Upload 13 files

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

config.json

@@ -0,0 +1,43 @@
+{
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "OUTROS",
+    "1": "BIO"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "BIO": 1,
+    "OUTROS": 0
+  },
+  "layer_norm_eps": 1e-07,
+  "legacy": true,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.3",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10700b5450c383cc2ef651fe5e32a955050319a1b62eb6a0d5a2193ed492f8a8
+size 737719272

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:643443d882d0f6080357d9857b424735d58eec2550d13376a3f2ecbd48d7e638
+size 1475558394

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f275eaf89aea104b177803f419d489f5ae45869c6d78b55be22044ab060c0a8
+size 14244

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b30172cf14f5dbe00280d63e36224a9f28dc7a0e8b38a74ceb5eb284e84da363
+size 988

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:564aa5bddb69ef2f2fa759bfb6aeb43a02946eab76db988ec89c351de54e07b5
+size 1064

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
+  }
+}

spm.model

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

tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "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
+    }
+  },
+  "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"
+}

trainer_state.json

@@ -0,0 +1,103 @@
+{
+  "best_global_step": 3988,
+  "best_metric": 0.7874481941977501,
+  "best_model_checkpoint": "./deberta_bio_result/checkpoint-3988",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 3988,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.25075225677031093,
+      "grad_norm": 325735.625,
+      "learning_rate": 1.7497492477432297e-05,
+      "loss": 0.412,
+      "step": 500
+    },
+    {
+      "epoch": 0.5015045135406219,
+      "grad_norm": 167717.0,
+      "learning_rate": 1.498996990972919e-05,
+      "loss": 0.3617,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7522567703109327,
+      "grad_norm": 278521.625,
+      "learning_rate": 1.2482447342026078e-05,
+      "loss": 0.3601,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.843530591775326,
+      "eval_f1": 0.770546056260342,
+      "eval_loss": 0.3484754264354706,
+      "eval_runtime": 122.603,
+      "eval_samples_per_second": 130.111,
+      "eval_steps_per_second": 4.07,
+      "step": 1994
+    },
+    {
+      "epoch": 1.0030090270812437,
+      "grad_norm": 120681.1328125,
+      "learning_rate": 9.974924774322969e-06,
+      "loss": 0.3392,
+      "step": 2000
+    },
+    {
+      "epoch": 1.2537612838515546,
+      "grad_norm": 123770.0234375,
+      "learning_rate": 7.46740220661986e-06,
+      "loss": 0.3112,
+      "step": 2500
+    },
+    {
+      "epoch": 1.5045135406218657,
+      "grad_norm": 149896.875,
+      "learning_rate": 4.959879638916751e-06,
+      "loss": 0.3082,
+      "step": 3000
+    },
+    {
+      "epoch": 1.7552657973921764,
+      "grad_norm": 137855.703125,
+      "learning_rate": 2.452357071213641e-06,
+      "loss": 0.305,
+      "step": 3500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8649699097291875,
+      "eval_f1": 0.7874481941977501,
+      "eval_loss": 0.33768922090530396,
+      "eval_runtime": 122.6162,
+      "eval_samples_per_second": 130.097,
+      "eval_steps_per_second": 4.07,
+      "step": 3988
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3988,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "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": 8394050978503680.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeba8078adacb21580952d285fd373b4e173f331597df0c8348d8a8de41e0ab6
+size 5304