Outer Step 0. Inner Step 84. Batch Size 496

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "distributed/optimized-gpt2-1b",
+  "_name_or_path": "Saadaslamkhan/M2",
   "activation_function": "gelu_new",
   "all_reduce_scores": {
     "0": "SUCCESS",
@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5050200,
-    5050205,
-    5050207,
-    5050214,
-    5050218
+    5050421,
+    5050426,
+    5050430,
+    5050435,
+    5050439
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 82,
+  "inner_step": 84,
   "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:afd133b7b38a5aca811c30be65547d5f5a5517947539a094612a77cf1d887baa
+oid sha256:a057f93fc91d652cfd346dc1570eedba8aa9c84167b926c32c4dc74d4fe0e446
 size 4040701744