updated model

.gitattributes

@@ -1,27 +0,0 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bin.* filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text 
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zstandard filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85664bbaf71e4f311de8791de77401a054335a20fd02e6362a5f325405bb97bc
+oid sha256:a0b561c6e0dd9c4a622129fc7e3c03a4bb31e56e681b1ac328bb817f3c5fbd29
 size 2224487441

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8374f88d473c09806c2de0ce5e9f02739bb6f0c87c8dd5c2a649c0cfd67bd027
+oid sha256:dd13fbac6d222ca915cb37bf59229e9697893c4f3de078f3619b8adb2a46091d
 size 1112271305

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aceba6248022075c5e64facf8ac618b8db0d55d396da9419df77273617db6f40
+oid sha256:b56bb5b378c122568841f7e569b8cbba0a8481e509e1db9bfd8f2288b4f98d52
 size 14657

trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.7989452316551693,
+  "best_metric": 0.7736625514403291,
   "best_model_checkpoint": "OS_OUT/harish/PT-UP-xlmR-FalseFalse-0_0_BEST/FalseFalse-0/2/checkpoint-40",
   "epoch": 8.0,
   "global_step": 40,
@@ -10,81 +10,81 @@
     {
       "epoch": 1.0,
       "eval_accuracy": 0.6300366520881653,
-      "eval_f1": 0.6314656194864177,
+      "eval_f1": 0.597609561752988,
       "eval_loss": 0.6447749137878418,
-      "eval_runtime": 0.7699,
-      "eval_samples_per_second": 354.583,
-      "eval_steps_per_second": 45.459,
+      "eval_runtime": 0.7675,
+      "eval_samples_per_second": 355.702,
+      "eval_steps_per_second": 45.603,
       "step": 5
     },
     {
       "epoch": 2.0,
       "eval_accuracy": 0.6813187003135681,
-      "eval_f1": 0.6795802519632642,
+      "eval_f1": 0.6200873362445415,
       "eval_loss": 0.5641180872917175,
-      "eval_runtime": 0.7712,
-      "eval_samples_per_second": 354.008,
-      "eval_steps_per_second": 45.386,
+      "eval_runtime": 0.7675,
+      "eval_samples_per_second": 355.721,
+      "eval_steps_per_second": 45.605,
       "step": 10
     },
     {
       "epoch": 3.0,
       "eval_accuracy": 0.7289377450942993,
-      "eval_f1": 0.7198230619283251,
+      "eval_f1": 0.6372549019607843,
       "eval_loss": 0.5698391795158386,
-      "eval_runtime": 0.7731,
-      "eval_samples_per_second": 353.121,
-      "eval_steps_per_second": 45.272,
+      "eval_runtime": 0.7673,
+      "eval_samples_per_second": 355.789,
+      "eval_steps_per_second": 45.614,
       "step": 15
     },
     {
       "epoch": 4.0,
       "eval_accuracy": 0.7289377450942993,
-      "eval_f1": 0.7299802761341222,
+      "eval_f1": 0.7153846153846154,
       "eval_loss": 0.5229743719100952,
-      "eval_runtime": 0.7777,
-      "eval_samples_per_second": 351.029,
-      "eval_steps_per_second": 45.004,
+      "eval_runtime": 0.7688,
+      "eval_samples_per_second": 355.082,
+      "eval_steps_per_second": 45.523,
       "step": 20
     },
     {
       "epoch": 5.0,
       "eval_accuracy": 0.7582417726516724,
-      "eval_f1": 0.7592382294429708,
+      "eval_f1": 0.7421875,
       "eval_loss": 0.5236229300498962,
-      "eval_runtime": 0.776,
-      "eval_samples_per_second": 351.819,
-      "eval_steps_per_second": 45.105,
+      "eval_runtime": 0.7675,
+      "eval_samples_per_second": 355.716,
+      "eval_steps_per_second": 45.605,
       "step": 25
     },
     {
       "epoch": 6.0,
       "eval_accuracy": 0.7655677795410156,
-      "eval_f1": 0.7641127492170192,
+      "eval_f1": 0.719298245614035,
       "eval_loss": 0.5164700150489807,
-      "eval_runtime": 0.7781,
-      "eval_samples_per_second": 350.85,
-      "eval_steps_per_second": 44.981,
+      "eval_runtime": 0.7779,
+      "eval_samples_per_second": 350.939,
+      "eval_steps_per_second": 44.992,
       "step": 30
     },
     {
       "epoch": 7.0,
       "eval_accuracy": 0.791208803653717,
-      "eval_f1": 0.7917637180095652,
+      "eval_f1": 0.7673469387755103,
       "eval_loss": 0.5138589143753052,
-      "eval_runtime": 0.7815,
-      "eval_samples_per_second": 349.344,
-      "eval_steps_per_second": 44.788,
+      "eval_runtime": 0.7778,
+      "eval_samples_per_second": 350.983,
+      "eval_steps_per_second": 44.998,
       "step": 35
     },
     {
       "epoch": 8.0,
       "eval_accuracy": 0.7985348105430603,
-      "eval_f1": 0.7989452316551693,
+      "eval_f1": 0.7736625514403291,
       "eval_loss": 0.5282412767410278,
-      "eval_runtime": 0.775,
-      "eval_samples_per_second": 352.252,
-      "eval_steps_per_second": 45.16,
+      "eval_runtime": 0.7588,
+      "eval_samples_per_second": 359.786,
+      "eval_steps_per_second": 46.126,
       "step": 40
     }
   ],

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb6b2d159bf34926f44f4ad85ed0f4ff3150d1c8ade5076ffed4381fe98805e8
+oid sha256:6ffe57bc3d408cea27bfc025869d1f0fe364485d3bf45695239aa98d20d4dd92
 size 2735