Upload folder using huggingface_hub

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e20f84166792753507ea6124bdd53360db24770abff12c0c1561863e51e82fd7
+oid sha256:95e2a19914eaa14513f860a0e901e2e1f0a0a709a4d92ea72ec0c3c855b69fd8
 size 160086542

all_results.json

@@ -1,17 +1,17 @@
 {
     "epoch": 1.0,
     "eval_accuracy": 0.8166666666666667,
-    "eval_f1_score": 0.8149425287356322,
-    "eval_gmean": 0.7636703179128833,
-    "eval_loss": 0.3408854305744171,
-    "eval_precision": 0.8137310606060607,
+    "eval_f1_score": 0.8080459770114942,
+    "eval_gmean": 0.7501820727030913,
+    "eval_loss": 0.5850911736488342,
+    "eval_precision": 0.8133022774327122,
     "eval_recall": 0.8166666666666667,
-    "eval_runtime": 180.7643,
-    "eval_samples_per_second": 0.332,
-    "eval_steps_per_second": 0.044,
+    "eval_runtime": 175.3378,
+    "eval_samples_per_second": 0.342,
+    "eval_steps_per_second": 0.046,
     "total_flos": 8.435821078904832e+16,
-    "train_loss": 0.43565983558768656,
-    "train_runtime": 13206.8117,
-    "train_samples_per_second": 0.324,
+    "train_loss": 0.405215135261194,
+    "train_runtime": 12957.5785,
+    "train_samples_per_second": 0.33,
     "train_steps_per_second": 0.005
 }

eval_results.json

@@ -1,12 +1,12 @@
 {
     "epoch": 1.0,
     "eval_accuracy": 0.8166666666666667,
-    "eval_f1_score": 0.8149425287356322,
-    "eval_gmean": 0.7636703179128833,
-    "eval_loss": 0.3408854305744171,
-    "eval_precision": 0.8137310606060607,
+    "eval_f1_score": 0.8080459770114942,
+    "eval_gmean": 0.7501820727030913,
+    "eval_loss": 0.5850911736488342,
+    "eval_precision": 0.8133022774327122,
     "eval_recall": 0.8166666666666667,
-    "eval_runtime": 180.7643,
-    "eval_samples_per_second": 0.332,
-    "eval_steps_per_second": 0.044
+    "eval_runtime": 175.3378,
+    "eval_samples_per_second": 0.342,
+    "eval_steps_per_second": 0.046
 }

runs/Apr02_23-40-54_3c3e34ad1384/events.out.tfevents.1712101256.3c3e34ad1384.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c446384ed4b1fb2dcfb64f086d9f3310938be2eea7eb29248560679c1130b9e0
+size 7924

runs/Apr02_23-40-54_3c3e34ad1384/events.out.tfevents.1712114389.3c3e34ad1384.34.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52f220ea6075bb904c8e69b55c315d3315a1a2b6e3cdc8fd0dcb223c65572ece
+size 605

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
     "total_flos": 8.435821078904832e+16,
-    "train_loss": 0.43565983558768656,
-    "train_runtime": 13206.8117,
-    "train_samples_per_second": 0.324,
+    "train_loss": 0.405215135261194,
+    "train_runtime": 12957.5785,
+    "train_samples_per_second": 0.33,
     "train_steps_per_second": 0.005
 }

trainer_state.json

@@ -10,93 +10,93 @@
   "log_history": [
     {
       "epoch": 0.12,
-      "grad_norm": 13.4375,
+      "grad_norm": 9.4375,
       "learning_rate": 1.8153846153846155e-05,
-      "loss": 0.4866,
+      "loss": 0.4282,
       "step": 8
     },
     {
       "epoch": 0.24,
-      "grad_norm": 14.5625,
+      "grad_norm": 10.5,
       "learning_rate": 1.5692307692307693e-05,
-      "loss": 0.4687,
+      "loss": 0.4335,
       "step": 16
     },
     {
       "epoch": 0.36,
-      "grad_norm": 6.6875,
+      "grad_norm": 5.03125,
       "learning_rate": 1.3230769230769231e-05,
-      "loss": 0.4295,
+      "loss": 0.3984,
       "step": 24
     },
     {
       "epoch": 0.42,
       "eval_accuracy": 0.8166666666666667,
-      "eval_f1_score": 0.8149425287356322,
-      "eval_gmean": 0.7636703179128833,
-      "eval_loss": 0.3428385555744171,
-      "eval_precision": 0.8137310606060607,
+      "eval_f1_score": 0.8080459770114942,
+      "eval_gmean": 0.7501820727030913,
+      "eval_loss": 0.5816406011581421,
+      "eval_precision": 0.8133022774327122,
       "eval_recall": 0.8166666666666667,
-      "eval_runtime": 180.8759,
-      "eval_samples_per_second": 0.332,
-      "eval_steps_per_second": 0.044,
+      "eval_runtime": 175.4354,
+      "eval_samples_per_second": 0.342,
+      "eval_steps_per_second": 0.046,
       "step": 28
     },
     {
       "epoch": 0.48,
-      "grad_norm": 6.46875,
+      "grad_norm": 6.625,
       "learning_rate": 1.076923076923077e-05,
-      "loss": 0.4236,
+      "loss": 0.3979,
       "step": 32
     },
     {
       "epoch": 0.6,
-      "grad_norm": 9.8125,
+      "grad_norm": 7.875,
       "learning_rate": 8.307692307692309e-06,
-      "loss": 0.3919,
+      "loss": 0.3657,
       "step": 40
     },
     {
       "epoch": 0.72,
-      "grad_norm": 13.5,
+      "grad_norm": 10.0,
       "learning_rate": 5.846153846153847e-06,
-      "loss": 0.4099,
+      "loss": 0.38,
       "step": 48
     },
     {
       "epoch": 0.84,
-      "grad_norm": 11.4375,
+      "grad_norm": 9.6875,
       "learning_rate": 3.384615384615385e-06,
-      "loss": 0.4242,
+      "loss": 0.4054,
       "step": 56
     },
     {
       "epoch": 0.84,
       "eval_accuracy": 0.8166666666666667,
-      "eval_f1_score": 0.8149425287356322,
-      "eval_gmean": 0.7636703179128833,
-      "eval_loss": 0.34062498807907104,
-      "eval_precision": 0.8137310606060607,
+      "eval_f1_score": 0.8080459770114942,
+      "eval_gmean": 0.7501820727030913,
+      "eval_loss": 0.5850911736488342,
+      "eval_precision": 0.8133022774327122,
       "eval_recall": 0.8166666666666667,
-      "eval_runtime": 180.4163,
-      "eval_samples_per_second": 0.333,
-      "eval_steps_per_second": 0.044,
+      "eval_runtime": 173.49,
+      "eval_samples_per_second": 0.346,
+      "eval_steps_per_second": 0.046,
       "step": 56
     },
     {
       "epoch": 0.96,
-      "grad_norm": 9.3125,
+      "grad_norm": 8.8125,
       "learning_rate": 9.230769230769232e-07,
-      "loss": 0.4092,
+      "loss": 0.3864,
       "step": 64
     },
     {
       "epoch": 1.0,
       "step": 67,
       "total_flos": 8.435821078904832e+16,
-      "train_loss": 0.43565983558768656,
-      "train_runtime": 13206.8117,
-      "train_samples_per_second": 0.324,
+      "train_loss": 0.405215135261194,
+      "train_runtime": 12957.5785,
+      "train_samples_per_second": 0.33,
       "train_steps_per_second": 0.005
     }
   ],