banglaT5_dg_LoRA_8_32

README.md

@@ -0,0 +1,57 @@
+---
+base_model: csebuetnlp/banglat5
+tags:
+- generated_from_trainer
+datasets:
+- dailydialogue_bn
+model-index:
+- name: banglaT5_dg_LoRA_8_32
+ 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. -->
+
+# banglaT5_dg_LoRA_8_32
+
+This model is a fine-tuned version of [csebuetnlp/banglat5](https://huggingface.co/csebuetnlp/banglat5) on the dailydialogue_bn dataset.
+
+## 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: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3
+- label_smoothing_factor: 0.1
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.32.1
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.4
+- Tokenizers 0.13.3

adapter_config.json

@@ -0,0 +1,21 @@
+{
+ "auto_mapping": null,
+ "base_model_name_or_path": "csebuetnlp/banglat5",
+ "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,
+ "revision": null,
+ "target_modules": [
+ "q",
+ "v"
+ ],
+ "task_type": "SEQ_2_SEQ_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c6bc72258ba8fa58d2f361daf9370777de90519312d42632013970cd0588dd2
+size 3591693

special_tokens_map.json

@@ -0,0 +1,107 @@
+{
+ "additional_special_tokens": [
+ "<extra_id_0>",
+ "<extra_id_1>",
+ "<extra_id_2>",
+ "<extra_id_3>",
+ "<extra_id_4>",
+ "<extra_id_5>",
+ "<extra_id_6>",
+ "<extra_id_7>",
+ "<extra_id_8>",
+ "<extra_id_9>",
+ "<extra_id_10>",
+ "<extra_id_11>",
+ "<extra_id_12>",
+ "<extra_id_13>",
+ "<extra_id_14>",
+ "<extra_id_15>",
+ "<extra_id_16>",
+ "<extra_id_17>",
+ "<extra_id_18>",
+ "<extra_id_19>",
+ "<extra_id_20>",
+ "<extra_id_21>",
+ "<extra_id_22>",
+ "<extra_id_23>",
+ "<extra_id_24>",
+ "<extra_id_25>",
+ "<extra_id_26>",
+ "<extra_id_27>",
+ "<extra_id_28>",
+ "<extra_id_29>",
+ "<extra_id_30>",
+ "<extra_id_31>",
+ "<extra_id_32>",
+ "<extra_id_33>",
+ "<extra_id_34>",
+ "<extra_id_35>",
+ "<extra_id_36>",
+ "<extra_id_37>",
+ "<extra_id_38>",
+ "<extra_id_39>",
+ "<extra_id_40>",
+ "<extra_id_41>",
+ "<extra_id_42>",
+ "<extra_id_43>",
+ "<extra_id_44>",
+ "<extra_id_45>",
+ "<extra_id_46>",
+ "<extra_id_47>",
+ "<extra_id_48>",
+ "<extra_id_49>",
+ "<extra_id_50>",
+ "<extra_id_51>",
+ "<extra_id_52>",
+ "<extra_id_53>",
+ "<extra_id_54>",
+ "<extra_id_55>",
+ "<extra_id_56>",
+ "<extra_id_57>",
+ "<extra_id_58>",
+ "<extra_id_59>",
+ "<extra_id_60>",
+ "<extra_id_61>",
+ "<extra_id_62>",
+ "<extra_id_63>",
+ "<extra_id_64>",
+ "<extra_id_65>",
+ "<extra_id_66>",
+ "<extra_id_67>",
+ "<extra_id_68>",
+ "<extra_id_69>",
+ "<extra_id_70>",
+ "<extra_id_71>",
+ "<extra_id_72>",
+ "<extra_id_73>",
+ "<extra_id_74>",
+ "<extra_id_75>",
+ "<extra_id_76>",
+ "<extra_id_77>",
+ "<extra_id_78>",
+ "<extra_id_79>",
+ "<extra_id_80>",
+ "<extra_id_81>",
+ "<extra_id_82>",
+ "<extra_id_83>",
+ "<extra_id_84>",
+ "<extra_id_85>",
+ "<extra_id_86>",
+ "<extra_id_87>",
+ "<extra_id_88>",
+ "<extra_id_89>",
+ "<extra_id_90>",
+ "<extra_id_91>",
+ "<extra_id_92>",
+ "<extra_id_93>",
+ "<extra_id_94>",
+ "<extra_id_95>",
+ "<extra_id_96>",
+ "<extra_id_97>",
+ "<extra_id_98>",
+ "<extra_id_99>"
+ ],
+ "eos_token": "</s>",
+ "pad_token": "<pad>",
+ "unk_token": "<unk>"
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dcab96935a2a51b1461c84e44c952ea8a3640c8bc3e2c6ae7a21d855454ae27
+size 1111492

tokenizer_config.json

@@ -0,0 +1,113 @@
+{
+ "additional_special_tokens": [
+ "<extra_id_0>",
+ "<extra_id_1>",
+ "<extra_id_2>",
+ "<extra_id_3>",
+ "<extra_id_4>",
+ "<extra_id_5>",
+ "<extra_id_6>",
+ "<extra_id_7>",
+ "<extra_id_8>",
+ "<extra_id_9>",
+ "<extra_id_10>",
+ "<extra_id_11>",
+ "<extra_id_12>",
+ "<extra_id_13>",
+ "<extra_id_14>",
+ "<extra_id_15>",
+ "<extra_id_16>",
+ "<extra_id_17>",
+ "<extra_id_18>",
+ "<extra_id_19>",
+ "<extra_id_20>",
+ "<extra_id_21>",
+ "<extra_id_22>",
+ "<extra_id_23>",
+ "<extra_id_24>",
+ "<extra_id_25>",
+ "<extra_id_26>",
+ "<extra_id_27>",
+ "<extra_id_28>",
+ "<extra_id_29>",
+ "<extra_id_30>",
+ "<extra_id_31>",
+ "<extra_id_32>",
+ "<extra_id_33>",
+ "<extra_id_34>",
+ "<extra_id_35>",
+ "<extra_id_36>",
+ "<extra_id_37>",
+ "<extra_id_38>",
+ "<extra_id_39>",
+ "<extra_id_40>",
+ "<extra_id_41>",
+ "<extra_id_42>",
+ "<extra_id_43>",
+ "<extra_id_44>",
+ "<extra_id_45>",
+ "<extra_id_46>",
+ "<extra_id_47>",
+ "<extra_id_48>",
+ "<extra_id_49>",
+ "<extra_id_50>",
+ "<extra_id_51>",
+ "<extra_id_52>",
+ "<extra_id_53>",
+ "<extra_id_54>",
+ "<extra_id_55>",
+ "<extra_id_56>",
+ "<extra_id_57>",
+ "<extra_id_58>",
+ "<extra_id_59>",
+ "<extra_id_60>",
+ "<extra_id_61>",
+ "<extra_id_62>",
+ "<extra_id_63>",
+ "<extra_id_64>",
+ "<extra_id_65>",
+ "<extra_id_66>",
+ "<extra_id_67>",
+ "<extra_id_68>",
+ "<extra_id_69>",
+ "<extra_id_70>",
+ "<extra_id_71>",
+ "<extra_id_72>",
+ "<extra_id_73>",
+ "<extra_id_74>",
+ "<extra_id_75>",
+ "<extra_id_76>",
+ "<extra_id_77>",
+ "<extra_id_78>",
+ "<extra_id_79>",
+ "<extra_id_80>",
+ "<extra_id_81>",
+ "<extra_id_82>",
+ "<extra_id_83>",
+ "<extra_id_84>",
+ "<extra_id_85>",
+ "<extra_id_86>",
+ "<extra_id_87>",
+ "<extra_id_88>",
+ "<extra_id_89>",
+ "<extra_id_90>",
+ "<extra_id_91>",
+ "<extra_id_92>",
+ "<extra_id_93>",
+ "<extra_id_94>",
+ "<extra_id_95>",
+ "<extra_id_96>",
+ "<extra_id_97>",
+ "<extra_id_98>",
+ "<extra_id_99>"
+ ],
+ "clean_up_tokenization_spaces": true,
+ "eos_token": "</s>",
+ "extra_ids": 100,
+ "legacy": true,
+ "model_max_length": 512,
+ "pad_token": "<pad>",
+ "sp_model_kwargs": {},
+ "tokenizer_class": "T5Tokenizer",
+ "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3df9c7cf857f22d1808e4612f1d4b73843ec5023a92432bfe19c7922708d012
+size 4219