Run 4. Outer Step 53. Inner Step 36.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5631371,
-    5631399
+    5631427,
+    5631453
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 33,
+  "inner_step": 36,
   "inner_steps": 0,
   "last_allreduce_block": 5630301,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b172d6671f7da300f5ec2c772413067c5d7cd56712f62f7e84016a8066ce67a8
+oid sha256:765fb1da4f2656058dd27940ba48e36748ae7169ff71b07ccca6e1b0ee4305f5
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e24df6d11a6d215f10432ff58866274e1ed8a4612dbc95c7f8d7e7ad3f6fe264
+oid sha256:084247892dc4cd194b4b56b0792395540f8eefefee52538f23bfc737ff69fe65
 size 4040701744