Upload folder using huggingface_hub

config.json

@@ -0,0 +1,37 @@
+{
+  "architectures": [
+    "XLMRobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": null,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "B-VERB",
+    "1": "I-VERB",
+    "2": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-VERB": 0,
+    "I-VERB": 1,
+    "O": 2
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.57.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50005
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:218868106a2db310958c6031e604b8c7eb39ff84319d865bb0e8cb5c4852226f
+size 495454596

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd09f4cb15d04f8e663d6e3a6a99173c2ed6c61abc1580dd9f3c9ad50596532d
+size 991030987

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a76586e3c035c089288cb015405246039b9e378016d628d5ab471f02a25bca3c
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52fe70ca94033e763509bb675342e685c13723821b1a90b39d898dd16b006fca
+size 1465

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "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
+  }
+}

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": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "stride": 256,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,262 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 20.0,
+  "eval_steps": 500,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8790855509912484,
+      "eval_f1": 0.0,
+      "eval_loss": 0.3699088394641876,
+      "eval_precision": 0.0,
+      "eval_recall": 0.0,
+      "eval_runtime": 0.8212,
+      "eval_samples_per_second": 73.061,
+      "eval_steps_per_second": 4.871,
+      "step": 15
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9203429183782819,
+      "eval_f1": 0.5233441910966341,
+      "eval_loss": 0.22088216245174408,
+      "eval_precision": 0.9563492063492064,
+      "eval_recall": 0.3602391629297459,
+      "eval_runtime": 0.7344,
+      "eval_samples_per_second": 81.702,
+      "eval_steps_per_second": 5.447,
+      "step": 30
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.980532237899625,
+      "eval_f1": 0.9270386266094419,
+      "eval_loss": 0.09267979115247726,
+      "eval_precision": 0.8888888888888888,
+      "eval_recall": 0.968609865470852,
+      "eval_runtime": 0.7392,
+      "eval_samples_per_second": 81.165,
+      "eval_steps_per_second": 5.411,
+      "step": 45
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9867833541703875,
+      "eval_f1": 0.9512727272727274,
+      "eval_loss": 0.062456704676151276,
+      "eval_precision": 0.9263456090651558,
+      "eval_recall": 0.9775784753363229,
+      "eval_runtime": 0.7363,
+      "eval_samples_per_second": 81.49,
+      "eval_steps_per_second": 5.433,
+      "step": 60
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9878549741025183,
+      "eval_f1": 0.9555717407137655,
+      "eval_loss": 0.057645417749881744,
+      "eval_precision": 0.9318181818181818,
+      "eval_recall": 0.9805680119581465,
+      "eval_runtime": 0.7382,
+      "eval_samples_per_second": 81.278,
+      "eval_steps_per_second": 5.419,
+      "step": 75
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.9887479907126272,
+      "eval_f1": 0.9591240875912408,
+      "eval_loss": 0.055171798914670944,
+      "eval_precision": 0.9372325249643366,
+      "eval_recall": 0.9820627802690582,
+      "eval_runtime": 0.737,
+      "eval_samples_per_second": 81.415,
+      "eval_steps_per_second": 5.428,
+      "step": 90
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.9887479907126272,
+      "eval_f1": 0.9591836734693878,
+      "eval_loss": 0.05424182116985321,
+      "eval_precision": 0.9359886201991465,
+      "eval_recall": 0.9835575485799701,
+      "eval_runtime": 0.7417,
+      "eval_samples_per_second": 80.901,
+      "eval_steps_per_second": 5.393,
+      "step": 105
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.9887479907126272,
+      "eval_f1": 0.9591240875912408,
+      "eval_loss": 0.053577546030282974,
+      "eval_precision": 0.9372325249643366,
+      "eval_recall": 0.9820627802690582,
+      "eval_runtime": 0.7435,
+      "eval_samples_per_second": 80.704,
+      "eval_steps_per_second": 5.38,
+      "step": 120
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.9885693873906055,
+      "eval_f1": 0.9583028529626921,
+      "eval_loss": 0.05330846458673477,
+      "eval_precision": 0.9383954154727794,
+      "eval_recall": 0.9790732436472347,
+      "eval_runtime": 0.743,
+      "eval_samples_per_second": 80.754,
+      "eval_steps_per_second": 5.384,
+      "step": 135
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.9885693873906055,
+      "eval_f1": 0.9584245076586433,
+      "eval_loss": 0.053431008011102676,
+      "eval_precision": 0.9358974358974359,
+      "eval_recall": 0.9820627802690582,
+      "eval_runtime": 0.7473,
+      "eval_samples_per_second": 80.292,
+      "eval_steps_per_second": 5.353,
+      "step": 150
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.9887479907126272,
+      "eval_f1": 0.9591240875912408,
+      "eval_loss": 0.052123092114925385,
+      "eval_precision": 0.9372325249643366,
+      "eval_recall": 0.9820627802690582,
+      "eval_runtime": 0.749,
+      "eval_samples_per_second": 80.104,
+      "eval_steps_per_second": 5.34,
+      "step": 165
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 0.9878549741025183,
+      "eval_f1": 0.9558291093410572,
+      "eval_loss": 0.05669364705681801,
+      "eval_precision": 0.9269662921348315,
+      "eval_recall": 0.9865470852017937,
+      "eval_runtime": 0.7512,
+      "eval_samples_per_second": 79.872,
+      "eval_steps_per_second": 5.325,
+      "step": 180
+    },
+    {
+      "epoch": 13.0,
+      "eval_accuracy": 0.9891051973566708,
+      "eval_f1": 0.9607558139534883,
+      "eval_loss": 0.05342329666018486,
+      "eval_precision": 0.9349363507779349,
+      "eval_recall": 0.9880418535127056,
+      "eval_runtime": 0.7576,
+      "eval_samples_per_second": 79.201,
+      "eval_steps_per_second": 5.28,
+      "step": 195
+    },
+    {
+      "epoch": 14.0,
+      "eval_accuracy": 0.9891051973566708,
+      "eval_f1": 0.9606986899563319,
+      "eval_loss": 0.05193372443318367,
+      "eval_precision": 0.9361702127659575,
+      "eval_recall": 0.9865470852017937,
+      "eval_runtime": 0.7617,
+      "eval_samples_per_second": 78.776,
+      "eval_steps_per_second": 5.252,
+      "step": 210
+    },
+    {
+      "epoch": 15.0,
+      "eval_accuracy": 0.988926594034649,
+      "eval_f1": 0.9599999999999999,
+      "eval_loss": 0.05363447591662407,
+      "eval_precision": 0.9348441926345609,
+      "eval_recall": 0.9865470852017937,
+      "eval_runtime": 0.7588,
+      "eval_samples_per_second": 79.077,
+      "eval_steps_per_second": 5.272,
+      "step": 225
+    },
+    {
+      "epoch": 16.0,
+      "eval_accuracy": 0.9891051973566708,
+      "eval_f1": 0.9606986899563319,
+      "eval_loss": 0.052914559841156006,
+      "eval_precision": 0.9361702127659575,
+      "eval_recall": 0.9865470852017937,
+      "eval_runtime": 0.7601,
+      "eval_samples_per_second": 78.937,
+      "eval_steps_per_second": 5.262,
+      "step": 240
+    },
+    {
+      "epoch": 17.0,
+      "eval_accuracy": 0.9891051973566708,
+      "eval_f1": 0.9606986899563319,
+      "eval_loss": 0.05266627296805382,
+      "eval_precision": 0.9361702127659575,
+      "eval_recall": 0.9865470852017937,
+      "eval_runtime": 0.7603,
+      "eval_samples_per_second": 78.916,
+      "eval_steps_per_second": 5.261,
+      "step": 255
+    },
+    {
+      "epoch": 18.0,
+      "eval_accuracy": 0.9891051973566708,
+      "eval_f1": 0.9606986899563319,
+      "eval_loss": 0.05201728269457817,
+      "eval_precision": 0.9361702127659575,
+      "eval_recall": 0.9865470852017937,
+      "eval_runtime": 0.7584,
+      "eval_samples_per_second": 79.114,
+      "eval_steps_per_second": 5.274,
+      "step": 270
+    },
+    {
+      "epoch": 19.0,
+      "eval_accuracy": 0.9891051973566708,
+      "eval_f1": 0.9606413994169095,
+      "eval_loss": 0.05047819763422012,
+      "eval_precision": 0.9374110953058321,
+      "eval_recall": 0.9850523168908819,
+      "eval_runtime": 0.761,
+      "eval_samples_per_second": 78.846,
+      "eval_steps_per_second": 5.256,
+      "step": 285
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 300,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1254235771699200.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e1e80dcf5665ae2cc5297ddef197382412f811a7ed083d63abc7044121f1b3c
+size 5905