Model save

last-checkpoint/config.json

@@ -1,43 +0,0 @@
-{
-  "_name_or_path": "neuralmind/bert-large-portuguese-cased",
-  "architectures": [
-    "ToxicityTypeForSequenceClassification"
-  ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "directionality": "bidi",
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 1024,
-  "id2label": {
-    "0": "INDIVIDUAL",
-    "1": "GROUP",
-    "2": "OTHER"
-  },
-  "initializer_range": 0.02,
-  "intermediate_size": 4096,
-  "label2id": {
-    "GROUP": 1,
-    "INDIVIDUAL": 0,
-    "OTHER": 2
-  },
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 24,
-  "output_past": true,
-  "pad_token_id": 0,
-  "pooler_fc_size": 768,
-  "pooler_num_attention_heads": 12,
-  "pooler_num_fc_layers": 3,
-  "pooler_size_per_head": 128,
-  "pooler_type": "first_token_transform",
-  "position_embedding_type": "absolute",
-  "problem_type": "single_label_classification",
-  "torch_dtype": "float32",
-  "transformers_version": "4.26.1",
-  "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 29794
-}

last-checkpoint/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4468673744bceca94436b1b737ca547696e8bb37b757a5ecfa504c6996936a9d
-size 3468339

last-checkpoint/pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:33616d69562b4704c4c978a9bd8f4b84df973a32d5b273dc87a97cc8272cae5e
-size 1337733933

last-checkpoint/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1a8640d95accf7f62986182888680ab0d89f419f6d439632ad5915c94c02d4ca
-size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d70d9f841c5d130f597e74d073ac68b6b30d0cb12a026c5366cb226db3f56738
-size 623

last-checkpoint/special_tokens_map.json

@@ -1,7 +0,0 @@
-{
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
-}

last-checkpoint/tokenizer_config.json

@@ -1,16 +0,0 @@
-{
-  "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
-  "do_lower_case": false,
-  "mask_token": "[MASK]",
-  "model_max_length": 1000000000000000019884624838656,
-  "name_or_path": "neuralmind/bert-large-portuguese-cased",
-  "never_split": null,
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "special_tokens_map_file": "/root/.cache/huggingface/hub/models--neuralmind--bert-large-portuguese-cased/snapshots/aa302f6ea73b759f7df9cad58bd272127b67ec28/special_tokens_map.json",
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
-  "unk_token": "[UNK]"
-}

last-checkpoint/trainer_state.json

@@ -1,94 +0,0 @@
-{
-  "best_metric": 0.7986186145166447,
-  "best_model_checkpoint": "/opt/ml/checkpoints/toxicity-target-type-identification-2023-02-26-12-48-26-617/model/checkpoint-1065",
-  "epoch": 5.0,
-  "global_step": 1775,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 1.0,
-      "eval_accuracy": 0.6902748414376322,
-      "eval_f1": 0.7052333645117603,
-      "eval_loss": 0.7145297527313232,
-      "eval_precision": 0.7527983972979847,
-      "eval_recall": 0.6902748414376322,
-      "eval_runtime": 19.9276,
-      "eval_samples_per_second": 47.472,
-      "eval_steps_per_second": 5.972,
-      "step": 355
-    },
-    {
-      "epoch": 1.41,
-      "learning_rate": 3.766830354166815e-05,
-      "loss": 0.8011,
-      "step": 500
-    },
-    {
-      "epoch": 2.0,
-      "eval_accuracy": 0.7928118393234672,
-      "eval_f1": 0.7840254300809458,
-      "eval_loss": 0.9930071234703064,
-      "eval_precision": 0.783507252961592,
-      "eval_recall": 0.7928118393234672,
-      "eval_runtime": 20.1728,
-      "eval_samples_per_second": 46.895,
-      "eval_steps_per_second": 5.899,
-      "step": 710
-    },
-    {
-      "epoch": 2.82,
-      "learning_rate": 3.581272208641356e-05,
-      "loss": 0.529,
-      "step": 1000
-    },
-    {
-      "epoch": 3.0,
-      "eval_accuracy": 0.8002114164904862,
-      "eval_f1": 0.7986186145166447,
-      "eval_loss": 1.4281493425369263,
-      "eval_precision": 0.7989985820486601,
-      "eval_recall": 0.8002114164904862,
-      "eval_runtime": 17.0638,
-      "eval_samples_per_second": 55.439,
-      "eval_steps_per_second": 6.974,
-      "step": 1065
-    },
-    {
-      "epoch": 4.0,
-      "eval_accuracy": 0.7727272727272727,
-      "eval_f1": 0.7753471858137818,
-      "eval_loss": 1.678259015083313,
-      "eval_precision": 0.778801583678501,
-      "eval_recall": 0.7727272727272727,
-      "eval_runtime": 17.2821,
-      "eval_samples_per_second": 54.739,
-      "eval_steps_per_second": 6.886,
-      "step": 1420
-    },
-    {
-      "epoch": 4.23,
-      "learning_rate": 3.3957140631158974e-05,
-      "loss": 0.2706,
-      "step": 1500
-    },
-    {
-      "epoch": 5.0,
-      "eval_accuracy": 0.7727272727272727,
-      "eval_f1": 0.7682734112208002,
-      "eval_loss": 2.390378475189209,
-      "eval_precision": 0.7659798393766588,
-      "eval_recall": 0.7727272727272727,
-      "eval_runtime": 19.0454,
-      "eval_samples_per_second": 49.671,
-      "eval_steps_per_second": 6.248,
-      "step": 1775
-    }
-  ],
-  "max_steps": 10650,
-  "num_train_epochs": 30,
-  "total_flos": 2462684273097684.0,
-  "trial_name": null,
-  "trial_params": null
-}

last-checkpoint/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:80715c069b8d9da3c0faa5ea124e133952b534e9fb42fb0b2f263286fbeb0100
-size 3695

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33616d69562b4704c4c978a9bd8f4b84df973a32d5b273dc87a97cc8272cae5e
+oid sha256:00d6d270e0be9438d10946bd174ffb0092a7e98228bee8a10caef76a29751629
 size 1337733933