Run 4. Outer Step 62. Inner Step 32.

config.json

@@ -268,19 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5611633,
-    5611637,
-    5611641,
-    5611645,
-    5611649,
-    5611654
+    5611658,
+    5611658,
+    5611658,
+    5611658,
+    5611658
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 31,
+  "inner_step": 32,
   "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 sha256:075e071a0df2f418411cd7e16c5fc3730ddf44f7fe3590094ec9aa12c9e5e039
+oid sha256:5b7a732e4a5fe782a54e3f0137d8b16a82501a6ce01ee27826738e4e32145fbe
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fffdcf998f24a8871cb46d524f15b7fe6636e88f2699127ccd1278338e7342ea
+oid sha256:69822f564968f46e286b3cc34927c995063871622cf61a7e31f2819c1b759947
 size 4040701744