Outer Step 2. Inner Step 7456. Batch Size 380

config.json

@@ -268,18 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5129004,
-    5129010,
-    5129026,
-    5129034,
-    5129044
+    5129134,
+    5129140,
+    5129146,
+    5129153,
+    5129163,
+    5129172,
+    5129180,
+    5129187,
+    5129191,
+    5129203
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 7451,
+  "inner_step": 7456,
   "inner_steps": 0,
   "last_allreduce_block": 5072405,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c9ea82423e9b56c53425c3267cf57392f8e62a8010d6e6c14506e2086696304
+size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b70e64075d7587675d9fffdff895147dc75a340288f1f16ed682d30d89ca2f69
+oid sha256:9c394cd13a08c94649e6f8a112f3fd1326a02b3a375225d37a2150a3c71e0a6c
 size 4040701744