Upload folder using huggingface_hub

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "distilbert-base-multilingual-cased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForTokenClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "O",
+    "1": "B-VF",
+    "2": "I-VF",
+    "3": "B-GF",
+    "4": "I-GF",
+    "5": "B-DF",
+    "6": "I-DF"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "B-DF": 5,
+    "B-GF": 3,
+    "B-VF": 1,
+    "I-DF": 6,
+    "I-GF": 4,
+    "I-VF": 2,
+    "O": 0
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
+  "vocab_size": 119547
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef9601060dd52a6400dcf3624e17b096e512481e371a9c22f63bd53c15a9cdaf
+size 538970204

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cb98afba1ae2e0d4a43db5147515206acb0fab19fdb0b55006c6f2415d7957b
+size 1077998394

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:013d13e4b269a8648da58d2f40bf48e004388ea0631771b8c8e588ab75375092
+size 13990

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67a0c5c299cf4cf4d2698b8536c2cc16b11a9f613f6883c3a39162f7c6bac6b5
+size 1064

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,172 @@
+{
+  "best_metric": 0.28888171911239624,
+  "best_model_checkpoint": "distilbert-base-multilingual-cased-ner/checkpoint-2514",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 6285,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.39777247414478917,
+      "grad_norm": 4.3097381591796875,
+      "learning_rate": 1.9204455051710422e-05,
+      "loss": 0.5264,
+      "step": 500
+    },
+    {
+      "epoch": 0.7955449482895783,
+      "grad_norm": 3.837048053741455,
+      "learning_rate": 1.8408910103420846e-05,
+      "loss": 0.3879,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.7860432834879172,
+      "eval_loss": 0.30707472562789917,
+      "eval_precision": 0.8233972240581626,
+      "eval_recall": 0.7519314340898117,
+      "eval_runtime": 10.8736,
+      "eval_samples_per_second": 200.578,
+      "eval_steps_per_second": 25.107,
+      "step": 1257
+    },
+    {
+      "epoch": 1.1933174224343674,
+      "grad_norm": 1.6951128244400024,
+      "learning_rate": 1.7613365155131266e-05,
+      "loss": 0.3353,
+      "step": 1500
+    },
+    {
+      "epoch": 1.5910898965791567,
+      "grad_norm": 1.5148378610610962,
+      "learning_rate": 1.681782020684169e-05,
+      "loss": 0.3168,
+      "step": 2000
+    },
+    {
+      "epoch": 1.988862370723946,
+      "grad_norm": 1.4144065380096436,
+      "learning_rate": 1.602227525855211e-05,
+      "loss": 0.3112,
+      "step": 2500
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.8054501337646985,
+      "eval_loss": 0.28888171911239624,
+      "eval_precision": 0.8310437796893054,
+      "eval_recall": 0.7813858039594399,
+      "eval_runtime": 4.8063,
+      "eval_samples_per_second": 453.778,
+      "eval_steps_per_second": 56.8,
+      "step": 2514
+    },
+    {
+      "epoch": 2.386634844868735,
+      "grad_norm": 1.5348472595214844,
+      "learning_rate": 1.5226730310262532e-05,
+      "loss": 0.2545,
+      "step": 3000
+    },
+    {
+      "epoch": 2.7844073190135243,
+      "grad_norm": 8.601534843444824,
+      "learning_rate": 1.4431185361972953e-05,
+      "loss": 0.2484,
+      "step": 3500
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1": 0.7892752918287936,
+      "eval_loss": 0.3192006051540375,
+      "eval_precision": 0.7950759431651151,
+      "eval_recall": 0.7835586673104781,
+      "eval_runtime": 4.7707,
+      "eval_samples_per_second": 457.169,
+      "eval_steps_per_second": 57.225,
+      "step": 3771
+    },
+    {
+      "epoch": 3.1821797931583133,
+      "grad_norm": 9.969681739807129,
+      "learning_rate": 1.3635640413683375e-05,
+      "loss": 0.2375,
+      "step": 4000
+    },
+    {
+      "epoch": 3.579952267303103,
+      "grad_norm": 1.7026457786560059,
+      "learning_rate": 1.2840095465393797e-05,
+      "loss": 0.2108,
+      "step": 4500
+    },
+    {
+      "epoch": 3.977724741447892,
+      "grad_norm": 3.7030036449432373,
+      "learning_rate": 1.2044550517104217e-05,
+      "loss": 0.2329,
+      "step": 5000
+    },
+    {
+      "epoch": 4.0,
+      "eval_f1": 0.7907032755298652,
+      "eval_loss": 0.36849531531333923,
+      "eval_precision": 0.7888034598750601,
+      "eval_recall": 0.7926122646064703,
+      "eval_runtime": 4.7505,
+      "eval_samples_per_second": 459.111,
+      "eval_steps_per_second": 57.468,
+      "step": 5028
+    },
+    {
+      "epoch": 4.375497215592681,
+      "grad_norm": 17.24141502380371,
+      "learning_rate": 1.1249005568814639e-05,
+      "loss": 0.1891,
+      "step": 5500
+    },
+    {
+      "epoch": 4.77326968973747,
+      "grad_norm": 4.236565113067627,
+      "learning_rate": 1.045346062052506e-05,
+      "loss": 0.1984,
+      "step": 6000
+    },
+    {
+      "epoch": 5.0,
+      "eval_f1": 0.812455003599712,
+      "eval_loss": 0.329479843378067,
+      "eval_precision": 0.8076097328244275,
+      "eval_recall": 0.8173587638821825,
+      "eval_runtime": 4.767,
+      "eval_samples_per_second": 457.525,
+      "eval_steps_per_second": 57.269,
+      "step": 6285
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 12570,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 787320405665112.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b17ea1d8eafad445d4a3475affbe2eaa7de7d090d8ff5f961570954dc86651cc
+size 5368