Outer Step 0. Inner Step 51. Batch Size 464

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "distributed/optimized-gpt2-1b",
+  "_name_or_path": "Mhair/modelnew",
   "activation_function": "gelu_new",
   "all_reduce_scores": {
     "0": "SUCCESS",
@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5049377,
-    5049380,
-    5049384,
-    5049388,
-    5049392
+    5049443,
+    5049448,
+    5049452,
+    5049456,
+    5049460
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 49,
+  "inner_step": 51,
   "inner_steps": 0,
   "last_allreduce_block": 4016775,
   "layer_norm_epsilon": 1e-05,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa47b00e7993782c0229941ce5d6a7b29ca15d8398b7c5d015e3d35454ede722
+oid sha256:5d13b2efc9e4777fda9794f1dac35d2e8d5f7988f1461e76f90629736ef1aa95
 size 4040701744