ernieMtask2

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: 1.3594
+- F1: 0.8030
+
+## 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     |
+|:-------------:|:-----:|:-----:|:---------------:|:------:|
+| 0.818         | 1.0   | 1469  | 0.7237          | 0.7282 |
+| 0.5339        | 2.0   | 2938  | 0.6703          | 0.7587 |
+| 0.3487        | 3.0   | 4407  | 0.7401          | 0.7683 |
+| 0.2386        | 4.0   | 5876  | 0.7384          | 0.7901 |
+| 0.143         | 5.0   | 7345  | 1.0072          | 0.7736 |
+| 0.0819        | 6.0   | 8814  | 1.0898          | 0.7979 |
+| 0.0438        | 7.0   | 10283 | 1.3199          | 0.7948 |
+| 0.0166        | 8.0   | 11752 | 1.3594          | 0.8030 |
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.2
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,43 @@
+{
+  "_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": "A",
+    "1": "B",
+    "2": "C",
+    "3": "D",
+    "4": "E",
+    "5": "F"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "A": 0,
+    "B": 1,
+    "C": 2,
+    "D": 3,
+    "E": 4,
+    "F": 5
+  },
+  "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 sha256:755239b9571f83a287c0ea4ef83c1c226313bd8a04e26b6b059243729cdd06e4
+size 1112213544

runs/Jun10_13-42-04_76ea5d7bb620/events.out.tfevents.1718026925.76ea5d7bb620.1920.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dd8bab4d9d998017b981c9821c4bd0a37f2c93ca99b107f218a472da8819a52
+size 12805

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 sha256:465296e11553000d239c71bb397af01f9a01423befd6580ad09f8f0a1357d194
+size 5176