Run 4. Outer Step 25. Inner Step 42.

config.json

@@ -268,18 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5534605,
-    5534608,
-    5534610,
-    5534612,
-    5534614
+    5534618,
+    5534620,
+    5534623,
+    5534625,
+    5534627,
+    5534630,
+    5534633,
+    5534634,
+    5534635,
+    5534637
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 41,
+  "inner_step": 42,
   "inner_steps": 0,
   "last_allreduce_block": 5533305,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:013a5acd54f840296466d79e97580de857f1f599eea0e2ccbf1141a1738c4ebf
+oid sha256:271baff723ec247f8e2a355f77e80f6193d4e4ea3ea40b7def7db65c13a0c342
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05c96a82ac76ea573a88689abc3786beedd3489bc172d0eed594c3c796e561f9
+oid sha256:f18fec2d518577e05ae7958a22a500eea59b3f1291fdff1d90a859527b76ede6
 size 4040701744