End of training

README.md

@@ -0,0 +1,52 @@
+---
+tags:
+- generated_from_trainer
+model-index:
+- name: gttbsc_distilbert-ft
+  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. -->
+
+# gttbsc_distilbert-ft
+
+This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
+
+## 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: 0.00043
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 20
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.2
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,19 @@
+{
+  "architectures": [
+    "SingleEmbeddingSentenceClassifier"
+  ],
+  "backbone": "distilbert-base-uncased",
+  "backbone_freezed": false,
+  "backbone_kwargs": {
+    "load_in_4bit": false
+  },
+  "classifier_dropout": 0.3,
+  "dropout": 0.3,
+  "embedding_strategy": "self-att",
+  "hidden_size": 768,
+  "labels": 18,
+  "model_type": "single-embedding-sentence-classifier",
+  "multilabel": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af3b7fb82340041faf6a54865f059859246610cf0b83981bcb99f172b82784ae
+size 267884860

runs/Jun09_18-06-56_0f1efd14a13d/events.out.tfevents.1717956418.0f1efd14a13d.4024.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c7aa21b2843efa2483258dbdf6eff8d0ddee702911c9ae6543817bff7258ae3
+size 4655

runs/Jun09_18-07-35_0f1efd14a13d/events.out.tfevents.1717956456.0f1efd14a13d.4024.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9363590fd6bb3b254a86edf06c8e5644b398e502a261d60260ab193df3b2f96d
+size 4655

runs/Jun09_18-07-57_0f1efd14a13d/events.out.tfevents.1717956478.0f1efd14a13d.4024.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:412ab832dd95603aec1e3f3a6c7b5bd92b6fe6792bc89a7576f89ee15f89e5f0
+size 38151

runs/Jun09_18-07-57_0f1efd14a13d/events.out.tfevents.1717959875.0f1efd14a13d.4024.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1164c55afc9a159ea8806e36773849516349d118dd0b4640e5f1a17b22b0997
+size 1548

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": "[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_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6335c11f49ef7503b83cc02e775ef65e0e4e99a5002969f6d539e01df1feaf88
+size 5176