NuNER_Zero_2025-02-17_12-11-11

BSC-NLP4BIA/chagas-ner/README.md

@@ -0,0 +1,64 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+model-index:
+- name: NuNER_Zero_2025-02-17_12-11-11
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# NuNER_Zero_2025-02-17_12-11-11
+
+This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 37.8851
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-06
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 16
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 4
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 30.303        | 0.6584 | 100  | 76.8218         |
+| 4.6085        | 1.3226 | 200  | 57.4994         |
+| 3.7912        | 1.9811 | 300  | 49.8785         |
+| 3.0424        | 2.6453 | 400  | 41.6180         |
+| 2.8036        | 3.3095 | 500  | 39.0891         |
+| 2.5307        | 3.9679 | 600  | 37.8851         |
+
+
+### Framework versions
+
+- Transformers 4.48.3
+- Pytorch 2.5.1+cu124
+- Datasets 3.3.0
+- Tokenizers 0.21.0

BSC-NLP4BIA/chagas-ner/added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "<<ENT>>": 128002,
+  "<<SEP>>": 128003,
+  "[FLERT]": 128001,
+  "[MASK]": 128000
+}

BSC-NLP4BIA/chagas-ner/checkpoint-604/added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "<<ENT>>": 128002,
+  "<<SEP>>": 128003,
+  "[FLERT]": 128001,
+  "[MASK]": 128000
+}

BSC-NLP4BIA/chagas-ner/checkpoint-604/gliner_config.json

@@ -0,0 +1,131 @@
+{
+  "class_token_index": 128002,
+  "dropout": 0.4,
+  "embed_ent_token": true,
+  "encoder_config": {
+    "_attn_implementation_autoset": false,
+    "_name_or_path": "microsoft/deberta-v3-large",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_probs_dropout_prob": 0.1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-07,
+    "legacy": true,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 512,
+    "max_relative_positions": -1,
+    "min_length": 0,
+    "model_type": "deberta-v2",
+    "no_repeat_ngram_size": 0,
+    "norm_rel_ebd": "layer_norm",
+    "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 24,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 0,
+    "pooler_dropout": 0,
+    "pooler_hidden_act": "gelu",
+    "pooler_hidden_size": 1024,
+    "pos_att_type": [
+      "p2c",
+      "c2p"
+    ],
+    "position_biased_input": false,
+    "position_buckets": 256,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "relative_attention": true,
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "share_att_key": true,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "type_vocab_size": 0,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "vocab_size": 128004
+  },
+  "ent_token": "<<ENT>>",
+  "eval_every": 2500,
+  "fine_tune": true,
+  "fuse_layers": false,
+  "gradient_accumulation_steps": 2,
+  "has_rnn": true,
+  "hidden_size": 768,
+  "labels_encoder": null,
+  "labels_encoder_config": null,
+  "log_dir": "logs",
+  "lr_encoder": "1e-5",
+  "lr_others": "5e-5",
+  "max_len": 384,
+  "max_neg_type_ratio": 1,
+  "max_types": 25,
+  "max_width": 1,
+  "model_name": "microsoft/deberta-v3-large",
+  "model_type": "gliner",
+  "name": "large",
+  "num_post_fusion_layers": 1,
+  "num_steps": 60000,
+  "post_fusion_schema": "",
+  "prev_path": "none",
+  "random_drop": true,
+  "root_dir": "ablation_backbone",
+  "sep_token": "<<SEP>>",
+  "shuffle_types": true,
+  "size_sup": -1,
+  "span_mode": "marker",
+  "subtoken_pooling": "first",
+  "train_batch_size": 4,
+  "train_data": "NuMinds_custom_data_mix.json",
+  "transformers_version": "4.48.3",
+  "vocab_size": 128004,
+  "warmup_ratio": 0.1,
+  "words_splitter_type": "whitespace"
+}

BSC-NLP4BIA/chagas-ner/checkpoint-604/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ebf9c88e34b1d1a0dd8696140ce7b3276fb9014de15e4f326e28d4644cfa64f
+size 3591324460

BSC-NLP4BIA/chagas-ner/checkpoint-604/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45c6fc56939820b78fda03d7dd5766055c6ca792e335743ef685564a446de6fb
+size 1795640934

BSC-NLP4BIA/chagas-ner/checkpoint-604/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f6fe7b680821a170330572b71670a5d386db44084f7c16f24d42279fadfecdc
+size 14244

BSC-NLP4BIA/chagas-ner/checkpoint-604/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e835f7f6bc97246ef77d213f5fc8d9d39c873b4d19ec47af4667388d9081ca4c
+size 1064

BSC-NLP4BIA/chagas-ner/checkpoint-604/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

BSC-NLP4BIA/chagas-ner/checkpoint-604/spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

BSC-NLP4BIA/chagas-ner/checkpoint-604/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dba35d5dbe252aeafc5330bb2c1dbccd1632c829ea62a142b4082179db3fd94
+size 8657331

BSC-NLP4BIA/chagas-ner/checkpoint-604/tokenizer_config.json

@@ -0,0 +1,83 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "[FLERT]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128002": {
+      "content": "<<ENT>>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128003": {
+      "content": "<<SEP>>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

BSC-NLP4BIA/chagas-ner/checkpoint-604/trainer_state.json

@@ -0,0 +1,123 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.994238683127572,
+  "eval_steps": 100,
+  "global_step": 604,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.6584362139917695,
+      "grad_norm": 317.5823974609375,
+      "learning_rate": 9.281767955801105e-06,
+      "loss": 30.303,
+      "step": 100
+    },
+    {
+      "epoch": 0.6584362139917695,
+      "eval_loss": 76.82180786132812,
+      "eval_runtime": 20.1289,
+      "eval_samples_per_second": 13.265,
+      "eval_steps_per_second": 6.657,
+      "step": 100
+    },
+    {
+      "epoch": 1.322633744855967,
+      "grad_norm": 779.8876342773438,
+      "learning_rate": 7.440147329650093e-06,
+      "loss": 4.6085,
+      "step": 200
+    },
+    {
+      "epoch": 1.322633744855967,
+      "eval_loss": 57.49937438964844,
+      "eval_runtime": 20.0303,
+      "eval_samples_per_second": 13.33,
+      "eval_steps_per_second": 6.69,
+      "step": 200
+    },
+    {
+      "epoch": 1.9810699588477365,
+      "grad_norm": 74.9585952758789,
+      "learning_rate": 5.59852670349908e-06,
+      "loss": 3.7912,
+      "step": 300
+    },
+    {
+      "epoch": 1.9810699588477365,
+      "eval_loss": 49.87845993041992,
+      "eval_runtime": 20.1122,
+      "eval_samples_per_second": 13.276,
+      "eval_steps_per_second": 6.663,
+      "step": 300
+    },
+    {
+      "epoch": 2.645267489711934,
+      "grad_norm": 734.7151489257812,
+      "learning_rate": 3.7569060773480665e-06,
+      "loss": 3.0424,
+      "step": 400
+    },
+    {
+      "epoch": 2.645267489711934,
+      "eval_loss": 41.61801528930664,
+      "eval_runtime": 20.2123,
+      "eval_samples_per_second": 13.21,
+      "eval_steps_per_second": 6.63,
+      "step": 400
+    },
+    {
+      "epoch": 3.309465020576132,
+      "grad_norm": 246.29994201660156,
+      "learning_rate": 1.9152854511970537e-06,
+      "loss": 2.8036,
+      "step": 500
+    },
+    {
+      "epoch": 3.309465020576132,
+      "eval_loss": 39.08913803100586,
+      "eval_runtime": 20.0366,
+      "eval_samples_per_second": 13.326,
+      "eval_steps_per_second": 6.688,
+      "step": 500
+    },
+    {
+      "epoch": 3.9679012345679014,
+      "grad_norm": 223.61874389648438,
+      "learning_rate": 7.366482504604052e-08,
+      "loss": 2.5307,
+      "step": 600
+    },
+    {
+      "epoch": 3.9679012345679014,
+      "eval_loss": 37.885135650634766,
+      "eval_runtime": 20.1417,
+      "eval_samples_per_second": 13.256,
+      "eval_steps_per_second": 6.653,
+      "step": 600
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 604,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 2500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

BSC-NLP4BIA/chagas-ner/gliner_config.json

@@ -0,0 +1,131 @@
+{
+  "class_token_index": 128002,
+  "dropout": 0.4,
+  "embed_ent_token": true,
+  "encoder_config": {
+    "_attn_implementation_autoset": false,
+    "_name_or_path": "microsoft/deberta-v3-large",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_probs_dropout_prob": 0.1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-07,
+    "legacy": true,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 512,
+    "max_relative_positions": -1,
+    "min_length": 0,
+    "model_type": "deberta-v2",
+    "no_repeat_ngram_size": 0,
+    "norm_rel_ebd": "layer_norm",
+    "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 24,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 0,
+    "pooler_dropout": 0,
+    "pooler_hidden_act": "gelu",
+    "pooler_hidden_size": 1024,
+    "pos_att_type": [
+      "p2c",
+      "c2p"
+    ],
+    "position_biased_input": false,
+    "position_buckets": 256,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "relative_attention": true,
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "share_att_key": true,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "type_vocab_size": 0,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "vocab_size": 128004
+  },
+  "ent_token": "<<ENT>>",
+  "eval_every": 2500,
+  "fine_tune": true,
+  "fuse_layers": false,
+  "gradient_accumulation_steps": 2,
+  "has_rnn": true,
+  "hidden_size": 768,
+  "labels_encoder": null,
+  "labels_encoder_config": null,
+  "log_dir": "logs",
+  "lr_encoder": "1e-5",
+  "lr_others": "5e-5",
+  "max_len": 384,
+  "max_neg_type_ratio": 1,
+  "max_types": 25,
+  "max_width": 1,
+  "model_name": "microsoft/deberta-v3-large",
+  "model_type": "gliner",
+  "name": "large",
+  "num_post_fusion_layers": 1,
+  "num_steps": 60000,
+  "post_fusion_schema": "",
+  "prev_path": "none",
+  "random_drop": true,
+  "root_dir": "ablation_backbone",
+  "sep_token": "<<SEP>>",
+  "shuffle_types": true,
+  "size_sup": -1,
+  "span_mode": "marker",
+  "subtoken_pooling": "first",
+  "train_batch_size": 4,
+  "train_data": "NuMinds_custom_data_mix.json",
+  "transformers_version": "4.48.3",
+  "vocab_size": 128004,
+  "warmup_ratio": 0.1,
+  "words_splitter_type": "whitespace"
+}

BSC-NLP4BIA/chagas-ner/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45c6fc56939820b78fda03d7dd5766055c6ca792e335743ef685564a446de6fb
+size 1795640934

BSC-NLP4BIA/chagas-ner/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

BSC-NLP4BIA/chagas-ner/spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

BSC-NLP4BIA/chagas-ner/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dba35d5dbe252aeafc5330bb2c1dbccd1632c829ea62a142b4082179db3fd94
+size 8657331

BSC-NLP4BIA/chagas-ner/tokenizer_config.json

@@ -0,0 +1,83 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "[FLERT]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128002": {
+      "content": "<<ENT>>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128003": {
+      "content": "<<SEP>>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}