Outer Step 8. Inner Step 211. Batch Size 88

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5292743,
-    5292747,
-    5292750,
-    5292754,
-    5292757,
-    5292761,
-    5292764,
-    5292768,
-    5292771,
-    5292775
+    5292839,
+    5292839,
+    5292844,
+    5292850,
+    5292851,
+    5292856,
+    5292861,
+    5292862,
+    5292868,
+    5292868
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 195,
+  "inner_step": 211,
   "inner_steps": 0,
   "last_allreduce_block": 5283755,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f89b2f9ccfd6f7822f43e8b190cb11336840dc0155853b5f06ff24d6facb1fb5
+oid sha256:ad0e5e128a9fae18c31aaaf977e9cc513a5bd124dc9c6b068c876a5029884aee
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c9d9045937fc6bd62872b4fb02c34c010f72753d9e22a905c8faaeb3592f352
+oid sha256:d8bb27c84dce99dc5558dca17fcbaf6334c74f175c01b6fdb2d50f71aece4341
 size 4040701744