ashishpatel26/span-marker-bert-base-fewnerd-coarse-super

README.md

@@ -0,0 +1,70 @@
+---
+base_model: ''
+tags:
+- generated_from_trainer
+datasets:
+- few-nerd
+model-index:
+- name: span-marker-bert-base-fewnerd-coarse-super
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# span-marker-bert-base-fewnerd-coarse-super
+
+This model is a fine-tuned version of [](https://huggingface.co/) on the few-nerd dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0191
+- Overall Precision: 0.7817
+- Overall Recall: 0.7683
+- Overall F1: 0.7749
+- Overall Accuracy: 0.9394
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:-----------------:|:--------------:|:----------:|:----------------:|
+| 0.0393        | 0.16  | 200  | 0.0348          | 0.7084            | 0.6377         | 0.6712     | 0.9082           |
+| 0.0311        | 0.33  | 400  | 0.0233          | 0.7744            | 0.6994         | 0.7350     | 0.9225           |
+| 0.0242        | 0.49  | 600  | 0.0214          | 0.7725            | 0.7293         | 0.7503     | 0.9323           |
+| 0.0238        | 0.65  | 800  | 0.0204          | 0.7744            | 0.7663         | 0.7703     | 0.9359           |
+| 0.0212        | 0.81  | 1000 | 0.0193          | 0.7878            | 0.7617         | 0.7746     | 0.9379           |
+| 0.0181        | 0.98  | 1200 | 0.0190          | 0.7830            | 0.7671         | 0.7750     | 0.9391           |
+
+
+### Framework versions
+
+- Transformers 4.32.1
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.4
+- Tokenizers 0.13.3

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<end>": 28997,
+  "<start>": 28996
+}

config.json

@@ -0,0 +1,113 @@
+{
+  "architectures": [
+    "SpanMarkerModel"
+  ],
+  "encoder": {
+    "_name_or_path": "bert-base-cased",
+    "add_cross_attention": false,
+    "architectures": [
+      "BertForMaskedLM"
+    ],
+    "attention_probs_dropout_prob": 0.1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": null,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "gradient_checkpointing": false,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 768,
+    "id2label": {
+      "0": "O",
+      "1": "art",
+      "2": "building",
+      "3": "event",
+      "4": "location",
+      "5": "organization",
+      "6": "other",
+      "7": "person",
+      "8": "product"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "O": 0,
+      "art": 1,
+      "building": 2,
+      "event": 3,
+      "location": 4,
+      "organization": 5,
+      "other": 6,
+      "person": 7,
+      "product": 8
+    },
+    "layer_norm_eps": 1e-12,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 512,
+    "min_length": 0,
+    "model_type": "bert",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 0,
+    "position_embedding_type": "absolute",
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.32.1",
+    "type_vocab_size": 2,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 28998
+  },
+  "entity_max_length": 8,
+  "marker_max_length": 128,
+  "max_next_context": null,
+  "max_prev_context": null,
+  "model_max_length": 256,
+  "model_max_length_default": 512,
+  "model_type": "span-marker",
+  "span_marker_version": "1.3.0",
+  "torch_dtype": "float32",
+  "trained_with_document_context": false,
+  "transformers_version": "4.32.1",
+  "vocab_size": 28998
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfd5c0de7229e20656754f7897d12042a4764103766b4afe854188c28c878750
+size 433371505

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "add_prefix_space": true,
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 256,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:661a4b70bb40184e29d4e53532079ff7084025a0ee7a7e5e3d8cd0c22ba43f87
+size 4091