Upload TFAlbertForSequenceClassification

README.md

@@ -0,0 +1,73 @@
+---
+license: apache-2.0
+tags:
+- generated_from_keras_callback
+model-index:
+- name: Regression_albert_aug_CustomLoss_3
+  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_albert_aug_CustomLoss_3
+
+This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 0.2368
+- Train Mae: 0.5301
+- Train Mse: 0.4296
+- Train R2-score: 0.7669
+- Validation Loss: 0.2410
+- Validation Mae: 0.5680
+- Validation Mse: 0.4286
+- Validation R2-score: 0.6930
+- 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 |
+|:----------:|:---------:|:---------:|:--------------:|:---------------:|:--------------:|:--------------:|:-------------------:|:-----:|
+| 0.2614     | 0.5480    | 0.4524    | 0.7369         | 0.2408          | 0.5194         | 0.4609         | 0.7578              | 0     |
+| 0.2442     | 0.5374    | 0.4362    | 0.7109         | 0.2334          | 0.5376         | 0.4391         | 0.7399              | 1     |
+| 0.2431     | 0.5349    | 0.4356    | 0.7503         | 0.2432          | 0.5234         | 0.4657         | 0.7591              | 2     |
+| 0.2386     | 0.5250    | 0.4264    | 0.7926         | 0.2348          | 0.5525         | 0.4316         | 0.7203              | 3     |
+| 0.2409     | 0.5342    | 0.4325    | 0.7166         | 0.2431          | 0.5233         | 0.4656         | 0.7591              | 4     |
+| 0.2400     | 0.5298    | 0.4310    | 0.7553         | 0.2358          | 0.5250         | 0.4490         | 0.7513              | 5     |
+| 0.2384     | 0.5274    | 0.4299    | 0.7791         | 0.2341          | 0.5491         | 0.4329         | 0.7253              | 6     |
+| 0.2413     | 0.5306    | 0.4335    | 0.7593         | 0.2365          | 0.5583         | 0.4299         | 0.7109              | 7     |
+| 0.2381     | 0.5299    | 0.4298    | 0.7784         | 0.2335          | 0.5452         | 0.4347         | 0.7306              | 8     |
+| 0.2379     | 0.5280    | 0.4297    | 0.7575         | 0.2335          | 0.5448         | 0.4349         | 0.7312              | 9     |
+| 0.2374     | 0.5306    | 0.4309    | 0.8098         | 0.2334          | 0.5441         | 0.4352         | 0.7321              | 10    |
+| 0.2381     | 0.5302    | 0.4303    | 0.7428         | 0.2337          | 0.5466         | 0.4340         | 0.7288              | 11    |
+| 0.2376     | 0.5323    | 0.4275    | 0.7806         | 0.2333          | 0.5411         | 0.4369         | 0.7358              | 12    |
+| 0.2339     | 0.5277    | 0.4217    | 0.7986         | 0.2363          | 0.5232         | 0.4506         | 0.7525              | 13    |
+| 0.2368     | 0.5301    | 0.4296    | 0.7669         | 0.2410          | 0.5680         | 0.4286         | 0.6930              | 14    |
+
+
+### Framework versions
+
+- Transformers 4.28.1
+- TensorFlow 2.12.0
+- Datasets 2.12.0
+- Tokenizers 0.13.3

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "albert-base-v2",
+  "architectures": [
+    "AlbertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0,
+  "bos_token_id": 2,
+  "classifier_dropout_prob": 0.1,
+  "down_scale_factor": 1,
+  "embedding_size": 128,
+  "eos_token_id": 3,
+  "gap_size": 0,
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "albert",
+  "net_structure_type": 0,
+  "num_attention_heads": 12,
+  "num_hidden_groups": 1,
+  "num_hidden_layers": 12,
+  "num_memory_blocks": 0,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "regression",
+  "transformers_version": "4.28.1",
+  "type_vocab_size": 2,
+  "vocab_size": 30000
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:304081f7cd620ad12a55f70ede321177390ebc54883bec0ae36093c6217ed7b3
+size 46778612