Initial upload of music entity classification model

README.md

@@ -1,3 +1,135 @@
----
-license: apache-2.0
----
+---
+library_name: transformers
+license: apache-2.0
+base_model: hfl/chinese-roberta-wwm-ext
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: music_ent_classification
+  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. -->
+
+# music_ent_classification
+
+This model is a fine-tuned version of [hfl/chinese-roberta-wwm-ext](https://huggingface.co/hfl/chinese-roberta-wwm-ext) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1230
+- Accuracy: 0.9662
+
+## 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: 32
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- total_train_batch_size: 128
+- total_eval_batch_size: 32
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 5.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.4408        | 1.0   | 54   | 0.1763          | 0.9459   |
+| 0.1407        | 2.0   | 108  | 0.1221          | 0.9628   |
+| 0.0762        | 3.0   | 162  | 0.1123          | 0.9640   |
+| 0.0563        | 4.0   | 216  | 0.1226          | 0.9718   |
+| 0.0423        | 5.0   | 270  | 0.1230          | 0.9662   |
+
+
+### Framework versions
+
+- Transformers 4.57.5
+- Pytorch 2.6.0+cu124
+- Datasets 2.19.0
+- Tokenizers 0.22.2
+
+
+### 训练
+```
+export WANDB_MODE=disabled # 禁用交互式登录
+export CUDA_VISIBLE_DEVICES=0,1,2,3 # 确保识别 4 张 V100
+# 变量定义
+model="hfl/chinese-roberta-wwm-ext"
+transformers_root="transformers"
+
+output_dir="./models/music_ent_classification"
+mkdir ${output_dir} -p
+
+# 使用 torchrun 启动
+torchrun --nproc_per_node=4 \
+    ${transformers_root}/examples/pytorch/text-classification/run_classification.py \
+    --model_name_or_path ${model} \
+    --train_file "./data/*.train.json" \
+    --validation_file "./data/*.test.json" \
+    --trust_remote_code True \
+    --do_train \
+    --do_eval \
+    --shuffle_train_dataset \
+    --metric_name accuracy \
+    --text_column_name sentence1 \
+    --label_column_name label \
+    --max_seq_length 256 \
+    --per_device_train_batch_size 32 \
+    --learning_rate 2e-5 \
+    --num_train_epochs 5 \
+    --logging_steps 50 \
+    --save_strategy epoch \
+    --eval_strategy epoch \
+    --fp16 True \
+    --output_dir ${output_dir} \
+    --overwrite_output_dir 
+```
+
+### 推理
+
+```
+# 启动分布式推理
+torchrun --nproc_per_node=$(echo $CUDA_DEVICES | tr ',' '\n' | wc -l) \
+    transformers/examples/pytorch/text-classification/run_classification.py \
+    --model_name_or_path "${MODEL_PATH}" \
+    --train_file "${TRAIN_DATA}" \
+    --validation_file "${TRAIN_DATA}" \
+    --test_file "${INPUT_FILE}" \
+    --text_column_name "sentence1" \
+    --label_column_name "label" \
+    --do_predict \
+    --max_seq_length 128 \
+    --per_device_eval_batch_size 256 \
+    --output_dir "${OUTPUT_DIR}" \
+    --fp16 True \
+    --trust_remote_code True \
+    --overwrite_output_dir
+
+if [ $? -eq 0 ]; then
+    echo "✅ [Infer] 推理完成。"
+else
+    echo "❌ [Infer] 推理失败。"
+    exit 1
+fi
+```

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.9662162162162162,
+    "eval_loss": 0.1229998990893364,
+    "eval_runtime": 0.6589,
+    "eval_samples": 888,
+    "eval_samples_per_second": 1347.673,
+    "eval_steps_per_second": 42.494,
+    "total_flos": 4546681584484352.0,
+    "train_loss": 0.1416260372709345,
+    "train_runtime": 63.0434,
+    "train_samples": 6900,
+    "train_samples_per_second": 547.242,
+    "train_steps_per_second": 4.283
+}

config.json

@@ -0,0 +1,47 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "dtype": "float32",
+  "finetuning_task": "text-classification",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Artist",
+    "1": "Event",
+    "2": "Group",
+    "3": "None",
+    "4": "Work"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Artist": 0,
+    "Event": 1,
+    "Group": 2,
+    "None": 3,
+    "Work": 4
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "transformers_version": "4.57.5",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 21128
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.9662162162162162,
+    "eval_loss": 0.1229998990893364,
+    "eval_runtime": 0.6589,
+    "eval_samples": 888,
+    "eval_samples_per_second": 1347.673,
+    "eval_steps_per_second": 42.494
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f81dac2e12d926959a3d38ac532d770c4f94d30901a67d02e22e315b8856202e
+size 409109468

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "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
+  }
+}

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.0,
+    "total_flos": 4546681584484352.0,
+    "train_loss": 0.1416260372709345,
+    "train_runtime": 63.0434,
+    "train_samples": 6900,
+    "train_samples_per_second": 547.242,
+    "train_steps_per_second": 4.283
+}

trainer_state.json

@@ -0,0 +1,123 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 270,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.9259259259259259,
+      "grad_norm": 2.8517868518829346,
+      "learning_rate": 1.6370370370370374e-05,
+      "loss": 0.4408,
+      "step": 50
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9459459459459459,
+      "eval_loss": 0.1763220876455307,
+      "eval_runtime": 0.5083,
+      "eval_samples_per_second": 1747.017,
+      "eval_steps_per_second": 55.086,
+      "step": 54
+    },
+    {
+      "epoch": 1.8518518518518519,
+      "grad_norm": 1.7455177307128906,
+      "learning_rate": 1.2666666666666667e-05,
+      "loss": 0.1407,
+      "step": 100
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9628378378378378,
+      "eval_loss": 0.1221194714307785,
+      "eval_runtime": 0.6023,
+      "eval_samples_per_second": 1474.32,
+      "eval_steps_per_second": 46.488,
+      "step": 108
+    },
+    {
+      "epoch": 2.7777777777777777,
+      "grad_norm": 3.1013050079345703,
+      "learning_rate": 8.962962962962963e-06,
+      "loss": 0.0762,
+      "step": 150
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.963963963963964,
+      "eval_loss": 0.11229722201824188,
+      "eval_runtime": 0.6443,
+      "eval_samples_per_second": 1378.158,
+      "eval_steps_per_second": 43.455,
+      "step": 162
+    },
+    {
+      "epoch": 3.7037037037037037,
+      "grad_norm": 1.3716905117034912,
+      "learning_rate": 5.259259259259259e-06,
+      "loss": 0.0563,
+      "step": 200
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9718468468468469,
+      "eval_loss": 0.12264640629291534,
+      "eval_runtime": 0.6481,
+      "eval_samples_per_second": 1370.16,
+      "eval_steps_per_second": 43.203,
+      "step": 216
+    },
+    {
+      "epoch": 4.62962962962963,
+      "grad_norm": 0.5899084806442261,
+      "learning_rate": 1.5555555555555558e-06,
+      "loss": 0.0423,
+      "step": 250
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9662162162162162,
+      "eval_loss": 0.1229998990893364,
+      "eval_runtime": 0.6595,
+      "eval_samples_per_second": 1346.563,
+      "eval_steps_per_second": 42.459,
+      "step": 270
+    },
+    {
+      "epoch": 5.0,
+      "step": 270,
+      "total_flos": 4546681584484352.0,
+      "train_loss": 0.1416260372709345,
+      "train_runtime": 63.0434,
+      "train_samples_per_second": 547.242,
+      "train_steps_per_second": 4.283
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 270,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "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": 4546681584484352.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:666711e834597c1913fb306f6b190201f3dff2fb420c5ad8cb7dd0f8dab59c59
+size 5496