Run 4. Outer Step 52. Inner Step 36.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5576141,
-    5576144,
-    5576146,
-    5576148,
-    5576151,
-    5576153,
-    5576155
+    5576157,
+    5576159,
+    5576163,
+    5576166,
+    5576169
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 35,
+  "inner_step": 36,
   "inner_steps": 0,
   "last_allreduce_block": 5574901,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97cb5e866236885a0394aa6ab952b3a0773349a0f0f1447d0d18bb5f9eff87d3
+oid sha256:944c0bc04e783cee578fd0c1c51e5fd1ff72c36ca457ee0bb509bc2d5547a0cf
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32d5ca6f48f86061ee0da4da30bd2ccd483007e751bfc273de62d3dc90dec63b
+oid sha256:11ab05ff8e73315009b897d0c749e179d3e6d3b1d4509bae8ee705d67a44307e
 size 4040701744