Upload folder using huggingface_hub

README.md

@@ -0,0 +1,36 @@
+
+---
+tags:
+- autotrain
+- text-classification
+base_model: sismetanin/sbert-ru-sentiment-rureviews
+widget:
+- text: "I love AutoTrain"
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Text Classification
+
+## Validation Metrics
+loss: 0.7923741936683655
+
+f1_macro: 0.477300844529545
+
+f1_micro: 0.6768415474297828
+
+f1_weighted: 0.6539238685786151
+
+precision_macro: 0.47572044522765333
+
+precision_micro: 0.6768415474297828
+
+precision_weighted: 0.6443369860797746
+
+recall_macro: 0.4940706423732507
+
+recall_micro: 0.6768415474297828
+
+recall_weighted: 0.6768415474297828
+
+accuracy: 0.6768415474297828

checkpoint-589/config.json

@@ -0,0 +1,49 @@
+{
+  "_name_or_path": "sismetanin/sbert-ru-sentiment-rureviews",
+  "_num_labels": 5,
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "finetuning_task": "sst2",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "1",
+    "1": "2",
+    "2": "3",
+    "3": "4",
+    "4": "5"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "1": 0,
+    "2": 1,
+    "3": 2,
+    "4": 3,
+    "5": 4
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 120138
+}

checkpoint-589/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39f404f99e9a46a93d0a2a0fa05ecd924e4e196416a79e333666ae10ef56f72c
+size 1707702436

checkpoint-589/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d1dbe7ea98ba93d5f657c5fd231ca4a78519668a0398007084d6df10a28237f
+size 3415639277

checkpoint-589/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15d1fe90d177fc6657840afac5d42c3bb42babde2a971424314319026c94bbe1
+size 14512

checkpoint-589/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f789f370861a91c8b2d2fac77b5b062b5221ea256ca4e469dcdf5e306871352c
+size 14512

checkpoint-589/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc14eee9a6e3ac806ec4b38cf80106ed826556261dcec99fe3bce49fbb45d73c
+size 1064

checkpoint-589/trainer_state.json

@@ -0,0 +1,221 @@
+{
+  "best_metric": 0.7976659536361694,
+  "best_model_checkpoint": "sbert-ru-huawei-rureviews-no-duplicates/checkpoint-589",
+  "epoch": 0.9987282746926663,
+  "eval_steps": 500,
+  "global_step": 589,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0423908435777872,
+      "grad_norm": 18.781570434570312,
+      "learning_rate": 7.062146892655368e-06,
+      "loss": 1.5601,
+      "step": 25
+    },
+    {
+      "epoch": 0.0847816871555744,
+      "grad_norm": 12.51102066040039,
+      "learning_rate": 1.4124293785310736e-05,
+      "loss": 1.0521,
+      "step": 50
+    },
+    {
+      "epoch": 0.1271725307333616,
+      "grad_norm": 24.600730895996094,
+      "learning_rate": 2.1186440677966103e-05,
+      "loss": 0.8671,
+      "step": 75
+    },
+    {
+      "epoch": 0.1695633743111488,
+      "grad_norm": 14.450693130493164,
+      "learning_rate": 2.8248587570621472e-05,
+      "loss": 0.8607,
+      "step": 100
+    },
+    {
+      "epoch": 0.21195421788893598,
+      "grad_norm": 15.730051040649414,
+      "learning_rate": 3.531073446327684e-05,
+      "loss": 0.8658,
+      "step": 125
+    },
+    {
+      "epoch": 0.2543450614667232,
+      "grad_norm": 15.596332550048828,
+      "learning_rate": 4.2372881355932206e-05,
+      "loss": 0.8358,
+      "step": 150
+    },
+    {
+      "epoch": 0.29673590504451036,
+      "grad_norm": 14.379067420959473,
+      "learning_rate": 4.9435028248587575e-05,
+      "loss": 0.8535,
+      "step": 175
+    },
+    {
+      "epoch": 0.3391267486222976,
+      "grad_norm": 14.174772262573242,
+      "learning_rate": 4.927672955974843e-05,
+      "loss": 0.8428,
+      "step": 200
+    },
+    {
+      "epoch": 0.3815175922000848,
+      "grad_norm": 15.868408203125,
+      "learning_rate": 4.849056603773585e-05,
+      "loss": 0.8436,
+      "step": 225
+    },
+    {
+      "epoch": 0.42390843577787196,
+      "grad_norm": 12.947571754455566,
+      "learning_rate": 4.7704402515723276e-05,
+      "loss": 0.8498,
+      "step": 250
+    },
+    {
+      "epoch": 0.4662992793556592,
+      "grad_norm": 12.922489166259766,
+      "learning_rate": 4.691823899371069e-05,
+      "loss": 0.8728,
+      "step": 275
+    },
+    {
+      "epoch": 0.5086901229334464,
+      "grad_norm": 16.116744995117188,
+      "learning_rate": 4.616352201257862e-05,
+      "loss": 0.8058,
+      "step": 300
+    },
+    {
+      "epoch": 0.5510809665112336,
+      "grad_norm": 13.213577270507812,
+      "learning_rate": 4.537735849056604e-05,
+      "loss": 0.8092,
+      "step": 325
+    },
+    {
+      "epoch": 0.5934718100890207,
+      "grad_norm": 13.749724388122559,
+      "learning_rate": 4.459119496855346e-05,
+      "loss": 0.8277,
+      "step": 350
+    },
+    {
+      "epoch": 0.6358626536668079,
+      "grad_norm": 14.099920272827148,
+      "learning_rate": 4.3805031446540885e-05,
+      "loss": 0.8172,
+      "step": 375
+    },
+    {
+      "epoch": 0.6782534972445952,
+      "grad_norm": 11.363203048706055,
+      "learning_rate": 4.301886792452831e-05,
+      "loss": 0.8397,
+      "step": 400
+    },
+    {
+      "epoch": 0.7206443408223824,
+      "grad_norm": 13.129080772399902,
+      "learning_rate": 4.2232704402515726e-05,
+      "loss": 0.8768,
+      "step": 425
+    },
+    {
+      "epoch": 0.7630351844001696,
+      "grad_norm": 13.105059623718262,
+      "learning_rate": 4.1477987421383654e-05,
+      "loss": 0.8453,
+      "step": 450
+    },
+    {
+      "epoch": 0.8054260279779568,
+      "grad_norm": 17.31393814086914,
+      "learning_rate": 4.069182389937107e-05,
+      "loss": 0.8207,
+      "step": 475
+    },
+    {
+      "epoch": 0.8478168715557439,
+      "grad_norm": 15.73338794708252,
+      "learning_rate": 3.9905660377358494e-05,
+      "loss": 0.8093,
+      "step": 500
+    },
+    {
+      "epoch": 0.8902077151335311,
+      "grad_norm": 10.630894660949707,
+      "learning_rate": 3.911949685534592e-05,
+      "loss": 0.7984,
+      "step": 525
+    },
+    {
+      "epoch": 0.9325985587113184,
+      "grad_norm": 14.764472961425781,
+      "learning_rate": 3.8333333333333334e-05,
+      "loss": 0.7914,
+      "step": 550
+    },
+    {
+      "epoch": 0.9749894022891056,
+      "grad_norm": 14.726776123046875,
+      "learning_rate": 3.754716981132076e-05,
+      "loss": 0.7818,
+      "step": 575
+    },
+    {
+      "epoch": 0.9987282746926663,
+      "eval_accuracy": 0.6771595124536302,
+      "eval_f1_macro": 0.47781142535236576,
+      "eval_f1_micro": 0.6771595124536302,
+      "eval_f1_weighted": 0.6542674498710257,
+      "eval_loss": 0.7976659536361694,
+      "eval_precision_macro": 0.6650293707575838,
+      "eval_precision_micro": 0.6771595124536302,
+      "eval_precision_weighted": 0.6930699230580497,
+      "eval_recall_macro": 0.5021643205507915,
+      "eval_recall_micro": 0.6771595124536302,
+      "eval_recall_weighted": 0.6771595124536302,
+      "eval_runtime": 60.5427,
+      "eval_samples_per_second": 155.84,
+      "eval_steps_per_second": 4.873,
+      "step": 589
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 1767,
+  "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": 1.7587586671312896e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-589/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae74f44dde39d500dff2c79d488590c540de669cdb651275236a09d118c70b66
+size 5304

config.json

@@ -0,0 +1,49 @@
+{
+  "_name_or_path": "sismetanin/sbert-ru-sentiment-rureviews",
+  "_num_labels": 5,
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "finetuning_task": "sst2",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "1",
+    "1": "2",
+    "2": "3",
+    "3": "4",
+    "4": "5"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "1": 0,
+    "2": 1,
+    "3": 2,
+    "4": 3,
+    "5": 4
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 120138
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39f404f99e9a46a93d0a2a0fa05ecd924e4e196416a79e333666ae10ef56f72c
+size 1707702436

runs/Nov14_16-11-37_bae606737fc2/events.out.tfevents.1731600699.bae606737fc2.271.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6124af757c2727301f61bc848f96df4e42299d5c199b26716d4f5f64f8da88a
-size 20698
+oid sha256:44e7ec8e5faef24b70a1241722600251008b7a32ed24c54e817eb5622428f895
+size 23151

runs/Nov14_16-11-37_bae606737fc2/events.out.tfevents.1731604971.bae606737fc2.271.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b1f5c7b9e756042038c5e0269d76f161eb16372fcd804a1e380bece6d7f8042
+size 921

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
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "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:ae74f44dde39d500dff2c79d488590c540de669cdb651275236a09d118c70b66
+size 5304

training_params.json

@@ -0,0 +1,30 @@
+{
+    "data_path": "sbert-ru-huawei-rureviews-no-duplicates/autotrain-data",
+    "model": "sismetanin/sbert-ru-sentiment-rureviews",
+    "lr": 5e-05,
+    "epochs": 3,
+    "max_seq_length": 256,
+    "batch_size": 8,
+    "warmup_ratio": 0.1,
+    "gradient_accumulation": 4,
+    "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": "sbert-ru-huawei-rureviews-no-duplicates",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "eval_strategy": "epoch",
+    "username": "ivanovsdesign",
+    "log": "tensorboard",
+    "early_stopping_patience": 5,
+    "early_stopping_threshold": 0.01
+}