Thijs040/ERNIE_finetuned

README.md

@@ -0,0 +1,64 @@
+---
+base_model: nghuyong/ernie-2.0-large-en
+tags:
+- generated_from_trainer
+metrics:
+- spearmanr
+model-index:
+- name: ernie-2.0-large-en-finetuned-stsb
+  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. -->
+
+# ernie-2.0-large-en-finetuned-stsb
+
+This model is a fine-tuned version of [nghuyong/ernie-2.0-large-en](https://huggingface.co/nghuyong/ernie-2.0-large-en) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3323
+- Pearson: 0.9239
+- Spearmanr: 0.9222
+
+## 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: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Pearson | Spearmanr |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:---------:|
+| No log        | 1.0   | 360  | 0.4713          | 0.9092  | 0.9111    |
+| 0.5167        | 2.0   | 720  | 0.4516          | 0.9180  | 0.9179    |
+| 0.2           | 3.0   | 1080 | 0.3402          | 0.9238  | 0.9211    |
+| 0.2           | 4.0   | 1440 | 0.3452          | 0.9238  | 0.9226    |
+| 0.1002        | 5.0   | 1800 | 0.3323          | 0.9239  | 0.9222    |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "nghuyong/ernie-2.0-large-en",
+  "architectures": [
+    "ErnieForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 512,
+  "model_type": "ernie",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "regression",
+  "task_type_vocab_size": 3,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 4,
+  "use_cache": true,
+  "use_task_id": false,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da72ad1fa25bcfdc899b0a26033dc77119ef9635430a07542fa937ce1085107b
+size 1340627220

runs/Mar05_13-37-33_27fc650b7055/events.out.tfevents.1709645860.27fc650b7055.2197.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f866283b7db51055a3192f1936356796ea40f43656a8c5cdd471849a67d6f5b
+size 7576

runs/Mar05_13-37-33_27fc650b7055/events.out.tfevents.1709647387.27fc650b7055.2197.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd3e4e3cc9d3fb1c0c7a5e116ae57be10b8a803ca7f74e6bc5e9d0994a4f8811
+size 463

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 +1,58 @@
+{
+  "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": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "full_tokenizer_file": null,
+  "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": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88fb156c883bf31446869b723f965ba65029bc48208823e947b4fdb50485f15c
+size 4920