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 +1,85 @@
+---
+base_model: asadfgglie/mDeBERTa-v3-base-xnli-multilingual-zeroshot-v1.0
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: mDeBERTa-v3-base-xnli-multilingual-zeroshot-v1.1
+  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. -->
+
+# mDeBERTa-v3-base-xnli-multilingual-zeroshot-v1.1
+
+This model is a fine-tuned version of [asadfgglie/mDeBERTa-v3-base-xnli-multilingual-zeroshot-v1.0](https://huggingface.co/asadfgglie/mDeBERTa-v3-base-xnli-multilingual-zeroshot-v1.0) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5335
+- F1 Macro: 0.8675
+- F1 Micro: 0.8692
+- Accuracy Balanced: 0.8674
+- Accuracy: 0.8692
+- Precision Macro: 0.8677
+- Recall Macro: 0.8674
+- Precision Micro: 0.8692
+- Recall Micro: 0.8692
+
+## 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: 2e-05
+- train_batch_size: 16
+- eval_batch_size: 128
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.06
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1 Micro | Accuracy Balanced | Accuracy | Precision Macro | Recall Macro | Precision Micro | Recall Micro |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:-----------------:|:--------:|:---------------:|:------------:|:---------------:|:------------:|
+| 0.1975        | 0.17  | 200  | 0.3474          | 0.8688   | 0.8708   | 0.8678            | 0.8708   | 0.8701          | 0.8678       | 0.8708          | 0.8708       |
+| 0.1974        | 0.34  | 400  | 0.3580          | 0.8600   | 0.8624   | 0.8585            | 0.8624   | 0.8621          | 0.8585       | 0.8624          | 0.8624       |
+| 0.2054        | 0.51  | 600  | 0.3616          | 0.8520   | 0.8565   | 0.8476            | 0.8565   | 0.8638          | 0.8476       | 0.8565          | 0.8565       |
+| 0.2094        | 0.68  | 800  | 0.3772          | 0.8658   | 0.8687   | 0.8630            | 0.8687   | 0.8710          | 0.8630       | 0.8687          | 0.8687       |
+| 0.2118        | 0.85  | 1000 | 0.3701          | 0.8729   | 0.8740   | 0.8747            | 0.8740   | 0.8719          | 0.8747       | 0.8740          | 0.8740       |
+| 0.1948        | 1.02  | 1200 | 0.3778          | 0.8698   | 0.8714   | 0.8702            | 0.8714   | 0.8696          | 0.8702       | 0.8714          | 0.8714       |
+| 0.1447        | 1.19  | 1400 | 0.3964          | 0.8666   | 0.8692   | 0.8642            | 0.8692   | 0.8706          | 0.8642       | 0.8692          | 0.8692       |
+| 0.1723        | 1.35  | 1600 | 0.3855          | 0.8718   | 0.8735   | 0.8716            | 0.8735   | 0.8720          | 0.8716       | 0.8735          | 0.8735       |
+| 0.1476        | 1.52  | 1800 | 0.4164          | 0.8637   | 0.8661   | 0.8620            | 0.8661   | 0.8661          | 0.8620       | 0.8661          | 0.8661       |
+| 0.1515        | 1.69  | 2000 | 0.3958          | 0.8724   | 0.8740   | 0.8725            | 0.8740   | 0.8724          | 0.8725       | 0.8740          | 0.8740       |
+| 0.1378        | 1.86  | 2200 | 0.4390          | 0.8694   | 0.8708   | 0.8699            | 0.8708   | 0.8689          | 0.8699       | 0.8708          | 0.8708       |
+| 0.1332        | 2.03  | 2400 | 0.4535          | 0.8732   | 0.8745   | 0.8740            | 0.8745   | 0.8726          | 0.8740       | 0.8745          | 0.8745       |
+| 0.0913        | 2.2   | 2600 | 0.5235          | 0.8638   | 0.8661   | 0.8625            | 0.8661   | 0.8656          | 0.8625       | 0.8661          | 0.8661       |
+| 0.1076        | 2.37  | 2800 | 0.5339          | 0.8638   | 0.8661   | 0.8623            | 0.8661   | 0.8659          | 0.8623       | 0.8661          | 0.8661       |
+| 0.09          | 2.54  | 3000 | 0.5388          | 0.8670   | 0.8687   | 0.8667            | 0.8687   | 0.8672          | 0.8667       | 0.8687          | 0.8687       |
+| 0.0928        | 2.71  | 3200 | 0.5266          | 0.8649   | 0.8666   | 0.8648            | 0.8666   | 0.8650          | 0.8648       | 0.8666          | 0.8666       |
+| 0.0805        | 2.88  | 3400 | 0.5433          | 0.8658   | 0.8677   | 0.8654            | 0.8677   | 0.8663          | 0.8654       | 0.8677          | 0.8677       |
+
+
+### Framework versions
+
+- Transformers 4.33.3
+- Pytorch 2.5.1+cu121
+- Datasets 2.14.7
+- Tokenizers 0.13.3

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 250101
+}

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "asadfgglie/mDeBERTa-v3-base-xnli-multilingual-zeroshot-v1.0",
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "entailment",
+    "1": "not_entailment"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "entailment": 0,
+    "not_entailment": 1
+  },
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.3",
+  "type_vocab_size": 0,
+  "vocab_size": 251000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16db08d0e39fc2fe34a2a7ef946f1c86b936320411d8b9f7566a5c3ec1a60035
+size 1115313586

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13c8d666d62a7bc4ac8f040aab68e942c861f93303156cc28f5c7e885d86d6e3
+size 4305025

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e23095eb61ba944c7be3a5d3e8ec19e37ce7ced0daa03550bde03e83c21b3f8a
+size 16316151

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "stride": 0,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22a59860775aa152a9ca91abced8ee65a115d8862e7dc3a4dc12477411e3f6e7
+size 4728