Run 4. Outer Step 62. Inner Step 25.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5611480,
-    5611483,
-    5611485,
-    5611488,
-    5611492,
-    5611494,
-    5611496
+    5611498,
+    5611500,
+    5611501,
+    5611505,
+    5611507
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 24,
+  "inner_step": 25,
   "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:c14012144eb1fe89181b7416c002955110b0741ac4232a7c98398f9f36720fae
+oid sha256:1ceed4142ab45cfb954558d5255673c9d025b4bad77f756b03721919385ea96f
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc23aa8dc1e84993ec1fc4c02c6d59bb846d0c3380015096b0622119e880bdb2
+oid sha256:c32d2eb19f8f5c4a549363f15526a19b49ea17f45cfc12240dc8b93a0bec8468
 size 4040701744