Upload folder using huggingface_hub

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bfec96e37ef6634530ef3293f303bd6acefe9e3e6d6abfe2f6ce7328f075f8a
+oid sha256:eea8d06f845a1a769d06a79654cd10d3d7cf85895cc5453a53e42c078aef3a56
 size 160086542

all_results.json

@@ -3,15 +3,15 @@
     "eval_accuracy": 0.87,
     "eval_f1_score": 0.8705157155935307,
     "eval_gmean": 0.8715093639362524,
-    "eval_loss": 0.26869142055511475,
+    "eval_loss": 0.2667187452316284,
     "eval_precision": 0.8726060606060605,
     "eval_recall": 0.87,
-    "eval_runtime": 308.1312,
-    "eval_samples_per_second": 0.325,
+    "eval_runtime": 309.7776,
+    "eval_samples_per_second": 0.323,
     "eval_steps_per_second": 0.042,
     "total_flos": 1.0505428534296576e+17,
-    "train_loss": 0.3734391375285823,
-    "train_runtime": 19598.5588,
-    "train_samples_per_second": 0.268,
+    "train_loss": 0.3787797137004573,
+    "train_runtime": 19813.7509,
+    "train_samples_per_second": 0.265,
     "train_steps_per_second": 0.004
 }

eval_results.json

@@ -3,10 +3,10 @@
     "eval_accuracy": 0.87,
     "eval_f1_score": 0.8705157155935307,
     "eval_gmean": 0.8715093639362524,
-    "eval_loss": 0.26869142055511475,
+    "eval_loss": 0.2667187452316284,
     "eval_precision": 0.8726060606060605,
     "eval_recall": 0.87,
-    "eval_runtime": 308.1312,
-    "eval_samples_per_second": 0.325,
+    "eval_runtime": 309.7776,
+    "eval_samples_per_second": 0.323,
     "eval_steps_per_second": 0.042
 }

runs/Mar24_01-32-58_77c662717e8e/events.out.tfevents.1711243980.77c662717e8e.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fff90242e3e059111b0dc4126a278997143f621895aa71e29698c6568050dc87
+size 12485

runs/Mar24_01-32-58_77c662717e8e/events.out.tfevents.1711264104.77c662717e8e.34.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:419d16146e12c90c674fa5522a64739f1d9eeb02e073afca9a74b29cd61aab66
+size 605

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
     "total_flos": 1.0505428534296576e+17,
-    "train_loss": 0.3734391375285823,
-    "train_runtime": 19598.5588,
-    "train_samples_per_second": 0.268,
+    "train_loss": 0.3787797137004573,
+    "train_runtime": 19813.7509,
+    "train_samples_per_second": 0.265,
     "train_steps_per_second": 0.004
 }

trainer_state.json

@@ -10,9 +10,9 @@
   "log_history": [
     {
       "epoch": 0.1,
-      "grad_norm": 6.96875,
+      "grad_norm": 6.65625,
       "learning_rate": 1.8500000000000002e-05,
-      "loss": 0.3825,
+      "loss": 0.3472,
       "step": 8
     },
     {
@@ -20,19 +20,19 @@
       "eval_accuracy": 0.87,
       "eval_f1_score": 0.8705157155935307,
       "eval_gmean": 0.8715093639362524,
-      "eval_loss": 0.27127930521965027,
+      "eval_loss": 0.26746582984924316,
       "eval_precision": 0.8726060606060605,
       "eval_recall": 0.87,
-      "eval_runtime": 308.2568,
-      "eval_samples_per_second": 0.324,
+      "eval_runtime": 310.6143,
+      "eval_samples_per_second": 0.322,
       "eval_steps_per_second": 0.042,
       "step": 8
     },
     {
       "epoch": 0.19,
-      "grad_norm": 8.0625,
+      "grad_norm": 6.25,
       "learning_rate": 1.65e-05,
-      "loss": 0.3684,
+      "loss": 0.389,
       "step": 16
     },
     {
@@ -40,19 +40,19 @@
       "eval_accuracy": 0.87,
       "eval_f1_score": 0.8705157155935307,
       "eval_gmean": 0.8715093639362524,
-      "eval_loss": 0.27037107944488525,
+      "eval_loss": 0.26725587248802185,
       "eval_precision": 0.8726060606060605,
       "eval_recall": 0.87,
-      "eval_runtime": 308.6792,
-      "eval_samples_per_second": 0.324,
+      "eval_runtime": 310.2803,
+      "eval_samples_per_second": 0.322,
       "eval_steps_per_second": 0.042,
       "step": 16
     },
     {
       "epoch": 0.29,
-      "grad_norm": 7.1875,
+      "grad_norm": 5.375,
       "learning_rate": 1.45e-05,
-      "loss": 0.3846,
+      "loss": 0.352,
       "step": 24
     },
     {
@@ -60,19 +60,19 @@
       "eval_accuracy": 0.87,
       "eval_f1_score": 0.8705157155935307,
       "eval_gmean": 0.8715093639362524,
-      "eval_loss": 0.26976072788238525,
+      "eval_loss": 0.26688477396965027,
       "eval_precision": 0.8726060606060605,
       "eval_recall": 0.87,
-      "eval_runtime": 308.4781,
-      "eval_samples_per_second": 0.324,
+      "eval_runtime": 310.5692,
+      "eval_samples_per_second": 0.322,
       "eval_steps_per_second": 0.042,
       "step": 24
     },
     {
       "epoch": 0.39,
-      "grad_norm": 6.96875,
+      "grad_norm": 8.0625,
       "learning_rate": 1.25e-05,
-      "loss": 0.368,
+      "loss": 0.4521,
       "step": 32
     },
     {
@@ -80,19 +80,19 @@
       "eval_accuracy": 0.87,
       "eval_f1_score": 0.8705157155935307,
       "eval_gmean": 0.8715093639362524,
-      "eval_loss": 0.26942384243011475,
+      "eval_loss": 0.26634764671325684,
       "eval_precision": 0.8726060606060605,
       "eval_recall": 0.87,
-      "eval_runtime": 308.2201,
-      "eval_samples_per_second": 0.324,
+      "eval_runtime": 310.415,
+      "eval_samples_per_second": 0.322,
       "eval_steps_per_second": 0.042,
       "step": 32
     },
     {
       "epoch": 0.49,
-      "grad_norm": 6.34375,
+      "grad_norm": 8.375,
       "learning_rate": 1.0500000000000001e-05,
-      "loss": 0.3954,
+      "loss": 0.3804,
       "step": 40
     },
     {
@@ -100,19 +100,19 @@
       "eval_accuracy": 0.87,
       "eval_f1_score": 0.8705157155935307,
       "eval_gmean": 0.8715093639362524,
-      "eval_loss": 0.26915037631988525,
+      "eval_loss": 0.2668701112270355,
       "eval_precision": 0.8726060606060605,
       "eval_recall": 0.87,
-      "eval_runtime": 308.3621,
-      "eval_samples_per_second": 0.324,
+      "eval_runtime": 310.2383,
+      "eval_samples_per_second": 0.322,
       "eval_steps_per_second": 0.042,
       "step": 40
     },
     {
       "epoch": 0.58,
-      "grad_norm": 5.28125,
+      "grad_norm": 5.4375,
       "learning_rate": 8.5e-06,
-      "loss": 0.3952,
+      "loss": 0.3733,
       "step": 48
     },
     {
@@ -120,19 +120,19 @@
       "eval_accuracy": 0.87,
       "eval_f1_score": 0.8705157155935307,
       "eval_gmean": 0.8715093639362524,
-      "eval_loss": 0.2691015601158142,
+      "eval_loss": 0.2667285203933716,
       "eval_precision": 0.8726060606060605,
       "eval_recall": 0.87,
-      "eval_runtime": 307.9578,
-      "eval_samples_per_second": 0.325,
+      "eval_runtime": 309.8771,
+      "eval_samples_per_second": 0.323,
       "eval_steps_per_second": 0.042,
       "step": 48
     },
     {
       "epoch": 0.68,
-      "grad_norm": 5.65625,
+      "grad_norm": 7.34375,
       "learning_rate": 6.5000000000000004e-06,
-      "loss": 0.368,
+      "loss": 0.4229,
       "step": 56
     },
     {
@@ -140,19 +140,19 @@
       "eval_accuracy": 0.87,
       "eval_f1_score": 0.8705157155935307,
       "eval_gmean": 0.8715093639362524,
-      "eval_loss": 0.2687695324420929,
+      "eval_loss": 0.26664063334465027,
       "eval_precision": 0.8726060606060605,
       "eval_recall": 0.87,
-      "eval_runtime": 308.2935,
-      "eval_samples_per_second": 0.324,
+      "eval_runtime": 309.6906,
+      "eval_samples_per_second": 0.323,
       "eval_steps_per_second": 0.042,
       "step": 56
     },
     {
       "epoch": 0.78,
-      "grad_norm": 6.03125,
+      "grad_norm": 8.3125,
       "learning_rate": 4.5e-06,
-      "loss": 0.3826,
+      "loss": 0.3482,
       "step": 64
     },
     {
@@ -160,19 +160,19 @@
       "eval_accuracy": 0.87,
       "eval_f1_score": 0.8705157155935307,
       "eval_gmean": 0.8715093639362524,
-      "eval_loss": 0.26869142055511475,
+      "eval_loss": 0.2667187452316284,
       "eval_precision": 0.8726060606060605,
       "eval_recall": 0.87,
-      "eval_runtime": 307.9498,
-      "eval_samples_per_second": 0.325,
+      "eval_runtime": 309.8874,
+      "eval_samples_per_second": 0.323,
       "eval_steps_per_second": 0.042,
       "step": 64
     },
     {
       "epoch": 0.88,
-      "grad_norm": 10.0,
+      "grad_norm": 6.375,
       "learning_rate": 2.5e-06,
-      "loss": 0.3254,
+      "loss": 0.3726,
       "step": 72
     },
     {
@@ -180,19 +180,19 @@
       "eval_accuracy": 0.87,
       "eval_f1_score": 0.8705157155935307,
       "eval_gmean": 0.8715093639362524,
-      "eval_loss": 0.26869142055511475,
+      "eval_loss": 0.2667187452316284,
       "eval_precision": 0.8726060606060605,
       "eval_recall": 0.87,
-      "eval_runtime": 308.1218,
-      "eval_samples_per_second": 0.325,
+      "eval_runtime": 310.1642,
+      "eval_samples_per_second": 0.322,
       "eval_steps_per_second": 0.042,
       "step": 72
     },
     {
       "epoch": 0.97,
-      "grad_norm": 8.75,
+      "grad_norm": 6.53125,
       "learning_rate": 5.000000000000001e-07,
-      "loss": 0.3547,
+      "loss": 0.3522,
       "step": 80
     },
     {
@@ -200,11 +200,11 @@
       "eval_accuracy": 0.87,
       "eval_f1_score": 0.8705157155935307,
       "eval_gmean": 0.8715093639362524,
-      "eval_loss": 0.26869142055511475,
+      "eval_loss": 0.2667187452316284,
       "eval_precision": 0.8726060606060605,
       "eval_recall": 0.87,
-      "eval_runtime": 308.2047,
-      "eval_samples_per_second": 0.324,
+      "eval_runtime": 309.8306,
+      "eval_samples_per_second": 0.323,
       "eval_steps_per_second": 0.042,
       "step": 80
     },
@@ -212,9 +212,9 @@
       "epoch": 1.0,
       "step": 82,
       "total_flos": 1.0505428534296576e+17,
-      "train_loss": 0.3734391375285823,
-      "train_runtime": 19598.5588,
-      "train_samples_per_second": 0.268,
+      "train_loss": 0.3787797137004573,
+      "train_runtime": 19813.7509,
+      "train_samples_per_second": 0.265,
       "train_steps_per_second": 0.004
     }
   ],