Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 250101
+}

config.json

@@ -0,0 +1,110 @@
+{
+  "_name_or_path": "/gpfsdswork/projects/rech/fmr/uft12cr/classification/deberta-large",
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Intention_Informer",
+    "1": "Intention_\u00c9duquer",
+    "2": "Intention_Sensibiliser",
+    "3": "Intention_Mobiliser",
+    "4": "Intention_Promouvoir",
+    "5": "Intention_Divertir",
+    "6": "Theme_Sant\u00e9",
+    "7": "Theme_Soci\u00e9t\u00e9",
+    "8": "Theme_\u00c9conomie",
+    "9": "Theme_Politique",
+    "10": "Theme_Pub",
+    "11": "Theme_Sports",
+    "12": "Theme_Environnement",
+    "13": "Theme_Culture",
+    "14": "Theme_je",
+    "15": "Expression_Publicite",
+    "16": "Expression_Informations",
+    "17": "Expression_Reportage/Enquete",
+    "18": "Expression_Interview/Discussion",
+    "19": "Expression_Meteo",
+    "20": "Tonalite_Informative",
+    "21": "Tonalite_Emotionnelle",
+    "22": "Tonalite_Publicitaire",
+    "23": "Tonalite_Analytique",
+    "24": "Tonalite_Satirique",
+    "25": "Emotion_Neutre",
+    "26": "Emotion_Alarmant",
+    "27": "Emotion_Indign\u00e9",
+    "28": "Emotion_Persuasif",
+    "29": "Emotion_Solennel",
+    "30": "Emotion_Optimiste",
+    "31": "Emotion_Ironique",
+    "32": "Figure_Metaphore",
+    "33": "Figure_Paradoxe",
+    "34": "Figure_Hyperbole"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Emotion_Alarmant": 26,
+    "Emotion_Indign\u00e9": 27,
+    "Emotion_Ironique": 31,
+    "Emotion_Neutre": 25,
+    "Emotion_Optimiste": 30,
+    "Emotion_Persuasif": 28,
+    "Emotion_Solennel": 29,
+    "Expression_Informations": 16,
+    "Expression_Interview/Discussion": 18,
+    "Expression_Meteo": 19,
+    "Expression_Publicite": 15,
+    "Expression_Reportage/Enquete": 17,
+    "Figure_Hyperbole": 34,
+    "Figure_Metaphore": 32,
+    "Figure_Paradoxe": 33,
+    "Intention_Divertir": 5,
+    "Intention_Informer": 0,
+    "Intention_Mobiliser": 3,
+    "Intention_Promouvoir": 4,
+    "Intention_Sensibiliser": 2,
+    "Intention_\u00c9duquer": 1,
+    "Theme_Culture": 13,
+    "Theme_Environnement": 12,
+    "Theme_Politique": 9,
+    "Theme_Pub": 10,
+    "Theme_Sant\u00e9": 6,
+    "Theme_Soci\u00e9t\u00e9": 7,
+    "Theme_Sports": 11,
+    "Theme_je": 14,
+    "Theme_\u00c9conomie": 8,
+    "Tonalite_Analytique": 23,
+    "Tonalite_Emotionnelle": 21,
+    "Tonalite_Informative": 20,
+    "Tonalite_Publicitaire": 22,
+    "Tonalite_Satirique": 24
+  },
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "problem_type": "multi_label_classification",
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.0.dev0",
+  "type_vocab_size": 0,
+  "vocab_size": 251000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c062326a3d397e2afad75b264aaef47a0923a24c2b66e3d7c43b69b6cc54ed46
+size 1115369724

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fd917d9135af97af2e6beb9601a7271692252feb68f771cf700fc43e479eaa5
+size 2230859002

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e2b27a523a9fd069d1154bb25df70d3244a9c0a81e1eff87a5bf621d7350745
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7df548493459caf2a0282cf8e370e77e5b78ca0b2c21d4560c164003ecd2189e
+size 1064

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13c8d666d62a7bc4ac8f040aab68e942c861f93303156cc28f5c7e885d86d6e3
+size 4305025

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f42839ec04c3025630c31f069df13d750b5a3c969345d768ca8e0da9119600c7
+size 16331661

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250101": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

trainer_state.json

@@ -0,0 +1,124 @@
+{
+  "best_metric": 0.7596717467760844,
+  "best_model_checkpoint": "deberta-classification-transcripts/checkpoint-4325",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 4325,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.58,
+      "learning_rate": 8.84393063583815e-06,
+      "loss": 0.4483,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.09210526315789473,
+      "eval_f1": 0.6887254901960784,
+      "eval_loss": 0.2805722951889038,
+      "eval_roc_auc": 0.7836829389177116,
+      "eval_runtime": 1.7776,
+      "eval_samples_per_second": 42.755,
+      "eval_steps_per_second": 42.755,
+      "step": 865
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 7.687861271676302e-06,
+      "loss": 0.339,
+      "step": 1000
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 6.531791907514451e-06,
+      "loss": 0.2866,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.10526315789473684,
+      "eval_f1": 0.7407407407407407,
+      "eval_loss": 0.22884871065616608,
+      "eval_roc_auc": 0.8162958199606408,
+      "eval_runtime": 1.7174,
+      "eval_samples_per_second": 44.252,
+      "eval_steps_per_second": 44.252,
+      "step": 1730
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 5.375722543352601e-06,
+      "loss": 0.265,
+      "step": 2000
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 4.219653179190752e-06,
+      "loss": 0.2368,
+      "step": 2500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.06578947368421052,
+      "eval_f1": 0.7450058754406581,
+      "eval_loss": 0.20490357279777527,
+      "eval_roc_auc": 0.8221279142285448,
+      "eval_runtime": 1.7181,
+      "eval_samples_per_second": 44.235,
+      "eval_steps_per_second": 44.235,
+      "step": 2595
+    },
+    {
+      "epoch": 3.47,
+      "learning_rate": 3.063583815028902e-06,
+      "loss": 0.2351,
+      "step": 3000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.09210526315789473,
+      "eval_f1": 0.7520759193357057,
+      "eval_loss": 0.19738489389419556,
+      "eval_roc_auc": 0.8239552326387778,
+      "eval_runtime": 1.7202,
+      "eval_samples_per_second": 44.18,
+      "eval_steps_per_second": 44.18,
+      "step": 3460
+    },
+    {
+      "epoch": 4.05,
+      "learning_rate": 1.907514450867052e-06,
+      "loss": 0.2232,
+      "step": 3500
+    },
+    {
+      "epoch": 4.62,
+      "learning_rate": 7.514450867052025e-07,
+      "loss": 0.2127,
+      "step": 4000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.10526315789473684,
+      "eval_f1": 0.7596717467760844,
+      "eval_loss": 0.19270123541355133,
+      "eval_roc_auc": 0.830700986111798,
+      "eval_runtime": 1.7179,
+      "eval_samples_per_second": 44.241,
+      "eval_steps_per_second": 44.241,
+      "step": 4325
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4325,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 1138312891315200.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:458c8d3b21adc6abf439f3039446992fc81ee61cc98a20d37234ca69deb52872
+size 4792