Run 3. Outer Step 6. Inner Step 238.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5388939,
-    5388943,
-    5388947,
-    5388950,
-    5388953
+    5388982,
+    5388985,
+    5388989,
+    5388992,
+    5388996
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 235,
+  "inner_step": 238,
   "inner_steps": 0,
   "last_allreduce_block": 5378990,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3608a4126a589949e1a574a54eb1245ce88d7efdd419f1add8d480a00adb4700
+oid sha256:a7279484ae61a161822aeabc4075802f1f2f9d65075e1d22721e8aba2597b89e
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9499921d8568b4920dd77d2d5813f4d3b23102a737755b9698302980d19e3681
+oid sha256:444b66ac697f08d66a237d9124bcdda7bd2b9b3cf956693029f8206570603e11
 size 4040701744