Outer Step 0. Inner Step 172. Batch Size 180

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5156265,
-    5156270,
-    5156275,
-    5156279,
-    5156284,
-    5156289,
-    5156295,
-    5156300,
-    5156305,
-    5156311
+    5156346,
+    5156351,
+    5156355,
+    5156360,
+    5156365,
+    5156370,
+    5156373,
+    5156379,
+    5156384,
+    5156389
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 163,
+  "inner_step": 172,
   "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:d82d328253a1b2011e1a59a1b8c4cec35c09838f22e5f4fdba558970af23b559
+oid sha256:c8ea946f3cc96878847a6c877e8598c3d8e138922f54d898499d448f34f19fe5
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6250fa9a770f60359738f9e0d21cc1d36774a1e2e08a618bcde3011ed648f8d
+oid sha256:56e3ec9acce16e6ca5e9f4a693c6a7d3c7e4400e10b095cc22675408e2696e08
 size 4040701744