Training in progress, step 200

checkpoint-1600/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9baef6d4daf2fe3ad56af5d63861f8bb58eb8a5aeba5000becdd4ab84e8affc5
+oid sha256:e42666cfd54577815cd1e6ecc369bcd3d3e155a9001c3a0105dd811c7dc75b86
 size 1762416361

checkpoint-1600/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47ec5ac06840ec6e716fb057f2c913c757269b70c160f1645a046ef34ff29bb6
+oid sha256:f845e41bf5d5f00e8d59cc0c78f89a59b6d7c737b7f8aaa11086970ff856554e
 size 440628841

checkpoint-1600/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8be8ab8c95c8e78b1057a56eebfabfc2adb049d90ba73c4e57255ddff3adaa1f
+oid sha256:0f19fb646aeea6bd1ee464ef9d1f6ec4fa56890cecb1622bf6ad8c9514599df8
 size 623

checkpoint-1600/trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.9256493506493506,
-  "best_model_checkpoint": "mpnet-metric/checkpoint-1200",
+  "best_metric": 0.9262987012987013,
+  "best_model_checkpoint": "mpnet-metric/checkpoint-1000",
   "epoch": 36.36363636363637,
   "global_step": 1600,
   "is_hyper_param_search": false,
@@ -9,196 +9,196 @@
   "log_history": [
     {
       "epoch": 2.27,
-      "eval_accuracy": 0.8103896103896104,
-      "eval_f1": 0.746449185181852,
-      "eval_loss": 1.668478012084961,
-      "eval_matthews_correlation": 0.8086456666016874,
-      "eval_runtime": 2.0655,
-      "eval_samples_per_second": 1491.145,
-      "eval_steps_per_second": 9.683,
+      "eval_accuracy": 0.8256493506493506,
+      "eval_f1": 0.767139705342691,
+      "eval_loss": 1.6677379608154297,
+      "eval_matthews_correlation": 0.8241228496240458,
+      "eval_runtime": 2.0013,
+      "eval_samples_per_second": 1538.964,
+      "eval_steps_per_second": 9.993,
       "step": 100
     },
     {
       "epoch": 4.55,
-      "eval_accuracy": 0.8993506493506493,
-      "eval_f1": 0.8870749489078757,
-      "eval_loss": 1.5130351781845093,
-      "eval_matthews_correlation": 0.8981291727918667,
-      "eval_runtime": 2.1669,
-      "eval_samples_per_second": 1421.395,
-      "eval_steps_per_second": 9.23,
+      "eval_accuracy": 0.8996753246753246,
+      "eval_f1": 0.8742257380416062,
+      "eval_loss": 1.441461205482483,
+      "eval_matthews_correlation": 0.8983616941255107,
+      "eval_runtime": 2.1335,
+      "eval_samples_per_second": 1443.647,
+      "eval_steps_per_second": 9.374,
       "step": 200
     },
     {
       "epoch": 6.82,
-      "eval_accuracy": 0.9136363636363637,
-      "eval_f1": 0.9133186996102747,
-      "eval_loss": 1.4830034971237183,
-      "eval_matthews_correlation": 0.9124692573548978,
-      "eval_runtime": 2.371,
-      "eval_samples_per_second": 1299.011,
-      "eval_steps_per_second": 8.435,
+      "eval_accuracy": 0.9133116883116883,
+      "eval_f1": 0.9058268969398903,
+      "eval_loss": 1.5148311853408813,
+      "eval_matthews_correlation": 0.9121632434709006,
+      "eval_runtime": 1.9975,
+      "eval_samples_per_second": 1541.892,
+      "eval_steps_per_second": 10.012,
       "step": 300
     },
     {
       "epoch": 9.09,
-      "eval_accuracy": 0.9185064935064935,
-      "eval_f1": 0.9193958955195628,
-      "eval_loss": 1.554843544960022,
-      "eval_matthews_correlation": 0.9174232321481893,
-      "eval_runtime": 2.271,
-      "eval_samples_per_second": 1356.211,
-      "eval_steps_per_second": 8.807,
+      "eval_accuracy": 0.9159090909090909,
+      "eval_f1": 0.9138729195364702,
+      "eval_loss": 1.4601272344589233,
+      "eval_matthews_correlation": 0.9147788306172325,
+      "eval_runtime": 2.2088,
+      "eval_samples_per_second": 1394.406,
+      "eval_steps_per_second": 9.055,
       "step": 400
     },
     {
       "epoch": 11.36,
-      "learning_rate": 5.8164769542877705e-05,
-      "loss": 1.1668,
+      "learning_rate": 3.4771142151811125e-05,
+      "loss": 1.174,
       "step": 500
     },
     {
       "epoch": 11.36,
-      "eval_accuracy": 0.9191558441558442,
-      "eval_f1": 0.9182257657526793,
-      "eval_loss": 1.5733816623687744,
-      "eval_matthews_correlation": 0.9180589419752883,
-      "eval_runtime": 2.1325,
-      "eval_samples_per_second": 1444.348,
-      "eval_steps_per_second": 9.379,
+      "eval_accuracy": 0.922077922077922,
+      "eval_f1": 0.9211670431122725,
+      "eval_loss": 1.521180272102356,
+      "eval_matthews_correlation": 0.921008385091896,
+      "eval_runtime": 2.0276,
+      "eval_samples_per_second": 1519.018,
+      "eval_steps_per_second": 9.864,
       "step": 500
     },
     {
       "epoch": 13.64,
-      "eval_accuracy": 0.9224025974025974,
-      "eval_f1": 0.9222945520415768,
-      "eval_loss": 1.6542637348175049,
-      "eval_matthews_correlation": 0.9213408220142598,
-      "eval_runtime": 2.0559,
-      "eval_samples_per_second": 1498.161,
-      "eval_steps_per_second": 9.728,
+      "eval_accuracy": 0.9123376623376623,
+      "eval_f1": 0.9115878307286494,
+      "eval_loss": 1.61051344871521,
+      "eval_matthews_correlation": 0.9111837360564913,
+      "eval_runtime": 2.3361,
+      "eval_samples_per_second": 1318.452,
+      "eval_steps_per_second": 8.561,
       "step": 600
     },
     {
       "epoch": 15.91,
-      "eval_accuracy": 0.9149350649350649,
-      "eval_f1": 0.9150956940776264,
-      "eval_loss": 1.8008909225463867,
-      "eval_matthews_correlation": 0.9137960558218593,
-      "eval_runtime": 2.1098,
-      "eval_samples_per_second": 1459.849,
-      "eval_steps_per_second": 9.48,
+      "eval_accuracy": 0.9181818181818182,
+      "eval_f1": 0.917226525071442,
+      "eval_loss": 1.6456242799758911,
+      "eval_matthews_correlation": 0.9170990228429879,
+      "eval_runtime": 2.1365,
+      "eval_samples_per_second": 1441.632,
+      "eval_steps_per_second": 9.361,
       "step": 700
     },
     {
       "epoch": 18.18,
-      "eval_accuracy": 0.9185064935064935,
-      "eval_f1": 0.9192382003835077,
-      "eval_loss": 1.7779642343521118,
-      "eval_matthews_correlation": 0.9174120352878115,
-      "eval_runtime": 2.0965,
-      "eval_samples_per_second": 1469.087,
-      "eval_steps_per_second": 9.54,
+      "eval_accuracy": 0.9233766233766234,
+      "eval_f1": 0.9234752474110686,
+      "eval_loss": 1.6500473022460938,
+      "eval_matthews_correlation": 0.9223537552000897,
+      "eval_runtime": 2.0725,
+      "eval_samples_per_second": 1486.112,
+      "eval_steps_per_second": 9.65,
       "step": 800
     },
     {
       "epoch": 20.45,
-      "eval_accuracy": 0.9188311688311688,
-      "eval_f1": 0.9195199493965469,
-      "eval_loss": 1.809897541999817,
-      "eval_matthews_correlation": 0.9177226637064488,
-      "eval_runtime": 2.0723,
-      "eval_samples_per_second": 1486.275,
-      "eval_steps_per_second": 9.651,
+      "eval_accuracy": 0.9246753246753247,
+      "eval_f1": 0.9233254033254772,
+      "eval_loss": 1.6642595529556274,
+      "eval_matthews_correlation": 0.9236535459191428,
+      "eval_runtime": 2.1095,
+      "eval_samples_per_second": 1460.069,
+      "eval_steps_per_second": 9.481,
       "step": 900
     },
     {
       "epoch": 22.73,
-      "learning_rate": 3.50835117877675e-05,
-      "loss": 0.328,
+      "learning_rate": 2.097306986934639e-05,
+      "loss": 0.4421,
       "step": 1000
     },
     {
       "epoch": 22.73,
-      "eval_accuracy": 0.9227272727272727,
-      "eval_f1": 0.922140600587416,
-      "eval_loss": 1.779833197593689,
-      "eval_matthews_correlation": 0.9216768826588398,
-      "eval_runtime": 2.4328,
-      "eval_samples_per_second": 1266.026,
-      "eval_steps_per_second": 8.221,
+      "eval_accuracy": 0.9262987012987013,
+      "eval_f1": 0.9248930548732827,
+      "eval_loss": 1.6844738721847534,
+      "eval_matthews_correlation": 0.925294067680153,
+      "eval_runtime": 2.1099,
+      "eval_samples_per_second": 1459.756,
+      "eval_steps_per_second": 9.479,
       "step": 1000
     },
     {
       "epoch": 25.0,
       "eval_accuracy": 0.9224025974025974,
-      "eval_f1": 0.9226631547186469,
-      "eval_loss": 1.7808905839920044,
-      "eval_matthews_correlation": 0.9213573189813875,
-      "eval_runtime": 2.0917,
-      "eval_samples_per_second": 1472.519,
-      "eval_steps_per_second": 9.562,
+      "eval_f1": 0.9215470321071054,
+      "eval_loss": 1.7112993001937866,
+      "eval_matthews_correlation": 0.9213308887590891,
+      "eval_runtime": 2.057,
+      "eval_samples_per_second": 1497.322,
+      "eval_steps_per_second": 9.723,
       "step": 1100
     },
     {
       "epoch": 27.27,
-      "eval_accuracy": 0.9256493506493506,
-      "eval_f1": 0.9248338905182639,
-      "eval_loss": 1.8451884984970093,
-      "eval_matthews_correlation": 0.9246391668538299,
-      "eval_runtime": 2.1322,
-      "eval_samples_per_second": 1444.526,
-      "eval_steps_per_second": 9.38,
+      "eval_accuracy": 0.9217532467532468,
+      "eval_f1": 0.9211440843843844,
+      "eval_loss": 1.7439706325531006,
+      "eval_matthews_correlation": 0.9206865199959117,
+      "eval_runtime": 2.0759,
+      "eval_samples_per_second": 1483.671,
+      "eval_steps_per_second": 9.634,
       "step": 1200
     },
     {
       "epoch": 29.55,
-      "eval_accuracy": 0.9227272727272727,
-      "eval_f1": 0.9229248003532363,
-      "eval_loss": 1.8795815706253052,
-      "eval_matthews_correlation": 0.9216722690268597,
-      "eval_runtime": 2.0563,
-      "eval_samples_per_second": 1497.833,
-      "eval_steps_per_second": 9.726,
+      "eval_accuracy": 0.9243506493506494,
+      "eval_f1": 0.92433351650032,
+      "eval_loss": 1.7422467470169067,
+      "eval_matthews_correlation": 0.9233063766805053,
+      "eval_runtime": 2.4142,
+      "eval_samples_per_second": 1275.772,
+      "eval_steps_per_second": 8.284,
       "step": 1300
     },
     {
       "epoch": 31.82,
-      "eval_accuracy": 0.923051948051948,
-      "eval_f1": 0.9217473756813872,
-      "eval_loss": 1.837622046470642,
-      "eval_matthews_correlation": 0.9219966197865194,
-      "eval_runtime": 2.137,
-      "eval_samples_per_second": 1441.271,
-      "eval_steps_per_second": 9.359,
+      "eval_accuracy": 0.9246753246753247,
+      "eval_f1": 0.9237776876133245,
+      "eval_loss": 1.743252158164978,
+      "eval_matthews_correlation": 0.923633849522442,
+      "eval_runtime": 2.103,
+      "eval_samples_per_second": 1464.579,
+      "eval_steps_per_second": 9.51,
       "step": 1400
     },
     {
       "epoch": 34.09,
-      "learning_rate": 1.2002254032657304e-05,
-      "loss": 0.0661,
+      "learning_rate": 7.174997586881661e-06,
+      "loss": 0.0852,
       "step": 1500
     },
     {
       "epoch": 34.09,
-      "eval_accuracy": 0.9237012987012987,
-      "eval_f1": 0.9232129873048178,
-      "eval_loss": 1.8602956533432007,
-      "eval_matthews_correlation": 0.9226684176274137,
-      "eval_runtime": 2.1985,
-      "eval_samples_per_second": 1400.979,
-      "eval_steps_per_second": 9.097,
+      "eval_accuracy": 0.9246753246753247,
+      "eval_f1": 0.92363429991791,
+      "eval_loss": 1.7739722728729248,
+      "eval_matthews_correlation": 0.9236362685843384,
+      "eval_runtime": 2.1876,
+      "eval_samples_per_second": 1407.951,
+      "eval_steps_per_second": 9.143,
       "step": 1500
     },
     {
       "epoch": 36.36,
       "eval_accuracy": 0.9237012987012987,
-      "eval_f1": 0.9224910551234583,
-      "eval_loss": 1.8571317195892334,
-      "eval_matthews_correlation": 0.9226584904074349,
-      "eval_runtime": 2.1098,
-      "eval_samples_per_second": 1459.868,
-      "eval_steps_per_second": 9.48,
+      "eval_f1": 0.9226842367802138,
+      "eval_loss": 1.7303967475891113,
+      "eval_matthews_correlation": 0.9226508244383498,
+      "eval_runtime": 2.1475,
+      "eval_samples_per_second": 1434.198,
+      "eval_steps_per_second": 9.313,
       "step": 1600
     }
   ],

checkpoint-1600/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9300b77d824d88fee67f8cbc0a418048d08b001e44b2f49ef13b26b835f03cfe
+oid sha256:6670b8f5e0c1f02cc0c10c54941bd072147753e3cf6a6671e66334c149ccadcf
 size 2927

checkpoint-200/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e7bba471d181812d32755207d15ce10fdfd6581cc2a19c9edaccde1290ff86f
+oid sha256:322bbff489a1a46eaf5cb4e29e93877572d21f4bb5581627e138d59bbf3d1679
 size 1762415977

checkpoint-200/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd71bf825edfe036a8f26153ab36d54a3a3677194f7784b12428bb14d02fa46c
+oid sha256:58e579c1cf9b1c713a67393c189c5294ef9aa105a39a436507e049eae22040fa
 size 440628841

checkpoint-200/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:154df0a467f173429e791edda52881d1040c6e3e281e681ffe16f2e0e3a969c3
+oid sha256:278fe999a13b6c23ed82fd202a0a81ce46392cb9a3b083ff234ca029e92cb067
 size 623

checkpoint-200/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.8996753246753246,
+  "best_metric": 0.8974025974025974,
   "best_model_checkpoint": "mpnet-metric/checkpoint-200",
   "epoch": 4.545454545454545,
   "global_step": 200,
@@ -9,24 +9,24 @@
   "log_history": [
     {
       "epoch": 2.27,
-      "eval_accuracy": 0.8256493506493506,
-      "eval_f1": 0.767139705342691,
-      "eval_loss": 1.6677379608154297,
-      "eval_matthews_correlation": 0.8241228496240458,
-      "eval_runtime": 2.0013,
-      "eval_samples_per_second": 1538.964,
-      "eval_steps_per_second": 9.993,
+      "eval_accuracy": 0.8126623376623376,
+      "eval_f1": 0.7513432596917168,
+      "eval_loss": 1.5586941242218018,
+      "eval_matthews_correlation": 0.8109452297664816,
+      "eval_runtime": 2.288,
+      "eval_samples_per_second": 1346.128,
+      "eval_steps_per_second": 8.741,
       "step": 100
     },
     {
       "epoch": 4.55,
-      "eval_accuracy": 0.8996753246753246,
-      "eval_f1": 0.8742257380416062,
-      "eval_loss": 1.441461205482483,
-      "eval_matthews_correlation": 0.8983616941255107,
-      "eval_runtime": 2.1335,
-      "eval_samples_per_second": 1443.647,
-      "eval_steps_per_second": 9.374,
+      "eval_accuracy": 0.8974025974025974,
+      "eval_f1": 0.8832273830358667,
+      "eval_loss": 1.3632994890213013,
+      "eval_matthews_correlation": 0.8960750775006787,
+      "eval_runtime": 2.1391,
+      "eval_samples_per_second": 1439.854,
+      "eval_steps_per_second": 9.35,
       "step": 200
     }
   ],

checkpoint-200/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6670b8f5e0c1f02cc0c10c54941bd072147753e3cf6a6671e66334c149ccadcf
+oid sha256:7016aa1ad06d1bf337e1916cfc62158dea150004389928efa3ff3987ea83d09f
 size 2927

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4195778be79ae9a71ecb3c03a93808809e9a59ceaaf33020031fa7fdddfcf2cf
+oid sha256:58e579c1cf9b1c713a67393c189c5294ef9aa105a39a436507e049eae22040fa
 size 440628841

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6670b8f5e0c1f02cc0c10c54941bd072147753e3cf6a6671e66334c149ccadcf
+oid sha256:7016aa1ad06d1bf337e1916cfc62158dea150004389928efa3ff3987ea83d09f
 size 2927