Run 4. Outer Step 58. Inner Step 16.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5586520,
-    5586524,
-    5586528,
-    5586532,
-    5586536
+    5586541,
+    5586545,
+    5586549,
+    5586553,
+    5586557
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 15,
+  "inner_step": 16,
   "inner_steps": 0,
   "last_allreduce_block": 5580790,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0e66d5304bcb9522c622aaf5e9feb1ba3d68033e5db98e25d745020a32e2aee
+oid sha256:4474dccdcddd107008e3ac7ced48364fef901fae48a5ae631ae750f0c6668e12
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad046e95454a0033ec4bac5ae9b18c5afff0b09aa16fca93f16f1999affcd906
+oid sha256:9ea00d9580578b27982a03cce5d5d5055ad56dd59447222cf068817a72c7b3a1
 size 4040701744