Run 4. Outer Step 3. Inner Step 136.

config.json

@@ -268,23 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5484822,
-    5484825,
-    5484827,
-    5484828,
-    5484829,
-    5484830,
-    5484832,
-    5484834,
-    5484836,
-    5484838
+    5484842,
+    5484845,
+    5484847,
+    5484849,
+    5484850
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 135,
+  "inner_step": 136,
   "inner_steps": 0,
   "last_allreduce_block": 5480541,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3738a13ca6dc283f55dda9c9901214b3d55df758e12ae776794c0e3d119c9751
+oid sha256:7c91689d78277ddfef303043e7ccd6eecb697543178d7dda2f45a46d8e6cb48c
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6bd385d260f63dc7472e7c7dd46dcbff28d805f504d75b591b66bc0f8a1ef78
+oid sha256:32e6aaf6d38c7e407ba2f48cb68570c6f9c0b487af9db4bc96fc779beac2a337
 size 4040701744