Pushing fine-tuned model to Hugging Face Hub

README.md

@@ -0,0 +1,48 @@
+
+---
+language:
+- pt
+- en
+tags:
+- aes
+datasets:
+- kamel-usp/aes_enem_dataset
+base_model: neuralmind/bert-large-portuguese-cased
+metrics:
+- accuracy
+- qwk
+library_name: transformers
+model-index:
+  - name: bert-large-portuguese-cased-encoder_classification-C5-essay_only
+    results:
+      - task:
+          type: text-classification
+          name: Automated Essay Score
+        dataset:
+          name: Automated Essay Score ENEM Dataset
+          type: kamel-usp/aes_enem_dataset
+          config: JBCS2025
+          split: test
+        metrics:
+          - name: Macro F1
+            type: f1
+            value: 0.3013676792556103
+          - name: QWK
+            type: qwk
+            value: 0.4591540693235608
+          - name: Weighted Macro F1
+            type: f1
+            value: 0.3597310868375336
+---
+# Model ID: bert-large-portuguese-cased-encoder_classification-C5-essay_only
+## Results
+|                  |   test_data |
+|:-----------------|------------:|
+| eval_accuracy    |    0.413043 |
+| eval_RMSE        |   59.758    |
+| eval_QWK         |    0.459154 |
+| eval_Macro_F1    |    0.301368 |
+| eval_Weighted_F1 |    0.359731 |
+| eval_Micro_F1    |    0.413043 |
+| eval_HDIV        |    0.144928 |
+        

config.json

@@ -0,0 +1,47 @@
+{
+  "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": 0,
+    "1": 40,
+    "2": 80,
+    "3": 120,
+    "4": 160,
+    "5": 200
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "0": 0,
+    "40": 1,
+    "80": 2,
+    "120": 3,
+    "160": 4,
+    "200": 5
+  },
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 29794
+}

emissions.csv

@@ -0,0 +1,2 @@
+timestamp,project_name,run_id,experiment_id,duration,emissions,emissions_rate,cpu_power,gpu_power,ram_power,cpu_energy,gpu_energy,ram_energy,energy_consumed,country_name,country_iso_code,region,cloud_provider,cloud_region,os,python_version,codecarbon_version,cpu_count,cpu_model,gpu_count,gpu_model,longitude,latitude,ram_total_size,tracking_mode,on_cloud,pue
+2025-07-09T17:01:24,jbcs2025,eeac1237-10cc-489f-9fff-9d2b32dc2447,bert-large-portuguese-cased-encoder_classification-C5-essay_only,218.28439827199327,0.004794613344546399,2.1964984133094436e-05,53.71,151.8616928158688,58.0,0.0027177277048807927,0.013759523507610005,0.003451893176540842,0.01992914438903164,Romania,ROU,gorj county,,,Linux-5.15.0-143-generic-x86_64-with-glibc2.35,3.12.11,3.0.2,36,Intel(R) Xeon(R) Gold 6248R CPU @ 3.00GHz,1,1 x NVIDIA RTX A6000,23.2904,45.0489,393.6063117980957,machine,N,1.0

evaluation_results.csv

@@ -0,0 +1,4 @@
+eval_loss,eval_model_preparation_time,eval_accuracy,eval_RMSE,eval_QWK,eval_HDIV,eval_Macro_F1,eval_Micro_F1,eval_Weighted_F1,eval_TP_0,eval_TN_0,eval_FP_0,eval_FN_0,eval_TP_1,eval_TN_1,eval_FP_1,eval_FN_1,eval_TP_2,eval_TN_2,eval_FP_2,eval_FN_2,eval_TP_3,eval_TN_3,eval_FP_3,eval_FN_3,eval_TP_4,eval_TN_4,eval_FP_4,eval_FN_4,eval_TP_5,eval_TN_5,eval_FP_5,eval_FN_5,eval_runtime,eval_samples_per_second,eval_steps_per_second,epoch,reference,timestamp,id
+1.9279780387878418,0.0037,0.13636363636363635,100.24213110506405,-0.014913745130773481,0.43181818181818177,0.05408522170328086,0.13636363636363635,0.053618698662808675,16,7,108,1,0,96,0,36,0,112,0,20,2,93,6,31,0,108,0,24,0,130,0,2,1.0644,124.016,8.456,-1,validation_before_training,2025-07-09 16:57:57,bert-large-portuguese-cased-encoder_classification-C5-essay_only
+1.7058095932006836,0.0037,0.3106060606060606,54.49492609130661,0.5028286803591193,0.08333333333333337,0.27143120393120396,0.3106060606060606,0.3049726999727,6,113,2,11,7,91,5,29,7,79,33,13,6,83,16,27,15,73,35,9,0,130,0,2,0.8907,148.192,10.104,11.0,validation_after_training,2025-07-09 16:57:57,bert-large-portuguese-cased-encoder_classification-C5-essay_only
+1.5725419521331787,0.0037,0.41304347826086957,59.75796593554388,0.45915406932356084,0.14492753623188404,0.3013676792556103,0.41304347826086957,0.3597310868375336,5,115,1,17,6,94,12,26,14,82,32,10,3,112,1,22,29,71,35,3,0,135,0,3,0.9202,149.972,9.781,11.0,test_results,2025-07-09 16:57:57,bert-large-portuguese-cased-encoder_classification-C5-essay_only

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7410bfd9a65bc8d306395c2d870b60f27dfdd30867aa59ae6f638ce4bab09a8
+size 1337657272

run_experiment.log

@@ -0,0 +1,403 @@
+[2025-07-09 16:57:42,869][__main__][INFO] - cache_dir: /tmp/
+dataset:
+  name: kamel-usp/aes_enem_dataset
+  split: JBCS2025
+training_params:
+  seed: 42
+  num_train_epochs: 20
+  logging_steps: 100
+  metric_for_best_model: QWK
+  bf16: true
+bootstrap:
+  enabled: true
+  n_bootstrap: 10000
+  bootstrap_seed: 42
+  metrics:
+  - QWK
+  - Macro_F1
+  - Weighted_F1
+post_training_results:
+  model_path: /workspace/jbcs2025/outputs/2025-03-24/20-42-59
+experiments:
+  model:
+    name: neuralmind/bert-large-portuguese-cased
+    type: encoder_classification
+    num_labels: 6
+    output_dir: ./results/bertimbau_large/C5
+    logging_dir: ./logs/bertimbau_large/C5
+    best_model_dir: ./results/bertimbau_large/C5/best_model
+  tokenizer:
+    name: neuralmind/bert-large-portuguese-cased
+  dataset:
+    grade_index: 4
+    use_full_context: false
+  training_params:
+    weight_decay: 0.01
+    warmup_ratio: 0.1
+    learning_rate: 5.0e-05
+    train_batch_size: 16
+    eval_batch_size: 16
+    gradient_accumulation_steps: 1
+    gradient_checkpointing: false
+
+[2025-07-09 16:57:46,732][__main__][INFO] - GPU 0: NVIDIA RTX A6000 | TDP ≈ 300 W
+[2025-07-09 16:57:46,733][__main__][INFO] - Starting the Fine Tuning training process.
+[2025-07-09 16:57:52,183][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /tmp/models--neuralmind--bert-large-portuguese-cased/snapshots/aa302f6ea73b759f7df9cad58bd272127b67ec28/config.json
+[2025-07-09 16:57:52,184][transformers.configuration_utils][INFO] - Model config BertConfig {
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "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",
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.53.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 29794
+}
+
+[2025-07-09 16:57:52,386][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /tmp/models--neuralmind--bert-large-portuguese-cased/snapshots/aa302f6ea73b759f7df9cad58bd272127b67ec28/config.json
+[2025-07-09 16:57:52,387][transformers.configuration_utils][INFO] - Model config BertConfig {
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "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",
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.53.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 29794
+}
+
+[2025-07-09 16:57:52,630][transformers.tokenization_utils_base][INFO] - loading file vocab.txt from cache at /tmp/models--neuralmind--bert-large-portuguese-cased/snapshots/aa302f6ea73b759f7df9cad58bd272127b67ec28/vocab.txt
+[2025-07-09 16:57:52,631][transformers.tokenization_utils_base][INFO] - loading file tokenizer.json from cache at None
+[2025-07-09 16:57:52,631][transformers.tokenization_utils_base][INFO] - loading file added_tokens.json from cache at /tmp/models--neuralmind--bert-large-portuguese-cased/snapshots/aa302f6ea73b759f7df9cad58bd272127b67ec28/added_tokens.json
+[2025-07-09 16:57:52,631][transformers.tokenization_utils_base][INFO] - loading file special_tokens_map.json from cache at /tmp/models--neuralmind--bert-large-portuguese-cased/snapshots/aa302f6ea73b759f7df9cad58bd272127b67ec28/special_tokens_map.json
+[2025-07-09 16:57:52,631][transformers.tokenization_utils_base][INFO] - loading file tokenizer_config.json from cache at /tmp/models--neuralmind--bert-large-portuguese-cased/snapshots/aa302f6ea73b759f7df9cad58bd272127b67ec28/tokenizer_config.json
+[2025-07-09 16:57:52,631][transformers.tokenization_utils_base][INFO] - loading file chat_template.jinja from cache at None
+[2025-07-09 16:57:52,631][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /tmp/models--neuralmind--bert-large-portuguese-cased/snapshots/aa302f6ea73b759f7df9cad58bd272127b67ec28/config.json
+[2025-07-09 16:57:52,632][transformers.configuration_utils][INFO] - Model config BertConfig {
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "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",
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.53.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 29794
+}
+
+[2025-07-09 16:57:52,662][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /tmp/models--neuralmind--bert-large-portuguese-cased/snapshots/aa302f6ea73b759f7df9cad58bd272127b67ec28/config.json
+[2025-07-09 16:57:52,663][transformers.configuration_utils][INFO] - Model config BertConfig {
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "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",
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.53.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 29794
+}
+
+[2025-07-09 16:57:52,682][__main__][INFO] - Tokenizer function parameters- Padding:longest; Truncation: True; Use Full Context: False
+[2025-07-09 16:57:53,334][__main__][INFO] - 
+Token statistics for 'train' split:
+[2025-07-09 16:57:53,334][__main__][INFO] -   Total examples: 500
+[2025-07-09 16:57:53,334][__main__][INFO] -   Min tokens: 512
+[2025-07-09 16:57:53,334][__main__][INFO] -   Max tokens: 512
+[2025-07-09 16:57:53,334][__main__][INFO] -   Avg tokens: 512.00
+[2025-07-09 16:57:53,335][__main__][INFO] -   Std tokens: 0.00
+[2025-07-09 16:57:53,430][__main__][INFO] - 
+Token statistics for 'validation' split:
+[2025-07-09 16:57:53,431][__main__][INFO] -   Total examples: 132
+[2025-07-09 16:57:53,431][__main__][INFO] -   Min tokens: 512
+[2025-07-09 16:57:53,431][__main__][INFO] -   Max tokens: 512
+[2025-07-09 16:57:53,431][__main__][INFO] -   Avg tokens: 512.00
+[2025-07-09 16:57:53,431][__main__][INFO] -   Std tokens: 0.00
+[2025-07-09 16:57:53,529][__main__][INFO] - 
+Token statistics for 'test' split:
+[2025-07-09 16:57:53,529][__main__][INFO] -   Total examples: 138
+[2025-07-09 16:57:53,529][__main__][INFO] -   Min tokens: 512
+[2025-07-09 16:57:53,529][__main__][INFO] -   Max tokens: 512
+[2025-07-09 16:57:53,529][__main__][INFO] -   Avg tokens: 512.00
+[2025-07-09 16:57:53,529][__main__][INFO] -   Std tokens: 0.00
+[2025-07-09 16:57:53,529][__main__][INFO] - If token statistics are the same (max, avg, min) keep in mind that this is due to batched tokenization and padding.
+[2025-07-09 16:57:53,529][__main__][INFO] - Model max length: 512. If it is the same as stats, then there is a high chance that sequences are being truncated.
+[2025-07-09 16:57:53,738][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /tmp/models--neuralmind--bert-large-portuguese-cased/snapshots/aa302f6ea73b759f7df9cad58bd272127b67ec28/config.json
+[2025-07-09 16:57:53,738][transformers.configuration_utils][INFO] - Model config BertConfig {
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": 0,
+    "1": 40,
+    "2": 80,
+    "3": 120,
+    "4": 160,
+    "5": 200
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "0": 0,
+    "40": 1,
+    "80": 2,
+    "120": 3,
+    "160": 4,
+    "200": 5
+  },
+  "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",
+  "transformers_version": "4.53.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 29794
+}
+
+[2025-07-09 16:57:54,136][transformers.modeling_utils][INFO] - loading weights file pytorch_model.bin from cache at /tmp/models--neuralmind--bert-large-portuguese-cased/snapshots/aa302f6ea73b759f7df9cad58bd272127b67ec28/pytorch_model.bin
+[2025-07-09 16:57:54,377][transformers.safetensors_conversion][INFO] - Attempting to create safetensors variant
+[2025-07-09 16:57:55,046][transformers.modeling_utils][INFO] - Since the `torch_dtype` attribute can't be found in model's config object, will use torch_dtype={torch_dtype} as derived from model's weights
+[2025-07-09 16:57:55,046][transformers.modeling_utils][INFO] - Instantiating BertForSequenceClassification model under default dtype torch.float32.
+[2025-07-09 16:57:55,324][transformers.safetensors_conversion][INFO] - Safetensors PR exists
+[2025-07-09 16:57:56,969][transformers.modeling_utils][INFO] - Some weights of the model checkpoint at neuralmind/bert-large-portuguese-cased were not used when initializing BertForSequenceClassification: ['cls.predictions.bias', 'cls.predictions.decoder.weight', 'cls.predictions.transform.LayerNorm.bias', 'cls.predictions.transform.LayerNorm.weight', 'cls.predictions.transform.dense.bias', 'cls.predictions.transform.dense.weight', 'cls.seq_relationship.bias', 'cls.seq_relationship.weight']
+- This IS expected if you are initializing BertForSequenceClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
+- This IS NOT expected if you are initializing BertForSequenceClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
+[2025-07-09 16:57:56,970][transformers.modeling_utils][WARNING] - Some weights of BertForSequenceClassification were not initialized from the model checkpoint at neuralmind/bert-large-portuguese-cased and are newly initialized: ['classifier.bias', 'classifier.weight']
+You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
+[2025-07-09 16:57:56,979][transformers.training_args][INFO] - PyTorch: setting up devices
+[2025-07-09 16:57:57,001][__main__][INFO] - Total steps: 620. Number of warmup steps: 62
+[2025-07-09 16:57:57,009][transformers.trainer][INFO] - You have loaded a model on multiple GPUs. `is_model_parallel` attribute will be force-set to `True` to avoid any unexpected behavior such as device placement mismatching.
+[2025-07-09 16:57:57,035][transformers.trainer][INFO] - Using auto half precision backend
+[2025-07-09 16:57:57,038][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt. If grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 16:57:57,044][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 16:57:57,044][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 16:57:57,045][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 16:57:58,469][transformers.trainer][INFO] - The following columns in the Training set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt. If grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 16:57:58,484][transformers.trainer][INFO] - ***** Running training *****
+[2025-07-09 16:57:58,484][transformers.trainer][INFO] -   Num examples = 500
+[2025-07-09 16:57:58,484][transformers.trainer][INFO] -   Num Epochs = 20
+[2025-07-09 16:57:58,484][transformers.trainer][INFO] -   Instantaneous batch size per device = 16
+[2025-07-09 16:57:58,484][transformers.trainer][INFO] -   Total train batch size (w. parallel, distributed & accumulation) = 16
+[2025-07-09 16:57:58,484][transformers.trainer][INFO] -   Gradient Accumulation steps = 1
+[2025-07-09 16:57:58,484][transformers.trainer][INFO] -   Total optimization steps = 640
+[2025-07-09 16:57:58,485][transformers.trainer][INFO] -   Number of trainable parameters = 334,402,566
+[2025-07-09 16:58:10,840][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt. If grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 16:58:10,842][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 16:58:10,843][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 16:58:10,843][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 16:58:11,763][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-32
+[2025-07-09 16:58:11,765][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-32/config.json
+[2025-07-09 16:58:14,552][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-32/model.safetensors
+[2025-07-09 16:58:29,916][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt. If grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 16:58:29,920][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 16:58:29,920][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 16:58:29,920][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 16:58:30,836][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-64
+[2025-07-09 16:58:30,837][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-64/config.json
+[2025-07-09 16:58:33,080][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-64/model.safetensors
+[2025-07-09 16:58:48,106][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt. If grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 16:58:48,110][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 16:58:48,110][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 16:58:48,110][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 16:58:49,026][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-96
+[2025-07-09 16:58:49,028][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-96/config.json
+[2025-07-09 16:58:50,997][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-96/model.safetensors
+[2025-07-09 16:58:53,331][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-32] due to args.save_total_limit
+[2025-07-09 16:58:53,540][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-64] due to args.save_total_limit
+[2025-07-09 16:59:06,189][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt. If grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 16:59:06,193][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 16:59:06,193][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 16:59:06,193][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 16:59:07,110][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-128
+[2025-07-09 16:59:07,112][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-128/config.json
+[2025-07-09 16:59:09,263][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-128/model.safetensors
+[2025-07-09 16:59:23,878][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt. If grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 16:59:23,880][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 16:59:23,881][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 16:59:23,881][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 16:59:24,800][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-160
+[2025-07-09 16:59:24,801][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-160/config.json
+[2025-07-09 16:59:27,049][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-160/model.safetensors
+[2025-07-09 16:59:29,822][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-128] due to args.save_total_limit
+[2025-07-09 16:59:42,490][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt. If grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 16:59:42,494][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 16:59:42,494][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 16:59:42,494][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 16:59:43,446][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-192
+[2025-07-09 16:59:43,448][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-192/config.json
+[2025-07-09 16:59:45,659][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-192/model.safetensors
+[2025-07-09 16:59:47,967][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-96] due to args.save_total_limit
+[2025-07-09 16:59:48,167][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-160] due to args.save_total_limit
+[2025-07-09 17:00:00,675][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt. If grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:00:00,679][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:00:00,679][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:00:00,679][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:00:01,594][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-224
+[2025-07-09 17:00:01,596][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-224/config.json
+[2025-07-09 17:00:04,095][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-224/model.safetensors
+[2025-07-09 17:00:18,859][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt. If grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:00:18,863][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:00:18,863][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:00:18,863][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:00:19,813][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-256
+[2025-07-09 17:00:19,816][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-256/config.json
+[2025-07-09 17:00:22,407][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-256/model.safetensors
+[2025-07-09 17:00:25,011][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-224] due to args.save_total_limit
+[2025-07-09 17:00:37,587][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt. If grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:00:37,589][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:00:37,589][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:00:37,589][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:00:38,507][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-288
+[2025-07-09 17:00:38,509][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-288/config.json
+[2025-07-09 17:00:40,642][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-288/model.safetensors
+[2025-07-09 17:00:42,927][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-256] due to args.save_total_limit
+[2025-07-09 17:00:55,513][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt. If grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:00:55,516][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:00:55,516][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:00:55,516][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:00:56,443][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-320
+[2025-07-09 17:00:56,445][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-320/config.json
+[2025-07-09 17:00:58,820][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-320/model.safetensors
+[2025-07-09 17:01:01,234][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-288] due to args.save_total_limit
+[2025-07-09 17:01:13,788][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt. If grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:01:13,791][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:01:13,792][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:01:13,792][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:01:14,713][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-352
+[2025-07-09 17:01:14,715][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-352/config.json
+[2025-07-09 17:01:16,746][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-352/model.safetensors
+[2025-07-09 17:01:19,071][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-320] due to args.save_total_limit
+[2025-07-09 17:01:19,334][transformers.trainer][INFO] - 
+
+Training completed. Do not forget to share your model on huggingface.co/models =)
+
+
+[2025-07-09 17:01:19,334][transformers.trainer][INFO] - Loading best model from /workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-192 (score: 0.5028286803591193).
+[2025-07-09 17:01:19,785][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/16-57-42/results/bertimbau_large/C5/checkpoint-352] due to args.save_total_limit
+[2025-07-09 17:01:20,049][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt. If grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:01:20,052][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:01:20,052][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 17:01:20,052][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:01:20,950][__main__][INFO] - Training completed successfully.
+[2025-07-09 17:01:20,950][__main__][INFO] - Running on Test
+[2025-07-09 17:01:20,951][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt. If grades, essay_year, id_prompt, essay_text, reference, id, supporting_text, prompt are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 17:01:20,953][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 17:01:20,953][transformers.trainer][INFO] -   Num examples = 138
+[2025-07-09 17:01:20,953][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 17:01:21,879][__main__][INFO] - Test metrics: {'eval_loss': 1.5725419521331787, 'eval_model_preparation_time': 0.0037, 'eval_accuracy': 0.41304347826086957, 'eval_RMSE': 59.75796593554388, 'eval_QWK': 0.45915406932356084, 'eval_HDIV': 0.14492753623188404, 'eval_Macro_F1': 0.3013676792556103, 'eval_Micro_F1': 0.41304347826086957, 'eval_Weighted_F1': 0.3597310868375336, 'eval_TP_0': 5, 'eval_TN_0': 115, 'eval_FP_0': 1, 'eval_FN_0': 17, 'eval_TP_1': 6, 'eval_TN_1': 94, 'eval_FP_1': 12, 'eval_FN_1': 26, 'eval_TP_2': 14, 'eval_TN_2': 82, 'eval_FP_2': 32, 'eval_FN_2': 10, 'eval_TP_3': 3, 'eval_TN_3': 112, 'eval_FP_3': 1, 'eval_FN_3': 22, 'eval_TP_4': 29, 'eval_TN_4': 71, 'eval_FP_4': 35, 'eval_FN_4': 3, 'eval_TP_5': 0, 'eval_TN_5': 135, 'eval_FP_5': 0, 'eval_FN_5': 3, 'eval_runtime': 0.9202, 'eval_samples_per_second': 149.972, 'eval_steps_per_second': 9.781, 'epoch': 11.0}
+[2025-07-09 17:01:21,880][transformers.trainer][INFO] - Saving model checkpoint to ./results/bertimbau_large/C5/best_model
+[2025-07-09 17:01:21,881][transformers.configuration_utils][INFO] - Configuration saved in ./results/bertimbau_large/C5/best_model/config.json
+[2025-07-09 17:01:23,984][transformers.modeling_utils][INFO] - Model weights saved in ./results/bertimbau_large/C5/best_model/model.safetensors
+[2025-07-09 17:01:23,987][transformers.tokenization_utils_base][INFO] - tokenizer config file saved in ./results/bertimbau_large/C5/best_model/tokenizer_config.json
+[2025-07-09 17:01:23,987][transformers.tokenization_utils_base][INFO] - Special tokens file saved in ./results/bertimbau_large/C5/best_model/special_tokens_map.json
+[2025-07-09 17:01:23,999][__main__][INFO] - Model and tokenizer saved to ./results/bertimbau_large/C5/best_model
+[2025-07-09 17:01:24,003][__main__][INFO] - Fine Tuning Finished.
+[2025-07-09 17:01:24,515][__main__][INFO] - Total emissions: 0.0048 kg CO2eq

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "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,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e692aea3147ca3a6411ab7e83b5922a32c56013007aeeb6a47a368b4527625cb
+size 5841