Run 4. Outer Step 58. Inner Step 7.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5604714,
-    5604723,
-    5604727,
-    5604732,
-    5604736
+    5604741,
+    5604745,
+    5604750,
+    5604754,
+    5604759
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 6,
+  "inner_step": 7,
   "inner_steps": 0,
   "last_allreduce_block": 5602341,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92bc738562ccbdcec9721117fca948630a29d158f39378f70370301d946f45e9
+oid sha256:b72e2b2e1acf34106fb2835bc8930925843cc6d7a52385ecf0cd65fb097d0699
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4cd5f312b61fe48aeff9ffea1fcc565b430b9633cfb0f8fd6567fff8cb07372
+oid sha256:e99303476804be7382bd847f95af48f5392ff75b54e30c1443421067e0cc7399
 size 4040701744