ftlora-mt5-base-on-opus100_en-ru

README.md

@@ -0,0 +1,74 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- generated_from_trainer
+datasets:
+- opus100
+base_model: google/mt5-base
+model-index:
+- name: ft-t5-small-on-opus100
+ 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. -->
+
+# ft-t5-small-on-opus100
+
+This model is a fine-tuned version of [google/mt5-base](https://huggingface.co/google/mt5-base) on the opus100 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: 32
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.37.2
+- Pytorch 2.0.1+cu117
+- Datasets 2.14.4
+- Tokenizers 0.15.1
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: QuantizationMethod.BITS_AND_BYTES
+- load_in_8bit: True
+- load_in_4bit: False
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+
+### Framework versions
+
+
+- PEFT 0.6.2.dev0

adapter_config.json

@@ -0,0 +1,24 @@
+{
+ "alpha_pattern": {},
+ "auto_mapping": null,
+ "base_model_name_or_path": "google/mt5-base",
+ "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": 0.01,
+ "modules_to_save": null,
+ "peft_type": "LORA",
+ "r": 8,
+ "rank_pattern": {},
+ "revision": null,
+ "target_modules": [
+ "v",
+ "q",
+ "k"
+ ],
+ "task_type": "SEQ_2_SEQ_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aed8fa77003a1fb51743256cc1ae241057c218902007be8d8e8e0cc55b4a092c
+size 5338352

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eba88fc3014925f4c95fae9291d11264857bf23f1adf5552225aa3837d72480e
+size 4411