End of training

all_results.json

@@ -1,15 +1,15 @@
 {
-    "epoch": 5.0,
-    "eval_accuracy": 0.6914216185247494,
-    "eval_loss": 1.320469856262207,
-    "eval_runtime": 4412.1637,
+    "epoch": 4.98,
+    "eval_accuracy": 0.6914040854429856,
+    "eval_loss": 1.3205146789550781,
+    "eval_runtime": 4403.2676,
     "eval_samples": 134942,
-    "eval_samples_per_second": 30.584,
-    "eval_steps_per_second": 7.646,
-    "perplexity": 3.745180660509808,
-    "train_loss": 1.6101340950849867,
-    "train_runtime": 65579.3531,
+    "eval_samples_per_second": 30.646,
+    "eval_steps_per_second": 7.662,
+    "perplexity": 3.7453485333545293,
+    "train_loss": 0.0,
+    "train_runtime": 0.0953,
     "train_samples": 134942,
-    "train_samples_per_second": 10.288,
-    "train_steps_per_second": 2.572
+    "train_samples_per_second": 4248275.036,
+    "train_steps_per_second": 1062084.5
 }

eval_results.json

@@ -1,10 +1,10 @@
 {
-    "epoch": 5.0,
-    "eval_accuracy": 0.6914216185247494,
-    "eval_loss": 1.320469856262207,
-    "eval_runtime": 4412.1637,
+    "epoch": 4.98,
+    "eval_accuracy": 0.6914040854429856,
+    "eval_loss": 1.3205146789550781,
+    "eval_runtime": 4403.2676,
     "eval_samples": 134942,
-    "eval_samples_per_second": 30.584,
-    "eval_steps_per_second": 7.646,
-    "perplexity": 3.745180660509808
+    "eval_samples_per_second": 30.646,
+    "eval_steps_per_second": 7.662,
+    "perplexity": 3.7453485333545293
 }

runs/Aug15_10-57-40_09d4b99a5f37/events.out.tfevents.1660567231.09d4b99a5f37.2797.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8aa1c9239e1022f81b2d658efb066191e8a1c59ef84167dcb5b6fefdb1243ab3
+size 369

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 5.0,
-    "train_loss": 1.6101340950849867,
-    "train_runtime": 65579.3531,
+    "epoch": 4.98,
+    "train_loss": 0.0,
+    "train_runtime": 0.0953,
     "train_samples": 134942,
-    "train_samples_per_second": 10.288,
-    "train_steps_per_second": 2.572
+    "train_samples_per_second": 4248275.036,
+    "train_steps_per_second": 1062084.5
 }

trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.0,
-  "global_step": 168680,
+  "epoch": 4.979843490633152,
+  "global_step": 168000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2024,24 +2024,18 @@
       "step": 168000
     },
     {
-      "epoch": 4.99,
-      "learning_rate": 5.3355465971069484e-08,
-      "loss": 1.5988,
-      "step": 168500
-    },
-    {
-      "epoch": 5.0,
-      "step": 168680,
-      "total_flos": 6.266036456049869e+17,
-      "train_loss": 1.6101340950849867,
-      "train_runtime": 65579.3531,
-      "train_samples_per_second": 10.288,
-      "train_steps_per_second": 2.572
+      "epoch": 4.98,
+      "step": 168000,
+      "total_flos": 6.240794371172598e+17,
+      "train_loss": 0.0,
+      "train_runtime": 0.0953,
+      "train_samples_per_second": 4248275.036,
+      "train_steps_per_second": 1062084.5
     }
   ],
-  "max_steps": 168680,
-  "num_train_epochs": 5,
-  "total_flos": 6.266036456049869e+17,
+  "max_steps": 101208,
+  "num_train_epochs": 3,
+  "total_flos": 6.240794371172598e+17,
   "trial_name": null,
   "trial_params": null
 }