training state at step 55

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6896551724137931,
+  "epoch": 0.7586206896551724,
   "eval_steps": 1,
-  "global_step": 50,
+  "global_step": 55,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -727,6 +727,81 @@
       "eval_samples_per_second": 1.275,
       "eval_steps_per_second": 0.638,
       "step": 49
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "grad_norm": 2.119081497192383,
+      "learning_rate": 2.272727272727273e-05,
+      "loss": 1.5447,
+      "step": 50
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "eval_loss": 0.8692445755004883,
+      "eval_runtime": 15.6827,
+      "eval_samples_per_second": 1.275,
+      "eval_steps_per_second": 0.638,
+      "step": 50
+    },
+    {
+      "epoch": 0.7034482758620689,
+      "grad_norm": 1.9801068305969238,
+      "learning_rate": 2.5e-05,
+      "loss": 1.2777,
+      "step": 51
+    },
+    {
+      "epoch": 0.7034482758620689,
+      "eval_loss": 0.8668963313102722,
+      "eval_runtime": 15.7049,
+      "eval_samples_per_second": 1.273,
+      "eval_steps_per_second": 0.637,
+      "step": 51
+    },
+    {
+      "epoch": 0.7172413793103448,
+      "grad_norm": 2.0645248889923096,
+      "learning_rate": 2.7272727272727273e-05,
+      "loss": 1.3444,
+      "step": 52
+    },
+    {
+      "epoch": 0.7172413793103448,
+      "eval_loss": 0.8615155220031738,
+      "eval_runtime": 15.6899,
+      "eval_samples_per_second": 1.275,
+      "eval_steps_per_second": 0.637,
+      "step": 52
+    },
+    {
+      "epoch": 0.7310344827586207,
+      "grad_norm": 2.1377453804016113,
+      "learning_rate": 2.954545454545455e-05,
+      "loss": 1.4174,
+      "step": 53
+    },
+    {
+      "epoch": 0.7310344827586207,
+      "eval_loss": 0.8575263023376465,
+      "eval_runtime": 15.6427,
+      "eval_samples_per_second": 1.279,
+      "eval_steps_per_second": 0.639,
+      "step": 53
+    },
+    {
+      "epoch": 0.7448275862068966,
+      "grad_norm": 2.1462454795837402,
+      "learning_rate": 3.181818181818182e-05,
+      "loss": 1.429,
+      "step": 54
+    },
+    {
+      "epoch": 0.7448275862068966,
+      "eval_loss": 0.8533774614334106,
+      "eval_runtime": 15.7668,
+      "eval_samples_per_second": 1.268,
+      "eval_steps_per_second": 0.634,
+      "step": 54
     }
   ],
   "logging_steps": 1,
@@ -746,7 +821,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.308160393859891e+16,
+  "total_flos": 6.947646271379866e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null