Run 4. Outer Step 100. Inner Step 18.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5695953,
-    5695971
+    5695988,
+    5696003
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 17,
+  "inner_step": 18,
   "inner_steps": 0,
   "last_allreduce_block": 5692898,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80b71a4fda5a4a3a0831d3d7b0599faee5a909065f9e4d954b80080513a97f7a
+oid sha256:13d4b4a3ff58925053522a6e3eecd4849ba1ad3eef1f08f23f065edcfb7c9f55
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3509485349bcf9f27a2bde25947fde3b90acb8af4eee18e71654fa83c4dfe6e6
+oid sha256:faba2d35dbb62f312fcd763d387ca79b0211180e09f4b8b7f95873bfa6fdd620
 size 4040701744