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 +1,26 @@
+
+---
+tags:
+- autotrain
+- text-classification
+base_model: cardiffnlp/twitter-xlm-roberta-base
+widget:
+- text: "I love AutoTrain"
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Text Classification
+
+## Validation Metrics
+loss: 0.34269535541534424
+
+f1: 0.9375
+
+precision: 0.9375
+
+recall: 0.9375
+
+auc: 0.9765625
+
+accuracy: 0.9375

checkpoint-32/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "cardiffnlp/twitter-xlm-roberta-base",
+  "_num_labels": 2,
+  "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": "negative",
+    "1": "positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "negative": 0,
+    "positive": 1
+  },
+  "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": "4.47.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

checkpoint-32/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed7b83d41a2eb046912e3096aa1375f12d7b78adbfe0be04f13dc4b1b364eecb
+size 1112205008

checkpoint-32/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5a7cfafb6160413e722bae6f4683d79fdf92eae2cca201b7e37e1bd75131d29
+size 2224524026

checkpoint-32/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca5ec946fdfe90f34dd2bec0db0afd570db0736624eececc0c0580f46dd96c44
+size 13990

checkpoint-32/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4ff2218f62bde97e50cb49bf1f95d3ff0f01ec9d6f754eee57659160c70a8b7
+size 1064

checkpoint-32/trainer_state.json

@@ -0,0 +1,292 @@
+{
+  "best_metric": 0.34269535541534424,
+  "best_model_checkpoint": "robertafinetuninglargedatacsv/checkpoint-32",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 32,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0625,
+      "grad_norm": 3.306401252746582,
+      "learning_rate": 1.25e-06,
+      "loss": 0.7102,
+      "step": 1
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 2.7323529720306396,
+      "learning_rate": 2.5e-06,
+      "loss": 0.6948,
+      "step": 2
+    },
+    {
+      "epoch": 0.1875,
+      "grad_norm": 3.1906545162200928,
+      "learning_rate": 3.75e-06,
+      "loss": 0.6916,
+      "step": 3
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 1.5763970613479614,
+      "learning_rate": 5e-06,
+      "loss": 0.692,
+      "step": 4
+    },
+    {
+      "epoch": 0.3125,
+      "grad_norm": 1.4885941743850708,
+      "learning_rate": 6.25e-06,
+      "loss": 0.6793,
+      "step": 5
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 2.1479969024658203,
+      "learning_rate": 7.5e-06,
+      "loss": 0.683,
+      "step": 6
+    },
+    {
+      "epoch": 0.4375,
+      "grad_norm": 1.085968017578125,
+      "learning_rate": 8.75e-06,
+      "loss": 0.6944,
+      "step": 7
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 2.4903621673583984,
+      "learning_rate": 1e-05,
+      "loss": 0.6797,
+      "step": 8
+    },
+    {
+      "epoch": 0.5625,
+      "grad_norm": 1.4184839725494385,
+      "learning_rate": 1.125e-05,
+      "loss": 0.6806,
+      "step": 9
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 2.2620794773101807,
+      "learning_rate": 1.25e-05,
+      "loss": 0.7063,
+      "step": 10
+    },
+    {
+      "epoch": 0.6875,
+      "grad_norm": 3.0892398357391357,
+      "learning_rate": 1.3750000000000002e-05,
+      "loss": 0.7136,
+      "step": 11
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 2.0407421588897705,
+      "learning_rate": 1.5e-05,
+      "loss": 0.6863,
+      "step": 12
+    },
+    {
+      "epoch": 0.8125,
+      "grad_norm": 2.0362789630889893,
+      "learning_rate": 1.6250000000000002e-05,
+      "loss": 0.6805,
+      "step": 13
+    },
+    {
+      "epoch": 0.875,
+      "grad_norm": 2.197580099105835,
+      "learning_rate": 1.75e-05,
+      "loss": 0.6669,
+      "step": 14
+    },
+    {
+      "epoch": 0.9375,
+      "grad_norm": 2.920393228530884,
+      "learning_rate": 1.8750000000000002e-05,
+      "loss": 0.727,
+      "step": 15
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.498661994934082,
+      "learning_rate": 2e-05,
+      "loss": 0.7028,
+      "step": 16
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5,
+      "eval_auc": 0.796875,
+      "eval_f1": 0.6666666666666666,
+      "eval_loss": 0.6834808588027954,
+      "eval_precision": 0.5,
+      "eval_recall": 1.0,
+      "eval_runtime": 5.1228,
+      "eval_samples_per_second": 6.247,
+      "eval_steps_per_second": 0.39,
+      "step": 16
+    },
+    {
+      "epoch": 1.0625,
+      "grad_norm": 3.0374414920806885,
+      "learning_rate": 2.125e-05,
+      "loss": 0.6991,
+      "step": 17
+    },
+    {
+      "epoch": 1.125,
+      "grad_norm": 3.0186045169830322,
+      "learning_rate": 2.25e-05,
+      "loss": 0.6261,
+      "step": 18
+    },
+    {
+      "epoch": 1.1875,
+      "grad_norm": 2.047957181930542,
+      "learning_rate": 2.375e-05,
+      "loss": 0.6778,
+      "step": 19
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 3.6687753200531006,
+      "learning_rate": 2.5e-05,
+      "loss": 0.6227,
+      "step": 20
+    },
+    {
+      "epoch": 1.3125,
+      "grad_norm": 1.6625615358352661,
+      "learning_rate": 2.625e-05,
+      "loss": 0.6775,
+      "step": 21
+    },
+    {
+      "epoch": 1.375,
+      "grad_norm": 2.2672011852264404,
+      "learning_rate": 2.7500000000000004e-05,
+      "loss": 0.6381,
+      "step": 22
+    },
+    {
+      "epoch": 1.4375,
+      "grad_norm": 3.273030996322632,
+      "learning_rate": 2.8749999999999997e-05,
+      "loss": 0.5787,
+      "step": 23
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 6.291239261627197,
+      "learning_rate": 3e-05,
+      "loss": 0.71,
+      "step": 24
+    },
+    {
+      "epoch": 1.5625,
+      "grad_norm": 3.6905951499938965,
+      "learning_rate": 3.125e-05,
+      "loss": 0.5826,
+      "step": 25
+    },
+    {
+      "epoch": 1.625,
+      "grad_norm": 4.929114818572998,
+      "learning_rate": 3.2500000000000004e-05,
+      "loss": 0.5892,
+      "step": 26
+    },
+    {
+      "epoch": 1.6875,
+      "grad_norm": 5.820431232452393,
+      "learning_rate": 3.375000000000001e-05,
+      "loss": 0.5683,
+      "step": 27
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 10.009285926818848,
+      "learning_rate": 3.5e-05,
+      "loss": 0.4001,
+      "step": 28
+    },
+    {
+      "epoch": 1.8125,
+      "grad_norm": 13.668211936950684,
+      "learning_rate": 3.625e-05,
+      "loss": 0.6159,
+      "step": 29
+    },
+    {
+      "epoch": 1.875,
+      "grad_norm": 11.277912139892578,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.7048,
+      "step": 30
+    },
+    {
+      "epoch": 1.9375,
+      "grad_norm": 7.137956142425537,
+      "learning_rate": 3.875e-05,
+      "loss": 0.4689,
+      "step": 31
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 4.847255229949951,
+      "learning_rate": 4e-05,
+      "loss": 0.3861,
+      "step": 32
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9375,
+      "eval_auc": 0.9765625,
+      "eval_f1": 0.9375,
+      "eval_loss": 0.34269535541534424,
+      "eval_precision": 0.9375,
+      "eval_recall": 0.9375,
+      "eval_runtime": 5.178,
+      "eval_samples_per_second": 6.18,
+      "eval_steps_per_second": 0.386,
+      "step": 32
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 400,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 25,
+  "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": 16839107543040.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-32/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f6c9c959c6c949f8beadbd95decf812fb8f6594131a70d14c7bbcd8d4f2b272
+size 5368

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "cardiffnlp/twitter-xlm-roberta-base",
+  "_num_labels": 2,
+  "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": "negative",
+    "1": "positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "negative": 0,
+    "positive": 1
+  },
+  "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": "4.47.1",
+  "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:ed7b83d41a2eb046912e3096aa1375f12d7b78adbfe0be04f13dc4b1b364eecb
+size 1112205008

runs/Jan07_11-41-29_r-phosphoregarden-roberta-fine-tuned-dhs0vwho-36b9b-rfpi7/events.out.tfevents.1736250091.r-phosphoregarden-roberta-fine-tuned-dhs0vwho-36b9b-rfpi7.107.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90a3ef15f9bfa57ec73bb483ec378df6d18cf2936c5078f264e9e2c688042343
-size 25284
+oid sha256:ef8ee3fc0966fb044d770bf291de45799038bd28fd7471f41c7e9ed4bb9aae7b
+size 32446

runs/Jan07_11-41-29_r-phosphoregarden-roberta-fine-tuned-dhs0vwho-36b9b-rfpi7/events.out.tfevents.1736250903.r-phosphoregarden-roberta-fine-tuned-dhs0vwho-36b9b-rfpi7.107.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5610a036c7ebc61bbdbba7246823821c2a2d45f3ef69b10d4cbd166742136258
+size 597

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 +1,55 @@
+{
+  "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>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "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 sha256:6f6c9c959c6c949f8beadbd95decf812fb8f6594131a70d14c7bbcd8d4f2b272
+size 5368

training_params.json

@@ -0,0 +1,30 @@
+{
+    "data_path": "robertafinetuninglargedatacsv/autotrain-data",
+    "model": "cardiffnlp/twitter-xlm-roberta-base",
+    "lr": 5e-05,
+    "epochs": 25,
+    "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": "robertafinetuninglargedatacsv",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "eval_strategy": "epoch",
+    "username": "PhosphoreGarden",
+    "log": "tensorboard",
+    "early_stopping_patience": 5,
+    "early_stopping_threshold": 0.01
+}