Run 4. Outer Step 50. Inner Step 8.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5571819,
-    5571824,
-    5571828,
-    5571833,
-    5571837
+    5571842,
+    5571846,
+    5571851,
+    5571856,
+    5571861
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 7,
+  "inner_step": 8,
   "inner_steps": 0,
   "last_allreduce_block": 5568918,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab686fffb4ffba4f8d7b64d696e27fb780e34ee350214d15512187d02bf059f8
+oid sha256:b23a7a40e24ad08d151e817e238783d3919f9d7bef30d4bfd123f6ce0fa49d4f
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46fe07c61264eb026542c8ceec03f569f5d4d7453980ed32b34b1d50773dac1e
+oid sha256:ebe7dfe9fc17868ad62192c12bed717f961f729c31a78663e43aa1b498cf4455
 size 4040701744