Run 4. Outer Step 58. Inner Step 24.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5586761,
-    5586766,
-    5586770,
-    5586775,
-    5586780
+    5586784,
+    5586788,
+    5586793,
+    5586797,
+    5586802
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 23,
+  "inner_step": 24,
   "inner_steps": 0,
   "last_allreduce_block": 5583387,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d5847d649968a79b68af730c527e5d0df59a98fe356374d81bbcf6206646d1e
+oid sha256:7c5e61abced5e81171e8fd1581cc3afb1a90a8bda3dbf8b936e9e1e27901a1cb
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb766f4fab1ec84fe7afa83f04a2fcee96edf0e0bf69f0db779e59956fbee01c
+oid sha256:b4384942c9ec33d3342d1a0451296990129ef0a14e759aec5170e5ef2d7bfedc
 size 4040701744