nhankins/zh_distilbert_lora_adapter_3.0

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: 0.4881
+- Precision: 0.7966
+- Recall: 0.9216
+- F1 and accuracy: {'accuracy': 0.7605985037406484, 'f1': 0.8545454545454545}
+
+## 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                                            |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:----------------------------------------------------------:|
+| No log        | 1.0   | 401  | 0.5429          | 0.7631    | 1.0    | {'accuracy': 0.7630922693266833, 'f1': 0.8656294200848657} |
+| 0.5808        | 2.0   | 802  | 0.5361          | 0.7631    | 1.0    | {'accuracy': 0.7630922693266833, 'f1': 0.8656294200848657} |
+| 0.5805        | 3.0   | 1203 | 0.5235          | 0.7631    | 1.0    | {'accuracy': 0.7630922693266833, 'f1': 0.8656294200848657} |
+| 0.5554        | 4.0   | 1604 | 0.5096          | 0.7669    | 1.0    | {'accuracy': 0.7680798004987531, 'f1': 0.8680851063829788} |
+| 0.5214        | 5.0   | 2005 | 0.5046          | 0.7734    | 0.9706 | {'accuracy': 0.7605985037406484, 'f1': 0.8608695652173913} |
+| 0.5214        | 6.0   | 2406 | 0.4971          | 0.7950    | 0.9379 | {'accuracy': 0.7680798004987531, 'f1': 0.8605697151424289} |
+| 0.5152        | 7.0   | 2807 | 0.4919          | 0.7983    | 0.9183 | {'accuracy': 0.7605985037406484, 'f1': 0.8541033434650457} |
+| 0.4956        | 8.0   | 3208 | 0.4881          | 0.8017    | 0.9118 | {'accuracy': 0.7605985037406484, 'f1': 0.8532110091743118} |
+| 0.4891        | 9.0   | 3609 | 0.4881          | 0.7972    | 0.9248 | {'accuracy': 0.7630922693266833, 'f1': 0.8562783661119516} |
+| 0.5038        | 10.0  | 4010 | 0.4881          | 0.7966    | 0.9216 | {'accuracy': 0.7605985037406484, 'f1': 0.8545454545454545} |
+
+
+### 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",
+    "out_lin",
+    "lin1",
+    "k_lin",
+    "v_lin",
+    "lin2"
+  ],
+  "task_type": "SEQ_CLS",
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:972c95eba13b916d51795df674130be111fbfb8bfd4f614cb5664b02010140fd
+size 3706232

runs/Feb15_20-29-50_dd85c6ed0450/events.out.tfevents.1708028994.dd85c6ed0450.636.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df3ce693d2cb4d4d7e9fd169bb60253eb1f6be2daff3e9fc4afe2adab7c33f69
+size 9791

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:e31c375ec35784bcc855eb19d00e3b1ef0e615e6a52fd03a341ed5543b029dc0
+size 4664