louisbrulenaudet/lemone-router-s

.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 +1,65 @@
+---
+library_name: transformers
+license: mit
+base_model: intfloat/multilingual-e5-small
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: lemone-router-s
+  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-s
+
+This model is a fine-tuned version of [intfloat/multilingual-e5-small](https://huggingface.co/intfloat/multilingual-e5-small) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4446
+- Accuracy: 0.9061
+
+## 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: 9.736038436571022e-05
+- train_batch_size: 8
+- eval_batch_size: 64
+- seed: 6
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 4
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 0.6002        | 1.0   | 5617  | 0.5964          | 0.8207   |
+| 0.4506        | 2.0   | 11234 | 0.4375          | 0.8788   |
+| 0.3138        | 3.0   | 16851 | 0.4400          | 0.8965   |
+| 0.189         | 4.0   | 22468 | 0.4446          | 0.9061   |
+
+
+### Framework versions
+
+- Transformers 4.45.2
+- Pytorch 2.4.1+cu121
+- Datasets 2.21.0
+- Tokenizers 0.20.1

config.json

@@ -0,0 +1,47 @@
+{
+  "_name_or_path": "intfloat/multilingual-e5-small",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "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": 1536,
+  "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-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250037
+}

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
+2024-10-23T03:06:41,codecarbon,2aa2f3c1-5e87-48bb-b699-f6381c979a7c,932.511025428772,0.04942378693389894,5.3000753434710015e-05,42.5,176.20270000514734,118.00735330581666,0.011008666932582855,0.09232817358470236,0.030554202674925642,0.13389104319221082,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 sha256:4985b2e959dc4b5b85b4de000bac9e4e5b1e376df376b03df1e337bee358db9a
+size 470650904

runs/Oct23_01-48-17_lemone/events.out.tfevents.1729651869.lemone

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d36f0c071d4ce1822e5ec206af6d24a4a5f592fbe2eb83208fa24333c1f78ce
+size 16595

runs/Oct23_01-48-17_lemone/events.out.tfevents.1729652808.lemone

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06dc1c5134e2346dd9b3b8854f69455dbc74e89035c0703d9e614dccc992a9f9
+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": false,
+    "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 sha256:3bc419f52a289472c7bc97f403dea966e9eaa4ffd74b547ddfec9f34843877e4
+size 17083065

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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": 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": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eeb4e0997d735fb012f0cb6f9e2c919c4b45620497a852bcfa54e0a59f1a038c
+size 5240