model_name1

README.md

@@ -0,0 +1,67 @@
+---
+license: apache-2.0
+base_model: distilbert/distilbert-base-cased
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: our_awesome_BERT_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. -->
+
+# our_awesome_BERT_model
+
+This model is a fine-tuned version of [distilbert/distilbert-base-cased](https://huggingface.co/distilbert/distilbert-base-cased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0567
+- Precision: 0.7594
+- Recall: 0.7909
+- F1: 0.7748
+- Accuracy: 0.9825
+
+## 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: 2
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.1072        | 1.0   | 784  | 0.0602          | 0.7686    | 0.7360 | 0.7520 | 0.9807   |
+| 0.0271        | 2.0   | 1568 | 0.0567          | 0.7594    | 0.7909 | 0.7748 | 0.9825   |
+
+
+### Framework versions
+
+- Transformers 4.39.3
+- Pytorch 2.2.0+cpu
+- Datasets 2.19.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "distilbert/distilbert-base-cased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForTokenClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "O",
+    "1": "B-LOC",
+    "2": "I-LOC",
+    "3": "B-PER",
+    "4": "B-ORG",
+    "5": "I-ORG",
+    "6": "I-PER"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "B-LOC": 1,
+    "B-ORG": 4,
+    "B-PER": 3,
+    "I-LOC": 2,
+    "I-ORG": 5,
+    "I-PER": 6,
+    "O": 0
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.3",
+  "vocab_size": 28996
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:958ed577c5d48d95181187f881a690c558b503ade17db95cc7f9fb6c5d8eed5e
+size 260797516

runs/Apr24_13-41-17_Petya/events.out.tfevents.1713958878.Petya.16164.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d737c60d25aa4ebd39b40868f966597476eb3bef165b6feee155dbd963ab7f6
+size 6738

runs/May05_13-12-17_Petya/events.out.tfevents.1714907539.Petya.19232.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a006df3c764075156671e223ccd57ffe1be08b083f5f2d9e7ade7bd62731fc4
+size 4807

runs/May06_15-22-38_Petya/events.out.tfevents.1715001760.Petya.25928.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bb950af7a9ee08df9ea16fdabc461c008208f1f137b0c3793ec2a7895b16598
+size 6738

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 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45f9a2ba9e300e8f8739a65a93f68f2ffd9aa84ea5ee803585a390bd59323f51
+size 4984