Model trained and pushed to Hugging Face Hub

.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 +1,66 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: google/mt5-small
+tags:
+- base_model:adapter:google/mt5-small
+- lora
+- transformers
+model-index:
+- name: mt5-small-GEC-spanish-LORA-merged
+  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. -->
+
+# mt5-small-GEC-spanish-LORA-merged
+
+This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1014
+- Gleu: 0.7351
+
+## 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: 0.001635475313478006
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
+- optimizer: Use OptimizerNames.ADAMW_TORCH 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: 0.0993688388184371
+- num_epochs: 2
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Gleu   |
+|:-------------:|:-----:|:-----:|:---------------:|:------:|
+| 0.2319        | 1.0   | 11213 | 0.1196          | 0.7133 |
+| 0.1766        | 2.0   | 22426 | 0.1014          | 0.7351 |
+
+
+### Framework versions
+
+- PEFT 0.18.1
+- Transformers 5.0.0
+- Pytorch 2.7.0+cu126
+- Datasets 4.8.5
+- Tokenizers 0.22.2

adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/mt5-small",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.15,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k",
+    "v",
+    "wi_1",
+    "wo",
+    "q",
+    "o",
+    "wi_0"
+  ],
+  "target_parameters": null,
+  "task_type": "SEQ_2_SEQ_LM",
+  "trainable_token_indices": 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 sha256:63c9c4e3011286912075d835d85c2bcf3f0815132cc4fc790d744090967c0bee
+size 40935440

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b31adff76c33d263bf238da902695ba9b6223cb55e8195c580fe56d48077a2c5
+size 16032985

tokenizer_config.json

@@ -0,0 +1,115 @@
+{
+  "backend": "tokenizers",
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "extra_special_tokens": [
+    "<pad>",
+    "</s>",
+    "▁<extra_id_99>",
+    "▁<extra_id_98>",
+    "▁<extra_id_97>",
+    "▁<extra_id_96>",
+    "▁<extra_id_95>",
+    "▁<extra_id_94>",
+    "▁<extra_id_93>",
+    "▁<extra_id_92>",
+    "▁<extra_id_91>",
+    "▁<extra_id_90>",
+    "▁<extra_id_89>",
+    "▁<extra_id_88>",
+    "▁<extra_id_87>",
+    "▁<extra_id_86>",
+    "▁<extra_id_85>",
+    "▁<extra_id_84>",
+    "▁<extra_id_83>",
+    "▁<extra_id_82>",
+    "▁<extra_id_81>",
+    "▁<extra_id_80>",
+    "▁<extra_id_79>",
+    "▁<extra_id_78>",
+    "▁<extra_id_77>",
+    "▁<extra_id_76>",
+    "▁<extra_id_75>",
+    "▁<extra_id_74>",
+    "▁<extra_id_73>",
+    "▁<extra_id_72>",
+    "▁<extra_id_71>",
+    "▁<extra_id_70>",
+    "▁<extra_id_69>",
+    "▁<extra_id_68>",
+    "▁<extra_id_67>",
+    "▁<extra_id_66>",
+    "▁<extra_id_65>",
+    "▁<extra_id_64>",
+    "▁<extra_id_63>",
+    "▁<extra_id_62>",
+    "▁<extra_id_61>",
+    "▁<extra_id_60>",
+    "▁<extra_id_59>",
+    "▁<extra_id_58>",
+    "▁<extra_id_57>",
+    "▁<extra_id_56>",
+    "▁<extra_id_55>",
+    "▁<extra_id_54>",
+    "▁<extra_id_53>",
+    "▁<extra_id_52>",
+    "▁<extra_id_51>",
+    "▁<extra_id_50>",
+    "▁<extra_id_49>",
+    "▁<extra_id_48>",
+    "▁<extra_id_47>",
+    "▁<extra_id_46>",
+    "▁<extra_id_45>",
+    "▁<extra_id_44>",
+    "▁<extra_id_43>",
+    "▁<extra_id_42>",
+    "▁<extra_id_41>",
+    "▁<extra_id_40>",
+    "▁<extra_id_39>",
+    "▁<extra_id_38>",
+    "▁<extra_id_37>",
+    "▁<extra_id_36>",
+    "▁<extra_id_35>",
+    "▁<extra_id_34>",
+    "▁<extra_id_33>",
+    "▁<extra_id_32>",
+    "▁<extra_id_31>",
+    "▁<extra_id_30>",
+    "▁<extra_id_29>",
+    "▁<extra_id_28>",
+    "▁<extra_id_27>",
+    "▁<extra_id_26>",
+    "▁<extra_id_25>",
+    "▁<extra_id_24>",
+    "▁<extra_id_23>",
+    "▁<extra_id_22>",
+    "▁<extra_id_21>",
+    "▁<extra_id_20>",
+    "▁<extra_id_19>",
+    "▁<extra_id_18>",
+    "▁<extra_id_17>",
+    "▁<extra_id_16>",
+    "▁<extra_id_15>",
+    "▁<extra_id_14>",
+    "▁<extra_id_13>",
+    "▁<extra_id_12>",
+    "▁<extra_id_11>",
+    "▁<extra_id_10>",
+    "▁<extra_id_9>",
+    "▁<extra_id_8>",
+    "▁<extra_id_7>",
+    "▁<extra_id_6>",
+    "▁<extra_id_5>",
+    "▁<extra_id_4>",
+    "▁<extra_id_3>",
+    "▁<extra_id_2>",
+    "▁<extra_id_1>",
+    "▁<extra_id_0>"
+  ],
+  "is_local": true,
+  "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:c0dabca51e72114eaca81aeef4be9b4ef21431994010b6e32ac801b4e53b25ee
+size 5393