Upload trainer_state.json

trainer_state.json

@@ -34,49 +34,49 @@
     {
       "epoch": 0.52,
       "learning_rate": 3.705468102734051e-05,
-      "loss": 0.0159,
+      "loss": 0.0156,
       "step": 2500
     },
     {
       "epoch": 0.62,
       "learning_rate": 3.4465617232808616e-05,
-      "loss": 0.0145,
+      "loss": 0.0137,
       "step": 3000
     },
     {
       "epoch": 0.72,
       "learning_rate": 3.187655343827672e-05,
-      "loss": 0.0107,
+      "loss": 0.0089,
       "step": 3500
     },
     {
       "epoch": 0.83,
       "learning_rate": 2.9287489643744827e-05,
-      "loss": 0.0085,
+      "loss": 0.0093,
       "step": 4000
     },
     {
       "epoch": 0.93,
       "learning_rate": 2.6698425849212926e-05,
-      "loss": 0.0067,
+      "loss": 0.0068,
       "step": 4500
     },
     {
       "epoch": 1.04,
       "learning_rate": 2.4109362054681028e-05,
-      "loss": 0.0068,
+      "loss": 0.0062,
       "step": 5000
     },
     {
       "epoch": 1.14,
       "learning_rate": 2.152029826014913e-05,
-      "loss": 0.0041,
+      "loss": 0.0042,
       "step": 5500
     },
     {
       "epoch": 1.24,
       "learning_rate": 1.8931234465617236e-05,
-      "loss": 0.0051,
+      "loss": 0.0043,
       "step": 6000
     },
     {
@@ -88,45 +88,45 @@
     {
       "epoch": 1.45,
       "learning_rate": 1.375310687655344e-05,
-      "loss": 0.0038,
+      "loss": 0.0015,
       "step": 7000
     },
     {
       "epoch": 1.55,
       "learning_rate": 1.1164043082021542e-05,
-      "loss": 0.0068,
+      "loss": 0.0046,
       "step": 7500
     },
     {
       "epoch": 1.66,
       "learning_rate": 8.574979287489644e-06,
-      "loss": 0.0028,
+      "loss": 0.0025,
       "step": 8000
     },
     {
       "epoch": 1.76,
       "learning_rate": 5.9859154929577465e-06,
-      "loss": 0.0036,
+      "loss": 0.0035,
       "step": 8500
     },
     {
       "epoch": 1.86,
       "learning_rate": 3.396851698425849e-06,
-      "loss": 0.001,
+      "loss": 0.0016,
       "step": 9000
     },
     {
       "epoch": 1.97,
       "learning_rate": 8.07787903893952e-07,
-      "loss": 0.005,
+      "loss": 0.0031,
       "step": 9500
     },
     {
       "epoch": 2.0,
       "step": 9656,
       "total_flos": 2.570302678695936e+16,
-      "train_runtime": 2777.1249,
-      "train_samples_per_second": 3.477
+      "train_runtime": 1563.26,
+      "train_samples_per_second": 6.177
     }
   ],
   "max_steps": 9656,