Run 4. Outer Step 42. Inner Step 28.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5560641,
-    5560646,
-    5560652,
-    5560657,
-    5560662
+    5560669,
+    5560675,
+    5560680,
+    5560685,
+    5560690
   ],
   "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": 5552497,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ada85a0cc1b4017fab24f0095e09a23c839849e241edc4f87fbbc596b1b940d
+oid sha256:85b84ea3fcb11d42dc3e00a6c0c9a60a29fc95fc75e9cb3decf9fba0ad3b214d
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a82d9ee374416cfe0057786c5544c4a5900bd7779943ec6f654ea421eea0fc6
+oid sha256:7bf8367b7a6da3f3a0d7d241cc2aa0bb2131234d53e02a8984d687362154c966
 size 4040701744