Run 4. Outer Step 62. Inner Step 35.

config.json

@@ -268,9 +268,9 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5611647,
-    5611651,
-    5611654,
+    5611658,
+    5611658,
+    5611658,
     5611658,
     5611658,
     5611658
@@ -280,7 +280,7 @@
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 34,
+  "inner_step": 35,
   "inner_steps": 0,
   "last_allreduce_block": 5610584,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2373d37cb9e45b0fddb39a29adef7b5935a8055e56da76a62e850cc2d6f4395f
+oid sha256:f16f177a66ac81db8dd8423770916c3a2fcc95b23b42930fe684a88af66122b3
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:537ff3c84388abd006313bab122d3dd76166ea60ae67fcfce41fa0250add69dd
+oid sha256:17f627a104811bb2e3139e185ec236589372e1fdb6abf93f5cfa619c44709857
 size 4040701744