training state at step 70

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.896551724137931,
+  "epoch": 0.9655172413793104,
   "eval_steps": 1,
-  "global_step": 65,
+  "global_step": 70,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -937,6 +937,81 @@
       "eval_samples_per_second": 1.097,
       "eval_steps_per_second": 0.549,
       "step": 64
+    },
+    {
+      "epoch": 0.896551724137931,
+      "grad_norm": 1.9588886499404907,
+      "learning_rate": 2.272727272727273e-05,
+      "loss": 1.3699,
+      "step": 65
+    },
+    {
+      "epoch": 0.896551724137931,
+      "eval_loss": 0.8241379857063293,
+      "eval_runtime": 18.6162,
+      "eval_samples_per_second": 1.074,
+      "eval_steps_per_second": 0.537,
+      "step": 65
+    },
+    {
+      "epoch": 0.9103448275862069,
+      "grad_norm": 2.001984119415283,
+      "learning_rate": 2.5e-05,
+      "loss": 1.4399,
+      "step": 66
+    },
+    {
+      "epoch": 0.9103448275862069,
+      "eval_loss": 0.8220138549804688,
+      "eval_runtime": 18.4936,
+      "eval_samples_per_second": 1.081,
+      "eval_steps_per_second": 0.541,
+      "step": 66
+    },
+    {
+      "epoch": 0.9241379310344827,
+      "grad_norm": 1.9502840042114258,
+      "learning_rate": 2.7272727272727273e-05,
+      "loss": 1.1969,
+      "step": 67
+    },
+    {
+      "epoch": 0.9241379310344827,
+      "eval_loss": 0.8098680377006531,
+      "eval_runtime": 18.2406,
+      "eval_samples_per_second": 1.096,
+      "eval_steps_per_second": 0.548,
+      "step": 67
+    },
+    {
+      "epoch": 0.9379310344827586,
+      "grad_norm": 1.8572745323181152,
+      "learning_rate": 2.954545454545455e-05,
+      "loss": 1.1968,
+      "step": 68
+    },
+    {
+      "epoch": 0.9379310344827586,
+      "eval_loss": 0.7934565544128418,
+      "eval_runtime": 18.2457,
+      "eval_samples_per_second": 1.096,
+      "eval_steps_per_second": 0.548,
+      "step": 68
+    },
+    {
+      "epoch": 0.9517241379310345,
+      "grad_norm": 2.0354831218719482,
+      "learning_rate": 3.181818181818182e-05,
+      "loss": 1.2528,
+      "step": 69
+    },
+    {
+      "epoch": 0.9517241379310345,
+      "eval_loss": 0.7829666137695312,
+      "eval_runtime": 18.2217,
+      "eval_samples_per_second": 1.098,
+      "eval_steps_per_second": 0.549,
+      "step": 69
     }
   ],
   "logging_steps": 1,
@@ -956,7 +1031,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.144087573982413e+16,
+  "total_flos": 8.799498944033587e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null