Upload 9 files

config.json

@@ -0,0 +1,52 @@
+{
+  "add_cross_attention": false,
+  "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-ADDRESS",
+    "1": "B-CITY",
+    "2": "B-LOC",
+    "3": "B-VERB",
+    "4": "I-ADDRESS",
+    "5": "I-CITY",
+    "6": "I-LOC",
+    "7": "I-VERB",
+    "8": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "label2id": {
+    "B-ADDRESS": 0,
+    "B-CITY": 1,
+    "B-LOC": 2,
+    "B-VERB": 3,
+    "I-ADDRESS": 4,
+    "I-CITY": 5,
+    "I-LOC": 6,
+    "I-VERB": 7,
+    "O": 8
+  },
+  "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",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.3.0",
+  "type_vocab_size": 1,
+  "use_cache": false,
+  "vocab_size": 50005
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32f09b85972ea9edffc0da314d503403cce5451d7fa1010634776b9ca758f891
+size 495473028

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa1d96b93dec4edf5c86dd8ce14351f077a692aa85e9f3872adf229d803f069b
+size 991059531

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49a621c22a605faed1dad3e8d9875601985b4f4860f90f857334b69cb8a97bfb
+size 14455

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b08f7c9ba5c511c1facdb7a11dbb826aa982554c16e441bdbd99c3b51d9063a3
+size 1465

tokenizer_config.json

@@ -0,0 +1,21 @@
+{
+  "backend": "tokenizers",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "is_local": false,
+  "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": "TokenizersBackend",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,391 @@
+{
+  "best_global_step": 96,
+  "best_metric": 0.23231297731399536,
+  "best_model_checkpoint": "/work/Ccp-HERMOD/output/checkpoint-96",
+  "epoch": 29.0,
+  "eval_steps": 500,
+  "global_step": 116,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8361204013377926,
+      "eval_f1": 0.004705882352941177,
+      "eval_loss": 0.7151198387145996,
+      "eval_precision": 1.0,
+      "eval_recall": 0.0023584905660377358,
+      "eval_runtime": 13.4495,
+      "eval_samples_per_second": 1.19,
+      "eval_steps_per_second": 0.074,
+      "step": 4
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8379784466740988,
+      "eval_f1": 0.02790697674418605,
+      "eval_loss": 0.5497016906738281,
+      "eval_precision": 1.0,
+      "eval_recall": 0.014150943396226415,
+      "eval_runtime": 13.2884,
+      "eval_samples_per_second": 1.204,
+      "eval_steps_per_second": 0.075,
+      "step": 8
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8963210702341137,
+      "eval_f1": 0.6404341926729987,
+      "eval_loss": 0.4771943986415863,
+      "eval_precision": 0.7539936102236422,
+      "eval_recall": 0.5566037735849056,
+      "eval_runtime": 13.3794,
+      "eval_samples_per_second": 1.196,
+      "eval_steps_per_second": 0.075,
+      "step": 12
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9000371609067261,
+      "eval_f1": 0.6586345381526104,
+      "eval_loss": 0.4278680682182312,
+      "eval_precision": 0.7616099071207431,
+      "eval_recall": 0.5801886792452831,
+      "eval_runtime": 13.2845,
+      "eval_samples_per_second": 1.204,
+      "eval_steps_per_second": 0.075,
+      "step": 16
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9004087699739873,
+      "eval_f1": 0.653950953678474,
+      "eval_loss": 0.37871769070625305,
+      "eval_precision": 0.7741935483870968,
+      "eval_recall": 0.5660377358490566,
+      "eval_runtime": 13.4787,
+      "eval_samples_per_second": 1.187,
+      "eval_steps_per_second": 0.074,
+      "step": 20
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.9000371609067261,
+      "eval_f1": 0.6521145975443383,
+      "eval_loss": 0.3332737684249878,
+      "eval_precision": 0.7734627831715211,
+      "eval_recall": 0.5636792452830188,
+      "eval_runtime": 13.303,
+      "eval_samples_per_second": 1.203,
+      "eval_steps_per_second": 0.075,
+      "step": 24
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.919732441471572,
+      "eval_f1": 0.7064676616915423,
+      "eval_loss": 0.29833075404167175,
+      "eval_precision": 0.7473684210526316,
+      "eval_recall": 0.6698113207547169,
+      "eval_runtime": 13.2964,
+      "eval_samples_per_second": 1.203,
+      "eval_steps_per_second": 0.075,
+      "step": 28
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.929022668153103,
+      "eval_f1": 0.7114716106604868,
+      "eval_loss": 0.2743655741214752,
+      "eval_precision": 0.6993166287015945,
+      "eval_recall": 0.7240566037735849,
+      "eval_runtime": 13.3825,
+      "eval_samples_per_second": 1.196,
+      "eval_steps_per_second": 0.075,
+      "step": 32
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.9256781865477518,
+      "eval_f1": 0.6946902654867256,
+      "eval_loss": 0.26543402671813965,
+      "eval_precision": 0.6541666666666667,
+      "eval_recall": 0.7405660377358491,
+      "eval_runtime": 13.2666,
+      "eval_samples_per_second": 1.206,
+      "eval_steps_per_second": 0.075,
+      "step": 36
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.9267930137495355,
+      "eval_f1": 0.6977777777777777,
+      "eval_loss": 0.2558903992176056,
+      "eval_precision": 0.6596638655462185,
+      "eval_recall": 0.7405660377358491,
+      "eval_runtime": 13.2905,
+      "eval_samples_per_second": 1.204,
+      "eval_steps_per_second": 0.075,
+      "step": 40
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.929022668153103,
+      "eval_f1": 0.7112597547380156,
+      "eval_loss": 0.25086769461631775,
+      "eval_precision": 0.6744186046511628,
+      "eval_recall": 0.7523584905660378,
+      "eval_runtime": 13.3975,
+      "eval_samples_per_second": 1.194,
+      "eval_steps_per_second": 0.075,
+      "step": 44
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 0.9271646228167967,
+      "eval_f1": 0.7041942604856511,
+      "eval_loss": 0.2514660656452179,
+      "eval_precision": 0.6618257261410788,
+      "eval_recall": 0.7523584905660378,
+      "eval_runtime": 13.4847,
+      "eval_samples_per_second": 1.187,
+      "eval_steps_per_second": 0.074,
+      "step": 48
+    },
+    {
+      "epoch": 13.0,
+      "eval_accuracy": 0.9264214046822743,
+      "eval_f1": 0.6977777777777777,
+      "eval_loss": 0.24668167531490326,
+      "eval_precision": 0.6596638655462185,
+      "eval_recall": 0.7405660377358491,
+      "eval_runtime": 13.3955,
+      "eval_samples_per_second": 1.194,
+      "eval_steps_per_second": 0.075,
+      "step": 52
+    },
+    {
+      "epoch": 14.0,
+      "eval_accuracy": 0.9256781865477518,
+      "eval_f1": 0.695364238410596,
+      "eval_loss": 0.24763518571853638,
+      "eval_precision": 0.6535269709543569,
+      "eval_recall": 0.7429245283018868,
+      "eval_runtime": 13.3935,
+      "eval_samples_per_second": 1.195,
+      "eval_steps_per_second": 0.075,
+      "step": 56
+    },
+    {
+      "epoch": 15.0,
+      "eval_accuracy": 0.9271646228167967,
+      "eval_f1": 0.6991150442477875,
+      "eval_loss": 0.24238130450248718,
+      "eval_precision": 0.6583333333333333,
+      "eval_recall": 0.7452830188679245,
+      "eval_runtime": 13.3707,
+      "eval_samples_per_second": 1.197,
+      "eval_steps_per_second": 0.075,
+      "step": 60
+    },
+    {
+      "epoch": 16.0,
+      "eval_accuracy": 0.927536231884058,
+      "eval_f1": 0.7021040974529346,
+      "eval_loss": 0.2429044097661972,
+      "eval_precision": 0.6617954070981211,
+      "eval_recall": 0.7476415094339622,
+      "eval_runtime": 13.4028,
+      "eval_samples_per_second": 1.194,
+      "eval_steps_per_second": 0.075,
+      "step": 64
+    },
+    {
+      "epoch": 17.0,
+      "eval_accuracy": 0.9282794500185805,
+      "eval_f1": 0.7065337763012183,
+      "eval_loss": 0.24402368068695068,
+      "eval_precision": 0.6659707724425887,
+      "eval_recall": 0.7523584905660378,
+      "eval_runtime": 13.3903,
+      "eval_samples_per_second": 1.195,
+      "eval_steps_per_second": 0.075,
+      "step": 68
+    },
+    {
+      "epoch": 18.0,
+      "eval_accuracy": 0.929022668153103,
+      "eval_f1": 0.7088888888888888,
+      "eval_loss": 0.23910246789455414,
+      "eval_precision": 0.6701680672268907,
+      "eval_recall": 0.7523584905660378,
+      "eval_runtime": 13.4843,
+      "eval_samples_per_second": 1.187,
+      "eval_steps_per_second": 0.074,
+      "step": 72
+    },
+    {
+      "epoch": 19.0,
+      "eval_accuracy": 0.9286510590858417,
+      "eval_f1": 0.7122381477398014,
+      "eval_loss": 0.23814627528190613,
+      "eval_precision": 0.6687370600414079,
+      "eval_recall": 0.7617924528301887,
+      "eval_runtime": 13.5199,
+      "eval_samples_per_second": 1.183,
+      "eval_steps_per_second": 0.074,
+      "step": 76
+    },
+    {
+      "epoch": 20.0,
+      "eval_accuracy": 0.9323671497584541,
+      "eval_f1": 0.7189249720044792,
+      "eval_loss": 0.23503288626670837,
+      "eval_precision": 0.6844349680170576,
+      "eval_recall": 0.7570754716981132,
+      "eval_runtime": 13.3797,
+      "eval_samples_per_second": 1.196,
+      "eval_steps_per_second": 0.075,
+      "step": 80
+    },
+    {
+      "epoch": 21.0,
+      "eval_accuracy": 0.9334819769602378,
+      "eval_f1": 0.7355555555555556,
+      "eval_loss": 0.2409704029560089,
+      "eval_precision": 0.6953781512605042,
+      "eval_recall": 0.7806603773584906,
+      "eval_runtime": 13.3361,
+      "eval_samples_per_second": 1.2,
+      "eval_steps_per_second": 0.075,
+      "step": 84
+    },
+    {
+      "epoch": 22.0,
+      "eval_accuracy": 0.9360832404310665,
+      "eval_f1": 0.7468785471055619,
+      "eval_loss": 0.23444412648677826,
+      "eval_precision": 0.7199124726477024,
+      "eval_recall": 0.7759433962264151,
+      "eval_runtime": 13.3693,
+      "eval_samples_per_second": 1.197,
+      "eval_steps_per_second": 0.075,
+      "step": 88
+    },
+    {
+      "epoch": 23.0,
+      "eval_accuracy": 0.936826458565589,
+      "eval_f1": 0.7545045045045046,
+      "eval_loss": 0.23746801912784576,
+      "eval_precision": 0.7219827586206896,
+      "eval_recall": 0.7900943396226415,
+      "eval_runtime": 13.2922,
+      "eval_samples_per_second": 1.204,
+      "eval_steps_per_second": 0.075,
+      "step": 92
+    },
+    {
+      "epoch": 24.0,
+      "eval_accuracy": 0.9360832404310665,
+      "eval_f1": 0.7550561797752808,
+      "eval_loss": 0.23231297731399536,
+      "eval_precision": 0.721030042918455,
+      "eval_recall": 0.7924528301886793,
+      "eval_runtime": 13.1678,
+      "eval_samples_per_second": 1.215,
+      "eval_steps_per_second": 0.076,
+      "step": 96
+    },
+    {
+      "epoch": 25.0,
+      "eval_accuracy": 0.9360832404310665,
+      "eval_f1": 0.753393665158371,
+      "eval_loss": 0.23396730422973633,
+      "eval_precision": 0.7239130434782609,
+      "eval_recall": 0.785377358490566,
+      "eval_runtime": 13.2825,
+      "eval_samples_per_second": 1.205,
+      "eval_steps_per_second": 0.075,
+      "step": 100
+    },
+    {
+      "epoch": 26.0,
+      "eval_accuracy": 0.9342251950947603,
+      "eval_f1": 0.7508379888268155,
+      "eval_loss": 0.2425457239151001,
+      "eval_precision": 0.7133757961783439,
+      "eval_recall": 0.7924528301886793,
+      "eval_runtime": 13.2954,
+      "eval_samples_per_second": 1.203,
+      "eval_steps_per_second": 0.075,
+      "step": 104
+    },
+    {
+      "epoch": 27.0,
+      "eval_accuracy": 0.936826458565589,
+      "eval_f1": 0.7582292849035186,
+      "eval_loss": 0.23761555552482605,
+      "eval_precision": 0.7308533916849015,
+      "eval_recall": 0.7877358490566038,
+      "eval_runtime": 13.271,
+      "eval_samples_per_second": 1.206,
+      "eval_steps_per_second": 0.075,
+      "step": 108
+    },
+    {
+      "epoch": 28.0,
+      "eval_accuracy": 0.9371980676328503,
+      "eval_f1": 0.7587768969422425,
+      "eval_loss": 0.23595334589481354,
+      "eval_precision": 0.7298474945533769,
+      "eval_recall": 0.7900943396226415,
+      "eval_runtime": 13.2785,
+      "eval_samples_per_second": 1.205,
+      "eval_steps_per_second": 0.075,
+      "step": 112
+    },
+    {
+      "epoch": 29.0,
+      "eval_accuracy": 0.936826458565589,
+      "eval_f1": 0.760942760942761,
+      "eval_loss": 0.237918421626091,
+      "eval_precision": 0.7259100642398287,
+      "eval_recall": 0.7995283018867925,
+      "eval_runtime": 13.2875,
+      "eval_samples_per_second": 1.204,
+      "eval_steps_per_second": 0.075,
+      "step": 116
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 200,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 50,
+  "save_steps": 1000000000,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 5
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 311391536163120.0,
+  "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 sha256:84ff8ca4618195917f03ff61265024f69e6fb8a4f9fd1409efd9f2b6a9445d5b
+size 5201