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: 0.6016618609428406
+
+f1: 0.8
+
+precision: 1.0
+
+recall: 0.6666666666666666
+
+auc: 0.6666666666666666
+
+accuracy: 0.8333333333333334

checkpoint-15/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-15/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d996ee1a0840828c1483a3cc032f53c9b6806853937be1be9558d38fd6215de0
+size 1112205008

checkpoint-15/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a946591730bd7c9237479b535e08caa2f9ee3ef889520bbda5b29b85b7f41eb8
+size 2224524026

checkpoint-15/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:545ae1e838ccab7f6663bbbec35613c6c08c997740339d8fc1d19a3f1a175fa8
+size 13990

checkpoint-15/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7236412b243c7d8e945790c13d85e31b2f23b8d90db5f5e738eb25a4698eef9f
+size 1064

checkpoint-15/trainer_state.json

@@ -0,0 +1,212 @@
+{
+  "best_metric": 0.6016618609428406,
+  "best_model_checkpoint": "robertafinetuningdatacsv/checkpoint-15",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 15,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 2.5679423809051514,
+      "learning_rate": 6.25e-06,
+      "loss": 0.6977,
+      "step": 1
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 1.0955673456192017,
+      "learning_rate": 1.25e-05,
+      "loss": 0.6913,
+      "step": 2
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.816250801086426,
+      "learning_rate": 1.8750000000000002e-05,
+      "loss": 0.6778,
+      "step": 3
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5,
+      "eval_auc": 0.3333333333333333,
+      "eval_f1": 0.6666666666666666,
+      "eval_loss": 0.694252073764801,
+      "eval_precision": 0.5,
+      "eval_recall": 1.0,
+      "eval_runtime": 1.1206,
+      "eval_samples_per_second": 5.354,
+      "eval_steps_per_second": 0.892,
+      "step": 3
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 1.407300591468811,
+      "learning_rate": 2.5e-05,
+      "loss": 0.6836,
+      "step": 4
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 1.5846749544143677,
+      "learning_rate": 3.125e-05,
+      "loss": 0.688,
+      "step": 5
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 3.1527740955352783,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.7187,
+      "step": 6
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5,
+      "eval_auc": 0.3333333333333333,
+      "eval_f1": 0.6666666666666666,
+      "eval_loss": 0.691937267780304,
+      "eval_precision": 0.5,
+      "eval_recall": 1.0,
+      "eval_runtime": 1.0497,
+      "eval_samples_per_second": 5.716,
+      "eval_steps_per_second": 0.953,
+      "step": 6
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 2.1362953186035156,
+      "learning_rate": 4.375e-05,
+      "loss": 0.7015,
+      "step": 7
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 2.9547247886657715,
+      "learning_rate": 5e-05,
+      "loss": 0.6617,
+      "step": 8
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.7702085971832275,
+      "learning_rate": 4.9253731343283586e-05,
+      "loss": 0.6504,
+      "step": 9
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6666666666666666,
+      "eval_auc": 0.4444444444444444,
+      "eval_f1": 0.5,
+      "eval_loss": 0.6782261729240417,
+      "eval_precision": 1.0,
+      "eval_recall": 0.3333333333333333,
+      "eval_runtime": 0.9829,
+      "eval_samples_per_second": 6.105,
+      "eval_steps_per_second": 1.017,
+      "step": 9
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 4.992651462554932,
+      "learning_rate": 4.850746268656717e-05,
+      "loss": 0.6348,
+      "step": 10
+    },
+    {
+      "epoch": 3.6666666666666665,
+      "grad_norm": 3.7911322116851807,
+      "learning_rate": 4.7761194029850745e-05,
+      "loss": 0.6122,
+      "step": 11
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 4.882939338684082,
+      "learning_rate": 4.7014925373134335e-05,
+      "loss": 0.481,
+      "step": 12
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6666666666666666,
+      "eval_auc": 0.6666666666666666,
+      "eval_f1": 0.5,
+      "eval_loss": 0.6346973776817322,
+      "eval_precision": 1.0,
+      "eval_recall": 0.3333333333333333,
+      "eval_runtime": 0.9747,
+      "eval_samples_per_second": 6.156,
+      "eval_steps_per_second": 1.026,
+      "step": 12
+    },
+    {
+      "epoch": 4.333333333333333,
+      "grad_norm": 5.750195503234863,
+      "learning_rate": 4.626865671641791e-05,
+      "loss": 0.5099,
+      "step": 13
+    },
+    {
+      "epoch": 4.666666666666667,
+      "grad_norm": 4.293231964111328,
+      "learning_rate": 4.5522388059701495e-05,
+      "loss": 0.4428,
+      "step": 14
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 8.988675117492676,
+      "learning_rate": 4.477611940298508e-05,
+      "loss": 0.4102,
+      "step": 15
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8333333333333334,
+      "eval_auc": 0.6666666666666666,
+      "eval_f1": 0.8,
+      "eval_loss": 0.6016618609428406,
+      "eval_precision": 1.0,
+      "eval_recall": 0.6666666666666666,
+      "eval_runtime": 0.9785,
+      "eval_samples_per_second": 6.132,
+      "eval_steps_per_second": 1.022,
+      "step": 15
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 75,
+  "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": 7235554022400.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-15/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0748cfe28b26ecb5dd5bf1f01d9ea07a94bb4d7382f68fcc0f9fc35dbca909cb
+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:d996ee1a0840828c1483a3cc032f53c9b6806853937be1be9558d38fd6215de0
+size 1112205008

runs/Jan07_11-04-01_r-phosphoregarden-roberta-fine-tuned-4djzkxqq-9b02c-46a8l/events.out.tfevents.1736247843.r-phosphoregarden-roberta-fine-tuned-4djzkxqq-9b02c-46a8l.125.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9cdb90d52ff1f83b747598fa3df17a4543e03c299aa1b07b6de1274dff629fd
-size 5336
+oid sha256:4596d1518962ae1d2a9c58acb35843692a3cbe9134795e3316ed5dcbcad868f8
+size 16984

runs/Jan07_11-04-01_r-phosphoregarden-roberta-fine-tuned-4djzkxqq-9b02c-46a8l/events.out.tfevents.1736248086.r-phosphoregarden-roberta-fine-tuned-4djzkxqq-9b02c-46a8l.125.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e06fd421316802e4c75b1dbf66eabb039832bf398cfc0c28d95501d6b8df756f
+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 sha256:0748cfe28b26ecb5dd5bf1f01d9ea07a94bb4d7382f68fcc0f9fc35dbca909cb
+size 5368

training_params.json

@@ -0,0 +1,30 @@
+{
+    "data_path": "robertafinetuningdatacsv/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": "robertafinetuningdatacsv",
+    "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
+}