy": 0.9318181818181818,
+      "eval_f1": 0.9303464520815973,
+      "eval_loss": 1.6600165367126465,
+      "eval_matthews_correlation": 0.9308986858617924,
+      "eval_runtime": 2.0457,
+      "eval_samples_per_second": 1505.575,
+      "eval_steps_per_second": 9.776,
       "step": 900
     },
     {
       "epoch": 22.73,
-      "learning_rate": 3.266522598524867e-05,
-      "loss": 0.4433,
+      "learning_rate": 1.63242541583172e-05,
+      "loss": 0.3881,
       "step": 1000
     },
     {
       "epoch": 22.73,
-      "eval_accuracy": 0.9292207792207792,
-      "eval_f1": 0.9315504613414909,
-      "eval_loss": 1.7811475992202759,
-      "eval_matthews_correlation": 0.9282657035558725,
-      "eval_runtime": 2.487,
-      "eval_samples_per_second": 1238.434,
-      "eval_steps_per_second": 8.042,
+      "eval_accuracy": 0.9262987012987013,
+      "eval_f1": 0.9278296659676756,
+      "eval_loss": 1.6724674701690674,
+      "eval_matthews_correlation": 0.9253043794901309,
+      "eval_runtime": 2.232,
+      "eval_samples_per_second": 1379.929,
+      "eval_steps_per_second": 8.961,
       "step": 1000
     },
     {
       "epoch": 25.0,
-      "eval_accuracy": 0.9279220779220779,
-      "eval_f1": 0.9297149049391985,
-      "eval_loss": 1.7164376974105835,
-      "eval_matthews_correlation": 0.9269366528927585,
-      "eval_runtime": 2.0462,
-      "eval_samples_per_second": 1505.214,
-      "eval_steps_per_second": 9.774,
+      "eval_accuracy": 0.9314935064935065,
+      "eval_f1": 0.9318825468171268,
+      "eval_loss": 1.797305941581726,
+      "eval_matthews_correlation": 0.9305766609812194,
+      "eval_runtime": 2.1057,
+      "eval_samples_per_second": 1462.7,
+      "eval_steps_per_second": 9.498,
       "step": 1100
     },
     {
       "epoch": 27.27,
-      "eval_accuracy": 0.925974025974026,
-      "eval_f1": 0.9277396272948383,
-      "eval_loss": 1.8341482877731323,
-      "eval_matthews_correlation": 0.9249701928533347,
-      "eval_runtime": 2.0387,
-      "eval_samples_per_second": 1510.753,
-      "eval_steps_per_second": 9.81,
+      "eval_accuracy": 0.9353896103896104,
+      "eval_f1": 0.9361728835983955,
+      "eval_loss": 1.882063627243042,
+      "eval_matthews_correlation": 0.9345315640515132,
+      "eval_runtime": 2.0581,
+      "eval_samples_per_second": 1496.504,
+      "eval_steps_per_second": 9.718,
       "step": 1200
     },
     {
       "epoch": 29.55,
-      "eval_accuracy": 0.9272727272727272,
-      "eval_f1": 0.9303073868506698,
-      "eval_loss": 1.8742587566375732,
-      "eval_matthews_correlation": 0.9262946963645845,
-      "eval_runtime": 2.1464,
-      "eval_samples_per_second": 1434.947,
-      "eval_steps_per_second": 9.318,
+      "eval_accuracy": 0.9331168831168831,
+      "eval_f1": 0.9336367435388829,
+      "eval_loss": 1.760854721069336,
+      "eval_matthews_correlation": 0.9322178856162862,
+      "eval_runtime": 2.3359,
+      "eval_samples_per_second": 1318.552,
+      "eval_steps_per_second": 8.562,
       "step": 1300
     },
     {
       "epoch": 31.82,
-      "eval_accuracy": 0.9298701298701298,
-      "eval_f1": 0.9317312475722468,
-      "eval_loss": 1.8492175340652466,
-      "eval_matthews_correlation": 0.9289212025361154,
-      "eval_runtime": 2.0656,
-      "eval_samples_per_second": 1491.062,
-      "eval_steps_per_second": 9.682,
+      "eval_accuracy": 0.9327922077922078,
+      "eval_f1": 0.9341097776295038,
+      "eval_loss": 1.7718247175216675,
+      "eval_matthews_correlation": 0.9318988835488757,
+      "eval_runtime": 2.0052,
+      "eval_samples_per_second": 1535.974,
+      "eval_steps_per_second": 9.974,
       "step": 1400
     },
     {
       "epoch": 34.09,
-      "learning_rate": 1.1174945731795597e-05,
-      "loss": 0.1033,
+      "learning_rate": 5.5846132646874635e-06,
+      "loss": 0.0634,
       "step": 1500
     },
     {
       "epoch": 34.09,
-      "eval_accuracy": 0.9321428571428572,
-      "eval_f1": 0.933543728307653,
-      "eval_loss": 1.8748821020126343,
-      "eval_matthews_correlation": 0.9312262454963814,
-      "eval_runtime": 2.0974,
-      "eval_samples_per_second": 1468.494,
-      "eval_steps_per_second": 9.536,
+      "eval_accuracy": 0.9331168831168831,
+      "eval_f1": 0.9346968268850435,
+      "eval_loss": 1.8285932540893555,
+      "eval_matthews_correlation": 0.9322186737012743,
+      "eval_runtime": 2.0633,
+      "eval_samples_per_second": 1492.735,
+      "eval_steps_per_second": 9.693,
       "step": 1500
     },
     {
       "epoch": 36.36,
-      "eval_accuracy": 0.9311688311688312,
-      "eval_f1": 0.9326935168816428,
-      "eval_loss": 1.8706436157226562,
-      "eval_matthews_correlation": 0.9302409001042274,
-      "eval_runtime": 2.1149,
-      "eval_samples_per_second": 1456.342,
-      "eval_steps_per_second": 9.457,
+      "eval_accuracy": 0.9331168831168831,
+      "eval_f1": 0.934572295784542,
+      "eval_loss": 1.7940177917480469,
+      "eval_matthews_correlation": 0.9322119650832548,
+      "eval_runtime": 2.0844,
+      "eval_samples_per_second": 1477.624,
+      "eval_steps_per_second": 9.595,
       "step": 1600
     }
   ],

checkpoint-1600/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d29331ba57d1ee2e4100784d9c6c603d4cd05a5267cdacfd698fa2fb9a121bd5
+oid sha256:3631a6250349c3bab25cc9f2945e9f86b3c8bf60eb8f342e5780a42c4164973b
 size 2927

checkpoint-200/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b994d7ccb8163d4a7243504f9cd34095dda2a40df85816dbf21b243746f61640
+oid sha256:c4657c0b1d01a420e05bfb79980dd195b1c4cc7e3464c93da99b473cc23dbd55
 size 1762415977

checkpoint-200/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79b12cc26859d1023f2495ed14eb3d14ba7cae84ce216e402f13a5db5512d331
+oid sha256:1833164cdbeeee6ad773bdfbb9224c97f830030451c502ac4f76e6994df612b4
 size 440628841

checkpoint-200/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:919dc1182c99ed3144403ce9ee5b2395988917b5369875db855b127facef61e2
+oid sha256:17a4169c08357e4ff184be9f20022428450bb238b1ad55ad31f2c906500bf3b1
 size 623

checkpoint-200/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.8551948051948052,
+  "best_metric": 0.9058441558441559,
   "best_model_checkpoint": "mpnet-metric/checkpoint-200",
   "epoch": 4.545454545454545,
   "global_step": 200,
@@ -9,24 +9,24 @@
   "log_history": [
     {
       "epoch": 2.27,
-      "eval_accuracy": 0.8159090909090909,
-      "eval_f1": 0.7511226652087337,
-      "eval_loss": 1.8484668731689453,
-      "eval_matthews_correlation": 0.8141220226006439,
-      "eval_runtime": 2.002,
-      "eval_samples_per_second": 1538.49,
-      "eval_steps_per_second": 9.99,
+      "eval_accuracy": 0.8301948051948052,
+      "eval_f1": 0.7627260704091138,
+      "eval_loss": 1.6476343870162964,
+      "eval_matthews_correlation": 0.8285143618760992,
+      "eval_runtime": 2.6998,
+      "eval_samples_per_second": 1140.818,
+      "eval_steps_per_second": 7.408,
       "step": 100
     },
     {
       "epoch": 4.55,
-      "eval_accuracy": 0.8551948051948052,
-      "eval_f1": 0.8020942917039883,
-      "eval_loss": 1.7144999504089355,
-      "eval_matthews_correlation": 0.8536409556631633,
-      "eval_runtime": 1.9896,
-      "eval_samples_per_second": 1548.081,
-      "eval_steps_per_second": 10.052,
+      "eval_accuracy": 0.9058441558441559,
+      "eval_f1": 0.8795235433431401,
+      "eval_loss": 1.5654271841049194,
+      "eval_matthews_correlation": 0.9046102502667962,
+      "eval_runtime": 2.1212,
+      "eval_samples_per_second": 1451.986,
+      "eval_steps_per_second": 9.428,
       "step": 200
     }
   ],

checkpoint-200/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3631a6250349c3bab25cc9f2945e9f86b3c8bf60eb8f342e5780a42c4164973b
+oid sha256:e2a75618958dd260c02e3f1429d19a584cb19e6d4409f6130f9e2987e8b463c0
 size 2927

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3ca34ed9808138d4c926cb61bb1dd14909cae5c1c7e4b0f448ed079dc8bace1
+oid sha256:1833164cdbeeee6ad773bdfbb9224c97f830030451c502ac4f76e6994df612b4
 size 440628841

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3631a6250349c3bab25cc9f2945e9f86b3c8bf60eb8f342e5780a42c4164973b
+oid sha256:e2a75618958dd260c02e3f1429d19a584cb19e6d4409f6130f9e2987e8b463c0
 size 2927