End of training

README.md

@@ -0,0 +1,73 @@
+---
+license: mit
+base_model: BAAI/bge-base-en-v1.5
+tags:
+- generated_from_trainer
+model-index:
+- name: SECTOR-multilabel-bge
+  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. -->
+
+# SECTOR-multilabel-bge
+
+This model is a fine-tuned version of [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6114
+- Precision-micro: 0.6428
+- Precision-samples: 0.7488
+- Precision-weighted: 0.6519
+- Recall-micro: 0.7855
+- Recall-samples: 0.8627
+- Recall-weighted: 0.7855
+- F1-micro: 0.7071
+- F1-samples: 0.7638
+- F1-weighted: 0.7109
+
+## 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: 7.04e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 300
+- num_epochs: 7
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision-micro | Precision-samples | Precision-weighted | Recall-micro | Recall-samples | Recall-weighted | F1-micro | F1-samples | F1-weighted |
+|:-------------:|:-----:|:----:|:---------------:|:---------------:|:-----------------:|:------------------:|:------------:|:--------------:|:---------------:|:--------:|:----------:|:-----------:|
+| 0.7077        | 1.0   | 633  | 0.5490          | 0.4226          | 0.5465            | 0.4954             | 0.8211       | 0.8908         | 0.8211          | 0.5580   | 0.6243     | 0.5977      |
+| 0.4546        | 2.0   | 1266 | 0.5009          | 0.4899          | 0.6127            | 0.5202             | 0.8438       | 0.9023         | 0.8438          | 0.6199   | 0.6822     | 0.6366      |
+| 0.3105        | 3.0   | 1899 | 0.4947          | 0.5005          | 0.6593            | 0.5317             | 0.8508       | 0.8970         | 0.8508          | 0.6303   | 0.7125     | 0.6474      |
+| 0.2044        | 4.0   | 2532 | 0.5430          | 0.5757          | 0.7044            | 0.5970             | 0.8106       | 0.8801         | 0.8106          | 0.6733   | 0.7379     | 0.6834      |
+| 0.1314        | 5.0   | 3165 | 0.5633          | 0.6132          | 0.7385            | 0.6271             | 0.8065       | 0.8772         | 0.8065          | 0.6967   | 0.7606     | 0.7032      |
+| 0.0892        | 6.0   | 3798 | 0.6073          | 0.6425          | 0.7499            | 0.6545             | 0.7844       | 0.8610         | 0.7844          | 0.7064   | 0.7634     | 0.7113      |
+| 0.0721        | 7.0   | 4431 | 0.6114          | 0.6428          | 0.7488            | 0.6519             | 0.7855       | 0.8627         | 0.7855          | 0.7071   | 0.7638     | 0.7109      |
+
+
+### Framework versions
+
+- Transformers 4.38.1
+- Pytorch 2.1.0+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,67 @@
+{
+  "_name_or_path": "BAAI/bge-base-en-v1.5",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Agriculture",
+    "1": "Buildings",
+    "2": "Coastal Zone",
+    "3": "Cross-Cutting Area",
+    "4": "Disaster Risk Management (DRM)",
+    "5": "Economy-wide",
+    "6": "Education",
+    "7": "Energy",
+    "8": "Environment",
+    "9": "Health",
+    "10": "Industries",
+    "11": "LULUCF/Forestry",
+    "12": "Social Development",
+    "13": "Tourism",
+    "14": "Transport",
+    "15": "Urban",
+    "16": "Waste",
+    "17": "Water"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Agriculture": 0,
+    "Buildings": 1,
+    "Coastal Zone": 2,
+    "Cross-Cutting Area": 3,
+    "Disaster Risk Management (DRM)": 4,
+    "Economy-wide": 5,
+    "Education": 6,
+    "Energy": 7,
+    "Environment": 8,
+    "Health": 9,
+    "Industries": 10,
+    "LULUCF/Forestry": 11,
+    "Social Development": 12,
+    "Tourism": 13,
+    "Transport": 14,
+    "Urban": 15,
+    "Waste": 16,
+    "Water": 17
+  },
+  "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": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

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
+2024-03-05T23:19:43,codecarbon,727eed1e-6387-4857-985b-e8da458c6c91,5151.265522003174,0.058193255324611504,1.1296885217048933e-05,42.5,33.394069299021034,4.753043174743652,0.06078969413803689,0.099053111742426,0.006792039566368056,0.1666348454468306,United States,USA,nevada,,,Linux-6.1.58+-x86_64-with-glibc2.35,3.10.12,2.3.4,2,Intel(R) Xeon(R) CPU @ 2.00GHz,1,1 x Tesla T4,-115.1164,36.1685,12.674781799316406,machine,N,1.0

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e509065ec107e8d83b1c883f4be7ee51c3528d203a85c93f6b8b00c2f0ac82a
+size 438007864

runs/Mar05_21-53-05_0fb3b3ae2e9b/events.out.tfevents.1709675632.0fb3b3ae2e9b.409.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69af92bcf6a10518ad8c900dc1563f7773689a5fbfdf6df40564db8b0bf02f1e
+size 12888

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "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": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "problem_type": "multi_label_classification",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65f47f0b0443faa91dcd012be844a6da2b3aed7c0f28a97077abf72657aeec91
+size 4920