Upload 12 files

.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 +1,53 @@
+{
+  "_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": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6
+  },
+  "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 sha256:5f04940d191d5116d1cdb84fb958d626c7cb6fe3561cc4e4a2aa5ef8b7c7b6ea
+size 1115283588

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:685362a4e376c51d038de9536e01e7b5d486c3f469024975b5800d12f1d7d16a
+size 2230686277

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42cd100366657e056c44ccf9126d34c08c902f596b2532bee723c91bd3220fa0
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d157d941cae3d6318e2b951c2b5e3f17b9c66893c4c246690a1e90c216a8558f
+size 627

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:d23afdb8c4f3b1b079dfcc28ad7828b09c183043487667b6527d9f75c60c2a87
+size 16316247

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"
+}

trainer_state.json

@@ -0,0 +1,229 @@
+{
+  "best_metric": 1.9327729940414429,
+  "best_model_checkpoint": "./results/checkpoint-322",
+  "epoch": 14.0,
+  "eval_steps": 500,
+  "global_step": 4508,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.2501650165016502,
+      "eval_loss": 1.9327729940414429,
+      "eval_precision": 0.21039270770334143,
+      "eval_recall": 0.2501650165016502,
+      "eval_runtime": 105.6438,
+      "eval_samples_per_second": 86.044,
+      "eval_steps_per_second": 0.435,
+      "step": 322
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 9.689440993788821e-05,
+      "loss": 1.5264,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.342024202420242,
+      "eval_loss": 2.632329225540161,
+      "eval_precision": 0.35262421551132295,
+      "eval_recall": 0.342024202420242,
+      "eval_runtime": 103.0666,
+      "eval_samples_per_second": 88.195,
+      "eval_steps_per_second": 0.446,
+      "step": 644
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.3278327832783278,
+      "eval_loss": 2.9007134437561035,
+      "eval_precision": 0.34602885917564774,
+      "eval_recall": 0.3278327832783278,
+      "eval_runtime": 102.8287,
+      "eval_samples_per_second": 88.399,
+      "eval_steps_per_second": 0.447,
+      "step": 966
+    },
+    {
+      "epoch": 3.11,
+      "learning_rate": 9.37888198757764e-05,
+      "loss": 0.6172,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.3423542354235424,
+      "eval_loss": 3.5746607780456543,
+      "eval_precision": 0.3512951146039761,
+      "eval_recall": 0.3423542354235424,
+      "eval_runtime": 101.7857,
+      "eval_samples_per_second": 89.305,
+      "eval_steps_per_second": 0.452,
+      "step": 1288
+    },
+    {
+      "epoch": 4.66,
+      "learning_rate": 9.068322981366461e-05,
+      "loss": 0.227,
+      "step": 1500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.3298129812981298,
+      "eval_loss": 4.564810276031494,
+      "eval_precision": 0.3549699546948268,
+      "eval_recall": 0.3298129812981298,
+      "eval_runtime": 101.7692,
+      "eval_samples_per_second": 89.32,
+      "eval_steps_per_second": 0.452,
+      "step": 1610
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.3282728272827283,
+      "eval_loss": 4.280569553375244,
+      "eval_precision": 0.3536771477074885,
+      "eval_recall": 0.3282728272827283,
+      "eval_runtime": 103.0369,
+      "eval_samples_per_second": 88.221,
+      "eval_steps_per_second": 0.446,
+      "step": 1932
+    },
+    {
+      "epoch": 6.21,
+      "learning_rate": 8.757763975155279e-05,
+      "loss": 0.118,
+      "step": 2000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.3460946094609461,
+      "eval_loss": 4.623283386230469,
+      "eval_precision": 0.344094580634609,
+      "eval_recall": 0.3460946094609461,
+      "eval_runtime": 89.9963,
+      "eval_samples_per_second": 101.004,
+      "eval_steps_per_second": 0.511,
+      "step": 2254
+    },
+    {
+      "epoch": 7.76,
+      "learning_rate": 8.4472049689441e-05,
+      "loss": 0.0775,
+      "step": 2500
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.3316831683168317,
+      "eval_loss": 4.871355056762695,
+      "eval_precision": 0.3530027915318833,
+      "eval_recall": 0.3316831683168317,
+      "eval_runtime": 90.9139,
+      "eval_samples_per_second": 99.985,
+      "eval_steps_per_second": 0.506,
+      "step": 2576
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.34026402640264025,
+      "eval_loss": 4.957677364349365,
+      "eval_precision": 0.33301623037601086,
+      "eval_recall": 0.34026402640264025,
+      "eval_runtime": 100.8674,
+      "eval_samples_per_second": 90.118,
+      "eval_steps_per_second": 0.456,
+      "step": 2898
+    },
+    {
+      "epoch": 9.32,
+      "learning_rate": 8.136645962732919e-05,
+      "loss": 0.056,
+      "step": 3000
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.33641364136413643,
+      "eval_loss": 5.228715419769287,
+      "eval_precision": 0.35135134065339246,
+      "eval_recall": 0.33641364136413643,
+      "eval_runtime": 101.1595,
+      "eval_samples_per_second": 89.858,
+      "eval_steps_per_second": 0.455,
+      "step": 3220
+    },
+    {
+      "epoch": 10.87,
+      "learning_rate": 7.82608695652174e-05,
+      "loss": 0.0418,
+      "step": 3500
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.3397139713971397,
+      "eval_loss": 5.417286396026611,
+      "eval_precision": 0.36541577660239133,
+      "eval_recall": 0.3397139713971397,
+      "eval_runtime": 100.0336,
+      "eval_samples_per_second": 90.869,
+      "eval_steps_per_second": 0.46,
+      "step": 3542
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 0.3288228822882288,
+      "eval_loss": 4.508035659790039,
+      "eval_precision": 0.3497733496975655,
+      "eval_recall": 0.3288228822882288,
+      "eval_runtime": 98.9066,
+      "eval_samples_per_second": 91.905,
+      "eval_steps_per_second": 0.465,
+      "step": 3864
+    },
+    {
+      "epoch": 12.42,
+      "learning_rate": 7.515527950310559e-05,
+      "loss": 0.0329,
+      "step": 4000
+    },
+    {
+      "epoch": 13.0,
+      "eval_accuracy": 0.33575357535753575,
+      "eval_loss": 5.399806022644043,
+      "eval_precision": 0.343976788298361,
+      "eval_recall": 0.33575357535753575,
+      "eval_runtime": 99.618,
+      "eval_samples_per_second": 91.249,
+      "eval_steps_per_second": 0.462,
+      "step": 4186
+    },
+    {
+      "epoch": 13.98,
+      "learning_rate": 7.20496894409938e-05,
+      "loss": 0.0255,
+      "step": 4500
+    },
+    {
+      "epoch": 14.0,
+      "eval_accuracy": 0.3254125412541254,
+      "eval_loss": 5.722477436065674,
+      "eval_precision": 0.37649139562875183,
+      "eval_recall": 0.3254125412541254,
+      "eval_runtime": 99.1531,
+      "eval_samples_per_second": 91.676,
+      "eval_steps_per_second": 0.464,
+      "step": 4508
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 16100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 50,
+  "save_steps": 500,
+  "total_flos": 2.3718794212945306e+17,
+  "train_batch_size": 200,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f35fea5e11dbad436c7699a462c1e691e1e4febbcd0a9928bae78d01e30d4c5
+size 4283