Run 4. Outer Step 52. Inner Step 35.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5576114,
-    5576117,
-    5576120,
-    5576122,
-    5576123
+    5576126,
+    5576127,
+    5576131,
+    5576134,
+    5576136
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 34,
+  "inner_step": 35,
   "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:d1d7d3e89a55f64c4c91d3e9616d3093704d233ddac1ac0444da7e084a140aaa
+oid sha256:28570965b05a4d3105a59e0d89b0fcce538ea01710a4eace95c53c894f47696a
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0af33a213e6c6c73b999f91482627ea0d2de17095d968020bde752639ca853c
+oid sha256:532bfbc8a787ea8a4de79c9fa0951d870746866f6ea4d150dd3a1eaf7d06b5cb
 size 4040701744