Upload folder using huggingface_hub

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b05aa72c8805edc2083463c9297e7c8886e44910950afe1ea2aab11cd5a1cae
+oid sha256:247fc2b9ff6d183a31785d3f2a3b4287662c9c74c22d00915bfc7758ee61e6a1
 size 160086542

all_results.json

@@ -1,17 +1,17 @@
 {
     "epoch": 1.0,
-    "eval_accuracy": 0.6666666666666666,
-    "eval_f1_score": 0.6865530303030304,
-    "eval_gmean": 0.587807253097444,
-    "eval_loss": 0.778515636920929,
-    "eval_precision": 0.7180145485665382,
-    "eval_recall": 0.6666666666666666,
-    "eval_runtime": 16.493,
-    "eval_samples_per_second": 3.638,
-    "eval_steps_per_second": 0.485,
+    "eval_accuracy": 0.7666666666666667,
+    "eval_f1_score": 0.7609087348217781,
+    "eval_gmean": 0.7486572528549951,
+    "eval_loss": 0.5165690183639526,
+    "eval_precision": 0.7716666666666666,
+    "eval_recall": 0.7666666666666667,
+    "eval_runtime": 170.2423,
+    "eval_samples_per_second": 0.352,
+    "eval_steps_per_second": 0.047,
     "total_flos": 2.597706419798016e+16,
-    "train_loss": 0.793304885643116,
-    "train_runtime": 5844.8313,
-    "train_samples_per_second": 3.03,
-    "train_steps_per_second": 0.024
+    "train_loss": 0.7354364809782609,
+    "train_runtime": 6240.8638,
+    "train_samples_per_second": 2.838,
+    "train_steps_per_second": 0.022
 }

eval_results.json

@@ -1,12 +1,12 @@
 {
     "epoch": 1.0,
-    "eval_accuracy": 0.6666666666666666,
-    "eval_f1_score": 0.6865530303030304,
-    "eval_gmean": 0.587807253097444,
-    "eval_loss": 0.778515636920929,
-    "eval_precision": 0.7180145485665382,
-    "eval_recall": 0.6666666666666666,
-    "eval_runtime": 16.493,
-    "eval_samples_per_second": 3.638,
-    "eval_steps_per_second": 0.485
+    "eval_accuracy": 0.7666666666666667,
+    "eval_f1_score": 0.7609087348217781,
+    "eval_gmean": 0.7486572528549951,
+    "eval_loss": 0.5165690183639526,
+    "eval_precision": 0.7716666666666666,
+    "eval_recall": 0.7666666666666667,
+    "eval_runtime": 170.2423,
+    "eval_samples_per_second": 0.352,
+    "eval_steps_per_second": 0.047
 }

runs/Apr02_15-26-42_06ec12e6d0c6/events.out.tfevents.1712071604.06ec12e6d0c6.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15684f75daf1c2a6508fcef6bfd39a4b634483fe679b7ecdcb1c8e0eff8f9ab8
+size 10883

runs/Apr02_15-26-42_06ec12e6d0c6/events.out.tfevents.1712078015.06ec12e6d0c6.34.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:731314460feaaf4b8bae44c2ad5501d610219efe3fdedd3c19b1c050313bcabc
+size 615

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
     "total_flos": 2.597706419798016e+16,
-    "train_loss": 0.793304885643116,
-    "train_runtime": 5844.8313,
-    "train_samples_per_second": 3.03,
-    "train_steps_per_second": 0.024
+    "train_loss": 0.7354364809782609,
+    "train_runtime": 6240.8638,
+    "train_samples_per_second": 2.838,
+    "train_steps_per_second": 0.022
 }

trainer_state.json

@@ -10,183 +10,183 @@
   "log_history": [
     {
       "epoch": 0.06,
-      "grad_norm": 23.125,
+      "grad_norm": 4.96875,
       "learning_rate": 1.911764705882353e-05,
-      "loss": 0.9447,
+      "loss": 0.7457,
       "step": 8
     },
     {
       "epoch": 0.12,
-      "grad_norm": 29.25,
+      "grad_norm": 12.75,
       "learning_rate": 1.7941176470588237e-05,
-      "loss": 0.958,
+      "loss": 0.7997,
       "step": 16
     },
     {
       "epoch": 0.17,
-      "grad_norm": 19.0,
+      "grad_norm": 7.5625,
       "learning_rate": 1.6764705882352943e-05,
-      "loss": 0.8606,
+      "loss": 0.7616,
       "step": 24
     },
     {
       "epoch": 0.2,
-      "eval_accuracy": 0.65,
-      "eval_f1_score": 0.6788342559426896,
-      "eval_gmean": 0.6373565754389918,
-      "eval_loss": 0.8578125238418579,
-      "eval_precision": 0.7467592592592592,
-      "eval_recall": 0.65,
-      "eval_runtime": 16.3545,
-      "eval_samples_per_second": 3.669,
-      "eval_steps_per_second": 0.489,
+      "eval_accuracy": 0.7666666666666667,
+      "eval_f1_score": 0.7609087348217781,
+      "eval_gmean": 0.7486572528549951,
+      "eval_loss": 0.5174153447151184,
+      "eval_precision": 0.7716666666666666,
+      "eval_recall": 0.7666666666666667,
+      "eval_runtime": 170.072,
+      "eval_samples_per_second": 0.353,
+      "eval_steps_per_second": 0.047,
       "step": 28
     },
     {
       "epoch": 0.23,
-      "grad_norm": 11.1875,
+      "grad_norm": 18.0,
       "learning_rate": 1.558823529411765e-05,
-      "loss": 0.8073,
+      "loss": 0.7458,
       "step": 32
     },
     {
       "epoch": 0.29,
-      "grad_norm": 10.125,
+      "grad_norm": 7.78125,
       "learning_rate": 1.4411764705882353e-05,
-      "loss": 0.7408,
+      "loss": 0.691,
       "step": 40
     },
     {
       "epoch": 0.35,
-      "grad_norm": 6.75,
+      "grad_norm": 5.78125,
       "learning_rate": 1.323529411764706e-05,
-      "loss": 0.7804,
+      "loss": 0.7286,
       "step": 48
     },
     {
       "epoch": 0.4,
-      "grad_norm": 9.6875,
+      "grad_norm": 6.40625,
       "learning_rate": 1.2058823529411765e-05,
-      "loss": 0.8548,
+      "loss": 0.8156,
       "step": 56
     },
     {
       "epoch": 0.4,
-      "eval_accuracy": 0.6666666666666666,
-      "eval_f1_score": 0.6865530303030304,
-      "eval_gmean": 0.587807253097444,
-      "eval_loss": 0.803906261920929,
-      "eval_precision": 0.7180145485665382,
-      "eval_recall": 0.6666666666666666,
-      "eval_runtime": 16.3685,
-      "eval_samples_per_second": 3.666,
-      "eval_steps_per_second": 0.489,
+      "eval_accuracy": 0.7666666666666667,
+      "eval_f1_score": 0.7609087348217781,
+      "eval_gmean": 0.7486572528549951,
+      "eval_loss": 0.5176106691360474,
+      "eval_precision": 0.7716666666666666,
+      "eval_recall": 0.7666666666666667,
+      "eval_runtime": 170.1289,
+      "eval_samples_per_second": 0.353,
+      "eval_steps_per_second": 0.047,
       "step": 56
     },
     {
       "epoch": 0.46,
-      "grad_norm": 7.15625,
+      "grad_norm": 10.3125,
       "learning_rate": 1.0882352941176471e-05,
-      "loss": 0.7523,
+      "loss": 0.7198,
       "step": 64
     },
     {
       "epoch": 0.52,
-      "grad_norm": 6.90625,
+      "grad_norm": 9.0625,
       "learning_rate": 9.705882352941177e-06,
-      "loss": 0.7838,
+      "loss": 0.7421,
       "step": 72
     },
     {
       "epoch": 0.58,
-      "grad_norm": 10.125,
+      "grad_norm": 6.625,
       "learning_rate": 8.529411764705883e-06,
-      "loss": 0.7783,
+      "loss": 0.7488,
       "step": 80
     },
     {
       "epoch": 0.61,
-      "eval_accuracy": 0.6666666666666666,
-      "eval_f1_score": 0.6865530303030304,
-      "eval_gmean": 0.587807253097444,
-      "eval_loss": 0.7865885496139526,
-      "eval_precision": 0.7180145485665382,
-      "eval_recall": 0.6666666666666666,
-      "eval_runtime": 16.3,
-      "eval_samples_per_second": 3.681,
-      "eval_steps_per_second": 0.491,
+      "eval_accuracy": 0.7666666666666667,
+      "eval_f1_score": 0.7609087348217781,
+      "eval_gmean": 0.7486572528549951,
+      "eval_loss": 0.5164387822151184,
+      "eval_precision": 0.7716666666666666,
+      "eval_recall": 0.7666666666666667,
+      "eval_runtime": 170.831,
+      "eval_samples_per_second": 0.351,
+      "eval_steps_per_second": 0.047,
       "step": 84
     },
     {
       "epoch": 0.64,
-      "grad_norm": 5.65625,
+      "grad_norm": 6.125,
       "learning_rate": 7.352941176470589e-06,
-      "loss": 0.7328,
+      "loss": 0.7045,
       "step": 88
     },
     {
       "epoch": 0.69,
-      "grad_norm": 6.25,
+      "grad_norm": 4.625,
       "learning_rate": 6.176470588235295e-06,
-      "loss": 0.6923,
+      "loss": 0.6564,
       "step": 96
     },
     {
       "epoch": 0.75,
-      "grad_norm": 11.375,
+      "grad_norm": 8.3125,
       "learning_rate": 5e-06,
-      "loss": 0.7355,
+      "loss": 0.7003,
       "step": 104
     },
     {
       "epoch": 0.81,
-      "grad_norm": 10.6875,
+      "grad_norm": 12.9375,
       "learning_rate": 3.8235294117647055e-06,
-      "loss": 0.783,
+      "loss": 0.7528,
       "step": 112
     },
     {
       "epoch": 0.81,
-      "eval_accuracy": 0.6666666666666666,
-      "eval_f1_score": 0.6865530303030304,
-      "eval_gmean": 0.587807253097444,
-      "eval_loss": 0.7805989384651184,
-      "eval_precision": 0.7180145485665382,
-      "eval_recall": 0.6666666666666666,
-      "eval_runtime": 16.5911,
-      "eval_samples_per_second": 3.616,
-      "eval_steps_per_second": 0.482,
+      "eval_accuracy": 0.7666666666666667,
+      "eval_f1_score": 0.7609087348217781,
+      "eval_gmean": 0.7486572528549951,
+      "eval_loss": 0.5166015625,
+      "eval_precision": 0.7716666666666666,
+      "eval_recall": 0.7666666666666667,
+      "eval_runtime": 170.3596,
+      "eval_samples_per_second": 0.352,
+      "eval_steps_per_second": 0.047,
       "step": 112
     },
     {
       "epoch": 0.87,
-      "grad_norm": 8.875,
+      "grad_norm": 7.46875,
       "learning_rate": 2.647058823529412e-06,
-      "loss": 0.7344,
+      "loss": 0.7045,
       "step": 120
     },
     {
       "epoch": 0.92,
-      "grad_norm": 5.28125,
+      "grad_norm": 5.8125,
       "learning_rate": 1.4705882352941177e-06,
-      "loss": 0.7383,
+      "loss": 0.7029,
       "step": 128
     },
     {
       "epoch": 0.98,
-      "grad_norm": 8.125,
+      "grad_norm": 10.1875,
       "learning_rate": 2.9411764705882356e-07,
-      "loss": 0.8187,
+      "loss": 0.7869,
       "step": 136
     },
     {
       "epoch": 1.0,
       "step": 138,
       "total_flos": 2.597706419798016e+16,
-      "train_loss": 0.793304885643116,
-      "train_runtime": 5844.8313,
-      "train_samples_per_second": 3.03,
-      "train_steps_per_second": 0.024
+      "train_loss": 0.7354364809782609,
+      "train_runtime": 6240.8638,
+      "train_samples_per_second": 2.838,
+      "train_steps_per_second": 0.022
     }
   ],
   "logging_steps": 8,