End of training

README.md

@@ -0,0 +1,65 @@
+---
+license: apache-2.0
+base_model: toastynews/electra-hongkongese-small-discriminator
+tags:
+- generated_from_trainer
+model-index:
+- name: electra_hongkongese_small_pos_wiki_lihkg_cc100
+  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. -->
+
+# electra_hongkongese_small_pos_wiki_lihkg_cc100
+
+This model is a fine-tuned version of [toastynews/electra-hongkongese-small-discriminator](https://huggingface.co/toastynews/electra-hongkongese-small-discriminator) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1796
+
+## 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: 2e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch  | Step  | Validation Loss |
+|:-------------:|:------:|:-----:|:---------------:|
+| 0.232         | 0.3000 | 6123  | 0.2192          |
+| 0.2465        | 0.6000 | 12246 | 0.2052          |
+| 0.2396        | 0.9000 | 18369 | 0.1906          |
+| 0.2128        | 1.2001 | 24492 | 0.1897          |
+| 0.2007        | 1.5001 | 30615 | 0.1883          |
+| 0.2019        | 1.8001 | 36738 | 0.1832          |
+| 0.1864        | 2.1001 | 42861 | 0.1813          |
+| 0.2051        | 2.4001 | 48984 | 0.1799          |
+| 0.1837        | 2.7001 | 55107 | 0.1796          |
+
+
+### Framework versions
+
+- Transformers 4.44.0
+- Pytorch 2.2.1
+- Datasets 2.21.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,68 @@
+{
+  "_name_or_path": "toastynews/electra-hongkongese-small-discriminator",
+  "architectures": [
+    "ElectraForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 128,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
+  "id2label": {
+    "0": "ADJ",
+    "1": "ADP",
+    "2": "ADV",
+    "3": "AUX",
+    "4": "CCONJ",
+    "5": "DET",
+    "6": "INTJ",
+    "7": "NOUN",
+    "8": "NUM",
+    "9": "PART",
+    "10": "PRON",
+    "11": "PROPN",
+    "12": "PUNCT",
+    "13": "SCONJ",
+    "14": "SYM",
+    "15": "VERB",
+    "16": "X"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "label2id": {
+    "ADJ": 0,
+    "ADP": 1,
+    "ADV": 2,
+    "AUX": 3,
+    "CCONJ": 4,
+    "DET": 5,
+    "INTJ": 6,
+    "NOUN": 7,
+    "NUM": 8,
+    "PART": 9,
+    "PRON": 10,
+    "PROPN": 11,
+    "PUNCT": 12,
+    "SCONJ": 13,
+    "SYM": 14,
+    "VERB": 15,
+    "X": 16
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37e99457433c0b72073f5a0bf0703fe26750a92deee6d859dc63dbde6313196e
+size 53705988

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 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "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": "ElectraTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6aed4c1b5dc817d711d7086223425faeecf9bbf83ae17ff364b6d098a0ca82a
+size 5176