Run 4. Outer Step 66. Inner Step 98.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5621867,
-    5621871,
-    5621875,
-    5621879,
-    5621883
+    5621887,
+    5621891,
+    5621895,
+    5621898,
+    5621903
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 97,
+  "inner_step": 98,
   "inner_steps": 0,
   "last_allreduce_block": 5611658,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e94e75b307ff4ecc849328273335ed286d2e9a9b7213e73affe8b313b21d2a23
+oid sha256:fdcb938feb9d57b203905e291d1d67c7b5190d19c1ea53eee0b150cf40a3ebf5
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3ff23c62fa0ca231946d555dbd3a5d967ba7b0faebc17d96ccfd265442d6fff
+oid sha256:da10ebbab22607c7c3caa31f30a968ce35f4f176fd7ca3fe612a6cf4accb8ac6
 size 4040701744