Run 4. Outer Step 62. Inner Step 36.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5611627,
-    5611631,
-    5611634,
-    5611638,
-    5611641,
-    5611645
+    5611650,
+    5611653,
+    5611657,
+    5611658,
+    5611658,
+    5611658
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 35,
+  "inner_step": 36,
   "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 sha256:1df482b2edfd71ba760ddf9788de92b84576b2a71687737595a84074cbfd1076
+oid sha256:d6ffba2190496a5866aba47e52fedbd7f232b3fc5f7eefc3e9395f9311dc1993
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d567c7db6ce957011c02a9dbbb7c02aeff863fd13a9ae6231127e0c6336755a5
+oid sha256:082d3a8f4ab1cd8718225d78e14ecacd57f2047ced905f43e08323f7bf411417
 size 4040701744