Model save

README.md

@@ -0,0 +1,67 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: google/bert_uncased_L-4_H-128_A-2
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: bert_uncased_L-4_H-128_A-2_wnli
+  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. -->
+
+# bert_uncased_L-4_H-128_A-2_wnli
+
+This model is a fine-tuned version of [google/bert_uncased_L-4_H-128_A-2](https://huggingface.co/google/bert_uncased_L-4_H-128_A-2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7140
+- Accuracy: 0.3239
+
+## 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: 5e-05
+- train_batch_size: 256
+- eval_batch_size: 256
+- seed: 10
+- optimizer: Use 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: 50
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.6968        | 1.0   | 3    | 0.7060          | 0.4225   |
+| 0.6898        | 2.0   | 6    | 0.7042          | 0.3521   |
+| 0.6912        | 3.0   | 9    | 0.7055          | 0.3662   |
+| 0.695         | 4.0   | 12   | 0.7075          | 0.3380   |
+| 0.6946        | 5.0   | 15   | 0.7099          | 0.3099   |
+| 0.6921        | 6.0   | 18   | 0.7122          | 0.3099   |
+| 0.6874        | 7.0   | 21   | 0.7140          | 0.3239   |
+
+
+### Framework versions
+
+- Transformers 4.46.3
+- Pytorch 2.2.1+cu118
+- Datasets 2.17.0
+- Tokenizers 0.20.3

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "google/bert_uncased_L-4_H-128_A-2",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "finetuning_task": "wnli",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 128,
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "label2id": {
+    "entailment": 1,
+    "not_entailment": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 2,
+  "num_hidden_layers": 4,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

logs/events.out.tfevents.1733338898.ki-g0008.1764072.32

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b792e2dfc9883471d31be7c94e254b0a099544a716575d749479de920138e86c
+size 9133

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cfbda7096fad86b9310ed0f614f945faece30a1c7fbac9ad8869189932bd551
+size 19139184

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 +1,57 @@
+{
+  "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,
+  "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 sha256:918403dd9df92158ec34c1f5eea7beb25069c0bfbd1d0d017df3a0a0e4cf81a7
+size 5304