Training in progress epoch 0

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,6 +1,6 @@
 ---
 license: mit
-base_model: badokorach/mobilebert-uncased-finetuned-agic-181223
+base_model: badokorach/afriqa_afroxlmr_eng_280124
 tags:
 - generated_from_keras_callback
 model-index:
@@ -13,11 +13,11 @@ probably proofread and complete it, then remove this comment. -->
 
 # badokorach/mobilebert-uncased-finetuned-agic-170224
 
-This model is a fine-tuned version of [badokorach/mobilebert-uncased-finetuned-agic-181223](https://huggingface.co/badokorach/mobilebert-uncased-finetuned-agic-181223) on an unknown dataset.
+This model is a fine-tuned version of [badokorach/afriqa_afroxlmr_eng_280124](https://huggingface.co/badokorach/afriqa_afroxlmr_eng_280124) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.0080
+- Train Loss: 1.0244
 - Validation Loss: 0.0
-- Epoch: 4
+- Epoch: 0
 
 ## Model description
 
@@ -36,18 +36,14 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'module': None, 'class_name': 'CustomLearningRateScheduler', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 2736, 'warmup_steps': 304, 'end_learning_rate': 1e-05}, 'registered_name': 'CustomLearningRateScheduler'}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
+- optimizer: {'inner_optimizer': {'module': 'keras.optimizers', 'class_name': 'Adam', 'config': {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'module': None, 'class_name': 'CustomLearningRateScheduler', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 2736, 'warmup_steps': 304, 'end_learning_rate': 1e-05}, 'registered_name': 'CustomLearningRateScheduler'}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}, 'registered_name': None}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
 - training_precision: mixed_float16
 
 ### Training results
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 2.0240     | 0.0             | 0     |
-| 0.0737     | 0.0             | 1     |
-| 0.0272     | 0.0             | 2     |
-| 0.0135     | 0.0             | 3     |
-| 0.0080     | 0.0             | 4     |
+| 1.0244     | 0.0             | 0     |
 
 
 ### Framework versions

config.json

@@ -1,32 +1,28 @@
 {
-  "_name_or_path": "badokorach/mobilebert-uncased-finetuned-agic-181223",
+  "_name_or_path": "badokorach/afriqa_afroxlmr_eng_280124",
   "architectures": [
-    "MobileBertForQuestionAnswering"
+    "XLMRobertaForQuestionAnswering"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "classifier_activation": false,
+  "bos_token_id": 0,
   "classifier_dropout": null,
-  "embedding_size": 128,
-  "hidden_act": "relu",
-  "hidden_dropout_prob": 0.0,
-  "hidden_size": 512,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "initializer_range": 0.02,
-  "intermediate_size": 512,
-  "intra_bottleneck_size": 128,
-  "key_query_shared_bottleneck": true,
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "mobilebert",
-  "normalization_type": "no_norm",
-  "num_attention_heads": 4,
-  "num_feedforward_networks": 4,
-  "num_hidden_layers": 24,
-  "pad_token_id": 0,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
   "transformers_version": "4.35.2",
-  "trigram_input": true,
-  "true_hidden_size": 128,
-  "type_vocab_size": 2,
-  "use_bottleneck": true,
-  "use_bottleneck_attention": false,
-  "vocab_size": 30522
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
 }

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -1,34 +1,48 @@
 {
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "cls_token": {
-    "content": "[CLS]",
+    "content": "<s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "mask_token": {
-    "content": "[MASK]",
+  "eos_token": {
+    "content": "</s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "pad_token": {
-    "content": "[PAD]",
+    "content": "<pad>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "sep_token": {
-    "content": "[SEP]",
+    "content": "</s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "unk_token": {
-    "content": "[UNK]",
+    "content": "<unk>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce5e61888ef9cb5cd025ad941ab9988bfd5fc33306436d527a25eb06214f3944
-size 99822192
+oid sha256:ba5b8eb12e62ba8528e74449fad33961e8961bc374eaa3d521d0de3af66a8082
+size 1110105320

tokenizer_config.json

@@ -1,58 +1,61 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "[PAD]",
+      "content": "<s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "100": {
-      "content": "[UNK]",
+    "1": {
+      "content": "<pad>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "101": {
-      "content": "[CLS]",
+    "2": {
+      "content": "</s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "102": {
-      "content": "[SEP]",
+    "3": {
+      "content": "<unk>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "103": {
-      "content": "[MASK]",
-      "lstrip": false,
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
+  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
-  "do_lower_case": true,
-  "full_tokenizer_file": null,
-  "mask_token": "[MASK]",
-  "model_max_length": 1000000000000000019884624838656,
-  "never_split": null,
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "MobileBertTokenizer",
-  "unk_token": "[UNK]"
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "max_length": 384,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 128,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "only_second",
+  "unk_token": "<unk>"
 }