Run 4. Outer Step 36. Inner Step 40.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5550717,
-    5550720,
-    5550724,
-    5550729,
-    5550732
+    5550737,
+    5550741,
+    5550745,
+    5550749,
+    5550753
   ],
   "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": 5549491,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c48a5be632f7007a5f92c0250059b25b878fed6122d52daebff712eaa70faa0d
+oid sha256:e8f7067fad4373e36e9242e12fa429cdf1dcb2000c6471df2c9bacb48e826e35
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac4ef715f575fe9cb52f4eda681fc8b147ac70313844cf2dc7cfa77188f16a0a
+oid sha256:aa10ec008e56480ef3cd3ccb6593576546fdb8be97d02784c3dc5e3c19f103b1
 size 4040701744