Run 4. Outer Step 53. Inner Step 0.

config.json

@@ -268,15 +268,16 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5630131,
-    5630159
+    5630189,
+    5630218,
+    5630269
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 66,
+  "inner_step": 0,
   "inner_steps": 0,
   "last_allreduce_block": 5568918,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49df784fad1eb49b3db17b8b2eb2730128401516ebc58b6cecadd3235dca5f0f
+oid sha256:9111816abce6d562b2d6a5d16f94b55aeb4062225b0b8a6138418f39dee72ced
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5464f171a0051428dd55ec920550a8ae01560629f13e9b4d22dca0b4b0a258bc
+oid sha256:7d48eb71cbb63492ac360d8277b8292fdd710e0f211d92c6bac4c4c32d0810fb
 size 4040701744