SciGPT2-ft-TweetAreas-ES

README.md

@@ -0,0 +1,77 @@
+---
+license: mit
+base_model: DeepESP/gpt2-spanish
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+model-index:
+- name: SciGPT2-ft-TweetAreas-ES
+  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. -->
+
+# SciGPT2-ft-TweetAreas-ES
+
+This model is a fine-tuned version of [DeepESP/gpt2-spanish](https://huggingface.co/DeepESP/gpt2-spanish) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2090
+- Roc Auc: 0.7863
+- Hamming Loss: 0.0548
+- F1 Score: 0.6523
+- Accuracy: 0.4083
+- Precision: 0.8301
+- Recall: 0.6023
+
+## 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: 4
+- eval_batch_size: 4
+- 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 | Roc Auc | Hamming Loss | F1 Score | Accuracy | Precision | Recall |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:------------:|:--------:|:--------:|:---------:|:------:|
+| 0.1499        | 1.0   | 747  | 0.1910          | 0.7062  | 0.0689       | 0.4861   | 0.3320   | 0.8506    | 0.4443 |
+| 0.1593        | 2.0   | 1494 | 0.1707          | 0.7546  | 0.0636       | 0.5862   | 0.3494   | 0.7958    | 0.5444 |
+| 0.1042        | 3.0   | 2241 | 0.1700          | 0.7718  | 0.0617       | 0.6133   | 0.3748   | 0.7891    | 0.5812 |
+| 0.0455        | 4.0   | 2988 | 0.1786          | 0.7934  | 0.0585       | 0.6533   | 0.3855   | 0.7900    | 0.6232 |
+| 0.0378        | 5.0   | 3735 | 0.1896          | 0.7903  | 0.0571       | 0.6564   | 0.3882   | 0.8020    | 0.6093 |
+| 0.0199        | 6.0   | 4482 | 0.1948          | 0.7983  | 0.0566       | 0.6627   | 0.3949   | 0.7763    | 0.6304 |
+| 0.0101        | 7.0   | 5229 | 0.2014          | 0.7888  | 0.0553       | 0.6625   | 0.3963   | 0.8127    | 0.6069 |
+| 0.0087        | 8.0   | 5976 | 0.2059          | 0.7830  | 0.0563       | 0.6507   | 0.3922   | 0.8271    | 0.5969 |
+| 0.0071        | 9.0   | 6723 | 0.2074          | 0.7888  | 0.0550       | 0.6587   | 0.4070   | 0.8304    | 0.6080 |
+| 0.0047        | 10.0  | 7470 | 0.2090          | 0.7863  | 0.0548       | 0.6523   | 0.4083   | 0.8301    | 0.6023 |
+
+
+### Framework versions
+
+- Transformers 4.43.2
+- Pytorch 2.3.1+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,82 @@
+{
+  "_name_or_path": "DeepESP/gpt2-spanish",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2ForSequenceClassification"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "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"
+  },
+  "initializer_range": 0.02,
+  "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_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "pad_token_id": 50256,
+  "problem_type": "multi_label_classification",
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.43.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:deab3157aa2259bd3ae237cb1ca1312d99084e51baf0dcbdb2de0c85ce0ec2a9
+size 497829584

special_tokens_map.json

@@ -0,0 +1,36 @@
+{
+  "additional_special_tokens": [
+    "<|talk|>",
+    "<|ax1|>",
+    "<|ax2|>",
+    "<|ax3|>",
+    "<|ax4|>",
+    "<|ax5|>",
+    "<|ax6|>",
+    "<|ax7|>",
+    "<|ax8|>",
+    "<|ax9|>"
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,115 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|talk|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|ax1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|ax2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<|ax3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<|ax4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<|ax5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<|ax6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<|ax7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<|ax8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<|ax9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|talk|>",
+    "<|ax1|>",
+    "<|ax2|>",
+    "<|ax3|>",
+    "<|ax4|>",
+    "<|ax5|>",
+    "<|ax6|>",
+    "<|ax7|>",
+    "<|ax8|>",
+    "<|ax9|>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "full_tokenizer_file": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5404cbd326ecf3b9a7fd7c4a3a051c3ffc85b339cc094d00eb8ab877a8661895
+size 5176