Sohaib/tinyBert-router-v0.2

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: tinyBert-router-v0.1
+  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. -->
+
+# tinyBert-router-v0.1
+
+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: 0.2489
+- 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   | 0.6853          | 0.52     |
+| No log        | 2.0   | 58   | 0.5893          | 0.96     |
+| No log        | 3.0   | 87   | 0.4202          | 1.0      |
+| No log        | 4.0   | 116  | 0.3176          | 1.0      |
+| No log        | 5.0   | 145  | 0.2649          | 1.0      |
+| No log        | 6.0   | 174  | 0.2489          | 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:b22e1790718c39d132e0640a1bd4cf92b56106465675177086748eb2a7e58832
+size 57411808

runs/Jan17_01-15-27_5f4211046702/events.out.tfevents.1737076534.5f4211046702.967.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b72d388675ed4d7070b43b09e903517323e3d12914de29db05b5092ece931e3e
+size 6525

runs/Jan17_01-22-14_5f4211046702/events.out.tfevents.1737076944.5f4211046702.15036.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e4c619894c906fbee07c7028a204031a2d9e45ec89f3085d7cffdb8c107b7d0
+size 6880

runs/Jan17_01-23-38_5f4211046702/events.out.tfevents.1737077020.5f4211046702.15036.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ad640a167d54ffa36fb98ff4d90a3497c2e8b4da58cfb936cf193e924c6e6b8
+size 7855

runs/Jan17_01-26-40_5f4211046702/events.out.tfevents.1737077203.5f4211046702.16743.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edecbe796619d1866a38cc0c4c0280332c395708a062f03e272da3733f5a63a8
+size 7532

runs/Jan17_01-26-40_5f4211046702/events.out.tfevents.1737077272.5f4211046702.16743.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee788413035597e196c41bd93077ec3bd0ce5b036e9b8905750bfa9f50456358
+size 734

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:caaa57ce0ad44d1ba3ca6a35901223f908c81095efceb3b6265fe600f10445d3
+size 5368