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 +1,68 @@
+---
+license: mit
+base_model: xlm-roberta-base
+tags:
+- generated_from_trainer
+model-index:
+- name: xlm-roberta-base-finetuned-Adapter-en-ar-mlm-0.15-large-29OCT
+  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. -->
+
+# xlm-roberta-base-finetuned-Adapter-en-ar-mlm-0.15-large-29OCT
+
+This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.2667
+- Model Preparation Time: 0.0044
+
+## 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: 0.0001
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- gradient_accumulation_steps: 32
+- total_train_batch_size: 128
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.05
+- num_epochs: 2
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Model Preparation Time |
+|:-------------:|:------:|:----:|:---------------:|:----------------------:|
+| 3.9064        | 0.2498 | 1000 | 3.2366          | 0.0044                 |
+| 3.0641        | 0.4995 | 2000 | 2.7403          | 0.0044                 |
+| 2.8162        | 0.7493 | 3000 | 2.5485          | 0.0044                 |
+| 2.7054        | 0.9990 | 4000 | 2.4384          | 0.0044                 |
+| 2.6108        | 1.2488 | 5000 | 2.3627          | 0.0044                 |
+| 2.5357        | 1.4985 | 6000 | 2.3141          | 0.0044                 |
+| 2.5089        | 1.7483 | 7000 | 2.2847          | 0.0044                 |
+| 2.4931        | 1.9980 | 8000 | 2.2667          | 0.0044                 |
+
+
+### Framework versions
+
+- Transformers 4.43.4
+- Pytorch 2.1.1+cu121
+- Datasets 3.0.2
+- Tokenizers 0.19.1

default/head_config.json

@@ -0,0 +1,19 @@
+{
+  "config": {
+    "activation_function": "gelu",
+    "bias": true,
+    "embedding_size": 768,
+    "head_type": "masked_lm",
+    "label2id": null,
+    "layer_norm": true,
+    "layers": 2,
+    "shift_labels": false,
+    "vocab_size": 250002
+  },
+  "hidden_size": 768,
+  "model_class": "XLMRobertaAdapterModel",
+  "model_name": "xlm-roberta-base",
+  "model_type": "xlm-roberta",
+  "name": "default",
+  "version": "adapters.1.0.0"
+}

default/pytorch_model_head.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33e5c04408c8c6e8687cf85f58d1f92461b84dca43b43f1195d30060a109a0a0
+size 771377398

lang_adapter/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "config": {
+    "adapter_residual_before_ln": false,
+    "cross_adapter": false,
+    "dropout": 0.0,
+    "factorized_phm_W": true,
+    "factorized_phm_rule": false,
+    "hypercomplex_nonlinearity": "glorot-uniform",
+    "init_weights": "bert",
+    "inv_adapter": null,
+    "inv_adapter_reduction_factor": null,
+    "is_parallel": false,
+    "learn_phm": true,
+    "leave_out": [],
+    "ln_after": false,
+    "ln_before": false,
+    "mh_adapter": false,
+    "non_linearity": "relu",
+    "original_ln_after": true,
+    "original_ln_before": true,
+    "output_adapter": true,
+    "phm_bias": true,
+    "phm_c_init": "normal",
+    "phm_dim": 4,
+    "phm_init_range": 0.0001,
+    "phm_layer": false,
+    "phm_rank": 1,
+    "reduction_factor": 2,
+    "residual_before_ln": true,
+    "scaling": 1.0,
+    "shared_W_phm": false,
+    "shared_phm_rule": true,
+    "use_gating": false
+  },
+  "config_id": "e15331acc3f0a5c0",
+  "hidden_size": 768,
+  "model_class": "XLMRobertaAdapterModel",
+  "model_name": "xlm-roberta-base",
+  "model_type": "xlm-roberta",
+  "name": "lang_adapter",
+  "version": "adapters.1.0.0"
+}

lang_adapter/pytorch_adapter.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94ac3b5b9eaa3f568e462ea5e6371a5f3e843035eafb751853be1b9a6004385e
+size 28384742

mlm_head/head_config.json

@@ -0,0 +1,19 @@
+{
+  "config": {
+    "activation_function": "gelu",
+    "bias": true,
+    "embedding_size": 768,
+    "head_type": "masked_lm",
+    "label2id": null,
+    "layer_norm": true,
+    "layers": 2,
+    "shift_labels": false,
+    "vocab_size": 250002
+  },
+  "hidden_size": 768,
+  "model_class": "XLMRobertaAdapterModel",
+  "model_name": "xlm-roberta-base",
+  "model_type": "xlm-roberta",
+  "name": "mlm_head",
+  "version": "adapters.1.0.0"
+}

mlm_head/pytorch_model_head.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc7897cb46dceba51346bf391090fb2ffb80dce0a2dd931cfb67d73494fa09af
+size 771377398

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

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 sha256:3a56def25aa40facc030ea8b0b87f3688e4b3c39eb8b45d5702b3a1300fe2a20
+size 17082734

tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "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": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c2e5d7dccdcc3d8662ab90cb5970a6621b976e0b841a268fcd08342942065bd
+size 5304