Model trained and pushed to Hugging Face Hub

.gitattributes

@@ -33,3 +33,5 @@ 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
+source.spm filter=lfs diff=lfs merge=lfs -text
+target.spm filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,68 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: Helsinki-NLP/opus-mt-es-en
+tags:
+- base_model:adapter:Helsinki-NLP/opus-mt-es-en
+- lora
+- transformers
+model-index:
+- name: opus-mt-es-en-GEC-spanish-LORA-cowsl2h
+  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. -->
+
+# opus-mt-es-en-GEC-spanish-LORA-cowsl2h
+
+This model is a fine-tuned version of [Helsinki-NLP/opus-mt-es-en](https://huggingface.co/Helsinki-NLP/opus-mt-es-en) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1722
+- Gleu: 0.3735
+
+## 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: 0.0013223040248761528
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 64
+- 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: 0.09857017609527079
+- num_epochs: 3
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Gleu   |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| No log        | 1.0   | 97   | 0.2185          | 0.3091 |
+| 9.8620        | 2.0   | 194  | 0.1818          | 0.3603 |
+| 1.6898        | 3.0   | 291  | 0.1722          | 0.3735 |
+
+
+### 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 +1,45 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Helsinki-NLP/opus-mt-es-en",
+  "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": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "fc1",
+    "v_proj",
+    "out_proj",
+    "q_proj",
+    "fc2"
+  ],
+  "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:afa13c862536f67747d3e0b88a8b8472f56654b249a28e368736d53fc98b41f4
+size 17327976

source.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e236ee6d866b635c0142114f8647f39831f9d92534aa2aad75c942f6a78ad0e3
+size 825924

target.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dd547c24816a335e7b0b2e63376a8f1b3cbfc671eda5ab808dd44fdadaa8791
+size 801636

tokenizer_config.json

@@ -0,0 +1,41 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "65000": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": null,
+  "backend": "custom",
+  "eos_token": "</s>",
+  "extra_special_tokens": [],
+  "is_local": true,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "separate_vocabs": false,
+  "source_lang": "spa",
+  "sp_model_kwargs": {},
+  "target_lang": "eng",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:029fe4d67eeb01f41180aa10880fbc747bbe73c0684149bc5609442033fa8523
+size 5393