Upload TFXLNetForSequenceClassification

README.md

@@ -0,0 +1,73 @@
+---
+license: mit
+tags:
+- generated_from_keras_callback
+model-index:
+- name: Regression_xlnet_aug_CustomLoss
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information Keras had access to. You should
+probably proofread and complete it, then remove this comment. -->
+
+# Regression_xlnet_aug_CustomLoss
+
+This model is a fine-tuned version of [xlnet-base-cased](https://huggingface.co/xlnet-base-cased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 0.3652
+- Train Mae: 0.5686
+- Train Mse: 0.4521
+- Train R2-score: 0.7022
+- Validation Loss: 0.3538
+- Validation Mae: 0.5478
+- Validation Mse: 0.4335
+- Validation R2-score: 0.7272
+- Epoch: 14
+
+## 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:
+- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': 1e-04, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
+- training_precision: float32
+
+### Training results
+
+| Train Loss | Train Mae | Train Mse | Train R2-score | Validation Loss | Validation Mae | Validation Mse | Validation R2-score | Epoch |
+|:----------:|:---------:|:---------:|:--------------:|:---------------:|:--------------:|:--------------:|:-------------------:|:-----:|
+| 0.3976     | 0.5843    | 0.4994    | 0.6170         | 0.3698          | 0.6232         | 0.4576         | 0.5391              | 0     |
+| 0.3938     | 0.5830    | 0.4901    | 0.5860         | 0.4330          | 0.6806         | 0.5537         | 0.2841              | 1     |
+| 0.3822     | 0.5739    | 0.4691    | -2.6800        | 0.3660          | 0.5198         | 0.4614         | 0.7579              | 2     |
+| 0.3716     | 0.5723    | 0.4607    | -0.3420        | 0.3541          | 0.5461         | 0.4343         | 0.7295              | 3     |
+| 0.3852     | 0.5794    | 0.4793    | 0.6654         | 0.3524          | 0.5654         | 0.4288         | 0.6982              | 4     |
+| 0.3826     | 0.5782    | 0.4787    | 0.5114         | 0.3584          | 0.5991         | 0.4374         | 0.6172              | 5     |
+| 0.3817     | 0.5746    | 0.4754    | 0.6431         | 0.3569          | 0.5945         | 0.4348         | 0.6304              | 6     |
+| 0.3705     | 0.5689    | 0.4541    | 0.6679         | 0.3621          | 0.5210         | 0.4528         | 0.7540              | 7     |
+| 0.3719     | 0.5654    | 0.4567    | 0.6807         | 0.3544          | 0.5446         | 0.4350         | 0.7315              | 8     |
+| 0.3752     | 0.5698    | 0.4638    | 0.6324         | 0.3571          | 0.5343         | 0.4413         | 0.7433              | 9     |
+| 0.3773     | 0.5714    | 0.4655    | 0.7523         | 0.3534          | 0.5787         | 0.4294         | 0.6701              | 10    |
+| 0.3651     | 0.5615    | 0.4490    | 0.6223         | 0.3766          | 0.5372         | 0.4846         | 0.7600              | 11    |
+| 0.3706     | 0.5649    | 0.4529    | 0.5998         | 0.3525          | 0.5683         | 0.4286         | 0.6924              | 12    |
+| 0.3779     | 0.5687    | 0.4619    | 0.6900         | 0.3532          | 0.5771         | 0.4291         | 0.6737              | 13    |
+| 0.3652     | 0.5686    | 0.4521    | 0.7022         | 0.3538          | 0.5478         | 0.4335         | 0.7272              | 14    |
+
+
+### Framework versions
+
+- Transformers 4.28.1
+- TensorFlow 2.12.0
+- Datasets 2.11.0
+- Tokenizers 0.13.3

config.json

@@ -0,0 +1,49 @@
+{
+  "_name_or_path": "xlnet-base-cased",
+  "architectures": [
+    "XLNetForSequenceClassification"
+  ],
+  "attn_type": "bi",
+  "bi_data": false,
+  "bos_token_id": 1,
+  "clamp_len": -1,
+  "d_head": 64,
+  "d_inner": 3072,
+  "d_model": 768,
+  "dropout": 0.1,
+  "end_n_top": 5,
+  "eos_token_id": 2,
+  "ff_activation": "gelu",
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "mem_len": null,
+  "model_type": "xlnet",
+  "n_head": 12,
+  "n_layer": 12,
+  "pad_token_id": 5,
+  "problem_type": "regression",
+  "reuse_len": null,
+  "same_length": false,
+  "start_n_top": 5,
+  "summary_activation": "tanh",
+  "summary_last_dropout": 0.1,
+  "summary_type": "last",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 250
+    }
+  },
+  "transformers_version": "4.28.1",
+  "untie_r": true,
+  "use_mems_eval": true,
+  "use_mems_train": false,
+  "vocab_size": 32000
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c7195d7f0b091346512a582bb130c9865eb2d4f2b3c02e3f30afcc5648a4e69
+size 469445640