End of training

runs/Feb26_20-51-04_b0051077c075/events.out.tfevents.1677444670.b0051077c075.1132.8

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9275e7189857b26064353adaee10a9b82b29378ad56a9ae212931d2e69bb1ce
-size 6237
+oid sha256:86e1938c98432ff65989afd08ffaf9b626069cc58af6568414f790b3c8969917
+size 6591

trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.0,
-  "global_step": 940,
+  "epoch": 15.0,
+  "global_step": 1410,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -148,18 +148,88 @@
       "step": 940
     },
     {
-      "epoch": 10.0,
-      "step": 940,
-      "total_flos": 2.2901801877504e+17,
-      "train_loss": 1.5650983120532747,
-      "train_runtime": 702.8978,
-      "train_samples_per_second": 10.67,
-      "train_steps_per_second": 1.337
+      "epoch": 11.0,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 3.0767,
+      "step": 1034
+    },
+    {
+      "epoch": 11.0,
+      "eval_loss": 2.634387254714966,
+      "eval_runtime": 23.8188,
+      "eval_samples_per_second": 8.397,
+      "eval_steps_per_second": 1.05,
+      "step": 1034
+    },
+    {
+      "epoch": 12.0,
+      "learning_rate": 2e-05,
+      "loss": 3.0397,
+      "step": 1128
+    },
+    {
+      "epoch": 12.0,
+      "eval_loss": 2.6142303943634033,
+      "eval_runtime": 23.2502,
+      "eval_samples_per_second": 8.602,
+      "eval_steps_per_second": 1.075,
+      "step": 1128
+    },
+    {
+      "epoch": 13.0,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 2.982,
+      "step": 1222
+    },
+    {
+      "epoch": 13.0,
+      "eval_loss": 2.678748369216919,
+      "eval_runtime": 22.8778,
+      "eval_samples_per_second": 8.742,
+      "eval_steps_per_second": 1.093,
+      "step": 1222
+    },
+    {
+      "epoch": 14.0,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 2.883,
+      "step": 1316
+    },
+    {
+      "epoch": 14.0,
+      "eval_loss": 2.6491620540618896,
+      "eval_runtime": 22.7109,
+      "eval_samples_per_second": 8.806,
+      "eval_steps_per_second": 1.101,
+      "step": 1316
+    },
+    {
+      "epoch": 15.0,
+      "learning_rate": 0.0,
+      "loss": 2.8978,
+      "step": 1410
+    },
+    {
+      "epoch": 15.0,
+      "eval_loss": 2.631659507751465,
+      "eval_runtime": 23.5813,
+      "eval_samples_per_second": 8.481,
+      "eval_steps_per_second": 1.06,
+      "step": 1410
+    },
+    {
+      "epoch": 15.0,
+      "step": 1410,
+      "total_flos": 3.4352702816256e+17,
+      "train_loss": 0.9919471253740026,
+      "train_runtime": 710.2043,
+      "train_samples_per_second": 15.841,
+      "train_steps_per_second": 1.985
     }
   ],
-  "max_steps": 940,
-  "num_train_epochs": 10,
-  "total_flos": 2.2901801877504e+17,
+  "max_steps": 1410,
+  "num_train_epochs": 15,
+  "total_flos": 3.4352702816256e+17,
   "trial_name": null,
   "trial_params": null
 }