Inicial commit

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": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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",
+  "type_vocab_size": 2,
+  "vocab_size": 29794
+}

eval_results.txt

@@ -0,0 +1,2 @@
+eval_loss = 0.697434716236745
+perplexity = tensor(2.0086)

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e23fcbbe5ac0d777fbf49b49bbf8b715986ec2dc0efd9c2310d326006bca16c
+size 435714904

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": 48, "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": 4e-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": 4, "output_dir": "outputs/LM/FineTune", "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": 48, "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/FineTune/checkpoint-30000/", "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 sha256:048110cd7852611b49ab7b831ecbbfb4db8b6ec684b7f84b4f9e743f23c90ff7
+size 438229514

special_tokens_map.json

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

tokenizer_config.json

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

training_progress_scores.csv

@@ -0,0 +1,18 @@
+global_step,perplexity,eval_loss,train_loss
+10000,tensor(2.1992),0.7880828963867849,0.8737165927886963
+20000,tensor(2.1610),0.7705507040390662,0.8072351813316345
+30000,tensor(2.1334),0.7577285939474578,0.7155318260192871
+34763,tensor(2.1201),0.7514673543713649,0.8827775716781616
+40000,tensor(2.1026),0.7431845677856856,0.7359579801559448
+50000,tensor(2.0772),0.731001776631241,0.6598162651062012
+60000,tensor(2.0668),0.726000594505081,0.7386130690574646
+69526,tensor(2.0506),0.7181160413628266,0.8968920707702637
+70000,tensor(2.0418),0.7138193785487026,0.706092894077301
+80000,tensor(2.0300),0.7080411803251254,0.7196658849716187
+90000,tensor(2.0187),0.7024395720692894,0.8007305264472961
+100000,tensor(2.0050),0.695622627103864,0.6531331539154053
+104289,tensor(2.0049),0.6956184461403945,0.8391630053520203
+110000,tensor(2.0087),0.6975072758021955,0.8131434917449951
+120000,tensor(1.9993),0.6927953025623087,0.7214128375053406
+130000,tensor(2.0056),0.6959200249105013,0.718044638633728
+139052,tensor(2.0068),0.6965351469204804,0.7522366046905518