Run 4. Outer Step 35. Inner Step 40.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5549418,
-    5549422,
-    5549426,
-    5549430,
-    5549434
+    5549439,
+    5549443,
+    5549447,
+    5549451,
+    5549455
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 39,
+  "inner_step": 40,
   "inner_steps": 0,
   "last_allreduce_block": 5548219,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f20fbb4f6241128d100b5ce33a1c7fc0dadd5f546dcce7fd9c4c5d5c75c5037d
+oid sha256:cd115bd9c710c5c0f3acc045f35381c73cdd0bb658c46106bf96ef6a31de9f8d
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:709ff0cfb8debe55cef12d608c14c5e91a68a7f528ada01886eb1bdb8f02c61e
+oid sha256:6049d23a50fd8c5262512abd07d4dcef5827db901f0967d04758370390c8dacb
 size 4040701744