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: cc-by-4.0
-base_model: deepset/roberta-base-squad2
+license: mit
+base_model: badokorach/afriqa_afroxlmr_squad_v2_060124
 tags:
 - generated_from_keras_callback
 model-index:
@@ -13,11 +13,11 @@ probably proofread and complete it, then remove this comment. -->
 
 # badokorach/roberta-base-squad2-agric-060124
 
-This model is a fine-tuned version of [deepset/roberta-base-squad2](https://huggingface.co/deepset/roberta-base-squad2) on an unknown dataset.
+This model is a fine-tuned version of [badokorach/afriqa_afroxlmr_squad_v2_060124](https://huggingface.co/badokorach/afriqa_afroxlmr_squad_v2_060124) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.3137
+- Train Loss: 2.0532
 - Validation Loss: 0.0
-- Epoch: 14
+- Epoch: 0
 
 ## Model description
 
@@ -36,28 +36,14 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 2265, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.001}
+- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 4e-05, 'decay_steps': 555, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.02}
 - training_precision: mixed_float16
 
 ### Training results
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 2.4828     | 0.0             | 0     |
-| 1.7955     | 0.0             | 1     |
-| 1.4683     | 0.0             | 2     |
-| 1.2295     | 0.0             | 3     |
-| 1.0351     | 0.0             | 4     |
-| 0.8807     | 0.0             | 5     |
-| 0.7193     | 0.0             | 6     |
-| 0.6236     | 0.0             | 7     |
-| 0.5352     | 0.0             | 8     |
-| 0.4966     | 0.0             | 9     |
-| 0.4385     | 0.0             | 10    |
-| 0.3925     | 0.0             | 11    |
-| 0.3501     | 0.0             | 12    |
-| 0.3384     | 0.0             | 13    |
-| 0.3137     | 0.0             | 14    |
+| 2.0532     | 0.0             | 0     |
 
 
 ### Framework versions
@@ -65,4 +51,4 @@ The following hyperparameters were used during training:
 - Transformers 4.35.2
 - TensorFlow 2.15.0
 - Datasets 2.16.1
-- Tokenizers 0.15.0
+- Tokenizers 0.15.1

config.json

@@ -1,29 +1,28 @@
 {
-  "_name_or_path": "deepset/roberta-base-squad2",
+  "_name_or_path": "badokorach/afriqa_afroxlmr_squad_v2_060124",
   "architectures": [
-    "RobertaForQuestionAnswering"
+    "XLMRobertaForQuestionAnswering"
   ],
   "attention_probs_dropout_prob": 0.1,
   "bos_token_id": 0,
   "classifier_dropout": null,
   "eos_token_id": 2,
-  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "initializer_range": 0.02,
   "intermediate_size": 3072,
-  "language": "english",
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 514,
-  "model_type": "roberta",
-  "name": "Roberta",
+  "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",
   "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 50265
+  "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

@@ -2,49 +2,49 @@
   "bos_token": {
     "content": "<s>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "cls_token": {
     "content": "<s>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
     "content": "</s>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "mask_token": {
     "content": "<mask>",
     "lstrip": true,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "pad_token": {
     "content": "<pad>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "sep_token": {
     "content": "</s>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:093d3c7d90855f4498a92813d45d41427e86d026a1c531b14ed1e615ef939638
-size 496513256
+oid sha256:b6d7c1aaec0ff03d7dcd558e30d9b5d9f88133293a9e9db262dd0b350765d4a5
+size 1110105320

tokenizer_config.json

@@ -1,10 +1,9 @@
 {
-  "add_prefix_space": false,
   "added_tokens_decoder": {
     "0": {
       "content": "<s>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -12,7 +11,7 @@
     "1": {
       "content": "<pad>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -20,7 +19,7 @@
     "2": {
       "content": "</s>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -28,15 +27,15 @@
     "3": {
       "content": "<unk>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "50264": {
+    "250001": {
       "content": "<mask>",
       "lstrip": true,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -45,15 +44,18 @@
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
   "cls_token": "<s>",
-  "do_lower_case": false,
   "eos_token": "</s>",
-  "errors": "replace",
-  "full_tokenizer_file": null,
   "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>",
-  "tokenizer_class": "RobertaTokenizer",
-  "trim_offsets": true,
+  "stride": 128,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "only_second",
   "unk_token": "<unk>"
 }