Run 4. Outer Step 58. Inner Step 2.

config.json

@@ -268,18 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5587579,
-    5587581,
-    5587585,
-    5587588,
-    5587591
+    5587594,
+    5587597,
+    5587600,
+    5587600,
+    5587605,
+    5587608
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 1,
+  "inner_step": 2,
   "inner_steps": 0,
   "last_allreduce_block": 5576204,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c7d2d1c8c78c03c835287484f5fb72e20ba2047c05a41989de12e33b68cc87a
+oid sha256:3a212ced91e33761bf657a1e544dd9650ad355f59cd8929d29bbe86bb9a8ae5e
 size 8081782439

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ba35fe72ed12b54c4e91ff5e916450689614454f76f3fc50436b55c099335a8
+oid sha256:21ad277e83a5a65e55c19bc379d342307880570fe396adac2d50bbe0dc2120f1
 size 4040701744