Run 4. Outer Step 54. Inner Step 91.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5580425,
-    5580428,
-    5580430,
-    5580432,
-    5580434,
-    5580435,
-    5580437,
-    5580440
+    5580443,
+    5580445,
+    5580447,
+    5580449,
+    5580450
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 90,
+  "inner_step": 91,
   "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 sha256:0cb5f25cb8c1c5edc154ab261a7be701e4a02542ef359541027b28ac04b6a48c
+oid sha256:4afa3c274ffff7bb693949b9ca3042404d0dacf3f9f51e1949278accb72bf8a2
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d9954f8629ea4ae078bf138d8bd2e2f8a8d3dd19ae0fc24b2c8cf99bc056a02
+oid sha256:56996c1c287d0d509e0b35524d1913a47985bf8b9e07c8689eedea5ade40e16b
 size 4040701744