End of training

README.md

@@ -0,0 +1,64 @@
+---
+license: apache-2.0
+base_model: funnel-transformer/xlarge-base
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: funnel-test-512
+  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. -->
+
+# funnel-test-512
+
+This model is a fine-tuned version of [funnel-transformer/xlarge-base](https://huggingface.co/funnel-transformer/xlarge-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4556
+- Accuracy: 0.8041
+
+## 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: 1e-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: 1
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.6108        | 0.2   | 59   | 0.6724          | 0.6460   |
+| 0.651         | 0.4   | 118  | 0.6463          | 0.6451   |
+| 0.6052        | 0.61  | 177  | 0.6210          | 0.6424   |
+| 0.4588        | 0.81  | 236  | 0.4556          | 0.8041   |
+
+
+### Framework versions
+
+- Transformers 4.36.2
+- Pytorch 2.0.1
+- Datasets 2.16.1
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,49 @@
+{
+  "_name_or_path": "funnel-transformer/xlarge-base",
+  "activation_dropout": 0.0,
+  "architectures": [
+    "FunnelForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "attention_type": "relative_shift",
+  "block_repeats": [
+    1,
+    1,
+    1
+  ],
+  "block_sizes": [
+    10,
+    10,
+    10
+  ],
+  "d_head": 64,
+  "d_inner": 4096,
+  "d_model": 1024,
+  "hidden_act": "gelu_new",
+  "hidden_dropout": 0.1,
+  "id2label": {
+    "0": "HUMAN",
+    "1": "AI"
+  },
+  "initializer_range": 0.1,
+  "initializer_std": null,
+  "label2id": {
+    "AI": 1,
+    "HUMAN": 0
+  },
+  "layer_norm_eps": 1e-09,
+  "max_position_embeddings": 512,
+  "model_type": "funnel",
+  "n_head": 16,
+  "num_decoder_layers": 2,
+  "pool_q_only": true,
+  "pooling_type": "mean",
+  "problem_type": "single_label_classification",
+  "rel_attn_type": "factorized",
+  "separate_cls": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "truncate_seq": true,
+  "type_vocab_size": 3,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86b3ddded2fdf1a7e1d1657cce68a53b3c80a1041fae02e44156b450d5770602
+size 1767173656

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<cls>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "<sep>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,75 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "96": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "97": {
+      "content": "</s>",
+      "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
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<cls>",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "<pad>",
+  "sep_token": "<sep>",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "FunnelTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b48da4236c403c99cf0915d65875fcc96978c9a77c24cd3b7e8948fb7b1d878
+size 4219