Run 4. Outer Step 61. Inner Step 42.

config.json

@@ -268,19 +268,20 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5609961,
-    5609965,
-    5609969,
-    5609973,
-    5609977,
-    5609981
+    5609986,
+    5609990,
+    5609992,
+    5609998,
+    5610003,
+    5610007,
+    5610011
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 41,
+  "inner_step": 42,
   "inner_steps": 0,
   "last_allreduce_block": 5602341,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f7051eafe97ac9255d1c0e0f0037ca91bbc64b0a1c772a88554b46a6d5d0ea8
+oid sha256:ea68fa7cf35522b181c58315c740e477d0e60e5bf8fc63abe599d8c8643a650d
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca1c7bcf0370046f4f6ff2e49e0314cec15ba3b584216b048396eddd268b7d7c
+oid sha256:81a0dfae70b8c9b21c120a85719ec5aeaf4b32fe4916a3a8fe36391446239c21
 size 4040701744