Outer Step 0. Inner Step 164. Batch Size 72

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5156237,
-    5156241,
-    5156246,
-    5156251,
-    5156255,
-    5156260,
-    5156265,
-    5156270,
-    5156275,
-    5156280
+    5156319,
+    5156323,
+    5156329,
+    5156334,
+    5156339,
+    5156345,
+    5156350,
+    5156355,
+    5156359,
+    5156364
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 154,
+  "inner_step": 164,
   "inner_steps": 0,
   "last_allreduce_block": 4016775,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcabda0d27def7f9d2226cf176e6ec27789e57dd9ec306d8e27c1a64575f7234
+oid sha256:b5d89f2d69f7ed00bb0efe9220134e1719ada5f2104e3f25397387203f68e17b
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8b2c02949ade7efdc8d6c5fd7f5ba677ea07dcde2f0dffce78fa58fd9eec9c9
+oid sha256:51154cd10b76916a58f070757fb1491668a0e727c8c2edbdfdd98844c40fcbf4
 size 4040701744