Run 4. Outer Step 35. Inner Step 43.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5549502,
-    5549506,
-    5549510,
-    5549514,
-    5549518
+    5549522,
+    5549526,
+    5549530,
+    5549534,
+    5549538
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 42,
+  "inner_step": 43,
   "inner_steps": 0,
   "last_allreduce_block": 5548219,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89f887df43e62c61be5159b7fdd57d99c396bbb8c54f88f11168165949cdd745
+oid sha256:e314773271aa9d2b956cc2e54f84890acf3c933662d72ac3053a035221264630
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f99373af6718a698572c860f5c37d62bdf1429049998f5dff907a8f8d485b234
+oid sha256:57c6dfb19fe2667f94a2a7a85faa35230757260581ba2130165c2490998b80d5
 size 4040701744