Training in progress, epoch 1

all_results.json

@@ -1,14 +1,14 @@
 {
     "epoch": 10.0,
-    "eval_accuracy": 0.5270758122743683,
-    "eval_loss": 0.6917716860771179,
-    "eval_runtime": 0.2094,
+    "eval_accuracy": 0.6787003610108303,
+    "eval_loss": 0.610024094581604,
+    "eval_runtime": 0.2213,
     "eval_samples": 277,
-    "eval_samples_per_second": 1322.889,
-    "eval_steps_per_second": 14.327,
-    "train_loss": 0.7107287480280949,
-    "train_runtime": 85.9798,
+    "eval_samples_per_second": 1251.949,
+    "eval_steps_per_second": 13.559,
+    "train_loss": 0.5981983282627203,
+    "train_runtime": 104.8491,
     "train_samples": 2490,
-    "train_samples_per_second": 289.603,
-    "train_steps_per_second": 9.072
+    "train_samples_per_second": 237.484,
+    "train_steps_per_second": 7.439
 }

eval_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 10.0,
-    "eval_accuracy": 0.5270758122743683,
-    "eval_loss": 0.6917716860771179,
-    "eval_runtime": 0.2094,
+    "eval_accuracy": 0.6787003610108303,
+    "eval_loss": 0.610024094581604,
+    "eval_runtime": 0.2213,
     "eval_samples": 277,
-    "eval_samples_per_second": 1322.889,
-    "eval_steps_per_second": 14.327
+    "eval_samples_per_second": 1251.949,
+    "eval_steps_per_second": 13.559
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22e3a53d0663e90766a587a1f74c45249ebf9112a439ca8236cbc5578e062041
-size 2670681
+oid sha256:93c88f6804ca0646e40219fe426bbc74d690f4e4872434d7363aed659aaef27f
+size 2667673

runs/Jan29_14-35-43_node4/events.out.tfevents.1643438164.node4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5139fa825b471f5bc70a4e4fc084029a40b9e460ccd3eb5643722a936d942e42
-size 6574
+oid sha256:a129ccc769b523d71323f8fa44791493298f8384a62722988dded926022a2036
+size 7251

runs/Jan29_14-35-43_node4/events.out.tfevents.1643438269.node4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57f21662018582640af6a8adab09e51593300f4aaceff08ed5997f3b6675a529
+size 363

runs/Jan29_14-47-20_node4/1643438860.7724378/events.out.tfevents.1643438860.node4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fee6f7a53ec222efee03c2e28aff19c6516a8fd32a277a0f74a65ab92744d18
+size 4585

runs/Jan29_14-47-20_node4/events.out.tfevents.1643438860.node4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af3c49aa2e27c60609bb32aab1edd52e554956132d65589a0987eccda6e1502c
+size 3516

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 10.0,
-    "train_loss": 0.7107287480280949,
-    "train_runtime": 85.9798,
+    "train_loss": 0.5981983282627203,
+    "train_runtime": 104.8491,
     "train_samples": 2490,
-    "train_samples_per_second": 289.603,
-    "train_steps_per_second": 9.072
+    "train_samples_per_second": 237.484,
+    "train_steps_per_second": 7.439
 }

trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.5270758122743683,
-  "best_model_checkpoint": "outputs/lora/roberta-base/v2/rte/checkpoint-78",
+  "best_metric": 0.6787003610108303,
+  "best_model_checkpoint": "outputs/lora/roberta-base/v2/rte/checkpoint-546",
   "epoch": 10.0,
   "global_step": 780,
   "is_hyper_param_search": false,
@@ -9,113 +9,113 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5270758122743683,
-      "eval_loss": 0.6917716860771179,
-      "eval_runtime": 0.2182,
-      "eval_samples_per_second": 1269.407,
-      "eval_steps_per_second": 13.748,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.7017449736595154,
+      "eval_runtime": 0.2158,
+      "eval_samples_per_second": 1283.674,
+      "eval_steps_per_second": 13.903,
       "step": 78
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.4729241877256318,
-      "eval_loss": 0.7047286033630371,
-      "eval_runtime": 0.2028,
-      "eval_samples_per_second": 1365.996,
-      "eval_steps_per_second": 14.794,
+      "eval_accuracy": 0.5054151624548736,
+      "eval_loss": 0.6921688318252563,
+      "eval_runtime": 0.196,
+      "eval_samples_per_second": 1412.998,
+      "eval_steps_per_second": 15.303,
       "step": 156
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.5270758122743683,
-      "eval_loss": 0.6930808424949646,
-      "eval_runtime": 0.2098,
-      "eval_samples_per_second": 1320.313,
-      "eval_steps_per_second": 14.299,
+      "eval_accuracy": 0.555956678700361,
+      "eval_loss": 0.66964191198349,
+      "eval_runtime": 0.2062,
+      "eval_samples_per_second": 1343.15,
+      "eval_steps_per_second": 14.547,
       "step": 234
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.4729241877256318,
-      "eval_loss": 0.7232272028923035,
-      "eval_runtime": 0.1976,
-      "eval_samples_per_second": 1402.153,
-      "eval_steps_per_second": 15.186,
+      "eval_accuracy": 0.6353790613718412,
+      "eval_loss": 0.6405073404312134,
+      "eval_runtime": 0.1941,
+      "eval_samples_per_second": 1427.34,
+      "eval_steps_per_second": 15.459,
       "step": 312
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.5270758122743683,
-      "eval_loss": 0.6920943856239319,
-      "eval_runtime": 0.2057,
-      "eval_samples_per_second": 1346.903,
-      "eval_steps_per_second": 14.587,
+      "eval_accuracy": 0.6209386281588448,
+      "eval_loss": 0.6625295877456665,
+      "eval_runtime": 0.195,
+      "eval_samples_per_second": 1420.282,
+      "eval_steps_per_second": 15.382,
       "step": 390
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.4729241877256318,
-      "eval_loss": 0.6970064640045166,
-      "eval_runtime": 0.2024,
-      "eval_samples_per_second": 1368.74,
-      "eval_steps_per_second": 14.824,
+      "eval_accuracy": 0.6750902527075813,
+      "eval_loss": 0.6230459809303284,
+      "eval_runtime": 0.2124,
+      "eval_samples_per_second": 1304.362,
+      "eval_steps_per_second": 14.127,
       "step": 468
     },
     {
       "epoch": 6.41,
-      "learning_rate": 0.001145975443383356,
-      "loss": 0.7186,
+      "learning_rate": 0.00019099590723055935,
+      "loss": 0.6432,
       "step": 500
     },
     {
       "epoch": 7.0,
-      "eval_accuracy": 0.4729241877256318,
-      "eval_loss": 0.7015413045883179,
-      "eval_runtime": 0.1977,
-      "eval_samples_per_second": 1400.937,
-      "eval_steps_per_second": 15.173,
+      "eval_accuracy": 0.6787003610108303,
+      "eval_loss": 0.610024094581604,
+      "eval_runtime": 0.2125,
+      "eval_samples_per_second": 1303.805,
+      "eval_steps_per_second": 14.121,
       "step": 546
     },
     {
       "epoch": 8.0,
-      "eval_accuracy": 0.5270758122743683,
-      "eval_loss": 0.6930446624755859,
-      "eval_runtime": 0.1967,
-      "eval_samples_per_second": 1408.036,
-      "eval_steps_per_second": 15.249,
+      "eval_accuracy": 0.6787003610108303,
+      "eval_loss": 0.6000346541404724,
+      "eval_runtime": 0.2026,
+      "eval_samples_per_second": 1367.422,
+      "eval_steps_per_second": 14.81,
       "step": 624
     },
     {
       "epoch": 9.0,
-      "eval_accuracy": 0.4729241877256318,
-      "eval_loss": 0.6936255693435669,
-      "eval_runtime": 0.1952,
-      "eval_samples_per_second": 1419.144,
-      "eval_steps_per_second": 15.37,
+      "eval_accuracy": 0.6534296028880866,
+      "eval_loss": 0.6206708550453186,
+      "eval_runtime": 0.2041,
+      "eval_samples_per_second": 1357.114,
+      "eval_steps_per_second": 14.698,
       "step": 702
     },
     {
       "epoch": 10.0,
-      "eval_accuracy": 0.4729241877256318,
-      "eval_loss": 0.6936009526252747,
-      "eval_runtime": 0.1961,
-      "eval_samples_per_second": 1412.526,
-      "eval_steps_per_second": 15.298,
+      "eval_accuracy": 0.6678700361010831,
+      "eval_loss": 0.6108516454696655,
+      "eval_runtime": 0.1973,
+      "eval_samples_per_second": 1404.203,
+      "eval_steps_per_second": 15.208,
       "step": 780
     },
     {
       "epoch": 10.0,
       "step": 780,
-      "total_flos": 1660792129689600.0,
-      "train_loss": 0.7107287480280949,
-      "train_runtime": 85.9798,
-      "train_samples_per_second": 289.603,
-      "train_steps_per_second": 9.072
+      "total_flos": 1638956800972800.0,
+      "train_loss": 0.5981983282627203,
+      "train_runtime": 104.8491,
+      "train_samples_per_second": 237.484,
+      "train_steps_per_second": 7.439
     }
   ],
   "max_steps": 780,
   "num_train_epochs": 10,
-  "total_flos": 1660792129689600.0,
+  "total_flos": 1638956800972800.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75e1b5af84fdcbf42e0873fad34374a31bc9b2fc6b96dd7213c0f8e08e3050fc
+oid sha256:dab0d68b1b046d6cb70008d1bc51e115e59f9d041f646d8215785aeef41b7265
 size 2991