Run 4. Outer Step 53. Inner Step 82.

config.json

@@ -268,18 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5588989,
-    5588994,
-    5588997,
-    5589002,
-    5589006
+    5589011,
+    5589015,
+    5589019,
+    5589023,
+    5589027,
+    5589031
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 81,
+  "inner_step": 82,
   "inner_steps": 0,
   "last_allreduce_block": 5576204,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d3a13df930e3ee7d0e94a5ee4a330071deaff5b645b43b28fd545f281c8c0bf
+oid sha256:71c4499c57595e3f80d3a920adcc3eb592713c918cdd4ffca04f265f8aea53d6
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a02ab79bdb04c4947ac5d39551a44a32c87f8b5d42483deb6a2fa3018adfd32d
+oid sha256:efe7ac00c3223932913bba00a24893756a032cc2b2bd870a1dff59737ce00278
 size 4040701744