Run 4. Outer Step 57. Inner Step 20.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5601461,
-    5601466,
-    5601471,
-    5601476,
-    5601481
+    5601487,
+    5601492,
+    5601497,
+    5601502,
+    5601507
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 19,
+  "inner_step": 20,
   "inner_steps": 0,
   "last_allreduce_block": 5599463,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:124c2d0bb7e90ef76a0162031cb8497d7fa70c1833ca8f41ea1fa0c96deab74c
+oid sha256:6e599d9d9f4e7b8e27b9113adaa9fd348f85090bda7d9408a3d3f88eb3a73ffc
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8daa9659b1ef920c9733ecb825c763479368123c47e38777cffb81f66ef35c7
+oid sha256:a1649b4c80d434c4f5f80cb3226c43f60fc3c5076e4409aa331e8531ebe407a3
 size 4040701744