Run 4. Outer Step 53. Inner Step 62.

config.json

@@ -268,19 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5588323,
-    5588327,
-    5588331,
-    5588335,
-    5588340,
-    5588344
+    5588348,
+    5588352,
+    5588356,
+    5588363,
+    5588367
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 61,
+  "inner_step": 62,
   "inner_steps": 0,
   "last_allreduce_block": 5565072,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b650638a98c63a2c4be22a25e586b5ca507a63ab7c113c5b3ba598e1b4d6088f
+oid sha256:400ce693222ea4d2340172ef49e473002bae501f8c35f19b1dac42e5865b4f67
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9512bf2d5d102cace24754ea32c04270a77d3ca53cc691484679fdff458baba
+oid sha256:bce30de74b57ec522de338d7ca305016d40e91e232d4c511f9f8f376da877c7b
 size 4040701744