Upload folder using huggingface_hub

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:447a1e485a3f111cf2ef769f24073ec0e50b4a06884a6f49f4dab1d2a562b562
+oid sha256:0052296dbb13857280beac8e7379c6ace74dc1bf153ca9cfe91838b5ffeb957c
 size 160086542

all_results.json

@@ -1,17 +1,17 @@
 {
     "epoch": 0.99,
-    "eval_accuracy": 0.9,
-    "eval_f1_score": 0.9015245623941276,
-    "eval_gmean": 0.8701338213935068,
-    "eval_loss": 0.30312439799308777,
-    "eval_precision": 0.9039473684210526,
-    "eval_recall": 0.9,
-    "eval_runtime": 152.4589,
-    "eval_samples_per_second": 0.328,
-    "eval_steps_per_second": 0.046,
+    "eval_accuracy": 0.86,
+    "eval_f1_score": 0.8597171717171715,
+    "eval_gmean": 0.8574842430349027,
+    "eval_loss": 0.3646777272224426,
+    "eval_precision": 0.8601298701298701,
+    "eval_recall": 0.86,
+    "eval_runtime": 150.5191,
+    "eval_samples_per_second": 0.332,
+    "eval_steps_per_second": 0.047,
     "total_flos": 1.1914693337677824e+17,
-    "train_loss": 0.3471187468497984,
-    "train_runtime": 19325.8318,
-    "train_samples_per_second": 0.31,
+    "train_loss": 0.34092466292842744,
+    "train_runtime": 18751.1569,
+    "train_samples_per_second": 0.32,
     "train_steps_per_second": 0.005
 }

eval_results.json

@@ -1,12 +1,12 @@
 {
     "epoch": 0.99,
-    "eval_accuracy": 0.9,
-    "eval_f1_score": 0.9015245623941276,
-    "eval_gmean": 0.8701338213935068,
-    "eval_loss": 0.30312439799308777,
-    "eval_precision": 0.9039473684210526,
-    "eval_recall": 0.9,
-    "eval_runtime": 152.4589,
-    "eval_samples_per_second": 0.328,
-    "eval_steps_per_second": 0.046
+    "eval_accuracy": 0.86,
+    "eval_f1_score": 0.8597171717171715,
+    "eval_gmean": 0.8574842430349027,
+    "eval_loss": 0.3646777272224426,
+    "eval_precision": 0.8601298701298701,
+    "eval_recall": 0.86,
+    "eval_runtime": 150.5191,
+    "eval_samples_per_second": 0.332,
+    "eval_steps_per_second": 0.047
 }

runs/Apr01_13-37-34_5dac5133c9b9/events.out.tfevents.1711978656.5dac5133c9b9.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4819946a78d86fcd12306830f41c21a53f71520a9af8bb0e93c8d4ef0563cb35
+size 5540

runs/Apr01_15-19-34_d68427716c29/events.out.tfevents.1711984776.d68427716c29.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:131fe0a2407e6defb41d9428fddb6acc5e385d8b98ee55a8e9c1fd8c1f67d208
+size 9095

runs/Apr01_15-19-34_d68427716c29/events.out.tfevents.1712003678.d68427716c29.34.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:199dd9f9a3a018f0b7ab635cbf30107bae878d26b7772163a4d85e7c87846345
+size 605

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 0.99,
     "total_flos": 1.1914693337677824e+17,
-    "train_loss": 0.3471187468497984,
-    "train_runtime": 19325.8318,
-    "train_samples_per_second": 0.31,
+    "train_loss": 0.34092466292842744,
+    "train_runtime": 18751.1569,
+    "train_samples_per_second": 0.32,
     "train_steps_per_second": 0.005
 }

trainer_state.json

@@ -10,127 +10,127 @@
   "log_history": [
     {
       "epoch": 0.09,
-      "grad_norm": 7.34375,
+      "grad_norm": 6.5,
       "learning_rate": 1.8681318681318682e-05,
-      "loss": 0.3872,
+      "loss": 0.338,
       "step": 8
     },
     {
       "epoch": 0.17,
-      "grad_norm": 5.59375,
+      "grad_norm": 6.59375,
       "learning_rate": 1.6923076923076924e-05,
-      "loss": 0.3649,
+      "loss": 0.2964,
       "step": 16
     },
     {
       "epoch": 0.26,
-      "grad_norm": 5.9375,
+      "grad_norm": 4.5625,
       "learning_rate": 1.5164835164835166e-05,
-      "loss": 0.4135,
+      "loss": 0.3441,
       "step": 24
     },
     {
       "epoch": 0.3,
-      "eval_accuracy": 0.9,
-      "eval_f1_score": 0.9015245623941276,
-      "eval_gmean": 0.8701338213935068,
-      "eval_loss": 0.3042968809604645,
-      "eval_precision": 0.9039473684210526,
-      "eval_recall": 0.9,
-      "eval_runtime": 150.7919,
+      "eval_accuracy": 0.86,
+      "eval_f1_score": 0.8597171717171715,
+      "eval_gmean": 0.8574842430349027,
+      "eval_loss": 0.36518555879592896,
+      "eval_precision": 0.8601298701298701,
+      "eval_recall": 0.86,
+      "eval_runtime": 150.657,
       "eval_samples_per_second": 0.332,
       "eval_steps_per_second": 0.046,
       "step": 28
     },
     {
       "epoch": 0.34,
-      "grad_norm": 9.0,
+      "grad_norm": 5.0625,
       "learning_rate": 1.3406593406593406e-05,
-      "loss": 0.3769,
+      "loss": 0.3407,
       "step": 32
     },
     {
       "epoch": 0.43,
-      "grad_norm": 5.71875,
+      "grad_norm": 7.21875,
       "learning_rate": 1.164835164835165e-05,
-      "loss": 0.3004,
+      "loss": 0.3418,
       "step": 40
     },
     {
       "epoch": 0.51,
-      "grad_norm": 6.5625,
+      "grad_norm": 9.75,
       "learning_rate": 9.890109890109892e-06,
-      "loss": 0.3444,
+      "loss": 0.3868,
       "step": 48
     },
     {
       "epoch": 0.6,
-      "grad_norm": 7.6875,
+      "grad_norm": 6.15625,
       "learning_rate": 8.131868131868132e-06,
-      "loss": 0.3599,
+      "loss": 0.3252,
       "step": 56
     },
     {
       "epoch": 0.6,
-      "eval_accuracy": 0.9,
-      "eval_f1_score": 0.9015245623941276,
-      "eval_gmean": 0.8701338213935068,
-      "eval_loss": 0.3040618896484375,
-      "eval_precision": 0.9039473684210526,
-      "eval_recall": 0.9,
-      "eval_runtime": 150.6764,
+      "eval_accuracy": 0.86,
+      "eval_f1_score": 0.8597171717171715,
+      "eval_gmean": 0.8574842430349027,
+      "eval_loss": 0.36469727754592896,
+      "eval_precision": 0.8601298701298701,
+      "eval_recall": 0.86,
+      "eval_runtime": 150.6949,
       "eval_samples_per_second": 0.332,
       "eval_steps_per_second": 0.046,
       "step": 56
     },
     {
       "epoch": 0.68,
-      "grad_norm": 5.78125,
+      "grad_norm": 5.875,
       "learning_rate": 6.373626373626373e-06,
-      "loss": 0.3341,
+      "loss": 0.3562,
       "step": 64
     },
     {
       "epoch": 0.77,
-      "grad_norm": 6.3125,
+      "grad_norm": 7.34375,
       "learning_rate": 4.615384615384616e-06,
-      "loss": 0.3116,
+      "loss": 0.3252,
       "step": 72
     },
     {
       "epoch": 0.85,
-      "grad_norm": 5.53125,
+      "grad_norm": 6.25,
       "learning_rate": 2.8571428571428573e-06,
-      "loss": 0.3222,
+      "loss": 0.3177,
       "step": 80
     },
     {
       "epoch": 0.9,
-      "eval_accuracy": 0.9,
-      "eval_f1_score": 0.9015245623941276,
-      "eval_gmean": 0.8701338213935068,
-      "eval_loss": 0.30312439799308777,
-      "eval_precision": 0.9039473684210526,
-      "eval_recall": 0.9,
-      "eval_runtime": 152.7595,
-      "eval_samples_per_second": 0.327,
+      "eval_accuracy": 0.86,
+      "eval_f1_score": 0.8597171717171715,
+      "eval_gmean": 0.8574842430349027,
+      "eval_loss": 0.3646777272224426,
+      "eval_precision": 0.8601298701298701,
+      "eval_recall": 0.86,
+      "eval_runtime": 150.7321,
+      "eval_samples_per_second": 0.332,
       "eval_steps_per_second": 0.046,
       "step": 84
     },
     {
       "epoch": 0.94,
-      "grad_norm": 7.84375,
+      "grad_norm": 6.9375,
       "learning_rate": 1.098901098901099e-06,
-      "loss": 0.3446,
+      "loss": 0.3777,
       "step": 88
     },
     {
       "epoch": 0.99,
       "step": 93,
       "total_flos": 1.1914693337677824e+17,
-      "train_loss": 0.3471187468497984,
-      "train_runtime": 19325.8318,
-      "train_samples_per_second": 0.31,
+      "train_loss": 0.34092466292842744,
+      "train_runtime": 18751.1569,
+      "train_samples_per_second": 0.32,
       "train_steps_per_second": 0.005
     }
   ],