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: 0.946372926235199
+
+f1_macro: 0.5230769230769231
+
+f1_micro: 0.7391304347826086
+
+f1_weighted: 0.7210702341137124
+
+precision_macro: 0.5277777777777778
+
+precision_micro: 0.7391304347826086
+
+precision_weighted: 0.710144927536232
+
+recall_macro: 0.5238095238095238
+
+recall_micro: 0.7391304347826086
+
+recall_weighted: 0.7391304347826086
+
+accuracy: 0.7391304347826086

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:faba478211bafa2450a74a6896510b1fd2413f04364a6ff5c61a935b2aacc530
+size 4968

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": "9b4cca20eb4faa4e",
+  "_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 sha256:56d817b35396ed4ddbce23ad7e048c1e28edbb59b5cb74fd5efbcf3545929500
+size 2016

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": "6bedf6a163b52e5f",
+  "_format_columns": [
+    "autotrain_text",
+    "autotrain_label"
+  ],
+  "_format_kwargs": {},
+  "_format_type": null,
+  "_output_all_columns": false,
+  "_split": null
+}

checkpoint-24/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-24/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05f5fe93423f2170a62ee644856c8c4f77c413bc8b152f40f3b63706294d6e58
+size 1112208084

checkpoint-24/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3426c89a8770d0331873dc0f6226443d6866907429c3754f330cd87365ebeb06
+size 2224530170

checkpoint-24/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9f949ebd38ae8393cd3eda0d6e6eb2354426cc686b2885735ccaeaea9352ebe
+size 13990

checkpoint-24/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c16a55e06cfdab3977ba138cb50c04901f2c418a126fa98556f2de0b0f4689f3
+size 1064

checkpoint-24/trainer_state.json

@@ -0,0 +1,264 @@
+{
+  "best_metric": 0.946372926235199,
+  "best_model_checkpoint": "finetune-tiktok-brat7\\checkpoint-24",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 24,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.125,
+      "grad_norm": 48.439212799072266,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 1.298,
+      "step": 1
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 17.51978874206543,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.3288,
+      "step": 2
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 36.70003128051758,
+      "learning_rate": 1e-05,
+      "loss": 0.5146,
+      "step": 3
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 36.54575729370117,
+      "learning_rate": 9.523809523809525e-06,
+      "loss": 1.3186,
+      "step": 4
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 38.397705078125,
+      "learning_rate": 9.047619047619049e-06,
+      "loss": 1.0083,
+      "step": 5
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 52.007572174072266,
+      "learning_rate": 8.571428571428571e-06,
+      "loss": 0.9936,
+      "step": 6
+    },
+    {
+      "epoch": 0.875,
+      "grad_norm": 57.42391586303711,
+      "learning_rate": 8.095238095238097e-06,
+      "loss": 1.1921,
+      "step": 7
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 39.129276275634766,
+      "learning_rate": 7.61904761904762e-06,
+      "loss": 1.2205,
+      "step": 8
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6521739130434783,
+      "eval_f1_macro": 0.4761904761904762,
+      "eval_f1_micro": 0.6521739130434783,
+      "eval_f1_weighted": 0.6521739130434783,
+      "eval_loss": 1.1324578523635864,
+      "eval_precision_macro": 0.4761904761904762,
+      "eval_precision_micro": 0.6521739130434783,
+      "eval_precision_weighted": 0.6521739130434783,
+      "eval_recall_macro": 0.4761904761904762,
+      "eval_recall_micro": 0.6521739130434783,
+      "eval_recall_weighted": 0.6521739130434783,
+      "eval_runtime": 27.369,
+      "eval_samples_per_second": 0.84,
+      "eval_steps_per_second": 0.073,
+      "step": 8
+    },
+    {
+      "epoch": 1.125,
+      "grad_norm": 30.69573211669922,
+      "learning_rate": 7.1428571428571436e-06,
+      "loss": 0.8532,
+      "step": 9
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 19.239377975463867,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.718,
+      "step": 10
+    },
+    {
+      "epoch": 1.375,
+      "grad_norm": 36.98495101928711,
+      "learning_rate": 6.1904761904761914e-06,
+      "loss": 0.7192,
+      "step": 11
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 29.336002349853516,
+      "learning_rate": 5.7142857142857145e-06,
+      "loss": 1.0733,
+      "step": 12
+    },
+    {
+      "epoch": 1.625,
+      "grad_norm": 8.844223022460938,
+      "learning_rate": 5.2380952380952384e-06,
+      "loss": 0.2654,
+      "step": 13
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 17.313766479492188,
+      "learning_rate": 4.761904761904762e-06,
+      "loss": 0.643,
+      "step": 14
+    },
+    {
+      "epoch": 1.875,
+      "grad_norm": 12.483030319213867,
+      "learning_rate": 4.2857142857142855e-06,
+      "loss": 0.3099,
+      "step": 15
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 8.137201309204102,
+      "learning_rate": 3.80952380952381e-06,
+      "loss": 0.0809,
+      "step": 16
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6956521739130435,
+      "eval_f1_macro": 0.49096880131362886,
+      "eval_f1_micro": 0.6956521739130435,
+      "eval_f1_weighted": 0.6791604197901049,
+      "eval_loss": 0.9708660840988159,
+      "eval_precision_macro": 0.48253968253968255,
+      "eval_precision_micro": 0.6956521739130435,
+      "eval_precision_weighted": 0.6637681159420289,
+      "eval_recall_macro": 0.5,
+      "eval_recall_micro": 0.6956521739130435,
+      "eval_recall_weighted": 0.6956521739130435,
+      "eval_runtime": 27.3832,
+      "eval_samples_per_second": 0.84,
+      "eval_steps_per_second": 0.073,
+      "step": 16
+    },
+    {
+      "epoch": 2.125,
+      "grad_norm": 15.641371726989746,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.4351,
+      "step": 17
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 23.520936965942383,
+      "learning_rate": 2.8571428571428573e-06,
+      "loss": 0.4472,
+      "step": 18
+    },
+    {
+      "epoch": 2.375,
+      "grad_norm": 19.283954620361328,
+      "learning_rate": 2.380952380952381e-06,
+      "loss": 0.216,
+      "step": 19
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 35.63965606689453,
+      "learning_rate": 1.904761904761905e-06,
+      "loss": 0.5644,
+      "step": 20
+    },
+    {
+      "epoch": 2.625,
+      "grad_norm": 14.39991283416748,
+      "learning_rate": 1.4285714285714286e-06,
+      "loss": 0.4427,
+      "step": 21
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 22.22780418395996,
+      "learning_rate": 9.523809523809525e-07,
+      "loss": 0.4644,
+      "step": 22
+    },
+    {
+      "epoch": 2.875,
+      "grad_norm": 21.318103790283203,
+      "learning_rate": 4.7619047619047623e-07,
+      "loss": 0.5123,
+      "step": 23
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 20.380773544311523,
+      "learning_rate": 0.0,
+      "loss": 0.8922,
+      "step": 24
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7391304347826086,
+      "eval_f1_macro": 0.5230769230769231,
+      "eval_f1_micro": 0.7391304347826086,
+      "eval_f1_weighted": 0.7210702341137124,
+      "eval_loss": 0.946372926235199,
+      "eval_precision_macro": 0.5277777777777778,
+      "eval_precision_micro": 0.7391304347826086,
+      "eval_precision_weighted": 0.710144927536232,
+      "eval_recall_macro": 0.5238095238095238,
+      "eval_recall_micro": 0.7391304347826086,
+      "eval_recall_weighted": 0.7391304347826086,
+      "eval_runtime": 27.6232,
+      "eval_samples_per_second": 0.833,
+      "eval_steps_per_second": 0.072,
+      "step": 24
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 24,
+  "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": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 46571074937856.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-24/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9b050b0ef212bec5d00b2af8ebbfd6cf5b41ea3e5dfdad889542b5a12122389
+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 sha256:05f5fe93423f2170a62ee644856c8c4f77c413bc8b152f40f3b63706294d6e58
+size 1112208084

runs/Nov24_00-33-58_DESKTOP-PHPU4HD/events.out.tfevents.1732404840.DESKTOP-PHPU4HD.3204.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:423c1e04de7a77a5d4bd89564096d2ee5f5d62ca03bbfbc46156b051a748bac6
-size 10347
+oid sha256:0321ddf4586f81259c92a728dc4d5a01e88daa1c1acd2d3b4b852387f568f0b5
+size 13169

runs/Nov24_00-33-58_DESKTOP-PHPU4HD/events.out.tfevents.1732405835.DESKTOP-PHPU4HD.3204.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1a80e85a1b2913d74ce65df8406bff99c114b6f274ecfbddd7006ac813cd2cd
+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:e9b050b0ef212bec5d00b2af8ebbfd6cf5b41ea3e5dfdad889542b5a12122389
+size 5304

training_params.json

@@ -0,0 +1,30 @@
+{
+    "data_path": "finetune-tiktok-brat7/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-brat7",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "eval_strategy": "epoch",
+    "username": "Lyreck",
+    "log": "tensorboard",
+    "early_stopping_patience": 5,
+    "early_stopping_threshold": 0.01
+}