Upload do modelo de Q&A

checkpoint-501/config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "pierreguillou/bert-base-cased-squad-v1.1-portuguese",
+  "architectures": [
+    "BertForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "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",
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 29794
+}

checkpoint-501/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34f56535a11b50fcfcbb073c7510e37ff57417edf2ce835257bf690d947da5ec
+size 433359664

checkpoint-501/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5e02a20b3bf0219113c56413813f47194cebc7e4c24ffedaef2f15b1282d1f
+size 866833530

checkpoint-501/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3aefd0179b98fc85cd30d19e03c1aa53d38723329dfde800d413bd5e9444df07
+size 13990

checkpoint-501/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:912325317201a1f76547539b0ab54cd581e0c25c0b9ebbff0cd2f78ed8a1b53c
+size 1064

checkpoint-501/trainer_state.json

@@ -0,0 +1,103 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9850746268656714,
+  "eval_steps": 500,
+  "global_step": 501,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.29850746268656714,
+      "grad_norm": 9.899151802062988,
+      "learning_rate": 4.901960784313725e-05,
+      "loss": 3.0988,
+      "step": 50
+    },
+    {
+      "epoch": 0.5970149253731343,
+      "grad_norm": 4.365601062774658,
+      "learning_rate": 4.4555555555555555e-05,
+      "loss": 1.6841,
+      "step": 100
+    },
+    {
+      "epoch": 0.8955223880597015,
+      "grad_norm": 6.207011699676514,
+      "learning_rate": 3.9000000000000006e-05,
+      "loss": 1.6733,
+      "step": 150
+    },
+    {
+      "epoch": 1.191044776119403,
+      "grad_norm": 5.989271640777588,
+      "learning_rate": 3.3444444444444443e-05,
+      "loss": 1.5234,
+      "step": 200
+    },
+    {
+      "epoch": 1.48955223880597,
+      "grad_norm": 5.798114776611328,
+      "learning_rate": 2.788888888888889e-05,
+      "loss": 1.4807,
+      "step": 250
+    },
+    {
+      "epoch": 1.7880597014925375,
+      "grad_norm": 5.086219787597656,
+      "learning_rate": 2.2333333333333335e-05,
+      "loss": 1.4934,
+      "step": 300
+    },
+    {
+      "epoch": 2.083582089552239,
+      "grad_norm": 9.068313598632812,
+      "learning_rate": 1.677777777777778e-05,
+      "loss": 1.4444,
+      "step": 350
+    },
+    {
+      "epoch": 2.382089552238806,
+      "grad_norm": 7.573103904724121,
+      "learning_rate": 1.1222222222222224e-05,
+      "loss": 1.2715,
+      "step": 400
+    },
+    {
+      "epoch": 2.680597014925373,
+      "grad_norm": 8.649182319641113,
+      "learning_rate": 5.666666666666667e-06,
+      "loss": 1.2803,
+      "step": 450
+    },
+    {
+      "epoch": 2.97910447761194,
+      "grad_norm": 8.986006736755371,
+      "learning_rate": 1.1111111111111112e-07,
+      "loss": 1.2893,
+      "step": 500
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 501,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1567388595280896.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-501/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14abf8755a247f484db8b73811aaace3bb041f9275cc68bf47f84a76ee79f0fe
+size 5304