Run 4. Outer Step 82. Inner Step 12.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5671636,
-    5671666
+    5671696,
+    5671726
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 10,
+  "inner_step": 12,
   "inner_steps": 0,
   "last_allreduce_block": 5664450,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8a6117af3a35747dd4daae48353d93fd73767330089f1f804a1e0dd405e9323
+oid sha256:77ba64c2eb2c5992799b3df202dd07dc6f2f79ca883a064b787917a49c1842c9
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36a4bf24d81808018a562fd1d1cffb3547d8309f273813f5e28e6937d0582892
+oid sha256:d4561c34f77ea19813d3870ff1f62423ef93ae27cc36b1f492a709501e98e754
 size 4040701744