Upload folder using huggingface_hub

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eea8d06f845a1a769d06a79654cd10d3d7cf85895cc5453a53e42c078aef3a56
+oid sha256:3c165d0b62d01dd989a09b638f70d1e0e4cc65d4e4e67081b177d4fbad18e25a
 size 160086542

all_results.json

@@ -3,15 +3,15 @@
     "eval_accuracy": 0.87,
     "eval_f1_score": 0.8705157155935307,
     "eval_gmean": 0.8715093639362524,
-    "eval_loss": 0.2667187452316284,
+    "eval_loss": 0.26673829555511475,
     "eval_precision": 0.8726060606060605,
     "eval_recall": 0.87,
-    "eval_runtime": 309.7776,
-    "eval_samples_per_second": 0.323,
-    "eval_steps_per_second": 0.042,
+    "eval_runtime": 328.4912,
+    "eval_samples_per_second": 0.304,
+    "eval_steps_per_second": 0.04,
     "total_flos": 1.0505428534296576e+17,
-    "train_loss": 0.3787797137004573,
-    "train_runtime": 19813.7509,
-    "train_samples_per_second": 0.265,
+    "train_loss": 0.3696013659965701,
+    "train_runtime": 20858.2303,
+    "train_samples_per_second": 0.252,
     "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": 0.2667187452316284,
+    "eval_loss": 0.26673829555511475,
     "eval_precision": 0.8726060606060605,
     "eval_recall": 0.87,
-    "eval_runtime": 309.7776,
-    "eval_samples_per_second": 0.323,
-    "eval_steps_per_second": 0.042
+    "eval_runtime": 328.4912,
+    "eval_samples_per_second": 0.304,
+    "eval_steps_per_second": 0.04
 }

runs/Mar24_13-56-33_e36e00e32a40/events.out.tfevents.1711288595.e36e00e32a40.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34a5e5e0d8f384d1c94ae371bd561b39a97b7054ee569fb1433a9a41d0bb5657
+size 12485

runs/Mar24_13-56-33_e36e00e32a40/events.out.tfevents.1711309782.e36e00e32a40.34.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbbe88cafdb1007213dd246dcec3e4747c62a8a5dd2635d72cf9ff965c5aa593
+size 605

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
     "total_flos": 1.0505428534296576e+17,
-    "train_loss": 0.3787797137004573,
-    "train_runtime": 19813.7509,
-    "train_samples_per_second": 0.265,
+    "train_loss": 0.3696013659965701,
+    "train_runtime": 20858.2303,
+    "train_samples_per_second": 0.252,
     "train_steps_per_second": 0.004
 }

trainer_state.json

@@ -10,9 +10,9 @@
   "log_history": [
     {
       "epoch": 0.1,
-      "grad_norm": 6.65625,
+      "grad_norm": 6.875,
       "learning_rate": 1.8500000000000002e-05,
-      "loss": 0.3472,
+      "loss": 0.3831,
       "step": 8
     },
     {
@@ -20,19 +20,19 @@
       "eval_accuracy": 0.87,
       "eval_f1_score": 0.8705157155935307,
       "eval_gmean": 0.8715093639362524,
-      "eval_loss": 0.26746582984924316,
+      "eval_loss": 0.2664209008216858,
       "eval_precision": 0.8726060606060605,
       "eval_recall": 0.87,
-      "eval_runtime": 310.6143,
-      "eval_samples_per_second": 0.322,
-      "eval_steps_per_second": 0.042,
+      "eval_runtime": 325.1061,
+      "eval_samples_per_second": 0.308,
+      "eval_steps_per_second": 0.04,
       "step": 8
     },
     {
       "epoch": 0.19,
-      "grad_norm": 6.25,
+      "grad_norm": 7.4375,
       "learning_rate": 1.65e-05,
-      "loss": 0.389,
+      "loss": 0.3261,
       "step": 16
     },
     {
@@ -40,19 +40,19 @@
       "eval_accuracy": 0.87,
       "eval_f1_score": 0.8705157155935307,
       "eval_gmean": 0.8715093639362524,
-      "eval_loss": 0.26725587248802185,
+      "eval_loss": 0.26719239354133606,
       "eval_precision": 0.8726060606060605,
       "eval_recall": 0.87,
-      "eval_runtime": 310.2803,
-      "eval_samples_per_second": 0.322,
-      "eval_steps_per_second": 0.042,
+      "eval_runtime": 325.6461,
+      "eval_samples_per_second": 0.307,
+      "eval_steps_per_second": 0.04,
       "step": 16
     },
     {
       "epoch": 0.29,
-      "grad_norm": 5.375,
+      "grad_norm": 10.5625,
       "learning_rate": 1.45e-05,
-      "loss": 0.352,
+      "loss": 0.3721,
       "step": 24
     },
     {
@@ -60,19 +60,19 @@
       "eval_accuracy": 0.87,
       "eval_f1_score": 0.8705157155935307,
       "eval_gmean": 0.8715093639362524,
-      "eval_loss": 0.26688477396965027,
+      "eval_loss": 0.2671875059604645,
       "eval_precision": 0.8726060606060605,
       "eval_recall": 0.87,
-      "eval_runtime": 310.5692,
-      "eval_samples_per_second": 0.322,
-      "eval_steps_per_second": 0.042,
+      "eval_runtime": 325.3707,
+      "eval_samples_per_second": 0.307,
+      "eval_steps_per_second": 0.04,
       "step": 24
     },
     {
       "epoch": 0.39,
-      "grad_norm": 8.0625,
+      "grad_norm": 9.5,
       "learning_rate": 1.25e-05,
-      "loss": 0.4521,
+      "loss": 0.3582,
       "step": 32
     },
     {
@@ -80,19 +80,19 @@
       "eval_accuracy": 0.87,
       "eval_f1_score": 0.8705157155935307,
       "eval_gmean": 0.8715093639362524,
-      "eval_loss": 0.26634764671325684,
+      "eval_loss": 0.2667529284954071,
       "eval_precision": 0.8726060606060605,
       "eval_recall": 0.87,
-      "eval_runtime": 310.415,
-      "eval_samples_per_second": 0.322,
-      "eval_steps_per_second": 0.042,
+      "eval_runtime": 325.8406,
+      "eval_samples_per_second": 0.307,
+      "eval_steps_per_second": 0.04,
       "step": 32
     },
     {
       "epoch": 0.49,
-      "grad_norm": 8.375,
+      "grad_norm": 5.84375,
       "learning_rate": 1.0500000000000001e-05,
-      "loss": 0.3804,
+      "loss": 0.4175,
       "step": 40
     },
     {
@@ -100,19 +100,19 @@
       "eval_accuracy": 0.87,
       "eval_f1_score": 0.8705157155935307,
       "eval_gmean": 0.8715093639362524,
-      "eval_loss": 0.2668701112270355,
+      "eval_loss": 0.26649415493011475,
       "eval_precision": 0.8726060606060605,
       "eval_recall": 0.87,
-      "eval_runtime": 310.2383,
-      "eval_samples_per_second": 0.322,
-      "eval_steps_per_second": 0.042,
+      "eval_runtime": 325.6291,
+      "eval_samples_per_second": 0.307,
+      "eval_steps_per_second": 0.04,
       "step": 40
     },
     {
       "epoch": 0.58,
-      "grad_norm": 5.4375,
+      "grad_norm": 4.90625,
       "learning_rate": 8.5e-06,
-      "loss": 0.3733,
+      "loss": 0.2994,
       "step": 48
     },
     {
@@ -120,19 +120,19 @@
       "eval_accuracy": 0.87,
       "eval_f1_score": 0.8705157155935307,
       "eval_gmean": 0.8715093639362524,
-      "eval_loss": 0.2667285203933716,
+      "eval_loss": 0.2669140696525574,
       "eval_precision": 0.8726060606060605,
       "eval_recall": 0.87,
-      "eval_runtime": 309.8771,
-      "eval_samples_per_second": 0.323,
-      "eval_steps_per_second": 0.042,
+      "eval_runtime": 325.6436,
+      "eval_samples_per_second": 0.307,
+      "eval_steps_per_second": 0.04,
       "step": 48
     },
     {
       "epoch": 0.68,
-      "grad_norm": 7.34375,
+      "grad_norm": 7.375,
       "learning_rate": 6.5000000000000004e-06,
-      "loss": 0.4229,
+      "loss": 0.3524,
       "step": 56
     },
     {
@@ -140,19 +140,19 @@
       "eval_accuracy": 0.87,
       "eval_f1_score": 0.8705157155935307,
       "eval_gmean": 0.8715093639362524,
-      "eval_loss": 0.26664063334465027,
+      "eval_loss": 0.2667480409145355,
       "eval_precision": 0.8726060606060605,
       "eval_recall": 0.87,
-      "eval_runtime": 309.6906,
-      "eval_samples_per_second": 0.323,
-      "eval_steps_per_second": 0.042,
+      "eval_runtime": 328.7964,
+      "eval_samples_per_second": 0.304,
+      "eval_steps_per_second": 0.04,
       "step": 56
     },
     {
       "epoch": 0.78,
-      "grad_norm": 8.3125,
+      "grad_norm": 5.40625,
       "learning_rate": 4.5e-06,
-      "loss": 0.3482,
+      "loss": 0.3961,
       "step": 64
     },
     {
@@ -160,19 +160,19 @@
       "eval_accuracy": 0.87,
       "eval_f1_score": 0.8705157155935307,
       "eval_gmean": 0.8715093639362524,
-      "eval_loss": 0.2667187452316284,
+      "eval_loss": 0.26673829555511475,
       "eval_precision": 0.8726060606060605,
       "eval_recall": 0.87,
-      "eval_runtime": 309.8874,
-      "eval_samples_per_second": 0.323,
-      "eval_steps_per_second": 0.042,
+      "eval_runtime": 327.9706,
+      "eval_samples_per_second": 0.305,
+      "eval_steps_per_second": 0.04,
       "step": 64
     },
     {
       "epoch": 0.88,
-      "grad_norm": 6.375,
+      "grad_norm": 8.3125,
       "learning_rate": 2.5e-06,
-      "loss": 0.3726,
+      "loss": 0.4341,
       "step": 72
     },
     {
@@ -180,19 +180,19 @@
       "eval_accuracy": 0.87,
       "eval_f1_score": 0.8705157155935307,
       "eval_gmean": 0.8715093639362524,
-      "eval_loss": 0.2667187452316284,
+      "eval_loss": 0.26673829555511475,
       "eval_precision": 0.8726060606060605,
       "eval_recall": 0.87,
-      "eval_runtime": 310.1642,
-      "eval_samples_per_second": 0.322,
-      "eval_steps_per_second": 0.042,
+      "eval_runtime": 328.7312,
+      "eval_samples_per_second": 0.304,
+      "eval_steps_per_second": 0.04,
       "step": 72
     },
     {
       "epoch": 0.97,
-      "grad_norm": 6.53125,
+      "grad_norm": 6.3125,
       "learning_rate": 5.000000000000001e-07,
-      "loss": 0.3522,
+      "loss": 0.3743,
       "step": 80
     },
     {
@@ -200,21 +200,21 @@
       "eval_accuracy": 0.87,
       "eval_f1_score": 0.8705157155935307,
       "eval_gmean": 0.8715093639362524,
-      "eval_loss": 0.2667187452316284,
+      "eval_loss": 0.26673829555511475,
       "eval_precision": 0.8726060606060605,
       "eval_recall": 0.87,
-      "eval_runtime": 309.8306,
-      "eval_samples_per_second": 0.323,
-      "eval_steps_per_second": 0.042,
+      "eval_runtime": 328.568,
+      "eval_samples_per_second": 0.304,
+      "eval_steps_per_second": 0.04,
       "step": 80
     },
     {
       "epoch": 1.0,
       "step": 82,
       "total_flos": 1.0505428534296576e+17,
-      "train_loss": 0.3787797137004573,
-      "train_runtime": 19813.7509,
-      "train_samples_per_second": 0.265,
+      "train_loss": 0.3696013659965701,
+      "train_runtime": 20858.2303,
+      "train_samples_per_second": 0.252,
       "train_steps_per_second": 0.004
     }
   ],