Run 4. Outer Step 33. Inner Step 18.

config.json

@@ -268,19 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5544535,
-    5544537,
-    5544541,
-    5544544,
-    5544546,
-    5544549
+    5544552,
+    5544555,
+    5544558,
+    5544561,
+    5544564
   ],
   "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": 5543976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:342bdddf2fc674fe0097188f484165172da478e329201ef08aad2317377f4a2c
+oid sha256:53e7bae6df7f64b9a87d1e51aefdc8c51b8c036a045c763d82c1d2a0719c8184
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7a8bf081018f21de8fa754483dd0205ab092339f06f1410be0e50601cb259ac
+oid sha256:3cc9c2b4b3a862ad27f105f11196d03f38847ff1c35c3fa267031722580e39db
 size 4040701744