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 +1,50 @@
+---
+base_model: asadfgglie/mDeBERTa-v3-base-xnli-multilingual-zeroshot-v1.0
+tags:
+- generated_from_trainer
+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.
+
+## 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: 45
+- 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
+
+### 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
+}

mDeBERTa-v3-base-xnli-multilingual-zeroshot-v1.0-nli-zh-tw-all_and_BanBan_2024-10-17-facial_expressions-nli-2024-12-02-21-22.md

@@ -0,0 +1,8 @@
+
+Model Card
+==========
+
+|Datasets|asadfgglie/nli-zh-tw-all/test|asadfgglie/BanBan_2024-10-17-facial_expressions-nli|eval_dataset|
+| :---: | :---: | :---: | :---: |
+|Accuracy|0.868|0.953|0.871|
+|Inference text/sec (RTX4060ti, batch=128)|126.0|829.0|125.0|

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ef44e26733ce31451dde75503209035db8b4f3bc5be63769fb2111797f52fb5
+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:ffe5b21c1b4f9b5174c8544f86659cc324f72593b8d5d5e1ee06e30e8488063c
+size 4728