Run 4. Outer Step 50. Inner Step 2.

config.json

@@ -268,18 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5622673,
-    5622676,
-    5622680,
-    5622683,
-    5622687
+    5622860,
+    5622887
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 0,
+  "inner_step": 2,
   "inner_steps": 0,
   "last_allreduce_block": 5571611,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a2a0cbd13d1df2fb67e6ed8feaa25aeaee68b7ee9840f2c8914b16ce6f3e484
-size 8081782026
+oid sha256:9362604d879b02f09ecbf952cc1fe6edc49408b68cac04a4467ed5745fa91629
+size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51896991661e02507298ba54890fd1fc262804a915cbfa14522803049877c769
+oid sha256:eb16b5c9655456f2b8cd98d2b2378713103942c63eea958b513f57342d067db0
 size 4040701744