Outer Step 8. Inner Step 185. Batch Size 8

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5292522,
-    5292525,
-    5292529,
-    5292532,
-    5292536,
-    5292539,
-    5292542,
-    5292546,
-    5292550,
-    5292553
+    5292672,
+    5292676,
+    5292679,
+    5292683,
+    5292686,
+    5292689,
+    5292693,
+    5292697,
+    5292700,
+    5292703
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 179,
+  "inner_step": 185,
   "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 sha256:84323e3f1748c35978cbeedc88453256ac296dc47ab6012fad71ea403e30af87
+oid sha256:692e4ca7a1bf7c43e1df013c8c10fa76ee115d5afe9c10787d25c66754ed427b
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d50fff1eb660f593c6e9511da644cc730db5498cfd99644ed7b75e70cb09a2c
+oid sha256:0c01f6206d7065f3ea01917938afa7bfdca395ce6b047fc71b3b0723433b5e48
 size 4040701744