BiLSTM test 1

README.md

@@ -0,0 +1,106 @@
+---
+license: mit
+base_model: allistair99/tinybert-6l-768d-BiLSTM-finetuned-squad-optiparam
+tags:
+- generated_from_trainer
+model-index:
+- name: tinybert-base-uncased-BiLSTM-Optiparam-ADVQA36K-V1
+  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-base-uncased-BiLSTM-Optiparam-ADVQA36K-V1
+
+This model is a fine-tuned version of [allistair99/tinybert-6l-768d-BiLSTM-finetuned-squad-optiparam](https://huggingface.co/allistair99/tinybert-6l-768d-BiLSTM-finetuned-squad-optiparam) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.9656
+
+## 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: 3e-05
+- train_batch_size: 6
+- eval_batch_size: 60
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 3.0036        | 0.0599 | 100  | 2.5920          |
+| 2.8317        | 0.1198 | 200  | 2.5140          |
+| 2.7926        | 0.1796 | 300  | 2.5142          |
+| 2.7339        | 0.2395 | 400  | 2.4734          |
+| 2.7291        | 0.2994 | 500  | 2.4903          |
+| 2.7906        | 0.3593 | 600  | 2.4795          |
+| 2.641         | 0.4192 | 700  | 2.4862          |
+| 2.5682        | 0.4790 | 800  | 2.5682          |
+| 2.6871        | 0.5389 | 900  | 2.4674          |
+| 2.7482        | 0.5988 | 1000 | 2.4033          |
+| 2.6894        | 0.6587 | 1100 | 2.3723          |
+| 2.4788        | 0.7186 | 1200 | 2.3302          |
+| 2.6424        | 0.7784 | 1300 | 2.4048          |
+| 2.6319        | 0.8383 | 1400 | 2.3805          |
+| 2.5736        | 0.8982 | 1500 | 2.3620          |
+| 2.5958        | 0.9581 | 1600 | 2.3191          |
+| 2.2015        | 1.0180 | 1700 | 2.7917          |
+| 1.8579        | 1.0778 | 1800 | 2.3981          |
+| 1.7857        | 1.1377 | 1900 | 2.6140          |
+| 1.7714        | 1.1976 | 2000 | 2.5079          |
+| 1.7564        | 1.2575 | 2100 | 2.6297          |
+| 1.8162        | 1.3174 | 2200 | 2.5810          |
+| 1.7704        | 1.3772 | 2300 | 2.4192          |
+| 1.8182        | 1.4371 | 2400 | 2.4714          |
+| 1.8095        | 1.4970 | 2500 | 2.6516          |
+| 1.9058        | 1.5569 | 2600 | 2.4050          |
+| 1.8567        | 1.6168 | 2700 | 2.4032          |
+| 1.7526        | 1.6766 | 2800 | 2.4313          |
+| 1.6995        | 1.7365 | 2900 | 2.5849          |
+| 1.7793        | 1.7964 | 3000 | 2.5520          |
+| 1.7435        | 1.8563 | 3100 | 2.4718          |
+| 1.8295        | 1.9162 | 3200 | 2.4131          |
+| 1.8069        | 1.9760 | 3300 | 2.4696          |
+| 1.4409        | 2.0359 | 3400 | 2.9758          |
+| 1.2772        | 2.0958 | 3500 | 2.9478          |
+| 1.1997        | 2.1557 | 3600 | 2.9533          |
+| 1.19          | 2.2156 | 3700 | 2.8930          |
+| 1.1831        | 2.2754 | 3800 | 3.0055          |
+| 1.1424        | 2.3353 | 3900 | 3.0072          |
+| 1.1612        | 2.3952 | 4000 | 2.9198          |
+| 1.242         | 2.4551 | 4100 | 2.9932          |
+| 1.1113        | 2.5150 | 4200 | 3.0195          |
+| 1.2147        | 2.5749 | 4300 | 2.9441          |
+| 1.1773        | 2.6347 | 4400 | 2.9556          |
+| 1.2346        | 2.6946 | 4500 | 2.9006          |
+| 1.1443        | 2.7545 | 4600 | 2.9683          |
+| 1.2002        | 2.8144 | 4700 | 2.9800          |
+| 1.1385        | 2.8743 | 4800 | 2.9573          |
+| 1.2266        | 2.9341 | 4900 | 2.9599          |
+| 1.2089        | 2.9940 | 5000 | 2.9656          |
+
+
+### Framework versions
+
+- Transformers 4.40.0
+- Pytorch 2.6.0+cu124
+- Datasets 2.21.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "allistair99/tinybert-6l-768d-BiLSTM-finetuned-squad-optiparam",
+  "architectures": [
+    "BertForQuestionAnswering1"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "cell": {},
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "language": "english",
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "name": "Bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "pre_trained": "",
+  "structure": [],
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.0",
+  "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:f677c0551fcde91ca2e2d128feeee1fab69a0f5986f31b453ca07e5291ce4319
+size 279656944

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0294e8f36581ab9f7da6571605ced1175f2383532e4fa95df4e47312f4a94158
+size 4920