Outer Step 2. Inner Step 127. Batch Size 200

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5074295,
-    5074299,
-    5074304,
-    5074308,
-    5074312
+    5074325,
+    5074330,
+    5074334,
+    5074338,
+    5074342
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 123,
+  "inner_step": 127,
   "inner_steps": 0,
   "last_allreduce_block": 5072405,
   "layer_norm_epsilon": 1e-05,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc5452c17a4d0b033f5bda7f973da884f04c8c26fcbb927b54f5f552df84659f
+oid sha256:0b8bc9e09e99a3f26b0af8043652486279a70fe5ef1c461d9f23928e40279987
 size 4040701744