Run 4. Outer Step 53. Inner Step 33.

config.json

@@ -268,19 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5577348,
-    5577351,
-    5577353,
-    5577356,
-    5577358,
-    5577361
+    5577363,
+    5577366,
+    5577368,
+    5577371,
+    5577373
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 32,
+  "inner_step": 33,
   "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:af3a5927d0728dfa6d148fdd359df9e386e65fc6f7720170ed022cdf4b74d91e
+oid sha256:f5d84c9a18a87abd9b0aa8ba51b568e460a968d682bb08a07d7425847e3800bd
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdf7fbc5a668fe0de43d2b8e376efdfcc332dd23dbe7b02d7a1d3ed1665ab6e2
+oid sha256:e64e60c0b0dcb67618e09288f3e5e6150c89c917dea1d5895bd89247f6e255f9
 size 4040701744