Run 4. Outer Step 38. Inner Step 40.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5553740,
-    5553742,
-    5553744,
-    5553746,
-    5553748,
-    5553751,
-    5553753,
-    5553756
+    5553758,
+    5553761,
+    5553763,
+    5553766,
+    5553768
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 39,
+  "inner_step": 40,
   "inner_steps": 0,
   "last_allreduce_block": 5552497,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be8e6b74d48fcf2795ef74de8be7a031cdcfe9b308c5846ef464f6a0a05dc3a6
+oid sha256:e936183e363769be3745b9653bdf3be9791664b8e5a049497d3abfb55245717a
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00046af9b4d6b3ed2d094d1a5a5f407fb6df76e38e450dcbc6f0b47f50f2f9ee
+oid sha256:71ae89e3dbef1920e9171bcd2fae8ad83666cc472dcf53c426dfeb61e4de475d
 size 4040701744