update NER model

config.json

@@ -10,7 +10,8 @@
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 1024,
-  "id2label": {"0": "O",
+  "id2label": {
+     "0": "O",
      "1": "B-job",
      "10": "I-event",
      "11": "B-organization",
@@ -28,28 +29,31 @@
      "6": "B-location",
      "7": "B-time",
      "8": "I-time",
-     "9": "B-event"},
+     "9": "B-event"
+  },
   "initializer_range": 0.02,
   "intermediate_size": 4096,
-  "label2id": {"B-artwork": 17,
-     "B-event": 9,
-     "B-job": 1,
-     "B-location": 6,
-     "B-nationality": 3,
-     "B-organization": 11,
-     "B-person": 4,
-     "B-product": 15,
-     "B-time": 7,
-     "I-artwork": 18,
-     "I-event": 10,
-     "I-job": 2,
-     "I-location": 13,
-     "I-nationality": 14,
-     "I-organization": 12,
-     "I-person": 5,
-     "I-product": 16,
-     "I-time": 8,
-     "O": 0},
+  "label2id": {
+    "B-artwork": 17,
+    "B-event": 9,
+    "B-job": 1,
+    "B-location": 6,
+    "B-nationality": 3,
+    "B-organization": 11,
+    "B-person": 4,
+    "B-product": 15,
+    "B-time": 7,
+    "I-artwork": 18,
+    "I-event": 10,
+    "I-job": 2,
+    "I-location": 13,
+    "I-nationality": 14,
+    "I-organization": 12,
+    "I-person": 5,
+    "I-product": 16,
+    "I-time": 8,
+    "O": 0
+  },
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 514,
   "model_type": "xlm-roberta",
@@ -58,7 +62,7 @@
   "output_past": true,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
-  "transformers_version": "4.6.1",
+  "transformers_version": "4.8.0",
   "type_vocab_size": 1,
   "use_cache": true,
   "vocab_size": 250002

model_args.json

@@ -1 +0,0 @@
-{"adafactor_beta1": null, "adafactor_clip_threshold": 1.0, "adafactor_decay_rate": -0.8, "adafactor_eps": [1e-30, 0.001], "adafactor_relative_step": true, "adafactor_scale_parameter": true, "adafactor_warmup_init": true, "adam_epsilon": 1e-08, "best_model_dir": "outputs/best_model", "cache_dir": "cache_dir/", "config": {}, "cosine_schedule_num_cycles": 0.5, "custom_layer_parameters": [], "custom_parameter_groups": [], "dataloader_num_workers": 0, "do_lower_case": false, "dynamic_quantize": false, "early_stopping_consider_epochs": false, "early_stopping_delta": 0, "early_stopping_metric": "eval_loss", "early_stopping_metric_minimize": true, "early_stopping_patience": 3, "encoding": null, "eval_batch_size": 8, "evaluate_during_training": false, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 2000, "evaluate_during_training_verbose": false, "evaluate_each_epoch": true, "fp16": true, "gradient_accumulation_steps": 1, "learning_rate": 2e-05, "local_rank": -1, "logging_steps": 50, "manual_seed": null, "max_grad_norm": 1.0, "max_seq_length": 128, "model_name": "xlm-roberta-large", "model_type": "xlmroberta", "multiprocessing_chunksize": -1, "n_gpu": 1, "no_cache": false, "no_save": false, "not_saved_args": [], "num_train_epochs": 10, "optimizer": "AdamW", "output_dir": "outputs/", "overwrite_output_dir": true, "polynomial_decay_schedule_lr_end": 1e-07, "polynomial_decay_schedule_power": 1.0, "process_count": 1, "quantized_model": false, "reprocess_input_data": true, "save_best_model": true, "save_eval_checkpoints": true, "save_model_every_epoch": true, "save_optimizer_and_scheduler": true, "save_steps": 2000, "scheduler": "linear_schedule_with_warmup", "silent": false, "skip_special_tokens": true, "tensorboard_dir": null, "thread_count": null, "tokenizer_name": null, "tokenizer_type": null, "train_batch_size": 8, "train_custom_parameters_only": false, "use_cached_eval_features": false, "use_early_stopping": false, "use_hf_datasets": false, "use_multiprocessing": true, "use_multiprocessing_for_evaluation": true, "wandb_kwargs": {}, "wandb_project": null, "warmup_ratio": 0.06, "warmup_steps": 1117, "weight_decay": 0.001, "model_class": "NERModel", "classification_report": false, "labels_list": ["O", "B-job", "I-job", "B-nationality", "B-person", "I-person", "B-location", "B-time", "I-time", "B-event", "I-event", "B-organization", "I-organization", "I-location", "I-nationality", "B-product", "I-product", "B-artwork", "I-artwork"], "lazy_loading": false, "lazy_loading_start_line": 0, "onnx": false, "special_tokens_list": []}

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76682a554be0386f7d8aa099bb31a285431a884690cf6d1be262e999635ee640
-size 4471129517
+oid sha256:1e015e14ae96831cdbfb558d6ebbea70a4e11dbe45658522f6573cd82d893886
+size 4471110437

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a68116126f007df58b80d3d4241d94834e9f324cf42c64e18115b02b6704fb95
-size 2235613943
+oid sha256:b0573363cbd9a9ac418edc7f8416d8e0251fe5937a013a47455a4662891f6885
+size 2235604657

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d26bb06c30dde94f1eb2f74699c1b5cb62f3fb8d6051a2940fae5f1149470ce
+size 14503

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d867df0a42b652e7db484987d7db7a415b4fbf7a871dcba8ed42223e4d3da6f5
+oid sha256:710a6bdce18d3c7ce72067f04b21ab94ae75a2ee4d731088bcedf84c21aed99f
 size 623

tokenizer_config.json

@@ -1 +1 @@
-{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "xlm-roberta-large"}
+{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "xlm-roberta-large", "tokenizer_class": "XLMRobertaTokenizer"}

trainer_state.json

@@ -0,0 +1,178 @@
+{
+  "best_metric": 0.3130991458892822,
+  "best_model_checkpoint": "/gdrive/MyDrive/Marefa/Tebyan/models/huggingface/model-xlm-roberta-large/checkpoint-13000",
+  "epoch": 9.0,
+  "global_step": 58500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.8e-05,
+      "loss": 0.4403,
+      "step": 6500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.900120719929763,
+      "eval_f1": 0.7773765268189059,
+      "eval_loss": 0.3497047424316406,
+      "eval_precision": 0.7735151130839146,
+      "eval_recall": 0.7812766865926558,
+      "eval_runtime": 26.5811,
+      "eval_samples_per_second": 70.99,
+      "eval_steps_per_second": 35.514,
+      "step": 6500
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.307,
+      "step": 13000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.904587357330992,
+      "eval_f1": 0.7846807172066689,
+      "eval_loss": 0.3130991458892822,
+      "eval_precision": 0.7710179270554296,
+      "eval_recall": 0.798836464560205,
+      "eval_runtime": 26.8623,
+      "eval_samples_per_second": 70.247,
+      "eval_steps_per_second": 35.142,
+      "step": 13000
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 1.4e-05,
+      "loss": 0.2386,
+      "step": 19500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9074187884108867,
+      "eval_f1": 0.7895801055644548,
+      "eval_loss": 0.348012775182724,
+      "eval_precision": 0.7771517187903851,
+      "eval_recall": 0.8024124679760888,
+      "eval_runtime": 26.5101,
+      "eval_samples_per_second": 71.18,
+      "eval_steps_per_second": 35.609,
+      "step": 19500
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 1.2e-05,
+      "loss": 0.1883,
+      "step": 26000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9088235294117647,
+      "eval_f1": 0.7946725265301746,
+      "eval_loss": 0.3668019771575928,
+      "eval_precision": 0.7980086114101184,
+      "eval_recall": 0.791364218616567,
+      "eval_runtime": 26.9144,
+      "eval_samples_per_second": 70.111,
+      "eval_steps_per_second": 35.074,
+      "step": 26000
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 1e-05,
+      "loss": 0.1439,
+      "step": 32500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9110074626865672,
+      "eval_f1": 0.801425039215165,
+      "eval_loss": 0.40606749057769775,
+      "eval_precision": 0.7984319542300153,
+      "eval_recall": 0.8044406490179334,
+      "eval_runtime": 26.8012,
+      "eval_samples_per_second": 70.407,
+      "eval_steps_per_second": 35.222,
+      "step": 32500
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.1108,
+      "step": 39000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.9115561896400352,
+      "eval_f1": 0.8033741926980361,
+      "eval_loss": 0.46604597568511963,
+      "eval_precision": 0.7936871712068337,
+      "eval_recall": 0.8133005977796754,
+      "eval_runtime": 26.6526,
+      "eval_samples_per_second": 70.8,
+      "eval_steps_per_second": 35.419,
+      "step": 39000
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 6e-06,
+      "loss": 0.0825,
+      "step": 45500
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.9102502194907814,
+      "eval_f1": 0.8003274619061452,
+      "eval_loss": 0.5183274149894714,
+      "eval_precision": 0.7920652344362553,
+      "eval_recall": 0.8087638770281811,
+      "eval_runtime": 26.7116,
+      "eval_samples_per_second": 70.643,
+      "eval_steps_per_second": 35.34,
+      "step": 45500
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.0601,
+      "step": 52000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.9106014047410009,
+      "eval_f1": 0.8013862969874699,
+      "eval_loss": 0.5683603882789612,
+      "eval_precision": 0.800575263662512,
+      "eval_recall": 0.802198975234842,
+      "eval_runtime": 26.5594,
+      "eval_samples_per_second": 71.048,
+      "eval_steps_per_second": 35.543,
+      "step": 52000
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.0431,
+      "step": 58500
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.91078797190518,
+      "eval_f1": 0.8022889236230693,
+      "eval_loss": 0.6140836477279663,
+      "eval_precision": 0.7964862448056388,
+      "eval_recall": 0.8081767719897524,
+      "eval_runtime": 26.6356,
+      "eval_samples_per_second": 70.845,
+      "eval_steps_per_second": 35.441,
+      "step": 58500
+    }
+  ],
+  "max_steps": 65000,
+  "num_train_epochs": 10,
+  "total_flos": 2.5323970171833972e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38da682fc8f5b1a45d948e5165d753debd1ee21627415b23d05208ce7115c6d8
-size 3183
+oid sha256:40697fbddeb3ba1528744eacd0f68bb1e8189da159f4a5eee73059ce6209e591
+size 2735