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: FacebookAI/xlm-roberta-large
+widget:
+- text: "I love AutoTrain"
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Text Classification
+
+## Validation Metrics
+loss: 2.0163416862487793
+
+f1_macro: 0.17560544673032039
+
+f1_micro: 0.234
+
+f1_weighted: 0.17560544673032036
+
+precision_macro: 0.3230402136577736
+
+precision_micro: 0.234
+
+precision_weighted: 0.3230402136577736
+
+recall_macro: 0.23400000000000004
+
+recall_micro: 0.234
+
+recall_weighted: 0.234
+
+accuracy: 0.234

checkpoint-750/config.json

@@ -0,0 +1,54 @@
+{
+  "_name_or_path": "FacebookAI/xlm-roberta-large",
+  "_num_labels": 10,
+  "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": 1024,
+  "id2label": {
+    "0": "AR",
+    "1": "BR",
+    "2": "CN",
+    "3": "FR",
+    "4": "IL",
+    "5": "IQ",
+    "6": "IT",
+    "7": "JP",
+    "8": "KR",
+    "9": "RU"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "AR": 0,
+    "BR": 1,
+    "CN": 2,
+    "FR": 3,
+    "IL": 4,
+    "IQ": 5,
+    "IT": 6,
+    "JP": 7,
+    "KR": 8,
+    "RU": 9
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

checkpoint-750/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b54fc65585891e0a96fc4e750f2cd7fede7dba2feb83a7a6c0237f998cc755c
+size 2239651472

checkpoint-750/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95d6add3d2caeae21aee3c8bea2d06c34d9d78653ac8bcaf9e3fefebb4a1ee48
+size 4479538321

checkpoint-750/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fe1c1b51385bc8d6cbefc8e1ef280e091092646ec858a1f4ce182968bf9f76f
+size 14512

checkpoint-750/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0016d965aaaea2bb8a9108508f5e0bf3cbaaa4b01512432612f20846d52ba2c1
+size 14512

checkpoint-750/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:feb973e535a321245a557f9c15d0ea755e12d349c68f2fb246881a74875cb21f
+size 1064

checkpoint-750/trainer_state.json

@@ -0,0 +1,306 @@
+{
+  "best_metric": 2.0163416862487793,
+  "best_model_checkpoint": "910-3-roberta-10/checkpoint-750",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 750,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "grad_norm": 23.742645263671875,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 2.3895,
+      "step": 25
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 11.274296760559082,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 2.3348,
+      "step": 50
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 7.359958171844482,
+      "learning_rate": 5e-06,
+      "loss": 2.3217,
+      "step": 75
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 8.179986000061035,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 2.3207,
+      "step": 100
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 18.304018020629883,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 2.2965,
+      "step": 125
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 12.443976402282715,
+      "learning_rate": 1e-05,
+      "loss": 2.3036,
+      "step": 150
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 14.003621101379395,
+      "learning_rate": 1.1666666666666668e-05,
+      "loss": 2.2321,
+      "step": 175
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 12.123735427856445,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 2.218,
+      "step": 200
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 26.824359893798828,
+      "learning_rate": 1.5e-05,
+      "loss": 2.1573,
+      "step": 225
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 12.286924362182617,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 2.146,
+      "step": 250
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.1845,
+      "eval_f1_macro": 0.0987979652095434,
+      "eval_f1_micro": 0.1845,
+      "eval_f1_weighted": 0.09879796520954343,
+      "eval_loss": 2.1069414615631104,
+      "eval_precision_macro": 0.10847279767673075,
+      "eval_precision_micro": 0.1845,
+      "eval_precision_weighted": 0.10847279767673075,
+      "eval_recall_macro": 0.1845,
+      "eval_recall_micro": 0.1845,
+      "eval_recall_weighted": 0.1845,
+      "eval_runtime": 5.8665,
+      "eval_samples_per_second": 340.92,
+      "eval_steps_per_second": 5.455,
+      "step": 250
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 13.818865776062012,
+      "learning_rate": 1.8333333333333333e-05,
+      "loss": 2.1453,
+      "step": 275
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 16.149505615234375,
+      "learning_rate": 2e-05,
+      "loss": 2.1011,
+      "step": 300
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 24.287403106689453,
+      "learning_rate": 2.1666666666666667e-05,
+      "loss": 2.087,
+      "step": 325
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 8.6444673538208,
+      "learning_rate": 2.3333333333333336e-05,
+      "loss": 2.11,
+      "step": 350
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 18.66366195678711,
+      "learning_rate": 2.5e-05,
+      "loss": 2.0991,
+      "step": 375
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 8.785151481628418,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 2.0281,
+      "step": 400
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 9.933465957641602,
+      "learning_rate": 2.8333333333333335e-05,
+      "loss": 2.0634,
+      "step": 425
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 13.846152305603027,
+      "learning_rate": 3e-05,
+      "loss": 2.0504,
+      "step": 450
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 24.698633193969727,
+      "learning_rate": 3.1666666666666666e-05,
+      "loss": 2.0754,
+      "step": 475
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 13.607393264770508,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 2.0,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.224,
+      "eval_f1_macro": 0.15699864365105617,
+      "eval_f1_micro": 0.224,
+      "eval_f1_weighted": 0.15699864365105617,
+      "eval_loss": 2.0973894596099854,
+      "eval_precision_macro": 0.17293733079797044,
+      "eval_precision_micro": 0.224,
+      "eval_precision_weighted": 0.17293733079797044,
+      "eval_recall_macro": 0.22400000000000003,
+      "eval_recall_micro": 0.224,
+      "eval_recall_weighted": 0.224,
+      "eval_runtime": 5.9646,
+      "eval_samples_per_second": 335.311,
+      "eval_steps_per_second": 5.365,
+      "step": 500
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 10.633151054382324,
+      "learning_rate": 3.5e-05,
+      "loss": 1.9934,
+      "step": 525
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 11.844949722290039,
+      "learning_rate": 3.6666666666666666e-05,
+      "loss": 1.9635,
+      "step": 550
+    },
+    {
+      "epoch": 2.3,
+      "grad_norm": 11.696029663085938,
+      "learning_rate": 3.8333333333333334e-05,
+      "loss": 1.9717,
+      "step": 575
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 10.775115966796875,
+      "learning_rate": 4e-05,
+      "loss": 1.99,
+      "step": 600
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 12.655854225158691,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 1.9839,
+      "step": 625
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 11.810218811035156,
+      "learning_rate": 4.3333333333333334e-05,
+      "loss": 1.9982,
+      "step": 650
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 8.966118812561035,
+      "learning_rate": 4.5e-05,
+      "loss": 1.9561,
+      "step": 675
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 14.116168975830078,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 1.9757,
+      "step": 700
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 26.801786422729492,
+      "learning_rate": 4.8333333333333334e-05,
+      "loss": 2.0137,
+      "step": 725
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 21.48545265197754,
+      "learning_rate": 5e-05,
+      "loss": 2.0136,
+      "step": 750
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.234,
+      "eval_f1_macro": 0.17560544673032039,
+      "eval_f1_micro": 0.234,
+      "eval_f1_weighted": 0.17560544673032036,
+      "eval_loss": 2.0163416862487793,
+      "eval_precision_macro": 0.3230402136577736,
+      "eval_precision_micro": 0.234,
+      "eval_precision_weighted": 0.3230402136577736,
+      "eval_recall_macro": 0.23400000000000004,
+      "eval_recall_micro": 0.234,
+      "eval_recall_weighted": 0.234,
+      "eval_runtime": 5.9722,
+      "eval_samples_per_second": 334.883,
+      "eval_steps_per_second": 5.358,
+      "step": 750
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 7500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 30,
+  "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": 5591739389706240.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-750/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:434f572b9ba41a9bce30f07ae3bc12b581eb66be4c641233e031b89b375065a8
+size 5176

config.json

@@ -0,0 +1,54 @@
+{
+  "_name_or_path": "FacebookAI/xlm-roberta-large",
+  "_num_labels": 10,
+  "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": 1024,
+  "id2label": {
+    "0": "AR",
+    "1": "BR",
+    "2": "CN",
+    "3": "FR",
+    "4": "IL",
+    "5": "IQ",
+    "6": "IT",
+    "7": "JP",
+    "8": "KR",
+    "9": "RU"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "AR": 0,
+    "BR": 1,
+    "CN": 2,
+    "FR": 3,
+    "IL": 4,
+    "IQ": 5,
+    "IT": 6,
+    "JP": 7,
+    "KR": 8,
+    "RU": 9
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.1",
+  "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 sha256:7b54fc65585891e0a96fc4e750f2cd7fede7dba2feb83a7a6c0237f998cc755c
+size 2239651472

runs/Sep10_22-03-10_irl-24/events.out.tfevents.1725973393.irl-24.215584.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2712e808e4bfa8f450073fefb15f92c0e2865d3ed6eab5820b9df1f7b26aeac5
-size 17684
+oid sha256:493847c464fafc507eff6ccf4905fcef1812788299a438682d13e338e1fae161
+size 29177

runs/Sep10_22-03-10_irl-24/events.out.tfevents.1725974543.irl-24.215584.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad1c7d3a7de5b292745c18f5a8beb59f2677c5943d81817dac7055acdca5353d
+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 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

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 sha256:434f572b9ba41a9bce30f07ae3bc12b581eb66be4c641233e031b89b375065a8
+size 5176

training_params.json

@@ -0,0 +1,30 @@
+{
+    "data_path": "910-3-roberta-10/autotrain-data",
+    "model": "FacebookAI/xlm-roberta-large",
+    "lr": 5e-05,
+    "epochs": 30,
+    "max_seq_length": 128,
+    "batch_size": 16,
+    "warmup_ratio": 0.1,
+    "gradient_accumulation": 1,
+    "optimizer": "adamw_torch",
+    "scheduler": "cosine_with_restarts",
+    "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": "910-3-roberta-10",
+    "auto_find_batch_size": false,
+    "mixed_precision": "none",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "eval_strategy": "epoch",
+    "username": "dzd828",
+    "log": "tensorboard",
+    "early_stopping_patience": 5,
+    "early_stopping_threshold": 0.01
+}