Run 4. Outer Step 60. Inner Step 4.

config.json

@@ -268,19 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5607401,
-    5607405,
-    5607409,
-    5607413,
-    5607417,
-    5607421
+    5607425,
+    5607430,
+    5607434,
+    5607437,
+    5607441
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 3,
+  "inner_step": 4,
   "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 sha256:3a42a54445e92431950f4e2c9c8bb169cc5006afb57e4aee0f6438ebf167cdad
+oid sha256:9b806924e197427fded28569c288b5ca794acdeb2ea0b4fbe541e1eed04fe45b
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d722dccb04da6c2434f73258ce7026c64075ab7b9e6a87d7ab6992749a59427
+oid sha256:455485986f442d5fac403cd2e34b14361d3006293c12643634c3313ec86a2ef9
 size 4040701744