Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,36 @@
+
+---
+tags:
+- autotrain
+- text-classification
+base_model: cardiffnlp/twitter-xlm-roberta-base-sentiment-multilingual
+widget:
+- text: "I love AutoTrain"
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Text Classification
+
+## Validation Metrics
+loss: 0.8851654529571533
+
+f1_macro: 0.6377799415774099
+
+f1_micro: 0.6805555555555556
+
+f1_weighted: 0.6723466407010711
+
+precision_macro: 0.6714285714285714
+
+precision_micro: 0.6805555555555556
+
+precision_weighted: 0.680952380952381
+
+recall_macro: 0.6266299193930772
+
+recall_micro: 0.6805555555555556
+
+recall_weighted: 0.6805555555555556
+
+accuracy: 0.6805555555555556

autotrain-data/dataset_dict.json

@@ -0,0 +1 @@
+{"splits": ["train", "validation"]}

autotrain-data/train/data-00000-of-00001.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02810de510790996f2d7a34f31ee52772d7bfba9395f8c15d62e3405e14645f4
+size 15848

autotrain-data/train/dataset_info.json

@@ -0,0 +1,20 @@
+{
+  "citation": "",
+  "description": "",
+  "features": {
+    "autotrain_text": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "autotrain_label": {
+      "names": [
+        "0",
+        "1",
+        "2"
+      ],
+      "_type": "ClassLabel"
+    }
+  },
+  "homepage": "",
+  "license": ""
+}

autotrain-data/train/state.json

@@ -0,0 +1,16 @@
+{
+  "_data_files": [
+    {
+      "filename": "data-00000-of-00001.arrow"
+    }
+  ],
+  "_fingerprint": "5accd5d6b3bde0e9",
+  "_format_columns": [
+    "autotrain_text",
+    "autotrain_label"
+  ],
+  "_format_kwargs": {},
+  "_format_type": null,
+  "_output_all_columns": false,
+  "_split": null
+}

autotrain-data/validation/data-00000-of-00001.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d528e914e8734813f59c55c533a208cec1911a85af2201bb06e1461f4ba4714f
+size 4840

autotrain-data/validation/dataset_info.json

@@ -0,0 +1,20 @@
+{
+  "citation": "",
+  "description": "",
+  "features": {
+    "autotrain_text": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "autotrain_label": {
+      "names": [
+        "0",
+        "1",
+        "2"
+      ],
+      "_type": "ClassLabel"
+    }
+  },
+  "homepage": "",
+  "license": ""
+}

autotrain-data/validation/state.json

@@ -0,0 +1,16 @@
+{
+  "_data_files": [
+    {
+      "filename": "data-00000-of-00001.arrow"
+    }
+  ],
+  "_fingerprint": "e3a5ba35b79dc8e7",
+  "_format_columns": [
+    "autotrain_text",
+    "autotrain_label"
+  ],
+  "_format_kwargs": {},
+  "_format_type": null,
+  "_output_all_columns": false,
+  "_split": null
+}

checkpoint-20/config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "cardiffnlp/twitter-xlm-roberta-base-sentiment-multilingual",
+  "_num_labels": 3,
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "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,
+  "id2label": {
+    "0": "0",
+    "1": "1",
+    "2": "2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "0": 0,
+    "1": 1,
+    "2": 2
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

checkpoint-20/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f7d65ebad7bf1b91b08ebc797a36d368613245e7c28f1a0dfcff55963b0fc1c
+size 1112208084

checkpoint-20/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c68b16ebae358875a2a248b5c6abf5b7177e08a80ee0fb58265cd56778433056
+size 2224530170

checkpoint-20/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65713b8cc4d6edc13dbc8bb0611c7d04eff5ce2e51c913293465d1192c9a9ca1
+size 13990

checkpoint-20/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bcfd4d0a8859e2aa8f8cbbc4395780e4509cc0bd5f22b24f929e6402982f859
+size 1064

checkpoint-20/trainer_state.json

@@ -0,0 +1,200 @@
+{
+  "best_metric": 0.8851654529571533,
+  "best_model_checkpoint": "finetune-tiktok-brat4\\checkpoint-20",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 20,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "grad_norm": 54.496673583984375,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 0.7894,
+      "step": 1
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 11.606372833251953,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.7589,
+      "step": 2
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 38.31898498535156,
+      "learning_rate": 5e-06,
+      "loss": 1.2543,
+      "step": 3
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 47.521976470947266,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.8361,
+      "step": 4
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 23.255413055419922,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.2909,
+      "step": 5
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 36.35523986816406,
+      "learning_rate": 1e-05,
+      "loss": 0.7906,
+      "step": 6
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 35.16067886352539,
+      "learning_rate": 9.814814814814815e-06,
+      "loss": 0.96,
+      "step": 7
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 36.35455322265625,
+      "learning_rate": 9.62962962962963e-06,
+      "loss": 0.3895,
+      "step": 8
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 119.45866394042969,
+      "learning_rate": 9.444444444444445e-06,
+      "loss": 0.5939,
+      "step": 9
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 32.66160202026367,
+      "learning_rate": 9.25925925925926e-06,
+      "loss": 0.9343,
+      "step": 10
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 16.789913177490234,
+      "learning_rate": 9.074074074074075e-06,
+      "loss": 0.6067,
+      "step": 11
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 13.208721160888672,
+      "learning_rate": 8.888888888888888e-06,
+      "loss": 0.3274,
+      "step": 12
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 21.66659927368164,
+      "learning_rate": 8.703703703703705e-06,
+      "loss": 1.8018,
+      "step": 13
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 14.522764205932617,
+      "learning_rate": 8.518518518518519e-06,
+      "loss": 0.9705,
+      "step": 14
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 33.81802749633789,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 1.3949,
+      "step": 15
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 46.284576416015625,
+      "learning_rate": 8.148148148148148e-06,
+      "loss": 1.7191,
+      "step": 16
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 18.38251304626465,
+      "learning_rate": 7.962962962962963e-06,
+      "loss": 0.4667,
+      "step": 17
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 18.9488582611084,
+      "learning_rate": 7.77777777777778e-06,
+      "loss": 1.1351,
+      "step": 18
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 9.29172420501709,
+      "learning_rate": 7.592592592592594e-06,
+      "loss": 0.1151,
+      "step": 19
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 39.511680603027344,
+      "learning_rate": 7.4074074074074075e-06,
+      "loss": 1.3048,
+      "step": 20
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6805555555555556,
+      "eval_f1_macro": 0.6377799415774099,
+      "eval_f1_micro": 0.6805555555555556,
+      "eval_f1_weighted": 0.6723466407010711,
+      "eval_loss": 0.8851654529571533,
+      "eval_precision_macro": 0.6714285714285714,
+      "eval_precision_micro": 0.6805555555555556,
+      "eval_precision_weighted": 0.680952380952381,
+      "eval_recall_macro": 0.6266299193930772,
+      "eval_recall_micro": 0.6805555555555556,
+      "eval_recall_weighted": 0.6805555555555556,
+      "eval_runtime": 85.5963,
+      "eval_samples_per_second": 0.841,
+      "eval_steps_per_second": 0.058,
+      "step": 20
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 60,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 0.01
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 42098146836480.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-20/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:928b58ff9e8515e921d6e412d5d9b7c13fbfd1ee7f1da5d801773cc16896e913
+size 5304

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "cardiffnlp/twitter-xlm-roberta-base-sentiment-multilingual",
+  "_num_labels": 3,
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "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,
+  "id2label": {
+    "0": "0",
+    "1": "1",
+    "2": "2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "0": 0,
+    "1": 1,
+    "2": 2
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f7d65ebad7bf1b91b08ebc797a36d368613245e7c28f1a0dfcff55963b0fc1c
+size 1112208084

runs/Dec15_13-08-39_DESKTOP-PHPU4HD/events.out.tfevents.1734264520.DESKTOP-PHPU4HD.13408.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acf102e93406c608322828aabbd3b6f7cfdfde06b8f02becf3c828c5fd1afe1a
-size 16558
+oid sha256:bfdfbd373cc46f49bf1e52f638a91f75a832452a6034080c01f0dbf9fd56b642
+size 20622

runs/Dec15_13-08-39_DESKTOP-PHPU4HD/events.out.tfevents.1734267115.DESKTOP-PHPU4HD.13408.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fedddacca51454a55a17e77956b221987babfa57e0a91c981f326d7c437f5c9
+size 906

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

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": true,
+    "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.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ffb37461c391f096759f4a9bbbc329da0f36952f88bab061fcf84940c022e98
+size 17082999

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
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "max_length": 128,
+  "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": "XLMRobertaTokenizer",
+  "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 sha256:928b58ff9e8515e921d6e412d5d9b7c13fbfd1ee7f1da5d801773cc16896e913
+size 5304

training_params.json

@@ -0,0 +1,30 @@
+{
+    "data_path": "finetune-tiktok-brat4/autotrain-data",
+    "model": "cardiffnlp/twitter-xlm-roberta-base-sentiment-multilingual",
+    "lr": 1e-05,
+    "epochs": 3,
+    "max_seq_length": 512,
+    "batch_size": 8,
+    "warmup_ratio": 0.1,
+    "gradient_accumulation": 1,
+    "optimizer": "adamw_torch",
+    "scheduler": "linear",
+    "weight_decay": 0.0,
+    "max_grad_norm": 1.0,
+    "seed": 42,
+    "train_split": "train",
+    "valid_split": "validation",
+    "text_column": "autotrain_text",
+    "target_column": "autotrain_label",
+    "logging_steps": -1,
+    "project_name": "finetune-tiktok-brat4",
+    "auto_find_batch_size": false,
+    "mixed_precision": null,
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "eval_strategy": "epoch",
+    "username": "Lyreck",
+    "log": "tensorboard",
+    "early_stopping_patience": 5,
+    "early_stopping_threshold": 0.01
+}