Run 4. Outer Step 75. Inner Step 28.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5663421,
-    5663433,
-    5663437,
-    5663441,
-    5663445
+    5663450,
+    5663463,
+    5663468,
+    5663472,
+    5663476
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 27,
+  "inner_step": 28,
   "inner_steps": 0,
   "last_allreduce_block": 5662361,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ff7bd5a61a5c1204ce24ca45e0473d8252012ecb921a769069843974291300d
+oid sha256:67a9c45350042dc9591ca941168c797e8e235c3f23358fdd4861c87943daf821
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:333fd1c40cded4ca33ae0cf215be36b66cf67bb27be24f2f3fec6379bf3a993e
+oid sha256:f4801225343b8241b832cdb5a5c9478ce27215e16345e17ed551e0f6ce0cde85
 size 4040701744