Model save

README.md

@@ -0,0 +1,65 @@
+---
+base_model: Hartunka/tiny_bert_km_50_v1
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: tiny_bert_km_50_v1_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. -->
+
+# tiny_bert_km_50_v1_wnli
+
+This model is a fine-tuned version of [Hartunka/tiny_bert_km_50_v1](https://huggingface.co/Hartunka/tiny_bert_km_50_v1) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7717
+- Accuracy: 0.2394
+
+## 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: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 50
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.7038        | 1.0   | 3    | 0.7232          | 0.3803   |
+| 0.6955        | 2.0   | 6    | 0.7139          | 0.3803   |
+| 0.692         | 3.0   | 9    | 0.7201          | 0.3662   |
+| 0.6926        | 4.0   | 12   | 0.7316          | 0.3521   |
+| 0.689         | 5.0   | 15   | 0.7488          | 0.2817   |
+| 0.6869        | 6.0   | 18   | 0.7665          | 0.2817   |
+| 0.6912        | 7.0   | 21   | 0.7717          | 0.2394   |
+
+
+### Framework versions
+
+- Transformers 4.40.0
+- Pytorch 2.6.0+cu124
+- Datasets 3.5.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "Hartunka/tiny_bert_km_50_v1",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 512,
+  "dropout": 0.1,
+  "finetuning_task": "wnli",
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "label2id": {
+    "entailment": 1,
+    "not_entailment": 0
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 8,
+  "n_layers": 4,
+  "n_topics": 50,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.0",
+  "vocab_size": 30522
+}

logs/events.out.tfevents.1744815395.s_004_m

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a266b5f3d2c643a8285b12f1a099cf7f39d83b34bef4d491c5a522a9f863db1
+size 8665

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ff47307312e44458b77215b5d94b19964791793c5bd2f28c7b6e6b550a168d5
+size 131856744

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9613f6fa2b6f7f008e7b59d3b8ad0673110280659cd3d5fbbaa0871aedd17ca
+size 5048