Training in progress epoch 0

README.md

@@ -1,6 +1,6 @@
 ---
-license: mit
-base_model: Davlan/afro-xlmr-small
+license: cc-by-4.0
+base_model: deepset/roberta-base-squad2
 tags:
 - generated_from_keras_callback
 model-index:
@@ -13,9 +13,9 @@ probably proofread and complete it, then remove this comment. -->
 
 # badokorach/afro-xlmr-base
 
-This model is a fine-tuned version of [Davlan/afro-xlmr-small](https://huggingface.co/Davlan/afro-xlmr-small) on an unknown dataset.
+This model is a fine-tuned version of [deepset/roberta-base-squad2](https://huggingface.co/deepset/roberta-base-squad2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.4984
+- Train Loss: 2.3092
 - Validation Loss: 0.0
 - Epoch: 0
 
@@ -36,19 +36,19 @@ 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': 171, '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': 2e-05, 'decay_steps': 1950, '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': 0.02}
 - training_precision: mixed_float16
 
 ### Training results
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 0.4984     | 0.0             | 0     |
+| 2.3092     | 0.0             | 0     |
 
 
 ### Framework versions
 
-- Transformers 4.32.1
+- Transformers 4.33.0
 - TensorFlow 2.12.0
 - Datasets 2.14.4
 - Tokenizers 0.13.3

config.json

@@ -1,28 +1,29 @@
 {
-  "_name_or_path": "Davlan/afro-xlmr-small",
+  "_name_or_path": "deepset/roberta-base-squad2",
   "architectures": [
-    "XLMRobertaForQuestionAnswering"
+    "RobertaForQuestionAnswering"
   ],
   "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": "xlm-roberta",
+  "model_type": "roberta",
+  "name": "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": "4.32.1",
+  "transformers_version": "4.33.0",
   "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 70611
+  "vocab_size": 50265
 }

special_tokens_map.json

@@ -1,7 +1,25 @@
 {
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
   "mask_token": {
     "content": "<mask>",
     "lstrip": true,
@@ -9,7 +27,25 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "unk_token": "<unk>"
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bc20d0a69e04f56528aed767023cc91f01bc54de498fcabb3bda296199cc53a
-size 559016168
+oid sha256:04538cb4e6ffb14d5f91407d8261b47332be122b6884eb280c5681237c6f620d
+size 496513256

tokenizer_config.json

@@ -1,8 +1,33 @@
 {
-  "bos_token": "<s>",
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
   "clean_up_tokenization_spaces": true,
-  "cls_token": "<s>",
-  "eos_token": "</s>",
+  "cls_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "do_lower_case": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "full_tokenizer_file": null,
   "mask_token": {
     "__type": "AddedToken",
     "content": "<mask>",
@@ -11,10 +36,31 @@
     "rstrip": false,
     "single_word": false
   },
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "sp_model_kwargs": {},
-  "tokenizer_class": "XLMRobertaTokenizer",
-  "unk_token": "<unk>"
+  "model_max_length": 512,
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
 }