Run 4. Outer Step 57. Inner Step 0.

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "philip324mark/mark2",
+  "_name_or_path": "distributed/optimized-gpt2-1b",
   "activation_function": "gelu_new",
   "all_reduce_scores": {
     "0": "NON_PARTICIPATING",
@@ -9,62 +9,62 @@
     "101": "NON_PARTICIPATING",
     "102": "NON_PARTICIPATING",
     "103": "NON_PARTICIPATING",
-    "104": "SUCCESS",
+    "104": "NON_PARTICIPATING",
     "105": "NON_PARTICIPATING",
     "106": "NON_PARTICIPATING",
-    "107": "NON_PARTICIPATING",
+    "107": "SUCCESS",
     "108": "NON_PARTICIPATING",
     "109": "NON_PARTICIPATING",
     "11": "SUCCESS",
     "110": "NON_PARTICIPATING",
-    "111": "NON_PARTICIPATING",
+    "111": "SUCCESS",
     "112": "NON_PARTICIPATING",
-    "113": "SUCCESS",
+    "113": "NON_PARTICIPATING",
     "114": "NON_PARTICIPATING",
     "115": "NON_PARTICIPATING",
     "116": "NON_PARTICIPATING",
     "117": "NON_PARTICIPATING",
-    "118": "SUCCESS",
+    "118": "NON_PARTICIPATING",
     "119": "NON_PARTICIPATING",
     "12": "SUCCESS",
     "120": "NON_PARTICIPATING",
-    "121": "SUCCESS",
+    "121": "NON_PARTICIPATING",
     "122": "NON_PARTICIPATING",
     "123": "NON_PARTICIPATING",
-    "124": "NON_PARTICIPATING",
+    "124": "SUCCESS",
     "125": "NON_PARTICIPATING",
     "126": "SUCCESS",
     "127": "NON_PARTICIPATING",
     "128": "NON_PARTICIPATING",
     "129": "NON_PARTICIPATING",
     "13": "SUCCESS",
-    "130": "NON_PARTICIPATING",
+    "130": "SUCCESS",
     "131": "NON_PARTICIPATING",
     "132": "NON_PARTICIPATING",
     "133": "NON_PARTICIPATING",
     "134": "NON_PARTICIPATING",
     "135": "NON_PARTICIPATING",
-    "136": "NON_PARTICIPATING",
+    "136": "SUCCESS",
     "137": "NON_PARTICIPATING",
     "138": "NON_PARTICIPATING",
     "139": "NON_PARTICIPATING",
-    "14": "NON_PARTICIPATING",
+    "14": "SUCCESS",
     "140": "NON_PARTICIPATING",
     "141": "NON_PARTICIPATING",
-    "142": "SUCCESS",
+    "142": "NON_PARTICIPATING",
     "143": "NON_PARTICIPATING",
     "144": "NON_PARTICIPATING",
     "145": "NON_PARTICIPATING",
     "146": "NON_PARTICIPATING",
     "147": "NON_PARTICIPATING",
-    "148": "SUCCESS",
+    "148": "NON_PARTICIPATING",
     "149": "NON_PARTICIPATING",
-    "15": "NON_PARTICIPATING",
+    "15": "SUCCESS",
     "150": "NON_PARTICIPATING",
     "151": "NON_PARTICIPATING",
     "152": "NON_PARTICIPATING",
-    "153": "SUCCESS",
-    "154": "NON_PARTICIPATING",
+    "153": "NON_PARTICIPATING",
+    "154": "SUCCESS",
     "155": "NON_PARTICIPATING",
     "156": "NON_PARTICIPATING",
     "157": "NON_PARTICIPATING",
@@ -73,9 +73,9 @@
     "16": "SUCCESS",
     "160": "NON_PARTICIPATING",
     "161": "NON_PARTICIPATING",
-    "162": "SUCCESS",
+    "162": "NON_PARTICIPATING",
     "163": "NON_PARTICIPATING",
-    "164": "SUCCESS",
+    "164": "NON_PARTICIPATING",
     "165": "SUCCESS",
     "166": "NON_PARTICIPATING",
     "167": "NON_PARTICIPATING",
@@ -87,7 +87,7 @@
     "172": "NON_PARTICIPATING",
     "173": "NON_PARTICIPATING",
     "174": "NON_PARTICIPATING",
-    "175": "SUCCESS",
+    "175": "NON_PARTICIPATING",
     "176": "NON_PARTICIPATING",
     "177": "NON_PARTICIPATING",
     "178": "NON_PARTICIPATING",
@@ -100,7 +100,7 @@
     "184": "NON_PARTICIPATING",
     "185": "NON_PARTICIPATING",
     "186": "NON_PARTICIPATING",
-    "187": "NON_PARTICIPATING",
+    "187": "SUCCESS",
     "188": "NON_PARTICIPATING",
     "189": "NON_PARTICIPATING",
     "19": "SUCCESS",
@@ -124,7 +124,7 @@
     "205": "NON_PARTICIPATING",
     "206": "NON_PARTICIPATING",
     "207": "NON_PARTICIPATING",
-    "208": "NON_PARTICIPATING",
+    "208": "SUCCESS",
     "209": "NON_PARTICIPATING",
     "21": "SUCCESS",
     "210": "NON_PARTICIPATING",
@@ -132,22 +132,22 @@
     "212": "NON_PARTICIPATING",
     "213": "NON_PARTICIPATING",
     "214": "NON_PARTICIPATING",
-    "215": "NON_PARTICIPATING",
+    "215": "SUCCESS",
     "216": "NON_PARTICIPATING",
     "217": "NON_PARTICIPATING",
     "218": "NON_PARTICIPATING",
-    "219": "SUCCESS",
+    "219": "NON_PARTICIPATING",
     "22": "SUCCESS",
-    "220": "SUCCESS",
+    "220": "NON_PARTICIPATING",
     "221": "NON_PARTICIPATING",
     "222": "NON_PARTICIPATING",
-    "223": "NON_PARTICIPATING",
+    "223": "SUCCESS",
     "224": "NON_PARTICIPATING",
     "225": "NON_PARTICIPATING",
     "226": "NON_PARTICIPATING",
     "227": "NON_PARTICIPATING",
     "228": "NON_PARTICIPATING",
-    "229": "NON_PARTICIPATING",
+    "229": "SUCCESS",
     "23": "SUCCESS",
     "230": "NON_PARTICIPATING",
     "231": "NON_PARTICIPATING",
@@ -161,13 +161,13 @@
     "239": "NON_PARTICIPATING",
     "24": "SUCCESS",
     "240": "SUCCESS",
-    "241": "NON_PARTICIPATING",
+    "241": "SUCCESS",
     "242": "NON_PARTICIPATING",
-    "243": "NON_PARTICIPATING",
+    "243": "SUCCESS",
     "244": "NON_PARTICIPATING",
     "245": "NON_PARTICIPATING",
     "246": "NON_PARTICIPATING",
-    "247": "SUCCESS",
+    "247": "NON_PARTICIPATING",
     "248": "NON_PARTICIPATING",
     "249": "SUCCESS",
     "25": "SUCCESS",
@@ -211,9 +211,9 @@
     "54": "SUCCESS",
     "55": "SUCCESS",
     "56": "SUCCESS",
-    "57": "FAIL",
+    "57": "SUCCESS",
     "58": "NON_PARTICIPATING",
-    "59": "FAIL",
+    "59": "SUCCESS",
     "6": "NON_PARTICIPATING",
     "60": "SUCCESS",
     "61": "NON_PARTICIPATING",
@@ -230,14 +230,14 @@
     "71": "NON_PARTICIPATING",
     "72": "SUCCESS",
     "73": "NON_PARTICIPATING",
-    "74": "FAIL",
+    "74": "SUCCESS",
     "75": "SUCCESS",
     "76": "SUCCESS",
     "77": "SUCCESS",
     "78": "SUCCESS",
     "79": "NON_PARTICIPATING",
     "8": "SUCCESS",
-    "80": "FAIL",
+    "80": "SUCCESS",
     "81": "SUCCESS",
     "82": "SUCCESS",
     "83": "NON_PARTICIPATING",
@@ -268,20 +268,20 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5584733,
-    5584737,
-    5584741,
-    5584745,
-    5584749
+    5584872,
+    5584876,
+    5584880,
+    5584884,
+    5584888
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 49,
+  "inner_step": 0,
   "inner_steps": 0,
-  "last_allreduce_block": 5580790,
+  "last_allreduce_block": 5584811,
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt_optimized",
   "n_embd": 1280,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fac46a1e328dc52a04a4fc89a9e7b4e781bfe2da866d32f3a9d0288595f0ddc2
+oid sha256:fd36f68d0aeb7bcb631ea1e85dd98365f621a9098f2b390d73989b58f23ea96d
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f73b7ecfc499d55f1da7140a94000fbae8ef609de1b1985ef6839a7292534dd5
+oid sha256:4dc410d58645ec73074afb23c4f31765c1affd6b2fffbd1a8ae49cac841bddb5
 size 4040701744