Run 4. Outer Step 58. Inner Step 38.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5603409,
-    5603413,
-    5603418,
-    5603422,
-    5603426
+    5603431,
+    5603438,
+    5603442,
+    5603447,
+    5603451
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 37,
+  "inner_step": 38,
   "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:ba0506fec07bac43a59941fa407f594c281e431d2cc623f607c643554d241dbd
+oid sha256:83add3ae5287ea6693766dd74ef6d2bfd0f5045be4645f2ef52e8960375ff43c
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02875bcd9f273289b8c836396710e66900f55063a6266a7c2d00bdf333bc7324
+oid sha256:9550f60f38944779052168b1594b6d31905621b557dcfb107d47b03ad43d11cd
 size 4040701744