Run 4. Outer Step 54. Inner Step 94.

config.json

@@ -268,19 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5580352,
-    5580355,
-    5580357,
-    5580359,
-    5580361,
-    5580365
+    5580368,
+    5580370,
+    5580373,
+    5580375,
+    5580378
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 93,
+  "inner_step": 94,
   "inner_steps": 0,
   "last_allreduce_block": 5577515,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6dabed41dc5e863d4bb4a27f5f5c022a5d3e2d0a1a06ca3aa386b55a5faeaf4
+oid sha256:6877be8647abda7abd4c67b2c362a9060725175397ba35ad5713a27f5ddb4642
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fbabe36aaabae867274b8aee2969e241e7a5ef30da3a69cc68c5ed9f1f010cf
+oid sha256:ff3e990edd5b6a55b8380513db19a8fdb5e5a2841923a2ecf2ee68e17cba242d
 size 4040701744