End of training

runs/Feb28_16-54-08_7c779bfb7013/events.out.tfevents.1677603252.7c779bfb7013.343.6

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fc70b496e42516c3c30d1322213233c7c4981543b816a9963e194286ff2c928
-size 6672
+oid sha256:d555a2b0f42e6420c3fbdf504df6f3f94388acb4213d83946408ba7ca3d3a42b
+size 7026

trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 15.0,
-  "global_step": 1410,
+  "epoch": 20.0,
+  "global_step": 1880,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -218,18 +218,88 @@
       "step": 1410
     },
     {
-      "epoch": 15.0,
-      "step": 1410,
-      "total_flos": 5.3762898528e+18,
-      "train_loss": 1.3009196721070202,
-      "train_runtime": 1911.8077,
-      "train_samples_per_second": 5.884,
-      "train_steps_per_second": 0.738
+      "epoch": 16.0,
+      "learning_rate": 2e-05,
+      "loss": 2.3134,
+      "step": 1504
+    },
+    {
+      "epoch": 16.0,
+      "eval_loss": 1.7698218822479248,
+      "eval_runtime": 34.7625,
+      "eval_samples_per_second": 5.753,
+      "eval_steps_per_second": 0.719,
+      "step": 1504
+    },
+    {
+      "epoch": 17.0,
+      "learning_rate": 1.5e-05,
+      "loss": 2.3423,
+      "step": 1598
+    },
+    {
+      "epoch": 17.0,
+      "eval_loss": 1.7581219673156738,
+      "eval_runtime": 35.8583,
+      "eval_samples_per_second": 5.578,
+      "eval_steps_per_second": 0.697,
+      "step": 1598
+    },
+    {
+      "epoch": 18.0,
+      "learning_rate": 1e-05,
+      "loss": 2.3536,
+      "step": 1692
+    },
+    {
+      "epoch": 18.0,
+      "eval_loss": 1.7658276557922363,
+      "eval_runtime": 35.6301,
+      "eval_samples_per_second": 5.613,
+      "eval_steps_per_second": 0.702,
+      "step": 1692
+    },
+    {
+      "epoch": 19.0,
+      "learning_rate": 5e-06,
+      "loss": 2.2957,
+      "step": 1786
+    },
+    {
+      "epoch": 19.0,
+      "eval_loss": 1.7328851222991943,
+      "eval_runtime": 36.2644,
+      "eval_samples_per_second": 5.515,
+      "eval_steps_per_second": 0.689,
+      "step": 1786
+    },
+    {
+      "epoch": 20.0,
+      "learning_rate": 0.0,
+      "loss": 2.274,
+      "step": 1880
+    },
+    {
+      "epoch": 20.0,
+      "eval_loss": 1.7334604263305664,
+      "eval_runtime": 34.2732,
+      "eval_samples_per_second": 5.835,
+      "eval_steps_per_second": 0.729,
+      "step": 1880
+    },
+    {
+      "epoch": 20.0,
+      "step": 1880,
+      "total_flos": 7.1683864704e+18,
+      "train_loss": 0.5789503787426238,
+      "train_runtime": 1191.4496,
+      "train_samples_per_second": 12.59,
+      "train_steps_per_second": 1.578
     }
   ],
-  "max_steps": 1410,
-  "num_train_epochs": 15,
-  "total_flos": 5.3762898528e+18,
+  "max_steps": 1880,
+  "num_train_epochs": 20,
+  "total_flos": 7.1683864704e+18,
   "trial_name": null,
   "trial_params": null
 }