Run 4. Outer Step 64. Inner Step 250.

config.json

@@ -268,19 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5617421,
-    5617425,
-    5617428,
-    5617432,
-    5617436,
-    5617440
+    5617444,
+    5617449,
+    5617452,
+    5617456,
+    5617460
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 249,
+  "inner_step": 250,
   "inner_steps": 0,
   "last_allreduce_block": 5613899,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fdeac7ccb7de338420713cd73cf29d9bac11af630a91fb4dd485dac1d8df6e1
+oid sha256:bab24563847f18635f01c6115067d8497caf71f19df089704ab4d43c5fcedd8c
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bfb694a6c485717ca28d6a3e1cceec1ebb1226b3dc32731d95ba2952fbe1f43
+oid sha256:cc846e67cb5f9bc3855efb4a4ca3de02fa1f689c7fa1163c9e7c65bca1bd829e
 size 4040701744