End of training

.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 +1,108 @@
+---
+library_name: transformers
+language:
+- multilingual
+- bn
+- cs
+- de
+- en
+- et
+- fi
+- fr
+- gu
+- ha
+- hi
+- is
+- ja
+- kk
+- km
+- lt
+- lv
+- pl
+- ps
+- ru
+- ta
+- tr
+- uk
+- xh
+- zh
+- zu
+license: mit
+base_model: FacebookAI/xlm-roberta-large
+tags:
+- quality-estimation
+- regression
+- generated_from_trainer
+datasets:
+- ymoslem/wmt-da-human-evaluation
+model-index:
+- name: Quality Estimation for Machine Translation
+  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. -->
+
+# Quality Estimation for Machine Translation
+
+This model is a fine-tuned version of [FacebookAI/xlm-roberta-large](https://huggingface.co/FacebookAI/xlm-roberta-large) on the ymoslem/wmt-da-human-evaluation dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0752
+
+## 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: 8e-05
+- train_batch_size: 64
+- eval_batch_size: 64
+- seed: 42
+- 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
+- training_steps: 20000
+
+### Training results
+
+| Training Loss | Epoch  | Step  | Validation Loss |
+|:-------------:|:------:|:-----:|:---------------:|
+| 0.0743        | 0.0502 | 1000  | 0.0598          |
+| 0.0853        | 0.1004 | 2000  | 0.0745          |
+| 0.0829        | 0.1506 | 3000  | 0.0726          |
+| 0.0814        | 0.2008 | 4000  | 0.0872          |
+| 0.0805        | 0.2509 | 5000  | 0.0715          |
+| 0.0782        | 0.3011 | 6000  | 0.0819          |
+| 0.0789        | 0.3513 | 7000  | 0.0733          |
+| 0.0791        | 0.4015 | 8000  | 0.0748          |
+| 0.0787        | 0.4517 | 9000  | 0.0759          |
+| 0.0761        | 0.5019 | 10000 | 0.0725          |
+| 0.0746        | 0.5521 | 11000 | 0.0745          |
+| 0.0762        | 0.6023 | 12000 | 0.0750          |
+| 0.077         | 0.6524 | 13000 | 0.0725          |
+| 0.0777        | 0.7026 | 14000 | 0.0737          |
+| 0.0764        | 0.7528 | 15000 | 0.0745          |
+| 0.0781        | 0.8030 | 16000 | 0.0750          |
+| 0.0748        | 0.8532 | 17000 | 0.0765          |
+| 0.0768        | 0.9034 | 18000 | 0.0750          |
+| 0.0737        | 0.9536 | 19000 | 0.0759          |
+| 0.0769        | 1.0038 | 20000 | 0.0752          |
+
+
+### Framework versions
+
+- Transformers 4.48.0
+- Pytorch 2.4.1+cu124
+- Datasets 3.2.0
+- Tokenizers 0.21.0

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9da49ac3dcb9792b31b9db0a35236784033286db9f1c2b260c1cc438b2daf7e5
+oid sha256:44a87b998ab829ef31229168b09c3e1e0c7bc45bfe6bf51b7020c3eef731bd3e
 size 1119831426

runs/Jan15_05-51-13_ea48e459ea32/events.out.tfevents.1736920273.ea48e459ea32.1232.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ff16f0b2ddc255945ad9f237257e899559acc212001b9be5c8305c75cefa4a9
-size 53102
+oid sha256:8c7eb780b41b3311fc7a2e4bad91115061d6fcabdae3787eacca8d3bb95bedda
+size 53462

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ffb37461c391f096759f4a9bbbc329da0f36952f88bab061fcf84940c022e98
+size 17082999

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}