Training in progress, epoch 1

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c4851d0fda021876b9eb5ecbd6ec0d108d643bb4b81a517a68af72134d8b407
+oid sha256:d9dcafb75e33763bcbb1dcac4844987b4bc4804afc8cd5a98e4c454d0a897ab4
 size 218138576

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
     "train_loss": 0.3465735912322998,
-    "train_runtime": 16.7146,
+    "train_runtime": 17.8418,
     "train_samples": 61966,
-    "train_samples_per_second": 0.598,
-    "train_steps_per_second": 0.06
+    "train_samples_per_second": 0.56,
+    "train_steps_per_second": 0.056
 }

runs/Dec10_16-14-13_uclaml03.cs.ucla.edu/events.out.tfevents.1702253749.uclaml03.cs.ucla.edu.2937386.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e7d1f1df561f86a586250bbb839d244013c095b1126974abb020c4a1c64145c
+size 6088

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
     "train_loss": 0.3465735912322998,
-    "train_runtime": 16.7146,
+    "train_runtime": 17.8418,
     "train_samples": 61966,
-    "train_samples_per_second": 0.598,
-    "train_steps_per_second": 0.06
+    "train_samples_per_second": 0.56,
+    "train_steps_per_second": 0.056
 }

trainer_state.json

@@ -33,9 +33,9 @@
       "eval_rewards/chosen": 0.0,
       "eval_rewards/margins": 0.0,
       "eval_rewards/rejected": 0.0,
-      "eval_runtime": 5.0795,
-      "eval_samples_per_second": 1.969,
-      "eval_steps_per_second": 0.394,
+      "eval_runtime": 5.1452,
+      "eval_samples_per_second": 1.944,
+      "eval_steps_per_second": 0.389,
       "step": 1
     },
     {
@@ -43,9 +43,9 @@
       "step": 1,
       "total_flos": 0.0,
       "train_loss": 0.3465735912322998,
-      "train_runtime": 16.7146,
-      "train_samples_per_second": 0.598,
-      "train_steps_per_second": 0.06
+      "train_runtime": 17.8418,
+      "train_samples_per_second": 0.56,
+      "train_steps_per_second": 0.056
     }
   ],
   "logging_steps": 10,