Training in progress, epoch 1

.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

added_tokens.json

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

config.json

@@ -0,0 +1,45 @@
+{
+ "_name_or_path": "MoritzLaurer/mDeBERTa-v3-base-xnli-multilingual-nli-2mil7",
+ "architectures": [
+ "DebertaV2ForSequenceClassification"
+ ],
+ "attention_probs_dropout_prob": 0.1,
+ "hidden_act": "gelu",
+ "hidden_dropout_prob": 0.1,
+ "hidden_size": 768,
+ "id2label": {
+ "0": "Less than 2 years",
+ "1": "2 to 5 years",
+ "2": "More than 5 years"
+ },
+ "initializer_range": 0.02,
+ "intermediate_size": 3072,
+ "label2id": {
+ "2 to 5 years": 1,
+ "Less than 2 years": 0,
+ "More than 5 years": 2
+ },
+ "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": "4.37.2",
+ "type_vocab_size": 0,
+ "vocab_size": 251000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ebe5495eccb3dbd698696f034d1d8228835aeada5029c91c43e15de1fd7e999
+size 1115271284

runs/Feb20_23-00-16_f3165fd0986f/events.out.tfevents.1708470025.f3165fd0986f.478.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc5a236e778622d1b36877862e0e7d8151ffa0c7898f7cf82dd7526d29119ab8
+size 5246

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+ "bos_token": {
+ "content": "[CLS]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "cls_token": {
+ "content": "[CLS]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "[SEP]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "mask_token": {
+ "content": "[MASK]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "[PAD]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "sep_token": {
+ "content": "[SEP]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "unk_token": {
+ "content": "[UNK]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}

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:bcc8903874b133941b537f7db855c20b5b792986bb08b32868afd0a3d593a042
+size 16316402

tokenizer_config.json

@@ -0,0 +1,62 @@
+{
+ "added_tokens_decoder": {
+ "0": {
+ "content": "[PAD]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "1": {
+ "content": "[CLS]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "2": {
+ "content": "[SEP]",
+ "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
+ },
+ "250101": {
+ "content": "[MASK]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "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 sha256:20e6fd5e075d2afd04445214cd5b71b9b0200ae48a2e6b33284b4589be1e8acb
+size 4792