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": 27.423,
+    "train_runtime": 17.6734,
     "train_samples": 61966,
-    "train_samples_per_second": 0.365,
-    "train_steps_per_second": 0.036
+    "train_samples_per_second": 0.566,
+    "train_steps_per_second": 0.057
 }

runs/Dec10_16-11-47_uclaml03.cs.ucla.edu/events.out.tfevents.1702253602.uclaml03.cs.ucla.edu.2936686.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbabe86d1716cd7d30bd6450626a9baf98dacbe028cc8c3efe53008e1814d7c0
+size 6089

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
     "train_loss": 0.3465735912322998,
-    "train_runtime": 27.423,
+    "train_runtime": 17.6734,
     "train_samples": 61966,
-    "train_samples_per_second": 0.365,
-    "train_steps_per_second": 0.036
+    "train_samples_per_second": 0.566,
+    "train_steps_per_second": 0.057
 }

trainer_state.json

@@ -24,18 +24,18 @@
     },
     {
       "epoch": 1.0,
-      "eval_logits/chosen": -2.9331436157226562,
-      "eval_logits/rejected": -3.0131616592407227,
-      "eval_logps/chosen": -168.64442443847656,
-      "eval_logps/rejected": -190.56906127929688,
+      "eval_logits/chosen": -3.0078587532043457,
+      "eval_logits/rejected": -3.042999744415283,
+      "eval_logps/chosen": -194.36697387695312,
+      "eval_logps/rejected": -179.82501220703125,
       "eval_loss": 0.6931471824645996,
       "eval_rewards/accuracies": 0.0,
       "eval_rewards/chosen": 0.0,
       "eval_rewards/margins": 0.0,
       "eval_rewards/rejected": 0.0,
-      "eval_runtime": 4.843,
-      "eval_samples_per_second": 2.065,
-      "eval_steps_per_second": 0.206,
+      "eval_runtime": 5.2287,
+      "eval_samples_per_second": 1.913,
+      "eval_steps_per_second": 0.383,
       "step": 1
     },
     {
@@ -43,9 +43,9 @@
       "step": 1,
       "total_flos": 0.0,
       "train_loss": 0.3465735912322998,
-      "train_runtime": 27.423,
-      "train_samples_per_second": 0.365,
-      "train_steps_per_second": 0.036
+      "train_runtime": 17.6734,
+      "train_samples_per_second": 0.566,
+      "train_steps_per_second": 0.057
     }
   ],
   "logging_steps": 10,