Model save

last-checkpoint/config.json

@@ -1,40 +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": "NOT-OFFENSIVE",
-    "1": "OFFENSIVE"
-  },
-  "initializer_range": 0.02,
-  "intermediate_size": 4096,
-  "label2id": {
-    "NOT-OFFENSIVE": 0,
-    "OFFENSIVE": 1
-  },
-  "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",
-  "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:ad6f0a7fef74b0a849fe0f1f072b9ad2a340d72ccc71361c7738247ba88ab8eb
-size 2675416477

last-checkpoint/pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d28275481f29f85dc64692bd1241eeb86b797b543f56ae08bda2af3b80cb1d6f
-size 1337729837

last-checkpoint/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7a48962e5ff4307118621d2d79e5364056e38baa3c35fdf947a099f7f109336e
-size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d2a6b4ae21d721bb29b01e6298b11f998e2f825381fa156b83df6311626b5a39
-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

@@ -1,184 +0,0 @@
-{
-  "best_metric": 0.8549217425622928,
-  "best_model_checkpoint": "/opt/ml/checkpoints/toxic-comment-classification-2023-02-26-22-07-06-968/model/checkpoint-1408",
-  "epoch": 6.0,
-  "global_step": 8448,
-  "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": 0.4937,
-      "step": 500
-    },
-    {
-      "epoch": 0.71,
-      "learning_rate": 3.1787104153700095e-05,
-      "loss": 0.4465,
-      "step": 1000
-    },
-    {
-      "epoch": 1.0,
-      "eval_accuracy": 0.8546529723000311,
-      "eval_f1": 0.8549217425622928,
-      "eval_loss": 0.41022783517837524,
-      "eval_precision": 0.8668618958335471,
-      "eval_recall": 0.8546529723000311,
-      "eval_runtime": 11.9429,
-      "eval_samples_per_second": 269.03,
-      "eval_steps_per_second": 33.66,
-      "step": 1408
-    },
-    {
-      "epoch": 1.07,
-      "learning_rate": 3.140171249325271e-05,
-      "loss": 0.4308,
-      "step": 1500
-    },
-    {
-      "epoch": 1.42,
-      "learning_rate": 3.1016320832805326e-05,
-      "loss": 0.3826,
-      "step": 2000
-    },
-    {
-      "epoch": 1.78,
-      "learning_rate": 3.063092917235795e-05,
-      "loss": 0.3839,
-      "step": 2500
-    },
-    {
-      "epoch": 2.0,
-      "eval_accuracy": 0.8509181450357921,
-      "eval_f1": 0.8496719953011838,
-      "eval_loss": 0.48135700821876526,
-      "eval_precision": 0.8531835536435355,
-      "eval_recall": 0.8509181450357921,
-      "eval_runtime": 11.8064,
-      "eval_samples_per_second": 272.14,
-      "eval_steps_per_second": 34.049,
-      "step": 2816
-    },
-    {
-      "epoch": 2.13,
-      "learning_rate": 3.0245537511910564e-05,
-      "loss": 0.4001,
-      "step": 3000
-    },
-    {
-      "epoch": 2.49,
-      "learning_rate": 2.986014585146318e-05,
-      "loss": 0.3603,
-      "step": 3500
-    },
-    {
-      "epoch": 2.84,
-      "learning_rate": 2.9474754191015798e-05,
-      "loss": 0.3945,
-      "step": 4000
-    },
-    {
-      "epoch": 3.0,
-      "eval_accuracy": 0.800186741363212,
-      "eval_f1": 0.7918442179147859,
-      "eval_loss": 0.6362168192863464,
-      "eval_precision": 0.8257966335436034,
-      "eval_recall": 0.800186741363212,
-      "eval_runtime": 11.7288,
-      "eval_samples_per_second": 273.94,
-      "eval_steps_per_second": 34.274,
-      "step": 4224
-    },
-    {
-      "epoch": 3.2,
-      "learning_rate": 2.9089362530568417e-05,
-      "loss": 0.3607,
-      "step": 4500
-    },
-    {
-      "epoch": 3.55,
-      "learning_rate": 2.8703970870121032e-05,
-      "loss": 0.345,
-      "step": 5000
-    },
-    {
-      "epoch": 3.91,
-      "learning_rate": 2.831857920967365e-05,
-      "loss": 0.3643,
-      "step": 5500
-    },
-    {
-      "epoch": 4.0,
-      "eval_accuracy": 0.8247743541861189,
-      "eval_f1": 0.8210678650289922,
-      "eval_loss": 0.49613112211227417,
-      "eval_precision": 0.8348592222910702,
-      "eval_recall": 0.8247743541861189,
-      "eval_runtime": 11.9823,
-      "eval_samples_per_second": 268.146,
-      "eval_steps_per_second": 33.55,
-      "step": 5632
-    },
-    {
-      "epoch": 4.26,
-      "learning_rate": 2.793318754922627e-05,
-      "loss": 0.3293,
-      "step": 6000
-    },
-    {
-      "epoch": 4.62,
-      "learning_rate": 2.7547795888778885e-05,
-      "loss": 0.3316,
-      "step": 6500
-    },
-    {
-      "epoch": 4.97,
-      "learning_rate": 2.7162404228331504e-05,
-      "loss": 0.3345,
-      "step": 7000
-    },
-    {
-      "epoch": 5.0,
-      "eval_accuracy": 0.8527855586679116,
-      "eval_f1": 0.8531826157402111,
-      "eval_loss": 0.5266692042350769,
-      "eval_precision": 0.8569563015662375,
-      "eval_recall": 0.8527855586679116,
-      "eval_runtime": 11.9018,
-      "eval_samples_per_second": 269.96,
-      "eval_steps_per_second": 33.777,
-      "step": 7040
-    },
-    {
-      "epoch": 5.33,
-      "learning_rate": 2.6777012567884123e-05,
-      "loss": 0.2956,
-      "step": 7500
-    },
-    {
-      "epoch": 5.68,
-      "learning_rate": 2.6391620907436738e-05,
-      "loss": 0.3053,
-      "step": 8000
-    },
-    {
-      "epoch": 6.0,
-      "eval_accuracy": 0.800186741363212,
-      "eval_f1": 0.791141616583017,
-      "eval_loss": 0.590166449546814,
-      "eval_precision": 0.8292050463846472,
-      "eval_recall": 0.800186741363212,
-      "eval_runtime": 11.946,
-      "eval_samples_per_second": 268.961,
-      "eval_steps_per_second": 33.652,
-      "step": 8448
-    }
-  ],
-  "max_steps": 42240,
-  "num_train_epochs": 30,
-  "total_flos": 9285913358832600.0,
-  "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:eb3b71907c1e39b22ef1ab915290602a79a529af398581187aa888ba7af47b38
-size 3695

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d28275481f29f85dc64692bd1241eeb86b797b543f56ae08bda2af3b80cb1d6f
+oid sha256:45592d7a0658665761f426eada85c30d56ec10d413005c3cec81e85c00eb944b
 size 1337729837