stackoverflow_tag_classification/initial_run/bert-base-cased/marvelous-pug-454

README.md

@@ -0,0 +1,77 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: google-bert/bert-base-cased
+tags:
+- generated_from_trainer
+model-index:
+- name: marvelous-pug-454
+  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. -->
+
+# marvelous-pug-454
+
+This model is a fine-tuned version of [google-bert/bert-base-cased](https://huggingface.co/google-bert/bert-base-cased) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4049
+- Hamming Loss: 0.1123
+- Zero One Loss: 1.0
+- Jaccard Score: 1.0
+- Hamming Loss Optimised: 0.1034
+- Hamming Loss Threshold: 0.4079
+- Zero One Loss Optimised: 0.7662
+- Zero One Loss Threshold: 0.3351
+- Jaccard Score Optimised: 0.7625
+- Jaccard Score Threshold: 0.3149
+
+## 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: 3.691774561796012e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 2024
+- 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: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Hamming Loss | Zero One Loss | Jaccard Score | Hamming Loss Optimised | Hamming Loss Threshold | Zero One Loss Optimised | Zero One Loss Threshold | Jaccard Score Optimised | Jaccard Score Threshold |
+|:-------------:|:-----:|:----:|:---------------:|:------------:|:-------------:|:-------------:|:----------------------:|:----------------------:|:-----------------------:|:-----------------------:|:-----------------------:|:-----------------------:|
+| No log        | 1.0   | 100  | 0.6553          | 0.3676       | 1.0           | 0.9280        | 0.1123                 | 0.6566                 | 0.95                    | 0.5576                  | 0.8863                  | 0.2993                  |
+| No log        | 2.0   | 200  | 0.5073          | 0.1205       | 0.94          | 0.9381        | 0.1123                 | 0.6530                 | 0.8175                  | 0.4434                  | 0.7941                  | 0.4421                  |
+| No log        | 3.0   | 300  | 0.4412          | 0.1121       | 0.9988        | 0.9988        | 0.1123                 | 0.5944                 | 0.7675                  | 0.3659                  | 0.7621                  | 0.3681                  |
+| No log        | 4.0   | 400  | 0.4228          | 0.1123       | 1.0           | 1.0           | 0.109                  | 0.4184                 | 0.7675                  | 0.3485                  | 0.7631                  | 0.3402                  |
+| 0.5269        | 5.0   | 500  | 0.4151          | 0.1123       | 1.0           | 1.0           | 0.1123                 | 0.5944                 | 0.7675                  | 0.3646                  | 0.7990                  | 0.2948                  |
+| 0.5269        | 6.0   | 600  | 0.4109          | 0.1123       | 1.0           | 1.0           | 0.1051                 | 0.4182                 | 0.7662                  | 0.3532                  | 0.7631                  | 0.3362                  |
+| 0.5269        | 7.0   | 700  | 0.4084          | 0.1123       | 1.0           | 1.0           | 0.1046                 | 0.4138                 | 0.7662                  | 0.3368                  | 0.7638                  | 0.3453                  |
+| 0.5269        | 8.0   | 800  | 0.4059          | 0.1123       | 1.0           | 1.0           | 0.1031                 | 0.4037                 | 0.7662                  | 0.3314                  | 0.7612                  | 0.3225                  |
+| 0.5269        | 9.0   | 900  | 0.4051          | 0.1123       | 1.0           | 1.0           | 0.1032                 | 0.4075                 | 0.7662                  | 0.3350                  | 0.7619                  | 0.3209                  |
+| 0.4202        | 10.0  | 1000 | 0.4049          | 0.1123       | 1.0           | 1.0           | 0.1034                 | 0.4079                 | 0.7662                  | 0.3351                  | 0.7625                  | 0.3149                  |
+
+
+### Framework versions
+
+- PEFT 0.13.2
+- Transformers 4.47.0
+- Pytorch 2.5.1+cu124
+- Datasets 3.1.0
+- Tokenizers 0.21.0

adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "BertForSequenceClassification",
+    "parent_library": "transformers.models.bert.modeling_bert"
+  },
+  "base_model_name_or_path": "google-bert/bert-base-cased",
+  "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": 18,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "value",
+    "query"
+  ],
+  "task_type": null,
+  "use_dora": true,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f63edfd1236f328d6216d31b2ab2bdb8e891c16b9afed66505cbb5283230bbb
+size 1263528

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 +1,56 @@
+{
+  "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": false,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "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 sha256:794bcd3c6a2a156899436ebfe8183a57ee20fd6c3d2f75728beac630254550ab
+size 5496