Run 4. Outer Step 29. Inner Step 18.

config.json

@@ -268,18 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5539073,
-    5539075,
-    5539077,
-    5539079,
-    5539081
+    5539083,
+    5539086,
+    5539089,
+    5539091,
+    5539094,
+    5539096,
+    5539098,
+    5539100,
+    5539103,
+    5539106
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 17,
+  "inner_step": 18,
   "inner_steps": 0,
   "last_allreduce_block": 5538408,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b8e62013309c8905caf5c97b61a4f3fc5f5e3f1682fa90b3e6bd478dd406862
+oid sha256:59e3fd1fbbe3035dd6a47a43187557f2ebde063dda623a0814ce6310d8131911
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae0d0c2ef754c9c57c9d09354db29f49b6bca43bedf6013b593c04f728634a90
+oid sha256:cb50af91ad1352cae9c96d84aa746baac1ebc46b795678dcb8f2d2a0428759c2
 size 4040701744