Training in progress, step 5

all_results.json

@@ -9,8 +9,8 @@
     "test_samples_per_second": 3.203,
     "test_steps_per_second": 0.4,
     "total_flos": 1340245973568.0,
-    "train_loss": 0.6810620188713074,
-    "train_runtime": 179.9526,
-    "train_samples_per_second": 0.445,
-    "train_steps_per_second": 0.056
+    "train_loss": 0.6667191207408905,
+    "train_runtime": 222.163,
+    "train_samples_per_second": 0.36,
+    "train_steps_per_second": 0.045
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f74d19caba9a0a7b9f7a6092c36a1ae7d34cfb3f7cf8e20c8d93f7ef57156385
+oid sha256:caba56241b771b05c2a925fcc682f6b8a912e67c4ecb792075873c9f5c74e28a
 size 737719272

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
     "total_flos": 1340245973568.0,
-    "train_loss": 0.6810620188713074,
-    "train_runtime": 179.9526,
-    "train_samples_per_second": 0.445,
-    "train_steps_per_second": 0.056
+    "train_loss": 0.6667191207408905,
+    "train_runtime": 222.163,
+    "train_samples_per_second": 0.36,
+    "train_steps_per_second": 0.045
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c9ae849db92db5b93a0643da15219c255ea6b6a158d9c2cb8e5181f2af8e476
+oid sha256:cb253c1f6c9ebfd65a617e8827c2a222d5972a85fffe8033e6dd0d1e5c802c01
 size 5240