End of training

runs/Feb28_17-52-06_7c779bfb7013/events.out.tfevents.1677606732.7c779bfb7013.343.8

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2620daea2fcc95077507cc9936f97d36567df7d216e83d3e7c6f94ef4eb83fb1
-size 6672
+oid sha256:e7200fb45c44e48bf44b411cce26f438d34e84dd1de1ec0c47c02652fb2e4761
+size 7026

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": 0.5789503787426238,
-      "train_runtime": 1191.4496,
-      "train_samples_per_second": 12.59,
-      "train_steps_per_second": 1.578
+      "epoch": 21.0,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 2.2906,
+      "step": 1974
+    },
+    {
+      "epoch": 21.0,
+      "eval_loss": 1.734320878982544,
+      "eval_runtime": 34.5789,
+      "eval_samples_per_second": 5.784,
+      "eval_steps_per_second": 0.723,
+      "step": 1974
+    },
+    {
+      "epoch": 22.0,
+      "learning_rate": 1.2e-05,
+      "loss": 2.2492,
+      "step": 2068
+    },
+    {
+      "epoch": 22.0,
+      "eval_loss": 1.7080261707305908,
+      "eval_runtime": 35.1218,
+      "eval_samples_per_second": 5.694,
+      "eval_steps_per_second": 0.712,
+      "step": 2068
+    },
+    {
+      "epoch": 23.0,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 2.2516,
+      "step": 2162
+    },
+    {
+      "epoch": 23.0,
+      "eval_loss": 1.718016505241394,
+      "eval_runtime": 34.8144,
+      "eval_samples_per_second": 5.745,
+      "eval_steps_per_second": 0.718,
+      "step": 2162
+    },
+    {
+      "epoch": 24.0,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 2.2574,
+      "step": 2256
+    },
+    {
+      "epoch": 24.0,
+      "eval_loss": 1.7081444263458252,
+      "eval_runtime": 34.6174,
+      "eval_samples_per_second": 5.777,
+      "eval_steps_per_second": 0.722,
+      "step": 2256
+    },
+    {
+      "epoch": 25.0,
+      "learning_rate": 0.0,
+      "loss": 2.2508,
+      "step": 2350
+    },
+    {
+      "epoch": 25.0,
+      "eval_loss": 1.7065184116363525,
+      "eval_runtime": 34.9055,
+      "eval_samples_per_second": 5.73,
+      "eval_steps_per_second": 0.716,
+      "step": 2350
+    },
+    {
+      "epoch": 25.0,
+      "step": 2350,
+      "total_flos": 8.960483088e+18,
+      "train_loss": 0.45198433734001,
+      "train_runtime": 1195.2772,
+      "train_samples_per_second": 15.687,
+      "train_steps_per_second": 1.966
     }
   ],
-  "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
 }