Run 4. Outer Step 53. Inner Step 31.

config.json

@@ -268,19 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5577240,
-    5577244,
-    5577247,
-    5577250,
-    5577252,
-    5577255
+    5577258,
+    5577261,
+    5577264,
+    5577264,
+    5577266
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 30,
+  "inner_step": 31,
   "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 sha256:831b40f6361f2f39377ffbb85b2a348a3da6219ecb5ca3bd02aff3ccd2ec1398
+oid sha256:fcf1b0cfaea3f7ad6bbb5deaabe98e98af7bfe1fc72ca06f25e5aa17790e9586
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2abe0ed423f08f0cade723841233316e2825af77dd8ae0bcb9835a054e4523b
+oid sha256:6b1fa95e2166a34fbf48d4ab27e6a754dc43be5225737464411dc0e05adce7e3
 size 4040701744