Run 4. Outer Step 43. Inner Step 80.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5563277,
-    5563282,
-    5563287,
-    5563292,
-    5563297
+    5563304,
+    5563308,
+    5563312,
+    5563317,
+    5563321
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 79,
+  "inner_step": 80,
   "inner_steps": 0,
   "last_allreduce_block": 5555115,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf5bd3f9993eef3eca2367b6b4be6d54bee3b43af382c5d348d342c890c9a69a
+oid sha256:8adcf59545cfc0c0942c18d828084ab51c708640e453374fcabf720d21aa6ffb
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f7d4a51dbfd47d62d30042910c53f796741db80eb25c1c09aa4b34434a7661e
+oid sha256:c4079c9bd8184e9bddb24b4caf3af0fe900da3a6a79320e9f8dd3fafdc54155d
 size 4040701744