End of training

README.md

@@ -1,3 +1,58 @@
 ---
-license: mit
+tags:
+- generated_from_trainer
+model-index:
+- name: distilbert-base-fire-class
+  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. -->
+
+# distilbert-base-fire-class
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4224
+
+## 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
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.4874        | 1.0   | 343  | 0.4324          |
+| 0.3073        | 2.0   | 686  | 0.4224          |
+| 0.1658        | 3.0   | 1029 | 0.4769          |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "/home/jude/huggingface/distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "Not_related",
+    "1": "Related_and_informative",
+    "2": "Related_but_not_informative"
+  },
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "vocab_size": 30522
+}

logs/events.out.tfevents.1709883730.mintj.2969.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:597431d64ee66f2edb1aa83716aee6f53e9e1b819938ecd3da34801932ee33c8
+size 4136

logs/events.out.tfevents.1709885743.mintj.18856.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:883657ab6fd17c2c908b975af38b7de9b8da4aaba74a9343e3a3d2aea28b53c0
+size 4866

logs/events.out.tfevents.1709886154.mintj.21845.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8a8af25d5f1a62aeec9c6f7638d4d7b21c6ef18dfb8556bbffc460b06bf77d8
+size 4136

logs/events.out.tfevents.1709889271.mintj.5038.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ede91bd5c68c68e379054a6a0cb0b2e969a6f50909dc65fb825d40e77ecb109e
+size 4866

logs/events.out.tfevents.1709889461.mintj.5713.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a22d4f26ace4350580d918dd8c2c5f12c2ce61c2851e808fe1c21fe3a0c60cc2
+size 4866

logs/events.out.tfevents.1709889660.mintj.6973.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6b191ddb05992e3f1d918c01f8e4d3b4d0461fed8523c7681036026261aec78
+size 4136

logs/events.out.tfevents.1709889695.mintj.7090.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6649564195979f8287e58ad3e1b37255b07cf17fedf5e66fc7e07fbaed4d7ff
+size 4866

logs/events.out.tfevents.1709890812.mintj.8006.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88dd5e8a85499257dd2dd1c5ac86a5da5ec94fe2fc1869f24aa2fcf5ea9e8b7b
+size 4136

logs/events.out.tfevents.1709892846.mintj.9313.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdf435de111a19b1c0f8a7975559c275928779be5ad442f81263daf4f48cb8f8
+size 27244

logs/events.out.tfevents.1709893302.mintj.9313.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d83911e998416f3e5f8546c3bfbb18a7836b50be0b5dc40d70692ce957aac2ef
+size 311

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:920e74092d9449e2da24582645080c23d16dbd8c9dfbb000bc9eb638ee478538
+size 267835644

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": 1000000000000000019884624838656,
+  "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 sha256:09a54a34e54a00a3d9c6ac748b9ce59eb5e1456e87006553c128dd6cd245f465
+size 4984