Run 4. Outer Step 29. Inner Step 13.

config.json

@@ -268,24 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5539493,
-    5539495,
-    5539498,
-    5539500,
-    5539502,
-    5539503,
-    5539505,
-    5539507,
-    5539510,
-    5539512,
-    5539513
+    5539516,
+    5539518,
+    5539521,
+    5539523,
+    5539526,
+    5539527,
+    5539529,
+    5539531,
+    5539534,
+    5539536
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 12,
+  "inner_step": 13,
   "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:db9a39d3f73b2e46baf7e3864d33fa2f6640701e9b831d1df2c03651745de0f2
+oid sha256:f6e7aff65db551592e7a85e3d5c8b7c7e4e26f53ee72e88da9bd5e9d1222da58
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:060cd60af014f26ce3048f0845f460351e8091cc1a5b68efaf56636880f666fc
+oid sha256:831904f2ef82bccf6741fed79d07e590447967297890b36129154253ac8e3ec8
 size 4040701744