Run 2. Outer Step 9. Inner Step 311.

config.json

@@ -1,13 +1,13 @@
 {
-  "_name_or_path": "distributed/optimized-gpt2-1b",
+  "_name_or_path": "crypt0trading/c66-h8",
   "activation_function": "gelu_new",
   "all_reduce_scores": {
     "0": "NON_PARTICIPATING",
     "1": "SUCCESS",
     "10": "NON_PARTICIPATING",
     "100": "NON_PARTICIPATING",
-    "101": "SUCCESS",
-    "102": "SUCCESS",
+    "101": "NON_PARTICIPATING",
+    "102": "NON_PARTICIPATING",
     "103": "NON_PARTICIPATING",
     "104": "NON_PARTICIPATING",
     "105": "NON_PARTICIPATING",
@@ -23,7 +23,7 @@
     "114": "NON_PARTICIPATING",
     "115": "NON_PARTICIPATING",
     "116": "NON_PARTICIPATING",
-    "117": "SUCCESS",
+    "117": "NON_PARTICIPATING",
     "118": "NON_PARTICIPATING",
     "119": "NON_PARTICIPATING",
     "12": "NON_PARTICIPATING",
@@ -75,12 +75,12 @@
     "161": "NON_PARTICIPATING",
     "162": "NON_PARTICIPATING",
     "163": "NON_PARTICIPATING",
-    "164": "SUCCESS",
+    "164": "NON_PARTICIPATING",
     "165": "NON_PARTICIPATING",
     "166": "NON_PARTICIPATING",
     "167": "NON_PARTICIPATING",
     "168": "NON_PARTICIPATING",
-    "169": "SUCCESS",
+    "169": "NON_PARTICIPATING",
     "17": "NON_PARTICIPATING",
     "170": "NON_PARTICIPATING",
     "171": "NON_PARTICIPATING",
@@ -89,7 +89,7 @@
     "174": "NON_PARTICIPATING",
     "175": "NON_PARTICIPATING",
     "176": "NON_PARTICIPATING",
-    "177": "SUCCESS",
+    "177": "NON_PARTICIPATING",
     "178": "NON_PARTICIPATING",
     "179": "NON_PARTICIPATING",
     "18": "NON_PARTICIPATING",
@@ -106,8 +106,8 @@
     "19": "NON_PARTICIPATING",
     "190": "NON_PARTICIPATING",
     "191": "NON_PARTICIPATING",
-    "192": "SUCCESS",
-    "193": "SUCCESS",
+    "192": "NON_PARTICIPATING",
+    "193": "NON_PARTICIPATING",
     "194": "NON_PARTICIPATING",
     "195": "NON_PARTICIPATING",
     "196": "NON_PARTICIPATING",
@@ -115,8 +115,8 @@
     "198": "NON_PARTICIPATING",
     "199": "NON_PARTICIPATING",
     "2": "NON_PARTICIPATING",
-    "20": "SUCCESS",
-    "200": "SUCCESS",
+    "20": "NON_PARTICIPATING",
+    "200": "NON_PARTICIPATING",
     "201": "NON_PARTICIPATING",
     "202": "NON_PARTICIPATING",
     "203": "NON_PARTICIPATING",
@@ -139,11 +139,11 @@
     "219": "NON_PARTICIPATING",
     "22": "SUCCESS",
     "220": "NON_PARTICIPATING",
-    "221": "SUCCESS",
+    "221": "NON_PARTICIPATING",
     "222": "NON_PARTICIPATING",
     "223": "NON_PARTICIPATING",
     "224": "NON_PARTICIPATING",
-    "225": "SUCCESS",
+    "225": "NON_PARTICIPATING",
     "226": "NON_PARTICIPATING",
     "227": "NON_PARTICIPATING",
     "228": "NON_PARTICIPATING",
@@ -169,7 +169,7 @@
     "246": "NON_PARTICIPATING",
     "247": "NON_PARTICIPATING",
     "248": "NON_PARTICIPATING",
-    "249": "SUCCESS",
+    "249": "NON_PARTICIPATING",
     "25": "SUCCESS",
     "250": "NON_PARTICIPATING",
     "251": "NON_PARTICIPATING",
@@ -184,19 +184,19 @@
     "3": "NON_PARTICIPATING",
     "30": "NON_PARTICIPATING",
     "31": "NON_PARTICIPATING",
-    "32": "SUCCESS",
+    "32": "NON_PARTICIPATING",
     "33": "NON_PARTICIPATING",
     "34": "NON_PARTICIPATING",
-    "35": "SUCCESS",
-    "36": "SUCCESS",
+    "35": "NON_PARTICIPATING",
+    "36": "NON_PARTICIPATING",
     "37": "NON_PARTICIPATING",
     "38": "NON_PARTICIPATING",
-    "39": "NON_PARTICIPATING",
+    "39": "SUCCESS",
     "4": "NON_PARTICIPATING",
     "40": "NON_PARTICIPATING",
     "41": "NON_PARTICIPATING",
-    "42": "SUCCESS",
-    "43": "SUCCESS",
+    "42": "NON_PARTICIPATING",
+    "43": "NON_PARTICIPATING",
     "44": "NON_PARTICIPATING",
     "45": "NON_PARTICIPATING",
     "46": "NON_PARTICIPATING",
@@ -238,7 +238,7 @@
     "79": "NON_PARTICIPATING",
     "8": "NON_PARTICIPATING",
     "80": "NON_PARTICIPATING",
-    "81": "SUCCESS",
+    "81": "NON_PARTICIPATING",
     "82": "NON_PARTICIPATING",
     "83": "NON_PARTICIPATING",
     "84": "NON_PARTICIPATING",
@@ -267,15 +267,21 @@
     "AutoConfig": "distributed/optimized-gpt2-500m--configuration_gpt_optimized.GPTOptimConfig",
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
-  "block_list": [],
+  "block_list": [
+    5356182,
+    5356186,
+    5356191,
+    5356195,
+    5356200
+  ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 0,
+  "inner_step": 311,
   "inner_steps": 0,
-  "last_allreduce_block": 5351170,
+  "last_allreduce_block": 5339896,
   "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 sha256:57a7560b7d6dcff2f9b986cdf1519151986f63582928104d82fbbcf373d695a7
+oid sha256:93dd1fbb8d2f816d87e5c50e66c6c16bb1dcc46ab0debd7a54e5d178059fb160
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30a3c2a1f583992135596ada96883cba467a485b6ef53f21ba48c2355f414587
+oid sha256:b92de830eca408d0743d6e96c2b84e08d052d17b8bb5f17da1a897feb7fa15ba
 size 4040701744