Outer Step 8. Inner Step 157. Batch Size 192

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5292300,
-    5292304,
-    5292307,
-    5292311,
-    5292315,
-    5292318,
-    5292322,
-    5292325,
-    5292329,
-    5292332
+    5292378,
+    5292381,
+    5292385,
+    5292389,
+    5292392,
+    5292395,
+    5292399,
+    5292402,
+    5292406,
+    5292410
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 145,
+  "inner_step": 157,
   "inner_steps": 0,
   "last_allreduce_block": 5283755,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:faea15b8935051443d450a788f72d36ef90bed13c214ed0d7b52f76d2657517a
+oid sha256:f69bbfb18e3e33cbf9106b2861c16cb7e03a1a38444b8288ad5cb13e51865e80
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a29e21fa94a6ddebf7a0d3ec18eac5b06a4190c941406671acab25d9f88bb6f7
+oid sha256:5eb0fb3d0d812a6885b4e74c5c151aee1fe3091b063c9618a97046f677db5a64
 size 4040701744