Curiousfox/mt5_tai-lo_to_chinese_LoRA_ver1.0.e

.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 +1,72 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: google/mt5-base
+tags:
+- base_model:adapter:google/mt5-base
+- lora
+- transformers
+model-index:
+- name: outputs
+  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. -->
+
+# outputs
+
+This model is a fine-tuned version of [google/mt5-base](https://huggingface.co/google/mt5-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 4.1438
+- Chrf: 0.3504
+
+## 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: 0.01
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 1
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 2000.0
+- training_steps: 20000
+
+### Training results
+
+| Training Loss | Epoch  | Step  | Validation Loss | Chrf   |
+|:-------------:|:------:|:-----:|:---------------:|:------:|
+| 6.5309        | 0.9337 | 2000  | 6.1412          | 0.0    |
+| 5.0243        | 1.8674 | 4000  | 4.7869          | 0.0    |
+| 5.8503        | 2.8011 | 6000  | 4.6079          | 0.0    |
+| 4.8561        | 3.7348 | 8000  | 5.4843          | 0.3906 |
+| 5.3422        | 4.6685 | 10000 | 4.6969          | 0.1913 |
+| 5.1278        | 5.6022 | 12000 | 4.5267          | 0.0638 |
+| 4.7362        | 6.5359 | 14000 | 4.4173          | 0.5746 |
+| 4.8027        | 7.4697 | 16000 | 4.2625          | 0.1913 |
+| 4.4404        | 8.4034 | 18000 | 4.1877          | 0.1276 |
+| 4.3010        | 9.3371 | 20000 | 4.1438          | 0.3504 |
+
+
+### Framework versions
+
+- PEFT 0.19.1
+- Transformers 5.0.0
+- Pytorch 2.10.0+cu128
+- Datasets 4.0.0
+- Tokenizers 0.22.2

adapter_config.json

@@ -0,0 +1,43 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/mt5-base",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q",
+    "v"
+  ],
+  "target_parameters": null,
+  "task_type": "SEQ_2_SEQ_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f43bb5c6c422c6a13cda8e30d4326f60b5cc647e173834c2e20a1b0ad3496648
+size 28331904

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ce3b8c7c21f06f06bc05213fc3c4e6778fecc43747508ce408b9ed1c9d875fd
+size 16013691

tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "backend": "tokenizers",
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "extra_special_tokens": [],
+  "is_local": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "T5Tokenizer",
+  "unk_id": 2,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd8dc6b2aeced2fc922ca26bea791b948d4673c9dec3b0ec502d2285daa203dc
+size 5393