training state at step 45

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5517241379310345,
+  "epoch": 0.6206896551724138,
   "eval_steps": 1,
-  "global_step": 40,
+  "global_step": 45,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -592,6 +592,66 @@
       "eval_samples_per_second": 1.137,
       "eval_steps_per_second": 0.569,
       "step": 39
+    },
+    {
+      "epoch": 0.5655172413793104,
+      "grad_norm": 2.2170450687408447,
+      "learning_rate": 2.2727272727272728e-06,
+      "loss": 1.316,
+      "step": 41
+    },
+    {
+      "epoch": 0.5655172413793104,
+      "eval_loss": 0.9163956642150879,
+      "eval_runtime": 15.7145,
+      "eval_samples_per_second": 1.273,
+      "eval_steps_per_second": 0.636,
+      "step": 41
+    },
+    {
+      "epoch": 0.5793103448275863,
+      "grad_norm": 2.2266974449157715,
+      "learning_rate": 4.5454545454545455e-06,
+      "loss": 1.3854,
+      "step": 42
+    },
+    {
+      "epoch": 0.5793103448275863,
+      "eval_loss": 0.9137259721755981,
+      "eval_runtime": 15.7133,
+      "eval_samples_per_second": 1.273,
+      "eval_steps_per_second": 0.636,
+      "step": 42
+    },
+    {
+      "epoch": 0.593103448275862,
+      "grad_norm": 2.3451268672943115,
+      "learning_rate": 6.818181818181818e-06,
+      "loss": 1.4208,
+      "step": 43
+    },
+    {
+      "epoch": 0.593103448275862,
+      "eval_loss": 0.9096618890762329,
+      "eval_runtime": 15.7895,
+      "eval_samples_per_second": 1.267,
+      "eval_steps_per_second": 0.633,
+      "step": 43
+    },
+    {
+      "epoch": 0.6068965517241379,
+      "grad_norm": 2.0125885009765625,
+      "learning_rate": 9.090909090909091e-06,
+      "loss": 1.4302,
+      "step": 44
+    },
+    {
+      "epoch": 0.6068965517241379,
+      "eval_loss": 0.9058458209037781,
+      "eval_runtime": 15.6899,
+      "eval_samples_per_second": 1.275,
+      "eval_steps_per_second": 0.637,
+      "step": 44
     }
   ],
   "logging_steps": 1,
@@ -611,7 +671,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.112519916024627e+16,
+  "total_flos": 5.643858048835584e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null