Training in progress epoch 0

README.md

@@ -1,6 +1,6 @@
 ---
-license: apache-2.0
-base_model: badokorach/bert-finetuned-squad-7
+license: mit
+base_model: Davlan/afro-xlmr-small
 tags:
 - generated_from_keras_callback
 model-index:
@@ -13,10 +13,10 @@ probably proofread and complete it, then remove this comment. -->
 
 # badokorach/afro-xlmr-base
 
-This model is a fine-tuned version of [badokorach/bert-finetuned-squad-7](https://huggingface.co/badokorach/bert-finetuned-squad-7) on an unknown dataset.
+This model is a fine-tuned version of [Davlan/afro-xlmr-small](https://huggingface.co/Davlan/afro-xlmr-small) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 1.1235
-- Epoch: 9
+- Train Loss: 4.1137
+- Epoch: 0
 
 ## Model description
 
@@ -35,28 +35,19 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'inner_optimizer': {'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 1e-05, 'decay_steps': 570, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.03}}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
+- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 1e-05, 'decay_steps': 1140, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.03}
 - training_precision: mixed_float16
 
 ### Training results
 
 | Train Loss | Epoch |
 |:----------:|:-----:|
-| 2.2403     | 0     |
-| 1.9141     | 1     |
-| 1.8119     | 2     |
-| 1.7013     | 3     |
-| 1.5896     | 4     |
-| 1.4655     | 5     |
-| 1.3218     | 6     |
-| 1.2406     | 7     |
-| 1.1339     | 8     |
-| 1.1235     | 9     |
+| 4.1137     | 0     |
 
 
 ### Framework versions
 
-- Transformers 4.32.0
+- Transformers 4.32.1
 - TensorFlow 2.12.0
 - Datasets 2.14.4
 - Tokenizers 0.13.3

config.json

@@ -1,25 +1,28 @@
 {
-  "_name_or_path": "badokorach/bert-finetuned-squad-7",
+  "_name_or_path": "Davlan/afro-xlmr-small",
   "architectures": [
-    "BertForQuestionAnswering"
+    "XLMRobertaForQuestionAnswering"
   ],
   "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
   "classifier_dropout": null,
-  "gradient_checkpointing": false,
+  "eos_token_id": 2,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "initializer_range": 0.02,
   "intermediate_size": 3072,
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "pad_token_id": 0,
+  "output_past": true,
+  "pad_token_id": 1,
   "position_embedding_type": "absolute",
-  "transformers_version": "4.32.0",
-  "type_vocab_size": 2,
+  "torch_dtype": "float32",
+  "transformers_version": "4.32.1",
+  "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 28996
+  "vocab_size": 70611
 }

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39379df87dca54c26980bc768996371af2537bfe9d33693e2aa90a4c57a25b5c
+size 1652624

special_tokens_map.json

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

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:faf95199d9c46c445375e2fd501581abacd0753a447f912cc87d1ee7abb99f95
-size 431158224
+oid sha256:3d368227c84d4faa065c0ee0afaf28bdb98ceb1e4ad92acb8d569bd9e05bcf30
+size 559016168

tokenizer_config.json

@@ -1,13 +1,20 @@
 {
+  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "[CLS]",
-  "do_lower_case": false,
-  "mask_token": "[MASK]",
-  "model_max_length": 512,
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
-  "unk_token": "[UNK]"
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
 }