Training in progress, epoch 1

.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

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,74 @@
+{
+  "_name_or_path": "microsoft/llmlingua-2-xlm-roberta-large-meetingbank",
+  "architectures": [
+    "XLMRobertaForTokenClassification"
+  ],
+  "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": "O",
+    "1": "B-Repetition",
+    "2": "B-Loaded_Language",
+    "3": "B-Name_Calling,Labeling",
+    "4": "B-Flag-Waving",
+    "5": "I-Flag-Waving",
+    "6": "B-Causal_Oversimplification",
+    "7": "I-Causal_Oversimplification",
+    "8": "B-Doubt",
+    "9": "I-Doubt",
+    "10": "I-Loaded_Language",
+    "11": "B-Appeal_to_Authority",
+    "12": "I-Appeal_to_Authority",
+    "13": "I-Name_Calling,Labeling",
+    "14": "B-Appeal_to_fear-prejudice",
+    "15": "I-Appeal_to_fear-prejudice",
+    "16": "I-Repetition",
+    "17": "B-Black-and-White_Fallacy",
+    "18": "I-Black-and-White_Fallacy",
+    "19": "B-Exaggeration,Minimisation",
+    "20": "I-Exaggeration,Minimisation"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "B-Appeal_to_Authority": 11,
+    "B-Appeal_to_fear-prejudice": 14,
+    "B-Black-and-White_Fallacy": 17,
+    "B-Causal_Oversimplification": 6,
+    "B-Doubt": 8,
+    "B-Exaggeration,Minimisation": 19,
+    "B-Flag-Waving": 4,
+    "B-Loaded_Language": 2,
+    "B-Name_Calling,Labeling": 3,
+    "B-Repetition": 1,
+    "I-Appeal_to_Authority": 12,
+    "I-Appeal_to_fear-prejudice": 15,
+    "I-Black-and-White_Fallacy": 18,
+    "I-Causal_Oversimplification": 7,
+    "I-Doubt": 9,
+    "I-Exaggeration,Minimisation": 20,
+    "I-Flag-Waving": 5,
+    "I-Loaded_Language": 10,
+    "I-Name_Calling,Labeling": 13,
+    "I-Repetition": 16,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250102
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:463178e632d7a5850a9c9a42516cc475eedc1a323a78d8b69c6e760408a1aca3
+size 2235998826

runs/Apr24_20-17-12_bb8-lix.polytechnique.fr/events.out.tfevents.1713982638.bb8-lix.polytechnique.fr.101922.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f5d399d7ca904954bce8826541faf42aa58563aece00c19a6a1816d2b843f33
+size 5952

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.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62c24cdc13d4c9952d63718d6c9fa4c287974249e16b7ade6d5a85e7bbb75626
+size 17082660

tokenizer_config.json

@@ -0,0 +1,61 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcc5850a155dbe9d0d30667b7271b7038ff1e57ed16af708c7b66caca4ba5e18
+size 4408