Run 4. Outer Step 42. Inner Step 38.

config.json

@@ -268,18 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5560817,
-    5560821,
-    5560826,
-    5560830,
-    5560834
+    5560839,
+    5560843,
+    5560847,
+    5560851,
+    5560855,
+    5560860
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 37,
+  "inner_step": 38,
   "inner_steps": 0,
   "last_allreduce_block": 5559633,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08b078c396c604cedf704594b693da7cc25687c8b9e03fda17c6f1b7d4e2b62e
+oid sha256:3231ceed0e47ea2ccab52754c9ef06f49058935b2455de28b0893a2e092af16e
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6537a39f817724a5d1db59236b1286097597a02b947e9a6c661fd353aca78290
+oid sha256:478866c267706f69a7b30fc1f73590536bb5a596b4bfa0bf1ee2bee69ebe7b06
 size 4040701744