Run 4. Outer Step 61. Inner Step 65.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5642838,
-    5642842,
-    5642846,
-    5642850,
-    5642854
+    5642858,
+    5642863,
+    5642867,
+    5642871,
+    5642875
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 64,
+  "inner_step": 65,
   "inner_steps": 0,
   "last_allreduce_block": 5641040,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e07b944baf44cecb795c28ec2dd8a7b764b878c32d64f42e2b206a8a46e3745d
+oid sha256:c112ed5f10ae62de38575a1f4e63daf739c0ec49245eff36729ebafc19d91122
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4e74b1720d92b785a238effd427ac2a55456652b04ead2ac4994c034714e97b
+oid sha256:2d8e58fc4452cd0d0dacbfe7736b9256ed8754e7ec0a1a3e1d220b2d309e2d67
 size 4040701744