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 +1,37 @@
+
+---
+tags:
+- autotrain
+- text-classification
+widget:
+- text: "I love AutoTrain"
+datasets:
+- autotrain-7ejr4-3wbhb/autotrain-data
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Text Classification
+
+## Validation Metrics
+loss: 0.34203216433525085
+
+f1_macro: 0.9457020850649197
+
+f1_micro: 0.946067415730337
+
+f1_weighted: 0.9461015789750475
+
+precision_macro: 0.9447370569809594
+
+precision_micro: 0.946067415730337
+
+precision_weighted: 0.9466487598452521
+
+recall_macro: 0.9472065189712249
+
+recall_micro: 0.946067415730337
+
+recall_weighted: 0.946067415730337
+
+accuracy: 0.946067415730337

checkpoint-446/config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "papluca/xlm-roberta-base-language-detection",
+  "_num_labels": 5,
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "business",
+    "1": "entertainment",
+    "2": "politics",
+    "3": "sport",
+    "4": "tech"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "business": 0,
+    "entertainment": 1,
+    "politics": 2,
+    "sport": 3,
+    "tech": 4
+  },
+  "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": "4.40.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

checkpoint-446/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9314d9a470ad4dc010ff93505deb3ee739b2c2937042c4416dd0a01d90e37222
+size 1112214236

checkpoint-446/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ddeff3b01c6e7e0ce4370df50b0170b722894b8224e22c470212ef51e4e680c
+size 2224548090

checkpoint-446/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53baf86f8a96a1dd3cf8551790d356b7f8592e5ad0257eef9380a747a00379f6
+size 14244

checkpoint-446/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4216d5b6dd557c6240c6a96b80fdf539ddaf40ac04a7e09efc71cbf5efda2d90
+size 1064

checkpoint-446/trainer_state.json

@@ -0,0 +1,337 @@
+{
+  "best_metric": 0.34203216433525085,
+  "best_model_checkpoint": "autotrain-7ejr4-3wbhb/checkpoint-446",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 446,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04932735426008968,
+      "grad_norm": 5.397119045257568,
+      "learning_rate": 8.208955223880597e-06,
+      "loss": 1.6001,
+      "step": 11
+    },
+    {
+      "epoch": 0.09865470852017937,
+      "grad_norm": 10.270828247070312,
+      "learning_rate": 1.6417910447761194e-05,
+      "loss": 1.6421,
+      "step": 22
+    },
+    {
+      "epoch": 0.14798206278026907,
+      "grad_norm": 6.842929363250732,
+      "learning_rate": 2.4626865671641793e-05,
+      "loss": 1.5659,
+      "step": 33
+    },
+    {
+      "epoch": 0.19730941704035873,
+      "grad_norm": 14.523164749145508,
+      "learning_rate": 3.208955223880597e-05,
+      "loss": 1.2199,
+      "step": 44
+    },
+    {
+      "epoch": 0.24663677130044842,
+      "grad_norm": Infinity,
+      "learning_rate": 3.9552238805970146e-05,
+      "loss": 0.9104,
+      "step": 55
+    },
+    {
+      "epoch": 0.29596412556053814,
+      "grad_norm": Infinity,
+      "learning_rate": 4.7014925373134335e-05,
+      "loss": 0.6866,
+      "step": 66
+    },
+    {
+      "epoch": 0.3452914798206278,
+      "grad_norm": 39.58903884887695,
+      "learning_rate": 4.941860465116279e-05,
+      "loss": 0.9257,
+      "step": 77
+    },
+    {
+      "epoch": 0.39461883408071746,
+      "grad_norm": 38.08815383911133,
+      "learning_rate": 4.8504983388704325e-05,
+      "loss": 0.5447,
+      "step": 88
+    },
+    {
+      "epoch": 0.4439461883408072,
+      "grad_norm": 32.093482971191406,
+      "learning_rate": 4.7674418604651164e-05,
+      "loss": 0.5951,
+      "step": 99
+    },
+    {
+      "epoch": 0.49327354260089684,
+      "grad_norm": 9.36325454711914,
+      "learning_rate": 4.684385382059801e-05,
+      "loss": 0.4972,
+      "step": 110
+    },
+    {
+      "epoch": 0.5426008968609866,
+      "grad_norm": 16.48912811279297,
+      "learning_rate": 4.593023255813954e-05,
+      "loss": 0.5117,
+      "step": 121
+    },
+    {
+      "epoch": 0.5919282511210763,
+      "grad_norm": 15.17750072479248,
+      "learning_rate": 4.5016611295681064e-05,
+      "loss": 0.5249,
+      "step": 132
+    },
+    {
+      "epoch": 0.6412556053811659,
+      "grad_norm": 73.44496154785156,
+      "learning_rate": 4.410299003322259e-05,
+      "loss": 0.2932,
+      "step": 143
+    },
+    {
+      "epoch": 0.6905829596412556,
+      "grad_norm": 7.012796878814697,
+      "learning_rate": 4.3189368770764125e-05,
+      "loss": 0.3703,
+      "step": 154
+    },
+    {
+      "epoch": 0.7399103139013453,
+      "grad_norm": 36.769142150878906,
+      "learning_rate": 4.227574750830565e-05,
+      "loss": 0.384,
+      "step": 165
+    },
+    {
+      "epoch": 0.7892376681614349,
+      "grad_norm": 0.5750433206558228,
+      "learning_rate": 4.136212624584718e-05,
+      "loss": 0.2024,
+      "step": 176
+    },
+    {
+      "epoch": 0.8385650224215246,
+      "grad_norm": 0.8097955584526062,
+      "learning_rate": 4.0448504983388706e-05,
+      "loss": 0.2261,
+      "step": 187
+    },
+    {
+      "epoch": 0.8878923766816144,
+      "grad_norm": 0.3052847683429718,
+      "learning_rate": 3.953488372093023e-05,
+      "loss": 0.3784,
+      "step": 198
+    },
+    {
+      "epoch": 0.9372197309417041,
+      "grad_norm": 9.378923416137695,
+      "learning_rate": 3.862126245847176e-05,
+      "loss": 0.334,
+      "step": 209
+    },
+    {
+      "epoch": 0.9865470852017937,
+      "grad_norm": 57.845924377441406,
+      "learning_rate": 3.7707641196013294e-05,
+      "loss": 0.5124,
+      "step": 220
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8337078651685393,
+      "eval_f1_macro": 0.8277707222765114,
+      "eval_f1_micro": 0.8337078651685393,
+      "eval_f1_weighted": 0.8270484241051885,
+      "eval_loss": 0.6007972359657288,
+      "eval_precision_macro": 0.8743021944472813,
+      "eval_precision_micro": 0.8337078651685393,
+      "eval_precision_weighted": 0.8814664248669926,
+      "eval_recall_macro": 0.8408823529411764,
+      "eval_recall_micro": 0.8337078651685393,
+      "eval_recall_weighted": 0.8337078651685393,
+      "eval_runtime": 1.7336,
+      "eval_samples_per_second": 256.693,
+      "eval_steps_per_second": 16.151,
+      "step": 223
+    },
+    {
+      "epoch": 1.0358744394618835,
+      "grad_norm": 4.146377086639404,
+      "learning_rate": 3.679401993355482e-05,
+      "loss": 0.4657,
+      "step": 231
+    },
+    {
+      "epoch": 1.0852017937219731,
+      "grad_norm": 2.958444833755493,
+      "learning_rate": 3.588039867109635e-05,
+      "loss": 0.2262,
+      "step": 242
+    },
+    {
+      "epoch": 1.1345291479820627,
+      "grad_norm": 18.36431312561035,
+      "learning_rate": 3.4966777408637875e-05,
+      "loss": 0.2503,
+      "step": 253
+    },
+    {
+      "epoch": 1.1838565022421526,
+      "grad_norm": 0.3763713538646698,
+      "learning_rate": 3.40531561461794e-05,
+      "loss": 0.1309,
+      "step": 264
+    },
+    {
+      "epoch": 1.2331838565022422,
+      "grad_norm": 0.1498165726661682,
+      "learning_rate": 3.313953488372093e-05,
+      "loss": 0.1149,
+      "step": 275
+    },
+    {
+      "epoch": 1.2825112107623318,
+      "grad_norm": 0.13080233335494995,
+      "learning_rate": 3.222591362126246e-05,
+      "loss": 0.2224,
+      "step": 286
+    },
+    {
+      "epoch": 1.3318385650224216,
+      "grad_norm": 6.366682052612305,
+      "learning_rate": 3.131229235880399e-05,
+      "loss": 0.3254,
+      "step": 297
+    },
+    {
+      "epoch": 1.3811659192825112,
+      "grad_norm": 0.08186858147382736,
+      "learning_rate": 3.0398671096345517e-05,
+      "loss": 0.0981,
+      "step": 308
+    },
+    {
+      "epoch": 1.4304932735426008,
+      "grad_norm": 0.14895343780517578,
+      "learning_rate": 2.9485049833887047e-05,
+      "loss": 0.1536,
+      "step": 319
+    },
+    {
+      "epoch": 1.4798206278026906,
+      "grad_norm": 0.07964171469211578,
+      "learning_rate": 2.857142857142857e-05,
+      "loss": 0.0458,
+      "step": 330
+    },
+    {
+      "epoch": 1.5291479820627802,
+      "grad_norm": 0.16557298600673676,
+      "learning_rate": 2.76578073089701e-05,
+      "loss": 0.2189,
+      "step": 341
+    },
+    {
+      "epoch": 1.57847533632287,
+      "grad_norm": 13.367328643798828,
+      "learning_rate": 2.674418604651163e-05,
+      "loss": 0.2818,
+      "step": 352
+    },
+    {
+      "epoch": 1.6278026905829597,
+      "grad_norm": 0.042071498930454254,
+      "learning_rate": 2.591362126245847e-05,
+      "loss": 0.1282,
+      "step": 363
+    },
+    {
+      "epoch": 1.6771300448430493,
+      "grad_norm": 0.0784522220492363,
+      "learning_rate": 2.5e-05,
+      "loss": 0.2491,
+      "step": 374
+    },
+    {
+      "epoch": 1.726457399103139,
+      "grad_norm": 0.17997685074806213,
+      "learning_rate": 2.4086378737541528e-05,
+      "loss": 0.022,
+      "step": 385
+    },
+    {
+      "epoch": 1.7757847533632287,
+      "grad_norm": 36.073631286621094,
+      "learning_rate": 2.3172757475083055e-05,
+      "loss": 0.1468,
+      "step": 396
+    },
+    {
+      "epoch": 1.8251121076233185,
+      "grad_norm": 46.98909378051758,
+      "learning_rate": 2.2259136212624586e-05,
+      "loss": 0.2726,
+      "step": 407
+    },
+    {
+      "epoch": 1.8744394618834082,
+      "grad_norm": 0.6519285440444946,
+      "learning_rate": 2.1345514950166116e-05,
+      "loss": 0.0038,
+      "step": 418
+    },
+    {
+      "epoch": 1.9237668161434978,
+      "grad_norm": 29.345619201660156,
+      "learning_rate": 2.0431893687707643e-05,
+      "loss": 0.251,
+      "step": 429
+    },
+    {
+      "epoch": 1.9730941704035874,
+      "grad_norm": 0.05096792057156563,
+      "learning_rate": 1.951827242524917e-05,
+      "loss": 0.3514,
+      "step": 440
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.946067415730337,
+      "eval_f1_macro": 0.9457020850649197,
+      "eval_f1_micro": 0.946067415730337,
+      "eval_f1_weighted": 0.9461015789750475,
+      "eval_loss": 0.34203216433525085,
+      "eval_precision_macro": 0.9447370569809594,
+      "eval_precision_micro": 0.946067415730337,
+      "eval_precision_weighted": 0.9466487598452521,
+      "eval_recall_macro": 0.9472065189712249,
+      "eval_recall_micro": 0.946067415730337,
+      "eval_recall_weighted": 0.946067415730337,
+      "eval_runtime": 1.7697,
+      "eval_samples_per_second": 251.457,
+      "eval_steps_per_second": 15.822,
+      "step": 446
+    }
+  ],
+  "logging_steps": 11,
+  "max_steps": 669,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 234175146792960.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-446/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dbb18bda7bd55a4f6a105f4c0cbfd62d9632c3a562cdbb4693af6112eb906d5
+size 5048

config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "papluca/xlm-roberta-base-language-detection",
+  "_num_labels": 5,
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "business",
+    "1": "entertainment",
+    "2": "politics",
+    "3": "sport",
+    "4": "tech"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "business": 0,
+    "entertainment": 1,
+    "politics": 2,
+    "sport": 3,
+    "tech": 4
+  },
+  "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": "4.40.1",
+  "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 sha256:9314d9a470ad4dc010ff93505deb3ee739b2c2937042c4416dd0a01d90e37222
+size 1112214236

runs/Apr30_06-44-49_r-nawincom-textclass2-hwsouds3-cf295-98bbt/events.out.tfevents.1714459490.r-nawincom-textclass2-hwsouds3-cf295-98bbt.62.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3c401c16df4fa1d676175f30ecaf140a0b8662038b26ca85a8a6d04b4b32a59
-size 5122
+oid sha256:eb010ef1d1ffd68fad1883964ec5e072f72cc6c14bccf9e5b2805e0f74d38bc8
+size 20591

runs/Apr30_06-44-49_r-nawincom-textclass2-hwsouds3-cf295-98bbt/events.out.tfevents.1714459650.r-nawincom-textclass2-hwsouds3-cf295-98bbt.62.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa0564add3d490875c3ac890e0a2c82a6dc4418ea671369301affd7347f382a6
+size 921

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 sha256:3c088c06cf975b7097e469bd69630cdb0d675c6db1ce3af1042b6e19c6d01f22
+size 17082999

tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "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": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dbb18bda7bd55a4f6a105f4c0cbfd62d9632c3a562cdbb4693af6112eb906d5
+size 5048

training_params.json

@@ -0,0 +1,28 @@
+{
+    "data_path": "autotrain-7ejr4-3wbhb/autotrain-data",
+    "model": "papluca/xlm-roberta-base-language-detection",
+    "lr": 5e-05,
+    "epochs": 3,
+    "max_seq_length": 128,
+    "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": "autotrain-7ejr4-3wbhb",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "evaluation_strategy": "epoch",
+    "username": "NawinCom",
+    "log": "tensorboard"
+}