Training in progress, step 100

.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 +1,81 @@
+---
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: vietcuna-3b_2048
+  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. -->
+
+# vietcuna-3b_2048
+
+This model was trained from scratch on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5250
+- Accuracy: 0.7375
+
+## 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: 5e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.18
+- training_steps: 1000
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.5694        | 1.05  | 50   | 0.5834          | 0.7087   |
+| 0.5614        | 2.1   | 100  | 0.5772          | 0.7165   |
+| 0.5475        | 3.15  | 150  | 0.5684          | 0.7165   |
+| 0.5503        | 4.2   | 200  | 0.5605          | 0.7087   |
+| 0.5305        | 5.25  | 250  | 0.5784          | 0.7192   |
+| 0.5353        | 6.3   | 300  | 0.5451          | 0.7323   |
+| 0.5063        | 7.35  | 350  | 0.5441          | 0.7270   |
+| 0.5141        | 8.4   | 400  | 0.5365          | 0.7244   |
+| 0.5035        | 9.45  | 450  | 0.5354          | 0.7297   |
+| 0.493         | 10.5  | 500  | 0.5322          | 0.7297   |
+| 0.4763        | 11.55 | 550  | 0.5299          | 0.7375   |
+| 0.5063        | 12.6  | 600  | 0.5295          | 0.7375   |
+| 0.4787        | 13.65 | 650  | 0.5280          | 0.7297   |
+| 0.4841        | 14.7  | 700  | 0.5266          | 0.7375   |
+| 0.4732        | 15.75 | 750  | 0.5283          | 0.7297   |
+| 0.4801        | 16.8  | 800  | 0.5259          | 0.7375   |
+| 0.4651        | 17.85 | 850  | 0.5256          | 0.7375   |
+| 0.4726        | 18.9  | 900  | 0.5260          | 0.7323   |
+| 0.4758        | 19.95 | 950  | 0.5248          | 0.7375   |
+| 0.4701        | 21.0  | 1000 | 0.5250          | 0.7375   |
+
+
+### Framework versions
+
+- Transformers 4.35.0.dev0
+- Pytorch 2.1.0+cu121
+- Datasets 2.14.6
+- Tokenizers 0.14.1

adapter_config.json

@@ -0,0 +1,22 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/kaggle/input/vietcuna-for-binary-classification/kalapa-vietcuna-3b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "query_key_value"
+  ],
+  "task_type": "SEQ_CLS"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7157a9425789f3dc6eebc4a187b8203f4cfc5f5fa089f3e105cc8e098b675c2
+size 9873829

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "sep_token": "[SEP]",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17a208233d2ee8d8c83b23bc214df737c44806a1919f444e89b31e586cd956ba
+size 14500471

tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "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": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "BloomTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:303b684398cbe6b39e16627081218289c5098690bdfd2926fac0c4c4b61ed03d
+size 4472