Run 4. Outer Step 65. Inner Step 111.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5650780,
-    5650806
+    5650833,
+    5650861
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 108,
+  "inner_step": 111,
   "inner_steps": 0,
   "last_allreduce_block": 5648011,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b6bf4917de18d7be22a84195fc342b23fdd989697a5a147f7e852aaabe33311
+oid sha256:77d0c94d09c8f99767150767a15c7f82d1f8a7ff95ca0833dec4d0d8e64a0e51
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61eddfecc9ad52a9b96f96ee2896573000e8f5ea914752061eaf00421d462826
+oid sha256:3c6af5210eefc6f8411b6edf87d7db1f7ade7215332b9986a6c6463447ad75fb
 size 4040701744