Training in progress, epoch 1

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
     "train_loss": 0.3465735912322998,
-    "train_runtime": 17.8418,
+    "train_runtime": 16.8246,
     "train_samples": 61966,
-    "train_samples_per_second": 0.56,
-    "train_steps_per_second": 0.056
+    "train_samples_per_second": 0.594,
+    "train_steps_per_second": 0.059
 }

runs/Dec10_16-14-13_uclaml03.cs.ucla.edu/events.out.tfevents.1702253775.uclaml03.cs.ucla.edu.2937386.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:982fa762187573083c1acd1a4cf68f11fb403c395af8312de02bb873b49b88e3
+size 6088

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
     "train_loss": 0.3465735912322998,
-    "train_runtime": 17.8418,
+    "train_runtime": 16.8246,
     "train_samples": 61966,
-    "train_samples_per_second": 0.56,
-    "train_steps_per_second": 0.056
+    "train_samples_per_second": 0.594,
+    "train_steps_per_second": 0.059
 }

trainer_state.json

@@ -33,9 +33,9 @@
       "eval_rewards/chosen": 0.0,
       "eval_rewards/margins": 0.0,
       "eval_rewards/rejected": 0.0,
-      "eval_runtime": 5.1452,
-      "eval_samples_per_second": 1.944,
-      "eval_steps_per_second": 0.389,
+      "eval_runtime": 5.132,
+      "eval_samples_per_second": 1.949,
+      "eval_steps_per_second": 0.39,
       "step": 1
     },
     {
@@ -43,9 +43,9 @@
       "step": 1,
       "total_flos": 0.0,
       "train_loss": 0.3465735912322998,
-      "train_runtime": 17.8418,
-      "train_samples_per_second": 0.56,
-      "train_steps_per_second": 0.056
+      "train_runtime": 16.8246,
+      "train_samples_per_second": 0.594,
+      "train_steps_per_second": 0.059
     }
   ],
   "logging_steps": 10,