Upload folder using huggingface_hub

README.md

@@ -0,0 +1,26 @@
+
+---
+tags:
+- autotrain
+- text-classification
+base_model: yiyanghkust/finbert-tone
+widget:
+- text: "I love AutoTrain"
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Text Classification
+
+## Validation Metrics
+loss: 0.5263932943344116
+
+f1: 0.6754385964912281
+
+precision: 0.7403846153846154
+
+recall: 0.6209677419354839
+
+auc: 0.8266129032258064
+
+accuracy: 0.7533333333333333

checkpoint-240/config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "yiyanghkust/finbert-tone",
+  "_num_labels": 2,
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "certain",
+    "1": "uncertain"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "certain": 0,
+    "uncertain": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30873
+}

checkpoint-240/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79d1dd6a07d9baedc1aff83b54a532520ce66bef3aa7f78fc3c43114bd6f6342
+size 439036920

checkpoint-240/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:591c6ce0fa3c0dfb019e472dcbee3d48156d374a0b32da85bf733eda72360796
+size 878194938

checkpoint-240/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d4cf4a9d72b7cedd3f1b28689604301d3de77a10e9f61ebf48cf9579dd085af
+size 14244

checkpoint-240/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e79ed1d15bf745f8d86305fe9299953468b601279543a8798117cf1ef6f8ff7f
+size 1064

checkpoint-240/trainer_state.json

@@ -0,0 +1,348 @@
+{
+  "best_metric": 0.5263932943344116,
+  "best_model_checkpoint": "autotrain-ecb-uncertainty-finbert-tone/checkpoint-240",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 240,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "grad_norm": 6.569391250610352,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 0.7768,
+      "step": 6
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 6.166207790374756,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.7568,
+      "step": 12
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 5.1863017082214355,
+      "learning_rate": 5e-06,
+      "loss": 0.7453,
+      "step": 18
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 5.514832496643066,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.7086,
+      "step": 24
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 6.145003795623779,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.7042,
+      "step": 30
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 3.795694351196289,
+      "learning_rate": 1e-05,
+      "loss": 0.6698,
+      "step": 36
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 3.8171277046203613,
+      "learning_rate": 9.814814814814815e-06,
+      "loss": 0.616,
+      "step": 42
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 5.604820728302002,
+      "learning_rate": 9.62962962962963e-06,
+      "loss": 0.6165,
+      "step": 48
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 6.14561653137207,
+      "learning_rate": 9.444444444444445e-06,
+      "loss": 0.6304,
+      "step": 54
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 5.619190216064453,
+      "learning_rate": 9.25925925925926e-06,
+      "loss": 0.5361,
+      "step": 60
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 4.290294647216797,
+      "learning_rate": 9.074074074074075e-06,
+      "loss": 0.5427,
+      "step": 66
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 8.48792839050293,
+      "learning_rate": 8.888888888888888e-06,
+      "loss": 0.7302,
+      "step": 72
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 4.4337029457092285,
+      "learning_rate": 8.703703703703705e-06,
+      "loss": 0.5709,
+      "step": 78
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 4.320799350738525,
+      "learning_rate": 8.518518518518519e-06,
+      "loss": 0.5945,
+      "step": 84
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 4.405670166015625,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.584,
+      "step": 90
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 6.364153861999512,
+      "learning_rate": 8.148148148148148e-06,
+      "loss": 0.5729,
+      "step": 96
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 5.696963310241699,
+      "learning_rate": 7.962962962962963e-06,
+      "loss": 0.5153,
+      "step": 102
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 6.018728256225586,
+      "learning_rate": 7.77777777777778e-06,
+      "loss": 0.4837,
+      "step": 108
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 6.9727630615234375,
+      "learning_rate": 7.592592592592594e-06,
+      "loss": 0.5397,
+      "step": 114
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 6.78570556640625,
+      "learning_rate": 7.4074074074074075e-06,
+      "loss": 0.5556,
+      "step": 120
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7433333333333333,
+      "eval_auc": 0.8076658724340174,
+      "eval_f1": 0.6451612903225806,
+      "eval_loss": 0.5290501117706299,
+      "eval_precision": 0.7526881720430108,
+      "eval_recall": 0.5645161290322581,
+      "eval_runtime": 0.5589,
+      "eval_samples_per_second": 536.748,
+      "eval_steps_per_second": 26.837,
+      "step": 120
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 8.623733520507812,
+      "learning_rate": 7.222222222222223e-06,
+      "loss": 0.4441,
+      "step": 126
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 5.180130481719971,
+      "learning_rate": 7.0370370370370375e-06,
+      "loss": 0.364,
+      "step": 132
+    },
+    {
+      "epoch": 1.15,
+      "grad_norm": 3.5196149349212646,
+      "learning_rate": 6.851851851851853e-06,
+      "loss": 0.4131,
+      "step": 138
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 6.338296413421631,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.3845,
+      "step": 144
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 7.1538214683532715,
+      "learning_rate": 6.481481481481482e-06,
+      "loss": 0.4711,
+      "step": 150
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 6.877357006072998,
+      "learning_rate": 6.296296296296297e-06,
+      "loss": 0.4216,
+      "step": 156
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 10.410565376281738,
+      "learning_rate": 6.111111111111112e-06,
+      "loss": 0.4526,
+      "step": 162
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 8.083864212036133,
+      "learning_rate": 5.925925925925926e-06,
+      "loss": 0.438,
+      "step": 168
+    },
+    {
+      "epoch": 1.45,
+      "grad_norm": 10.988332748413086,
+      "learning_rate": 5.740740740740741e-06,
+      "loss": 0.5299,
+      "step": 174
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 6.402344703674316,
+      "learning_rate": 5.555555555555557e-06,
+      "loss": 0.3972,
+      "step": 180
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 5.067495346069336,
+      "learning_rate": 5.370370370370371e-06,
+      "loss": 0.2848,
+      "step": 186
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 7.7700347900390625,
+      "learning_rate": 5.185185185185185e-06,
+      "loss": 0.4724,
+      "step": 192
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 6.948176860809326,
+      "learning_rate": 5e-06,
+      "loss": 0.394,
+      "step": 198
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 7.933591365814209,
+      "learning_rate": 4.814814814814815e-06,
+      "loss": 0.4175,
+      "step": 204
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 4.761749267578125,
+      "learning_rate": 4.62962962962963e-06,
+      "loss": 0.3985,
+      "step": 210
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 8.314071655273438,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 0.4011,
+      "step": 216
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 4.415229797363281,
+      "learning_rate": 4.2592592592592596e-06,
+      "loss": 0.336,
+      "step": 222
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 8.338693618774414,
+      "learning_rate": 4.074074074074074e-06,
+      "loss": 0.5084,
+      "step": 228
+    },
+    {
+      "epoch": 1.95,
+      "grad_norm": 9.162919998168945,
+      "learning_rate": 3.88888888888889e-06,
+      "loss": 0.4164,
+      "step": 234
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 5.912008285522461,
+      "learning_rate": 3.7037037037037037e-06,
+      "loss": 0.3517,
+      "step": 240
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7533333333333333,
+      "eval_auc": 0.8266129032258064,
+      "eval_f1": 0.6754385964912281,
+      "eval_loss": 0.5263932943344116,
+      "eval_precision": 0.7403846153846154,
+      "eval_recall": 0.6209677419354839,
+      "eval_runtime": 0.5569,
+      "eval_samples_per_second": 538.693,
+      "eval_steps_per_second": 26.935,
+      "step": 240
+    }
+  ],
+  "logging_steps": 6,
+  "max_steps": 360,
+  "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": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 315733266432000.0,
+  "train_batch_size": 10,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-240/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1d9f60664ccb977bb0e1d3cedfd50eb77365f3350a83c357bbc02e594aa96a2
+size 5304

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "yiyanghkust/finbert-tone",
+  "_num_labels": 2,
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "certain",
+    "1": "uncertain"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "certain": 0,
+    "uncertain": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30873
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79d1dd6a07d9baedc1aff83b54a532520ce66bef3aa7f78fc3c43114bd6f6342
+size 439036920

runs/Sep05_14-29-50_r-jjonas313-autotrain-ecb-uncertainy-7lc13857-3e966-8536m/events.out.tfevents.1725546591.r-jjonas313-autotrain-ecb-uncertainy-7lc13857-3e966-8536m.166.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:575b94b2243e2a6d1659a66763cfbb25dedb7d867d6ff7c7acfd3f065ed9eb69
-size 5128
+oid sha256:7310dba0f373ef0b706853050c568d174a71d476a0997d043e6c2ec47849afed
+size 19605

runs/Sep05_14-29-50_r-jjonas313-autotrain-ecb-uncertainy-7lc13857-3e966-8536m/events.out.tfevents.1725546628.r-jjonas313-autotrain-ecb-uncertainy-7lc13857-3e966-8536m.166.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47f26d33954c393d9a0804ec4c5c8816d24cf2498c55b9abe472cc3904a277b0
+size 607

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1d9f60664ccb977bb0e1d3cedfd50eb77365f3350a83c357bbc02e594aa96a2
+size 5304

training_params.json

@@ -0,0 +1,30 @@
+{
+    "data_path": "autotrain-ecb-uncertainty-finbert-tone/autotrain-data",
+    "model": "yiyanghkust/finbert-tone",
+    "lr": 1e-05,
+    "epochs": 3,
+    "max_seq_length": 256,
+    "batch_size": 10,
+    "warmup_ratio": 0.1,
+    "gradient_accumulation": 1,
+    "optimizer": "adamw_torch",
+    "scheduler": "linear",
+    "weight_decay": 0.0,
+    "max_grad_norm": 1.0,
+    "seed": 333,
+    "train_split": "train",
+    "valid_split": "validation",
+    "text_column": "autotrain_text",
+    "target_column": "autotrain_label",
+    "logging_steps": -1,
+    "project_name": "autotrain-ecb-uncertainty-finbert-tone",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "eval_strategy": "epoch",
+    "username": "jjonas313",
+    "log": "tensorboard",
+    "early_stopping_patience": 5,
+    "early_stopping_threshold": 0.01
+}