Upload folder using huggingface_hub

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1a86700c1252c736346a01d5363786e9fcfede8e32722382df82888062649dc
+oid sha256:8890be9771be69e02157d292ce062e7059a7194a8554e5fc1e05bd2cb43efe56
 size 160086542

all_results.json

@@ -3,15 +3,15 @@
     "eval_accuracy": 0.86,
     "eval_f1_score": 0.8603998368013055,
     "eval_gmean": 0.8596058209945328,
-    "eval_loss": 0.27683594822883606,
+    "eval_loss": 0.27339842915534973,
     "eval_precision": 0.8614935064935065,
     "eval_recall": 0.86,
-    "eval_runtime": 306.7277,
-    "eval_samples_per_second": 0.326,
+    "eval_runtime": 308.5581,
+    "eval_samples_per_second": 0.324,
     "eval_steps_per_second": 0.042,
     "total_flos": 1.0505428534296576e+17,
-    "train_loss": 0.366200889029154,
-    "train_runtime": 19534.4865,
+    "train_loss": 0.3621236289419779,
+    "train_runtime": 19535.7167,
     "train_samples_per_second": 0.269,
     "train_steps_per_second": 0.004
 }

eval_results.json

@@ -3,10 +3,10 @@
     "eval_accuracy": 0.86,
     "eval_f1_score": 0.8603998368013055,
     "eval_gmean": 0.8596058209945328,
-    "eval_loss": 0.27683594822883606,
+    "eval_loss": 0.27339842915534973,
     "eval_precision": 0.8614935064935065,
     "eval_recall": 0.86,
-    "eval_runtime": 306.7277,
-    "eval_samples_per_second": 0.326,
+    "eval_runtime": 308.5581,
+    "eval_samples_per_second": 0.324,
     "eval_steps_per_second": 0.042
 }

runs/Mar23_00-51-47_b5a16491d8d5/events.out.tfevents.1711155109.b5a16491d8d5.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ea91bced9668f5c51ba213235a106c2fce00f4e85f3e087d1eebb0da737b125
+size 12485

runs/Mar23_00-51-47_b5a16491d8d5/events.out.tfevents.1711174954.b5a16491d8d5.34.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a229147307234295668bade9b190f4adadedd093c635a12acfffeb296d777ee
+size 605

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
     "total_flos": 1.0505428534296576e+17,
-    "train_loss": 0.366200889029154,
-    "train_runtime": 19534.4865,
+    "train_loss": 0.3621236289419779,
+    "train_runtime": 19535.7167,
     "train_samples_per_second": 0.269,
     "train_steps_per_second": 0.004
 }

trainer_state.json

@@ -10,9 +10,9 @@
   "log_history": [
     {
       "epoch": 0.1,
-      "grad_norm": 5.78125,
+      "grad_norm": 5.8125,
       "learning_rate": 1.8500000000000002e-05,
-      "loss": 0.3492,
+      "loss": 0.3424,
       "step": 8
     },
     {
@@ -20,19 +20,19 @@
       "eval_accuracy": 0.86,
       "eval_f1_score": 0.8603998368013055,
       "eval_gmean": 0.8596058209945328,
-      "eval_loss": 0.27931639552116394,
+      "eval_loss": 0.27559569478034973,
       "eval_precision": 0.8614935064935065,
       "eval_recall": 0.86,
-      "eval_runtime": 306.5917,
-      "eval_samples_per_second": 0.326,
+      "eval_runtime": 307.9009,
+      "eval_samples_per_second": 0.325,
       "eval_steps_per_second": 0.042,
       "step": 8
     },
     {
       "epoch": 0.19,
-      "grad_norm": 6.09375,
+      "grad_norm": 6.15625,
       "learning_rate": 1.65e-05,
-      "loss": 0.2969,
+      "loss": 0.2941,
       "step": 16
     },
     {
@@ -40,19 +40,19 @@
       "eval_accuracy": 0.86,
       "eval_f1_score": 0.8603998368013055,
       "eval_gmean": 0.8596058209945328,
-      "eval_loss": 0.2782519459724426,
+      "eval_loss": 0.27452147006988525,
       "eval_precision": 0.8614935064935065,
       "eval_recall": 0.86,
-      "eval_runtime": 306.7174,
-      "eval_samples_per_second": 0.326,
+      "eval_runtime": 308.1743,
+      "eval_samples_per_second": 0.324,
       "eval_steps_per_second": 0.042,
       "step": 16
     },
     {
       "epoch": 0.29,
-      "grad_norm": 8.125,
+      "grad_norm": 8.0,
       "learning_rate": 1.45e-05,
-      "loss": 0.4192,
+      "loss": 0.4138,
       "step": 24
     },
     {
@@ -60,19 +60,19 @@
       "eval_accuracy": 0.86,
       "eval_f1_score": 0.8603998368013055,
       "eval_gmean": 0.8596058209945328,
-      "eval_loss": 0.2776171863079071,
+      "eval_loss": 0.27406251430511475,
       "eval_precision": 0.8614935064935065,
       "eval_recall": 0.86,
-      "eval_runtime": 306.6283,
-      "eval_samples_per_second": 0.326,
+      "eval_runtime": 308.7677,
+      "eval_samples_per_second": 0.324,
       "eval_steps_per_second": 0.042,
       "step": 24
     },
     {
       "epoch": 0.39,
-      "grad_norm": 7.65625,
+      "grad_norm": 7.59375,
       "learning_rate": 1.25e-05,
-      "loss": 0.3537,
+      "loss": 0.3497,
       "step": 32
     },
     {
@@ -80,19 +80,19 @@
       "eval_accuracy": 0.86,
       "eval_f1_score": 0.8603998368013055,
       "eval_gmean": 0.8596058209945328,
-      "eval_loss": 0.27734375,
+      "eval_loss": 0.27359864115715027,
       "eval_precision": 0.8614935064935065,
       "eval_recall": 0.86,
-      "eval_runtime": 306.9153,
-      "eval_samples_per_second": 0.326,
+      "eval_runtime": 307.8988,
+      "eval_samples_per_second": 0.325,
       "eval_steps_per_second": 0.042,
       "step": 32
     },
     {
       "epoch": 0.49,
-      "grad_norm": 6.46875,
+      "grad_norm": 6.40625,
       "learning_rate": 1.0500000000000001e-05,
-      "loss": 0.2969,
+      "loss": 0.2935,
       "step": 40
     },
     {
@@ -100,19 +100,19 @@
       "eval_accuracy": 0.86,
       "eval_f1_score": 0.8603998368013055,
       "eval_gmean": 0.8596058209945328,
-      "eval_loss": 0.2774414122104645,
+      "eval_loss": 0.273681640625,
       "eval_precision": 0.8614935064935065,
       "eval_recall": 0.86,
-      "eval_runtime": 306.7575,
-      "eval_samples_per_second": 0.326,
+      "eval_runtime": 307.426,
+      "eval_samples_per_second": 0.325,
       "eval_steps_per_second": 0.042,
       "step": 40
     },
     {
       "epoch": 0.58,
-      "grad_norm": 7.375,
+      "grad_norm": 7.25,
       "learning_rate": 8.5e-06,
-      "loss": 0.3783,
+      "loss": 0.3741,
       "step": 48
     },
     {
@@ -120,19 +120,19 @@
       "eval_accuracy": 0.86,
       "eval_f1_score": 0.8603998368013055,
       "eval_gmean": 0.8596058209945328,
-      "eval_loss": 0.27705079317092896,
+      "eval_loss": 0.27381837368011475,
       "eval_precision": 0.8614935064935065,
       "eval_recall": 0.86,
-      "eval_runtime": 306.7281,
-      "eval_samples_per_second": 0.326,
+      "eval_runtime": 308.5186,
+      "eval_samples_per_second": 0.324,
       "eval_steps_per_second": 0.042,
       "step": 48
     },
     {
       "epoch": 0.68,
-      "grad_norm": 7.09375,
+      "grad_norm": 6.96875,
       "learning_rate": 6.5000000000000004e-06,
-      "loss": 0.4144,
+      "loss": 0.41,
       "step": 56
     },
     {
@@ -140,11 +140,11 @@
       "eval_accuracy": 0.86,
       "eval_f1_score": 0.8603998368013055,
       "eval_gmean": 0.8596058209945328,
-      "eval_loss": 0.27685546875,
+      "eval_loss": 0.2735644578933716,
       "eval_precision": 0.8614935064935065,
       "eval_recall": 0.86,
-      "eval_runtime": 306.848,
-      "eval_samples_per_second": 0.326,
+      "eval_runtime": 307.8108,
+      "eval_samples_per_second": 0.325,
       "eval_steps_per_second": 0.042,
       "step": 56
     },
@@ -152,7 +152,7 @@
       "epoch": 0.78,
       "grad_norm": 5.6875,
       "learning_rate": 4.5e-06,
-      "loss": 0.4167,
+      "loss": 0.4139,
       "step": 64
     },
     {
@@ -160,19 +160,19 @@
       "eval_accuracy": 0.86,
       "eval_f1_score": 0.8603998368013055,
       "eval_gmean": 0.8596058209945328,
-      "eval_loss": 0.2767578065395355,
+      "eval_loss": 0.27348631620407104,
       "eval_precision": 0.8614935064935065,
       "eval_recall": 0.86,
-      "eval_runtime": 306.3539,
-      "eval_samples_per_second": 0.326,
+      "eval_runtime": 308.2439,
+      "eval_samples_per_second": 0.324,
       "eval_steps_per_second": 0.042,
       "step": 64
     },
     {
       "epoch": 0.88,
-      "grad_norm": 5.34375,
+      "grad_norm": 5.3125,
       "learning_rate": 2.5e-06,
-      "loss": 0.3515,
+      "loss": 0.3477,
       "step": 72
     },
     {
@@ -180,11 +180,11 @@
       "eval_accuracy": 0.86,
       "eval_f1_score": 0.8603998368013055,
       "eval_gmean": 0.8596058209945328,
-      "eval_loss": 0.2766796946525574,
+      "eval_loss": 0.27347657084465027,
       "eval_precision": 0.8614935064935065,
       "eval_recall": 0.86,
-      "eval_runtime": 306.4227,
-      "eval_samples_per_second": 0.326,
+      "eval_runtime": 307.7434,
+      "eval_samples_per_second": 0.325,
       "eval_steps_per_second": 0.042,
       "step": 72
     },
@@ -192,7 +192,7 @@
       "epoch": 0.97,
       "grad_norm": 4.84375,
       "learning_rate": 5.000000000000001e-07,
-      "loss": 0.3856,
+      "loss": 0.3824,
       "step": 80
     },
     {
@@ -200,11 +200,11 @@
       "eval_accuracy": 0.86,
       "eval_f1_score": 0.8603998368013055,
       "eval_gmean": 0.8596058209945328,
-      "eval_loss": 0.27683594822883606,
+      "eval_loss": 0.27339842915534973,
       "eval_precision": 0.8614935064935065,
       "eval_recall": 0.86,
-      "eval_runtime": 306.6542,
-      "eval_samples_per_second": 0.326,
+      "eval_runtime": 308.324,
+      "eval_samples_per_second": 0.324,
       "eval_steps_per_second": 0.042,
       "step": 80
     },
@@ -212,8 +212,8 @@
       "epoch": 1.0,
       "step": 82,
       "total_flos": 1.0505428534296576e+17,
-      "train_loss": 0.366200889029154,
-      "train_runtime": 19534.4865,
+      "train_loss": 0.3621236289419779,
+      "train_runtime": 19535.7167,
       "train_samples_per_second": 0.269,
       "train_steps_per_second": 0.004
     }