Run 4. Outer Step 54. Inner Step 26.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5580329,
-    5580334,
-    5580339,
-    5580344,
-    5580349
+    5580354,
+    5580359,
+    5580367,
+    5580372,
+    5580377
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 25,
+  "inner_step": 26,
   "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 sha256:97e1ccb2eb0f9115b69bbfc1525686e0b884dbc748d16ad4e79d6410a5cc6747
+oid sha256:299cd412aaafa5cdaf72af486a61ed50ef1e99a5ce62b8f6433f5a494421d943
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cefb34d920a3a643a0943d5bc7422a59654e1cfc0bb84d25d9ae25d3d5bfbcc
+oid sha256:aa9c5d4f57822d5b3d7cc88ed0be707099ce9727f9ecc01757d09606e800cce8
 size 4040701744