Run 4. Outer Step 60. Inner Step 4.

config.json

@@ -268,19 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5607483,
-    5607486,
-    5607488,
-    5607490,
-    5607493,
-    5607495
+    5607499,
+    5607503,
+    5607507,
+    5607509,
+    5607511
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 3,
+  "inner_step": 4,
   "inner_steps": 0,
   "last_allreduce_block": 5607244,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6762e80784523ad379083e5e39a31358093edea5060780e7c0e6a29dc2c2cc3b
+oid sha256:d42edd12ba957bb9300ee052f27bb9eae6085d6655f8891ada08a835a9df8467
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74fb82d3adb2cf8775c5832d5fe1d02fbf338d0c73b29ce66d8a8ae975504f56
+oid sha256:dfad6597d40ecc56fbeea7633ddbf01534c61309919c528123d0036a0858b4eb
 size 4040701744