Outer Step 0. Inner Step 14. Batch Size 476

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "distributed/optimized-gpt2-1b",
+  "_name_or_path": "maher4488/minor3",
   "activation_function": "gelu_new",
   "all_reduce_scores": {
     "0": "NON_PARTICIPATING",
@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5129605,
-    5129611,
-    5129620,
-    5129640,
-    5129645
+    5129757,
+    5129765,
+    5129779,
+    5129790,
+    5129804
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 12,
+  "inner_step": 14,
   "inner_steps": 0,
   "last_allreduce_block": 5072405,
   "layer_norm_epsilon": 1e-05,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34b4e985baad5ee77476b4eb655deddafaddbd591f67fa1483811bbea75def20
+oid sha256:b26d31c36df44b756ce797236901d80f9713a864bc2a8ce603734365d4ec1678
 size 4040701744