Run 2. Outer Step 9. Inner Step 289.

config.json

@@ -1,13 +1,13 @@
 {
-  "_name_or_path": "distributed/optimized-gpt2-1b",
+  "_name_or_path": "crypt0trading/c66-h5",
   "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",
@@ -75,8 +75,8 @@
     "161": "NON_PARTICIPATING",
     "162": "NON_PARTICIPATING",
     "163": "NON_PARTICIPATING",
-    "164": "SUCCESS",
-    "165": "NON_PARTICIPATING",
+    "164": "NON_PARTICIPATING",
+    "165": "SUCCESS",
     "166": "NON_PARTICIPATING",
     "167": "NON_PARTICIPATING",
     "168": "NON_PARTICIPATING",
@@ -100,14 +100,14 @@
     "184": "NON_PARTICIPATING",
     "185": "NON_PARTICIPATING",
     "186": "NON_PARTICIPATING",
-    "187": "NON_PARTICIPATING",
+    "187": "SUCCESS",
     "188": "NON_PARTICIPATING",
     "189": "NON_PARTICIPATING",
     "19": "NON_PARTICIPATING",
     "190": "NON_PARTICIPATING",
     "191": "NON_PARTICIPATING",
     "192": "SUCCESS",
-    "193": "SUCCESS",
+    "193": "NON_PARTICIPATING",
     "194": "NON_PARTICIPATING",
     "195": "NON_PARTICIPATING",
     "196": "NON_PARTICIPATING",
@@ -135,27 +135,27 @@
     "215": "NON_PARTICIPATING",
     "216": "NON_PARTICIPATING",
     "217": "NON_PARTICIPATING",
-    "218": "NON_PARTICIPATING",
+    "218": "SUCCESS",
     "219": "NON_PARTICIPATING",
-    "22": "SUCCESS",
+    "22": "NON_PARTICIPATING",
     "220": "NON_PARTICIPATING",
     "221": "SUCCESS",
     "222": "NON_PARTICIPATING",
     "223": "NON_PARTICIPATING",
     "224": "NON_PARTICIPATING",
-    "225": "SUCCESS",
-    "226": "NON_PARTICIPATING",
+    "225": "NON_PARTICIPATING",
+    "226": "SUCCESS",
     "227": "NON_PARTICIPATING",
     "228": "NON_PARTICIPATING",
     "229": "NON_PARTICIPATING",
-    "23": "SUCCESS",
+    "23": "NON_PARTICIPATING",
     "230": "NON_PARTICIPATING",
     "231": "NON_PARTICIPATING",
     "232": "NON_PARTICIPATING",
     "233": "NON_PARTICIPATING",
     "234": "NON_PARTICIPATING",
     "235": "NON_PARTICIPATING",
-    "236": "NON_PARTICIPATING",
+    "236": "SUCCESS",
     "237": "NON_PARTICIPATING",
     "238": "NON_PARTICIPATING",
     "239": "NON_PARTICIPATING",
@@ -176,7 +176,7 @@
     "252": "NON_PARTICIPATING",
     "253": "NON_PARTICIPATING",
     "254": "NON_PARTICIPATING",
-    "255": "NON_PARTICIPATING",
+    "255": "SUCCESS",
     "26": "NON_PARTICIPATING",
     "27": "NON_PARTICIPATING",
     "28": "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",
-    "37": "NON_PARTICIPATING",
+    "35": "NON_PARTICIPATING",
+    "36": "NON_PARTICIPATING",
+    "37": "SUCCESS",
     "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",
@@ -204,7 +204,7 @@
     "48": "NON_PARTICIPATING",
     "49": "NON_PARTICIPATING",
     "5": "NON_PARTICIPATING",
-    "50": "NON_PARTICIPATING",
+    "50": "SUCCESS",
     "51": "NON_PARTICIPATING",
     "52": "NON_PARTICIPATING",
     "53": "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",
@@ -268,20 +268,20 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5355556,
-    5355561,
-    5355566,
-    5355570,
-    5355575
+    5355731,
+    5355737,
+    5355742,
+    5355747,
+    5355752
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 61,
+  "inner_step": 289,
   "inner_steps": 0,
-  "last_allreduce_block": 5351170,
+  "last_allreduce_block": 5350023,
   "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:df943dd303bcb4f442af267083c79a631ff95821e1de04247c580ed4d7770370
+oid sha256:3130560d03c4421dcda82ca747ef761856e4cd4e049896cac14cd81406c77a88
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfff0225e487f3a307d4d3d1d4f04a0d34bf7878b72f6e0338c595a4243c007c
+oid sha256:5f439a3c9dc44e27ebee294fd39df6d4db3317edc82980784605567ad70dc81a
 size 4040701744