Run 4. Outer Step 54. Inner Step 85.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5580105,
-    5580107,
-    5580110,
-    5580113,
-    5580115,
-    5580116,
-    5580119
+    5580121,
+    5580124,
+    5580126,
+    5580129,
+    5580130
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 84,
+  "inner_step": 85,
   "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 sha256:2e47b710dea010083107dbc39a969e925385df1783d55d9a655a071265936298
+oid sha256:b5719722f73951ba3f7f5c270e24b8d913089c1614bc741f2d4af1753c54c487
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a511c18b631ea916a8cba21d97ffef578684fd0ca25784d0498477c1f2c713e
+oid sha256:62591484c854271e0d57fd48caace736c954141ec3897199525a482455dbe8ae
 size 4040701744