Models

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+model.ckpt.data-00000-of-00001 filter=lfs diff=lfs merge=lfs -text
+model.ckpt.meta filter=lfs diff=lfs merge=lfs -text

checkpoint

@@ -0,0 +1,2 @@
+model_checkpoint_path: "model.ckpt"
+all_model_checkpoint_paths: "model.ckpt"

config.json

@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "directionality": "bidi",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "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",
+  "type_vocab_size": 2,
+  "vocab_size": 29794
+}

eval_results.txt

@@ -0,0 +1,2 @@
+eval_loss = 0.6595255749467598
+perplexity = tensor(1.9339)

model.ckpt.data-00000-of-00001

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f33f3b4e0641e1c03c74fb0b584e96cdeefd2884396916415aeb6eb9576ce2d
+size 1337585664

model.ckpt.meta

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18227ad8e125f18043b12c8526e628639ef53565470b3d25157fe80661ebc055
+size 2936928

model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc7d7f8059b65a6f8b94e355784ad7a64343bc6b1bae47b5ea6d070836fce638
+size 1338077297

model_args.json

@@ -0,0 +1 @@
+{"adam_epsilon": 1e-08, "best_model_dir": "outputs/best_model", "cache_dir": "cache_dir/", "custom_layer_parameters": [], "custom_parameter_groups": [], "train_custom_parameters_only": false, "config": {}, "do_lower_case": true, "early_stopping_consider_epochs": false, "early_stopping_delta": 0, "early_stopping_metric": "eval_loss", "early_stopping_metric_minimize": true, "early_stopping_patience": 3, "encoding": "utf-8", "eval_batch_size": 32, "evaluate_during_training": true, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 10000, "evaluate_during_training_verbose": true, "fp16": true, "fp16_opt_level": "O1", "gradient_accumulation_steps": 1, "learning_rate": 2e-05, "local_rank": -1, "logging_steps": 50, "manual_seed": null, "max_grad_norm": 1.0, "max_seq_length": 128, "multiprocessing_chunksize": 500, "n_gpu": 1, "no_cache": true, "no_save": false, "num_train_epochs": 1, "output_dir": "outputs/LM/FineTuneLarge", "overwrite_output_dir": true, "process_count": 2, "reprocess_input_data": false, "save_best_model": true, "save_eval_checkpoints": true, "save_model_every_epoch": true, "save_steps": 10000, "save_optimizer_and_scheduler": true, "silent": false, "tensorboard_dir": null, "train_batch_size": 32, "use_cached_eval_features": false, "use_early_stopping": false, "use_multiprocessing": true, "wandb_kwargs": {}, "wandb_project": null, "warmup_ratio": 0.06, "warmup_steps": 1000, "weight_decay": 0, "block_size": 128, "config_name": null, "dataset_class": null, "dataset_type": "simple", "discriminator_config": {}, "discriminator_loss_weight": 50.0, "generator_config": {}, "max_steps": -1, "min_frequency": 2, "mlm": true, "mlm_probability": 0.15, "sliding_window": false, "special_tokens": ["<s>", "<pad>", "</s>", "<unk>", "<mask>"], "stride": 0.8, "tie_generator_and_discriminator_embeddings": true, "tokenizer_name": "/dados/projetos/sentimentos/outputs/LM/FineTuneLarge/checkpoint-104289-epoch-3/", "vocab_size": null, "clean_text": true, "handle_chinese_chars": false, "strip_accents": true}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0592e65d465827a9245e909ee17660fdf7c08231c69952487d761a0ca8666e7
+size 1342007651

special_tokens_map.json

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

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ab87719d2dbecd263829af6f583ffc3f368913fbcfcda3f8f7c117fd79e62
+size 1338100480

tokenizer_config.json

@@ -0,0 +1 @@
+{"special_tokens_map_file": null, "full_tokenizer_file": null}

training_progress_scores.csv

@@ -0,0 +1,7 @@
+global_step,perplexity,eval_loss,train_loss
+10000,tensor(1.9330),0.659087556891259,0.5109515190124512
+20000,tensor(1.9278),0.6563766614771557,0.6348448395729065
+30000,tensor(1.9368),0.6610437813159591,0.7273242473602295
+40000,tensor(1.9303),0.6576739994996246,0.6494269371032715
+50000,tensor(1.9290),0.6570122954839838,0.6384057998657227
+52144,tensor(1.9377),0.6615094625095226,0.7903710007667542