End of training

runs/Feb26_21-44-51_952abec28ae3/events.out.tfevents.1677447897.952abec28ae3.204.18

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b73c6723f1f176f5d5d3c51d1cdf0de8120563b3260a7b917ea12bbc649b66b
-size 6618
+oid sha256:919ecfdf0abfd9fc3122e048fa8400a9b15c3d174c42bfc547962f364933aaff
+size 6972

trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 45.0,
-  "global_step": 4230,
+  "epoch": 50.0,
+  "global_step": 4700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -638,18 +638,88 @@
       "step": 4230
     },
     {
-      "epoch": 45.0,
-      "step": 4230,
-      "total_flos": 1.61288695584e+19,
-      "train_loss": 0.2412280865031213,
-      "train_runtime": 1234.9371,
-      "train_samples_per_second": 27.329,
-      "train_steps_per_second": 3.425
+      "epoch": 46.0,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 2.1464,
+      "step": 4324
+    },
+    {
+      "epoch": 46.0,
+      "eval_loss": 1.6795276403427124,
+      "eval_runtime": 37.4735,
+      "eval_samples_per_second": 5.337,
+      "eval_steps_per_second": 0.667,
+      "step": 4324
+    },
+    {
+      "epoch": 47.0,
+      "learning_rate": 6e-06,
+      "loss": 2.1809,
+      "step": 4418
+    },
+    {
+      "epoch": 47.0,
+      "eval_loss": 1.6775075197219849,
+      "eval_runtime": 37.2204,
+      "eval_samples_per_second": 5.373,
+      "eval_steps_per_second": 0.672,
+      "step": 4418
+    },
+    {
+      "epoch": 48.0,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 2.174,
+      "step": 4512
+    },
+    {
+      "epoch": 48.0,
+      "eval_loss": 1.666752576828003,
+      "eval_runtime": 36.9029,
+      "eval_samples_per_second": 5.42,
+      "eval_steps_per_second": 0.677,
+      "step": 4512
+    },
+    {
+      "epoch": 49.0,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 2.1391,
+      "step": 4606
+    },
+    {
+      "epoch": 49.0,
+      "eval_loss": 1.6559373140335083,
+      "eval_runtime": 36.8614,
+      "eval_samples_per_second": 5.426,
+      "eval_steps_per_second": 0.678,
+      "step": 4606
+    },
+    {
+      "epoch": 50.0,
+      "learning_rate": 0.0,
+      "loss": 2.1466,
+      "step": 4700
+    },
+    {
+      "epoch": 50.0,
+      "eval_loss": 1.6657767295837402,
+      "eval_runtime": 37.3694,
+      "eval_samples_per_second": 5.352,
+      "eval_steps_per_second": 0.669,
+      "step": 4700
+    },
+    {
+      "epoch": 50.0,
+      "step": 4700,
+      "total_flos": 1.7920966176e+19,
+      "train_loss": 0.21573773972531582,
+      "train_runtime": 1237.9738,
+      "train_samples_per_second": 30.291,
+      "train_steps_per_second": 3.797
     }
   ],
-  "max_steps": 4230,
-  "num_train_epochs": 45,
-  "total_flos": 1.61288695584e+19,
+  "max_steps": 4700,
+  "num_train_epochs": 50,
+  "total_flos": 1.7920966176e+19,
   "trial_name": null,
   "trial_params": null
 }