Run 4. Outer Step 36. Inner Step 26.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5550336,
-    5550340,
-    5550344,
-    5550348,
-    5550352
+    5550357,
+    5550361,
+    5550364,
+    5550369,
+    5550373
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 25,
+  "inner_step": 26,
   "inner_steps": 0,
   "last_allreduce_block": 5549491,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bef765131fa13b09d1325a5c2ce66a2927a53471bb6fd35b0b06f3ee9db97d5a
+oid sha256:eee1e63a56b1fe78618636777e815fabaf35c3b3f4e7119e749929c651685827
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50e06999f6c9ff0a5b71eb26739a6d434d7874f0269266c2f9434a0f4ada0bc5
+oid sha256:2c5843229370377b0058932ba76200eb7a4615b419606ccb180ab9e901190aa9
 size 4040701744