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": "NOT-OFFENSIVE",
-    "1": "OFFENSIVE"
-  },
-  "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "label2id": {
-    "NOT-OFFENSIVE": 0,
-    "OFFENSIVE": 1
-  },
-  "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 sha256:3abd9e432cd17aa227c77a4602995a7d44a2d5b8db7d09756643847c4bdb3b4a
-size 871513885

last-checkpoint/pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ea0028124c16c42b0173d84c15dfc6aaf99389e964846d869e1df752e59e8dec
-size 435769709

last-checkpoint/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:69726e2727b419acf15202f62187cf0581b6c2bfd7c023bc96716f05fa3e0d08
-size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c784665c0bd4de01cbb7e9c50f86d2b0ebff72eead0e3ffd23f231c6475b92bf
-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

@@ -1,274 +0,0 @@
-{
-  "best_metric": 0.8580479726153486,
-  "best_model_checkpoint": "./output/toxic-comment-classification-2023-02-12-03-38-39-438/model/checkpoint-5632",
-  "epoch": 9.0,
-  "global_step": 12672,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.36,
-      "learning_rate": 3.217249581414747e-05,
-      "loss": 0.4962,
-      "step": 500
-    },
-    {
-      "epoch": 0.71,
-      "learning_rate": 3.1787104153700095e-05,
-      "loss": 0.4422,
-      "step": 1000
-    },
-    {
-      "epoch": 1.0,
-      "eval_accuracy": 0.8465608465608465,
-      "eval_f1": 0.846971473226303,
-      "eval_loss": 0.4196861684322357,
-      "eval_precision": 0.8505491368402285,
-      "eval_recall": 0.8465608465608465,
-      "eval_runtime": 14.7315,
-      "eval_samples_per_second": 218.104,
-      "eval_steps_per_second": 27.288,
-      "step": 1408
-    },
-    {
-      "epoch": 1.07,
-      "learning_rate": 3.140171249325271e-05,
-      "loss": 0.424,
-      "step": 1500
-    },
-    {
-      "epoch": 1.42,
-      "learning_rate": 3.1016320832805326e-05,
-      "loss": 0.3631,
-      "step": 2000
-    },
-    {
-      "epoch": 1.78,
-      "learning_rate": 3.063092917235795e-05,
-      "loss": 0.3566,
-      "step": 2500
-    },
-    {
-      "epoch": 2.0,
-      "eval_accuracy": 0.8412698412698413,
-      "eval_f1": 0.8394018830559876,
-      "eval_loss": 0.47242870926856995,
-      "eval_precision": 0.8453384370339388,
-      "eval_recall": 0.8412698412698413,
-      "eval_runtime": 15.5699,
-      "eval_samples_per_second": 206.359,
-      "eval_steps_per_second": 25.819,
-      "step": 2816
-    },
-    {
-      "epoch": 2.13,
-      "learning_rate": 3.0245537511910564e-05,
-      "loss": 0.3359,
-      "step": 3000
-    },
-    {
-      "epoch": 2.49,
-      "learning_rate": 2.986014585146318e-05,
-      "loss": 0.3024,
-      "step": 3500
-    },
-    {
-      "epoch": 2.84,
-      "learning_rate": 2.9474754191015798e-05,
-      "loss": 0.3135,
-      "step": 4000
-    },
-    {
-      "epoch": 3.0,
-      "eval_accuracy": 0.844693432928727,
-      "eval_f1": 0.8433530690879544,
-      "eval_loss": 0.48013588786125183,
-      "eval_precision": 0.8469664276626117,
-      "eval_recall": 0.844693432928727,
-      "eval_runtime": 15.5293,
-      "eval_samples_per_second": 206.899,
-      "eval_steps_per_second": 25.887,
-      "step": 4224
-    },
-    {
-      "epoch": 3.2,
-      "learning_rate": 2.9089362530568417e-05,
-      "loss": 0.2789,
-      "step": 4500
-    },
-    {
-      "epoch": 3.55,
-      "learning_rate": 2.8703970870121032e-05,
-      "loss": 0.263,
-      "step": 5000
-    },
-    {
-      "epoch": 3.91,
-      "learning_rate": 2.831857920967365e-05,
-      "loss": 0.2638,
-      "step": 5500
-    },
-    {
-      "epoch": 4.0,
-      "eval_accuracy": 0.8577653283535637,
-      "eval_f1": 0.8580479726153486,
-      "eval_loss": 0.5590450167655945,
-      "eval_precision": 0.8593690748266627,
-      "eval_recall": 0.8577653283535637,
-      "eval_runtime": 15.5871,
-      "eval_samples_per_second": 206.132,
-      "eval_steps_per_second": 25.791,
-      "step": 5632
-    },
-    {
-      "epoch": 4.26,
-      "learning_rate": 2.793318754922627e-05,
-      "loss": 0.2316,
-      "step": 6000
-    },
-    {
-      "epoch": 4.62,
-      "learning_rate": 2.7547795888778885e-05,
-      "loss": 0.2292,
-      "step": 6500
-    },
-    {
-      "epoch": 4.97,
-      "learning_rate": 2.7162404228331504e-05,
-      "loss": 0.2314,
-      "step": 7000
-    },
-    {
-      "epoch": 5.0,
-      "eval_accuracy": 0.8490507314036726,
-      "eval_f1": 0.8487038312585119,
-      "eval_loss": 0.5605392456054688,
-      "eval_precision": 0.848937798685001,
-      "eval_recall": 0.8490507314036726,
-      "eval_runtime": 14.9336,
-      "eval_samples_per_second": 215.153,
-      "eval_steps_per_second": 26.919,
-      "step": 7040
-    },
-    {
-      "epoch": 5.33,
-      "learning_rate": 2.6777012567884123e-05,
-      "loss": 0.1992,
-      "step": 7500
-    },
-    {
-      "epoch": 5.68,
-      "learning_rate": 2.6391620907436738e-05,
-      "loss": 0.2221,
-      "step": 8000
-    },
-    {
-      "epoch": 6.0,
-      "eval_accuracy": 0.8415810768751946,
-      "eval_f1": 0.8413911882051015,
-      "eval_loss": 0.6368530988693237,
-      "eval_precision": 0.8413807388640939,
-      "eval_recall": 0.8415810768751946,
-      "eval_runtime": 14.6321,
-      "eval_samples_per_second": 219.586,
-      "eval_steps_per_second": 27.474,
-      "step": 8448
-    },
-    {
-      "epoch": 6.04,
-      "learning_rate": 2.600622924698936e-05,
-      "loss": 0.2064,
-      "step": 8500
-    },
-    {
-      "epoch": 6.39,
-      "learning_rate": 2.5620837586541976e-05,
-      "loss": 0.1943,
-      "step": 9000
-    },
-    {
-      "epoch": 6.75,
-      "learning_rate": 2.5235445926094595e-05,
-      "loss": 0.1939,
-      "step": 9500
-    },
-    {
-      "epoch": 7.0,
-      "eval_accuracy": 0.8400248988484282,
-      "eval_f1": 0.8401859753110656,
-      "eval_loss": 0.6518161296844482,
-      "eval_precision": 0.8405358987959715,
-      "eval_recall": 0.8400248988484282,
-      "eval_runtime": 15.2445,
-      "eval_samples_per_second": 210.764,
-      "eval_steps_per_second": 26.37,
-      "step": 9856
-    },
-    {
-      "epoch": 7.1,
-      "learning_rate": 2.4850054265647214e-05,
-      "loss": 0.2117,
-      "step": 10000
-    },
-    {
-      "epoch": 7.46,
-      "learning_rate": 2.446466260519983e-05,
-      "loss": 0.198,
-      "step": 10500
-    },
-    {
-      "epoch": 7.81,
-      "learning_rate": 2.4079270944752448e-05,
-      "loss": 0.2015,
-      "step": 11000
-    },
-    {
-      "epoch": 8.0,
-      "eval_accuracy": 0.8462496109554933,
-      "eval_f1": 0.8456511274707091,
-      "eval_loss": 0.6041903495788574,
-      "eval_precision": 0.8464673674599805,
-      "eval_recall": 0.8462496109554933,
-      "eval_runtime": 14.8589,
-      "eval_samples_per_second": 216.234,
-      "eval_steps_per_second": 27.054,
-      "step": 11264
-    },
-    {
-      "epoch": 8.17,
-      "learning_rate": 2.3693879284305067e-05,
-      "loss": 0.1896,
-      "step": 11500
-    },
-    {
-      "epoch": 8.52,
-      "learning_rate": 2.3308487623857682e-05,
-      "loss": 0.1932,
-      "step": 12000
-    },
-    {
-      "epoch": 8.88,
-      "learning_rate": 2.29230959634103e-05,
-      "loss": 0.1989,
-      "step": 12500
-    },
-    {
-      "epoch": 9.0,
-      "eval_accuracy": 0.8499844382197324,
-      "eval_f1": 0.8496464092791962,
-      "eval_loss": 0.6235840320587158,
-      "eval_precision": 0.8498702852768623,
-      "eval_recall": 0.8499844382197324,
-      "eval_runtime": 15.7802,
-      "eval_samples_per_second": 203.61,
-      "eval_steps_per_second": 25.475,
-      "step": 12672
-    }
-  ],
-  "max_steps": 42240,
-  "num_train_epochs": 30,
-  "total_flos": 3931395111413520.0,
-  "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:c07d398af21a16d9c74ceca38be74c689e7fefb963b4f8da37b6c49e55121eea
-size 3631

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea0028124c16c42b0173d84c15dfc6aaf99389e964846d869e1df752e59e8dec
+oid sha256:5cc09466df4f7451ec73c9e2f59c8ca058f7d217f855947f6d8de3558d655167
 size 435769709