Upload folder using huggingface_hub

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d661b5d8e28c6286c4f688153e59f25326218295967aead1da1fcca840dd8cde
+oid sha256:e1f061d4fe605304382b94e7f5a8f2230c7c7ba50f77add04cea55be514ab750
 size 160086542

all_results.json

@@ -1,17 +1,17 @@
 {
     "epoch": 1.0,
-    "eval_accuracy": 0.72,
-    "eval_f1_score": 0.7154911433172302,
-    "eval_gmean": 0.7399824497743348,
-    "eval_loss": 0.6498633027076721,
-    "eval_precision": 0.7727777777777777,
-    "eval_recall": 0.72,
-    "eval_runtime": 137.6618,
-    "eval_samples_per_second": 0.363,
-    "eval_steps_per_second": 0.051,
+    "eval_accuracy": 0.7666666666666667,
+    "eval_f1_score": 0.7677224736048267,
+    "eval_gmean": 0.765713693437345,
+    "eval_loss": 0.5444498658180237,
+    "eval_precision": 0.7704826038159371,
+    "eval_recall": 0.7666666666666667,
+    "eval_runtime": 188.2947,
+    "eval_samples_per_second": 0.319,
+    "eval_steps_per_second": 0.042,
     "total_flos": 8.468389371174912e+16,
-    "train_loss": 0.9084581972947762,
-    "train_runtime": 14096.0939,
-    "train_samples_per_second": 0.304,
+    "train_loss": 0.6622405550373134,
+    "train_runtime": 13770.5671,
+    "train_samples_per_second": 0.311,
     "train_steps_per_second": 0.005
 }

eval_results.json

@@ -1,12 +1,12 @@
 {
     "epoch": 1.0,
-    "eval_accuracy": 0.72,
-    "eval_f1_score": 0.7154911433172302,
-    "eval_gmean": 0.7399824497743348,
-    "eval_loss": 0.6498633027076721,
-    "eval_precision": 0.7727777777777777,
-    "eval_recall": 0.72,
-    "eval_runtime": 137.6618,
-    "eval_samples_per_second": 0.363,
-    "eval_steps_per_second": 0.051
+    "eval_accuracy": 0.7666666666666667,
+    "eval_f1_score": 0.7677224736048267,
+    "eval_gmean": 0.765713693437345,
+    "eval_loss": 0.5444498658180237,
+    "eval_precision": 0.7704826038159371,
+    "eval_recall": 0.7666666666666667,
+    "eval_runtime": 188.2947,
+    "eval_samples_per_second": 0.319,
+    "eval_steps_per_second": 0.042
 }

runs/Apr02_02-36-30_f5b09d025ffe/events.out.tfevents.1712025392.f5b09d025ffe.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e95d7c987cf1c6cb9f8e9fbe5806720a6e344b8f47d6a1b136006d1eeee2427
+size 7948

runs/Apr02_02-36-30_f5b09d025ffe/events.out.tfevents.1712039351.f5b09d025ffe.34.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7d0cbf5246eea7aa31fe78df556d504877c2f52b3ebfb061b5ca5bf0c05f9c7
+size 605

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
     "total_flos": 8.468389371174912e+16,
-    "train_loss": 0.9084581972947762,
-    "train_runtime": 14096.0939,
-    "train_samples_per_second": 0.304,
+    "train_loss": 0.6622405550373134,
+    "train_runtime": 13770.5671,
+    "train_samples_per_second": 0.311,
     "train_steps_per_second": 0.005
 }

trainer_state.json

@@ -10,93 +10,93 @@
   "log_history": [
     {
       "epoch": 0.12,
-      "grad_norm": 47.25,
+      "grad_norm": 34.75,
       "learning_rate": 1.8153846153846155e-05,
-      "loss": 1.1395,
+      "loss": 0.7945,
       "step": 8
     },
     {
       "epoch": 0.24,
-      "grad_norm": 39.75,
+      "grad_norm": 28.25,
       "learning_rate": 1.5692307692307693e-05,
-      "loss": 1.0434,
+      "loss": 0.7456,
       "step": 16
     },
     {
       "epoch": 0.36,
-      "grad_norm": 42.0,
+      "grad_norm": 27.5,
       "learning_rate": 1.3230769230769231e-05,
-      "loss": 0.8923,
+      "loss": 0.6596,
       "step": 24
     },
     {
       "epoch": 0.42,
-      "eval_accuracy": 0.66,
-      "eval_f1_score": 0.6473765809873521,
-      "eval_gmean": 0.6861694917646597,
-      "eval_loss": 0.692578136920929,
-      "eval_precision": 0.7367619047619047,
-      "eval_recall": 0.66,
-      "eval_runtime": 137.4001,
-      "eval_samples_per_second": 0.364,
-      "eval_steps_per_second": 0.051,
+      "eval_accuracy": 0.7333333333333333,
+      "eval_f1_score": 0.7351290684624019,
+      "eval_gmean": 0.7371330133463562,
+      "eval_loss": 0.548876941204071,
+      "eval_precision": 0.743418613274008,
+      "eval_recall": 0.7333333333333333,
+      "eval_runtime": 187.8728,
+      "eval_samples_per_second": 0.319,
+      "eval_steps_per_second": 0.043,
       "step": 28
     },
     {
       "epoch": 0.48,
-      "grad_norm": 41.5,
+      "grad_norm": 29.125,
       "learning_rate": 1.076923076923077e-05,
-      "loss": 0.8968,
+      "loss": 0.6566,
       "step": 32
     },
     {
       "epoch": 0.6,
-      "grad_norm": 40.75,
+      "grad_norm": 28.875,
       "learning_rate": 8.307692307692309e-06,
-      "loss": 0.8597,
+      "loss": 0.6498,
       "step": 40
     },
     {
       "epoch": 0.72,
-      "grad_norm": 29.0,
+      "grad_norm": 18.25,
       "learning_rate": 5.846153846153847e-06,
-      "loss": 0.8077,
+      "loss": 0.5961,
       "step": 48
     },
     {
       "epoch": 0.84,
-      "grad_norm": 37.75,
+      "grad_norm": 26.0,
       "learning_rate": 3.384615384615385e-06,
-      "loss": 0.8601,
+      "loss": 0.6411,
       "step": 56
     },
     {
       "epoch": 0.84,
-      "eval_accuracy": 0.72,
-      "eval_f1_score": 0.7154911433172302,
-      "eval_gmean": 0.7399824497743348,
-      "eval_loss": 0.6498633027076721,
-      "eval_precision": 0.7727777777777777,
-      "eval_recall": 0.72,
-      "eval_runtime": 137.4306,
-      "eval_samples_per_second": 0.364,
-      "eval_steps_per_second": 0.051,
+      "eval_accuracy": 0.7666666666666667,
+      "eval_f1_score": 0.7677224736048267,
+      "eval_gmean": 0.765713693437345,
+      "eval_loss": 0.544189453125,
+      "eval_precision": 0.7704826038159371,
+      "eval_recall": 0.7666666666666667,
+      "eval_runtime": 188.0296,
+      "eval_samples_per_second": 0.319,
+      "eval_steps_per_second": 0.043,
       "step": 56
     },
     {
       "epoch": 0.96,
-      "grad_norm": 39.25,
+      "grad_norm": 25.625,
       "learning_rate": 9.230769230769232e-07,
-      "loss": 0.8283,
+      "loss": 0.6016,
       "step": 64
     },
     {
       "epoch": 1.0,
       "step": 67,
       "total_flos": 8.468389371174912e+16,
-      "train_loss": 0.9084581972947762,
-      "train_runtime": 14096.0939,
-      "train_samples_per_second": 0.304,
+      "train_loss": 0.6622405550373134,
+      "train_runtime": 13770.5671,
+      "train_samples_per_second": 0.311,
       "train_steps_per_second": 0.005
     }
   ],