nhankins/multilingual_euph_lora

README.md

@@ -0,0 +1,72 @@
+---
+license: apache-2.0
+base_model: distilbert/distilbert-base-multilingual-cased
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+model-index:
+- name: distilbert-base-multilingual-cased-lora-text-classification
+  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. -->
+
+# distilbert-base-multilingual-cased-lora-text-classification
+
+This model is a fine-tuned version of [distilbert/distilbert-base-multilingual-cased](https://huggingface.co/distilbert/distilbert-base-multilingual-cased) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5321
+- Precision: 0.7883
+- Recall: 0.8589
+- F1 and accuracy: {'accuracy': 0.7487113402061856, 'f1': 0.8220802919708029}
+
+## 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: 1e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Precision | Recall | F1 and accuracy                                            |
+|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:----------------------------------------------------------:|
+| 0.6034        | 1.0   | 1552  | 0.5999          | 0.6781    | 0.9981 | {'accuracy': 0.678479381443299, 'f1': 0.8075588121866564}  |
+| 0.5756        | 2.0   | 3104  | 0.5892          | 0.7067    | 0.9418 | {'accuracy': 0.696520618556701, 'f1': 0.8075194115243155}  |
+| 0.5607        | 3.0   | 4656  | 0.5630          | 0.7449    | 0.8770 | {'accuracy': 0.7139175257731959, 'f1': 0.8056042031523644} |
+| 0.5458        | 4.0   | 6208  | 0.5549          | 0.7544    | 0.8990 | {'accuracy': 0.7338917525773195, 'f1': 0.8203566768160069} |
+| 0.5342        | 5.0   | 7760  | 0.5816          | 0.7381    | 0.9457 | {'accuracy': 0.7364690721649485, 'f1': 0.8290848307563727} |
+| 0.5266        | 6.0   | 9312  | 0.5399          | 0.7705    | 0.8799 | {'accuracy': 0.7416237113402062, 'f1': 0.8215398308856252} |
+| 0.519         | 7.0   | 10864 | 0.5315          | 0.7932    | 0.8408 | {'accuracy': 0.7442010309278351, 'f1': 0.8162887552059231} |
+| 0.4878        | 8.0   | 12416 | 0.5318          | 0.7880    | 0.8541 | {'accuracy': 0.7461340206185567, 'f1': 0.8197621225983532} |
+| 0.485         | 9.0   | 13968 | 0.5332          | 0.7851    | 0.8637 | {'accuracy': 0.7480670103092784, 'f1': 0.8225147526100772} |
+| 0.5044        | 10.0  | 15520 | 0.5321          | 0.7883    | 0.8589 | {'accuracy': 0.7487113402061856, 'f1': 0.8220802919708029} |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.17.0
+- Tokenizers 0.15.2

adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "distilbert/distilbert-base-multilingual-cased",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.01,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 4,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_lin",
+    "v_lin",
+    "k_lin",
+    "out_lin",
+    "lin2",
+    "lin1"
+  ],
+  "task_type": "SEQ_CLS",
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54e84781204c5fb69a416622059c23e021f5667a6892d848c0bd67bda552e5bb
+size 3706232

runs/Feb16_19-51-35_3366cfa255a1/events.out.tfevents.1708113100.3366cfa255a1.407.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c622c57a6fb9a3cdc9a789c55aba117d80332302bc091a85504e0013c8163b82
+size 13402

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "add_prefix_space": true,
+  "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_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f140abab093cac587b8125ea4ad40a16d3d975ffea3facf1490395620ae32e5
+size 4664