End of training

README.md

@@ -0,0 +1,46 @@
+---
+tags:
+- generated_from_trainer
+model-index:
+- name: bERT-poEm-meTRE
+  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. -->
+
+# bERT-poEm-meTRE
+
+This model was trained from scratch on the None 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 2.1.0+cu121
+- Datasets 2.17.1
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,127 @@
+{
+  "_name_or_path": "model",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "finetuning_task": "text-classification",
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "--U----U--",
+    "1": "--U---U---U-",
+    "2": "--U---U---U---U-",
+    "3": "--U-U----U-U--",
+    "4": "--U-U-UU---",
+    "5": "--U-U-UU--U-U-",
+    "6": "--U-U-UU--U-U--",
+    "7": "--U-UU---U-UU-",
+    "8": "--UU-----UU---",
+    "9": "--UU--U-U-",
+    "10": "--UU--U-U--",
+    "11": "--UU--UU--UU-",
+    "12": "--UU--UU--UU--",
+    "13": "--UU-U-U--",
+    "14": "--UU-U-U---",
+    "15": "-U---U---U-",
+    "16": "-U---U---U--",
+    "17": "-U---U---U---U-",
+    "18": "-U---U---U---U--",
+    "19": "-U-U----U-U---",
+    "20": "-U-U--U-U",
+    "21": "-UU--U--UU--U-",
+    "22": "-UU--U-U--",
+    "23": "-UU--U-U-UU--",
+    "24": "-UU--UU--U-",
+    "25": "-UU--UU--UU-",
+    "26": "-UU--UU--UU--UU-",
+    "27": "-UU-U-U--UU-U-U-",
+    "28": "U---U---U--",
+    "29": "U---U---U---",
+    "30": "U---U---U---U---",
+    "31": "U--U--U--U-",
+    "32": "U--U--U--U--",
+    "33": "U--U--U-U-",
+    "34": "U--U-U-U--U-U-",
+    "35": "U--UU--UU--UU--",
+    "36": "U-U--U-U--",
+    "37": "U-U-UU--U-U-UU-",
+    "38": "U-U-UU--U-U-UU--",
+    "39": "UU--U-U-UU-",
+    "40": "UU--U-U-UU--",
+    "41": "UU--U-U-UU--U-U-",
+    "42": "UU--UU--UU-",
+    "43": "UU--UU--UU---",
+    "44": "UU--UU--UU--UU-",
+    "45": "UU--UU--UU--UU--",
+    "46": "UU-U-U--UU-U-U--",
+    "47": "UU-U-UU-U-UU-U-UU-U-"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "--U----U--": 0,
+    "--U---U---U-": 1,
+    "--U---U---U---U-": 2,
+    "--U-U----U-U--": 3,
+    "--U-U-UU---": 4,
+    "--U-U-UU--U-U-": 5,
+    "--U-U-UU--U-U--": 6,
+    "--U-UU---U-UU-": 7,
+    "--UU-----UU---": 8,
+    "--UU--U-U-": 9,
+    "--UU--U-U--": 10,
+    "--UU--UU--UU-": 11,
+    "--UU--UU--UU--": 12,
+    "--UU-U-U--": 13,
+    "--UU-U-U---": 14,
+    "-U---U---U-": 15,
+    "-U---U---U--": 16,
+    "-U---U---U---U-": 17,
+    "-U---U---U---U--": 18,
+    "-U-U----U-U---": 19,
+    "-U-U--U-U": 20,
+    "-UU--U--UU--U-": 21,
+    "-UU--U-U--": 22,
+    "-UU--U-U-UU--": 23,
+    "-UU--UU--U-": 24,
+    "-UU--UU--UU-": 25,
+    "-UU--UU--UU--UU-": 26,
+    "-UU-U-U--UU-U-U-": 27,
+    "U---U---U--": 28,
+    "U---U---U---": 29,
+    "U---U---U---U---": 30,
+    "U--U--U--U-": 31,
+    "U--U--U--U--": 32,
+    "U--U--U-U-": 33,
+    "U--U-U-U--U-U-": 34,
+    "U--UU--UU--UU--": 35,
+    "U-U--U-U--": 36,
+    "U-U-UU--U-U-UU-": 37,
+    "U-U-UU--U-U-UU--": 38,
+    "UU--U-U-UU-": 39,
+    "UU--U-U-UU--": 40,
+    "UU--U-U-UU--U-U-": 41,
+    "UU--UU--UU-": 42,
+    "UU--UU--UU---": 43,
+    "UU--UU--UU--UU-": 44,
+    "UU--UU--UU--UU--": 45,
+    "UU-U-U--UU-U-U--": 46,
+    "UU-U-UU-U-UU-U-UU-U-": 47
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "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": 42000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:589911091f48496a757cda7397f4fbe6b4a6525d79bb708e197ef1e0531c96e3
+size 303234496

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d20e83ca81367d523b23ff362960334f3fd844f18fb5caa8cf11864f9efd641
+size 4600