Run 4. Outer Step 54. Inner Step 108.

config.json

@@ -268,19 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5580870,
-    5580874,
-    5580879,
-    5580883,
-    5580887,
-    5580891
+    5580896,
+    5580901,
+    5580905,
+    5580909,
+    5580914
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 107,
+  "inner_step": 108,
   "inner_steps": 0,
   "last_allreduce_block": 5577515,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:459e797f2f29e7691daacc0648f413a9409d4f36534eb14a78f02172d0fa564f
+oid sha256:bade7c6daa00e4e79fb83dd1a857b7fb70f9af6ad14601d39a77d6ab4d7c35fb
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ce273c3af9cf068b94a2ea3e76b53c19719b8985aa79fbdd686329ee3369e80
+oid sha256:c234ac69c248d0a2c81b173fd363bb3047302a08d127d685f02f5f02ccac35bb
 size 4040701744