louisbrulenaudet/lemone-router-l

.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

README.md

@@ -0,0 +1,64 @@
+---
+library_name: transformers
+license: mit
+base_model: intfloat/multilingual-e5-large
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: lemone-router-l
+  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. -->
+
+# lemone-router-l
+
+This model is a fine-tuned version of [intfloat/multilingual-e5-large](https://huggingface.co/intfloat/multilingual-e5-large) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4734
+- Accuracy: 0.9191
+
+## 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: 2.6763799752474963e-05
+- train_batch_size: 4
+- eval_batch_size: 64
+- seed: 25
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 0.6402        | 1.0   | 11233 | 0.6569          | 0.8630   |
+| 0.5031        | 2.0   | 22466 | 0.5058          | 0.9025   |
+| 0.2196        | 3.0   | 33699 | 0.4734          | 0.9191   |
+
+
+### Framework versions
+
+- Transformers 4.45.2
+- Pytorch 2.4.1+cu121
+- Datasets 2.21.0
+- Tokenizers 0.20.1

config.json

@@ -0,0 +1,49 @@
+{
+  "_name_or_path": "intfloat/multilingual-e5-large",
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "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": "B\u00e9n\u00e9fices professionnels",
+    "1": "Contr\u00f4le et contentieux",
+    "2": "Dispositifs transversaux",
+    "3": "Fiscalit\u00e9 des entreprises",
+    "4": "Patrimoine et enregistrement",
+    "5": "Revenus particuliers",
+    "6": "Revenus patrimoniaux",
+    "7": "Taxes sur la consommation"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "B\u00e9n\u00e9fices professionnels": 0,
+    "Contr\u00f4le et contentieux": 1,
+    "Dispositifs transversaux": 2,
+    "Fiscalit\u00e9 des entreprises": 3,
+    "Patrimoine et enregistrement": 4,
+    "Revenus particuliers": 5,
+    "Revenus patrimoniaux": 6,
+    "Taxes sur la consommation": 7
+  },
+  "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",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

emissions.csv

@@ -0,0 +1,2 @@
+timestamp,project_name,run_id,duration,emissions,emissions_rate,cpu_power,gpu_power,ram_power,cpu_energy,gpu_energy,ram_energy,energy_consumed,country_name,country_iso_code,region,cloud_provider,cloud_region,os,python_version,codecarbon_version,cpu_count,cpu_model,gpu_count,gpu_model,longitude,latitude,ram_total_size,tracking_mode,on_cloud,pue
+2024-10-23T01:46:10,codecarbon,658515b9-e954-4888-b272-77aa42d95f5f,4975.769150018692,0.28156086190449553,5.658639969328919e-05,42.5,69.40840784547605,118.00735330581666,0.058741146238313814,0.5409897852914813,0.16302886210783388,0.7627597936376294,United States,USA,virginia,,,Linux-6.8.0-1014-azure-x86_64-with-glibc2.35,3.10.12,2.5.0,40,AMD EPYC 9V84 96-Core Processor,1,1 x NVIDIA H100 NVL,-78.1539,38.7095,314.68627548217773,machine,N,1.0

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40a8aea275c4c932a2add7e498a8fd566bfd01954ca94d7529d491613796ae15
+size 2239643272

runs/Oct22_18-57-08_lemone/events.out.tfevents.1729642994.lemone

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40ce80decf773509ebc6002b881bb470ef3781a5a695f3e9b6096f197f90ee13
+size 21254

runs/Oct22_18-57-08_lemone/events.out.tfevents.1729648020.lemone

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fb0705b891dbb8e5d03ff64db9b3d1ec018e92114c301205e43e1138d04f60e
+size 40

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a56def25aa40facc030ea8b0b87f3688e4b3c39eb8b45d5702b3a1300fe2a20
+size 17082734

tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "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
+    },
+    "3": {
+      "content": "<unk>",
+      "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
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "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 sha256:3d3c2434baba0f5a0f2ddbdfcc5404aef5e057ac292f3018686a0b9afc138e75
+size 5240