Run 4. Outer Step 90. Inner Step 6.

config.json

@@ -267,16 +267,13 @@
     "AutoConfig": "distributed/optimized-gpt2-500m--configuration_gpt_optimized.GPTOptimConfig",
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
-  "block_list": [
-    5682275,
-    5682306
-  ],
+  "block_list": [],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 4,
+  "inner_step": 6,
   "inner_steps": 0,
   "last_allreduce_block": 5676357,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:251138e2bfbc8968df4546d92b2d5e008f264b36aff020e38cd71d33f1e14005
+oid sha256:aec95e62e668c17a6e1fc42f59f1b3f82832f3799d33a211c97ff7e1aa9b2012
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67a2cee065b44d46b4a84461172db055998ca6fda4b53e07af0a0163ea4cefd5
+oid sha256:ff22822fd37fbf3081f14190b7f45d195c8f4640f9868ddd6a68982ca345bfe8
 size 4040701744