Run 4. Outer Step 58. Inner Step 48.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5603707,
-    5603711,
-    5603716,
-    5603720,
-    5603724
+    5603728,
+    5603732,
+    5603737,
+    5603741,
+    5603745
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 47,
+  "inner_step": 48,
   "inner_steps": 0,
   "last_allreduce_block": 5576204,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4daece8b574e0042b580cfe0686438b46d14b69652d91bcda4c36290a82e12da
+oid sha256:716693cf395234d76db83bf0854c22b640a0176e8efa2b6abb2302fa3885b236
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a7e35a9ee0eef2ab44ba3d7ea30c07dbf390d5f0a05f581695d28ea105b3e63
+oid sha256:5b117838960988c7831c759b5fed3148e7224561687d60e256c5b074e0881333
 size 4040701744