End of training

README.md

@@ -0,0 +1,57 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: lemon-mint/LLM-Router-Test-01
+tags:
+- generated_from_trainer
+model-index:
+- name: LLM-Router-Test-02
+  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. -->
+
+# LLM-Router-Test-02
+
+This model is a fine-tuned version of [lemon-mint/LLM-Router-Test-01](https://huggingface.co/lemon-mint/LLM-Router-Test-01) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- eval_loss: 0.2848
+- eval_accuracy: 0.89
+- eval_runtime: 1.4714
+- eval_samples_per_second: 67.962
+- eval_steps_per_second: 2.718
+- epoch: 0.4484
+- step: 1400
+
+## 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: 1e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Use OptimizerNames.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: 1
+
+### Framework versions
+
+- Transformers 4.48.3
+- Pytorch 2.5.1+cu124
+- Datasets 3.3.0
+- Tokenizers 0.21.0

config.json

@@ -0,0 +1,59 @@
+{
+  "_name_or_path": "lemon-mint/LLM-Router-Test-01",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "Coding & Debugging",
+    "1": "Science",
+    "2": "Planning",
+    "3": "Information seeking",
+    "4": "Reasoning",
+    "5": "Math",
+    "6": "Medical Knowledge",
+    "7": "Data analysis",
+    "8": "Editing",
+    "9": "Brainstorming",
+    "10": "Creative writing",
+    "11": "Advice seeking",
+    "12": "Role playing",
+    "13": "Others",
+    "14": "Translating"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "Advice seeking": 11,
+    "Brainstorming": 9,
+    "Coding & Debugging": 0,
+    "Creative writing": 10,
+    "Data analysis": 7,
+    "Editing": 8,
+    "Information seeking": 3,
+    "Math": 5,
+    "Medical Knowledge": 6,
+    "Others": 13,
+    "Planning": 2,
+    "Reasoning": 4,
+    "Role playing": 12,
+    "Science": 1,
+    "Translating": 14
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.3",
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e7ba925d8f211a6e05cadf10bb865b37dc59ca6fc6e37d8961d76ffc50bb444
+size 267872556

runs/Feb17_05-09-27_12b2b67672f2/events.out.tfevents.1739768968.12b2b67672f2.735.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f90e9ef7ce5b77d5bba00cfd24249bd767101f0e0260792ade5d61987c9eeb5b
+size 7327

runs/Feb17_05-10-26_12b2b67672f2/events.out.tfevents.1739769027.12b2b67672f2.735.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fca4f35e309f40038d0e7768e7381aa3ebeb48f42ebaad9a83635ede0c27d3d
+size 13223

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 +1,60 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cd70964e5e155e3d9e02009e7381f4c61e0c8c33da0d5e883018b628eea3fd4
+size 5304