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-base-portuguese-cased
+metrics:
+- accuracy
+- qwk
+library_name: transformers
+model-index:
+  - name: bert-base-portuguese-cased-encoder_classification-C2-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: 0.2490308302808302
+          - name: QWK
+            type: qwk
+            value: 0.3477835723598436
+          - name: Weighted Macro F1
+            type: f1
+            value: 0.3493722461113765
+---
+# Model ID: bert-base-portuguese-cased-encoder_classification-C2-essay_only
+## Results
+|                  |   test_data |
+|:-----------------|------------:|
+| eval_accuracy    |    0.347826 |
+| eval_RMSE        |   63.5199   |
+| eval_QWK         |    0.347784 |
+| eval_Macro_F1    |    0.249031 |
+| eval_Weighted_F1 |    0.349372 |
+| eval_Micro_F1    |    0.347826 |
+| eval_HDIV        |    0.115942 |
+        

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": 768,
+  "id2label": {
+    "0": 0,
+    "1": 40,
+    "2": 80,
+    "3": 120,
+    "4": 160,
+    "5": 200
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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": 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": "4.53.1",
+  "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
+2025-07-09T16:34:51,jbcs2025,fd63b1ba-b0a5-4e24-95eb-9ad49bc1882a,bert-base-portuguese-cased-encoder_classification-C2-essay_only,82.2578282339964,0.0016470799263036229,2.0023382110432377e-05,45.11863636363636,210.4038427300964,58.0,0.0009896148093088753,0.004555671700089192,0.0013009159500592634,0.006846202459457331,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
+1.7808504104614258,0.0022,0.1893939393939394,95.6635518445513,0.0,0.34090909090909094,0.06369426751592357,0.1893939393939394,0.06031654120826095,0,131,0,1,25,0,107,0,0,132,0,0,0,71,0,61,0,102,0,30,0,117,0,15,0.7765,169.985,11.59,-1,validation_before_training,2025-07-09 16:33:37,bert-base-portuguese-cased-encoder_classification-C2-essay_only
+1.6876201629638672,0.0022,0.3333333333333333,60.201681240995455,0.397729353598242,0.06060606060606055,0.20920999173426358,0.3333333333333333,0.33920595438689,0,131,0,1,7,84,23,18,0,124,8,0,23,52,19,38,4,94,8,26,10,87,30,5,0.3941,334.952,22.838,10.0,validation_after_training,2025-07-09 16:33:37,bert-base-portuguese-cased-encoder_classification-C2-essay_only
+1.7175557613372803,0.0022,0.34782608695652173,63.519938670433646,0.3477835723598436,0.1159420289855072,0.24903083028083028,0.34782608695652173,0.34937224611137657,0,137,0,1,17,70,33,18,1,124,9,4,19,66,21,32,6,92,20,20,5,111,7,15,0.3923,351.73,22.939,10.0,test_results,2025-07-09 16:33:37,bert-base-portuguese-cased-encoder_classification-C2-essay_only

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82cf240e9af36a107c9e8ad3f6a630ed12113f2548f820af2331c86eff1d0b44
+size 435734528

run_experiment.log

@@ -0,0 +1,394 @@
+[2025-07-09 16:33:25,901][__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-base-portuguese-cased
+    type: encoder_classification
+    num_labels: 6
+    output_dir: ./results/
+    logging_dir: ./logs/
+    best_model_dir: ./results/best_model
+  tokenizer:
+    name: neuralmind/bert-base-portuguese-cased
+  dataset:
+    grade_index: 1
+    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 16:33:29,741][__main__][INFO] - GPU 0: NVIDIA RTX A6000 | TDP ≈ 300 W
+[2025-07-09 16:33:29,741][__main__][INFO] - Starting the Fine Tuning training process.
+[2025-07-09 16:33:34,824][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /tmp/models--neuralmind--bert-base-portuguese-cased/snapshots/94d69c95f98f7d5b2a8700c420230ae10def0baa/config.json
+[2025-07-09 16:33:34,825][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": 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",
+  "transformers_version": "4.53.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 29794
+}
+
+[2025-07-09 16:33:35,020][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /tmp/models--neuralmind--bert-base-portuguese-cased/snapshots/94d69c95f98f7d5b2a8700c420230ae10def0baa/config.json
+[2025-07-09 16:33:35,021][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": 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",
+  "transformers_version": "4.53.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 29794
+}
+
+[2025-07-09 16:33:35,219][transformers.tokenization_utils_base][INFO] - loading file vocab.txt from cache at /tmp/models--neuralmind--bert-base-portuguese-cased/snapshots/94d69c95f98f7d5b2a8700c420230ae10def0baa/vocab.txt
+[2025-07-09 16:33:35,219][transformers.tokenization_utils_base][INFO] - loading file tokenizer.json from cache at None
+[2025-07-09 16:33:35,219][transformers.tokenization_utils_base][INFO] - loading file added_tokens.json from cache at /tmp/models--neuralmind--bert-base-portuguese-cased/snapshots/94d69c95f98f7d5b2a8700c420230ae10def0baa/added_tokens.json
+[2025-07-09 16:33:35,219][transformers.tokenization_utils_base][INFO] - loading file special_tokens_map.json from cache at /tmp/models--neuralmind--bert-base-portuguese-cased/snapshots/94d69c95f98f7d5b2a8700c420230ae10def0baa/special_tokens_map.json
+[2025-07-09 16:33:35,219][transformers.tokenization_utils_base][INFO] - loading file tokenizer_config.json from cache at /tmp/models--neuralmind--bert-base-portuguese-cased/snapshots/94d69c95f98f7d5b2a8700c420230ae10def0baa/tokenizer_config.json
+[2025-07-09 16:33:35,219][transformers.tokenization_utils_base][INFO] - loading file chat_template.jinja from cache at None
+[2025-07-09 16:33:35,219][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /tmp/models--neuralmind--bert-base-portuguese-cased/snapshots/94d69c95f98f7d5b2a8700c420230ae10def0baa/config.json
+[2025-07-09 16:33:35,220][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": 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",
+  "transformers_version": "4.53.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 29794
+}
+
+[2025-07-09 16:33:35,250][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /tmp/models--neuralmind--bert-base-portuguese-cased/snapshots/94d69c95f98f7d5b2a8700c420230ae10def0baa/config.json
+[2025-07-09 16:33:35,250][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": 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",
+  "transformers_version": "4.53.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 29794
+}
+
+[2025-07-09 16:33:35,268][__main__][INFO] - Tokenizer function parameters- Padding:longest; Truncation: True; Use Full Context: False
+[2025-07-09 16:33:35,890][__main__][INFO] - 
+Token statistics for 'train' split:
+[2025-07-09 16:33:35,890][__main__][INFO] -   Total examples: 500
+[2025-07-09 16:33:35,890][__main__][INFO] -   Min tokens: 512
+[2025-07-09 16:33:35,890][__main__][INFO] -   Max tokens: 512
+[2025-07-09 16:33:35,891][__main__][INFO] -   Avg tokens: 512.00
+[2025-07-09 16:33:35,891][__main__][INFO] -   Std tokens: 0.00
+[2025-07-09 16:33:35,983][__main__][INFO] - 
+Token statistics for 'validation' split:
+[2025-07-09 16:33:35,983][__main__][INFO] -   Total examples: 132
+[2025-07-09 16:33:35,983][__main__][INFO] -   Min tokens: 512
+[2025-07-09 16:33:35,983][__main__][INFO] -   Max tokens: 512
+[2025-07-09 16:33:35,983][__main__][INFO] -   Avg tokens: 512.00
+[2025-07-09 16:33:35,983][__main__][INFO] -   Std tokens: 0.00
+[2025-07-09 16:33:36,082][__main__][INFO] - 
+Token statistics for 'test' split:
+[2025-07-09 16:33:36,083][__main__][INFO] -   Total examples: 138
+[2025-07-09 16:33:36,083][__main__][INFO] -   Min tokens: 512
+[2025-07-09 16:33:36,083][__main__][INFO] -   Max tokens: 512
+[2025-07-09 16:33:36,083][__main__][INFO] -   Avg tokens: 512.00
+[2025-07-09 16:33:36,083][__main__][INFO] -   Std tokens: 0.00
+[2025-07-09 16:33:36,083][__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 16:33:36,083][__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 16:33:36,300][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /tmp/models--neuralmind--bert-base-portuguese-cased/snapshots/94d69c95f98f7d5b2a8700c420230ae10def0baa/config.json
+[2025-07-09 16:33:36,301][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": 768,
+  "id2label": {
+    "0": 0,
+    "1": 40,
+    "2": 80,
+    "3": 120,
+    "4": 160,
+    "5": 200
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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": 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",
+  "transformers_version": "4.53.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 29794
+}
+
+[2025-07-09 16:33:36,719][transformers.modeling_utils][INFO] - loading weights file pytorch_model.bin from cache at /tmp/models--neuralmind--bert-base-portuguese-cased/snapshots/94d69c95f98f7d5b2a8700c420230ae10def0baa/pytorch_model.bin
+[2025-07-09 16:33:36,846][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 16:33:36,846][transformers.modeling_utils][INFO] - Instantiating BertForSequenceClassification model under default dtype torch.float32.
+[2025-07-09 16:33:36,911][transformers.safetensors_conversion][INFO] - Attempting to create safetensors variant
+[2025-07-09 16:33:37,672][transformers.safetensors_conversion][INFO] - Safetensors PR exists
+[2025-07-09 16:33:37,900][transformers.modeling_utils][INFO] - Some weights of the model checkpoint at neuralmind/bert-base-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 16:33:37,901][transformers.modeling_utils][WARNING] - Some weights of BertForSequenceClassification were not initialized from the model checkpoint at neuralmind/bert-base-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 16:33:37,907][transformers.training_args][INFO] - PyTorch: setting up devices
+[2025-07-09 16:33:37,929][__main__][INFO] - Total steps: 620. Number of warmup steps: 62
+[2025-07-09 16:33:37,937][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 16:33:37,961][transformers.trainer][INFO] - Using auto half precision backend
+[2025-07-09 16:33:37,964][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: essay_text, reference, essay_year, grades, id, supporting_text, prompt, id_prompt. If essay_text, reference, essay_year, grades, id, supporting_text, prompt, id_prompt are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 16:33:37,969][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 16:33:37,969][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 16:33:37,969][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 16:33:39,133][transformers.trainer][INFO] - The following columns in the Training set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: essay_text, reference, essay_year, grades, id, supporting_text, prompt, id_prompt. If essay_text, reference, essay_year, grades, id, supporting_text, prompt, id_prompt are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 16:33:39,143][transformers.trainer][INFO] - ***** Running training *****
+[2025-07-09 16:33:39,143][transformers.trainer][INFO] -   Num examples = 500
+[2025-07-09 16:33:39,143][transformers.trainer][INFO] -   Num Epochs = 20
+[2025-07-09 16:33:39,143][transformers.trainer][INFO] -   Instantaneous batch size per device = 16
+[2025-07-09 16:33:39,143][transformers.trainer][INFO] -   Total train batch size (w. parallel, distributed & accumulation) = 16
+[2025-07-09 16:33:39,143][transformers.trainer][INFO] -   Gradient Accumulation steps = 1
+[2025-07-09 16:33:39,143][transformers.trainer][INFO] -   Total optimization steps = 640
+[2025-07-09 16:33:39,143][transformers.trainer][INFO] -   Number of trainable parameters = 108,927,750
+[2025-07-09 16:33:43,844][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: essay_text, reference, essay_year, grades, id, supporting_text, prompt, id_prompt. If essay_text, reference, essay_year, grades, id, supporting_text, prompt, id_prompt are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 16:33:43,847][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 16:33:43,847][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 16:33:43,847][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 16:33:44,238][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-32
+[2025-07-09 16:33:44,240][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-32/config.json
+[2025-07-09 16:33:45,191][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-32/model.safetensors
+[2025-07-09 16:33:50,697][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: essay_text, reference, essay_year, grades, id, supporting_text, prompt, id_prompt. If essay_text, reference, essay_year, grades, id, supporting_text, prompt, id_prompt are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 16:33:50,700][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 16:33:50,701][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 16:33:50,701][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 16:33:51,122][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-64
+[2025-07-09 16:33:51,123][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-64/config.json
+[2025-07-09 16:33:51,996][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-64/model.safetensors
+[2025-07-09 16:33:53,125][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-32] due to args.save_total_limit
+[2025-07-09 16:33:57,709][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: essay_text, reference, essay_year, grades, id, supporting_text, prompt, id_prompt. If essay_text, reference, essay_year, grades, id, supporting_text, prompt, id_prompt are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 16:33:57,711][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 16:33:57,712][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 16:33:57,712][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 16:33:58,097][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-96
+[2025-07-09 16:33:58,098][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-96/config.json
+[2025-07-09 16:33:58,892][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-96/model.safetensors
+[2025-07-09 16:34:04,225][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: essay_text, reference, essay_year, grades, id, supporting_text, prompt, id_prompt. If essay_text, reference, essay_year, grades, id, supporting_text, prompt, id_prompt are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 16:34:04,229][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 16:34:04,229][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 16:34:04,229][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 16:34:04,615][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-128
+[2025-07-09 16:34:04,616][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-128/config.json
+[2025-07-09 16:34:05,587][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-128/model.safetensors
+[2025-07-09 16:34:06,570][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-64] due to args.save_total_limit
+[2025-07-09 16:34:06,664][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-96] due to args.save_total_limit
+[2025-07-09 16:34:11,268][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: essay_text, reference, essay_year, grades, id, supporting_text, prompt, id_prompt. If essay_text, reference, essay_year, grades, id, supporting_text, prompt, id_prompt are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 16:34:11,271][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 16:34:11,271][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 16:34:11,271][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 16:34:11,660][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-160
+[2025-07-09 16:34:11,662][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-160/config.json
+[2025-07-09 16:34:12,471][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-160/model.safetensors
+[2025-07-09 16:34:13,431][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-128] due to args.save_total_limit
+[2025-07-09 16:34:18,058][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: essay_text, reference, essay_year, grades, id, supporting_text, prompt, id_prompt. If essay_text, reference, essay_year, grades, id, supporting_text, prompt, id_prompt are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 16:34:18,060][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 16:34:18,060][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 16:34:18,060][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 16:34:18,451][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-192
+[2025-07-09 16:34:18,453][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-192/config.json
+[2025-07-09 16:34:19,471][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-192/model.safetensors
+[2025-07-09 16:34:25,567][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: essay_text, reference, essay_year, grades, id, supporting_text, prompt, id_prompt. If essay_text, reference, essay_year, grades, id, supporting_text, prompt, id_prompt are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 16:34:25,570][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 16:34:25,570][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 16:34:25,570][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 16:34:25,964][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-224
+[2025-07-09 16:34:25,966][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-224/config.json
+[2025-07-09 16:34:27,025][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-224/model.safetensors
+[2025-07-09 16:34:27,806][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-192] due to args.save_total_limit
+[2025-07-09 16:34:32,442][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: essay_text, reference, essay_year, grades, id, supporting_text, prompt, id_prompt. If essay_text, reference, essay_year, grades, id, supporting_text, prompt, id_prompt are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 16:34:32,445][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 16:34:32,445][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 16:34:32,445][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 16:34:32,834][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-256
+[2025-07-09 16:34:32,835][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-256/config.json
+[2025-07-09 16:34:33,763][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-256/model.safetensors
+[2025-07-09 16:34:34,710][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-224] due to args.save_total_limit
+[2025-07-09 16:34:39,399][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: essay_text, reference, essay_year, grades, id, supporting_text, prompt, id_prompt. If essay_text, reference, essay_year, grades, id, supporting_text, prompt, id_prompt are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 16:34:39,401][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 16:34:39,402][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 16:34:39,402][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 16:34:39,809][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-288
+[2025-07-09 16:34:39,810][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-288/config.json
+[2025-07-09 16:34:40,771][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-288/model.safetensors
+[2025-07-09 16:34:41,710][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-256] due to args.save_total_limit
+[2025-07-09 16:34:46,344][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: essay_text, reference, essay_year, grades, id, supporting_text, prompt, id_prompt. If essay_text, reference, essay_year, grades, id, supporting_text, prompt, id_prompt are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 16:34:46,347][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 16:34:46,347][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 16:34:46,347][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 16:34:46,736][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-320
+[2025-07-09 16:34:46,737][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-320/config.json
+[2025-07-09 16:34:47,962][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-320/model.safetensors
+[2025-07-09 16:34:48,900][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-288] due to args.save_total_limit
+[2025-07-09 16:34:49,006][transformers.trainer][INFO] - 
+
+Training completed. Do not forget to share your model on huggingface.co/models =)
+
+
+[2025-07-09 16:34:49,006][transformers.trainer][INFO] - Loading best model from /workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-160 (score: 0.397729353598242).
+[2025-07-09 16:34:49,183][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-09/16-33-25/results/checkpoint-320] due to args.save_total_limit
+[2025-07-09 16:34:49,284][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: essay_text, reference, essay_year, grades, id, supporting_text, prompt, id_prompt. If essay_text, reference, essay_year, grades, id, supporting_text, prompt, id_prompt are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 16:34:49,287][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 16:34:49,287][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-09 16:34:49,287][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 16:34:49,688][__main__][INFO] - Training completed successfully.
+[2025-07-09 16:34:49,688][__main__][INFO] - Running on Test
+[2025-07-09 16:34:49,688][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `BertForSequenceClassification.forward` and have been ignored: essay_text, reference, essay_year, grades, id, supporting_text, prompt, id_prompt. If essay_text, reference, essay_year, grades, id, supporting_text, prompt, id_prompt are not expected by `BertForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-09 16:34:49,690][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-09 16:34:49,690][transformers.trainer][INFO] -   Num examples = 138
+[2025-07-09 16:34:49,690][transformers.trainer][INFO] -   Batch size = 16
+[2025-07-09 16:34:50,088][__main__][INFO] - Test metrics: {'eval_loss': 1.7175557613372803, 'eval_model_preparation_time': 0.0022, 'eval_accuracy': 0.34782608695652173, 'eval_RMSE': 63.519938670433646, 'eval_QWK': 0.3477835723598436, 'eval_HDIV': 0.1159420289855072, 'eval_Macro_F1': 0.24903083028083028, 'eval_Micro_F1': 0.34782608695652173, 'eval_Weighted_F1': 0.34937224611137657, 'eval_TP_0': 0, 'eval_TN_0': 137, 'eval_FP_0': 0, 'eval_FN_0': 1, 'eval_TP_1': 17, 'eval_TN_1': 70, 'eval_FP_1': 33, 'eval_FN_1': 18, 'eval_TP_2': 1, 'eval_TN_2': 124, 'eval_FP_2': 9, 'eval_FN_2': 4, 'eval_TP_3': 19, 'eval_TN_3': 66, 'eval_FP_3': 21, 'eval_FN_3': 32, 'eval_TP_4': 6, 'eval_TN_4': 92, 'eval_FP_4': 20, 'eval_FN_4': 20, 'eval_TP_5': 5, 'eval_TN_5': 111, 'eval_FP_5': 7, 'eval_FN_5': 15, 'eval_runtime': 0.3923, 'eval_samples_per_second': 351.73, 'eval_steps_per_second': 22.939, 'epoch': 10.0}
+[2025-07-09 16:34:50,089][transformers.trainer][INFO] - Saving model checkpoint to ./results/best_model
+[2025-07-09 16:34:50,091][transformers.configuration_utils][INFO] - Configuration saved in ./results/best_model/config.json
+[2025-07-09 16:34:50,968][transformers.modeling_utils][INFO] - Model weights saved in ./results/best_model/model.safetensors
+[2025-07-09 16:34:50,970][transformers.tokenization_utils_base][INFO] - tokenizer config file saved in ./results/best_model/tokenizer_config.json
+[2025-07-09 16:34:50,970][transformers.tokenization_utils_base][INFO] - Special tokens file saved in ./results/best_model/special_tokens_map.json
+[2025-07-09 16:34:50,982][__main__][INFO] - Model and tokenizer saved to ./results/best_model
+[2025-07-09 16:34:50,986][__main__][INFO] - Fine Tuning Finished.
+[2025-07-09 16:34:51,496][__main__][INFO] - Total emissions: 0.0016 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:e5a1cf317cea6294f76b2498e37e016ea60bc65f19ee6fc421882f88fdcf04c7
+size 5777