Outer Step 8. Inner Step 375. Batch Size 492

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5293808,
-    5293811,
-    5293815,
-    5293817,
-    5293822,
-    5293823,
-    5293828,
-    5293833,
-    5293834,
-    5293840
+    5293893,
+    5293894,
+    5293899,
+    5293904,
+    5293905,
+    5293911,
+    5293911,
+    5293917,
+    5293921,
+    5293923
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 362,
+  "inner_step": 375,
   "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:f6be74b6ad93ccc959cacfe52bc11642b4fca8682471001a61c7ee934719f434
+oid sha256:13d6ebd6e95adc17b4fe518845664c6e264bb119775dba730619526e8c9bce8c
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:147fc33f95cd23f268950ddcd32dea942e4d1d1d8596862d6cc5267f8ea2745e
+oid sha256:07da843c94ae26af3a066afe15b5d33a0882805066ca541ca741fe9860340722
 size 4040701744