pos-polish-gpt2-large

README.md

@@ -0,0 +1,69 @@
+---
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: pos-polish-gpt2-large
+  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. -->
+
+# pos-polish-gpt2-large
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2290
+- Precision: 0.8910
+- Recall: 0.9328
+- F1: 0.9114
+- Accuracy: 0.9450
+
+## 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: 2
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.1952        | 1.0   | 2444 | 0.1942          | 0.8865    | 0.9304 | 0.9079 | 0.9426   |
+| 0.1287        | 2.0   | 4889 | 0.1984          | 0.8903    | 0.9322 | 0.9108 | 0.9449   |
+| 0.0832        | 3.0   | 7332 | 0.2290          | 0.8910    | 0.9328 | 0.9114 | 0.9450   |
+
+
+### Framework versions
+
+- Transformers 4.36.2
+- Pytorch 2.1.2+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,107 @@
+{
+  "_name_or_path": "polish-gpt2-large",
+  "activation_function": "gelu_fast",
+  "architectures": [
+    "GPT2ForTokenClassification"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 0,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "id2label": {
+    "0": "numcol",
+    "1": "subst",
+    "2": "num",
+    "3": "comp",
+    "4": "xxx",
+    "5": "bedzie",
+    "6": "interp",
+    "7": "winien",
+    "8": "interj",
+    "9": "siebie",
+    "10": "conj",
+    "11": "pcon",
+    "12": "ppas",
+    "13": "burk",
+    "14": "imps",
+    "15": "ppron12",
+    "16": "pant",
+    "17": "adj",
+    "18": "prep",
+    "19": "adjp",
+    "20": "fin",
+    "21": "pred",
+    "22": "ger",
+    "23": "praet",
+    "24": "adjc",
+    "25": "ppron3",
+    "26": "adv",
+    "27": "aglt",
+    "28": "brev",
+    "29": "depr",
+    "30": "inf",
+    "31": "adja",
+    "32": "pact",
+    "33": "qub",
+    "34": "impt"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "adj": 17,
+    "adja": 31,
+    "adjc": 24,
+    "adjp": 19,
+    "adv": 26,
+    "aglt": 27,
+    "bedzie": 5,
+    "brev": 28,
+    "burk": 13,
+    "comp": 3,
+    "conj": 10,
+    "depr": 29,
+    "fin": 20,
+    "ger": 22,
+    "imps": 14,
+    "impt": 34,
+    "inf": 30,
+    "interj": 8,
+    "interp": 6,
+    "num": 2,
+    "numcol": 0,
+    "pact": 32,
+    "pant": 16,
+    "pcon": 11,
+    "ppas": 12,
+    "ppron12": 15,
+    "ppron3": 25,
+    "praet": 23,
+    "pred": 21,
+    "prep": 18,
+    "qub": 33,
+    "siebie": 9,
+    "subst": 1,
+    "winien": 7,
+    "xxx": 4
+  },
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_embd": 1280,
+  "n_head": 20,
+  "n_inner": 5120,
+  "n_layer": 36,
+  "n_positions": 1536,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "tokenizer_class": "GPT2TokenizerFast",
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "use_cache": true,
+  "vocab_size": 51200
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea2eeb0fc0732ea158b2ce942405ad6d3fbd7106eb94ee1028a3b307a9325532
+size 3103795028

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "add_bos_token": false,
+  "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
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "errors": "replace",
+  "model_max_length": 1536,
+  "pad_token": "</s>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e86319ddacddc1883b2c9cb2399fd3e06e7593c805cc216e9ee65c848edf1d7e
+size 4728