End of training

all_results.json

@@ -1,14 +1,14 @@
 {
-    "epoch": 10.0,
-    "eval_accuracy": 0.8104042259990814,
-    "eval_f1": 0.8313368471490178,
-    "eval_loss": 0.5929840803146362,
-    "eval_precision": 0.7980680772769089,
-    "eval_recall": 0.8675,
-    "eval_runtime": 2.4572,
+    "epoch": 26.67,
+    "eval_accuracy": 0.8414101975195223,
+    "eval_f1": 0.8868156150257795,
+    "eval_loss": 0.6016380190849304,
+    "eval_precision": 0.8712011577424024,
+    "eval_recall": 0.903,
+    "eval_runtime": 3.9126,
     "eval_samples": 54,
-    "eval_samples_per_second": 21.976,
-    "eval_steps_per_second": 2.442,
+    "eval_samples_per_second": 13.801,
+    "eval_steps_per_second": 1.533,
     "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": 0.7810765075683593,
-    "train_runtime": 94.7164,
+    "train_loss": 0.3642783355712891,
+    "train_runtime": 422.1629,
     "train_samples": 150,
-    "train_samples_per_second": 15.837,
-    "train_steps_per_second": 1.584
+    "train_samples_per_second": 9.475,
+    "train_steps_per_second": 0.948
 }

eval_results.json

@@ -1,12 +1,12 @@
 {
-    "epoch": 10.0,
-    "eval_accuracy": 0.8104042259990814,
-    "eval_f1": 0.8313368471490178,
-    "eval_loss": 0.5929840803146362,
-    "eval_precision": 0.7980680772769089,
-    "eval_recall": 0.8675,
-    "eval_runtime": 2.4572,
+    "epoch": 26.67,
+    "eval_accuracy": 0.8414101975195223,
+    "eval_f1": 0.8868156150257795,
+    "eval_loss": 0.6016380190849304,
+    "eval_precision": 0.8712011577424024,
+    "eval_recall": 0.903,
+    "eval_runtime": 3.9126,
     "eval_samples": 54,
-    "eval_samples_per_second": 21.976,
-    "eval_steps_per_second": 2.442
+    "eval_samples_per_second": 13.801,
+    "eval_steps_per_second": 1.533
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:841506f6c6c0a194bcb07157467ddcf167f6909db9a6af7260982b8d5abc6e08
+oid sha256:8356f85a16aec70deef67c107e63fd773b89ce3c9d102cc38b7811b85a8d9f28
 size 501420883

runs/Aug24_18-22-33_bernini/1724516563.6851988/events.out.tfevents.1724516563.bernini.17841.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1e8940cb1bbb04e933bcbd75e44e4cc408caedcd13138e70fa304b1bb45082d
+size 4671

runs/Aug24_18-22-33_bernini/events.out.tfevents.1724516563.bernini.17841.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01d0a4d477821d2c2b62e7d108caec6511c646418d088d0de0f0489130766f8f
+size 4088

runs/Aug24_18-32-17_bernini/1724517150.2935843/events.out.tfevents.1724517150.bernini.31282.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:973e343088863c70872623627f05d8a41950c931fb81980efcb6a91b8a765e5c
+size 4671

runs/Aug24_18-32-17_bernini/events.out.tfevents.1724517150.bernini.31282.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1b1e582bc38077dcfc75784c4d8d42dd47878f91fc711614faf3c888bf8d959
+size 4088

runs/Aug24_18-33-02_bernini/1724517195.431775/events.out.tfevents.1724517195.bernini.32539.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b52a187b8f6cbaded77baa92e421ad8931132e5a273f12be0b22f7a476851f1
+size 4671

runs/Aug24_18-33-02_bernini/events.out.tfevents.1724517195.bernini.32539.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6444f0a2b4e3bbc6adf7365c5a20f7fac948204dd9ed7c062a949658f87c2b3c
+size 11949

runs/Aug24_18-33-02_bernini/events.out.tfevents.1724517626.bernini.32539.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02f8bb50b51aa38df749470f03a61b8dcd8867a35578004c2577d86726c3b170
+size 512

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 10.0,
-    "train_loss": 0.7810765075683593,
-    "train_runtime": 94.7164,
+    "epoch": 26.67,
+    "train_loss": 0.3642783355712891,
+    "train_runtime": 422.1629,
     "train_samples": 150,
-    "train_samples_per_second": 15.837,
-    "train_steps_per_second": 1.584
+    "train_samples_per_second": 9.475,
+    "train_steps_per_second": 0.948
 }

trainer_state.json

@@ -1,97 +1,217 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.0,
-  "global_step": 150,
+  "epoch": 26.666666666666668,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.67,
-      "eval_accuracy": 0.6559485530546624,
-      "eval_f1": 0.48850983179341384,
-      "eval_loss": 1.2209023237228394,
-      "eval_precision": 0.46420531292210715,
-      "eval_recall": 0.5155,
-      "eval_runtime": 2.3635,
-      "eval_samples_per_second": 22.848,
-      "eval_steps_per_second": 2.539,
+      "eval_accuracy": 0.6659393661001378,
+      "eval_f1": 0.5035663338088445,
+      "eval_loss": 1.1944581270217896,
+      "eval_precision": 0.4800543970988214,
+      "eval_recall": 0.5295,
+      "eval_runtime": 3.6881,
+      "eval_samples_per_second": 14.641,
+      "eval_steps_per_second": 1.627,
       "step": 25
     },
     {
       "epoch": 3.33,
-      "eval_accuracy": 0.7619430408819476,
-      "eval_f1": 0.7535809662539452,
-      "eval_loss": 0.8171831965446472,
-      "eval_precision": 0.732420953279849,
-      "eval_recall": 0.776,
-      "eval_runtime": 2.3634,
-      "eval_samples_per_second": 22.849,
-      "eval_steps_per_second": 2.539,
+      "eval_accuracy": 0.7687184198438217,
+      "eval_f1": 0.7759615384615385,
+      "eval_loss": 0.7770130038261414,
+      "eval_precision": 0.7472222222222222,
+      "eval_recall": 0.807,
+      "eval_runtime": 3.715,
+      "eval_samples_per_second": 14.536,
+      "eval_steps_per_second": 1.615,
       "step": 50
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.8125861276986679,
-      "eval_f1": 0.8145823273780782,
-      "eval_loss": 0.6125288605690002,
-      "eval_precision": 0.7875816993464052,
-      "eval_recall": 0.8435,
-      "eval_runtime": 2.3662,
-      "eval_samples_per_second": 22.821,
-      "eval_steps_per_second": 2.536,
+      "eval_accuracy": 0.8118971061093248,
+      "eval_f1": 0.8231029482841953,
+      "eval_loss": 0.5989910364151001,
+      "eval_precision": 0.7965388213283442,
+      "eval_recall": 0.8515,
+      "eval_runtime": 3.6727,
+      "eval_samples_per_second": 14.703,
+      "eval_steps_per_second": 1.634,
       "step": 75
     },
     {
       "epoch": 6.67,
-      "eval_accuracy": 0.8107487367937529,
-      "eval_f1": 0.8347784200385356,
-      "eval_loss": 0.5983520150184631,
-      "eval_precision": 0.8052973977695167,
-      "eval_recall": 0.8665,
-      "eval_runtime": 2.4636,
-      "eval_samples_per_second": 21.92,
-      "eval_steps_per_second": 2.436,
+      "eval_accuracy": 0.7702112999540652,
+      "eval_f1": 0.8409471418320977,
+      "eval_loss": 0.6813620924949646,
+      "eval_precision": 0.8060522696011004,
+      "eval_recall": 0.879,
+      "eval_runtime": 3.7496,
+      "eval_samples_per_second": 14.402,
+      "eval_steps_per_second": 1.6,
       "step": 100
     },
     {
       "epoch": 8.33,
-      "eval_accuracy": 0.8216582452916859,
-      "eval_f1": 0.8363723608445298,
-      "eval_loss": 0.5673876404762268,
-      "eval_precision": 0.8039667896678967,
-      "eval_recall": 0.8715,
-      "eval_runtime": 2.3684,
-      "eval_samples_per_second": 22.8,
-      "eval_steps_per_second": 2.533,
+      "eval_accuracy": 0.8316490583371612,
+      "eval_f1": 0.8467469879518073,
+      "eval_loss": 0.5391940474510193,
+      "eval_precision": 0.8172093023255814,
+      "eval_recall": 0.8785,
+      "eval_runtime": 3.7027,
+      "eval_samples_per_second": 14.584,
+      "eval_steps_per_second": 1.62,
       "step": 125
     },
     {
       "epoch": 10.0,
-      "eval_accuracy": 0.8104042259990814,
-      "eval_f1": 0.8313368471490178,
-      "eval_loss": 0.5929840803146362,
-      "eval_precision": 0.7980680772769089,
-      "eval_recall": 0.8675,
-      "eval_runtime": 2.4505,
-      "eval_samples_per_second": 22.036,
-      "eval_steps_per_second": 2.448,
+      "eval_accuracy": 0.811437758383096,
+      "eval_f1": 0.8603297769156159,
+      "eval_loss": 0.5438030362129211,
+      "eval_precision": 0.835216572504708,
+      "eval_recall": 0.887,
+      "eval_runtime": 3.7703,
+      "eval_samples_per_second": 14.322,
+      "eval_steps_per_second": 1.591,
       "step": 150
     },
     {
-      "epoch": 10.0,
-      "step": 150,
-      "total_flos": 395408014848000.0,
-      "train_loss": 0.7810765075683593,
-      "train_runtime": 94.7164,
-      "train_samples_per_second": 15.837,
-      "train_steps_per_second": 1.584
+      "epoch": 11.67,
+      "eval_accuracy": 0.838194763435921,
+      "eval_f1": 0.8752145133611179,
+      "eval_loss": 0.5429797172546387,
+      "eval_precision": 0.8585858585858586,
+      "eval_recall": 0.8925,
+      "eval_runtime": 3.7262,
+      "eval_samples_per_second": 14.492,
+      "eval_steps_per_second": 1.61,
+      "step": 175
+    },
+    {
+      "epoch": 13.33,
+      "eval_accuracy": 0.8257923748277446,
+      "eval_f1": 0.8691817736403724,
+      "eval_loss": 0.5896742939949036,
+      "eval_precision": 0.8520653218059558,
+      "eval_recall": 0.887,
+      "eval_runtime": 3.7744,
+      "eval_samples_per_second": 14.307,
+      "eval_steps_per_second": 1.59,
+      "step": 200
+    },
+    {
+      "epoch": 15.0,
+      "eval_accuracy": 0.8430179145613229,
+      "eval_f1": 0.8809756097560977,
+      "eval_loss": 0.5427059531211853,
+      "eval_precision": 0.86,
+      "eval_recall": 0.903,
+      "eval_runtime": 3.6854,
+      "eval_samples_per_second": 14.652,
+      "eval_steps_per_second": 1.628,
+      "step": 225
+    },
+    {
+      "epoch": 16.67,
+      "eval_accuracy": 0.8410656867248507,
+      "eval_f1": 0.8822512959763021,
+      "eval_loss": 0.5541779398918152,
+      "eval_precision": 0.871282301316431,
+      "eval_recall": 0.8935,
+      "eval_runtime": 3.7194,
+      "eval_samples_per_second": 14.518,
+      "eval_steps_per_second": 1.613,
+      "step": 250
+    },
+    {
+      "epoch": 18.33,
+      "eval_accuracy": 0.83210840606339,
+      "eval_f1": 0.8821515892420537,
+      "eval_loss": 0.6013592481613159,
+      "eval_precision": 0.8631578947368421,
+      "eval_recall": 0.902,
+      "eval_runtime": 3.7675,
+      "eval_samples_per_second": 14.333,
+      "eval_steps_per_second": 1.593,
+      "step": 275
+    },
+    {
+      "epoch": 20.0,
+      "eval_accuracy": 0.8365870463941204,
+      "eval_f1": 0.8843036109064112,
+      "eval_loss": 0.5971384644508362,
+      "eval_precision": 0.8691453404152584,
+      "eval_recall": 0.9,
+      "eval_runtime": 3.72,
+      "eval_samples_per_second": 14.516,
+      "eval_steps_per_second": 1.613,
+      "step": 300
+    },
+    {
+      "epoch": 21.67,
+      "eval_accuracy": 0.8313045475424896,
+      "eval_f1": 0.8891637803067788,
+      "eval_loss": 0.598324716091156,
+      "eval_precision": 0.8800195886385896,
+      "eval_recall": 0.8985,
+      "eval_runtime": 3.78,
+      "eval_samples_per_second": 14.286,
+      "eval_steps_per_second": 1.587,
+      "step": 325
+    },
+    {
+      "epoch": 23.33,
+      "eval_accuracy": 0.8414101975195223,
+      "eval_f1": 0.8964497041420119,
+      "eval_loss": 0.5867139101028442,
+      "eval_precision": 0.8842412451361867,
+      "eval_recall": 0.909,
+      "eval_runtime": 4.0235,
+      "eval_samples_per_second": 13.421,
+      "eval_steps_per_second": 1.491,
+      "step": 350
+    },
+    {
+      "epoch": 25.0,
+      "eval_accuracy": 0.8465778594395957,
+      "eval_f1": 0.8928835262250677,
+      "eval_loss": 0.5947966575622559,
+      "eval_precision": 0.8796700630761766,
+      "eval_recall": 0.9065,
+      "eval_runtime": 3.6989,
+      "eval_samples_per_second": 14.599,
+      "eval_steps_per_second": 1.622,
+      "step": 375
+    },
+    {
+      "epoch": 26.67,
+      "eval_accuracy": 0.8414101975195223,
+      "eval_f1": 0.8868156150257795,
+      "eval_loss": 0.6016380190849304,
+      "eval_precision": 0.8712011577424024,
+      "eval_recall": 0.903,
+      "eval_runtime": 3.6913,
+      "eval_samples_per_second": 14.629,
+      "eval_steps_per_second": 1.625,
+      "step": 400
+    },
+    {
+      "epoch": 26.67,
+      "step": 400,
+      "total_flos": 1054421372928000.0,
+      "train_loss": 0.3642783355712891,
+      "train_runtime": 422.1629,
+      "train_samples_per_second": 9.475,
+      "train_steps_per_second": 0.948
     }
   ],
-  "max_steps": 150,
-  "num_train_epochs": 10,
-  "total_flos": 395408014848000.0,
+  "max_steps": 400,
+  "num_train_epochs": 27,
+  "total_flos": 1054421372928000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67e671d048c6381947443975ece3fe1b7ffa48552b826dcbe8f9155c1dca716d
+oid sha256:c8562d79844654a7b5375505088993c1664cd2a797de81729e592c18046e9651
 size 2927