Outer Step 1. Inner Step 986. Batch Size 264

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5071254,
-    5071260,
-    5071265,
-    5071270,
-    5071274
+    5071292,
+    5071297,
+    5071306,
+    5071314,
+    5071321
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 981,
+  "inner_step": 986,
   "inner_steps": 0,
   "last_allreduce_block": 5063053,
   "layer_norm_epsilon": 1e-05,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70ee832bd0df62bd80f8975cd562c3ec65334ec8c4bd55d84cbd835eb71428cd
+oid sha256:a01cedfcf90170e3f7cb8a0efbe905d5939e0749f322d4602d71e4d77e5b41ec
 size 4040701744