End of training

README.md

@@ -0,0 +1,87 @@
+---
+license: cc-by-4.0
+base_model: allegro/herbert-large-cased
+tags:
+- generated_from_trainer
+datasets:
+- universal_dependencies
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: herbert-large-cased-upos
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: universal_dependencies
+      type: universal_dependencies
+      config: pl_pdb
+      split: validation
+      args: pl_pdb
+    metrics:
+    - name: Precision
+      type: precision
+      value: 0.9876397732043457
+    - name: Recall
+      type: recall
+      value: 0.991338336393956
+    - name: F1
+      type: f1
+      value: 0.9894469851843459
+    - name: Accuracy
+      type: accuracy
+      value: 0.9953262628078375
+---
+
+<!-- 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. -->
+
+# herbert-large-cased-upos
+
+This model is a fine-tuned version of [allegro/herbert-large-cased](https://huggingface.co/allegro/herbert-large-cased) on the universal_dependencies dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0398
+- Precision: 0.9876
+- Recall: 0.9913
+- F1: 0.9894
+- Accuracy: 0.9953
+
+## 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: 32
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 20
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.39.3
+- Pytorch 1.11.0a0+17540c5
+- Datasets 2.21.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,72 @@
+{
+  "_name_or_path": "allegro/herbert-large-cased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11",
+    "12": "LABEL_12",
+    "13": "LABEL_13",
+    "14": "LABEL_14",
+    "15": "LABEL_15",
+    "16": "LABEL_16",
+    "17": "LABEL_17"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_12": 12,
+    "LABEL_13": 13,
+    "LABEL_14": 14,
+    "LABEL_15": 15,
+    "LABEL_16": 16,
+    "LABEL_17": 17,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 514,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "tokenizer_class": "HerbertTokenizerFast",
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 50000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50d0bbe18b65a3f4a39e6dabfd68c89cd32d23030bfd4b509aad4c225e643500
+size 1416279904

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea7fd5e1ef0900d671752cbd31f61933be1c38a14b2866082416278f3185bcfd
+size 4591