lucienbaumgartner/mtg-vorthos-multilabel-distilbert

README.md

@@ -0,0 +1,74 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: distilbert-base-uncased
+metrics:
+- accuracy
+model-index:
+- name: multilabel_classification
+  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. -->
+
+# multilabel_classification
+
+This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3550
+- F1 Micro: 0.3846
+- F1 Macro: 0.3832
+- F1 Weighted: 0.3836
+- Accuracy: 0.3008
+
+## 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: 0.0001
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | F1 Micro | F1 Macro | F1 Weighted | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:-----------:|:--------:|
+| No log        | 1.0   | 288  | 0.4072          | 0.0078   | 0.0074   | 0.0077      | 0.0859   |
+| 0.4124        | 2.0   | 576  | 0.3695          | 0.2230   | 0.2164   | 0.2160      | 0.1914   |
+| 0.4124        | 3.0   | 864  | 0.3614          | 0.3195   | 0.3123   | 0.3118      | 0.2578   |
+| 0.3467        | 4.0   | 1152 | 0.3584          | 0.3580   | 0.3547   | 0.3539      | 0.2695   |
+| 0.3467        | 5.0   | 1440 | 0.3550          | 0.3846   | 0.3832   | 0.3836      | 0.3008   |
+| 0.3168        | 6.0   | 1728 | 0.3578          | 0.4127   | 0.4089   | 0.4091      | 0.3164   |
+| 0.291         | 7.0   | 2016 | 0.3618          | 0.4136   | 0.4096   | 0.4099      | 0.3164   |
+| 0.291         | 8.0   | 2304 | 0.3636          | 0.4175   | 0.4134   | 0.4137      | 0.3242   |
+| 0.281         | 9.0   | 2592 | 0.3640          | 0.4235   | 0.4197   | 0.4201      | 0.3320   |
+| 0.281         | 10.0  | 2880 | 0.3647          | 0.4125   | 0.4094   | 0.4096      | 0.3203   |
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.37.2
+- Pytorch 2.2.0
+- Datasets 2.19.1
+- Tokenizers 0.15.1

adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "distilbert-base-uncased",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "classifier",
+    "score"
+  ],
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_lin",
+    "k_lin",
+    "q_lin"
+  ],
+  "task_type": "SEQ_CLS",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6dae306d1f533dedc0eb27d9cd48b67d9e7eb8e488bc3bd35fde1e2be3f169c
+size 3268052

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 +1,55 @@
+{
+  "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:eab9a001314ff0d32993e205c39ca97adb423ac57659d64ab8cd7eda9c0737fe
+size 4728