Training in progress, epoch 1

README.md

@@ -1,6 +1,6 @@
 ---
 license: mit
-base_model: PORTULAN/albertina-100m-portuguese-ptpt-encoder
+base_model: neuralmind/bert-large-portuguese-cased
 tags:
 - generated_from_trainer
 metrics:
@@ -9,22 +9,22 @@ metrics:
 - precision
 - recall
 model-index:
-- name: LVI_albertina-100m-portuguese-ptpt-encoder
+- name: LVI_bert-large-portuguese-cased
   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. -->
 
-# LVI_albertina-100m-portuguese-ptpt-encoder
+# LVI_bert-large-portuguese-cased
 
-This model is a fine-tuned version of [PORTULAN/albertina-100m-portuguese-ptpt-encoder](https://huggingface.co/PORTULAN/albertina-100m-portuguese-ptpt-encoder) on the None dataset.
+This model is a fine-tuned version of [neuralmind/bert-large-portuguese-cased](https://huggingface.co/neuralmind/bert-large-portuguese-cased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6932
-- Accuracy: 0.5
-- F1: 0.0
-- Precision: 0.0
-- Recall: 0.0
+- Loss: 0.0755
+- Accuracy: 0.9775
+- F1: 0.9775
+- Precision: 0.9758
+- Recall: 0.9793
 
 ## Model description
 
@@ -43,7 +43,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
+- learning_rate: 5e-06
 - train_batch_size: 16
 - eval_batch_size: 16
 - seed: 42
@@ -53,15 +53,9 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step  | Validation Loss | Accuracy | F1     | Precision | Recall |
-|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:---------:|:------:|
-| 0.5678        | 1.0   | 3217  | 0.6316          | 0.6653   | 0.5619 | 0.8128    | 0.4294 |
-| 0.6042        | 2.0   | 6434  | 0.6911          | 0.5      | 0.0    | 0.0       | 0.0    |
-| 0.6946        | 3.0   | 9651  | 0.6932          | 0.5      | 0.0    | 0.0       | 0.0    |
-| 0.694         | 4.0   | 12868 | 0.6932          | 0.5      | 0.6667 | 0.5       | 1.0    |
-| 0.6942        | 5.0   | 16085 | 0.6933          | 0.5      | 0.6667 | 0.5       | 1.0    |
-| 0.6936        | 6.0   | 19302 | 0.6937          | 0.5      | 0.6667 | 0.5       | 1.0    |
-| 0.6937        | 7.0   | 22519 | 0.6932          | 0.5      | 0.0    | 0.0       | 0.0    |
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
+| 0.1071        | 1.0   | 3217 | 0.0755          | 0.9775   | 0.9775 | 0.9758    | 0.9793 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5333189bc54454612d23d846c0995dfc4cb235496fc187f0d2f217687e6b99c0
+oid sha256:b5f00b138409021c800a8ff86021b5b35d3c99dc28d8be1e156d20c731306f28
 size 556799560

tmp-checkpoint-6434/config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "neuralmind/bert-large-portuguese-cased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "PT-PT",
+    "1": "PT-BR"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "PT-BR": 1,
+    "PT-PT": 0
+  },
+  "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": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 29794
+}

tmp-checkpoint-6434/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:874ec343b9437083fe17a8f75e5256a152f29906afbe9a591a41afc20def4c8a
+size 1337640872

tmp-checkpoint-6434/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6085c2e2b602d2ff46761b8cc3b0580e2715f72e47624913132b0afe11dffebe
+size 2675516589

tmp-checkpoint-6434/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bd5fe8d06a3bfa5e0111ae42f40e9072e65f3004a6c69b1447211ab7ff7fcd8
+size 14244

tmp-checkpoint-6434/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79d818fbe78bd027946b5f8726af2230fba2536a3a219eff3b16cc710b1831ed
+size 1064

tmp-checkpoint-6434/special_tokens_map.json

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

tmp-checkpoint-6434/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

tmp-checkpoint-6434/trainer_state.json

@@ -0,0 +1,129 @@
+{
+  "best_metric": 0.5745548592459963,
+  "best_model_checkpoint": "/home/ruben/PT-Pump-Up/package-client/src/pt_pump_up/benchmarking/output/checkpoint-3217",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 6434,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "grad_norm": 18.098752975463867,
+      "learning_rate": 4.9222878458190864e-05,
+      "loss": 0.393,
+      "step": 500
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 1.4246498346328735,
+      "learning_rate": 4.8445756916381726e-05,
+      "loss": 0.3577,
+      "step": 1000
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 20.033092498779297,
+      "learning_rate": 4.766863537457259e-05,
+      "loss": 0.2749,
+      "step": 1500
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.9361429214477539,
+      "learning_rate": 4.689151383276344e-05,
+      "loss": 0.2693,
+      "step": 2000
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 2.208453893661499,
+      "learning_rate": 4.6114392290954305e-05,
+      "loss": 0.2839,
+      "step": 2500
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 5.299256324768066,
+      "learning_rate": 4.5337270749145166e-05,
+      "loss": 0.3315,
+      "step": 3000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6945,
+      "eval_f1": 0.5745548592459963,
+      "eval_loss": 0.5727517604827881,
+      "eval_precision": 0.9459547985587946,
+      "eval_recall": 0.4125714285714286,
+      "eval_runtime": 971.5986,
+      "eval_samples_per_second": 28.818,
+      "eval_steps_per_second": 1.801,
+      "step": 3217
+    },
+    {
+      "epoch": 1.09,
+      "grad_norm": 2.0671701431274414,
+      "learning_rate": 4.456014920733603e-05,
+      "loss": 0.5044,
+      "step": 3500
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 2.1807188987731934,
+      "learning_rate": 4.378302766552689e-05,
+      "loss": 0.6689,
+      "step": 4000
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 5.214261054992676,
+      "learning_rate": 4.300590612371775e-05,
+      "loss": 0.6711,
+      "step": 4500
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 4.0813446044921875,
+      "learning_rate": 4.2228784581908613e-05,
+      "loss": 0.69,
+      "step": 5000
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 14.689708709716797,
+      "learning_rate": 4.1451663040099475e-05,
+      "loss": 0.709,
+      "step": 5500
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 3.6824076175689697,
+      "learning_rate": 4.067454149829034e-05,
+      "loss": 0.6821,
+      "step": 6000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5,
+      "eval_f1": 0.0,
+      "eval_loss": 0.685297429561615,
+      "eval_precision": 0.0,
+      "eval_recall": 0.0,
+      "eval_runtime": 964.7135,
+      "eval_samples_per_second": 29.024,
+      "eval_steps_per_second": 1.814,
+      "step": 6434
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 32170,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 3.215241835190381e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

tmp-checkpoint-6434/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2026ad5b81d5bd011f6117e2f1893b125e45c7f5d9f2735596c30361ea737dd
+size 5048

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04bd7c83bfa10fa1094349afa3a643b8aa1f8c5e29cc2f25cc54e8e78e657e13
+oid sha256:d19fad054636ef9accce9a4758d63dcdf2c7f666b2f98bcc3bb45720359ede5d
 size 5048