Run 4. Outer Step 91. Inner Step 7.

config.json

@@ -267,13 +267,16 @@
     "AutoConfig": "distributed/optimized-gpt2-500m--configuration_gpt_optimized.GPTOptimConfig",
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
-  "block_list": [],
+  "block_list": [
+    5683671,
+    5683701
+  ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 5,
+  "inner_step": 7,
   "inner_steps": 0,
   "last_allreduce_block": 5676357,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae5d79dfc99eec9b216fa9d9becdc0a18b543211c5cbb96fcafd6a0f6ddb2337
+oid sha256:ab143d2969dc693d2618304464230c902e28fc462149a859d4361a642bc5bfec
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec79f83ce0f14928f9b865e01a5b12c85525f16f9ac8c6e0add328cde5fb63e6
+oid sha256:293c6239b8bc141df3aa92086d82d9cbd7f251e4da34896d1ed5e111170adb54
 size 4040701744