Upload 12 files

README.md

@@ -1,3 +1,53 @@
----
-license: mit
----
+---
+library_name: transformers
+license: apache-2.0
+base_model: toastynews/electra-hongkongese-small-discriminator
+tags:
+- generated_from_trainer
+model-index:
+- name: electra_small_hkcancor_multi
+  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_small_hkcancor_multi
+
+This model is a fine-tuned version of [toastynews/electra-hongkongese-small-discriminator](https://huggingface.co/toastynews/electra-hongkongese-small-discriminator) on an unknown dataset.
+
+## 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: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.45.0.dev0
+- Pytorch 2.4.0
+- Datasets 2.20.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 71142932377296.0,
+    "train_loss": 0.08043386847769664,
+    "train_runtime": 787.9023,
+    "train_samples": 12290,
+    "train_samples_per_second": 46.795,
+    "train_steps_per_second": 5.852
+}

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "toastynews/electra-hongkongese-small-discriminator",
+  "architectures": [
+    "ElectraForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 128,
+  "finetuning_task": "ner",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
+  "id2label": {
+    "0": "D",
+    "1": "I",
+    "2": "P",
+    "3": "S"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "label2id": {
+    "D": 0,
+    "I": 1,
+    "P": 2,
+    "S": 3
+  },
+  "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": "4.45.0.dev0",
+  "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:f6b5774c8007e5a07e3a4d7cf49cd507453f1be28864a21a98872df07233d84b
+size 53692616

runs/Sep06_10-19-14_192.168.2.6/events.out.tfevents.1725589162.192.168.2.6.80068.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:612acf83259db6ebdefe68a01b32d75598823b0135b345eb0e4f1fad4f98618c
+size 7583

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]"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 71142932377296.0,
+    "train_loss": 0.08043386847769664,
+    "train_runtime": 787.9023,
+    "train_samples": 12290,
+    "train_samples_per_second": 46.795,
+    "train_steps_per_second": 5.852
+}

trainer_state.json

@@ -0,0 +1,105 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 4611,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.32530904359141183,
+      "grad_norm": 0.7525109052658081,
+      "learning_rate": 4.4578182606809806e-05,
+      "loss": 0.2922,
+      "step": 500
+    },
+    {
+      "epoch": 0.6506180871828237,
+      "grad_norm": 1.5843052864074707,
+      "learning_rate": 3.91563652136196e-05,
+      "loss": 0.1019,
+      "step": 1000
+    },
+    {
+      "epoch": 0.9759271307742355,
+      "grad_norm": 1.2410870790481567,
+      "learning_rate": 3.3734547820429406e-05,
+      "loss": 0.0743,
+      "step": 1500
+    },
+    {
+      "epoch": 1.3012361743656473,
+      "grad_norm": 1.6869269609451294,
+      "learning_rate": 2.8312730427239213e-05,
+      "loss": 0.0566,
+      "step": 2000
+    },
+    {
+      "epoch": 1.6265452179570592,
+      "grad_norm": 0.7089857459068298,
+      "learning_rate": 2.2890913034049014e-05,
+      "loss": 0.0514,
+      "step": 2500
+    },
+    {
+      "epoch": 1.951854261548471,
+      "grad_norm": 1.388731837272644,
+      "learning_rate": 1.7469095640858817e-05,
+      "loss": 0.05,
+      "step": 3000
+    },
+    {
+      "epoch": 2.277163305139883,
+      "grad_norm": 2.429743528366089,
+      "learning_rate": 1.204727824766862e-05,
+      "loss": 0.0374,
+      "step": 3500
+    },
+    {
+      "epoch": 2.6024723487312946,
+      "grad_norm": 3.7513585090637207,
+      "learning_rate": 6.625460854478421e-06,
+      "loss": 0.0346,
+      "step": 4000
+    },
+    {
+      "epoch": 2.9277813923227067,
+      "grad_norm": 0.6153927445411682,
+      "learning_rate": 1.203643461288224e-06,
+      "loss": 0.0363,
+      "step": 4500
+    },
+    {
+      "epoch": 3.0,
+      "step": 4611,
+      "total_flos": 71142932377296.0,
+      "train_loss": 0.08043386847769664,
+      "train_runtime": 787.9023,
+      "train_samples_per_second": 46.795,
+      "train_steps_per_second": 5.852
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4611,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 71142932377296.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83defb9a5a855f0bda1b5bcf688b09eb8920d57be2f0e6a30c12811b9d33cffc
+size 5240