Training in progress, epoch 1

README.md

@@ -1,6 +1,6 @@
 ---
-license: apache-2.0
-base_model: distilbert-base-uncased
+license: mit
+base_model: roberta-base
 tags:
 - generated_from_trainer
 model-index:
@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # hausa-distilbert
 
-This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
+This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
 
 ## Model description
 

config.json

@@ -1,36 +1,33 @@
 {
-  "_name_or_path": "roberta-base",
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
   "architectures": [
-    "RobertaForSequenceClassification"
+    "DistilBertForSequenceClassification"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
-  "classifier_dropout": null,
-  "eos_token_id": 2,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
   "id2label": {
     "0": "Negative",
     "1": "Positive"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
   "label2id": {
     "Negative": 0,
     "Positive": 1
   },
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "roberta",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "pad_token_id": 1,
-  "position_embedding_type": "absolute",
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
   "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.40.1",
-  "type_vocab_size": 1,
-  "use_cache": true,
-  "vocab_size": 50265
+  "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:190d26aae00acfce55a7831a18971d1c10b70d26792d728628d26952bde29d37
-size 498612824
+oid sha256:969574eeeae955749d0c3aeb358d2e78c2d13e80e9ebdd37f4025edb72af899c
+size 267832560

runs/Apr30_01-41-54_e3a7e781a484/events.out.tfevents.1714441318.e3a7e781a484.1903.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ecea3cce76d26729547905be730f415faad4bb6d66bbb899f68e1d04697c2ba
-size 4184
+oid sha256:1c723df7c1db50d2672f1fdac6c91f35a5d06f8c81ea611c5f0d9a2afb536c05
+size 4801

runs/Apr30_01-42-55_e3a7e781a484/events.out.tfevents.1714441377.e3a7e781a484.1903.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a5225daf22d7a1a75a2249a18450fae3484b37bb60d98e21a38602420a40112
-size 4184
+oid sha256:e0d81d1ea94f18f2a99b9cfab3d746fc650f69879d5ebc4b1de80770a1f79b4b
+size 5155

runs/Apr30_01-46-34_e3a7e781a484/events.out.tfevents.1714441597.e3a7e781a484.3313.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f20116d64518aeee5d7f2f3ae5309b772cf2fd3c54d55a3450c91fc57e340687
+size 4184

special_tokens_map.json

@@ -1,15 +1,7 @@
 {
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "mask_token": {
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "unk_token": "<unk>"
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
 }

tokenizer_config.json

@@ -1,57 +1,55 @@
 {
-  "add_prefix_space": false,
   "added_tokens_decoder": {
     "0": {
-      "content": "<s>",
+      "content": "[PAD]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "1": {
-      "content": "<pad>",
+    "100": {
+      "content": "[UNK]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "2": {
-      "content": "</s>",
+    "101": {
+      "content": "[CLS]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "3": {
-      "content": "<unk>",
+    "102": {
+      "content": "[SEP]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "50264": {
-      "content": "<mask>",
-      "lstrip": true,
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
-  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "errors": "replace",
-  "mask_token": "<mask>",
-  "model_max_length": 512,
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "tokenizer_class": "RobertaTokenizer",
-  "trim_offsets": true,
-  "unk_token": "<unk>"
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f66844bf59a1647466bf05bf6aa708fa1869c775e0cc8a94931a1d75a08ee5af
+oid sha256:c80d4c7bd4be6fa549578a2457dd57c01b0ab0628adfc2aaca9f72043716e7fb
 size 5048