Run 3. Outer Step 8. Inner Step 0.

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "crypt0trading/c66-h4",
+  "_name_or_path": "distributed/optimized-gpt2-1b",
   "activation_function": "gelu_new",
   "all_reduce_scores": {
     "0": "NON_PARTICIPATING",
@@ -115,7 +115,7 @@
     "198": "NON_PARTICIPATING",
     "199": "NON_PARTICIPATING",
     "2": "SUCCESS",
-    "20": "SUCCESS",
+    "20": "NON_PARTICIPATING",
     "200": "NON_PARTICIPATING",
     "201": "NON_PARTICIPATING",
     "202": "NON_PARTICIPATING",
@@ -137,7 +137,7 @@
     "217": "NON_PARTICIPATING",
     "218": "NON_PARTICIPATING",
     "219": "NON_PARTICIPATING",
-    "22": "FAIL",
+    "22": "NON_PARTICIPATING",
     "220": "NON_PARTICIPATING",
     "221": "NON_PARTICIPATING",
     "222": "NON_PARTICIPATING",
@@ -189,14 +189,14 @@
     "34": "NON_PARTICIPATING",
     "35": "NON_PARTICIPATING",
     "36": "NON_PARTICIPATING",
-    "37": "SUCCESS",
+    "37": "NON_PARTICIPATING",
     "38": "NON_PARTICIPATING",
-    "39": "SUCCESS",
+    "39": "NON_PARTICIPATING",
     "4": "NON_PARTICIPATING",
     "40": "NON_PARTICIPATING",
-    "41": "NON_PARTICIPATING",
+    "41": "SUCCESS",
     "42": "NON_PARTICIPATING",
-    "43": "FAIL",
+    "43": "SUCCESS",
     "44": "SUCCESS",
     "45": "NON_PARTICIPATING",
     "46": "NON_PARTICIPATING",
@@ -217,17 +217,17 @@
     "6": "NON_PARTICIPATING",
     "60": "NON_PARTICIPATING",
     "61": "NON_PARTICIPATING",
-    "62": "SUCCESS",
+    "62": "NON_PARTICIPATING",
     "63": "NON_PARTICIPATING",
     "64": "NON_PARTICIPATING",
     "65": "NON_PARTICIPATING",
     "66": "NON_PARTICIPATING",
-    "67": "FAIL",
+    "67": "SUCCESS",
     "68": "NON_PARTICIPATING",
     "69": "NON_PARTICIPATING",
     "7": "NON_PARTICIPATING",
     "70": "NON_PARTICIPATING",
-    "71": "SUCCESS",
+    "71": "NON_PARTICIPATING",
     "72": "NON_PARTICIPATING",
     "73": "NON_PARTICIPATING",
     "74": "NON_PARTICIPATING",
@@ -237,11 +237,11 @@
     "78": "NON_PARTICIPATING",
     "79": "NON_PARTICIPATING",
     "8": "NON_PARTICIPATING",
-    "80": "FAIL",
+    "80": "NON_PARTICIPATING",
     "81": "NON_PARTICIPATING",
     "82": "NON_PARTICIPATING",
     "83": "NON_PARTICIPATING",
-    "84": "SUCCESS",
+    "84": "NON_PARTICIPATING",
     "85": "NON_PARTICIPATING",
     "86": "NON_PARTICIPATING",
     "87": "NON_PARTICIPATING",
@@ -256,7 +256,7 @@
     "95": "NON_PARTICIPATING",
     "96": "SUCCESS",
     "97": "NON_PARTICIPATING",
-    "98": "FAIL",
+    "98": "NON_PARTICIPATING",
     "99": "NON_PARTICIPATING"
   },
   "architectures": [
@@ -268,20 +268,20 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5395522,
-    5395526,
-    5395530,
-    5395534,
-    5395538
+    5395806,
+    5395810,
+    5395815,
+    5395819,
+    5395823
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 79,
+  "inner_step": 0,
   "inner_steps": 0,
-  "last_allreduce_block": 5392742,
+  "last_allreduce_block": 5395632,
   "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:fcfea18d8dcabfacac1fe54346f6e6c281870b21da29e59ccc1c2d53ad8f7c42
+oid sha256:3a9de59582f1efe499f7f8c2f7a2f7264304beba633b0bb929e53fe31d401577
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a37fae9bd2469fa44f3ab96c72a99fa01c7cf76f3ff675a88efb9c80b4bc7990
+oid sha256:22f339a6f66964efc25710cefa4bf7100e0613a2b429de3960b6d9fa873a1c3a
 size 4040701744