Outer Step 8. Inner Step 339. Batch Size 164

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5293579,
-    5293585,
-    5293590,
-    5293594,
-    5293596,
-    5293602,
-    5293602,
-    5293608,
-    5293612,
-    5293614
+    5293658,
+    5293662,
+    5293662,
+    5293668,
+    5293673,
+    5293674,
+    5293679,
+    5293679,
+    5293685,
+    5293690
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 327,
+  "inner_step": 339,
   "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 sha256:0c758d6700a7100a55df482ade158a89d3350ab38595d84ea8eef311961c7a17
+oid sha256:69f409fd0665d3d15b06e3cdf862fb4fdbf72dd508aefb51ba9132121c0a403c
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e3ea253a144a11bb280296b3425b4605f88ee9396b35c2f801b91001588124a
+oid sha256:5e32ef5aab0095dffeaf1b6ef6402c9dcdec59f6443a7a2362947278ad0585c2
 size 4040701744