Run 4. Outer Step 60. Inner Step 12.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5608074,
-    5608078,
-    5608083,
-    5608087,
-    5608092
+    5608099,
+    5608103,
+    5608107,
+    5608111,
+    5608115
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 11,
+  "inner_step": 12,
   "inner_steps": 0,
   "last_allreduce_block": 5607244,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:017630e82024237f8c8a44d3b6a9dae8b55dc7e91dd54b34b859f6fda7f01cb0
+oid sha256:77b94eebb6a2404ae796c84e0b00e4cd868587c05b6be0f6694602259e7dcd5a
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31bc63b3391bf3e2283a5ab5fd73c2c9fdb85696e5dba9fde1dc7a9e4fccd6a0
+oid sha256:52e3866259fecc08106eed3cc4711b59d79da912c17eddacdd6eda412ae8c0c4
 size 4040701744