Run 4. Outer Step 60. Inner Step 2.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5607409,
-    5607411,
-    5607414,
-    5607417,
-    5607419,
-    5607422,
-    5607423
+    5607426,
+    5607428,
+    5607431,
+    5607433,
+    5607436
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 1,
+  "inner_step": 2,
   "inner_steps": 0,
   "last_allreduce_block": 5607244,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b107bd4ce0ae800d66ae6d3f60af78d1a1a21fd1e648bdd5f5e82f132f80776
+oid sha256:6b1790b16b2895b22057fa090de39d1cb654a6c17bd4dadb33c5057647047cfa
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f46f3db386fd253af2534abddfd00df2ed425aaa111da4c7c1aea1ce35d47a5
+oid sha256:ca02d13e7cbb972c4f10ad939794d58f7ad60b92e72c47ab742cffb135105c07
 size 4040701744