training state at step 110

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.4551724137931035,
+  "epoch": 1.524137931034483,
   "eval_steps": 1,
-  "global_step": 105,
+  "global_step": 110,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1522,6 +1522,81 @@
       "eval_samples_per_second": 1.309,
       "eval_steps_per_second": 0.655,
       "step": 104
+    },
+    {
+      "epoch": 1.4551724137931035,
+      "grad_norm": 1.98838472366333,
+      "learning_rate": 1.1363636363636365e-05,
+      "loss": 1.2297,
+      "step": 105
+    },
+    {
+      "epoch": 1.4551724137931035,
+      "eval_loss": 0.6155186891555786,
+      "eval_runtime": 15.2373,
+      "eval_samples_per_second": 1.313,
+      "eval_steps_per_second": 0.656,
+      "step": 105
+    },
+    {
+      "epoch": 1.4689655172413794,
+      "grad_norm": 1.8609561920166016,
+      "learning_rate": 1.3636363636363637e-05,
+      "loss": 0.9922,
+      "step": 106
+    },
+    {
+      "epoch": 1.4689655172413794,
+      "eval_loss": 0.6143234372138977,
+      "eval_runtime": 15.4977,
+      "eval_samples_per_second": 1.291,
+      "eval_steps_per_second": 0.645,
+      "step": 106
+    },
+    {
+      "epoch": 1.4827586206896552,
+      "grad_norm": 2.010931968688965,
+      "learning_rate": 1.590909090909091e-05,
+      "loss": 1.1338,
+      "step": 107
+    },
+    {
+      "epoch": 1.4827586206896552,
+      "eval_loss": 0.610894501209259,
+      "eval_runtime": 15.4008,
+      "eval_samples_per_second": 1.299,
+      "eval_steps_per_second": 0.649,
+      "step": 107
+    },
+    {
+      "epoch": 1.4965517241379311,
+      "grad_norm": 1.9721729755401611,
+      "learning_rate": 1.8181818181818182e-05,
+      "loss": 1.0459,
+      "step": 108
+    },
+    {
+      "epoch": 1.4965517241379311,
+      "eval_loss": 0.606325089931488,
+      "eval_runtime": 15.2962,
+      "eval_samples_per_second": 1.308,
+      "eval_steps_per_second": 0.654,
+      "step": 108
+    },
+    {
+      "epoch": 1.510344827586207,
+      "grad_norm": 2.1253089904785156,
+      "learning_rate": 2.0454545454545457e-05,
+      "loss": 1.285,
+      "step": 109
+    },
+    {
+      "epoch": 1.510344827586207,
+      "eval_loss": 0.6013532876968384,
+      "eval_runtime": 15.3278,
+      "eval_samples_per_second": 1.305,
+      "eval_steps_per_second": 0.652,
+      "step": 109
     }
   ],
   "logging_steps": 1,
@@ -1541,7 +1616,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.325273987039232e+17,
+  "total_flos": 1.3916678204158771e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null