Run 4. Outer Step 66. Inner Step 94.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5621763,
-    5621767,
-    5621771,
-    5621774,
-    5621779
+    5621784,
+    5621787,
+    5621791,
+    5621794,
+    5621798
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 93,
+  "inner_step": 94,
   "inner_steps": 0,
   "last_allreduce_block": 5611658,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d30048e0c19aa89bb594306e02d67a6f6a09c7bbf364df5d5fa9079bfdbe609
+oid sha256:2e52fb7a73a6388d733423f01662c7d7b8fb912a8515323c31d64cb23b805968
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a23fa99e7882703c0683decc5b6b32e355b02f5c5d2e7dfcd9f3869e276e2b3
+oid sha256:55a16d1fd9ba7f737b3cc6851c9d05472ac4f38c071daf91825c3a8f45b1349b
 size 4040701744