Run 4. Outer Step 63. Inner Step 58.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5613861,
-    5613862,
-    5613863,
-    5613864,
-    5613864
+    5613865,
+    5613866,
+    5613866,
+    5613867,
+    5613867
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 57,
+  "inner_step": 58,
   "inner_steps": 0,
   "last_allreduce_block": 5611658,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc0c4a325b3a6ef0931883486d3c6dddb574447174c6317b7bb421f9992dddc0
+oid sha256:098789380db87d29a0414dbc6fa20dfb2664ae72fdbf094ff1310b1295ea8b74
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1a70a494857a4b91746a4533f17fe974e98ead0ae57034d61859f82240a6ddf
+oid sha256:a27e6b3dd4e7139159e1d398a498d3c02e2de72a25e4838066884d98f111a915
 size 4040701744