Model save

README.md

@@ -0,0 +1,75 @@
+---
+library_name: transformers
+license: gpl-3.0
+base_model: ckiplab/albert-tiny-chinese
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+model-index:
+- name: tunned_albert_model2
+  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. -->
+
+# tunned_albert_model2
+
+This model is a fine-tuned version of [ckiplab/albert-tiny-chinese](https://huggingface.co/ckiplab/albert-tiny-chinese) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6809
+- Accuracy: 0.5
+- Precision: 0.25
+- Recall: 0.5
+- F1: 0.3333
+
+## 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: 2e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- 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: 3
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
+|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
+| 0.6897        | 0.3333 | 3    | 0.6932          | 0.5      | 0.25      | 0.5    | 0.3333 |
+| 0.6693        | 0.6667 | 6    | 0.6925          | 0.5      | 0.25      | 0.5    | 0.3333 |
+| 0.6937        | 1.0    | 9    | 0.6915          | 0.5      | 0.25      | 0.5    | 0.3333 |
+| 0.6736        | 1.3333 | 12   | 0.6887          | 0.5      | 0.25      | 0.5    | 0.3333 |
+| 0.6498        | 1.6667 | 15   | 0.6866          | 0.5      | 0.25      | 0.5    | 0.3333 |
+| 0.7069        | 2.0    | 18   | 0.6851          | 0.5      | 0.25      | 0.5    | 0.3333 |
+| 0.6634        | 2.3333 | 21   | 0.6832          | 0.5      | 0.25      | 0.5    | 0.3333 |
+| 0.659         | 2.6667 | 24   | 0.6815          | 0.5      | 0.25      | 0.5    | 0.3333 |
+| 0.6476        | 3.0    | 27   | 0.6809          | 0.5      | 0.25      | 0.5    | 0.3333 |
+
+
+### Framework versions
+
+- Transformers 4.49.0
+- Pytorch 2.5.1+cu124
+- Datasets 3.5.0
+- Tokenizers 0.21.0

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "ckiplab/albert-tiny-chinese",
+  "architectures": [
+    "AlbertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "bos_token_id": 101,
+  "classifier_dropout_prob": 0.1,
+  "down_scale_factor": 1,
+  "embedding_size": 128,
+  "eos_token_id": 102,
+  "gap_size": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 312,
+  "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 1248,
+  "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": 4,
+  "num_memory_blocks": 0,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "tokenizer_class": "BertTokenizerFast",
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0",
+  "type_vocab_size": 2,
+  "vocab_size": 21128
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d1849498aadd795b0490bf8884e01cd8113e2e81f18d756161eb028c23130fa
+size 16328008

runs/Apr16_17-29-11_pop-os/events.out.tfevents.1744795752.pop-os.5232.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11fa3105efe5e348fb519a37cc584bbca9897c6396987dabffec9867bd00cbc7
+size 11730

runs/Apr16_17-29-11_pop-os/events.out.tfevents.1744795758.pop-os.5232.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:891e0836810116ee654c3f81a00d5201977459dee5a2d30becc9d54fffbc820a
+size 551

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 +1,58 @@
+{
+  "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,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "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 sha256:3a80ae3ceab928639a91902920c8fe87ca1c398c4a974527376d7cacc85e0e2e
+size 5368