Adi's training complete!

README.md

@@ -0,0 +1,80 @@
+---
+library_name: transformers
+base_model: huawei-noah/TinyBERT_General_4L_312D
+tags:
+- news-classifier
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: news_item_classifier
+  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. -->
+
+# news_item_classifier
+
+This model is a fine-tuned version of [huawei-noah/TinyBERT_General_4L_312D](https://huggingface.co/huawei-noah/TinyBERT_General_4L_312D) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.3865
+- Accuracy: 0.271
+
+## 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: 0.056
+- train_batch_size: 128
+- eval_batch_size: 128
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 20
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 4.2291        | 1.0   | 32   | 3.5369          | 0.249    |
+| 2.2138        | 2.0   | 64   | 2.1160          | 0.262    |
+| 2.3143        | 3.0   | 96   | 1.8886          | 0.262    |
+| 2.6088        | 4.0   | 128  | 2.4046          | 0.262    |
+| 2.8324        | 5.0   | 160  | 2.9637          | 0.249    |
+| 1.6379        | 6.0   | 192  | 1.8444          | 0.271    |
+| 1.8639        | 7.0   | 224  | 1.9289          | 0.218    |
+| 1.8878        | 8.0   | 256  | 1.8120          | 0.271    |
+| 1.8503        | 9.0   | 288  | 1.7120          | 0.262    |
+| 2.3268        | 10.0  | 320  | 1.7966          | 0.271    |
+| 1.5671        | 11.0  | 352  | 1.3987          | 0.271    |
+| 1.6683        | 12.0  | 384  | 1.5892          | 0.218    |
+| 1.4877        | 13.0  | 416  | 1.4932          | 0.262    |
+| 1.8511        | 14.0  | 448  | 1.7354          | 0.218    |
+| 1.5663        | 15.0  | 480  | 1.5564          | 0.262    |
+| 1.5913        | 16.0  | 512  | 1.3891          | 0.271    |
+| 1.5751        | 17.0  | 544  | 1.6062          | 0.271    |
+| 1.5021        | 18.0  | 576  | 1.4647          | 0.249    |
+| 1.3676        | 19.0  | 608  | 1.4898          | 0.262    |
+| 1.4029        | 20.0  | 640  | 1.3865          | 0.271    |
+
+
+### Framework versions
+
+- Transformers 4.57.1
+- Pytorch 2.8.0+cu126
+- Datasets 4.0.0
+- Tokenizers 0.22.1

config.json

@@ -0,0 +1,41 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "cell": {},
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "emb_size": 312,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 312,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1200,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 4,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "pre_trained": "",
+  "problem_type": "single_label_classification",
+  "structure": [],
+  "transformers_version": "4.57.1",
+  "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:ae9082dd20ea223563e7860c357e5d122a108b6ddc875b25cdc07102edc1ade0
+size 57414312

runs/Nov06_00-34-52_1393d9cd8552/events.out.tfevents.1762389295.1393d9cd8552.907.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29d2abf7cfd3e4d434558572999f10f85ac0534d8f2265d99602acca903d78cc
+size 45749

runs/Nov06_00-36-57_1393d9cd8552/events.out.tfevents.1762389418.1393d9cd8552.907.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fe4123c3cb1b7e4675642aedee319595c8b80f85b534001af63c819d5cc632c
+size 45860

runs/Nov06_00-36-57_1393d9cd8552/events.out.tfevents.1762389451.1393d9cd8552.907.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:319b5f6c90074b53fe4ce4d9ff6e094c49ec0d8e7e9caffdbb31e9441b33cd36
+size 411

runs/Nov06_00-40-24_1393d9cd8552/events.out.tfevents.1762389627.1393d9cd8552.907.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fa6706e8caf7e7534a6ce748403f5c4588fff39669ee5bcb3b2f3ecc3fdd15e
+size 79404

runs/Nov06_00-40-24_1393d9cd8552/events.out.tfevents.1762389839.1393d9cd8552.907.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55ca659b3cb318eb07eef443e69faa7d7de50377e28e8f3f5169dce232c921e3
+size 411

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,
+  "extra_special_tokens": {},
+  "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 sha256:3c9ba6c101e519aa606087e46c9e614e52562ca02addaa8176d649cf6a8de078
+size 5905