End of training

runs/Feb26_19-45-51_952abec28ae3/events.out.tfevents.1677440757.952abec28ae3.204.8

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:772d1a2b6349d174f4f593ba723419561901737442b8cbdfd1a112308e0cb08f
-size 6618
+oid sha256:dbbf275ad546f0ef5560e410b86461273d6b7e360bd5a8a783e1b2fe5429877c
+size 6972

trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 20.0,
-  "global_step": 1880,
+  "epoch": 25.0,
+  "global_step": 2350,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -288,18 +288,88 @@
       "step": 1880
     },
     {
-      "epoch": 20.0,
-      "step": 1880,
-      "total_flos": 7.1683864704e+18,
-      "train_loss": 0.5733721875129862,
-      "train_runtime": 1226.2208,
-      "train_samples_per_second": 12.233,
-      "train_steps_per_second": 1.533
+      "epoch": 21.0,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 2.3083,
+      "step": 1974
+    },
+    {
+      "epoch": 21.0,
+      "eval_loss": 1.7549386024475098,
+      "eval_runtime": 37.0581,
+      "eval_samples_per_second": 5.397,
+      "eval_steps_per_second": 0.675,
+      "step": 1974
+    },
+    {
+      "epoch": 22.0,
+      "learning_rate": 1.2e-05,
+      "loss": 2.2542,
+      "step": 2068
+    },
+    {
+      "epoch": 22.0,
+      "eval_loss": 1.7174808979034424,
+      "eval_runtime": 36.8163,
+      "eval_samples_per_second": 5.432,
+      "eval_steps_per_second": 0.679,
+      "step": 2068
+    },
+    {
+      "epoch": 23.0,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 2.2262,
+      "step": 2162
+    },
+    {
+      "epoch": 23.0,
+      "eval_loss": 1.699831485748291,
+      "eval_runtime": 36.7706,
+      "eval_samples_per_second": 5.439,
+      "eval_steps_per_second": 0.68,
+      "step": 2162
+    },
+    {
+      "epoch": 24.0,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 2.2644,
+      "step": 2256
+    },
+    {
+      "epoch": 24.0,
+      "eval_loss": 1.7019526958465576,
+      "eval_runtime": 37.036,
+      "eval_samples_per_second": 5.4,
+      "eval_steps_per_second": 0.675,
+      "step": 2256
+    },
+    {
+      "epoch": 25.0,
+      "learning_rate": 0.0,
+      "loss": 2.2392,
+      "step": 2350
+    },
+    {
+      "epoch": 25.0,
+      "eval_loss": 1.6933141946792603,
+      "eval_runtime": 36.9874,
+      "eval_samples_per_second": 5.407,
+      "eval_steps_per_second": 0.676,
+      "step": 2350
+    },
+    {
+      "epoch": 25.0,
+      "step": 2350,
+      "total_flos": 8.960483088e+18,
+      "train_loss": 0.45169270616896606,
+      "train_runtime": 1228.9697,
+      "train_samples_per_second": 15.257,
+      "train_steps_per_second": 1.912
     }
   ],
-  "max_steps": 1880,
-  "num_train_epochs": 20,
-  "total_flos": 7.1683864704e+18,
+  "max_steps": 2350,
+  "num_train_epochs": 25,
+  "total_flos": 8.960483088e+18,
   "trial_name": null,
   "trial_params": null
 }