Outer Step 0. Inner Step 131. Batch Size 88

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5155830,
-    5155835,
-    5155840,
-    5155844,
-    5155849,
-    5155853,
-    5155857,
-    5155861,
-    5155865,
-    5155869
+    5155901,
+    5155904,
+    5155909,
+    5155914,
+    5155918,
+    5155922,
+    5155926,
+    5155930,
+    5155935,
+    5155939
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 122,
+  "inner_step": 131,
   "inner_steps": 0,
   "last_allreduce_block": 4016775,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a5be9daa31154f453f04cce820683e3adcefd43b64496b93532aefe07c5a846
+oid sha256:82dc24b45797cc41dcad8a328a6c86daf05c96e238ae1fa05b6abfdc2eb23f07
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a251ea4915599e10b2e1f8f9664c88d38b4c075baa191e01af5907231dab1c01
+oid sha256:c58c6cc4ad6b89d00c4258037daadd573379735216c1da25bbcc880ed7f69cfb
 size 4040701744