Upload folder using huggingface_hub

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b349cc388254688729bb2bee539e11e35048cffe1a215edda714ab0e5e576f87
+oid sha256:0e8bc85aa083b75a30b7ba295a754ce02e0c5fadb33d7e0468f13c629931a720
 size 160086542

all_results.json

@@ -1,17 +1,17 @@
 {
     "epoch": 0.99,
-    "eval_accuracy": 0.8,
-    "eval_f1_score": 0.7993558776167471,
-    "eval_gmean": 0.7980746061134115,
-    "eval_loss": 0.5084765553474426,
-    "eval_precision": 0.8012987012987013,
-    "eval_recall": 0.8,
-    "eval_runtime": 158.4717,
-    "eval_samples_per_second": 0.316,
-    "eval_steps_per_second": 0.044,
+    "eval_accuracy": 0.82,
+    "eval_f1_score": 0.8184577723378215,
+    "eval_gmean": 0.8139876199369547,
+    "eval_loss": 0.33375000953674316,
+    "eval_precision": 0.8230000000000001,
+    "eval_recall": 0.82,
+    "eval_runtime": 163.2928,
+    "eval_samples_per_second": 0.306,
+    "eval_steps_per_second": 0.043,
     "total_flos": 1.1914693337677824e+17,
-    "train_loss": 0.3557273290490591,
-    "train_runtime": 19662.2913,
-    "train_samples_per_second": 0.305,
+    "train_loss": 0.34641749884492606,
+    "train_runtime": 20162.3344,
+    "train_samples_per_second": 0.298,
     "train_steps_per_second": 0.005
 }

eval_results.json

@@ -1,12 +1,12 @@
 {
     "epoch": 0.99,
-    "eval_accuracy": 0.8,
-    "eval_f1_score": 0.7993558776167471,
-    "eval_gmean": 0.7980746061134115,
-    "eval_loss": 0.5084765553474426,
-    "eval_precision": 0.8012987012987013,
-    "eval_recall": 0.8,
-    "eval_runtime": 158.4717,
-    "eval_samples_per_second": 0.316,
-    "eval_steps_per_second": 0.044
+    "eval_accuracy": 0.82,
+    "eval_f1_score": 0.8184577723378215,
+    "eval_gmean": 0.8139876199369547,
+    "eval_loss": 0.33375000953674316,
+    "eval_precision": 0.8230000000000001,
+    "eval_recall": 0.82,
+    "eval_runtime": 163.2928,
+    "eval_samples_per_second": 0.306,
+    "eval_steps_per_second": 0.043
 }

runs/Mar31_18-25-38_a22c766383b5/events.out.tfevents.1711909540.a22c766383b5.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b7755fac8c174276415b660caa3a37263a2aff2e2d9d347068aaec3b0457168
+size 9095

runs/Mar31_18-25-38_a22c766383b5/events.out.tfevents.1711929866.a22c766383b5.34.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62fe50438adbafc6ccd74de88b333c865460e8ed8b927f662013574f5846e9d7
+size 605

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 0.99,
     "total_flos": 1.1914693337677824e+17,
-    "train_loss": 0.3557273290490591,
-    "train_runtime": 19662.2913,
-    "train_samples_per_second": 0.305,
+    "train_loss": 0.34641749884492606,
+    "train_runtime": 20162.3344,
+    "train_samples_per_second": 0.298,
     "train_steps_per_second": 0.005
 }

trainer_state.json

@@ -10,127 +10,127 @@
   "log_history": [
     {
       "epoch": 0.09,
-      "grad_norm": 6.0,
+      "grad_norm": 6.78125,
       "learning_rate": 1.8681318681318682e-05,
-      "loss": 0.266,
+      "loss": 0.3728,
       "step": 8
     },
     {
       "epoch": 0.17,
-      "grad_norm": 8.75,
+      "grad_norm": 5.03125,
       "learning_rate": 1.6923076923076924e-05,
-      "loss": 0.404,
+      "loss": 0.353,
       "step": 16
     },
     {
       "epoch": 0.26,
-      "grad_norm": 7.90625,
+      "grad_norm": 6.5,
       "learning_rate": 1.5164835164835166e-05,
-      "loss": 0.4084,
+      "loss": 0.3137,
       "step": 24
     },
     {
       "epoch": 0.3,
-      "eval_accuracy": 0.8,
-      "eval_f1_score": 0.7993558776167471,
-      "eval_gmean": 0.7980746061134115,
-      "eval_loss": 0.5118359327316284,
-      "eval_precision": 0.8012987012987013,
-      "eval_recall": 0.8,
-      "eval_runtime": 158.1221,
-      "eval_samples_per_second": 0.316,
-      "eval_steps_per_second": 0.044,
+      "eval_accuracy": 0.82,
+      "eval_f1_score": 0.8184577723378215,
+      "eval_gmean": 0.8139876199369547,
+      "eval_loss": 0.33320313692092896,
+      "eval_precision": 0.8230000000000001,
+      "eval_recall": 0.82,
+      "eval_runtime": 163.4252,
+      "eval_samples_per_second": 0.306,
+      "eval_steps_per_second": 0.043,
       "step": 28
     },
     {
       "epoch": 0.34,
-      "grad_norm": 6.84375,
+      "grad_norm": 7.40625,
       "learning_rate": 1.3406593406593406e-05,
-      "loss": 0.3697,
+      "loss": 0.3488,
       "step": 32
     },
     {
       "epoch": 0.43,
-      "grad_norm": 5.9375,
+      "grad_norm": 4.375,
       "learning_rate": 1.164835164835165e-05,
-      "loss": 0.3647,
+      "loss": 0.3013,
       "step": 40
     },
     {
       "epoch": 0.51,
-      "grad_norm": 7.1875,
+      "grad_norm": 8.375,
       "learning_rate": 9.890109890109892e-06,
-      "loss": 0.3738,
+      "loss": 0.4057,
       "step": 48
     },
     {
       "epoch": 0.6,
-      "grad_norm": 6.46875,
+      "grad_norm": 5.90625,
       "learning_rate": 8.131868131868132e-06,
-      "loss": 0.3298,
+      "loss": 0.3598,
       "step": 56
     },
     {
       "epoch": 0.6,
-      "eval_accuracy": 0.8,
-      "eval_f1_score": 0.7993558776167471,
-      "eval_gmean": 0.7980746061134115,
-      "eval_loss": 0.5087890625,
-      "eval_precision": 0.8012987012987013,
-      "eval_recall": 0.8,
-      "eval_runtime": 158.641,
-      "eval_samples_per_second": 0.315,
-      "eval_steps_per_second": 0.044,
+      "eval_accuracy": 0.82,
+      "eval_f1_score": 0.8184577723378215,
+      "eval_gmean": 0.8139876199369547,
+      "eval_loss": 0.3338281214237213,
+      "eval_precision": 0.8230000000000001,
+      "eval_recall": 0.82,
+      "eval_runtime": 163.4717,
+      "eval_samples_per_second": 0.306,
+      "eval_steps_per_second": 0.043,
       "step": 56
     },
     {
       "epoch": 0.68,
-      "grad_norm": 6.75,
+      "grad_norm": 7.6875,
       "learning_rate": 6.373626373626373e-06,
-      "loss": 0.333,
+      "loss": 0.295,
       "step": 64
     },
     {
       "epoch": 0.77,
-      "grad_norm": 7.3125,
+      "grad_norm": 6.8125,
       "learning_rate": 4.615384615384616e-06,
-      "loss": 0.3813,
+      "loss": 0.3881,
       "step": 72
     },
     {
       "epoch": 0.85,
-      "grad_norm": 6.5,
+      "grad_norm": 5.90625,
       "learning_rate": 2.8571428571428573e-06,
-      "loss": 0.3403,
+      "loss": 0.3761,
       "step": 80
     },
     {
       "epoch": 0.9,
-      "eval_accuracy": 0.8,
-      "eval_f1_score": 0.7993558776167471,
-      "eval_gmean": 0.7980746061134115,
-      "eval_loss": 0.5084765553474426,
-      "eval_precision": 0.8012987012987013,
-      "eval_recall": 0.8,
-      "eval_runtime": 158.2765,
-      "eval_samples_per_second": 0.316,
-      "eval_steps_per_second": 0.044,
+      "eval_accuracy": 0.82,
+      "eval_f1_score": 0.8184577723378215,
+      "eval_gmean": 0.8139876199369547,
+      "eval_loss": 0.33375000953674316,
+      "eval_precision": 0.8230000000000001,
+      "eval_recall": 0.82,
+      "eval_runtime": 163.4454,
+      "eval_samples_per_second": 0.306,
+      "eval_steps_per_second": 0.043,
       "step": 84
     },
     {
       "epoch": 0.94,
-      "grad_norm": 6.84375,
+      "grad_norm": 4.96875,
       "learning_rate": 1.098901098901099e-06,
-      "loss": 0.3473,
+      "loss": 0.2953,
       "step": 88
     },
     {
       "epoch": 0.99,
       "step": 93,
       "total_flos": 1.1914693337677824e+17,
-      "train_loss": 0.3557273290490591,
-      "train_runtime": 19662.2913,
-      "train_samples_per_second": 0.305,
+      "train_loss": 0.34641749884492606,
+      "train_runtime": 20162.3344,
+      "train_samples_per_second": 0.298,
       "train_steps_per_second": 0.005
     }
   ],