Upload 15 files

added_tokens.json

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

config.json

@@ -0,0 +1,35 @@
+{
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "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-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "transformers_version": "4.57.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:535c472d25776fd934de97a7032f8210b718dbc92d353fb80ba301ac04a0c4df
+size 498612824

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6612d8b0060fcdf78cdf9ff40bf2cb9daf56679c80d1aa9aac8f470c10ae3bc6
+size 997348747

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0eb35c4d8c39e70c22734a402379479ad9d31c632fc4320d47496037717dc79
+size 14645

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87b9a23c9a78c365dbe3e2f26a1678dd2ef42d05fd488a4a1c14137deecb7cc1
+size 1383

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aded39731ecca94f7940c4b5428ebba35e6a017ee2d29c3c7f7483897eddf3ca
+size 1465

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

spm.model

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

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,159 @@
+{
+  "best_global_step": 7976,
+  "best_metric": 0.7853136155022947,
+  "best_model_checkpoint": "./deberta_bio_result/checkpoint-7976",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 7976,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.12537612838515547,
+      "grad_norm": 7.210555553436279,
+      "learning_rate": 1.874874623871615e-05,
+      "loss": 0.4265,
+      "step": 500
+    },
+    {
+      "epoch": 0.25075225677031093,
+      "grad_norm": 6.844402313232422,
+      "learning_rate": 1.7494984954864596e-05,
+      "loss": 0.3875,
+      "step": 1000
+    },
+    {
+      "epoch": 0.37612838515546637,
+      "grad_norm": 3.695915460586548,
+      "learning_rate": 1.624122367101304e-05,
+      "loss": 0.3651,
+      "step": 1500
+    },
+    {
+      "epoch": 0.5015045135406219,
+      "grad_norm": 10.602663040161133,
+      "learning_rate": 1.4987462387161487e-05,
+      "loss": 0.373,
+      "step": 2000
+    },
+    {
+      "epoch": 0.6268806419257773,
+      "grad_norm": 2.402719259262085,
+      "learning_rate": 1.3733701103309932e-05,
+      "loss": 0.3744,
+      "step": 2500
+    },
+    {
+      "epoch": 0.7522567703109327,
+      "grad_norm": 5.753551006317139,
+      "learning_rate": 1.2479939819458375e-05,
+      "loss": 0.3696,
+      "step": 3000
+    },
+    {
+      "epoch": 0.8776328986960883,
+      "grad_norm": 4.795076847076416,
+      "learning_rate": 1.1226178535606823e-05,
+      "loss": 0.3445,
+      "step": 3500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8630892678034102,
+      "eval_f1": 0.7817309614231461,
+      "eval_loss": 0.3573812246322632,
+      "eval_runtime": 30.8925,
+      "eval_samples_per_second": 516.371,
+      "eval_steps_per_second": 32.273,
+      "step": 3988
+    },
+    {
+      "epoch": 1.0030090270812437,
+      "grad_norm": 7.011142253875732,
+      "learning_rate": 9.972417251755266e-06,
+      "loss": 0.3543,
+      "step": 4000
+    },
+    {
+      "epoch": 1.1283851554663993,
+      "grad_norm": 3.9173672199249268,
+      "learning_rate": 8.718655967903712e-06,
+      "loss": 0.3149,
+      "step": 4500
+    },
+    {
+      "epoch": 1.2537612838515546,
+      "grad_norm": 3.875389814376831,
+      "learning_rate": 7.464894684052158e-06,
+      "loss": 0.321,
+      "step": 5000
+    },
+    {
+      "epoch": 1.3791374122367102,
+      "grad_norm": 5.462708473205566,
+      "learning_rate": 6.211133400200602e-06,
+      "loss": 0.3176,
+      "step": 5500
+    },
+    {
+      "epoch": 1.5045135406218657,
+      "grad_norm": 5.192739963531494,
+      "learning_rate": 4.957372116349047e-06,
+      "loss": 0.3111,
+      "step": 6000
+    },
+    {
+      "epoch": 1.629889669007021,
+      "grad_norm": 23.06952476501465,
+      "learning_rate": 3.703610832497493e-06,
+      "loss": 0.3156,
+      "step": 6500
+    },
+    {
+      "epoch": 1.7552657973921764,
+      "grad_norm": 5.229244232177734,
+      "learning_rate": 2.449849548645938e-06,
+      "loss": 0.3049,
+      "step": 7000
+    },
+    {
+      "epoch": 1.880641925777332,
+      "grad_norm": 7.030540466308594,
+      "learning_rate": 1.1960882647943831e-06,
+      "loss": 0.3164,
+      "step": 7500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8680416248746239,
+      "eval_f1": 0.7853136155022947,
+      "eval_loss": 0.36421605944633484,
+      "eval_runtime": 31.0404,
+      "eval_samples_per_second": 513.911,
+      "eval_steps_per_second": 32.119,
+      "step": 7976
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7976,
+  "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": 8393900443622400.0,
+  "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 sha256:30cee9201d06b92448b4964136406dca91f20f6c6e501529bc35006ac27561db
+size 5841