End of training

README.md

@@ -0,0 +1,74 @@
+---
+license: mit
+base_model: avsolatorio/GIST-large-Embedding-v0
+tags:
+- generated_from_trainer
+metrics:
+- f1
+model-index:
+- name: my-clf
+  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. -->
+
+# my-clf
+
+This model is a fine-tuned version of [avsolatorio/GIST-large-Embedding-v0](https://huggingface.co/avsolatorio/GIST-large-Embedding-v0) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1824
+- F1: 0.6653
+
+## 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: 15
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 0.1488        | 1.0   | 100  | 1.1930          | 0.6355 |
+| 0.1232        | 2.0   | 200  | 0.9133          | 0.6473 |
+| 0.0797        | 3.0   | 300  | 1.0238          | 0.6603 |
+| 0.0522        | 4.0   | 400  | 0.9822          | 0.6713 |
+| 0.0366        | 5.0   | 500  | 1.0208          | 0.6664 |
+| 0.0252        | 6.0   | 600  | 0.9856          | 0.6755 |
+| 0.0199        | 7.0   | 700  | 1.0628          | 0.6665 |
+| 0.0174        | 8.0   | 800  | 1.0667          | 0.6651 |
+| 0.0155        | 9.0   | 900  | 1.0934          | 0.6664 |
+| 0.0141        | 10.0  | 1000 | 1.1478          | 0.6676 |
+| 0.0131        | 11.0  | 1100 | 1.1644          | 0.6707 |
+| 0.0124        | 12.0  | 1200 | 1.1661          | 0.6638 |
+| 0.0122        | 13.0  | 1300 | 1.1781          | 0.6648 |
+| 0.0118        | 14.0  | 1400 | 1.1810          | 0.6664 |
+| 0.0116        | 15.0  | 1500 | 1.1824          | 0.6653 |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.1.0+cu118
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,67 @@
+{
+  "_name_or_path": "avsolatorio/GIST-large-Embedding-v0",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "CE",
+    "1": "ENV",
+    "2": "BME",
+    "3": "PE",
+    "4": "METAL",
+    "5": "ME",
+    "6": "EE",
+    "7": "CPE",
+    "8": "OPTIC",
+    "9": "NANO",
+    "10": "CHE",
+    "11": "MATENG",
+    "12": "AGRI",
+    "13": "EDU",
+    "14": "IE",
+    "15": "SAFETY",
+    "16": "MATH",
+    "17": "MATSCI"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "AGRI": 12,
+    "BME": 2,
+    "CE": 0,
+    "CHE": 10,
+    "CPE": 7,
+    "EDU": 13,
+    "EE": 6,
+    "ENV": 1,
+    "IE": 14,
+    "MATENG": 11,
+    "MATH": 16,
+    "MATSCI": 17,
+    "ME": 5,
+    "METAL": 4,
+    "NANO": 9,
+    "OPTIC": 8,
+    "PE": 3,
+    "SAFETY": 15
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:765ae656981361b3e6e7475604f55c236d72e6f028eadbf7e75633b9de2796a9
+size 1340688368

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 +1,57 @@
+{
+  "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,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "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:d0c810b0b81ed7a018d18992203047dc4b7fed32d287d4d728173b5d99bf6e25
+size 4856