Training in progress epoch 0

README.md

@@ -1,4 +1,6 @@
 ---
+license: cc-by-4.0
+base_model: deepset/minilm-uncased-squad2
 tags:
 - generated_from_keras_callback
 model-index:
@@ -11,11 +13,11 @@ probably proofread and complete it, then remove this comment. -->
 
 # badokorach/minilm-uncased-squad2-agric-041223
 
-This model was trained from scratch on an unknown dataset.
+This model is a fine-tuned version of [deepset/minilm-uncased-squad2](https://huggingface.co/deepset/minilm-uncased-squad2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.0442
+- Train Loss: 2.5655
 - Validation Loss: 0.0
-- Epoch: 1
+- Epoch: 0
 
 ## Model description
 
@@ -41,8 +43,7 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 0.0534     | 0.0             | 0     |
-| 0.0442     | 0.0             | 1     |
+| 2.5655     | 0.0             | 0     |
 
 
 ### Framework versions

config.json

@@ -1,24 +1,25 @@
 {
-  "_name_or_path": "badokorach/minilm-uncased-squad2-agric-041223",
-  "activation": "gelu",
+  "_name_or_path": "deepset/minilm-uncased-squad2",
   "architectures": [
-    "DistilBertForQuestionAnswering"
+    "BertForQuestionAnswering"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
   "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
-  "output_past": true,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "pad_token_id": 0,
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": true,
-  "tie_weights_": true,
+  "position_embedding_type": "absolute",
   "transformers_version": "4.35.2",
-  "vocab_size": 28996
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
 }

special_tokens_map.json

@@ -1,37 +1,7 @@
 {
-  "cls_token": {
-    "content": "[CLS]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "mask_token": {
-    "content": "[MASK]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "[PAD]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "sep_token": {
-    "content": "[SEP]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "[UNK]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4fa5797fb1e15607dbfc8b39ac9ee2c1e2ea7a4b8948d137f10d49243b0a0c8
-size 260895720
+oid sha256:b1c2a33fef7d6c468c1d081a8dcf7946e51c49c5e39b399e224a950f3fca4cf0
+size 133140216

tokenizer_config.json

@@ -43,13 +43,16 @@
   },
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
-  "do_lower_case": false,
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "full_tokenizer_file": null,
   "mask_token": "[MASK]",
-  "model_max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "strip_accents": null,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "DistilBertTokenizer",
+  "tokenizer_class": "BertTokenizer",
   "unk_token": "[UNK]"
 }