Run 3. Outer Step 6. Inner Step 295.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5389886,
-    5389889,
-    5389893,
-    5389896,
-    5389900
+    5389928,
+    5389933,
+    5389937,
+    5389941,
+    5389944
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 293,
+  "inner_step": 295,
   "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 sha256:756aa2a036d784cadacd74156345ec18d0f6e6ad581481ad12a310f624fc423b
+oid sha256:ce9d70c294e249b4ccf2db41a22f38d50f8b34d87dd84dea64d5a27b80eb84d3
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e354aec353b6ba3cd3955828ce4ec56306c18d38408b8d00736246cd6e3c1f68
+oid sha256:3bd7251fd27c5d534e6fc4a2087d30a3fa0471ccca8a2b2dc3116a7e74facdf2
 size 4040701744