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 +1,74 @@
+{
+  "_name_or_path": "deberta-large",
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Fait divers",
+    "1": "\u00c9conomie",
+    "2": "Politique",
+    "3": "Soci\u00e9t\u00e9",
+    "4": "Relations internationales",
+    "5": "D\u00e9bat",
+    "6": "Inclassable",
+    "7": "Intervenant",
+    "8": "\u00c9ducation",
+    "9": "Sport",
+    "10": "Culture",
+    "11": "Citation",
+    "12": "M\u00e9ta",
+    "13": "Sant\u00e9",
+    "14": "Sondage",
+    "15": "Clip",
+    "16": "Attribution"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Attribution": 16,
+    "Citation": 11,
+    "Clip": 15,
+    "Culture": 10,
+    "D\u00e9bat": 5,
+    "Fait divers": 0,
+    "Inclassable": 6,
+    "Intervenant": 7,
+    "M\u00e9ta": 12,
+    "Politique": 2,
+    "Relations internationales": 4,
+    "Sant\u00e9": 13,
+    "Soci\u00e9t\u00e9": 3,
+    "Sondage": 14,
+    "Sport": 9,
+    "\u00c9conomie": 1,
+    "\u00c9ducation": 8
+  },
+  "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": "4.41.2",
+  "type_vocab_size": 0,
+  "vocab_size": 251000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6ae01ec5ea9664e340bffa561d66209ab3d6dfcb3445dde83740b924b6b0098
+size 1115314348

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb40f4d68239009dc360184c32e96c5c5fe40d46161fa2fe74b4d0e0808ae344
+size 2230748282

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddc66d47a306b3e53d889093b28ba9746e6e89eb7d0534c2f3eb25a8cc6ca954
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76bd2722733e6c0816ef855c559e7b44b866c02d7448be7b00f12a92b78e0f1d
+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 sha256:7dbb7b63c76007984d0e58a90ee901ceb5b16c8e78252d36ddcde748b3474a1a
+size 16331639

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 +1,167 @@
+{
+  "best_metric": 0.686046511627907,
+  "best_model_checkpoint": "deberta-transcript-classification/checkpoint-8126",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 8126,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.12306177701206006,
+      "grad_norm": 2.0186474323272705,
+      "learning_rate": 1.9179588153252935e-05,
+      "loss": 0.2543,
+      "step": 500
+    },
+    {
+      "epoch": 0.24612355402412012,
+      "grad_norm": 2.220743417739868,
+      "learning_rate": 1.8359176306505868e-05,
+      "loss": 0.1969,
+      "step": 1000
+    },
+    {
+      "epoch": 0.3691853310361802,
+      "grad_norm": 2.504720449447632,
+      "learning_rate": 1.75387644597588e-05,
+      "loss": 0.1779,
+      "step": 1500
+    },
+    {
+      "epoch": 0.49224710804824023,
+      "grad_norm": 0.3125078082084656,
+      "learning_rate": 1.671835261301173e-05,
+      "loss": 0.1607,
+      "step": 2000
+    },
+    {
+      "epoch": 0.6153088850603002,
+      "grad_norm": 0.8753023147583008,
+      "learning_rate": 1.5897940766264664e-05,
+      "loss": 0.1519,
+      "step": 2500
+    },
+    {
+      "epoch": 0.7383706620723604,
+      "grad_norm": 1.9338386058807373,
+      "learning_rate": 1.50775289195176e-05,
+      "loss": 0.1481,
+      "step": 3000
+    },
+    {
+      "epoch": 0.8614324390844204,
+      "grad_norm": 4.1667304039001465,
+      "learning_rate": 1.4257117072770533e-05,
+      "loss": 0.1308,
+      "step": 3500
+    },
+    {
+      "epoch": 0.9844942160964805,
+      "grad_norm": 1.195173978805542,
+      "learning_rate": 1.3436705226023466e-05,
+      "loss": 0.141,
+      "step": 4000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5977653631284916,
+      "eval_f1": 0.6445783132530121,
+      "eval_loss": 0.12648048996925354,
+      "eval_roc_auc": 0.7908519553072625,
+      "eval_runtime": 8.0537,
+      "eval_samples_per_second": 44.452,
+      "eval_steps_per_second": 44.452,
+      "step": 4063
+    },
+    {
+      "epoch": 1.1075559931085406,
+      "grad_norm": 5.743582248687744,
+      "learning_rate": 1.26162933792764e-05,
+      "loss": 0.1232,
+      "step": 4500
+    },
+    {
+      "epoch": 1.2306177701206005,
+      "grad_norm": 1.529942274093628,
+      "learning_rate": 1.1795881532529329e-05,
+      "loss": 0.111,
+      "step": 5000
+    },
+    {
+      "epoch": 1.3536795471326606,
+      "grad_norm": 0.2728979289531708,
+      "learning_rate": 1.0975469685782262e-05,
+      "loss": 0.1241,
+      "step": 5500
+    },
+    {
+      "epoch": 1.4767413241447207,
+      "grad_norm": 0.21842879056930542,
+      "learning_rate": 1.0155057839035196e-05,
+      "loss": 0.1185,
+      "step": 6000
+    },
+    {
+      "epoch": 1.5998031011567808,
+      "grad_norm": 0.08660631626844406,
+      "learning_rate": 9.334645992288129e-06,
+      "loss": 0.1276,
+      "step": 6500
+    },
+    {
+      "epoch": 1.7228648781688407,
+      "grad_norm": 0.07522659748792648,
+      "learning_rate": 8.514234145541062e-06,
+      "loss": 0.1116,
+      "step": 7000
+    },
+    {
+      "epoch": 1.8459266551809008,
+      "grad_norm": 0.2456115484237671,
+      "learning_rate": 7.693822298793995e-06,
+      "loss": 0.1065,
+      "step": 7500
+    },
+    {
+      "epoch": 1.968988432192961,
+      "grad_norm": 0.16100919246673584,
+      "learning_rate": 6.873410452046928e-06,
+      "loss": 0.1113,
+      "step": 8000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6564245810055865,
+      "eval_f1": 0.686046511627907,
+      "eval_loss": 0.1288219690322876,
+      "eval_roc_auc": 0.8214036312849162,
+      "eval_runtime": 7.9308,
+      "eval_samples_per_second": 45.141,
+      "eval_steps_per_second": 45.141,
+      "step": 8126
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 12189,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2138366728169472.0,
+  "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 sha256:4aa5310d6ba88a25eca47dd9fa56586e863fe941e9c9955f4867279a9f4989ee
+size 5176