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

@@ -1,21 +1,8 @@
 {
-    "epoch": 3.0,
-    "eval_logits/chosen": -2.0658671855926514,
-    "eval_logits/rejected": -1.9411793947219849,
-    "eval_logps/chosen": -266.13037109375,
-    "eval_logps/rejected": -228.2694091796875,
-    "eval_loss": 0.5265706777572632,
-    "eval_rewards/accuracies": 0.7459999918937683,
-    "eval_rewards/chosen": -0.1469534933567047,
-    "eval_rewards/margins": 0.7515553832054138,
-    "eval_rewards/rejected": -0.8985088467597961,
-    "eval_runtime": 453.4186,
-    "eval_samples": 2000,
-    "eval_samples_per_second": 4.411,
-    "eval_steps_per_second": 0.276,
-    "train_loss": 0.5642705829018732,
-    "train_runtime": 71197.0849,
+    "epoch": 1.0,
+    "train_loss": 0.3465735912322998,
+    "train_runtime": 29.428,
     "train_samples": 61966,
-    "train_samples_per_second": 2.611,
-    "train_steps_per_second": 0.041
+    "train_samples_per_second": 0.34,
+    "train_steps_per_second": 0.034
 }

runs/Dec10_15-50-15_uclaml03.cs.ucla.edu/events.out.tfevents.1702252337.uclaml03.cs.ucla.edu.2934315.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a95af9f0d4bdb525ac33ddcad00eac1c6938a94f290dd586076e256e29c9d409
+size 6089

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 3.0,
-    "train_loss": 0.5642705829018732,
-    "train_runtime": 71197.0849,
+    "epoch": 1.0,
+    "train_loss": 0.3465735912322998,
+    "train_runtime": 29.428,
     "train_samples": 61966,
-    "train_samples_per_second": 2.611,
-    "train_steps_per_second": 0.041
+    "train_samples_per_second": 0.34,
+    "train_steps_per_second": 0.034
 }