reflex-project/distilbert-base-uncased-italian-ch-cr-entry-classification

README.md

@@ -0,0 +1,46 @@
+---
+tags:
+- generated_from_trainer
+model-index:
+- name: tmp_trainer
+  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. -->
+
+# tmp_trainer
+
+This model was trained from scratch on an unknown dataset.
+
+## 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: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.1
+- Datasets 2.15.0
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,71 @@
+{
+  "_name_or_path": "models/distilbert-base-uncased/it/hf_dataset_80-10-10_20240112T210443Z_distilbert-base-uncased/model-best",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "11",
+    "1": "12",
+    "2": "13",
+    "3": "141",
+    "4": "20",
+    "5": "311",
+    "6": "312",
+    "7": "313",
+    "8": "314",
+    "9": "321",
+    "10": "322",
+    "11": "323",
+    "12": "324",
+    "13": "33",
+    "14": "34",
+    "15": "351",
+    "16": "352",
+    "17": "36",
+    "18": "37",
+    "19": "40",
+    "20": "50"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "11": 0,
+    "12": 1,
+    "13": 2,
+    "141": 3,
+    "20": 4,
+    "311": 5,
+    "312": 6,
+    "313": 7,
+    "314": 8,
+    "321": 9,
+    "322": 10,
+    "323": 11,
+    "324": 12,
+    "33": 13,
+    "34": 14,
+    "351": 15,
+    "352": 16,
+    "36": 17,
+    "37": 18,
+    "40": 19,
+    "50": 20
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:228398c46ffffc97498a65f9a56fc0e3cc705060d99ef84adb390162588e9c76
+size 267891012

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:010f298494d249abe8151303a1f9fec5dcc7e537e115a9a63aca0d094987c414
+size 4536