Upload folder using huggingface_hub

README.md

@@ -0,0 +1,36 @@
+
+---
+tags:
+- autotrain
+- text-classification
+base_model: FacebookAI/roberta-base
+widget:
+- text: "I love AutoTrain"
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Text Classification
+
+## Validation Metrics
+loss: 0.6774867177009583
+
+f1_macro: 0.6839774417313933
+
+f1_micro: 0.7177177177177178
+
+f1_weighted: 0.7107988255501857
+
+precision_macro: 0.7089199316136637
+
+precision_micro: 0.7177177177177178
+
+precision_weighted: 0.7240729310198633
+
+recall_macro: 0.6773815101662369
+
+recall_micro: 0.7177177177177178
+
+recall_weighted: 0.7177177177177178
+
+accuracy: 0.7177177177177178

checkpoint-1000/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "FacebookAI/roberta-base",
+  "_num_labels": 3,
+  "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": "negative",
+    "1": "neutral",
+    "2": "positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "negative": 0,
+    "neutral": 1,
+    "positive": 2
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

checkpoint-1000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fee1feee5845ef055879b996ffc2d6165dadbcc33308345edf32e6065f0bf77
+size 498615900

checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:390128b24867d70f7b745270cce00675e98764d9adce1b6b53423c10e3780b0b
+size 997351674

checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b66eb8462f26ee453a8310396c637436290a60feb26e1c8e9baf9df72fb0490
+size 14244

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f84afb97863d979f20ce12ae5c712aa2e97571255a1443e24a47949a68da3bae
+size 1064

checkpoint-1000/trainer_state.json

@@ -0,0 +1,365 @@
+{
+  "best_metric": 0.6774867177009583,
+  "best_model_checkpoint": "autotrain-xt6nb-pf6ri/checkpoint-1000",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.048,
+      "grad_norm": 4.167473793029785,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 1.0876,
+      "step": 24
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 5.14194917678833,
+      "learning_rate": 1.5666666666666667e-05,
+      "loss": 1.1048,
+      "step": 48
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 8.47073745727539,
+      "learning_rate": 2.3666666666666668e-05,
+      "loss": 1.085,
+      "step": 72
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 6.285531997680664,
+      "learning_rate": 3.1e-05,
+      "loss": 1.0327,
+      "step": 96
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 10.787246704101562,
+      "learning_rate": 3.9000000000000006e-05,
+      "loss": 1.0035,
+      "step": 120
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 11.439258575439453,
+      "learning_rate": 4.7e-05,
+      "loss": 1.0177,
+      "step": 144
+    },
+    {
+      "epoch": 0.336,
+      "grad_norm": 6.169108867645264,
+      "learning_rate": 4.9444444444444446e-05,
+      "loss": 0.8407,
+      "step": 168
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 7.220673084259033,
+      "learning_rate": 4.8592592592592596e-05,
+      "loss": 1.0002,
+      "step": 192
+    },
+    {
+      "epoch": 0.432,
+      "grad_norm": 8.805166244506836,
+      "learning_rate": 4.770370370370371e-05,
+      "loss": 0.8377,
+      "step": 216
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 15.92953872680664,
+      "learning_rate": 4.681481481481482e-05,
+      "loss": 0.975,
+      "step": 240
+    },
+    {
+      "epoch": 0.528,
+      "grad_norm": 12.280447006225586,
+      "learning_rate": 4.592592592592593e-05,
+      "loss": 0.8324,
+      "step": 264
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 7.390661716461182,
+      "learning_rate": 4.503703703703704e-05,
+      "loss": 0.8676,
+      "step": 288
+    },
+    {
+      "epoch": 0.624,
+      "grad_norm": 3.326416492462158,
+      "learning_rate": 4.414814814814815e-05,
+      "loss": 1.0311,
+      "step": 312
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 1.4128365516662598,
+      "learning_rate": 4.325925925925926e-05,
+      "loss": 0.9408,
+      "step": 336
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.4254629611968994,
+      "learning_rate": 4.237037037037037e-05,
+      "loss": 0.9534,
+      "step": 360
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 5.265137195587158,
+      "learning_rate": 4.148148148148148e-05,
+      "loss": 0.8517,
+      "step": 384
+    },
+    {
+      "epoch": 0.816,
+      "grad_norm": 139.75430297851562,
+      "learning_rate": 4.059259259259259e-05,
+      "loss": 0.9692,
+      "step": 408
+    },
+    {
+      "epoch": 0.864,
+      "grad_norm": 172.7858123779297,
+      "learning_rate": 3.97037037037037e-05,
+      "loss": 0.9143,
+      "step": 432
+    },
+    {
+      "epoch": 0.912,
+      "grad_norm": 42.714324951171875,
+      "learning_rate": 3.885185185185186e-05,
+      "loss": 0.8104,
+      "step": 456
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 7.165309906005859,
+      "learning_rate": 3.7962962962962964e-05,
+      "loss": 0.9425,
+      "step": 480
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6906906906906907,
+      "eval_f1_macro": 0.6632603879089224,
+      "eval_f1_micro": 0.6906906906906907,
+      "eval_f1_weighted": 0.6878712561273783,
+      "eval_loss": 0.8078358769416809,
+      "eval_precision_macro": 0.6746375251220212,
+      "eval_precision_micro": 0.6906906906906907,
+      "eval_precision_weighted": 0.6963016741978844,
+      "eval_recall_macro": 0.6637361051449268,
+      "eval_recall_micro": 0.6906906906906907,
+      "eval_recall_weighted": 0.6906906906906907,
+      "eval_runtime": 2.1598,
+      "eval_samples_per_second": 462.551,
+      "eval_steps_per_second": 29.17,
+      "step": 500
+    },
+    {
+      "epoch": 1.008,
+      "grad_norm": 40.330535888671875,
+      "learning_rate": 3.7074074074074075e-05,
+      "loss": 0.8571,
+      "step": 504
+    },
+    {
+      "epoch": 1.056,
+      "grad_norm": 18.710975646972656,
+      "learning_rate": 3.6185185185185186e-05,
+      "loss": 0.8107,
+      "step": 528
+    },
+    {
+      "epoch": 1.104,
+      "grad_norm": 7.848007678985596,
+      "learning_rate": 3.52962962962963e-05,
+      "loss": 0.8219,
+      "step": 552
+    },
+    {
+      "epoch": 1.152,
+      "grad_norm": 12.77737808227539,
+      "learning_rate": 3.440740740740741e-05,
+      "loss": 0.6249,
+      "step": 576
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 4.067225456237793,
+      "learning_rate": 3.351851851851852e-05,
+      "loss": 0.7372,
+      "step": 600
+    },
+    {
+      "epoch": 1.248,
+      "grad_norm": 22.771604537963867,
+      "learning_rate": 3.262962962962963e-05,
+      "loss": 0.6791,
+      "step": 624
+    },
+    {
+      "epoch": 1.296,
+      "grad_norm": 32.429100036621094,
+      "learning_rate": 3.174074074074074e-05,
+      "loss": 0.7434,
+      "step": 648
+    },
+    {
+      "epoch": 1.3439999999999999,
+      "grad_norm": 7.296426773071289,
+      "learning_rate": 3.0851851851851854e-05,
+      "loss": 0.7742,
+      "step": 672
+    },
+    {
+      "epoch": 1.392,
+      "grad_norm": 52.18477249145508,
+      "learning_rate": 2.9962962962962966e-05,
+      "loss": 0.7379,
+      "step": 696
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 47.735477447509766,
+      "learning_rate": 2.9074074074074077e-05,
+      "loss": 0.7652,
+      "step": 720
+    },
+    {
+      "epoch": 1.488,
+      "grad_norm": 214.20318603515625,
+      "learning_rate": 2.8185185185185185e-05,
+      "loss": 0.6941,
+      "step": 744
+    },
+    {
+      "epoch": 1.536,
+      "grad_norm": 20.468931198120117,
+      "learning_rate": 2.7296296296296296e-05,
+      "loss": 0.7389,
+      "step": 768
+    },
+    {
+      "epoch": 1.584,
+      "grad_norm": 4.2643866539001465,
+      "learning_rate": 2.6407407407407408e-05,
+      "loss": 0.7372,
+      "step": 792
+    },
+    {
+      "epoch": 1.6320000000000001,
+      "grad_norm": 18.783554077148438,
+      "learning_rate": 2.551851851851852e-05,
+      "loss": 0.711,
+      "step": 816
+    },
+    {
+      "epoch": 1.6800000000000002,
+      "grad_norm": 28.915599822998047,
+      "learning_rate": 2.462962962962963e-05,
+      "loss": 0.7423,
+      "step": 840
+    },
+    {
+      "epoch": 1.728,
+      "grad_norm": 4.792373180389404,
+      "learning_rate": 2.3740740740740742e-05,
+      "loss": 0.6692,
+      "step": 864
+    },
+    {
+      "epoch": 1.776,
+      "grad_norm": 19.33057975769043,
+      "learning_rate": 2.2851851851851853e-05,
+      "loss": 0.631,
+      "step": 888
+    },
+    {
+      "epoch": 1.8239999999999998,
+      "grad_norm": 18.55846405029297,
+      "learning_rate": 2.1962962962962964e-05,
+      "loss": 0.6367,
+      "step": 912
+    },
+    {
+      "epoch": 1.8719999999999999,
+      "grad_norm": 5.190149784088135,
+      "learning_rate": 2.1074074074074072e-05,
+      "loss": 0.6872,
+      "step": 936
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 38.714290618896484,
+      "learning_rate": 2.0185185185185187e-05,
+      "loss": 0.6252,
+      "step": 960
+    },
+    {
+      "epoch": 1.968,
+      "grad_norm": 20.541481018066406,
+      "learning_rate": 1.92962962962963e-05,
+      "loss": 0.6303,
+      "step": 984
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7177177177177178,
+      "eval_f1_macro": 0.6839774417313933,
+      "eval_f1_micro": 0.7177177177177178,
+      "eval_f1_weighted": 0.7107988255501857,
+      "eval_loss": 0.6774867177009583,
+      "eval_precision_macro": 0.7089199316136637,
+      "eval_precision_micro": 0.7177177177177178,
+      "eval_precision_weighted": 0.7240729310198633,
+      "eval_recall_macro": 0.6773815101662369,
+      "eval_recall_micro": 0.7177177177177178,
+      "eval_recall_weighted": 0.7177177177177178,
+      "eval_runtime": 2.1078,
+      "eval_samples_per_second": 473.965,
+      "eval_steps_per_second": 29.89,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 24,
+  "max_steps": 1500,
+  "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": 525305938493952.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbef626c6609bae40dbb92611a35f5e4807ae1cc6704fcdfb0b6be6ade4deb57
+size 5240

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "FacebookAI/roberta-base",
+  "_num_labels": 3,
+  "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": "negative",
+    "1": "neutral",
+    "2": "positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "negative": 0,
+    "neutral": 1,
+    "positive": 2
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fee1feee5845ef055879b996ffc2d6165dadbcc33308345edf32e6065f0bf77
+size 498615900

runs/Oct08_13-38-18_488e8b10b557/events.out.tfevents.1728394700.488e8b10b557.3615.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d36c417c13b076f6a41e1b95b975b1d58c0f2cd906af6974318ad6ab3037b649
-size 4184
+oid sha256:f683fa050a62c762a3e82ffe3aa461657ab6109c8d58165f3f60268de496ea3d
+size 21047

runs/Oct08_13-38-18_488e8b10b557/events.out.tfevents.1728394904.488e8b10b557.3615.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2da90488bf5210e326d45186e88c2e90d2bd2f8ee2c53e96d53c5a95c83c84e
+size 921

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_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "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>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbef626c6609bae40dbb92611a35f5e4807ae1cc6704fcdfb0b6be6ade4deb57
+size 5240

training_params.json

@@ -0,0 +1,30 @@
+{
+    "data_path": "autotrain-xt6nb-pf6ri/autotrain-data",
+    "model": "FacebookAI/roberta-base",
+    "lr": 5e-05,
+    "epochs": 3,
+    "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": "autotrain-xt6nb-pf6ri",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "eval_strategy": "epoch",
+    "username": "wangrongsheng",
+    "log": "tensorboard",
+    "early_stopping_patience": 5,
+    "early_stopping_threshold": 0.01
+}