training state at step 60

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7586206896551724,
+  "epoch": 0.8275862068965517,
   "eval_steps": 1,
-  "global_step": 55,
+  "global_step": 60,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -802,6 +802,66 @@
       "eval_samples_per_second": 1.268,
       "eval_steps_per_second": 0.634,
       "step": 54
+    },
+    {
+      "epoch": 0.7724137931034483,
+      "grad_norm": 2.1803667545318604,
+      "learning_rate": 2.2727272727272728e-06,
+      "loss": 1.4271,
+      "step": 56
+    },
+    {
+      "epoch": 0.7724137931034483,
+      "eval_loss": 0.8433731198310852,
+      "eval_runtime": 17.9885,
+      "eval_samples_per_second": 1.112,
+      "eval_steps_per_second": 0.556,
+      "step": 56
+    },
+    {
+      "epoch": 0.7862068965517242,
+      "grad_norm": 2.3162448406219482,
+      "learning_rate": 4.5454545454545455e-06,
+      "loss": 1.4689,
+      "step": 57
+    },
+    {
+      "epoch": 0.7862068965517242,
+      "eval_loss": 0.8418852090835571,
+      "eval_runtime": 18.2763,
+      "eval_samples_per_second": 1.094,
+      "eval_steps_per_second": 0.547,
+      "step": 57
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.9732853174209595,
+      "learning_rate": 6.818181818181818e-06,
+      "loss": 1.2825,
+      "step": 58
+    },
+    {
+      "epoch": 0.8,
+      "eval_loss": 0.8386393785476685,
+      "eval_runtime": 18.1184,
+      "eval_samples_per_second": 1.104,
+      "eval_steps_per_second": 0.552,
+      "step": 58
+    },
+    {
+      "epoch": 0.8137931034482758,
+      "grad_norm": 2.0547423362731934,
+      "learning_rate": 9.090909090909091e-06,
+      "loss": 1.2972,
+      "step": 59
+    },
+    {
+      "epoch": 0.8137931034482758,
+      "eval_loss": 0.8355510830879211,
+      "eval_runtime": 18.2216,
+      "eval_samples_per_second": 1.098,
+      "eval_steps_per_second": 0.549,
+      "step": 59
     }
   ],
   "logging_steps": 1,
@@ -821,7 +881,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.947646271379866e+16,
+  "total_flos": 7.477855969291469e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null