End of training

all_results.json

@@ -1,14 +1,14 @@
 {
-    "epoch": 3.0,
-    "eval_loss": 0.6499619483947754,
+    "epoch": 5.0,
+    "eval_loss": 0.6500726342201233,
     "eval_matthews_correlation": 0.0,
-    "eval_runtime": 23.3578,
+    "eval_runtime": 23.0231,
     "eval_samples": 1043,
-    "eval_samples_per_second": 44.653,
-    "eval_steps_per_second": 5.608,
-    "train_loss": 0.0,
-    "train_runtime": 0.0205,
+    "eval_samples_per_second": 45.302,
+    "eval_steps_per_second": 5.69,
+    "train_loss": 0.2530779532565482,
+    "train_runtime": 1420.0633,
     "train_samples": 8551,
-    "train_samples_per_second": 1248914.483,
-    "train_steps_per_second": 312265.134
+    "train_samples_per_second": 30.108,
+    "train_steps_per_second": 7.528
 }

eval_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 3.0,
-    "eval_loss": 0.6499619483947754,
+    "epoch": 5.0,
+    "eval_loss": 0.6500726342201233,
     "eval_matthews_correlation": 0.0,
-    "eval_runtime": 23.3578,
+    "eval_runtime": 23.0231,
     "eval_samples": 1043,
-    "eval_samples_per_second": 44.653,
-    "eval_steps_per_second": 5.608
+    "eval_samples_per_second": 45.302,
+    "eval_steps_per_second": 5.69
 }

runs/Oct10_19-05-40_patrick-general-gpu/events.out.tfevents.1633892756.patrick-general-gpu.125503.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c948bd98023c44aa14a8569fddadf0202d6d271d154cb83234eaf39d0811306
-size 4260
+oid sha256:03fb645e00e2084e20fb6a704ba71080e4c774bd2c71f9a07a3ec0e1719f6cd9
+size 4614

runs/Oct10_19-05-40_patrick-general-gpu/events.out.tfevents.1633894217.patrick-general-gpu.125503.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c20c35361cbf4976f5b9d6dedeb387031cbd381449eb2474220cabbf2f30fff6
+size 375

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 3.0,
-    "train_loss": 0.0,
-    "train_runtime": 0.0205,
+    "epoch": 5.0,
+    "train_loss": 0.2530779532565482,
+    "train_runtime": 1420.0633,
     "train_samples": 8551,
-    "train_samples_per_second": 1248914.483,
-    "train_steps_per_second": 312265.134
+    "train_samples_per_second": 30.108,
+    "train_steps_per_second": 7.528
 }

trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.0,
-  "global_step": 6414,
+  "epoch": 5.0,
+  "global_step": 10690,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -53,18 +53,48 @@
       "step": 6414
     },
     {
-      "epoch": 3.0,
-      "step": 6414,
-      "total_flos": 1.6048929796061184e+16,
-      "train_loss": 0.0,
-      "train_runtime": 0.0205,
-      "train_samples_per_second": 1248914.483,
-      "train_steps_per_second": 312265.134
+      "epoch": 4.0,
+      "learning_rate": 8.966666666666667e-06,
+      "loss": 0.6342,
+      "step": 8552
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.6344217658042908,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 22.7688,
+      "eval_samples_per_second": 45.808,
+      "eval_steps_per_second": 5.753,
+      "step": 8552
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 1e-07,
+      "loss": 0.6312,
+      "step": 10690
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.6500726342201233,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 22.7519,
+      "eval_samples_per_second": 45.842,
+      "eval_steps_per_second": 5.758,
+      "step": 10690
+    },
+    {
+      "epoch": 5.0,
+      "step": 10690,
+      "total_flos": 2.674821632676864e+16,
+      "train_loss": 0.2530779532565482,
+      "train_runtime": 1420.0633,
+      "train_samples_per_second": 30.108,
+      "train_steps_per_second": 7.528
     }
   ],
-  "max_steps": 6414,
-  "num_train_epochs": 3,
-  "total_flos": 1.6048929796061184e+16,
+  "max_steps": 10690,
+  "num_train_epochs": 5,
+  "total_flos": 2.674821632676864e+16,
   "trial_name": null,
   "trial_params": null
 }