Training in progress, step 500

adapter_config.json

@@ -16,7 +16,7 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 4,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef29793fdeb70cd463420a499083756697b3cbcd64adef0def0ce1c84eeac0c8
-size 6832600
+oid sha256:2d5d5663d081dd2ed3bdc9f9aa993a3e89f77cbee9f93248ef06bae92cc88d52
+size 27280152

special_tokens_map.json

@@ -13,5 +13,11 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<|eot_id|>"
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer.json

@@ -2306,6 +2306,15 @@
       "rstrip": false,
       "normalized": false,
       "special": true
+    },
+    {
+      "id": 128256,
+      "content": "[PAD]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
     }
   ],
   "normalizer": null,
@@ -2329,69 +2338,85 @@
     ]
   },
   "post_processor": {
-    "type": "Sequence",
-    "processors": [
+    "type": "TemplateProcessing",
+    "single": [
       {
-        "type": "ByteLevel",
-        "add_prefix_space": true,
-        "trim_offsets": false,
-        "use_regex": true
+        "SpecialToken": {
+          "id": "<|begin_of_text|>",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "SpecialToken": {
+          "id": "<|eot_id|>",
+          "type_id": 0
+        }
+      }
+    ],
+    "pair": [
+      {
+        "SpecialToken": {
+          "id": "<|begin_of_text|>",
+          "type_id": 0
+        }
       },
       {
-        "type": "TemplateProcessing",
-        "single": [
-          {
-            "SpecialToken": {
-              "id": "<|begin_of_text|>",
-              "type_id": 0
-            }
-          },
-          {
-            "Sequence": {
-              "id": "A",
-              "type_id": 0
-            }
-          }
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "SpecialToken": {
+          "id": "<|eot_id|>",
+          "type_id": 0
+        }
+      },
+      {
+        "SpecialToken": {
+          "id": "<|begin_of_text|>",
+          "type_id": 1
+        }
+      },
+      {
+        "Sequence": {
+          "id": "B",
+          "type_id": 1
+        }
+      },
+      {
+        "SpecialToken": {
+          "id": "<|eot_id|>",
+          "type_id": 1
+        }
+      }
+    ],
+    "special_tokens": {
+      "<|begin_of_text|>": {
+        "id": "<|begin_of_text|>",
+        "ids": [
+          128000
         ],
-        "pair": [
-          {
-            "SpecialToken": {
-              "id": "<|begin_of_text|>",
-              "type_id": 0
-            }
-          },
-          {
-            "Sequence": {
-              "id": "A",
-              "type_id": 0
-            }
-          },
-          {
-            "SpecialToken": {
-              "id": "<|begin_of_text|>",
-              "type_id": 1
-            }
-          },
-          {
-            "Sequence": {
-              "id": "B",
-              "type_id": 1
-            }
-          }
+        "tokens": [
+          "<|begin_of_text|>"
+        ]
+      },
+      "<|eot_id|>": {
+        "id": "<|eot_id|>",
+        "ids": [
+          128009
         ],
-        "special_tokens": {
-          "<|begin_of_text|>": {
-            "id": "<|begin_of_text|>",
-            "ids": [
-              128000
-            ],
-            "tokens": [
-              "<|begin_of_text|>"
-            ]
-          }
-        }
+        "tokens": [
+          "<|eot_id|>"
+        ]
       }
-    ]
+    }
   },
   "decoder": {
     "type": "ByteLevel",

tokenizer_config.json

@@ -2048,6 +2048,14 @@
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "128256": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
   "bos_token": "<|begin_of_text|>",
@@ -2059,6 +2067,6 @@
     "attention_mask"
   ],
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<|eot_id|>",
+  "pad_token": "[PAD]",
   "tokenizer_class": "PreTrainedTokenizerFast"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:633f123ed505c82416c6859e5f8240c19ecd7b4aba29a53f4bfcedf01efb295d
+oid sha256:2d21fbcb234c9a8116e056525690421ae6a5e06638471ae2d1eb03cce41f7da2
 size 5432