Run 4. Outer Step 58. Inner Step 22.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5603332,
-    5603340,
-    5603345,
-    5603352,
-    5603359
+    5603367,
+    5603374,
+    5603381,
+    5603387,
+    5603394
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 21,
+  "inner_step": 22,
   "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 sha256:548d4603b2091a033d7c9c8d0dd8d2c0d5a714fda274463ccea3d5c098b3a1ec
+oid sha256:843543ffce2c61c3f6a2645a759b04f45ae7f0def042da9dc5edf3d8ccab14f2
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5542a02c6b329b06464e8a7aa59d579a4c8e959a7be3abe2944882aca4367c15
+oid sha256:82f6076be5ed776d3d66c6cd12db2afb9b10a33d1e0e69157da51813b1ae1c52
 size 4040701744