Run 4. Outer Step 53. Inner Step 83.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5588894,
-    5588898,
-    5588902,
-    5588905,
-    5588909,
-    5588913
+    5588918,
+    5588922,
+    5588926,
+    5588930,
+    5588934,
+    5588938
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 82,
+  "inner_step": 83,
   "inner_steps": 0,
   "last_allreduce_block": 5565072,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f41f7ec0608a8409de721db3c759deb39a6b3dcb5b7bf4577ec181b9bd1103ed
+oid sha256:e965fd16882d3579b488b22fe57dd5814f4b55516aefd38b3c24a161ce3d1263
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd37760509e3f4cf92844fd947573cf8b851680434affa3088f57ee6a298102b
+oid sha256:e7caa68e0a49404a29d18eb30de53aa67d0d214d6e425aff183a8b5eef75914e
 size 4040701744