training state at step 10

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.06896551724137931,
+  "epoch": 0.13793103448275862,
   "eval_steps": 1,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -67,6 +67,81 @@
       "eval_samples_per_second": 1.134,
       "eval_steps_per_second": 0.567,
       "step": 4
+    },
+    {
+      "epoch": 0.06896551724137931,
+      "grad_norm": 3.4548702239990234,
+      "learning_rate": 1.1363636363636365e-05,
+      "loss": 1.8838,
+      "step": 5
+    },
+    {
+      "epoch": 0.06896551724137931,
+      "eval_loss": 1.7746165990829468,
+      "eval_runtime": 18.0257,
+      "eval_samples_per_second": 1.11,
+      "eval_steps_per_second": 0.555,
+      "step": 5
+    },
+    {
+      "epoch": 0.08275862068965517,
+      "grad_norm": 3.1943702697753906,
+      "learning_rate": 1.3636363636363637e-05,
+      "loss": 1.7707,
+      "step": 6
+    },
+    {
+      "epoch": 0.08275862068965517,
+      "eval_loss": 1.6792665719985962,
+      "eval_runtime": 17.7498,
+      "eval_samples_per_second": 1.127,
+      "eval_steps_per_second": 0.563,
+      "step": 6
+    },
+    {
+      "epoch": 0.09655172413793103,
+      "grad_norm": 3.318288564682007,
+      "learning_rate": 1.590909090909091e-05,
+      "loss": 1.7171,
+      "step": 7
+    },
+    {
+      "epoch": 0.09655172413793103,
+      "eval_loss": 1.5874873399734497,
+      "eval_runtime": 17.6295,
+      "eval_samples_per_second": 1.134,
+      "eval_steps_per_second": 0.567,
+      "step": 7
+    },
+    {
+      "epoch": 0.1103448275862069,
+      "grad_norm": 3.210330009460449,
+      "learning_rate": 1.8181818181818182e-05,
+      "loss": 1.5734,
+      "step": 8
+    },
+    {
+      "epoch": 0.1103448275862069,
+      "eval_loss": 1.535287618637085,
+      "eval_runtime": 17.6232,
+      "eval_samples_per_second": 1.135,
+      "eval_steps_per_second": 0.567,
+      "step": 8
+    },
+    {
+      "epoch": 0.12413793103448276,
+      "grad_norm": 3.2319107055664062,
+      "learning_rate": 2.0454545454545457e-05,
+      "loss": 1.7986,
+      "step": 9
+    },
+    {
+      "epoch": 0.12413793103448276,
+      "eval_loss": 1.467301607131958,
+      "eval_runtime": 17.5824,
+      "eval_samples_per_second": 1.138,
+      "eval_steps_per_second": 0.569,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -86,7 +161,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5047562107060224.0,
+  "total_flos": 1.169340664455168e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null