End of training

all_results.json

@@ -1,14 +1,14 @@
 {
     "epoch": 26.67,
-    "eval_accuracy": 0.8472668810289389,
-    "eval_f1": 0.9070631970260222,
-    "eval_loss": 0.8292201161384583,
-    "eval_precision": 0.8992628992628993,
-    "eval_recall": 0.915,
-    "eval_runtime": 3.7663,
+    "eval_accuracy": 0.8414101975195223,
+    "eval_f1": 0.8868156150257795,
+    "eval_loss": 0.6016380190849304,
+    "eval_precision": 0.8712011577424024,
+    "eval_recall": 0.903,
+    "eval_runtime": 3.7201,
     "eval_samples": 54,
-    "eval_samples_per_second": 14.338,
-    "eval_steps_per_second": 1.593,
+    "eval_samples_per_second": 14.516,
+    "eval_steps_per_second": 1.613,
     "predict_accuracy": 0.8218373936014088,
     "predict_f1": 0.9038133181559477,
     "predict_loss": 0.6888472437858582,
@@ -17,9 +17,9 @@
     "predict_runtime": 2.0596,
     "predict_samples_per_second": 8.74,
     "predict_steps_per_second": 0.971,
-    "train_loss": 0.23747550964355468,
-    "train_runtime": 422.9436,
+    "train_loss": 0.3642783355712891,
+    "train_runtime": 422.552,
     "train_samples": 150,
-    "train_samples_per_second": 9.458,
-    "train_steps_per_second": 0.946
+    "train_samples_per_second": 9.466,
+    "train_steps_per_second": 0.947
 }

eval_results.json

@@ -1,12 +1,12 @@
 {
     "epoch": 26.67,
-    "eval_accuracy": 0.8472668810289389,
-    "eval_f1": 0.9070631970260222,
-    "eval_loss": 0.8292201161384583,
-    "eval_precision": 0.8992628992628993,
-    "eval_recall": 0.915,
-    "eval_runtime": 3.7663,
+    "eval_accuracy": 0.8414101975195223,
+    "eval_f1": 0.8868156150257795,
+    "eval_loss": 0.6016380190849304,
+    "eval_precision": 0.8712011577424024,
+    "eval_recall": 0.903,
+    "eval_runtime": 3.7201,
     "eval_samples": 54,
-    "eval_samples_per_second": 14.338,
-    "eval_steps_per_second": 1.593
+    "eval_samples_per_second": 14.516,
+    "eval_steps_per_second": 1.613
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cccafe3ee6c7777239da85ed0fd1a57b6880a4a472915b408a120b0a2f81081
+oid sha256:8356f85a16aec70deef67c107e63fd773b89ce3c9d102cc38b7811b85a8d9f28
 size 501420883

runs/Aug24_18-54-42_bernini/1724518492.3371837/events.out.tfevents.1724518492.bernini.1037.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3cd699b00c94a44e6ca0e74ec37104488c83275ffaf0362c2ee3c990559b242
+size 4665

runs/Aug24_18-54-42_bernini/events.out.tfevents.1724518492.bernini.1037.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4de822d225c11c0d9e01c4ac3b89baf5ba187ba9b2fe33fa6494c0bcf80bc713
+size 11945

runs/Aug24_18-54-42_bernini/events.out.tfevents.1724518923.bernini.1037.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e1f5c7bbc9adcc5e99a82487c7c62900589be70d2ec018ffb7a5a5babb97b06
+size 512

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 26.67,
-    "train_loss": 0.23747550964355468,
-    "train_runtime": 422.9436,
+    "train_loss": 0.3642783355712891,
+    "train_runtime": 422.552,
     "train_samples": 150,
-    "train_samples_per_second": 9.458,
-    "train_steps_per_second": 0.946
+    "train_samples_per_second": 9.466,
+    "train_steps_per_second": 0.947
 }

trainer_state.json

@@ -9,204 +9,204 @@
   "log_history": [
     {
       "epoch": 1.67,
-      "eval_accuracy": 0.743913642627469,
-      "eval_f1": 0.728670634920635,
-      "eval_loss": 0.8680385947227478,
-      "eval_precision": 0.7229330708661418,
-      "eval_recall": 0.7345,
-      "eval_runtime": 3.6798,
-      "eval_samples_per_second": 14.675,
-      "eval_steps_per_second": 1.631,
+      "eval_accuracy": 0.6659393661001378,
+      "eval_f1": 0.5035663338088445,
+      "eval_loss": 1.1944581270217896,
+      "eval_precision": 0.4800543970988214,
+      "eval_recall": 0.5295,
+      "eval_runtime": 3.6912,
+      "eval_samples_per_second": 14.629,
+      "eval_steps_per_second": 1.625,
       "step": 25
     },
     {
       "epoch": 3.33,
-      "eval_accuracy": 0.821773082223243,
-      "eval_f1": 0.8277523488316069,
-      "eval_loss": 0.5806225538253784,
-      "eval_precision": 0.798698279869828,
-      "eval_recall": 0.859,
-      "eval_runtime": 3.6893,
-      "eval_samples_per_second": 14.637,
-      "eval_steps_per_second": 1.626,
+      "eval_accuracy": 0.7687184198438217,
+      "eval_f1": 0.7759615384615385,
+      "eval_loss": 0.7770130038261414,
+      "eval_precision": 0.7472222222222222,
+      "eval_recall": 0.807,
+      "eval_runtime": 3.7057,
+      "eval_samples_per_second": 14.572,
+      "eval_steps_per_second": 1.619,
       "step": 50
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.8143086816720257,
-      "eval_f1": 0.8518784398181383,
-      "eval_loss": 0.5963883399963379,
-      "eval_precision": 0.8168884809545663,
-      "eval_recall": 0.89,
-      "eval_runtime": 3.7336,
-      "eval_samples_per_second": 14.463,
-      "eval_steps_per_second": 1.607,
+      "eval_accuracy": 0.8118971061093248,
+      "eval_f1": 0.8231029482841953,
+      "eval_loss": 0.5989910364151001,
+      "eval_precision": 0.7965388213283442,
+      "eval_recall": 0.8515,
+      "eval_runtime": 3.6962,
+      "eval_samples_per_second": 14.61,
+      "eval_steps_per_second": 1.623,
       "step": 75
     },
     {
       "epoch": 6.67,
-      "eval_accuracy": 0.8248736793752871,
-      "eval_f1": 0.8816108685104318,
-      "eval_loss": 0.5634802579879761,
-      "eval_precision": 0.8562676720075401,
-      "eval_recall": 0.9085,
-      "eval_runtime": 3.7322,
-      "eval_samples_per_second": 14.469,
-      "eval_steps_per_second": 1.608,
+      "eval_accuracy": 0.7702112999540652,
+      "eval_f1": 0.8409471418320977,
+      "eval_loss": 0.6813620924949646,
+      "eval_precision": 0.8060522696011004,
+      "eval_recall": 0.879,
+      "eval_runtime": 3.7519,
+      "eval_samples_per_second": 14.393,
+      "eval_steps_per_second": 1.599,
       "step": 100
     },
     {
       "epoch": 8.33,
-      "eval_accuracy": 0.8344051446945338,
-      "eval_f1": 0.8806224167274495,
-      "eval_loss": 0.6465535163879395,
-      "eval_precision": 0.8570752484619025,
-      "eval_recall": 0.9055,
-      "eval_runtime": 3.6961,
-      "eval_samples_per_second": 14.61,
-      "eval_steps_per_second": 1.623,
+      "eval_accuracy": 0.8316490583371612,
+      "eval_f1": 0.8467469879518073,
+      "eval_loss": 0.5391940474510193,
+      "eval_precision": 0.8172093023255814,
+      "eval_recall": 0.8785,
+      "eval_runtime": 3.7222,
+      "eval_samples_per_second": 14.508,
+      "eval_steps_per_second": 1.612,
       "step": 125
     },
     {
       "epoch": 10.0,
-      "eval_accuracy": 0.8325677537896188,
-      "eval_f1": 0.8935960591133005,
-      "eval_loss": 0.6587353944778442,
-      "eval_precision": 0.8805825242718447,
-      "eval_recall": 0.907,
-      "eval_runtime": 3.8161,
-      "eval_samples_per_second": 14.151,
-      "eval_steps_per_second": 1.572,
+      "eval_accuracy": 0.811437758383096,
+      "eval_f1": 0.8603297769156159,
+      "eval_loss": 0.5438030362129211,
+      "eval_precision": 0.835216572504708,
+      "eval_recall": 0.887,
+      "eval_runtime": 3.7662,
+      "eval_samples_per_second": 14.338,
+      "eval_steps_per_second": 1.593,
       "step": 150
     },
     {
       "epoch": 11.67,
-      "eval_accuracy": 0.837620578778135,
-      "eval_f1": 0.8977886977886977,
-      "eval_loss": 0.698390543460846,
-      "eval_precision": 0.8826086956521739,
-      "eval_recall": 0.9135,
-      "eval_runtime": 3.7001,
-      "eval_samples_per_second": 14.594,
-      "eval_steps_per_second": 1.622,
+      "eval_accuracy": 0.838194763435921,
+      "eval_f1": 0.8752145133611179,
+      "eval_loss": 0.5429797172546387,
+      "eval_precision": 0.8585858585858586,
+      "eval_recall": 0.8925,
+      "eval_runtime": 3.7544,
+      "eval_samples_per_second": 14.383,
+      "eval_steps_per_second": 1.598,
       "step": 175
     },
     {
       "epoch": 13.33,
-      "eval_accuracy": 0.843706936150666,
-      "eval_f1": 0.9129898940103525,
-      "eval_loss": 0.696682870388031,
-      "eval_precision": 0.9003403014098201,
-      "eval_recall": 0.926,
-      "eval_runtime": 3.7624,
-      "eval_samples_per_second": 14.353,
-      "eval_steps_per_second": 1.595,
+      "eval_accuracy": 0.8257923748277446,
+      "eval_f1": 0.8691817736403724,
+      "eval_loss": 0.5896742939949036,
+      "eval_precision": 0.8520653218059558,
+      "eval_recall": 0.887,
+      "eval_runtime": 3.775,
+      "eval_samples_per_second": 14.305,
+      "eval_steps_per_second": 1.589,
       "step": 200
     },
     {
       "epoch": 15.0,
-      "eval_accuracy": 0.8450849793293523,
-      "eval_f1": 0.9041708043694141,
-      "eval_loss": 0.7260191440582275,
-      "eval_precision": 0.8979289940828402,
-      "eval_recall": 0.9105,
-      "eval_runtime": 3.7153,
-      "eval_samples_per_second": 14.535,
-      "eval_steps_per_second": 1.615,
+      "eval_accuracy": 0.8430179145613229,
+      "eval_f1": 0.8809756097560977,
+      "eval_loss": 0.5427059531211853,
+      "eval_precision": 0.86,
+      "eval_recall": 0.903,
+      "eval_runtime": 3.6868,
+      "eval_samples_per_second": 14.647,
+      "eval_steps_per_second": 1.627,
       "step": 225
     },
     {
       "epoch": 16.67,
-      "eval_accuracy": 0.8510564997703262,
-      "eval_f1": 0.9003944773175543,
-      "eval_loss": 0.7542734742164612,
-      "eval_precision": 0.8881322957198443,
-      "eval_recall": 0.913,
-      "eval_runtime": 3.8842,
-      "eval_samples_per_second": 13.903,
-      "eval_steps_per_second": 1.545,
+      "eval_accuracy": 0.8410656867248507,
+      "eval_f1": 0.8822512959763021,
+      "eval_loss": 0.5541779398918152,
+      "eval_precision": 0.871282301316431,
+      "eval_recall": 0.8935,
+      "eval_runtime": 3.7479,
+      "eval_samples_per_second": 14.408,
+      "eval_steps_per_second": 1.601,
       "step": 250
     },
     {
       "epoch": 18.33,
-      "eval_accuracy": 0.844855305466238,
-      "eval_f1": 0.898422090729783,
-      "eval_loss": 0.7764595746994019,
-      "eval_precision": 0.8861867704280155,
-      "eval_recall": 0.911,
-      "eval_runtime": 3.7089,
-      "eval_samples_per_second": 14.56,
-      "eval_steps_per_second": 1.618,
+      "eval_accuracy": 0.83210840606339,
+      "eval_f1": 0.8821515892420537,
+      "eval_loss": 0.6013592481613159,
+      "eval_precision": 0.8631578947368421,
+      "eval_recall": 0.902,
+      "eval_runtime": 3.7532,
+      "eval_samples_per_second": 14.388,
+      "eval_steps_per_second": 1.599,
       "step": 275
     },
     {
       "epoch": 20.0,
-      "eval_accuracy": 0.8473817179604961,
-      "eval_f1": 0.9038365719980069,
-      "eval_loss": 0.8023993968963623,
-      "eval_precision": 0.900695134061569,
-      "eval_recall": 0.907,
-      "eval_runtime": 3.6987,
-      "eval_samples_per_second": 14.6,
-      "eval_steps_per_second": 1.622,
+      "eval_accuracy": 0.8365870463941204,
+      "eval_f1": 0.8843036109064112,
+      "eval_loss": 0.5971384644508362,
+      "eval_precision": 0.8691453404152584,
+      "eval_recall": 0.9,
+      "eval_runtime": 3.7851,
+      "eval_samples_per_second": 14.267,
+      "eval_steps_per_second": 1.585,
       "step": 300
     },
     {
       "epoch": 21.67,
-      "eval_accuracy": 0.8509416628387689,
-      "eval_f1": 0.9098584554258753,
-      "eval_loss": 0.814669132232666,
-      "eval_precision": 0.9037987173162308,
-      "eval_recall": 0.916,
-      "eval_runtime": 3.712,
-      "eval_samples_per_second": 14.547,
-      "eval_steps_per_second": 1.616,
+      "eval_accuracy": 0.8313045475424896,
+      "eval_f1": 0.8891637803067788,
+      "eval_loss": 0.598324716091156,
+      "eval_precision": 0.8800195886385896,
+      "eval_recall": 0.8985,
+      "eval_runtime": 3.7401,
+      "eval_samples_per_second": 14.438,
+      "eval_steps_per_second": 1.604,
       "step": 325
     },
     {
       "epoch": 23.33,
-      "eval_accuracy": 0.8510564997703262,
-      "eval_f1": 0.9098136645962732,
-      "eval_loss": 0.8133536577224731,
-      "eval_precision": 0.9041975308641975,
-      "eval_recall": 0.9155,
-      "eval_runtime": 3.7319,
-      "eval_samples_per_second": 14.47,
-      "eval_steps_per_second": 1.608,
+      "eval_accuracy": 0.8414101975195223,
+      "eval_f1": 0.8964497041420119,
+      "eval_loss": 0.5867139101028442,
+      "eval_precision": 0.8842412451361867,
+      "eval_recall": 0.909,
+      "eval_runtime": 3.7391,
+      "eval_samples_per_second": 14.442,
+      "eval_steps_per_second": 1.605,
       "step": 350
     },
     {
       "epoch": 25.0,
-      "eval_accuracy": 0.846692696371153,
-      "eval_f1": 0.9083229813664596,
-      "eval_loss": 0.8293821811676025,
-      "eval_precision": 0.9027160493827161,
-      "eval_recall": 0.914,
-      "eval_runtime": 3.6785,
-      "eval_samples_per_second": 14.68,
-      "eval_steps_per_second": 1.631,
+      "eval_accuracy": 0.8465778594395957,
+      "eval_f1": 0.8928835262250677,
+      "eval_loss": 0.5947966575622559,
+      "eval_precision": 0.8796700630761766,
+      "eval_recall": 0.9065,
+      "eval_runtime": 3.6661,
+      "eval_samples_per_second": 14.73,
+      "eval_steps_per_second": 1.637,
       "step": 375
     },
     {
       "epoch": 26.67,
-      "eval_accuracy": 0.8472668810289389,
-      "eval_f1": 0.9070631970260222,
-      "eval_loss": 0.8292201161384583,
-      "eval_precision": 0.8992628992628993,
-      "eval_recall": 0.915,
-      "eval_runtime": 3.7118,
-      "eval_samples_per_second": 14.548,
-      "eval_steps_per_second": 1.616,
+      "eval_accuracy": 0.8414101975195223,
+      "eval_f1": 0.8868156150257795,
+      "eval_loss": 0.6016380190849304,
+      "eval_precision": 0.8712011577424024,
+      "eval_recall": 0.903,
+      "eval_runtime": 3.6984,
+      "eval_samples_per_second": 14.601,
+      "eval_steps_per_second": 1.622,
       "step": 400
     },
     {
       "epoch": 26.67,
       "step": 400,
       "total_flos": 1054421372928000.0,
-      "train_loss": 0.23747550964355468,
-      "train_runtime": 422.9436,
-      "train_samples_per_second": 9.458,
-      "train_steps_per_second": 0.946
+      "train_loss": 0.3642783355712891,
+      "train_runtime": 422.552,
+      "train_samples_per_second": 9.466,
+      "train_steps_per_second": 0.947
     }
   ],
   "max_steps": 400,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2966ff448a4928b45d06f166b511b270ce1009954dfb204cae97cf2a3dabe1ce
+oid sha256:18524bbd71a9c1f456e0c326136d3674e674011210065da46f04684edfe11cdc
 size 2927