End of training

README.md

@@ -0,0 +1,92 @@
+---
+license: lgpl-3.0
+base_model: sdadas/polish-roberta-base-v2
+tags:
+- generated_from_trainer
+datasets:
+- nkjp1m
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: polish-roberta-base-v2-pos-tagging
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: nkjp1m
+      type: nkjp1m
+      config: nkjp1m
+      split: test
+      args: nkjp1m
+    metrics:
+    - name: Precision
+      type: precision
+      value: 0.9853198910270871
+    - name: Recall
+      type: recall
+      value: 0.9858245297268206
+    - name: F1
+      type: f1
+      value: 0.9855721457799069
+    - name: Accuracy
+      type: accuracy
+      value: 0.9884294612942691
+---
+
+<!-- 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. -->
+
+# polish-roberta-base-v2-pos-tagging
+
+This model is a fine-tuned version of [sdadas/polish-roberta-base-v2](https://huggingface.co/sdadas/polish-roberta-base-v2) on the nkjp1m dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0508
+- Precision: 0.9853
+- Recall: 0.9858
+- F1: 0.9856
+- Accuracy: 0.9884
+
+## 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: 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: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.0665        | 1.0   | 2155 | 0.0629          | 0.9835    | 0.9836 | 0.9836 | 0.9867   |
+| 0.0369        | 2.0   | 4310 | 0.0539          | 0.9842    | 0.9848 | 0.9845 | 0.9876   |
+| 0.0243        | 3.0   | 6465 | 0.0508          | 0.9853    | 0.9858 | 0.9856 | 0.9884   |
+
+
+### Framework versions
+
+- Transformers 4.36.0
+- Pytorch 2.1.0+cu118
+- Datasets 2.15.0
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,112 @@
+{
+  "_name_or_path": "sdadas/polish-roberta-base-v2",
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "adj",
+    "1": "adja",
+    "2": "adjc",
+    "3": "adjp",
+    "4": "adv",
+    "5": "aglt",
+    "6": "bedzie",
+    "7": "brev",
+    "8": "comp",
+    "9": "conj",
+    "10": "depr",
+    "11": "dig",
+    "12": "fin",
+    "13": "frag",
+    "14": "ger",
+    "15": "imps",
+    "16": "impt",
+    "17": "inf",
+    "18": "interj",
+    "19": "interp",
+    "20": "num",
+    "21": "numcomp",
+    "22": "pact",
+    "23": "pacta",
+    "24": "pant",
+    "25": "part",
+    "26": "pcon",
+    "27": "ppas",
+    "28": "ppron12",
+    "29": "ppron3",
+    "30": "praet",
+    "31": "pred",
+    "32": "prep",
+    "33": "romandig",
+    "34": "siebie",
+    "35": "subst",
+    "36": "sym",
+    "37": "winien",
+    "38": "xxs",
+    "39": "xxx"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "adj": 0,
+    "adja": 1,
+    "adjc": 2,
+    "adjp": 3,
+    "adv": 4,
+    "aglt": 5,
+    "bedzie": 6,
+    "brev": 7,
+    "comp": 8,
+    "conj": 9,
+    "depr": 10,
+    "dig": 11,
+    "fin": 12,
+    "frag": 13,
+    "ger": 14,
+    "imps": 15,
+    "impt": 16,
+    "inf": 17,
+    "interj": 18,
+    "interp": 19,
+    "num": 20,
+    "numcomp": 21,
+    "pact": 22,
+    "pacta": 23,
+    "pant": 24,
+    "part": 25,
+    "pcon": 26,
+    "ppas": 27,
+    "ppron12": 28,
+    "ppron3": 29,
+    "praet": 30,
+    "pred": 31,
+    "prep": 32,
+    "romandig": 33,
+    "siebie": 34,
+    "subst": 35,
+    "sym": 36,
+    "winien": 37,
+    "xxs": 38,
+    "xxx": 39
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50001
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4762f72e49c0a80fe7b849fe694777ee1b1d5acfdca661faf9d62e106ca46d5c
+size 495556128

runs/Dec11_19-52-09_01ab72bb6d36/events.out.tfevents.1702324329.01ab72bb6d36.118.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46913af8e0c50a00c0e8087051078cd4054c8217786ad79140ab00d37af24599
+size 9553

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "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": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50000": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:738e65a0913f7b4f6bb11f79e56091b1bc46aaf47a655eb97407662c44500436
+size 4728