End of training

README.md

@@ -0,0 +1,68 @@
+---
+license: apache-2.0
+base_model: PartAI/TookaBERT-Base
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: my_model
+  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. -->
+
+# my_model
+
+This model is a fine-tuned version of [PartAI/TookaBERT-Base](https://huggingface.co/PartAI/TookaBERT-Base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.3774
+- Precision: 0.2
+- Recall: 0.0909
+- F1: 0.1250
+- Accuracy: 0.5319
+
+## 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: 2e-05
+- 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: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 1.0   | 2    | 2.8942          | 0.0       | 0.0    | 0.0    | 0.3830   |
+| No log        | 2.0   | 4    | 2.5283          | 0.0       | 0.0    | 0.0    | 0.4894   |
+| No log        | 3.0   | 6    | 2.3774          | 0.2       | 0.0909 | 0.1250 | 0.5319   |
+
+
+### Framework versions
+
+- Transformers 4.42.4
+- Pytorch 2.3.1+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,89 @@
+{
+  "_name_or_path": "PartAI/TookaBERT-Base",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 2,
+  "classifier_dropout": null,
+  "eos_token_id": 3,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-brand",
+    "10": "I-form",
+    "11": "B-ingredient",
+    "12": "I-ingredient",
+    "13": "B-manufacturer",
+    "14": "I-manufacturer",
+    "15": "B-model",
+    "16": "I-model",
+    "17": "B-product",
+    "18": "I-product",
+    "19": "B-quantity",
+    "2": "I-brand",
+    "20": "I-quantity",
+    "21": "B-skin_type",
+    "22": "I-skin_type",
+    "23": "B-type",
+    "24": "I-type",
+    "25": "B-usage",
+    "26": "I-usage",
+    "27": "B-benefit",
+    "28": "I-benefit",
+    "3": "B-certification",
+    "4": "I-certification",
+    "5": "B-color",
+    "6": "I-color",
+    "7": "B-country_of_origin",
+    "8": "I-country_of_origin",
+    "9": "B-form"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "0": "O",
+    "1": "B-brand",
+    "10": "I-form",
+    "11": "B-ingredient",
+    "12": "I-ingredient",
+    "13": "B-manufacturer",
+    "14": "I-manufacturer",
+    "15": "B-model",
+    "16": "I-model",
+    "17": "B-product",
+    "18": "I-product",
+    "19": "B-quantity",
+    "2": "I-brand",
+    "20": "I-quantity",
+    "21": "B-skin_type",
+    "22": "I-skin_type",
+    "23": "B-type",
+    "24": "I-type",
+    "25": "B-usage",
+    "26": "I-usage",
+    "27": "B-benefit",
+    "28": "I-benefit",
+    "3": "B-certification",
+    "4": "I-certification",
+    "5": "B-color",
+    "6": "I-color",
+    "7": "B-country_of_origin",
+    "8": "I-country_of_origin",
+    "9": "B-form"
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 48000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:149eaf76b80ee1422c9159f9c47f1083e1750c0214507c33ec4bc02e9fd1e70e
+size 489371572

runs/Aug05_23-24-44_0680ddc51f3a/events.out.tfevents.1722900285.0680ddc51f3a.231.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7420aa9e689d44e769f91816946dc1dc0e550168526bc1e26b893cc3cf8becd4
+size 6234

runs/Aug05_23-26-23_0680ddc51f3a/events.out.tfevents.1722900384.0680ddc51f3a.231.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7df94d2e97efe0d5ac2cc0859ecd3c0ad943ba1bbd7b733da2d28a9d08148702
+size 6234

runs/Aug05_23-26-36_0680ddc51f3a/events.out.tfevents.1722900397.0680ddc51f3a.231.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6678f5a1e7f58d9f08be60aaac0a8c7eb45fc6091b09ec2710a338f79b2cc33
+size 7970

special_tokens_map.json

@@ -0,0 +1,44 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "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 +1,62 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "max_length": null,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "truncation_side": "right",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b516cebefa23cb900ba82fa5299d234c97bbeb613ce3db9711f3b7ecf8e3c5d1
+size 5112