Upload folder using huggingface_hub

README.md

@@ -0,0 +1,36 @@
+
+---
+tags:
+- autotrain
+- text-classification
+base_model: vinai/phobert-base-v2
+widget:
+- text: "I love AutoTrain"
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Text Classification
+
+## Validation Metrics
+loss: 0.6724494099617004
+
+f1_macro: 0.7569331733597563
+
+f1_micro: 0.772892295280355
+
+f1_weighted: 0.7744819967617077
+
+precision_macro: 0.7857208805541623
+
+precision_micro: 0.772892295280355
+
+precision_weighted: 0.7858918730269342
+
+recall_macro: 0.7453180945213479
+
+recall_micro: 0.772892295280355
+
+recall_weighted: 0.772892295280355
+
+accuracy: 0.772892295280355

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<mask>": 64000
+}

checkpoint-466/config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "vinai/phobert-base-v2",
+  "_num_labels": 6,
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "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": "2733522",
+    "1": "2733534",
+    "2": "2733540",
+    "3": "2733546",
+    "4": "2733552",
+    "5": "2733570"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "2733522": 0,
+    "2733534": 1,
+    "2733540": 2,
+    "2733546": 3,
+    "2733552": 4,
+    "2733570": 5
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 258,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "tokenizer_class": "PhobertTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 64001
+}

checkpoint-466/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e3eb2520c31131f6de761972090246080ab66e4eb12791d3d83f5ccde67a920
+size 540035688

checkpoint-466/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7260c33f8f9b2bb87943b75f20d91d513b436718d884485e7efe76678fed41e8
+size 1080185594

checkpoint-466/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2480a58924f72444e0dbbcc68164e099e2a2b4170da0a89a5e62f7347ebc83a
+size 13990

checkpoint-466/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81182a500cca6817c72a4126a7fa76215f553b3b4d59b78ccfe205857b7a901e
+size 1064

checkpoint-466/trainer_state.json

@@ -0,0 +1,295 @@
+{
+  "best_metric": 0.6724494099617004,
+  "best_model_checkpoint": "autotrain-tvscq-k8x1j/checkpoint-466",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 466,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06437768240343347,
+      "grad_norm": 1.5937669277191162,
+      "learning_rate": 3.218884120171674e-06,
+      "loss": 1.8041,
+      "step": 15
+    },
+    {
+      "epoch": 0.12875536480686695,
+      "grad_norm": 1.9162086248397827,
+      "learning_rate": 6.437768240343348e-06,
+      "loss": 1.7646,
+      "step": 30
+    },
+    {
+      "epoch": 0.19313304721030042,
+      "grad_norm": 3.83647084236145,
+      "learning_rate": 9.65665236051502e-06,
+      "loss": 1.7276,
+      "step": 45
+    },
+    {
+      "epoch": 0.2575107296137339,
+      "grad_norm": 2.4570248126983643,
+      "learning_rate": 1.2875536480686696e-05,
+      "loss": 1.6562,
+      "step": 60
+    },
+    {
+      "epoch": 0.3218884120171674,
+      "grad_norm": 2.4348771572113037,
+      "learning_rate": 1.609442060085837e-05,
+      "loss": 1.5545,
+      "step": 75
+    },
+    {
+      "epoch": 0.38626609442060084,
+      "grad_norm": 3.5921103954315186,
+      "learning_rate": 1.931330472103004e-05,
+      "loss": 1.3961,
+      "step": 90
+    },
+    {
+      "epoch": 0.45064377682403434,
+      "grad_norm": 2.730750799179077,
+      "learning_rate": 2.2532188841201716e-05,
+      "loss": 1.2951,
+      "step": 105
+    },
+    {
+      "epoch": 0.5150214592274678,
+      "grad_norm": 4.738720417022705,
+      "learning_rate": 2.575107296137339e-05,
+      "loss": 1.1584,
+      "step": 120
+    },
+    {
+      "epoch": 0.5793991416309013,
+      "grad_norm": 3.7729783058166504,
+      "learning_rate": 2.896995708154507e-05,
+      "loss": 1.1065,
+      "step": 135
+    },
+    {
+      "epoch": 0.6437768240343348,
+      "grad_norm": 6.2229108810424805,
+      "learning_rate": 3.218884120171674e-05,
+      "loss": 1.0275,
+      "step": 150
+    },
+    {
+      "epoch": 0.7081545064377682,
+      "grad_norm": 6.119204998016357,
+      "learning_rate": 3.5407725321888415e-05,
+      "loss": 0.9499,
+      "step": 165
+    },
+    {
+      "epoch": 0.7725321888412017,
+      "grad_norm": 5.544712066650391,
+      "learning_rate": 3.862660944206008e-05,
+      "loss": 0.9326,
+      "step": 180
+    },
+    {
+      "epoch": 0.8369098712446352,
+      "grad_norm": 4.458618640899658,
+      "learning_rate": 4.1845493562231765e-05,
+      "loss": 0.9,
+      "step": 195
+    },
+    {
+      "epoch": 0.9012875536480687,
+      "grad_norm": 3.0510473251342773,
+      "learning_rate": 4.506437768240343e-05,
+      "loss": 0.8479,
+      "step": 210
+    },
+    {
+      "epoch": 0.9656652360515021,
+      "grad_norm": 8.005799293518066,
+      "learning_rate": 4.828326180257511e-05,
+      "loss": 0.8235,
+      "step": 225
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7450584913271481,
+      "eval_f1_macro": 0.7276861781009197,
+      "eval_f1_micro": 0.7450584913271481,
+      "eval_f1_weighted": 0.7452323860287042,
+      "eval_loss": 0.804132342338562,
+      "eval_precision_macro": 0.7505006504444173,
+      "eval_precision_micro": 0.7450584913271481,
+      "eval_precision_weighted": 0.7539412866996655,
+      "eval_recall_macro": 0.7172758860348246,
+      "eval_recall_micro": 0.7450584913271481,
+      "eval_recall_weighted": 0.7450584913271481,
+      "eval_runtime": 392.8413,
+      "eval_samples_per_second": 6.31,
+      "eval_steps_per_second": 0.099,
+      "step": 233
+    },
+    {
+      "epoch": 1.0300429184549356,
+      "grad_norm": 4.325954437255859,
+      "learning_rate": 4.983309489747258e-05,
+      "loss": 0.8441,
+      "step": 240
+    },
+    {
+      "epoch": 1.094420600858369,
+      "grad_norm": 4.232270240783691,
+      "learning_rate": 4.9475441106342394e-05,
+      "loss": 0.8237,
+      "step": 255
+    },
+    {
+      "epoch": 1.1587982832618025,
+      "grad_norm": 5.351541519165039,
+      "learning_rate": 4.911778731521221e-05,
+      "loss": 0.8127,
+      "step": 270
+    },
+    {
+      "epoch": 1.2231759656652361,
+      "grad_norm": 5.942873001098633,
+      "learning_rate": 4.8760133524082023e-05,
+      "loss": 0.7591,
+      "step": 285
+    },
+    {
+      "epoch": 1.2875536480686696,
+      "grad_norm": 7.406440734863281,
+      "learning_rate": 4.840247973295184e-05,
+      "loss": 0.7636,
+      "step": 300
+    },
+    {
+      "epoch": 1.351931330472103,
+      "grad_norm": 5.3224897384643555,
+      "learning_rate": 4.804482594182165e-05,
+      "loss": 0.7011,
+      "step": 315
+    },
+    {
+      "epoch": 1.4163090128755365,
+      "grad_norm": 10.202744483947754,
+      "learning_rate": 4.768717215069147e-05,
+      "loss": 0.7374,
+      "step": 330
+    },
+    {
+      "epoch": 1.48068669527897,
+      "grad_norm": 7.358770370483398,
+      "learning_rate": 4.732951835956128e-05,
+      "loss": 0.7279,
+      "step": 345
+    },
+    {
+      "epoch": 1.5450643776824036,
+      "grad_norm": 9.469185829162598,
+      "learning_rate": 4.69718645684311e-05,
+      "loss": 0.6922,
+      "step": 360
+    },
+    {
+      "epoch": 1.6094420600858368,
+      "grad_norm": 8.004199981689453,
+      "learning_rate": 4.661421077730091e-05,
+      "loss": 0.7618,
+      "step": 375
+    },
+    {
+      "epoch": 1.6738197424892705,
+      "grad_norm": 6.05955696105957,
+      "learning_rate": 4.6256556986170726e-05,
+      "loss": 0.666,
+      "step": 390
+    },
+    {
+      "epoch": 1.738197424892704,
+      "grad_norm": 6.0875630378723145,
+      "learning_rate": 4.589890319504054e-05,
+      "loss": 0.6997,
+      "step": 405
+    },
+    {
+      "epoch": 1.8025751072961373,
+      "grad_norm": 8.000418663024902,
+      "learning_rate": 4.5541249403910355e-05,
+      "loss": 0.6706,
+      "step": 420
+    },
+    {
+      "epoch": 1.8669527896995708,
+      "grad_norm": 5.948812484741211,
+      "learning_rate": 4.518359561278016e-05,
+      "loss": 0.7025,
+      "step": 435
+    },
+    {
+      "epoch": 1.9313304721030042,
+      "grad_norm": 10.356701850891113,
+      "learning_rate": 4.482594182164998e-05,
+      "loss": 0.6772,
+      "step": 450
+    },
+    {
+      "epoch": 1.995708154506438,
+      "grad_norm": 3.6088099479675293,
+      "learning_rate": 4.446828803051979e-05,
+      "loss": 0.6119,
+      "step": 465
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.772892295280355,
+      "eval_f1_macro": 0.7569331733597563,
+      "eval_f1_micro": 0.772892295280355,
+      "eval_f1_weighted": 0.7744819967617077,
+      "eval_loss": 0.6724494099617004,
+      "eval_precision_macro": 0.7857208805541623,
+      "eval_precision_micro": 0.772892295280355,
+      "eval_precision_weighted": 0.7858918730269342,
+      "eval_recall_macro": 0.7453180945213479,
+      "eval_recall_micro": 0.772892295280355,
+      "eval_recall_weighted": 0.772892295280355,
+      "eval_runtime": 391.2861,
+      "eval_samples_per_second": 6.336,
+      "eval_steps_per_second": 0.1,
+      "step": 466
+    }
+  ],
+  "logging_steps": 15,
+  "max_steps": 2330,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "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": 977755795955712.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-466/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12356f1d2f2ead1891882323d17fcbf14a1ffb5a03e7bf10c1985d3ec8b72926
+size 5176

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "vinai/phobert-base-v2",
+  "_num_labels": 6,
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "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": "2733522",
+    "1": "2733534",
+    "2": "2733540",
+    "3": "2733546",
+    "4": "2733552",
+    "5": "2733570"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "2733522": 0,
+    "2733534": 1,
+    "2733540": 2,
+    "2733546": 3,
+    "2733552": 4,
+    "2733570": 5
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 258,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "tokenizer_class": "PhobertTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 64001
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e3eb2520c31131f6de761972090246080ab66e4eb12791d3d83f5ccde67a920
+size 540035688

runs/Jun20_15-49-40_r-nhown2002-phobert-thesis-yep606tt-b43ba-l0s6o/events.out.tfevents.1718898580.r-nhown2002-phobert-thesis-yep606tt-b43ba-l0s6o.96.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2217b9c5a8be56a42fd97bd18136bd5f37fe3b752c07c5633d208ca15570c334
-size 32342
+oid sha256:f7970aa72331779c6394a75cc2e9d1a85b34e0bde69d4b9df9c614a07b5670cd
+size 34162

runs/Jun20_15-49-40_r-nhown2002-phobert-thesis-yep606tt-b43ba-l0s6o/events.out.tfevents.1718928811.r-nhown2002-phobert-thesis-yep606tt-b43ba-l0s6o.96.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdd37ec526a328bbde9ad72d377b40ccb584eb005113e163e5aacde6afe7e685
+size 921

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

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
+    },
+    "64000": {
+      "content": "<mask>",
+      "lstrip": false,
+      "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": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "PhobertTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12356f1d2f2ead1891882323d17fcbf14a1ffb5a03e7bf10c1985d3ec8b72926
+size 5176

training_params.json

@@ -0,0 +1,30 @@
+{
+    "data_path": "autotrain-tvscq-k8x1j/autotrain-data",
+    "model": "vinai/phobert-base-v2",
+    "lr": 5e-05,
+    "epochs": 10,
+    "max_seq_length": 128,
+    "batch_size": 32,
+    "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-tvscq-k8x1j",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "eval_strategy": "epoch",
+    "username": "Nhown2002",
+    "log": "tensorboard",
+    "early_stopping_patience": 5,
+    "early_stopping_threshold": 0.01
+}