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": 0.1984,
+    "eval_accuracy": 0.5270758122743683,
+    "eval_loss": 0.6920769214630127,
+    "eval_runtime": 0.2317,
     "eval_samples": 277,
-    "eval_samples_per_second": 1396.357,
-    "eval_steps_per_second": 15.123,
-    "train_loss": 0.5984805376101763,
-    "train_runtime": 104.4798,
+    "eval_samples_per_second": 1195.766,
+    "eval_steps_per_second": 12.951,
+    "train_loss": 0.7036660610101162,
+    "train_runtime": 56.517,
     "train_samples": 2490,
-    "train_samples_per_second": 238.323,
-    "train_steps_per_second": 7.466
+    "train_samples_per_second": 440.575,
+    "train_steps_per_second": 13.801
 }

eval_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 10.0,
-    "eval_accuracy": 0.6750902527075813,
-    "eval_loss": 0.6114864945411682,
-    "eval_runtime": 0.1984,
+    "eval_accuracy": 0.5270758122743683,
+    "eval_loss": 0.6920769214630127,
+    "eval_runtime": 0.2317,
     "eval_samples": 277,
-    "eval_samples_per_second": 1396.357,
-    "eval_steps_per_second": 15.123
+    "eval_samples_per_second": 1195.766,
+    "eval_steps_per_second": 12.951
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0b91bf2cf0f6fcac484b060ad2c08c23df32716b824343eb6e3396e5dbbad19
-size 7217721
+oid sha256:56ce94d00c7fbfff0f1c8d9f61018176598366835336cec0699657e07ada6ba4
+size 7221369

runs/Jan29_14-26-43_node4/events.out.tfevents.1643437622.node4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b9738cd2c41cbe8c6133aa579112a5d56e3e4962c12255b1821cf31534802b4
-size 3515
+oid sha256:2be1fc1b5dea6d643ede519e4444365dbca2cdf50511a8f6be4113cd13aa8243
+size 7250

runs/Jan29_14-26-43_node4/events.out.tfevents.1643437679.node4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99c9d36e871fc65f6112ce244c1a692844af554a8288fd08c73067cd642ce50b
+size 363

runs/Jan29_14-31-32_node4/1643437914.7647812/events.out.tfevents.1643437914.node4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:278c4424ecc3772c2a6f0036d2dee7184ea6f6953c2554d619fb8397ea46b10d
+size 4585

runs/Jan29_14-31-32_node4/events.out.tfevents.1643437914.node4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f00c6d0641d097a06ef40f50befc5374aa9eb2e103b2c40b4ed9db97f029a56
+size 3515

runs/Jan29_14-32-47_node4/1643437989.0232658/events.out.tfevents.1643437989.node4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af66ed2973530dc3ab5cb36a5a1fb2f13304c611402979e7027ec22c8b3826ef
+size 4585

runs/Jan29_14-32-47_node4/events.out.tfevents.1643437989.node4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1991ecf5317789cd4084aeb1d1aff4bef0e9988c81377e0631a6db2acc5831e
+size 3515

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 10.0,
-    "train_loss": 0.5984805376101763,
-    "train_runtime": 104.4798,
+    "train_loss": 0.7036660610101162,
+    "train_runtime": 56.517,
     "train_samples": 2490,
-    "train_samples_per_second": 238.323,
-    "train_steps_per_second": 7.466
+    "train_samples_per_second": 440.575,
+    "train_steps_per_second": 13.801
 }

trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.6750902527075813,
-  "best_model_checkpoint": "outputs/lora/roberta-base/v2/rte/checkpoint-624",
+  "best_metric": 0.5270758122743683,
+  "best_model_checkpoint": "outputs/lora/roberta-base/v2/rte/checkpoint-234",
   "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": 0.2363,
-      "eval_samples_per_second": 1172.313,
-      "eval_steps_per_second": 12.697,
+      "eval_loss": 0.6932649612426758,
+      "eval_runtime": 0.2128,
+      "eval_samples_per_second": 1301.835,
+      "eval_steps_per_second": 14.099,
       "step": 78
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.5018050541516246,
-      "eval_loss": 0.6921780109405518,
-      "eval_runtime": 0.1983,
-      "eval_samples_per_second": 1396.542,
-      "eval_steps_per_second": 15.125,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.7044342160224915,
+      "eval_runtime": 0.1974,
+      "eval_samples_per_second": 1403.492,
+      "eval_steps_per_second": 15.2,
       "step": 156
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.5667870036101083,
-      "eval_loss": 0.6696296334266663,
-      "eval_runtime": 0.1952,
-      "eval_samples_per_second": 1419.099,
-      "eval_steps_per_second": 15.369,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.6920769214630127,
+      "eval_runtime": 0.1955,
+      "eval_samples_per_second": 1416.913,
+      "eval_steps_per_second": 15.346,
       "step": 234
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.631768953068592,
-      "eval_loss": 0.643951416015625,
-      "eval_runtime": 0.2015,
-      "eval_samples_per_second": 1374.381,
-      "eval_steps_per_second": 14.885,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.6917607188224792,
+      "eval_runtime": 0.195,
+      "eval_samples_per_second": 1420.227,
+      "eval_steps_per_second": 15.382,
       "step": 312
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.631768953068592,
-      "eval_loss": 0.6657952070236206,
-      "eval_runtime": 0.1948,
-      "eval_samples_per_second": 1422.01,
-      "eval_steps_per_second": 15.401,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.6931599974632263,
+      "eval_runtime": 0.202,
+      "eval_samples_per_second": 1371.399,
+      "eval_steps_per_second": 14.853,
       "step": 390
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.6570397111913358,
-      "eval_loss": 0.6278102993965149,
-      "eval_runtime": 0.1944,
-      "eval_samples_per_second": 1424.734,
-      "eval_steps_per_second": 15.43,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.6917369961738586,
+      "eval_runtime": 0.2087,
+      "eval_samples_per_second": 1327.528,
+      "eval_steps_per_second": 14.378,
       "step": 468
     },
     {
       "epoch": 6.41,
-      "learning_rate": 0.00019099590723055935,
-      "loss": 0.6432,
+      "learning_rate": 0.001145975443383356,
+      "loss": 0.7089,
       "step": 500
     },
     {
       "epoch": 7.0,
-      "eval_accuracy": 0.6642599277978339,
-      "eval_loss": 0.6154282689094543,
-      "eval_runtime": 0.2257,
-      "eval_samples_per_second": 1227.515,
-      "eval_steps_per_second": 13.294,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.694267213344574,
+      "eval_runtime": 0.2034,
+      "eval_samples_per_second": 1361.602,
+      "eval_steps_per_second": 14.747,
       "step": 546
     },
     {
       "epoch": 8.0,
-      "eval_accuracy": 0.6750902527075813,
-      "eval_loss": 0.6114864945411682,
-      "eval_runtime": 0.2056,
-      "eval_samples_per_second": 1347.068,
-      "eval_steps_per_second": 14.589,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.6940146088600159,
+      "eval_runtime": 0.1951,
+      "eval_samples_per_second": 1420.005,
+      "eval_steps_per_second": 15.379,
       "step": 624
     },
     {
       "epoch": 9.0,
-      "eval_accuracy": 0.6534296028880866,
-      "eval_loss": 0.6326375603675842,
-      "eval_runtime": 0.1939,
-      "eval_samples_per_second": 1428.743,
-      "eval_steps_per_second": 15.474,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.6937310099601746,
+      "eval_runtime": 0.205,
+      "eval_samples_per_second": 1350.94,
+      "eval_steps_per_second": 14.631,
       "step": 702
     },
     {
       "epoch": 10.0,
-      "eval_accuracy": 0.6678700361010831,
-      "eval_loss": 0.6225477457046509,
-      "eval_runtime": 0.2062,
-      "eval_samples_per_second": 1343.504,
-      "eval_steps_per_second": 14.551,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.6936615705490112,
+      "eval_runtime": 0.2027,
+      "eval_samples_per_second": 1366.613,
+      "eval_steps_per_second": 14.801,
       "step": 780
     },
     {
       "epoch": 10.0,
       "step": 780,
-      "total_flos": 1638956800972800.0,
-      "train_loss": 0.5984805376101763,
-      "train_runtime": 104.4798,
-      "train_samples_per_second": 238.323,
-      "train_steps_per_second": 7.466
+      "total_flos": 1660792129689600.0,
+      "train_loss": 0.7036660610101162,
+      "train_runtime": 56.517,
+      "train_samples_per_second": 440.575,
+      "train_steps_per_second": 13.801
     }
   ],
   "max_steps": 780,
   "num_train_epochs": 10,
-  "total_flos": 1638956800972800.0,
+  "total_flos": 1660792129689600.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5a4e8316ff09f9bd9ad541a70e1856cd7b7afe71e81ba764de8d4f37b8178de
+oid sha256:48c9a54a38d9e64120e2c92f18e65d38808fdcfcc42f6ddd8a4537d560e788b1
 size 2991