Training in progress, step 500

config.json

@@ -42,5 +42,5 @@
   "transformers_version": "5.0.0",
   "use_cache": false,
   "use_weighted_layer_sum": false,
-  "vocab_size": 51865
+  "vocab_size": 51866
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7e42688ee5249477b7adcd3665da84f5afa55f2a855b4f693110190341f382b
-size 966995080
+oid sha256:0433f83140d2e7971370fa122b17130631af22bd02399046847a03e7d919cac4
+size 966998152

runs/Mar03_09-43-16_f606be61dfea/events.out.tfevents.1772530996.f606be61dfea.275.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54e031dee7e386c2c27753959acb91d5a77ac23965a663ce74db2ecf5df836fd
+size 9537

tokenizer.json

@@ -14474,6 +14474,15 @@
       "rstrip": false,
       "normalized": true,
       "special": false
+    },
+    {
+      "id": 51865,
+      "content": "<|ig|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
     }
   ],
   "normalizer": null,
@@ -14492,18 +14501,6 @@
           "type_id": 0
         }
       },
-      {
-        "SpecialToken": {
-          "id": "<|ha|>",
-          "type_id": 0
-        }
-      },
-      {
-        "SpecialToken": {
-          "id": "<|transcribe|>",
-          "type_id": 0
-        }
-      },
       {
         "SpecialToken": {
           "id": "<|notimestamps|>",
@@ -14530,18 +14527,6 @@
           "type_id": 0
         }
       },
-      {
-        "SpecialToken": {
-          "id": "<|ha|>",
-          "type_id": 0
-        }
-      },
-      {
-        "SpecialToken": {
-          "id": "<|transcribe|>",
-          "type_id": 0
-        }
-      },
       {
         "SpecialToken": {
           "id": "<|notimestamps|>",
@@ -14577,15 +14562,6 @@
           "<|endoftext|>"
         ]
       },
-      "<|ha|>": {
-        "id": "<|ha|>",
-        "ids": [
-          50354
-        ],
-        "tokens": [
-          "<|ha|>"
-        ]
-      },
       "<|notimestamps|>": {
         "id": "<|notimestamps|>",
         "ids": [
@@ -14603,15 +14579,6 @@
         "tokens": [
           "<|startoftranscript|>"
         ]
-      },
-      "<|transcribe|>": {
-        "id": "<|transcribe|>",
-        "ids": [
-          50359
-        ],
-        "tokens": [
-          "<|transcribe|>"
-        ]
       }
     }
   },

tokenizer_config.json

@@ -6,122 +6,16 @@
   "eos_token": "<|endoftext|>",
   "errors": "replace",
   "extra_special_tokens": [
-    "<|endoftext|>",
-    "<|startoftranscript|>",
-    "<|en|>",
-    "<|zh|>",
-    "<|de|>",
-    "<|es|>",
-    "<|ru|>",
-    "<|ko|>",
-    "<|fr|>",
-    "<|ja|>",
-    "<|pt|>",
-    "<|tr|>",
-    "<|pl|>",
-    "<|ca|>",
-    "<|nl|>",
-    "<|ar|>",
-    "<|sv|>",
-    "<|it|>",
-    "<|id|>",
-    "<|hi|>",
-    "<|fi|>",
-    "<|vi|>",
-    "<|he|>",
-    "<|uk|>",
-    "<|el|>",
-    "<|ms|>",
-    "<|cs|>",
-    "<|ro|>",
-    "<|da|>",
-    "<|hu|>",
-    "<|ta|>",
-    "<|no|>",
-    "<|th|>",
-    "<|ur|>",
-    "<|hr|>",
-    "<|bg|>",
-    "<|lt|>",
-    "<|la|>",
-    "<|mi|>",
-    "<|ml|>",
-    "<|cy|>",
-    "<|sk|>",
-    "<|te|>",
-    "<|fa|>",
-    "<|lv|>",
-    "<|bn|>",
-    "<|sr|>",
-    "<|az|>",
-    "<|sl|>",
-    "<|kn|>",
-    "<|et|>",
-    "<|mk|>",
-    "<|br|>",
-    "<|eu|>",
-    "<|is|>",
-    "<|hy|>",
-    "<|ne|>",
-    "<|mn|>",
-    "<|bs|>",
-    "<|kk|>",
-    "<|sq|>",
-    "<|sw|>",
-    "<|gl|>",
-    "<|mr|>",
-    "<|pa|>",
-    "<|si|>",
-    "<|km|>",
-    "<|sn|>",
-    "<|yo|>",
-    "<|so|>",
-    "<|af|>",
-    "<|oc|>",
-    "<|ka|>",
-    "<|be|>",
-    "<|tg|>",
-    "<|sd|>",
-    "<|gu|>",
-    "<|am|>",
-    "<|yi|>",
-    "<|lo|>",
-    "<|uz|>",
-    "<|fo|>",
-    "<|ht|>",
-    "<|ps|>",
-    "<|tk|>",
-    "<|nn|>",
-    "<|mt|>",
-    "<|sa|>",
-    "<|lb|>",
-    "<|my|>",
-    "<|bo|>",
-    "<|tl|>",
-    "<|mg|>",
-    "<|as|>",
-    "<|tt|>",
-    "<|haw|>",
-    "<|ln|>",
-    "<|ha|>",
-    "<|ba|>",
-    "<|jw|>",
-    "<|su|>",
-    "<|translate|>",
-    "<|transcribe|>",
-    "<|startoflm|>",
-    "<|startofprev|>",
-    "<|nocaptions|>",
-    "<|notimestamps|>"
+    "<|ig|>"
   ],
   "is_local": false,
-  "language": "hausa",
+  "language": null,
   "model_max_length": 1024,
   "pad_token": "<|endoftext|>",
   "predict_timestamps": false,
   "processor_class": "WhisperProcessor",
   "return_attention_mask": false,
-  "task": "transcribe",
+  "task": null,
   "tokenizer_class": "WhisperTokenizer",
   "unk_token": "<|endoftext|>"
 }