training state at step 80

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0344827586206897,
+  "epoch": 1.103448275862069,
   "eval_steps": 1,
-  "global_step": 75,
+  "global_step": 80,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1087,6 +1087,81 @@
       "eval_samples_per_second": 1.097,
       "eval_steps_per_second": 0.549,
       "step": 74
+    },
+    {
+      "epoch": 1.0344827586206897,
+      "grad_norm": 2.0641109943389893,
+      "learning_rate": 4.545454545454546e-05,
+      "loss": 1.0793,
+      "step": 75
+    },
+    {
+      "epoch": 1.0344827586206897,
+      "eval_loss": 0.7307212948799133,
+      "eval_runtime": 18.5348,
+      "eval_samples_per_second": 1.079,
+      "eval_steps_per_second": 0.54,
+      "step": 75
+    },
+    {
+      "epoch": 1.0482758620689656,
+      "grad_norm": 1.918042778968811,
+      "learning_rate": 4.772727272727273e-05,
+      "loss": 1.0897,
+      "step": 76
+    },
+    {
+      "epoch": 1.0482758620689656,
+      "eval_loss": 0.7253277897834778,
+      "eval_runtime": 18.4554,
+      "eval_samples_per_second": 1.084,
+      "eval_steps_per_second": 0.542,
+      "step": 76
+    },
+    {
+      "epoch": 1.0620689655172413,
+      "grad_norm": 2.216691493988037,
+      "learning_rate": 5e-05,
+      "loss": 1.2309,
+      "step": 77
+    },
+    {
+      "epoch": 1.0620689655172413,
+      "eval_loss": 0.7224608659744263,
+      "eval_runtime": 18.0728,
+      "eval_samples_per_second": 1.107,
+      "eval_steps_per_second": 0.553,
+      "step": 77
+    },
+    {
+      "epoch": 1.0758620689655172,
+      "grad_norm": 2.304621934890747,
+      "learning_rate": 4.999672209164081e-05,
+      "loss": 1.1722,
+      "step": 78
+    },
+    {
+      "epoch": 1.0758620689655172,
+      "eval_loss": 0.7266848683357239,
+      "eval_runtime": 18.2053,
+      "eval_samples_per_second": 1.099,
+      "eval_steps_per_second": 0.549,
+      "step": 78
+    },
+    {
+      "epoch": 1.089655172413793,
+      "grad_norm": 2.0087103843688965,
+      "learning_rate": 4.998688922613788e-05,
+      "loss": 1.105,
+      "step": 79
+    },
+    {
+      "epoch": 1.089655172413793,
+      "eval_loss": 0.7276325225830078,
+      "eval_runtime": 18.0661,
+      "eval_samples_per_second": 1.107,
+      "eval_steps_per_second": 0.554,
+      "step": 79
     }
   ],
   "logging_steps": 1,
@@ -1106,7 +1181,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.437537876803584e+16,
+  "total_flos": 1.0083257447114342e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null