Adapting `google-bert/bert-base-uncased` for `wnut_17`.

README.md

@@ -0,0 +1,81 @@
+---
+base_model: google-bert/bert-base-uncased
+datasets:
+- wnut_17
+library_name: peft
+license: apache-2.0
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+tags:
+- trl
+- sft
+- generated_from_trainer
+model-index:
+- name: bert-base-uncased-wnut_17
+  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. -->
+
+# bert-base-uncased-wnut_17
+
+This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on the wnut_17 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2870
+- Precision: 0.4802
+- Recall: 0.2132
+- F1: 0.2953
+- Accuracy: 0.9366
+
+## 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: 5e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- 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 | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 1.0   | 213  | 0.4305          | 1.0       | 0.0    | 0.0    | 0.9256   |
+| No log        | 2.0   | 426  | 0.3568          | 0.0       | 0.0    | 0.0    | 0.9256   |
+| 0.496         | 3.0   | 639  | 0.3379          | 0.3495    | 0.0334 | 0.0609 | 0.9277   |
+| 0.496         | 4.0   | 852  | 0.3166          | 0.3824    | 0.1205 | 0.1832 | 0.9321   |
+| 0.1935        | 5.0   | 1065 | 0.3034          | 0.3907    | 0.1705 | 0.2374 | 0.9343   |
+| 0.1935        | 6.0   | 1278 | 0.2956          | 0.4313    | 0.1863 | 0.2602 | 0.9353   |
+| 0.1935        | 7.0   | 1491 | 0.2941          | 0.4700    | 0.1891 | 0.2697 | 0.9357   |
+| 0.1717        | 8.0   | 1704 | 0.2960          | 0.4874    | 0.1965 | 0.2801 | 0.9363   |
+| 0.1717        | 9.0   | 1917 | 0.2882          | 0.4797    | 0.2076 | 0.2898 | 0.9364   |
+| 0.1594        | 10.0  | 2130 | 0.2870          | 0.4802    | 0.2132 | 0.2953 | 0.9366   |
+
+
+### Framework versions
+
+- PEFT 0.12.1.dev0
+- Transformers 4.45.0.dev0
+- Pytorch 2.4.0+cu121
+- Datasets 2.21.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google-bert/bert-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": 16,
+  "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": [
+    "value",
+    "query"
+  ],
+  "task_type": "TOKEN_CLS",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23806713665aa55c220be586bdd488f0620a604c3f63199e4e0e26c67cbe587d
+size 1226516

runs/Aug31_23-42-48_3dc975fa5721/events.out.tfevents.1725147769.3dc975fa5721.3366.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72d37f1f8ed365f209b9589945e332c41fabc004c9423a694e29052261534e5f
+size 11804

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": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f21120c19a7623c68dd39983a8a6e286d7da654da8d73e0264f1a261dde6564e
+size 5496