Run 4. Outer Step 53. Inner Step 35.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5577356,
-    5577358,
-    5577360,
-    5577363,
-    5577364,
-    5577366,
-    5577369,
-    5577371
+    5577373,
+    5577375,
+    5577377,
+    5577379,
+    5577381
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 34,
+  "inner_step": 35,
   "inner_steps": 0,
   "last_allreduce_block": 5576204,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b944046ca3545c301bc96a9534bf5d38ca2625b153794782f555b11a7f687951
+oid sha256:5ab6820aa510b6bbf3dd5b3b4f2d019c8ac88588e899f5208736cf937062c878
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91a0c7376306fae109133c6c6db0d2a1e08d103fb69bb66cebd32ae4855bda56
+oid sha256:80f7037e560cebef85194e0490ca6fc3f223dec6093518f3c9aa8c8f9f3c7a03
 size 4040701744