olipol/smaug_part1

README.md

@@ -0,0 +1,66 @@
+---
+library_name: transformers
+base_model: dkleczek/bert-base-polish-cased-v1
+tags:
+- generated_from_trainer
+model-index:
+- name: smaug_part1_v2
+  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. -->
+
+# smaug_part1_v2
+
+This model is a fine-tuned version of [dkleczek/bert-base-polish-cased-v1](https://huggingface.co/dkleczek/bert-base-polish-cased-v1) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0000
+
+## 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: 1e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- 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: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.0312        | 1.0   | 662  | 0.0291          |
+| 0.0057        | 2.0   | 1324 | 0.0001          |
+| 0.0007        | 3.0   | 1986 | 0.1799          |
+| 0.0007        | 4.0   | 2648 | 0.0000          |
+| 0.0           | 5.0   | 3310 | 0.0000          |
+| 0.0           | 6.0   | 3972 | 0.0000          |
+| 0.0           | 7.0   | 4634 | 0.0000          |
+| 0.0           | 8.0   | 5296 | 0.0000          |
+| 0.0           | 9.0   | 5958 | 0.0000          |
+| 0.0           | 10.0  | 6620 | 0.0000          |
+
+
+### Framework versions
+
+- Transformers 4.46.3
+- Pytorch 2.5.1+cu118
+- Datasets 3.1.0
+- Tokenizers 0.20.3

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "dkleczek/bert-base-polish-cased-v1",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 60000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02433795e42392f791dee71ca38a15ed3e6eed4e103b33887043d3dd8ce58b2a
+size 528515072

runs/Dec13_00-57-42_DESKTOP-HMVHQ8L/events.out.tfevents.1734047864.DESKTOP-HMVHQ8L.16672.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9f93619bbb4ff9bfcc401345d7ade79b74d45b0a6c22645aa562cba9b22301a
+size 5052

runs/Dec13_01-16-45_DESKTOP-HMVHQ8L/events.out.tfevents.1734049007.DESKTOP-HMVHQ8L.29052.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f12a9d4e568b3051adac79c2f7d92d4f6d70579e55cdb0e1cd4d25e2e7335386
+size 5054

runs/Dec13_01-18-46_DESKTOP-HMVHQ8L/events.out.tfevents.1734049129.DESKTOP-HMVHQ8L.25736.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfd525ebc0838cb1fb4482e9325df419b6bb753123eaf2c977e0c7cb26996e2e
+size 10859

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 +1,57 @@
+{
+  "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": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "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 sha256:31a2db91ab977765af1e9e66744de04ebbcc57e53a2b83985293d65d12258b80
+size 5304