Model save

last-checkpoint/config.json

@@ -1,40 +0,0 @@
-{
-  "_name_or_path": "neuralmind/bert-base-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": 768,
-  "id2label": {
-    "0": "UNTARGETED",
-    "1": "TARGETED INSULT"
-  },
-  "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "label2id": {
-    "TARGETED INSULT": 1,
-    "UNTARGETED": 0
-  },
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "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",
-  "torch_dtype": "float32",
-  "transformers_version": "4.26.0",
-  "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:ae1f20a5dd95d74b92d0fbd2b3d729d317e72cb4b30acf98e2fe3430984998eb
-size 871513885

last-checkpoint/pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7054c1135eb4d88629f5742261fc4be64a83155f14009e3184699de050a323f6
-size 435769709

last-checkpoint/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:30d26db9fde6f1200cb35b02d4feec7f2c5f9df5a195b8befa619cd6e0ff1757
-size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:418a9b4a7c7bf0006de027ceb40407fc5486b06fb4d17b5412d09664d5482ca2
-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-base-portuguese-cased",
-  "never_split": null,
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "special_tokens_map_file": "/root/.cache/huggingface/hub/models--neuralmind--bert-base-portuguese-cased/snapshots/94d69c95f98f7d5b2a8700c420230ae10def0baa/special_tokens_map.json",
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
-  "unk_token": "[UNK]"
-}

last-checkpoint/trainer_state.json

@@ -1,88 +0,0 @@
-{
-  "best_metric": 0.687234433366349,
-  "best_model_checkpoint": "/opt/ml/checkpoints/toxicity-target-classification-2023-02-13-11-33-34-745/model/checkpoint-1074",
-  "epoch": 4.0,
-  "global_step": 2148,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.93,
-      "learning_rate": 4.0444740261144315e-05,
-      "loss": 0.633,
-      "step": 500
-    },
-    {
-      "epoch": 1.0,
-      "eval_accuracy": 0.691933240611961,
-      "eval_f1": 0.580523179491889,
-      "eval_loss": 0.6039695739746094,
-      "eval_precision": 0.6350591049567901,
-      "eval_recall": 0.691933240611961,
-      "eval_runtime": 8.9923,
-      "eval_samples_per_second": 159.915,
-      "eval_steps_per_second": 20.017,
-      "step": 537
-    },
-    {
-      "epoch": 1.86,
-      "learning_rate": 3.9149264916456794e-05,
-      "loss": 0.5915,
-      "step": 1000
-    },
-    {
-      "epoch": 2.0,
-      "eval_accuracy": 0.6863699582753825,
-      "eval_f1": 0.687234433366349,
-      "eval_loss": 0.6110407710075378,
-      "eval_precision": 0.6881518808333719,
-      "eval_recall": 0.6863699582753825,
-      "eval_runtime": 9.2368,
-      "eval_samples_per_second": 155.681,
-      "eval_steps_per_second": 19.487,
-      "step": 1074
-    },
-    {
-      "epoch": 2.79,
-      "learning_rate": 3.785378957176927e-05,
-      "loss": 0.4584,
-      "step": 1500
-    },
-    {
-      "epoch": 3.0,
-      "eval_accuracy": 0.6933240611961057,
-      "eval_f1": 0.6605600739460796,
-      "eval_loss": 0.7104145288467407,
-      "eval_precision": 0.6605071455841258,
-      "eval_recall": 0.6933240611961057,
-      "eval_runtime": 9.2844,
-      "eval_samples_per_second": 154.883,
-      "eval_steps_per_second": 19.387,
-      "step": 1611
-    },
-    {
-      "epoch": 3.72,
-      "learning_rate": 3.655831422708176e-05,
-      "loss": 0.3564,
-      "step": 2000
-    },
-    {
-      "epoch": 4.0,
-      "eval_accuracy": 0.6168289290681502,
-      "eval_f1": 0.6306803768959991,
-      "eval_loss": 0.981565535068512,
-      "eval_precision": 0.6670641987183653,
-      "eval_recall": 0.6168289290681502,
-      "eval_runtime": 9.261,
-      "eval_samples_per_second": 155.275,
-      "eval_steps_per_second": 19.436,
-      "step": 2148
-    }
-  ],
-  "max_steps": 16110,
-  "num_train_epochs": 30,
-  "total_flos": 851104652991120.0,
-  "trial_name": null,
-  "trial_params": null
-}

last-checkpoint/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8acb02433984d2e11aaaabc91c31689c394d0774abcace260233569cc66f1a91
-size 3695

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7054c1135eb4d88629f5742261fc4be64a83155f14009e3184699de050a323f6
+oid sha256:2494ada141fc9b43ee71dd958e772766aedc9a020ce7e6f7b3a5de7cbcc44948
 size 435769709