Outer Step 2. Inner Step 635. Batch Size 428

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5127318,
-    5127327,
-    5127334,
-    5127344,
-    5127351,
-    5127358
+    5127370,
+    5127375,
+    5127382,
+    5127405,
+    5127417,
+    5127426
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 632,
+  "inner_step": 636,
   "inner_steps": 0,
   "last_allreduce_block": 4016775,
   "layer_norm_epsilon": 1e-05,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2aa89b2b237d39d32868c2bd14ade83c2db94ed0fb4397551f1cfa1f39c2765d
+oid sha256:9e40b24bd7393a0e5338f8050dd1b116e3d9adecfa9a4be201dff189001a1b63
 size 4040701744