distilbert_cheat_massive

README.md

@@ -0,0 +1,95 @@
+---
+license: apache-2.0
+base_model: distilbert/distilbert-base-uncased
+tags:
+- generated_from_trainer
+datasets:
+- massive
+metrics:
+- f1
+model-index:
+- name: results
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: massive
+      type: massive
+      config: en-US
+      split: test
+      args: en-US
+    metrics:
+    - name: F1
+      type: f1
+      value: 0.9734295558770142
+---
+
+<!-- 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. -->
+
+# results
+
+This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on the massive dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0231
+- F1: 0.9734
+
+## 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
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 3.8235        | 0.5   | 185  | 3.7551          | 0.0022 |
+| 3.5949        | 0.99  | 370  | 3.1246          | 0.0454 |
+| 2.8705        | 1.49  | 555  | 2.4379          | 0.1543 |
+| 2.3444        | 1.99  | 740  | 1.7732          | 0.2967 |
+| 1.7151        | 2.49  | 925  | 1.2983          | 0.4403 |
+| 1.3959        | 2.98  | 1110 | 0.9965          | 0.5490 |
+| 0.9919        | 3.48  | 1295 | 0.7098          | 0.6880 |
+| 0.9495        | 3.98  | 1480 | 0.5798          | 0.7014 |
+| 0.6           | 4.48  | 1665 | 0.4419          | 0.7408 |
+| 0.5952        | 4.97  | 1850 | 0.3653          | 0.7522 |
+| 0.3715        | 5.47  | 2035 | 0.3077          | 0.7957 |
+| 0.3783        | 5.97  | 2220 | 0.2050          | 0.8453 |
+| 0.196         | 6.47  | 2405 | 0.1532          | 0.8386 |
+| 0.22          | 6.96  | 2590 | 0.0968          | 0.8871 |
+| 0.1117        | 7.46  | 2775 | 0.0725          | 0.9057 |
+| 0.1065        | 7.96  | 2960 | 0.0458          | 0.9265 |
+| 0.0644        | 8.45  | 3145 | 0.0378          | 0.9336 |
+| 0.0526        | 8.95  | 3330 | 0.0324          | 0.9616 |
+| 0.0521        | 9.45  | 3515 | 0.0251          | 0.9708 |
+| 0.0302        | 9.95  | 3700 | 0.0231          | 0.9734 |
+
+
+### Framework versions
+
+- Transformers 4.38.1
+- Pytorch 2.1.0+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,161 @@
+{
+  "_name_or_path": "distilbert/distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dim": 3072,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "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",
+    "18": "LABEL_18",
+    "19": "LABEL_19",
+    "20": "LABEL_20",
+    "21": "LABEL_21",
+    "22": "LABEL_22",
+    "23": "LABEL_23",
+    "24": "LABEL_24",
+    "25": "LABEL_25",
+    "26": "LABEL_26",
+    "27": "LABEL_27",
+    "28": "LABEL_28",
+    "29": "LABEL_29",
+    "30": "LABEL_30",
+    "31": "LABEL_31",
+    "32": "LABEL_32",
+    "33": "LABEL_33",
+    "34": "LABEL_34",
+    "35": "LABEL_35",
+    "36": "LABEL_36",
+    "37": "LABEL_37",
+    "38": "LABEL_38",
+    "39": "LABEL_39",
+    "40": "LABEL_40",
+    "41": "LABEL_41",
+    "42": "LABEL_42",
+    "43": "LABEL_43",
+    "44": "LABEL_44",
+    "45": "LABEL_45",
+    "46": "LABEL_46",
+    "47": "LABEL_47",
+    "48": "LABEL_48",
+    "49": "LABEL_49",
+    "50": "LABEL_50",
+    "51": "LABEL_51",
+    "52": "LABEL_52",
+    "53": "LABEL_53",
+    "54": "LABEL_54",
+    "55": "LABEL_55",
+    "56": "LABEL_56",
+    "57": "LABEL_57",
+    "58": "LABEL_58",
+    "59": "LABEL_59"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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_18": 18,
+    "LABEL_19": 19,
+    "LABEL_2": 2,
+    "LABEL_20": 20,
+    "LABEL_21": 21,
+    "LABEL_22": 22,
+    "LABEL_23": 23,
+    "LABEL_24": 24,
+    "LABEL_25": 25,
+    "LABEL_26": 26,
+    "LABEL_27": 27,
+    "LABEL_28": 28,
+    "LABEL_29": 29,
+    "LABEL_3": 3,
+    "LABEL_30": 30,
+    "LABEL_31": 31,
+    "LABEL_32": 32,
+    "LABEL_33": 33,
+    "LABEL_34": 34,
+    "LABEL_35": 35,
+    "LABEL_36": 36,
+    "LABEL_37": 37,
+    "LABEL_38": 38,
+    "LABEL_39": 39,
+    "LABEL_4": 4,
+    "LABEL_40": 40,
+    "LABEL_41": 41,
+    "LABEL_42": 42,
+    "LABEL_43": 43,
+    "LABEL_44": 44,
+    "LABEL_45": 45,
+    "LABEL_46": 46,
+    "LABEL_47": 47,
+    "LABEL_48": 48,
+    "LABEL_49": 49,
+    "LABEL_5": 5,
+    "LABEL_50": 50,
+    "LABEL_51": 51,
+    "LABEL_52": 52,
+    "LABEL_53": 53,
+    "LABEL_54": 54,
+    "LABEL_55": 55,
+    "LABEL_56": 56,
+    "LABEL_57": 57,
+    "LABEL_58": 58,
+    "LABEL_59": 59,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "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": "4.38.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1e0d5a42409f25cca84b32fbd3e5a7ef4e01b1c777c638e4d0730ed0fe53f3f
+size 438137056

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0e5ef26ac2667f1eda020d60129cda16aec5b65b71529d3378dce4d8b763604
+size 4792