Upload trainer_state.json

trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.5,
-  "global_step": 17500,
+  "epoch": 5.0,
+  "global_step": 25000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -238,13 +238,111 @@
     {
       "epoch": 3.5,
       "learning_rate": 6e-06,
-      "loss": 1.3259,
+      "loss": 1.3106,
       "step": 17500
+    },
+    {
+      "epoch": 3.6,
+      "learning_rate": 5.600000000000001e-06,
+      "loss": 1.3268,
+      "step": 18000
+    },
+    {
+      "epoch": 3.7,
+      "learning_rate": 5.2e-06,
+      "loss": 1.3112,
+      "step": 18500
+    },
+    {
+      "epoch": 3.8,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 1.3199,
+      "step": 19000
+    },
+    {
+      "epoch": 3.9,
+      "learning_rate": 4.4e-06,
+      "loss": 1.3137,
+      "step": 19500
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.3216,
+      "step": 20000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.1937603950500488,
+      "eval_runtime": 291.0578,
+      "eval_samples_per_second": 34.357,
+      "eval_steps_per_second": 4.295,
+      "step": 20000
+    },
+    {
+      "epoch": 4.1,
+      "learning_rate": 3.6000000000000003e-06,
+      "loss": 1.3143,
+      "step": 20500
+    },
+    {
+      "epoch": 4.2,
+      "learning_rate": 3.2000000000000003e-06,
+      "loss": 1.327,
+      "step": 21000
+    },
+    {
+      "epoch": 4.3,
+      "learning_rate": 2.8000000000000003e-06,
+      "loss": 1.3079,
+      "step": 21500
+    },
+    {
+      "epoch": 4.4,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 1.3193,
+      "step": 22000
+    },
+    {
+      "epoch": 4.5,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.3018,
+      "step": 22500
+    },
+    {
+      "epoch": 4.6,
+      "learning_rate": 1.6000000000000001e-06,
+      "loss": 1.3092,
+      "step": 23000
+    },
+    {
+      "epoch": 4.7,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 1.3076,
+      "step": 23500
+    },
+    {
+      "epoch": 4.8,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 1.3124,
+      "step": 24000
+    },
+    {
+      "epoch": 4.9,
+      "learning_rate": 4.0000000000000003e-07,
+      "loss": 1.3079,
+      "step": 24500
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.0,
+      "loss": 1.3194,
+      "step": 25000
     }
   ],
   "max_steps": 25000,
   "num_train_epochs": 5,
-  "total_flos": 1.856705292288e+16,
+  "total_flos": 2.65243613184e+16,
   "trial_name": null,
   "trial_params": null
 }