textificationErnieM

README.md

@@ -0,0 +1,70 @@
+---
+license: apache-2.0
+base_model: susnato/ernie-m-base_pytorch
+tags:
+- generated_from_trainer
+metrics:
+- f1
+model-index:
+- name: Model
+  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. -->
+
+# Model
+
+This model is a fine-tuned version of [susnato/ernie-m-base_pytorch](https://huggingface.co/susnato/ernie-m-base_pytorch) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6189
+- F1: 0.9294
+
+## 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
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 8
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | F1     |
+|:-------------:|:-----:|:-----:|:---------------:|:------:|
+| 0.2019        | 1.0   | 1500  | 0.1825          | 0.9304 |
+| 0.1199        | 2.0   | 3000  | 0.3103          | 0.8986 |
+| 0.085         | 3.0   | 4500  | 0.2546          | 0.9268 |
+| 0.0516        | 4.0   | 6000  | 0.3140          | 0.9387 |
+| 0.0281        | 5.0   | 7500  | 0.6603          | 0.9022 |
+| 0.0142        | 6.0   | 9000  | 0.8612          | 0.8931 |
+| 0.0068        | 7.0   | 10500 | 0.5700          | 0.9332 |
+| 0.002         | 8.0   | 12000 | 0.6189          | 0.9294 |
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.2
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "susnato/ernie-m-base_pytorch",
+  "act_dropout": 0.0,
+  "architectures": [
+    "ErnieMForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "generated",
+    "1": "human"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "generated": 0,
+    "human": 1
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "ernie_m",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "paddlenlp_version": null,
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 16,
+  "vocab_size": 250002
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f13c6bae945867fd236d7e830b1ffaa8ee8c3427ffe6472d4c86849b0b5228e
+size 1112201232

runs/Jun09_19-45-14_7e0f4658e5f3/events.out.tfevents.1717962315.7e0f4658e5f3.1241.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5016bcf64d0627cc82a7d2b7a25651f4aa950934b79c03dc95c92f3f973e97dd
+size 12936

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

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 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "encoding": "utf8",
+  "mask_token": "[MASK]",
+  "model_max_length": 514,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "ErnieMTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9a6321fc8d2b6ba813ba1a0e84b9b4d745cfa9607ee6cc7f08959ba7580cc6c
+size 5176