training state at step 105

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.3793103448275863,
+  "epoch": 1.4551724137931035,
   "eval_steps": 1,
-  "global_step": 100,
+  "global_step": 105,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1462,6 +1462,66 @@
       "eval_samples_per_second": 1.101,
       "eval_steps_per_second": 0.55,
       "step": 99
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 2.0707523822784424,
+      "learning_rate": 2.2727272727272728e-06,
+      "loss": 1.2557,
+      "step": 101
+    },
+    {
+      "epoch": 1.4,
+      "eval_loss": 0.6193124055862427,
+      "eval_runtime": 15.3335,
+      "eval_samples_per_second": 1.304,
+      "eval_steps_per_second": 0.652,
+      "step": 101
+    },
+    {
+      "epoch": 1.4137931034482758,
+      "grad_norm": 2.099379539489746,
+      "learning_rate": 4.5454545454545455e-06,
+      "loss": 1.1953,
+      "step": 102
+    },
+    {
+      "epoch": 1.4137931034482758,
+      "eval_loss": 0.6185603141784668,
+      "eval_runtime": 15.3458,
+      "eval_samples_per_second": 1.303,
+      "eval_steps_per_second": 0.652,
+      "step": 102
+    },
+    {
+      "epoch": 1.4275862068965517,
+      "grad_norm": 1.9917728900909424,
+      "learning_rate": 6.818181818181818e-06,
+      "loss": 1.2443,
+      "step": 103
+    },
+    {
+      "epoch": 1.4275862068965517,
+      "eval_loss": 0.6176949739456177,
+      "eval_runtime": 15.2437,
+      "eval_samples_per_second": 1.312,
+      "eval_steps_per_second": 0.656,
+      "step": 103
+    },
+    {
+      "epoch": 1.4413793103448276,
+      "grad_norm": 1.8723604679107666,
+      "learning_rate": 9.090909090909091e-06,
+      "loss": 1.0864,
+      "step": 104
+    },
+    {
+      "epoch": 1.4413793103448276,
+      "eval_loss": 0.6164005994796753,
+      "eval_runtime": 15.2753,
+      "eval_samples_per_second": 1.309,
+      "eval_steps_per_second": 0.655,
+      "step": 104
     }
   ],
   "logging_steps": 1,
@@ -1481,7 +1541,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2709753377329971e+17,
+  "total_flos": 1.325273987039232e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null