End of training

README.md

@@ -0,0 +1,52 @@
+---
+license: mit
+base_model: flaubert/flaubert_base_cased
+tags:
+- generated_from_trainer
+model-index:
+- name: bert-base-banking77-pt2
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# bert-base-banking77-pt2
+
+This model is a fine-tuned version of [flaubert/flaubert_base_cased](https://huggingface.co/flaubert/flaubert_base_cased) on the None dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 1024
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.1+cu121
+- Datasets 2.19.2
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,325 @@
+{
+  "_name_or_path": "flaubert/flaubert_base_cased",
+  "amp": 1,
+  "architectures": [
+    "FlaubertForSequenceClassification"
+  ],
+  "asm": false,
+  "attention_dropout": 0.1,
+  "bos_index": 0,
+  "bos_token_id": 0,
+  "bptt": 512,
+  "causal": false,
+  "clip_grad_norm": 5,
+  "dropout": 0.1,
+  "emb_dim": 768,
+  "embed_init_std": 0.02209708691207961,
+  "encoder_only": true,
+  "end_n_top": 5,
+  "eos_index": 1,
+  "fp16": true,
+  "gelu_activation": true,
+  "group_by_size": true,
+  "id2label": {
+    "0": "Taxes",
+    "1": "Esth\u00e9tique",
+    "2": "Ch\u00e8ques",
+    "3": "Baby-sitters & Cr\u00e8ches",
+    "4": "Entretien",
+    "5": "Frais juridique",
+    "6": "Internet",
+    "7": "Billets de train",
+    "8": "Sport",
+    "9": "H\u00f4tels",
+    "10": "Transports en commun",
+    "11": "Assurance habitation",
+    "12": "TVA",
+    "13": "Alimentation - Autres",
+    "14": "Carburant",
+    "15": "Frais bancaires",
+    "16": "D\u00e9p\u00f4t d'argent",
+    "17": "D\u00e9bit mensuel carte",
+    "18": "Sant\u00e9 - Autres",
+    "19": "Publicit\u00e9",
+    "20": "Stationnement",
+    "21": "Pr\u00e9voyance",
+    "22": "Spa & Massage",
+    "23": "Extra",
+    "24": "T\u00e9l\u00e9phonie mobile",
+    "25": "Articles de sport",
+    "26": "Musique",
+    "27": "Loyer",
+    "28": "Salaires",
+    "29": "Livres",
+    "30": "C\u00e2ble / Satellite",
+    "31": "Divertissements",
+    "32": "Billets d'avion",
+    "33": "Virements internes",
+    "34": "Entretien v\u00e9hicule",
+    "35": "P\u00e9age",
+    "36": "Remboursements",
+    "37": "Hypoth\u00e8que",
+    "38": "Cadeaux",
+    "39": "Conseils",
+    "40": "V\u00eatements/Chaussures",
+    "41": "Remboursement emprunt",
+    "42": "Auto & Transports - Autres",
+    "43": "Marketing",
+    "44": "Esth\u00e9tique & Soins - Autres",
+    "45": "Sortie au restaurant",
+    "46": "Subventions",
+    "47": "Pressing",
+    "48": "Sports d'hiver",
+    "49": "R\u00e9mun\u00e9rations dirigeants",
+    "50": "Cosm\u00e9tique",
+    "51": "Charges diverses",
+    "52": "Retraite",
+    "53": "Autres rentr\u00e9es",
+    "54": "Allocations et pensions",
+    "55": "Dons",
+    "56": "Economies",
+    "57": "Comptabilit\u00e9",
+    "58": "Frais d'impressions",
+    "59": "Jouets",
+    "60": "Taxe d'apprentissage",
+    "61": "Imp\u00f4ts & Taxes - Autres",
+    "62": "Fast foods",
+    "63": "Tabac",
+    "64": "Licences",
+    "65": "Supermarch\u00e9 / Epicerie",
+    "66": "M\u00e9decin",
+    "67": "Frais d'exp\u00e9ditions",
+    "68": "Ecole",
+    "69": "Films & DVDs",
+    "70": "Emprunt",
+    "71": "Pharmacie",
+    "72": "Incidents de paiement",
+    "73": "Autres d\u00e9penses",
+    "74": "Sorties culturelles",
+    "75": "Voyages / Vacances",
+    "76": "Logement \u00e9tudiant",
+    "77": "Frais Animaux",
+    "78": "Mutuelle",
+    "79": "Electricit\u00e9",
+    "80": "Ext\u00e9rieur et jardin",
+    "81": "Assurance",
+    "82": "Opticien / Ophtalmo.",
+    "83": "D\u00e9penses pro - Autres",
+    "84": "Amendes",
+    "85": "Epargne",
+    "86": "Abonnements - Autres",
+    "87": "Bars / Clubs",
+    "88": "Dentiste",
+    "89": "Retraits",
+    "90": "Fournitures de bureau",
+    "91": "Loisirs & Sorties - Autres",
+    "92": "Coiffeur",
+    "93": "Banque - Autres",
+    "94": "Eau",
+    "95": "Sous-traitance",
+    "96": "D\u00e9coration",
+    "97": "Logement - Autres",
+    "98": "Gaz",
+    "99": "Location de v\u00e9hicule",
+    "100": "Imp\u00f4ts fonciers",
+    "101": "Services Bancaires",
+    "102": "Hobbies",
+    "103": "Virements",
+    "104": "Ventes",
+    "105": "Loyers re\u00e7us",
+    "106": "A cat\u00e9goriser",
+    "107": "Services",
+    "108": "Services en ligne",
+    "109": "Maintenance bureaux",
+    "110": "Notes de frais",
+    "111": "Achats & Shopping - Autres",
+    "112": "Pensions",
+    "113": "Fournitures scolaires",
+    "114": "High Tech",
+    "115": "Assurance v\u00e9hicule",
+    "116": "Restaurants",
+    "117": "Int\u00e9r\u00eats",
+    "118": "Scolarit\u00e9 & Enfants - Autres",
+    "119": "Caf\u00e9"
+  },
+  "id2lang": {
+    "0": "fr"
+  },
+  "init_std": 0.02,
+  "is_encoder": true,
+  "label2id": {
+    "A cat\u00e9goriser": 106,
+    "Abonnements - Autres": 86,
+    "Achats & Shopping - Autres": 111,
+    "Alimentation - Autres": 13,
+    "Allocations et pensions": 54,
+    "Amendes": 84,
+    "Articles de sport": 25,
+    "Assurance": 81,
+    "Assurance habitation": 11,
+    "Assurance v\u00e9hicule": 115,
+    "Auto & Transports - Autres": 42,
+    "Autres d\u00e9penses": 73,
+    "Autres rentr\u00e9es": 53,
+    "Baby-sitters & Cr\u00e8ches": 3,
+    "Banque - Autres": 93,
+    "Bars / Clubs": 87,
+    "Billets d'avion": 32,
+    "Billets de train": 7,
+    "Cadeaux": 38,
+    "Caf\u00e9": 119,
+    "Carburant": 14,
+    "Charges diverses": 51,
+    "Ch\u00e8ques": 2,
+    "Coiffeur": 92,
+    "Comptabilit\u00e9": 57,
+    "Conseils": 39,
+    "Cosm\u00e9tique": 50,
+    "C\u00e2ble / Satellite": 30,
+    "Dentiste": 88,
+    "Divertissements": 31,
+    "Dons": 55,
+    "D\u00e9bit mensuel carte": 17,
+    "D\u00e9coration": 96,
+    "D\u00e9penses pro - Autres": 83,
+    "D\u00e9p\u00f4t d'argent": 16,
+    "Eau": 94,
+    "Ecole": 68,
+    "Economies": 56,
+    "Electricit\u00e9": 79,
+    "Emprunt": 70,
+    "Entretien": 4,
+    "Entretien v\u00e9hicule": 34,
+    "Epargne": 85,
+    "Esth\u00e9tique": 1,
+    "Esth\u00e9tique & Soins - Autres": 44,
+    "Extra": 23,
+    "Ext\u00e9rieur et jardin": 80,
+    "Fast foods": 62,
+    "Films & DVDs": 69,
+    "Fournitures de bureau": 90,
+    "Fournitures scolaires": 113,
+    "Frais Animaux": 77,
+    "Frais bancaires": 15,
+    "Frais d'exp\u00e9ditions": 67,
+    "Frais d'impressions": 58,
+    "Frais juridique": 5,
+    "Gaz": 98,
+    "High Tech": 114,
+    "Hobbies": 102,
+    "Hypoth\u00e8que": 37,
+    "H\u00f4tels": 9,
+    "Imp\u00f4ts & Taxes - Autres": 61,
+    "Imp\u00f4ts fonciers": 100,
+    "Incidents de paiement": 72,
+    "Internet": 6,
+    "Int\u00e9r\u00eats": 117,
+    "Jouets": 59,
+    "Licences": 64,
+    "Livres": 29,
+    "Location de v\u00e9hicule": 99,
+    "Logement - Autres": 97,
+    "Logement \u00e9tudiant": 76,
+    "Loisirs & Sorties - Autres": 91,
+    "Loyer": 27,
+    "Loyers re\u00e7us": 105,
+    "Maintenance bureaux": 109,
+    "Marketing": 43,
+    "Musique": 26,
+    "Mutuelle": 78,
+    "M\u00e9decin": 66,
+    "Notes de frais": 110,
+    "Opticien / Ophtalmo.": 82,
+    "Pensions": 112,
+    "Pharmacie": 71,
+    "Pressing": 47,
+    "Pr\u00e9voyance": 21,
+    "Publicit\u00e9": 19,
+    "P\u00e9age": 35,
+    "Remboursement emprunt": 41,
+    "Remboursements": 36,
+    "Restaurants": 116,
+    "Retraite": 52,
+    "Retraits": 89,
+    "R\u00e9mun\u00e9rations dirigeants": 49,
+    "Salaires": 28,
+    "Sant\u00e9 - Autres": 18,
+    "Scolarit\u00e9 & Enfants - Autres": 118,
+    "Services": 107,
+    "Services Bancaires": 101,
+    "Services en ligne": 108,
+    "Sortie au restaurant": 45,
+    "Sorties culturelles": 74,
+    "Sous-traitance": 95,
+    "Spa & Massage": 22,
+    "Sport": 8,
+    "Sports d'hiver": 48,
+    "Stationnement": 20,
+    "Subventions": 46,
+    "Supermarch\u00e9 / Epicerie": 65,
+    "TVA": 12,
+    "Tabac": 63,
+    "Taxe d'apprentissage": 60,
+    "Taxes": 0,
+    "Transports en commun": 10,
+    "T\u00e9l\u00e9phonie mobile": 24,
+    "Ventes": 104,
+    "Virements": 103,
+    "Virements internes": 33,
+    "Voyages / Vacances": 75,
+    "V\u00eatements/Chaussures": 40
+  },
+  "lang2id": {
+    "fr": 0
+  },
+  "lang_id": 0,
+  "langs": [
+    "fr"
+  ],
+  "layer_norm_eps": 1e-12,
+  "layerdrop": 0.0,
+  "lg_sampling_factor": -1,
+  "lgs": "fr",
+  "mask_index": 5,
+  "mask_token_id": 0,
+  "max_batch_size": 0,
+  "max_position_embeddings": 512,
+  "max_vocab": -1,
+  "mlm_steps": [
+    [
+      "fr",
+      null
+    ]
+  ],
+  "model_type": "flaubert",
+  "n_heads": 12,
+  "n_langs": 1,
+  "n_layers": 12,
+  "pad_index": 2,
+  "pad_token_id": 2,
+  "pre_norm": false,
+  "problem_type": "single_label_classification",
+  "sample_alpha": 0,
+  "share_inout_emb": true,
+  "sinusoidal_embeddings": false,
+  "start_n_top": 5,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "tokens_per_batch": -1,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "unk_index": 3,
+  "use_lang_emb": true,
+  "vocab_size": 68729,
+  "word_blank": 0,
+  "word_dropout": 0,
+  "word_keep": 0.1,
+  "word_mask": 0.8,
+  "word_mask_keep_rand": "0.8,0.1,0.1",
+  "word_pred": 0.15,
+  "word_rand": 0.1,
+  "word_shuffle": 0
+}

logs/events.out.tfevents.1718202403.pytorch-2-0-0-gpu-p-ml-g5-12xlarge-bd6adb7f7a95188f931aa4f47fd4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f37953a5b9c168e581c3d31c25f5c6b832d4759e1ba60d423df6ed2eab33d40
+size 10806

logs/events.out.tfevents.1718203072.pytorch-2-0-0-gpu-p-ml-g5-12xlarge-bd6adb7f7a95188f931aa4f47fd4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b2842bbab6edaa5eaac39e985d4fe3d408b75b7b800c262e18aa1a3b2a48523
+size 10802

logs/events.out.tfevents.1718203388.pytorch-2-0-0-gpu-p-ml-g5-12xlarge-bd6adb7f7a95188f931aa4f47fd4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:085c1ced60bb1efc34ae1d7a3ba8470d9c7f47f342bc57a36a8acca2118bc7a4
+size 10636

logs/events.out.tfevents.1718203821.pytorch-2-0-0-gpu-p-ml-g5-12xlarge-bd6adb7f7a95188f931aa4f47fd4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad925c909e8337b70d4133d8159a7c3e3bc0912d472f0d13aa9a42b7273708e5
+size 10470

logs/events.out.tfevents.1718204662.pytorch-2-0-0-gpu-p-ml-g5-12xlarge-bd6adb7f7a95188f931aa4f47fd4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eca26a587e2ec4e57ca01e7b581b0955e37b1c631a2103e21a18c1a057f168af
+size 12813

logs/events.out.tfevents.1718206952.pytorch-2-0-0-gpu-p-ml-g5-12xlarge-bd6adb7f7a95188f931aa4f47fd4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caee9db9140fccb285633825a40aecb438dab496386c506039d7902d2abfd1c2
+size 12813

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25bc504f7d46b0adcf3a6902664efebaac77736935464fa04230557b87523303
+size 553322104

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<special0>",
+    "<special1>",
+    "<special2>",
+    "<special3>",
+    "<special4>",
+    "<special5>",
+    "<special6>",
+    "<special7>",
+    "<special8>",
+    "<special9>"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "</s>",
+  "mask_token": "<special1>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,140 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<pad>",
+      "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
+    },
+    "4": {
+      "content": "<special0>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<special1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<special2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<special3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<special4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<special5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<special6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<special7>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<special8>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<special9>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<special0>",
+    "<special1>",
+    "<special2>",
+    "<special3>",
+    "<special4>",
+    "<special5>",
+    "<special6>",
+    "<special7>",
+    "<special8>",
+    "<special9>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "</s>",
+  "do_lower_case": false,
+  "id2lang": null,
+  "lang2id": null,
+  "mask_token": "<special1>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "FlaubertTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f61f85c5a97b6db5a59ff5a06f3b7b4d9ac62ce87b819291d65fbf7027758e4b
+size 5112