Run 4. Outer Step 57. Inner Step 37.

config.json

@@ -268,24 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5602040,
-    5602043,
-    5602045,
-    5602046,
-    5602046,
-    5602050,
-    5602051,
-    5602052,
-    5602053,
-    5602054,
-    5602055
+    5602058,
+    5602060,
+    5602062,
+    5602063,
+    5602065
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 36,
+  "inner_step": 37,
   "inner_steps": 0,
   "last_allreduce_block": 5600871,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3f0fce284890ae581136eba76056bad5064aec1c661aadec680ff121db94e1e
+oid sha256:b7b2fc659b468e5f8810a1c0b962ab87dfb328bd9ef92b34255139896d9d62fd
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7dd6b2c86120ea1c0903de5f2005ab54bb6ccc2e2adadb2dc3143de1873c961
+oid sha256:9853812d91222dafd95ed9aa1f247a2aeb9604578f97535062dd252bd4296edb
 size 4040701744