Run 4. Outer Step 42. Inner Step 40.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5560886,
-    5560891,
-    5560895,
-    5560899,
-    5560903
+    5560908,
+    5560912,
+    5560916,
+    5560920,
+    5560925
   ],
   "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": 5559633,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8312b444e82c2dea7e56f5746751d731247ed4a5c9780d9c5437e1b40f459e6
+oid sha256:bf4ef76f781a0f2290a458b70a1157e3c42b424ef479583eac39c0de793aa0ac
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0af87713d2d24a464d099793e6a05ff203f146ff21a3363b653cfdefa597cf44
+oid sha256:60b29916776abae6f8213960c4c7c2a313d4112b6f87ac5d5019b38fb69826bb
 size 4040701744