Suramya/Newmsd

README.md

@@ -0,0 +1,71 @@
+---
+license: apache-2.0
+base_model: somosnlp-hackathon-2022/twitter_sexismo-finetuned-robertuito-exist2021
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+model-index:
+- name: NewSpanishFinetunedtrainepoch10
+  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. -->
+
+# NewSpanishFinetunedtrainepoch10
+
+This model is a fine-tuned version of [somosnlp-hackathon-2022/twitter_sexismo-finetuned-robertuito-exist2021](https://huggingface.co/somosnlp-hackathon-2022/twitter_sexismo-finetuned-robertuito-exist2021) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.9422
+- Accuracy: 0.7818
+- F1: 0.7723
+
+## 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: 16
+- eval_batch_size: 64
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
+| No log        | 1.0   | 390  | 2.2975          | 0.75     | 0.7280 |
+| 0.0373        | 2.0   | 780  | 1.6730          | 0.7645   | 0.7570 |
+| 0.0227        | 3.0   | 1170 | 1.6890          | 0.7688   | 0.7536 |
+| 0.0303        | 4.0   | 1560 | 1.6623          | 0.7659   | 0.7573 |
+| 0.0303        | 5.0   | 1950 | 1.4957          | 0.7717   | 0.7588 |
+| 0.0133        | 6.0   | 2340 | 1.8339          | 0.7731   | 0.7627 |
+| 0.0086        | 7.0   | 2730 | 1.9297          | 0.7717   | 0.7651 |
+| 0.0031        | 8.0   | 3120 | 1.8540          | 0.7775   | 0.7677 |
+| 0.0021        | 9.0   | 3510 | 1.9277          | 0.7803   | 0.7704 |
+| 0.0021        | 10.0  | 3900 | 1.9422          | 0.7818   | 0.7723 |
+
+
+### Framework versions
+
+- Transformers 4.40.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "somosnlp-hackathon-2022/twitter_sexismo-finetuned-robertuito-exist2021",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 130,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 30000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5179ba9ca7945bd61aa89a1a16a5d2b9a5a168cb2da60293fa92d138e261a0bb
+size 435179080

runs/May06_19-39-25_890b8a612db0/events.out.tfevents.1715024371.890b8a612db0.9103.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fc34ef394a504048e7091aa5a45a6cf1419e0f68cdfbb9c9436b94bfff55ec2
+size 10422

runs/May06_19-39-25_890b8a612db0/events.out.tfevents.1715025323.890b8a612db0.9103.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:394cfb54e6b3ac09bf4b6f4c145fa546cd1d0bb13ee98f46903dba09b9712a77
+size 457

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "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": "</s>",
+    "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 +1,61 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "max_length": 120,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7db9b11676a72972ba045228dd6d17fc3e0b2afdb8e523e62f1c9397f1d05e4
+size 4984