Run 4. Outer Step 29. Inner Step 12.

config.json

@@ -268,18 +268,24 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5539480,
-    5539483,
-    5539486,
-    5539488,
-    5539490
+    5539493,
+    5539495,
+    5539498,
+    5539500,
+    5539502,
+    5539503,
+    5539505,
+    5539507,
+    5539510,
+    5539512,
+    5539513
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 11,
+  "inner_step": 12,
   "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:d681d99cf3110bb04cbcedc4016072d525851f5833dd248bfb0cf71377701a24
+oid sha256:db9a39d3f73b2e46baf7e3864d33fa2f6640701e9b831d1df2c03651745de0f2
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cb45f941a2fb0b38909c374b3cdf5f83438db34b4468cd43ebad600eafae50c
+oid sha256:060cd60af014f26ce3048f0845f460351e8091cc1a5b68efaf56636880f666fc
 size 4040701744