Run 4. Outer Step 52. Inner Step 42.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5576250,
-    5576252,
-    5576254,
-    5576256,
-    5576258,
-    5576261,
-    5576263,
-    5576265
+    5576267,
+    5576269,
+    5576271,
+    5576273,
+    5576274
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 41,
+  "inner_step": 42,
   "inner_steps": 0,
   "last_allreduce_block": 5574901,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c03278d7d519ab33e93cb057ace2711f193a813ef4bcd1aede8fc0e95d2d79a8
+oid sha256:f8ce79294cdf30197191b935478502da39e020dc8fee954556bf5d1fb7e9e87e
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a67215f512c218061bf6be3f80b07139172c20b5b29acef33187212976ea3b9f
+oid sha256:53dd73532637557cbcd28d57c8c4d5b075de29fd14a389b29047bdde407ed73d
 size 4040701744