Run 4. Outer Step 52. Inner Step 25.

config.json

@@ -268,19 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5575766,
-    5575768,
-    5575771,
-    5575773,
-    5575776,
-    5575779
+    5575782,
+    5575785,
+    5575788,
+    5575790,
+    5575792
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 24,
+  "inner_step": 25,
   "inner_steps": 0,
   "last_allreduce_block": 5574901,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95da13912f82d0746b4d006f4e8c9ef2ff73ddd4b201b9e432fa1ff11b1386fb
+oid sha256:18917ab34eb635e44f99bc40c1a9f9bdf197494146768b5ad649a0a7fbab23e4
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6797c4bb1a4e8c02ecaf351ac808449069679810877b44ee06745272fa541aa6
+oid sha256:7c3f43d487f4d31c30841f69041ed86d07b66c35b64fc57d4386595889321c24
 size 4040701744