Upload 10 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

config.json

@@ -0,0 +1,54 @@
+{
+  "_name_or_path": "assets/facebookai_xlm_roberta_base_pretrain_20240825",
+  "architectures": [
+    "XLMRobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-EVT",
+    "2": "I-EVT",
+    "3": "B-LOC",
+    "4": "I-LOC",
+    "5": "B-ORG",
+    "6": "I-ORG",
+    "7": "B-PER",
+    "8": "I-PER",
+    "9": "B-PRD",
+    "10": "I-PRD"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-EVT": 1,
+    "B-LOC": 3,
+    "B-ORG": 5,
+    "B-PER": 7,
+    "B-PRD": 9,
+    "I-EVT": 2,
+    "I-LOC": 4,
+    "I-ORG": 6,
+    "I-PER": 8,
+    "I-PRD": 10,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

metrics.json

@@ -0,0 +1,62 @@
+{
+    "eval_loss": 0.02277005836367607,
+    "eval_f1": 0.7852199094697778,
+    "eval_recall": 0.8112753523547611,
+    "eval_accuracy": 0.9927801284665579,
+    "eval_precision": 0.7610698020868087,
+    "eval_classification_report": {
+        "EVT": {
+            "precision": 0.7716535433070866,
+            "recall": 0.7461928934010152,
+            "f1-score": 0.7587096774193549,
+            "support": 394
+        },
+        "LOC": {
+            "precision": 0.7782152230971129,
+            "recall": 0.8375706214689266,
+            "f1-score": 0.8068027210884353,
+            "support": 708
+        },
+        "ORG": {
+            "precision": 0.7717908082408875,
+            "recall": 0.795751633986928,
+            "f1-score": 0.7835880933226066,
+            "support": 612
+        },
+        "PER": {
+            "precision": 0.8608108108108108,
+            "recall": 0.8959212376933896,
+            "f1-score": 0.8780151619572709,
+            "support": 711
+        },
+        "PRD": {
+            "precision": 0.7205882352941176,
+            "recall": 0.7190775681341719,
+            "f1-score": 0.7198321091290661,
+            "support": 477
+        },
+        "micro avg": {
+            "precision": 0.7872909698996655,
+            "recall": 0.8111647139903515,
+            "f1-score": 0.7990495587236932,
+            "support": 2902
+        },
+        "macro avg": {
+            "precision": 0.7806117241500031,
+            "recall": 0.7989027909368863,
+            "f1-score": 0.7893895525833468,
+            "support": 2902
+        },
+        "weighted avg": {
+            "precision": 0.7867336055757932,
+            "recall": 0.8111647139903515,
+            "f1-score": 0.7985294792396477,
+            "support": 2902
+        }
+    },
+    "eval_runtime": 4.347,
+    "eval_samples_per_second": 282.035,
+    "eval_steps_per_second": 2.3,
+    "epoch": 7.884922749067661,
+    "train_loss": 0.0145
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:994e16bff10a124f70bdd4abf12ffe06b1e4500e167b255e8b366f212e2589de
+size 1109914790

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 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a56def25aa40facc030ea8b0b87f3688e4b3c39eb8b45d5702b3a1300fe2a20
+size 17082734

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8647bfd714d3e8ba8091d106f391128fe8eda962364ebb5c1921618f150989c1
+size 5112

training_args.json

@@ -0,0 +1,147 @@
+{
+    "output_dir": "output",
+    "overwrite_output_dir": false,
+    "do_train": false,
+    "do_eval": true,
+    "do_predict": false,
+    "eval_strategy": "steps",
+    "prediction_loss_only": false,
+    "per_device_train_batch_size": 32,
+    "per_device_eval_batch_size": 128,
+    "per_gpu_train_batch_size": null,
+    "per_gpu_eval_batch_size": null,
+    "gradient_accumulation_steps": 2,
+    "eval_accumulation_steps": null,
+    "eval_delay": 0,
+    "torch_empty_cache_steps": null,
+    "learning_rate": 2e-05,
+    "weight_decay": 0.01,
+    "adam_beta1": 0.9,
+    "adam_beta2": 0.999,
+    "adam_epsilon": 1e-08,
+    "max_grad_norm": 1.0,
+    "num_train_epochs": 24,
+    "max_steps": -1,
+    "lr_scheduler_type": "linear",
+    "lr_scheduler_kwargs": {},
+    "warmup_ratio": 0.1,
+    "warmup_steps": 0,
+    "log_level": "passive",
+    "log_level_replica": "warning",
+    "log_on_each_node": true,
+    "logging_dir": "logs",
+    "logging_strategy": "steps",
+    "logging_first_step": false,
+    "logging_steps": 20,
+    "logging_nan_inf_filter": true,
+    "save_strategy": "no",
+    "save_steps": 500,
+    "save_total_limit": null,
+    "save_safetensors": false,
+    "save_on_each_node": false,
+    "save_only_model": false,
+    "restore_callback_states_from_checkpoint": false,
+    "no_cuda": false,
+    "use_cpu": false,
+    "use_mps_device": false,
+    "seed": 42,
+    "data_seed": null,
+    "jit_mode_eval": false,
+    "use_ipex": false,
+    "bf16": true,
+    "fp16": false,
+    "fp16_opt_level": "O1",
+    "half_precision_backend": "auto",
+    "bf16_full_eval": true,
+    "fp16_full_eval": false,
+    "tf32": null,
+    "local_rank": 0,
+    "ddp_backend": null,
+    "tpu_num_cores": null,
+    "tpu_metrics_debug": false,
+    "debug": [],
+    "dataloader_drop_last": false,
+    "eval_steps": 200,
+    "dataloader_num_workers": 0,
+    "dataloader_prefetch_factor": null,
+    "past_index": -1,
+    "run_name": "output",
+    "disable_tqdm": false,
+    "remove_unused_columns": true,
+    "label_names": null,
+    "load_best_model_at_end": false,
+    "metric_for_best_model": null,
+    "greater_is_better": null,
+    "ignore_data_skip": false,
+    "fsdp": [],
+    "fsdp_min_num_params": 0,
+    "fsdp_config": {
+        "min_num_params": 0,
+        "xla": false,
+        "xla_fsdp_v2": false,
+        "xla_fsdp_grad_ckpt": false
+    },
+    "fsdp_transformer_layer_cls_to_wrap": null,
+    "accelerator_config": {
+        "split_batches": false,
+        "dispatch_batches": null,
+        "even_batches": true,
+        "use_seedable_sampler": true,
+        "non_blocking": false,
+        "gradient_accumulation_kwargs": null,
+        "use_configured_state": false
+    },
+    "deepspeed": null,
+    "label_smoothing_factor": 0.0,
+    "optim": "adamw_8bit",
+    "optim_args": null,
+    "adafactor": false,
+    "group_by_length": false,
+    "length_column_name": "length",
+    "report_to": [
+        "tensorboard",
+        "wandb"
+    ],
+    "ddp_find_unused_parameters": null,
+    "ddp_bucket_cap_mb": null,
+    "ddp_broadcast_buffers": null,
+    "dataloader_pin_memory": true,
+    "dataloader_persistent_workers": false,
+    "skip_memory_metrics": true,
+    "use_legacy_prediction_loop": false,
+    "push_to_hub": false,
+    "resume_from_checkpoint": null,
+    "hub_model_id": null,
+    "hub_strategy": "every_save",
+    "hub_token": null,
+    "hub_private_repo": false,
+    "hub_always_push": false,
+    "gradient_checkpointing": false,
+    "gradient_checkpointing_kwargs": null,
+    "include_inputs_for_metrics": false,
+    "eval_do_concat_batches": true,
+    "fp16_backend": "auto",
+    "evaluation_strategy": null,
+    "push_to_hub_model_id": null,
+    "push_to_hub_organization": null,
+    "push_to_hub_token": null,
+    "_n_gpu": 1,
+    "mp_parameters": "",
+    "auto_find_batch_size": false,
+    "full_determinism": false,
+    "torchdynamo": null,
+    "ray_scope": "last",
+    "ddp_timeout": 1800,
+    "torch_compile": false,
+    "torch_compile_backend": null,
+    "torch_compile_mode": null,
+    "dispatch_batches": null,
+    "split_batches": null,
+    "include_tokens_per_second": false,
+    "include_num_input_tokens_seen": false,
+    "neftune_noise_alpha": null,
+    "optim_target_modules": null,
+    "batch_eval_metrics": false,
+    "eval_on_start": false,
+    "eval_use_gather_object": false
+}