Run 4. Outer Step 64. Inner Step 260.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5617674,
-    5617678,
-    5617683,
-    5617686,
-    5617692
+    5617696,
+    5617700,
+    5617705,
+    5617708,
+    5617712
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 259,
+  "inner_step": 260,
   "inner_steps": 0,
   "last_allreduce_block": 5613899,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e34f82855c911f8d0542d4c44ea5f7d4fab86c2812af6e90dc7cc7322b326b5
+oid sha256:1995f12c20e1e830b887accfefdc6eac295c4f52c9f7308e1f862e537c52245e
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc1b1d19e39249b4e4b3db59c8d11e4f24cabb73229c580990f9d3e35c4717d2
+oid sha256:bcc94f50794fce56590def58b3e7614e459ebc3fa843b4cbf14296bd2ab24fa4
 size 4040701744