model

README.md

@@ -1,3 +1,54 @@
 ---
-license: mit
+license: other
+base_model: PORTULAN/albertina-ptbr
+tags:
+- generated_from_trainer
+datasets:
+- ArthurBaia/squad_v1_pt_br
+model-index:
+- name: albertina
+  results: []
 ---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# albertina
+
+This model is a fine-tuned version of [PORTULAN/albertina-ptbr](https://huggingface.co/PORTULAN/albertina-ptbr) on the ArthurBaia/squad_v1_pt_br dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 64
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.31.0.dev0
+- Pytorch 2.0.1+cu117
+- Datasets 2.13.1
+- Tokenizers 0.13.3

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "PORTULAN/albertina-ptbr",
+  "architectures": [
+    "DebertaV2ForQuestionAnswering"
+  ],
+  "attention_head_size": 64,
+  "attention_probs_dropout_prob": 0.1,
+  "conv_act": "gelu",
+  "conv_kernel_size": 3,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 1536,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.31.0.dev0",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "eval_exact_match": 76.96310312204352,
+    "eval_f1": 87.82372321450285,
+    "eval_runtime": 189.7132,
+    "eval_samples": 10977,
+    "eval_samples_per_second": 57.861,
+    "eval_steps_per_second": 7.237
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7320869396b829aec3341b8dee6ad32c900124ac4f59f9e15dcaa6dcb5d53b4
+size 3538522173

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

trainer_state.json

@@ -0,0 +1,70 @@
+{
+  "best_metric": 87.82372321450285,
+  "best_model_checkpoint": "albertina/checkpoint-2806",
+  "epoch": 3.0,
+  "global_step": 4209,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.3357091945830365e-05,
+      "loss": 0.9145,
+      "step": 1403
+    },
+    {
+      "epoch": 1.0,
+      "eval_exact_match": 76.90633869441817,
+      "eval_f1": 87.45778804454862,
+      "eval_runtime": 189.9155,
+      "eval_samples_per_second": 57.799,
+      "eval_steps_per_second": 7.23,
+      "step": 1403
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 6.690425279163697e-06,
+      "loss": 0.5008,
+      "step": 2806
+    },
+    {
+      "epoch": 2.0,
+      "eval_exact_match": 76.96310312204352,
+      "eval_f1": 87.82372321450285,
+      "eval_runtime": 190.0892,
+      "eval_samples_per_second": 57.747,
+      "eval_steps_per_second": 7.223,
+      "step": 2806
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 2.3758612497030175e-08,
+      "loss": 0.2529,
+      "step": 4209
+    },
+    {
+      "epoch": 3.0,
+      "eval_exact_match": 75.63859981078524,
+      "eval_f1": 87.40646900990333,
+      "eval_runtime": 189.9958,
+      "eval_samples_per_second": 57.775,
+      "eval_steps_per_second": 7.226,
+      "step": 4209
+    },
+    {
+      "epoch": 3.0,
+      "step": 4209,
+      "total_flos": 5.682949586646958e+17,
+      "train_loss": 0.5560661419238351,
+      "train_runtime": 17808.0437,
+      "train_samples_per_second": 15.12,
+      "train_steps_per_second": 0.236
+    }
+  ],
+  "max_steps": 4209,
+  "num_train_epochs": 3,
+  "total_flos": 5.682949586646958e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af046c4af5fec6a3003ebc0cd183d44b6b85a2451d1c4e7e992a44fb98734995
+size 3963