Outer Step 2. Inner Step 6740. Batch Size 392

config.json

@@ -268,18 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5129056,
-    5129069,
-    5129080,
-    5129092,
-    5129098
+    5129179,
+    5129184,
+    5129188,
+    5129193,
+    5129212,
+    5129222,
+    5129230,
+    5129242,
+    5129252,
+    5129268
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 6735,
+  "inner_step": 6740,
   "inner_steps": 0,
   "last_allreduce_block": 5063053,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53e40decf0fd7c9d7b812127868ce71d0aa2dd1f2f2062205766db80f5ba146b
+size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e60512e4abeff6962033e8beb0b03270d55ea046111a1820a3b98ff3939862d0
+oid sha256:fa0f72b38f4f100e19fc97a50e8cf51318dfd47a04fa4d0b2a60e950b356c430
 size 4040701744