Run 4. Outer Step 62. Inner Step 27.

config.json

@@ -268,19 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5611450,
-    5611454,
-    5611458,
-    5611461,
-    5611465,
-    5611469
+    5611473,
+    5611477,
+    5611481,
+    5611485,
+    5611487
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 26,
+  "inner_step": 27,
   "inner_steps": 0,
   "last_allreduce_block": 5610584,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6efcc19aa5f82b611367759a4bea40b9b1b866b85191e64f2b35ae769bbf70af
+oid sha256:a15006e82bbbd8fbcf05cdfc0d886783408f2e918c89bc4160f02aa9c0435b32
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f84ddae8cc818952f42cef8d9e1b2c446d726ecd0a1375a09ed73862cd680ba
+oid sha256:b12ccb1ea2b3a0b5e35c9bc51c2f82954a15d350d7b8655b26d0c08455af0773
 size 4040701744