nhankins/en_distilbert_lora_adapter_2.0

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: 0.5714
+- Precision: 0.7417
+- Recall: 1.0
+- F1 and accuracy: {'accuracy': 0.7416879795396419, 'f1': 0.8516886930983847}
+
+## 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: 0.001
+- 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                                            |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:----------------------------------------------------------:|
+| No log        | 1.0   | 391  | 0.5780          | 0.7417    | 1.0    | {'accuracy': 0.7416879795396419, 'f1': 0.8516886930983847} |
+| 0.647         | 2.0   | 782  | 0.5748          | 0.7417    | 1.0    | {'accuracy': 0.7416879795396419, 'f1': 0.8516886930983847} |
+| 0.6216        | 3.0   | 1173 | 0.5713          | 0.7417    | 1.0    | {'accuracy': 0.7416879795396419, 'f1': 0.8516886930983847} |
+| 0.6201        | 4.0   | 1564 | 0.5726          | 0.7417    | 1.0    | {'accuracy': 0.7416879795396419, 'f1': 0.8516886930983847} |
+| 0.6201        | 5.0   | 1955 | 0.5765          | 0.7417    | 1.0    | {'accuracy': 0.7416879795396419, 'f1': 0.8516886930983847} |
+| 0.6199        | 6.0   | 2346 | 0.5756          | 0.7417    | 1.0    | {'accuracy': 0.7416879795396419, 'f1': 0.8516886930983847} |
+| 0.6365        | 7.0   | 2737 | 0.5827          | 0.7417    | 1.0    | {'accuracy': 0.7416879795396419, 'f1': 0.8516886930983847} |
+| 0.6165        | 8.0   | 3128 | 0.5715          | 0.7417    | 1.0    | {'accuracy': 0.7416879795396419, 'f1': 0.8516886930983847} |
+| 0.6185        | 9.0   | 3519 | 0.5715          | 0.7417    | 1.0    | {'accuracy': 0.7416879795396419, 'f1': 0.8516886930983847} |
+| 0.6185        | 10.0  | 3910 | 0.5714          | 0.7417    | 1.0    | {'accuracy': 0.7416879795396419, 'f1': 0.8516886930983847} |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.17.0
+- Tokenizers 0.15.1

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": [
+    "lin2",
+    "q_lin",
+    "v_lin",
+    "lin1",
+    "out_lin",
+    "k_lin"
+  ],
+  "task_type": "SEQ_CLS",
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddd58d9706ad0dbc1ddefe28de2aa8e3ae8eabd5911a9df605dc231c61be6ded
+size 3706232

runs/Feb13_15-36-32_e336aafcca9e/events.out.tfevents.1707838595.e336aafcca9e.153.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebc50844c268cf401ec944851375179b8cfb3e3bdcba342288c1311b10c60d36
+size 9634

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 sha256:49b2f1533cb8754bcec721d2c4046163ba166641b6b4198541b744e1c07beff8
+size 4664