Run 4. Outer Step 57. Inner Step 38.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5602052,
-    5602054,
-    5602056,
-    5602058,
-    5602060,
-    5602063,
-    5602065
+    5602068,
+    5602071,
+    5602074,
+    5602076,
+    5602078
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 37,
+  "inner_step": 38,
   "inner_steps": 0,
   "last_allreduce_block": 5600871,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b253efa8d4c26aa734a61fb1e7c08f0dca1b8cdc6c6f2c1cb477e9977aee258
+oid sha256:27a3de3a536ad4e865aa57734abf7741ef65e67302195cfa8e8b66cc52bd731f
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8e4c2527c0ba3fb8142fdd5b89ed2938658a183742550790a137ca4c2f78985
+oid sha256:5dcba80b510ff2e36311a647f186591d5ace5b27de935d59442ca1db3603fe0c
 size 4040701744