training state at step 15

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.13793103448275862,
+  "epoch": 0.20689655172413793,
   "eval_steps": 1,
-  "global_step": 10,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -142,6 +142,81 @@
       "eval_samples_per_second": 1.138,
       "eval_steps_per_second": 0.569,
       "step": 9
+    },
+    {
+      "epoch": 0.13793103448275862,
+      "grad_norm": 2.79286789894104,
+      "learning_rate": 2.272727272727273e-05,
+      "loss": 1.5025,
+      "step": 10
+    },
+    {
+      "epoch": 0.13793103448275862,
+      "eval_loss": 1.3961191177368164,
+      "eval_runtime": 18.3446,
+      "eval_samples_per_second": 1.09,
+      "eval_steps_per_second": 0.545,
+      "step": 10
+    },
+    {
+      "epoch": 0.15172413793103448,
+      "grad_norm": 2.885422706604004,
+      "learning_rate": 2.5e-05,
+      "loss": 1.5477,
+      "step": 11
+    },
+    {
+      "epoch": 0.15172413793103448,
+      "eval_loss": 1.3420469760894775,
+      "eval_runtime": 17.7683,
+      "eval_samples_per_second": 1.126,
+      "eval_steps_per_second": 0.563,
+      "step": 11
+    },
+    {
+      "epoch": 0.16551724137931034,
+      "grad_norm": 2.7671327590942383,
+      "learning_rate": 2.7272727272727273e-05,
+      "loss": 1.6921,
+      "step": 12
+    },
+    {
+      "epoch": 0.16551724137931034,
+      "eval_loss": 1.3071445226669312,
+      "eval_runtime": 17.652,
+      "eval_samples_per_second": 1.133,
+      "eval_steps_per_second": 0.567,
+      "step": 12
+    },
+    {
+      "epoch": 0.1793103448275862,
+      "grad_norm": 2.9047963619232178,
+      "learning_rate": 2.954545454545455e-05,
+      "loss": 1.5365,
+      "step": 13
+    },
+    {
+      "epoch": 0.1793103448275862,
+      "eval_loss": 1.2601890563964844,
+      "eval_runtime": 17.5232,
+      "eval_samples_per_second": 1.141,
+      "eval_steps_per_second": 0.571,
+      "step": 13
+    },
+    {
+      "epoch": 0.19310344827586207,
+      "grad_norm": 2.6054675579071045,
+      "learning_rate": 3.181818181818182e-05,
+      "loss": 1.6621,
+      "step": 14
+    },
+    {
+      "epoch": 0.19310344827586207,
+      "eval_loss": 1.2506535053253174,
+      "eval_runtime": 17.6295,
+      "eval_samples_per_second": 1.134,
+      "eval_steps_per_second": 0.567,
+      "step": 14
     }
   ],
   "logging_steps": 1,
@@ -161,7 +236,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.169340664455168e+16,
+  "total_flos": 1.8199561861840896e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null