Training in progress, epoch 1

all_results.json

@@ -1,14 +1,14 @@
 {
     "epoch": 10.0,
     "eval_accuracy": 0.5270758122743683,
-    "eval_loss": 0.6920769214630127,
-    "eval_runtime": 0.2317,
+    "eval_loss": 0.6917716860771179,
+    "eval_runtime": 0.2094,
     "eval_samples": 277,
-    "eval_samples_per_second": 1195.766,
-    "eval_steps_per_second": 12.951,
-    "train_loss": 0.7036660610101162,
-    "train_runtime": 56.517,
+    "eval_samples_per_second": 1322.889,
+    "eval_steps_per_second": 14.327,
+    "train_loss": 0.7107287480280949,
+    "train_runtime": 85.9798,
     "train_samples": 2490,
-    "train_samples_per_second": 440.575,
-    "train_steps_per_second": 13.801
+    "train_samples_per_second": 289.603,
+    "train_steps_per_second": 9.072
 }

eval_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 10.0,
     "eval_accuracy": 0.5270758122743683,
-    "eval_loss": 0.6920769214630127,
-    "eval_runtime": 0.2317,
+    "eval_loss": 0.6917716860771179,
+    "eval_runtime": 0.2094,
     "eval_samples": 277,
-    "eval_samples_per_second": 1195.766,
-    "eval_steps_per_second": 12.951
+    "eval_samples_per_second": 1322.889,
+    "eval_steps_per_second": 14.327
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5869f9426aa4ba299ec8eb6333dc547808f230889e0bfb27b2acdff703ebfab
-size 7221369
+oid sha256:a335351205bbde01523ac0a31f450ed4c8c47959fbc677fc3bdb28d5176380f1
+size 2670681

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a73f6b75b58a21cd97c706fa15248cd850a0ec9ca12d0ea8e257bddc874bc7f
-size 6250
+oid sha256:540034784e35c4216106bdcd1c535d0a0643dd56a8d1c41bb99ee867514fc2a2
+size 7250

runs/Jan29_14-32-47_node4/events.out.tfevents.1643438075.node4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef5e7903640b71fa8c0987efca40e067f31f9ad4e303e2ba288eab76babdcf4d
+size 363

runs/Jan29_14-35-43_node4/1643438164.4820805/events.out.tfevents.1643438164.node4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec5184470c3d1ed874a218e95846b345e703335495af2e895d82bbcdb70fbc5c
+size 4585

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0deff3a04efbd1e3132c54ba773ed8549b47dd9710b5f0a003ab08f7293fdd8b
+size 3516

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 10.0,
-    "train_loss": 0.7036660610101162,
-    "train_runtime": 56.517,
+    "train_loss": 0.7107287480280949,
+    "train_runtime": 85.9798,
     "train_samples": 2490,
-    "train_samples_per_second": 440.575,
-    "train_steps_per_second": 13.801
+    "train_samples_per_second": 289.603,
+    "train_steps_per_second": 9.072
 }

trainer_state.json

@@ -1,6 +1,6 @@
 {
   "best_metric": 0.5270758122743683,
-  "best_model_checkpoint": "outputs/lora/roberta-base/v2/rte/checkpoint-234",
+  "best_model_checkpoint": "outputs/lora/roberta-base/v2/rte/checkpoint-78",
   "epoch": 10.0,
   "global_step": 780,
   "is_hyper_param_search": false,
@@ -9,108 +9,108 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.4729241877256318,
-      "eval_loss": 0.6932649612426758,
-      "eval_runtime": 0.2128,
-      "eval_samples_per_second": 1301.835,
-      "eval_steps_per_second": 14.099,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.6917716860771179,
+      "eval_runtime": 0.2182,
+      "eval_samples_per_second": 1269.407,
+      "eval_steps_per_second": 13.748,
       "step": 78
     },
     {
       "epoch": 2.0,
       "eval_accuracy": 0.4729241877256318,
-      "eval_loss": 0.7044342160224915,
-      "eval_runtime": 0.1974,
-      "eval_samples_per_second": 1403.492,
-      "eval_steps_per_second": 15.2,
+      "eval_loss": 0.7047286033630371,
+      "eval_runtime": 0.2028,
+      "eval_samples_per_second": 1365.996,
+      "eval_steps_per_second": 14.794,
       "step": 156
     },
     {
       "epoch": 3.0,
       "eval_accuracy": 0.5270758122743683,
-      "eval_loss": 0.6920769214630127,
-      "eval_runtime": 0.1955,
-      "eval_samples_per_second": 1416.913,
-      "eval_steps_per_second": 15.346,
+      "eval_loss": 0.6930808424949646,
+      "eval_runtime": 0.2098,
+      "eval_samples_per_second": 1320.313,
+      "eval_steps_per_second": 14.299,
       "step": 234
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.5270758122743683,
-      "eval_loss": 0.6917607188224792,
-      "eval_runtime": 0.195,
-      "eval_samples_per_second": 1420.227,
-      "eval_steps_per_second": 15.382,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.7232272028923035,
+      "eval_runtime": 0.1976,
+      "eval_samples_per_second": 1402.153,
+      "eval_steps_per_second": 15.186,
       "step": 312
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.4729241877256318,
-      "eval_loss": 0.6931599974632263,
-      "eval_runtime": 0.202,
-      "eval_samples_per_second": 1371.399,
-      "eval_steps_per_second": 14.853,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.6920943856239319,
+      "eval_runtime": 0.2057,
+      "eval_samples_per_second": 1346.903,
+      "eval_steps_per_second": 14.587,
       "step": 390
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.5270758122743683,
-      "eval_loss": 0.6917369961738586,
-      "eval_runtime": 0.2087,
-      "eval_samples_per_second": 1327.528,
-      "eval_steps_per_second": 14.378,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.6970064640045166,
+      "eval_runtime": 0.2024,
+      "eval_samples_per_second": 1368.74,
+      "eval_steps_per_second": 14.824,
       "step": 468
     },
     {
       "epoch": 6.41,
       "learning_rate": 0.001145975443383356,
-      "loss": 0.7089,
+      "loss": 0.7186,
       "step": 500
     },
     {
       "epoch": 7.0,
       "eval_accuracy": 0.4729241877256318,
-      "eval_loss": 0.694267213344574,
-      "eval_runtime": 0.2034,
-      "eval_samples_per_second": 1361.602,
-      "eval_steps_per_second": 14.747,
+      "eval_loss": 0.7015413045883179,
+      "eval_runtime": 0.1977,
+      "eval_samples_per_second": 1400.937,
+      "eval_steps_per_second": 15.173,
       "step": 546
     },
     {
       "epoch": 8.0,
-      "eval_accuracy": 0.4729241877256318,
-      "eval_loss": 0.6940146088600159,
-      "eval_runtime": 0.1951,
-      "eval_samples_per_second": 1420.005,
-      "eval_steps_per_second": 15.379,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.6930446624755859,
+      "eval_runtime": 0.1967,
+      "eval_samples_per_second": 1408.036,
+      "eval_steps_per_second": 15.249,
       "step": 624
     },
     {
       "epoch": 9.0,
       "eval_accuracy": 0.4729241877256318,
-      "eval_loss": 0.6937310099601746,
-      "eval_runtime": 0.205,
-      "eval_samples_per_second": 1350.94,
-      "eval_steps_per_second": 14.631,
+      "eval_loss": 0.6936255693435669,
+      "eval_runtime": 0.1952,
+      "eval_samples_per_second": 1419.144,
+      "eval_steps_per_second": 15.37,
       "step": 702
     },
     {
       "epoch": 10.0,
       "eval_accuracy": 0.4729241877256318,
-      "eval_loss": 0.6936615705490112,
-      "eval_runtime": 0.2027,
-      "eval_samples_per_second": 1366.613,
-      "eval_steps_per_second": 14.801,
+      "eval_loss": 0.6936009526252747,
+      "eval_runtime": 0.1961,
+      "eval_samples_per_second": 1412.526,
+      "eval_steps_per_second": 15.298,
       "step": 780
     },
     {
       "epoch": 10.0,
       "step": 780,
       "total_flos": 1660792129689600.0,
-      "train_loss": 0.7036660610101162,
-      "train_runtime": 56.517,
-      "train_samples_per_second": 440.575,
-      "train_steps_per_second": 13.801
+      "train_loss": 0.7107287480280949,
+      "train_runtime": 85.9798,
+      "train_samples_per_second": 289.603,
+      "train_steps_per_second": 9.072
     }
   ],
   "max_steps": 780,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48c9a54a38d9e64120e2c92f18e65d38808fdcfcc42f6ddd8a4537d560e788b1
+oid sha256:75e1b5af84fdcbf42e0873fad34374a31bc9b2fc6b96dd7213c0f8e08e3050fc
 size 2991