End of training

README.md

@@ -0,0 +1,78 @@
+---
+license: mit
+base_model: avsolatorio/GIST-large-Embedding-v0
+tags:
+- generated_from_trainer
+metrics:
+- f1
+- accuracy
+model-index:
+- name: my-clf-microsoft
+  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-microsoft
+
+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: 0.2381
+- F1: 0.5822
+- Roc Auc: 0.7634
+- Accuracy: 0.1786
+
+## 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: 16
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | F1     | Roc Auc | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|
+| No log        | 1.0   | 50   | 0.3147          | 0.0656 | 0.5250  | 0.0      |
+| No log        | 2.0   | 100  | 0.2808          | 0.2809 | 0.6082  | 0.0536   |
+| No log        | 3.0   | 150  | 0.2539          | 0.3854 | 0.6521  | 0.0357   |
+| No log        | 4.0   | 200  | 0.2451          | 0.4085 | 0.6582  | 0.0714   |
+| No log        | 5.0   | 250  | 0.2351          | 0.4365 | 0.6734  | 0.1071   |
+| No log        | 6.0   | 300  | 0.2361          | 0.4977 | 0.7133  | 0.125    |
+| No log        | 7.0   | 350  | 0.2325          | 0.5629 | 0.7433  | 0.1607   |
+| No log        | 8.0   | 400  | 0.2294          | 0.5488 | 0.7401  | 0.1964   |
+| No log        | 9.0   | 450  | 0.2336          | 0.5750 | 0.7567  | 0.1964   |
+| 0.1718        | 10.0  | 500  | 0.2342          | 0.5695 | 0.7563  | 0.1964   |
+| 0.1718        | 11.0  | 550  | 0.2354          | 0.5809 | 0.7648  | 0.1964   |
+| 0.1718        | 12.0  | 600  | 0.2349          | 0.5862 | 0.7658  | 0.1786   |
+| 0.1718        | 13.0  | 650  | 0.2390          | 0.5811 | 0.7645  | 0.1786   |
+| 0.1718        | 14.0  | 700  | 0.2367          | 0.5841 | 0.7633  | 0.2143   |
+| 0.1718        | 15.0  | 750  | 0.2376          | 0.5778 | 0.7606  | 0.1786   |
+| 0.1718        | 16.0  | 800  | 0.2381          | 0.5822 | 0.7634  | 0.1786   |
+
+
+### Framework versions
+
+- Transformers 4.38.1
+- Pytorch 2.1.2
+- Datasets 2.1.0
+- 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": "4.38.1",
+  "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 sha256:3f51868aae7f837693f1b5f727549fea9e3d637b37175c7fd35f3efa6ef3d975
+size 1340688368

runs/Mar10_11-45-53_572537bbfd13/events.out.tfevents.1710071154.572537bbfd13.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1a3c61093607ab2123081ce161f7bdef5cbf9578abecf7ceb91077e7ffb1414
+size 12540

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 sha256:02dcf46570ea201059afe314371fe1e23c9aaa1fdcb5bc7960b7582036bf622f
+size 4920