Upload folder using huggingface_hub

README.md

@@ -0,0 +1,37 @@
+
+---
+library_name: transformers
+tags:
+- autotrain
+- text-classification
+base_model: FacebookAI/roberta-large
+widget:
+- text: "I love AutoTrain"
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Text Classification
+
+## Validation Metrics
+loss: 0.727709949016571
+
+f1_macro: 0.5042735042735043
+
+f1_micro: 0.7647058823529411
+
+f1_weighted: 0.7149321266968326
+
+precision_macro: 0.48412698412698413
+
+precision_micro: 0.7647058823529411
+
+precision_weighted: 0.6722689075630253
+
+recall_macro: 0.5277777777777778
+
+recall_micro: 0.7647058823529411
+
+recall_weighted: 0.7647058823529411
+
+accuracy: 0.7647058823529411

checkpoint-27/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "FacebookAI/roberta-large",
+  "_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": 1024,
+  "id2label": {
+    "0": "inne",
+    "1": "komunikat prasowy",
+    "2": "zaproszenie"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "inne": 0,
+    "komunikat prasowy": 1,
+    "zaproszenie": 2
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

checkpoint-27/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f44fd94b271ec8a41ca178b9018e017b31c39b564d7aa952a91665de391112d5
+size 1421499516

checkpoint-27/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b32f066dce6ede7278ab359a97cbd90bdc06be8966ea60db2e3f083476480c5
+size 2843220461

checkpoint-27/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43c117f833006258dd07ef6470201c78c4cab683cbb92557d23fb52f550785ef
+size 13990

checkpoint-27/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d794caad09a83675e886abbc4e495aef96f68012cb6bb1fdaa7553c616e46c3b
+size 1064

checkpoint-27/trainer_state.json

@@ -0,0 +1,285 @@
+{
+  "best_metric": 0.727709949016571,
+  "best_model_checkpoint": "email-classifier-large/checkpoint-27",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 27,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1111111111111111,
+      "grad_norm": 21.054508209228516,
+      "learning_rate": 5.555555555555556e-06,
+      "loss": 1.2646,
+      "step": 1
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 14.41618537902832,
+      "learning_rate": 1.1111111111111112e-05,
+      "loss": 1.2543,
+      "step": 2
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 11.813241004943848,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 1.1985,
+      "step": 3
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 10.183070182800293,
+      "learning_rate": 2.2222222222222223e-05,
+      "loss": 1.0548,
+      "step": 4
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 10.102678298950195,
+      "learning_rate": 2.777777777777778e-05,
+      "loss": 0.9208,
+      "step": 5
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 9.924948692321777,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 1.0067,
+      "step": 6
+    },
+    {
+      "epoch": 0.7777777777777778,
+      "grad_norm": 15.725824356079102,
+      "learning_rate": 3.888888888888889e-05,
+      "loss": 0.7678,
+      "step": 7
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 13.782758712768555,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.7465,
+      "step": 8
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 70.53299713134766,
+      "learning_rate": 5e-05,
+      "loss": 1.3437,
+      "step": 9
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7058823529411765,
+      "eval_f1_macro": 0.27586206896551724,
+      "eval_f1_micro": 0.7058823529411765,
+      "eval_f1_weighted": 0.5841784989858012,
+      "eval_loss": 1.0482426881790161,
+      "eval_precision_macro": 0.23529411764705885,
+      "eval_precision_micro": 0.7058823529411765,
+      "eval_precision_weighted": 0.49826989619377166,
+      "eval_recall_macro": 0.3333333333333333,
+      "eval_recall_micro": 0.7058823529411765,
+      "eval_recall_weighted": 0.7058823529411765,
+      "eval_runtime": 9.661,
+      "eval_samples_per_second": 1.76,
+      "eval_steps_per_second": 0.207,
+      "step": 9
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 44.6027717590332,
+      "learning_rate": 4.938271604938271e-05,
+      "loss": 1.4167,
+      "step": 10
+    },
+    {
+      "epoch": 1.2222222222222223,
+      "grad_norm": 8.45134449005127,
+      "learning_rate": 4.876543209876544e-05,
+      "loss": 0.8386,
+      "step": 11
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 462.1361389160156,
+      "learning_rate": 4.814814814814815e-05,
+      "loss": 0.9442,
+      "step": 12
+    },
+    {
+      "epoch": 1.4444444444444444,
+      "grad_norm": 11.159658432006836,
+      "learning_rate": 4.7530864197530866e-05,
+      "loss": 0.5886,
+      "step": 13
+    },
+    {
+      "epoch": 1.5555555555555556,
+      "grad_norm": 8.21164608001709,
+      "learning_rate": 4.691358024691358e-05,
+      "loss": 0.7998,
+      "step": 14
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 11.218172073364258,
+      "learning_rate": 4.62962962962963e-05,
+      "loss": 0.8271,
+      "step": 15
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "grad_norm": 8.036384582519531,
+      "learning_rate": 4.567901234567901e-05,
+      "loss": 0.4155,
+      "step": 16
+    },
+    {
+      "epoch": 1.8888888888888888,
+      "grad_norm": 11.879496574401855,
+      "learning_rate": 4.506172839506173e-05,
+      "loss": 1.0315,
+      "step": 17
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 33.30108642578125,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.6819,
+      "step": 18
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7058823529411765,
+      "eval_f1_macro": 0.27586206896551724,
+      "eval_f1_micro": 0.7058823529411765,
+      "eval_f1_weighted": 0.5841784989858012,
+      "eval_loss": 0.7542034983634949,
+      "eval_precision_macro": 0.23529411764705885,
+      "eval_precision_micro": 0.7058823529411765,
+      "eval_precision_weighted": 0.49826989619377166,
+      "eval_recall_macro": 0.3333333333333333,
+      "eval_recall_micro": 0.7058823529411765,
+      "eval_recall_weighted": 0.7058823529411765,
+      "eval_runtime": 10.5136,
+      "eval_samples_per_second": 1.617,
+      "eval_steps_per_second": 0.19,
+      "step": 18
+    },
+    {
+      "epoch": 2.111111111111111,
+      "grad_norm": 70.35055541992188,
+      "learning_rate": 4.3827160493827164e-05,
+      "loss": 0.9715,
+      "step": 19
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 18.602529525756836,
+      "learning_rate": 4.3209876543209875e-05,
+      "loss": 1.0681,
+      "step": 20
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 11.670511245727539,
+      "learning_rate": 4.259259259259259e-05,
+      "loss": 0.9926,
+      "step": 21
+    },
+    {
+      "epoch": 2.4444444444444446,
+      "grad_norm": 11.727529525756836,
+      "learning_rate": 4.197530864197531e-05,
+      "loss": 0.4386,
+      "step": 22
+    },
+    {
+      "epoch": 2.5555555555555554,
+      "grad_norm": 24.286405563354492,
+      "learning_rate": 4.135802469135803e-05,
+      "loss": 0.8252,
+      "step": 23
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 10.522771835327148,
+      "learning_rate": 4.074074074074074e-05,
+      "loss": 0.6967,
+      "step": 24
+    },
+    {
+      "epoch": 2.7777777777777777,
+      "grad_norm": 10.512320518493652,
+      "learning_rate": 4.012345679012346e-05,
+      "loss": 0.6406,
+      "step": 25
+    },
+    {
+      "epoch": 2.888888888888889,
+      "grad_norm": 13.10132122039795,
+      "learning_rate": 3.950617283950617e-05,
+      "loss": 0.7791,
+      "step": 26
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 32.59843826293945,
+      "learning_rate": 3.888888888888889e-05,
+      "loss": 0.5143,
+      "step": 27
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7647058823529411,
+      "eval_f1_macro": 0.5042735042735043,
+      "eval_f1_micro": 0.7647058823529411,
+      "eval_f1_weighted": 0.7149321266968326,
+      "eval_loss": 0.727709949016571,
+      "eval_precision_macro": 0.48412698412698413,
+      "eval_precision_micro": 0.7647058823529411,
+      "eval_precision_weighted": 0.6722689075630253,
+      "eval_recall_macro": 0.5277777777777778,
+      "eval_recall_micro": 0.7647058823529411,
+      "eval_recall_weighted": 0.7647058823529411,
+      "eval_runtime": 9.5294,
+      "eval_samples_per_second": 1.784,
+      "eval_steps_per_second": 0.21,
+      "step": 27
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 90,
+  "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": 47528660118528.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-27/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc5b52057bd048972d829048f3b69bdb3f32d9a1300a61378eaa2a353421e758
+size 5368

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "FacebookAI/roberta-large",
+  "_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": 1024,
+  "id2label": {
+    "0": "inne",
+    "1": "komunikat prasowy",
+    "2": "zaproszenie"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "inne": 0,
+    "komunikat prasowy": 1,
+    "zaproszenie": 2
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.0",
+  "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:f44fd94b271ec8a41ca178b9018e017b31c39b564d7aa952a91665de391112d5
+size 1421499516

runs/May17_17-16-58_r-igiag-document-classification-11uvtc3e-2329a-nxhz1/events.out.tfevents.1747502219.r-igiag-document-classification-11uvtc3e-2329a-nxhz1.103.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78efcc5910de5151fef09d5d7bb27a64c921716fa22670d1dcfe934ed73ce869
-size 16029
+oid sha256:711b321940ead4fd21071991d574c79c7dfa09a49dbfdc3bed4182d3cd23db97
+size 27101

runs/May17_17-16-58_r-igiag-document-classification-11uvtc3e-2329a-nxhz1/events.out.tfevents.1747503460.r-igiag-document-classification-11uvtc3e-2329a-nxhz1.103.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c599b5db36e1066ac481d2a481cffbe79a638c1432a116b984b27986ad650030
+size 906

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 +1,58 @@
+{
+  "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": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "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:bc5b52057bd048972d829048f3b69bdb3f32d9a1300a61378eaa2a353421e758
+size 5368

training_params.json

@@ -0,0 +1,30 @@
+{
+    "data_path": "email-classifier-large/autotrain-data",
+    "model": "FacebookAI/roberta-large",
+    "lr": 5e-05,
+    "epochs": 10,
+    "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": "email-classifier-large",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "eval_strategy": "epoch",
+    "username": "igiag",
+    "log": "tensorboard",
+    "early_stopping_patience": 5,
+    "early_stopping_threshold": 0.01
+}