Run 3. Outer Step 11. Inner Step 212.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5443459,
-    5443465,
-    5443469,
-    5443478,
-    5443481
+    5443509,
+    5443515,
+    5443519,
+    5443523,
+    5443527
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 210,
+  "inner_step": 212,
   "inner_steps": 0,
   "last_allreduce_block": 5422706,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ba00756b2ed24ebea0bbdbdb2a46619f0756f2aaf644dce22aeb923de54737b
+oid sha256:27321ec636a506a4498e8af14f0596b7f7343d81b1f3acb74bc95981bed458c1
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73c98c4f5d9f1931d8de7c73609c815f3331487c033f454335f8c340319bc581
+oid sha256:5f932e4d9b59c70477f859f522a779d0f05cc5dc8b3c2c8c46d9bd4d163e1d2e
 size 4040701744