stackoverflow_tag_classification/initial_run/bert-base-cased/rogue-crane-540

README.md

@@ -0,0 +1,69 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: google-bert/bert-base-cased
+tags:
+- generated_from_trainer
+model-index:
+- name: rogue-crane-540
+  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. -->
+
+# rogue-crane-540
+
+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: 0.6200
+- Hamming Loss: 0.2812
+- Zero One Loss: 1.0
+- Jaccard Score: 0.8617
+- Hamming Loss Optimised: 0.1123
+- Hamming Loss Threshold: 0.6724
+- Zero One Loss Optimised: 0.8575
+- Zero One Loss Threshold: 0.5775
+- Jaccard Score Optimised: 0.8790
+- Jaccard Score Threshold: 0.3808
+
+## 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: 2.4790601469455396e-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: 2
+
+### 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  | 0.6447          | 0.36         | 1.0           | 0.8848        | 0.1123                 | 0.6863                 | 0.915                   | 0.5569                  | 0.8878                  | 0.2889                  |
+| No log        | 2.0   | 200  | 0.6200          | 0.2812       | 1.0           | 0.8617        | 0.1123                 | 0.6724                 | 0.8575                  | 0.5775                  | 0.8790                  | 0.3808                  |
+
+
+### 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": 21,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 4,
+  "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:ecb44d4cc58905a567a8767c62bddf88f5ba7daaf8848ee2ad5287246091f9f2
+size 673664

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 sha256:9b871f4f6017c99cc75aaadc8779adfb09f6601566576d7fc38e82985f5d1939
+size 5496