Training in progress, epoch 1

all_results.json

@@ -1,14 +1,14 @@
 {
     "epoch": 10.0,
-    "eval_accuracy": 0.6750902527075813,
-    "eval_loss": 0.6114864945411682,
-    "eval_runtime": 0.2285,
+    "eval_accuracy": 0.6859205776173285,
+    "eval_loss": 0.612417459487915,
+    "eval_runtime": 0.1858,
     "eval_samples": 277,
-    "eval_samples_per_second": 1212.012,
-    "eval_steps_per_second": 13.126,
-    "train_loss": 0.5984805376101763,
-    "train_runtime": 94.4914,
+    "eval_samples_per_second": 1490.45,
+    "eval_steps_per_second": 16.142,
+    "train_loss": 0.6145670572916667,
+    "train_runtime": 72.3203,
     "train_samples": 2490,
-    "train_samples_per_second": 263.516,
-    "train_steps_per_second": 8.255
+    "train_samples_per_second": 344.302,
+    "train_steps_per_second": 10.785
 }

eval_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 10.0,
-    "eval_accuracy": 0.6750902527075813,
-    "eval_loss": 0.6114864945411682,
-    "eval_runtime": 0.2285,
+    "eval_accuracy": 0.6859205776173285,
+    "eval_loss": 0.612417459487915,
+    "eval_runtime": 0.1858,
     "eval_samples": 277,
-    "eval_samples_per_second": 1212.012,
-    "eval_steps_per_second": 13.126
+    "eval_samples_per_second": 1490.45,
+    "eval_steps_per_second": 16.142
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd5801b4e1c5b479cf8dcb8c563bdac9fcea334e09eb4ed2e87c3ad03c69948b
-size 2587045
+oid sha256:186f3a00a6d3211008923fc2a8dcbca14f684341100ab01540c2dce27d7c6ef6
+size 7217721

runs/Jan29_11-35-56_node4/events.out.tfevents.1643427381.node4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa82b928e9b913fbb6a0818dfe544ec3c40153f114351b2d0146650394b8f7b3
-size 6251
+oid sha256:78390e1448e8ab4121fe68634ab9b4efbe979e8b2ff8d4f5efbe4ff348a74c67
+size 7251

runs/Jan29_11-35-56_node4/events.out.tfevents.1643427453.node4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ea49ffd81804b4e434584dfca608e1f258f931d2d4db7c054b957ff0005d7a2
+size 363

runs/Jan29_12-47-43_node4/1643431691.7466369/events.out.tfevents.1643431691.node4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8832580edced3c405361c8fdb912ccedbb071b46a492ec139f464d9891790505
+size 4585

runs/Jan29_12-47-43_node4/events.out.tfevents.1643431691.node4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47ff14da4afc84bc60cb56c97810325098989d20d0bb74ce1235a03112526c0d
+size 3516

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 10.0,
-    "train_loss": 0.5984805376101763,
-    "train_runtime": 94.4914,
+    "train_loss": 0.6145670572916667,
+    "train_runtime": 72.3203,
     "train_samples": 2490,
-    "train_samples_per_second": 263.516,
-    "train_steps_per_second": 8.255
+    "train_samples_per_second": 344.302,
+    "train_steps_per_second": 10.785
 }

trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.6750902527075813,
-  "best_model_checkpoint": "outputs/lora/roberta-base/v2/rte/checkpoint-624",
+  "best_metric": 0.6859205776173285,
+  "best_model_checkpoint": "outputs/lora/roberta-base/v2/rte/checkpoint-702",
   "epoch": 10.0,
   "global_step": 780,
   "is_hyper_param_search": false,
@@ -10,112 +10,112 @@
     {
       "epoch": 1.0,
       "eval_accuracy": 0.4729241877256318,
-      "eval_loss": 0.70159912109375,
-      "eval_runtime": 0.2776,
-      "eval_samples_per_second": 997.786,
-      "eval_steps_per_second": 10.806,
+      "eval_loss": 0.701078474521637,
+      "eval_runtime": 0.2176,
+      "eval_samples_per_second": 1273.167,
+      "eval_steps_per_second": 13.789,
       "step": 78
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.5018050541516246,
-      "eval_loss": 0.6921780109405518,
-      "eval_runtime": 0.2113,
-      "eval_samples_per_second": 1310.929,
-      "eval_steps_per_second": 14.198,
+      "eval_accuracy": 0.5306859205776173,
+      "eval_loss": 0.6873822212219238,
+      "eval_runtime": 0.1844,
+      "eval_samples_per_second": 1502.516,
+      "eval_steps_per_second": 16.273,
       "step": 156
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.5667870036101083,
-      "eval_loss": 0.6696296334266663,
-      "eval_runtime": 0.2287,
-      "eval_samples_per_second": 1211.094,
-      "eval_steps_per_second": 13.117,
+      "eval_accuracy": 0.6209386281588448,
+      "eval_loss": 0.6623168587684631,
+      "eval_runtime": 0.1918,
+      "eval_samples_per_second": 1443.912,
+      "eval_steps_per_second": 15.638,
       "step": 234
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.631768953068592,
-      "eval_loss": 0.643951416015625,
-      "eval_runtime": 0.2582,
-      "eval_samples_per_second": 1072.841,
-      "eval_steps_per_second": 11.619,
+      "eval_accuracy": 0.6353790613718412,
+      "eval_loss": 0.6254002451896667,
+      "eval_runtime": 0.1883,
+      "eval_samples_per_second": 1470.879,
+      "eval_steps_per_second": 15.93,
       "step": 312
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.631768953068592,
-      "eval_loss": 0.6657952070236206,
-      "eval_runtime": 0.2373,
-      "eval_samples_per_second": 1167.361,
-      "eval_steps_per_second": 12.643,
+      "eval_accuracy": 0.6678700361010831,
+      "eval_loss": 0.6433575749397278,
+      "eval_runtime": 0.1749,
+      "eval_samples_per_second": 1583.662,
+      "eval_steps_per_second": 17.152,
       "step": 390
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.6570397111913358,
-      "eval_loss": 0.6278102993965149,
-      "eval_runtime": 0.2222,
-      "eval_samples_per_second": 1246.371,
-      "eval_steps_per_second": 13.499,
+      "eval_accuracy": 0.6787003610108303,
+      "eval_loss": 0.6127150654792786,
+      "eval_runtime": 0.1752,
+      "eval_samples_per_second": 1580.655,
+      "eval_steps_per_second": 17.119,
       "step": 468
     },
     {
       "epoch": 6.41,
       "learning_rate": 0.00019099590723055935,
-      "loss": 0.6432,
+      "loss": 0.6474,
       "step": 500
     },
     {
       "epoch": 7.0,
-      "eval_accuracy": 0.6642599277978339,
-      "eval_loss": 0.6154282689094543,
-      "eval_runtime": 0.2258,
-      "eval_samples_per_second": 1226.508,
-      "eval_steps_per_second": 13.283,
+      "eval_accuracy": 0.6750902527075813,
+      "eval_loss": 0.6097350716590881,
+      "eval_runtime": 0.1749,
+      "eval_samples_per_second": 1584.068,
+      "eval_steps_per_second": 17.156,
       "step": 546
     },
     {
       "epoch": 8.0,
-      "eval_accuracy": 0.6750902527075813,
-      "eval_loss": 0.6114864945411682,
-      "eval_runtime": 0.2213,
-      "eval_samples_per_second": 1251.904,
-      "eval_steps_per_second": 13.559,
+      "eval_accuracy": 0.6642599277978339,
+      "eval_loss": 0.6075621843338013,
+      "eval_runtime": 0.1774,
+      "eval_samples_per_second": 1561.774,
+      "eval_steps_per_second": 16.915,
       "step": 624
     },
     {
       "epoch": 9.0,
-      "eval_accuracy": 0.6534296028880866,
-      "eval_loss": 0.6326375603675842,
-      "eval_runtime": 0.2324,
-      "eval_samples_per_second": 1192.091,
-      "eval_steps_per_second": 12.911,
+      "eval_accuracy": 0.6859205776173285,
+      "eval_loss": 0.612417459487915,
+      "eval_runtime": 0.1749,
+      "eval_samples_per_second": 1584.01,
+      "eval_steps_per_second": 17.155,
       "step": 702
     },
     {
       "epoch": 10.0,
-      "eval_accuracy": 0.6678700361010831,
-      "eval_loss": 0.6225477457046509,
-      "eval_runtime": 0.2107,
-      "eval_samples_per_second": 1314.871,
-      "eval_steps_per_second": 14.24,
+      "eval_accuracy": 0.6859205776173285,
+      "eval_loss": 0.615571916103363,
+      "eval_runtime": 0.1758,
+      "eval_samples_per_second": 1575.457,
+      "eval_steps_per_second": 17.063,
       "step": 780
     },
     {
       "epoch": 10.0,
       "step": 780,
-      "total_flos": 1638956800972800.0,
-      "train_loss": 0.5984805376101763,
-      "train_runtime": 94.4914,
-      "train_samples_per_second": 263.516,
-      "train_steps_per_second": 8.255
+      "total_flos": 1637866319616000.0,
+      "train_loss": 0.6145670572916667,
+      "train_runtime": 72.3203,
+      "train_samples_per_second": 344.302,
+      "train_steps_per_second": 10.785
     }
   ],
   "max_steps": 780,
   "num_train_epochs": 10,
-  "total_flos": 1638956800972800.0,
+  "total_flos": 1637866319616000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b87fc109746fef165a5437bcaba71950ecac52b6d309d88608d3b828a6f71f9
+oid sha256:d127150b35bda60fc25029913e66011b61f383708299bd634ced50fb7165ee3d
 size 2991