sohaib/tinyBert-classifier-v0.5

README.md

@@ -0,0 +1,65 @@
+---
+library_name: transformers
+base_model: huawei-noah/TinyBERT_General_4L_312D
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: train_dir
+  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. -->
+
+# train_dir
+
+This model is a fine-tuned version of [huawei-noah/TinyBERT_General_4L_312D](https://huggingface.co/huawei-noah/TinyBERT_General_4L_312D) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2060
+- Accuracy: 1.0
+
+## 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: 2e-05
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 6
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| No log        | 1.0   | 29   | 0.6396          | 1.0      |
+| No log        | 2.0   | 58   | 0.5003          | 1.0      |
+| No log        | 3.0   | 87   | 0.3552          | 1.0      |
+| No log        | 4.0   | 116  | 0.2633          | 1.0      |
+| No log        | 5.0   | 145  | 0.2191          | 1.0      |
+| No log        | 6.0   | 174  | 0.2060          | 1.0      |
+
+
+### Framework versions
+
+- Transformers 4.49.0.dev0
+- Pytorch 2.5.1+cu121
+- Datasets 3.2.0
+- Tokenizers 0.21.0

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "huawei-noah/TinyBERT_General_4L_312D",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "cell": {},
+  "classifier_dropout": null,
+  "emb_size": 312,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 312,
+  "id2label": {
+    "0": "history_of_cars",
+    "1": "sleep_science"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1200,
+  "label2id": {
+    "history_of_cars": 0,
+    "sleep_science": 1
+  },
+  "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": [],
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0.dev0",
+  "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 sha256:761c4d05b9764da56b5f12e560ffa481074fd6ac6a8546250f5afffaa365e12d
+size 57411808

runs/Jan17_00-22-17_5f4211046702/events.out.tfevents.1737073340.5f4211046702.967.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3d907910dcefe1e5d91650a72529ace60f2e2a103ef0e01ed2067a609cbb542
+size 6826

runs/Jan17_00-22-17_5f4211046702/events.out.tfevents.1737073489.5f4211046702.967.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:841a713aa93c5744f43ed4d4d89a0ceeccc73b83b1cc6f2f2854795736b84d39
+size 405

runs/Jan17_00-26-45_5f4211046702/events.out.tfevents.1737073608.5f4211046702.967.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b1a55e1dc18e66ec985652c1ed8c24ddc7e36ea6481689246f13c4b89bf8d11
+size 7226

runs/Jan17_00-28-53_5f4211046702/events.out.tfevents.1737073736.5f4211046702.967.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b2352a034a145d47accdd55b7724ba7eaf9ac03296575ee0cd5c5327a3c96f5
+size 5527

runs/Jan17_00-29-32_5f4211046702/events.out.tfevents.1737073774.5f4211046702.967.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47c6fc14a6667960c811dca624ee341e67c4478b3fa9f51cd4050e373559b6ff
+size 7478

runs/Jan17_00-31-45_5f4211046702/events.out.tfevents.1737073905.5f4211046702.967.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da4a3f6784efe5b21581df384bbfbd553437acb4164d46ec5a6e71225b4d7c09
+size 7478

runs/Jan17_00-31-45_5f4211046702/events.out.tfevents.1737073978.5f4211046702.967.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d474e1436c26ffc8020a44ba9dd2f65b899d2a1c32dc302017325b68c0505ed8
+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:e96e01ba00108ea0c1787d2c613a392daaca1da81bb4931868c461327a592c87
+size 5304