Upload 11 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

README.md

@@ -0,0 +1,54 @@
+---
+license: mit
+base_model: xlm-roberta-large
+tags:
+- generated_from_trainer
+model-index:
+- name: xlm-roberta-large-metaie
+  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-large-metaie
+
+This model is a fine-tuned version of [xlm-roberta-large](https://huggingface.co/xlm-roberta-large) on an unknown 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: 1e-05
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.0.0+cu117
+- Datasets 2.15.0
+- Tokenizers 0.15.0

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.15453521883514917,
+    "train_runtime": 3360.3852,
+    "train_samples": 112146,
+    "train_samples_per_second": 33.373,
+    "train_steps_per_second": 1.043
+}

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "xlm-roberta-large",
+  "architectures": [
+    "XLMRobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "finetuning_task": "ner",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "B",
+    "1": "I",
+    "2": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "B": 0,
+    "I": 1,
+    "O": 2
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61367b621964e152f4f367b65efed165dfb8d603d234f5d55844a3b2f6c1fa4e
+size 2235424156

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 sha256:9a4661b2cb6b8a1007906509fe18cbfbc03062a086102bf7b80cfedb80f16c37
+size 17082854

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>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.15453521883514917,
+    "train_runtime": 3360.3852,
+    "train_samples": 112146,
+    "train_samples_per_second": 33.373,
+    "train_steps_per_second": 1.043
+}

trainer_state.json

@@ -0,0 +1,70 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9998394949440907,
+  "eval_steps": 500,
+  "global_step": 3504,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.14,
+      "learning_rate": 8.573059360730594e-06,
+      "loss": 0.2664,
+      "step": 500
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 7.146118721461188e-06,
+      "loss": 0.1606,
+      "step": 1000
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 5.719178082191781e-06,
+      "loss": 0.1463,
+      "step": 1500
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 4.292237442922374e-06,
+      "loss": 0.1354,
+      "step": 2000
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 2.8652968036529682e-06,
+      "loss": 0.1274,
+      "step": 2500
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.4383561643835616e-06,
+      "loss": 0.1246,
+      "step": 3000
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.1415525114155251e-08,
+      "loss": 0.1213,
+      "step": 3500
+    },
+    {
+      "epoch": 1.0,
+      "step": 3504,
+      "total_flos": 1.7775025975647528e+16,
+      "train_loss": 0.15453521883514917,
+      "train_runtime": 3360.3852,
+      "train_samples_per_second": 33.373,
+      "train_steps_per_second": 1.043
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3504,
+  "num_train_epochs": 1,
+  "save_steps": 1000,
+  "total_flos": 1.7775025975647528e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:505266d1453f5cad54530d715725225467bc0ac6e083b94d50151dddedb48629
+size 4155