Training in progress, epoch 1

all_results.json

@@ -1,14 +1,14 @@
 {
     "epoch": 10.0,
-    "eval_accuracy": 0.6859205776173285,
-    "eval_loss": 0.612417459487915,
-    "eval_runtime": 0.1858,
+    "eval_accuracy": 0.5270758122743683,
+    "eval_loss": 0.6929515600204468,
+    "eval_runtime": 0.3612,
     "eval_samples": 277,
-    "eval_samples_per_second": 1490.45,
-    "eval_steps_per_second": 16.142,
-    "train_loss": 0.6145670572916667,
-    "train_runtime": 72.3203,
+    "eval_samples_per_second": 766.792,
+    "eval_steps_per_second": 8.305,
+    "train_loss": 0.6998463752942208,
+    "train_runtime": 85.2333,
     "train_samples": 2490,
-    "train_samples_per_second": 344.302,
-    "train_steps_per_second": 10.785
+    "train_samples_per_second": 292.139,
+    "train_steps_per_second": 9.151
 }

eval_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 10.0,
-    "eval_accuracy": 0.6859205776173285,
-    "eval_loss": 0.612417459487915,
-    "eval_runtime": 0.1858,
+    "eval_accuracy": 0.5270758122743683,
+    "eval_loss": 0.6929515600204468,
+    "eval_runtime": 0.3612,
     "eval_samples": 277,
-    "eval_samples_per_second": 1490.45,
-    "eval_steps_per_second": 16.142
+    "eval_samples_per_second": 766.792,
+    "eval_steps_per_second": 8.305
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5379072a3b84585e24cb3553806b6440c213a3b6717744f40613c9c72111a625
-size 7217721
+oid sha256:702b5b42f2f46eac93b0efd1d36de4ad747fe663f5ef4af10ac2242302d2f305
+size 2661529

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ecfe798d5c45fd31ae55f4c3c515a5067c470d2bfea8277ddeb18628802f4eb
-size 6251
+oid sha256:a954d63a428994aff2e7d234bc47c74112e4757bbe685cb73679e58cf0c5bc99
+size 7251

runs/Jan29_12-47-43_node4/events.out.tfevents.1643431777.node4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:176d294e85e4bdc219899b3f1408380778ac69cc1a25e0804e1cd67fe4b9de48
+size 363

runs/Jan29_13-50-41_node4/1643435470.2313247/events.out.tfevents.1643435470.node4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:852a0d4ebed9ac7486613cd94970f6d157d8f1f17484f403e682aa332323f611
+size 4585

runs/Jan29_13-50-41_node4/events.out.tfevents.1643435470.node4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e91ca2d9b5be9971232f88c473a88b9f8a3f9922a2c7ee32cf097b26f1d5e9ff
+size 3516

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 10.0,
-    "train_loss": 0.6145670572916667,
-    "train_runtime": 72.3203,
+    "train_loss": 0.6998463752942208,
+    "train_runtime": 85.2333,
     "train_samples": 2490,
-    "train_samples_per_second": 344.302,
-    "train_steps_per_second": 10.785
+    "train_samples_per_second": 292.139,
+    "train_steps_per_second": 9.151
 }

trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.6859205776173285,
-  "best_model_checkpoint": "outputs/lora/roberta-base/v2/rte/checkpoint-702",
+  "best_metric": 0.5270758122743683,
+  "best_model_checkpoint": "outputs/lora/roberta-base/v2/rte/checkpoint-312",
   "epoch": 10.0,
   "global_step": 780,
   "is_hyper_param_search": false,
@@ -10,112 +10,112 @@
     {
       "epoch": 1.0,
       "eval_accuracy": 0.4729241877256318,
-      "eval_loss": 0.701078474521637,
-      "eval_runtime": 0.2176,
-      "eval_samples_per_second": 1273.167,
-      "eval_steps_per_second": 13.789,
+      "eval_loss": 0.6938314437866211,
+      "eval_runtime": 0.2645,
+      "eval_samples_per_second": 1047.294,
+      "eval_steps_per_second": 11.343,
       "step": 78
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.5306859205776173,
-      "eval_loss": 0.6873822212219238,
-      "eval_runtime": 0.1844,
-      "eval_samples_per_second": 1502.516,
-      "eval_steps_per_second": 16.273,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.6956566572189331,
+      "eval_runtime": 0.1955,
+      "eval_samples_per_second": 1416.775,
+      "eval_steps_per_second": 15.344,
       "step": 156
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.6209386281588448,
-      "eval_loss": 0.6623168587684631,
-      "eval_runtime": 0.1918,
-      "eval_samples_per_second": 1443.912,
-      "eval_steps_per_second": 15.638,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.6933903098106384,
+      "eval_runtime": 0.2248,
+      "eval_samples_per_second": 1232.274,
+      "eval_steps_per_second": 13.346,
       "step": 234
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.6353790613718412,
-      "eval_loss": 0.6254002451896667,
-      "eval_runtime": 0.1883,
-      "eval_samples_per_second": 1470.879,
-      "eval_steps_per_second": 15.93,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.6929515600204468,
+      "eval_runtime": 0.1967,
+      "eval_samples_per_second": 1408.198,
+      "eval_steps_per_second": 15.251,
       "step": 312
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.6678700361010831,
-      "eval_loss": 0.6433575749397278,
-      "eval_runtime": 0.1749,
-      "eval_samples_per_second": 1583.662,
-      "eval_steps_per_second": 17.152,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.7013436555862427,
+      "eval_runtime": 0.2215,
+      "eval_samples_per_second": 1250.465,
+      "eval_steps_per_second": 13.543,
       "step": 390
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.6787003610108303,
-      "eval_loss": 0.6127150654792786,
-      "eval_runtime": 0.1752,
-      "eval_samples_per_second": 1580.655,
-      "eval_steps_per_second": 17.119,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.6958906650543213,
+      "eval_runtime": 0.1949,
+      "eval_samples_per_second": 1420.918,
+      "eval_steps_per_second": 15.389,
       "step": 468
     },
     {
       "epoch": 6.41,
       "learning_rate": 0.00019099590723055935,
-      "loss": 0.6474,
+      "loss": 0.7027,
       "step": 500
     },
     {
       "epoch": 7.0,
-      "eval_accuracy": 0.6750902527075813,
-      "eval_loss": 0.6097350716590881,
-      "eval_runtime": 0.1749,
-      "eval_samples_per_second": 1584.068,
-      "eval_steps_per_second": 17.156,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.6951103806495667,
+      "eval_runtime": 0.2035,
+      "eval_samples_per_second": 1360.881,
+      "eval_steps_per_second": 14.739,
       "step": 546
     },
     {
       "epoch": 8.0,
-      "eval_accuracy": 0.6642599277978339,
-      "eval_loss": 0.6075621843338013,
-      "eval_runtime": 0.1774,
-      "eval_samples_per_second": 1561.774,
-      "eval_steps_per_second": 16.915,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.6951630711555481,
+      "eval_runtime": 0.1983,
+      "eval_samples_per_second": 1396.879,
+      "eval_steps_per_second": 15.129,
       "step": 624
     },
     {
       "epoch": 9.0,
-      "eval_accuracy": 0.6859205776173285,
-      "eval_loss": 0.612417459487915,
-      "eval_runtime": 0.1749,
-      "eval_samples_per_second": 1584.01,
-      "eval_steps_per_second": 17.155,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.6940933465957642,
+      "eval_runtime": 0.2,
+      "eval_samples_per_second": 1384.676,
+      "eval_steps_per_second": 14.996,
       "step": 702
     },
     {
       "epoch": 10.0,
-      "eval_accuracy": 0.6859205776173285,
-      "eval_loss": 0.615571916103363,
-      "eval_runtime": 0.1758,
-      "eval_samples_per_second": 1575.457,
-      "eval_steps_per_second": 17.063,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.694451630115509,
+      "eval_runtime": 0.2448,
+      "eval_samples_per_second": 1131.765,
+      "eval_steps_per_second": 12.257,
       "step": 780
     },
     {
       "epoch": 10.0,
       "step": 780,
-      "total_flos": 1637866319616000.0,
-      "train_loss": 0.6145670572916667,
-      "train_runtime": 72.3203,
-      "train_samples_per_second": 344.302,
-      "train_steps_per_second": 10.785
+      "total_flos": 1660792129689600.0,
+      "train_loss": 0.6998463752942208,
+      "train_runtime": 85.2333,
+      "train_samples_per_second": 292.139,
+      "train_steps_per_second": 9.151
     }
   ],
   "max_steps": 780,
   "num_train_epochs": 10,
-  "total_flos": 1637866319616000.0,
+  "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:d127150b35bda60fc25029913e66011b61f383708299bd634ced50fb7165ee3d
+oid sha256:158f9c592b0108c1fc37ee53cdf7e163fa2c36d2fd97522f75d4bd5fc6611ad3
 size 2991