Training in progress, epoch 1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "neuralmind/bert-base-portuguese-cased",
+  "_name_or_path": "neuralmind/bert-large-portuguese-cased",
   "architectures": [
     "ToxicityTypeForSequenceClassification"
   ],
@@ -8,14 +8,14 @@
   "directionality": "bidi",
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "hidden_size": 1024,
   "id2label": {
     "0": "INDIVIDUAL",
     "1": "GROUP",
     "2": "OTHER"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 4096,
   "label2id": {
     "GROUP": 1,
     "INDIVIDUAL": 0,
@@ -24,8 +24,8 @@
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
   "output_past": true,
   "pad_token_id": 0,
   "pooler_fc_size": 768,

last-checkpoint/config.json

@@ -0,0 +1,43 @@
+{
+  "_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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b924c4df2a7a383c6e21fa2b4994f0707e75646c0353d02238d3531a5866707f
+size 3468339

last-checkpoint/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ce392739bf37bbf308c0e0d58c24d7f62006911cfb0ccef33aa174cfcc5ab60
+size 1337733933

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e70f9bacfce971fc134d218db94ce2540e833beff8b4f6613ef42305ac2b6fee
+size 14503

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80e3bce3c0ea15d7b424ec6761f0c5066770082ab56e25f2ea2827bbbc47848b
+size 623

last-checkpoint/special_tokens_map.json

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

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "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

@@ -0,0 +1,28 @@
+{
+  "best_metric": 0.7052333645117603,
+  "best_model_checkpoint": "/opt/ml/checkpoints/toxicity-target-type-identification-2023-02-26-11-44-04-863/model/checkpoint-355",
+  "epoch": 1.0,
+  "global_step": 355,
+  "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": 18.5563,
+      "eval_samples_per_second": 50.98,
+      "eval_steps_per_second": 6.413,
+      "step": 355
+    }
+  ],
+  "max_steps": 10650,
+  "num_train_epochs": 30,
+  "total_flos": 491451660564594.0,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17fee243adf1d020640843f6197611182ca090919cb15d3455ae60e528b4209a
+size 3695

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ec383c18a5b94a5d739dec9c5befc670c3fc650f033ee271224cc462f76d529
-size 435772781
+oid sha256:3ce392739bf37bbf308c0e0d58c24d7f62006911cfb0ccef33aa174cfcc5ab60
+size 1337733933

tokenizer_config.json

@@ -4,11 +4,11 @@
   "do_lower_case": false,
   "mask_token": "[MASK]",
   "model_max_length": 1000000000000000019884624838656,
-  "name_or_path": "neuralmind/bert-base-portuguese-cased",
+  "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-base-portuguese-cased/snapshots/94d69c95f98f7d5b2a8700c420230ae10def0baa/special_tokens_map.json",
+  "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",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29ea1e9a63ff6356100cc945f6ca8285154323a795ec0916bd9de37f42dc85eb
+oid sha256:17fee243adf1d020640843f6197611182ca090919cb15d3455ae60e528b4209a
 size 3695