run_experiment.log

[2025-07-10 19:36:14,254][__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: PORTULAN/albertina-1b5-portuguese-ptbr-encoder
    type: encoder_classification
    num_labels: 6
    output_dir: ./results/
    logging_dir: ./logs/
    best_model_dir: ./results/best_model
  tokenizer:
    name: PORTULAN/albertina-1b5-portuguese-ptbr-encoder
  dataset:
    grade_index: 3
    use_full_context: false
  training_params:
    weight_decay: 0.01
    warmup_ratio: 0.1
    learning_rate: 5.0e-05
    train_batch_size: 4
    eval_batch_size: 4
    gradient_accumulation_steps: 4
    gradient_checkpointing: false

[2025-07-10 19:36:18,158][__main__][INFO] - GPU 0: NVIDIA RTX A6000 | TDP ≈ 300 W
[2025-07-10 19:36:18,158][__main__][INFO] - Starting the Fine Tuning training process.
[2025-07-10 19:36:23,915][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /tmp/models--PORTULAN--albertina-1b5-portuguese-ptbr-encoder/snapshots/b22008e5096af9c398b75762d4e28e5008762916/config.json
[2025-07-10 19:36:23,918][transformers.configuration_utils][INFO] - Model config DebertaV2Config {
  "architectures": [
    "DebertaV2ForMaskedLM"
  ],
  "attention_head_size": 64,
  "attention_probs_dropout_prob": 0.1,
  "conv_act": "gelu",
  "conv_kernel_size": 3,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 1536,
  "initializer_range": 0.02,
  "intermediate_size": 6144,
  "layer_norm_eps": 1e-07,
  "legacy": true,
  "max_position_embeddings": 512,
  "max_relative_positions": -1,
  "model_type": "deberta-v2",
  "norm_rel_ebd": "layer_norm",
  "num_attention_heads": 24,
  "num_hidden_layers": 48,
  "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": "bfloat16",
  "transformers_version": "4.53.1",
  "type_vocab_size": 0,
  "vocab_size": 128100
}

[2025-07-10 19:36:24,341][transformers.tokenization_utils_base][INFO] - loading file spm.model from cache at /tmp/models--PORTULAN--albertina-1b5-portuguese-ptbr-encoder/snapshots/b22008e5096af9c398b75762d4e28e5008762916/spm.model
[2025-07-10 19:36:24,341][transformers.tokenization_utils_base][INFO] - loading file tokenizer.json from cache at /tmp/models--PORTULAN--albertina-1b5-portuguese-ptbr-encoder/snapshots/b22008e5096af9c398b75762d4e28e5008762916/tokenizer.json
[2025-07-10 19:36:24,341][transformers.tokenization_utils_base][INFO] - loading file added_tokens.json from cache at /tmp/models--PORTULAN--albertina-1b5-portuguese-ptbr-encoder/snapshots/b22008e5096af9c398b75762d4e28e5008762916/added_tokens.json
[2025-07-10 19:36:24,341][transformers.tokenization_utils_base][INFO] - loading file special_tokens_map.json from cache at /tmp/models--PORTULAN--albertina-1b5-portuguese-ptbr-encoder/snapshots/b22008e5096af9c398b75762d4e28e5008762916/special_tokens_map.json
[2025-07-10 19:36:24,341][transformers.tokenization_utils_base][INFO] - loading file tokenizer_config.json from cache at /tmp/models--PORTULAN--albertina-1b5-portuguese-ptbr-encoder/snapshots/b22008e5096af9c398b75762d4e28e5008762916/tokenizer_config.json
[2025-07-10 19:36:24,341][transformers.tokenization_utils_base][INFO] - loading file chat_template.jinja from cache at None
[2025-07-10 19:36:24,583][__main__][INFO] - Tokenizer function parameters- Padding:longest; Truncation: True; Use Full Context: False
[2025-07-10 19:36:25,378][__main__][INFO] - 
Token statistics for 'train' split:
[2025-07-10 19:36:25,378][__main__][INFO] -   Total examples: 500
[2025-07-10 19:36:25,378][__main__][INFO] -   Min tokens: 512
[2025-07-10 19:36:25,378][__main__][INFO] -   Max tokens: 512
[2025-07-10 19:36:25,378][__main__][INFO] -   Avg tokens: 512.00
[2025-07-10 19:36:25,378][__main__][INFO] -   Std tokens: 0.00
[2025-07-10 19:36:25,473][__main__][INFO] - 
Token statistics for 'validation' split:
[2025-07-10 19:36:25,474][__main__][INFO] -   Total examples: 132
[2025-07-10 19:36:25,474][__main__][INFO] -   Min tokens: 512
[2025-07-10 19:36:25,474][__main__][INFO] -   Max tokens: 512
[2025-07-10 19:36:25,474][__main__][INFO] -   Avg tokens: 512.00
[2025-07-10 19:36:25,474][__main__][INFO] -   Std tokens: 0.00
[2025-07-10 19:36:25,573][__main__][INFO] - 
Token statistics for 'test' split:
[2025-07-10 19:36:25,574][__main__][INFO] -   Total examples: 138
[2025-07-10 19:36:25,574][__main__][INFO] -   Min tokens: 512
[2025-07-10 19:36:25,574][__main__][INFO] -   Max tokens: 512
[2025-07-10 19:36:25,574][__main__][INFO] -   Avg tokens: 512.00
[2025-07-10 19:36:25,574][__main__][INFO] -   Std tokens: 0.00
[2025-07-10 19:36:25,574][__main__][INFO] - If token statistics are the same (max, avg, min) keep in mind that this is due to batched tokenization and padding.
[2025-07-10 19:36:25,574][__main__][INFO] - Model max length: 512. If it is the same as stats, then there is a high chance that sequences are being truncated.
[2025-07-10 19:36:25,776][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /tmp/models--PORTULAN--albertina-1b5-portuguese-ptbr-encoder/snapshots/b22008e5096af9c398b75762d4e28e5008762916/config.json
[2025-07-10 19:36:25,777][transformers.configuration_utils][INFO] - Model config DebertaV2Config {
  "architectures": [
    "DebertaV2ForMaskedLM"
  ],
  "attention_head_size": 64,
  "attention_probs_dropout_prob": 0.1,
  "conv_act": "gelu",
  "conv_kernel_size": 3,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 1536,
  "id2label": {
    "0": 0,
    "1": 40,
    "2": 80,
    "3": 120,
    "4": 160,
    "5": 200
  },
  "initializer_range": 0.02,
  "intermediate_size": 6144,
  "label2id": {
    "0": 0,
    "40": 1,
    "80": 2,
    "120": 3,
    "160": 4,
    "200": 5
  },
  "layer_norm_eps": 1e-07,
  "legacy": true,
  "max_position_embeddings": 512,
  "max_relative_positions": -1,
  "model_type": "deberta-v2",
  "norm_rel_ebd": "layer_norm",
  "num_attention_heads": 24,
  "num_hidden_layers": 48,
  "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": "bfloat16",
  "transformers_version": "4.53.1",
  "type_vocab_size": 0,
  "vocab_size": 128100
}

[2025-07-10 19:36:26,345][transformers.modeling_utils][INFO] - loading weights file pytorch_model.bin from cache at /tmp/models--PORTULAN--albertina-1b5-portuguese-ptbr-encoder/snapshots/b22008e5096af9c398b75762d4e28e5008762916/pytorch_model.bin
[2025-07-10 19:36:26,346][transformers.modeling_utils][INFO] - Will use torch_dtype=torch.bfloat16 as defined in model's config object
[2025-07-10 19:36:26,346][transformers.modeling_utils][INFO] - Instantiating DebertaV2ForSequenceClassification model under default dtype torch.bfloat16.
[2025-07-10 19:36:26,839][transformers.safetensors_conversion][INFO] - Attempting to create safetensors variant
[2025-07-10 19:36:27,622][transformers.safetensors_conversion][INFO] - Attempting to convert .bin model on the fly to safetensors.
[2025-07-10 19:46:29,883][transformers.modeling_utils][INFO] - Some weights of the model checkpoint at PORTULAN/albertina-1b5-portuguese-ptbr-encoder were not used when initializing DebertaV2ForSequenceClassification: ['cls.predictions.bias', 'cls.predictions.decoder.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']
- This IS expected if you are initializing DebertaV2ForSequenceClassification 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 DebertaV2ForSequenceClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
[2025-07-10 19:46:29,883][transformers.modeling_utils][WARNING] - Some weights of DebertaV2ForSequenceClassification were not initialized from the model checkpoint at PORTULAN/albertina-1b5-portuguese-ptbr-encoder and are newly initialized: ['classifier.bias', 'classifier.weight', 'pooler.dense.bias', 'pooler.dense.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
[2025-07-10 19:46:29,901][transformers.training_args][INFO] - PyTorch: setting up devices
[2025-07-10 19:46:29,924][__main__][INFO] - Total steps: 620. Number of warmup steps: 62
[2025-07-10 19:46:29,934][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.
[2025-07-10 19:46:29,961][transformers.trainer][INFO] - Using auto half precision backend
[2025-07-10 19:46:29,963][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `DebertaV2ForSequenceClassification.forward` and have been ignored: id, id_prompt, essay_text, grades, reference, supporting_text, prompt, essay_year. If id, id_prompt, essay_text, grades, reference, supporting_text, prompt, essay_year are not expected by `DebertaV2ForSequenceClassification.forward`,  you can safely ignore this message.
[2025-07-10 19:46:29,974][transformers.trainer][INFO] - 
***** Running Evaluation *****
[2025-07-10 19:46:29,974][transformers.trainer][INFO] -   Num examples = 132
[2025-07-10 19:46:29,974][transformers.trainer][INFO] -   Batch size = 4
[2025-07-10 19:46:39,340][transformers.trainer][INFO] - The following columns in the Training set don't have a corresponding argument in `DebertaV2ForSequenceClassification.forward` and have been ignored: id, id_prompt, essay_text, grades, reference, supporting_text, prompt, essay_year. If id, id_prompt, essay_text, grades, reference, supporting_text, prompt, essay_year are not expected by `DebertaV2ForSequenceClassification.forward`,  you can safely ignore this message.
[2025-07-10 19:46:39,370][transformers.trainer][INFO] - ***** Running training *****
[2025-07-10 19:46:39,370][transformers.trainer][INFO] -   Num examples = 500
[2025-07-10 19:46:39,370][transformers.trainer][INFO] -   Num Epochs = 20
[2025-07-10 19:46:39,370][transformers.trainer][INFO] -   Instantaneous batch size per device = 4
[2025-07-10 19:46:39,370][transformers.trainer][INFO] -   Total train batch size (w. parallel, distributed & accumulation) = 16
[2025-07-10 19:46:39,370][transformers.trainer][INFO] -   Gradient Accumulation steps = 4
[2025-07-10 19:46:39,370][transformers.trainer][INFO] -   Total optimization steps = 640
[2025-07-10 19:46:39,372][transformers.trainer][INFO] -   Number of trainable parameters = 1,566,919,686
[2025-07-10 19:53:34,212][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `DebertaV2ForSequenceClassification.forward` and have been ignored: id, id_prompt, essay_text, grades, reference, supporting_text, prompt, essay_year. If id, id_prompt, essay_text, grades, reference, supporting_text, prompt, essay_year are not expected by `DebertaV2ForSequenceClassification.forward`,  you can safely ignore this message.
[2025-07-10 19:53:34,217][transformers.trainer][INFO] - 
***** Running Evaluation *****
[2025-07-10 19:53:34,217][transformers.trainer][INFO] -   Num examples = 132
[2025-07-10 19:53:34,217][transformers.trainer][INFO] -   Batch size = 4
[2025-07-10 19:53:42,682][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-10/19-36-14/results/checkpoint-32
[2025-07-10 19:53:42,685][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-10/19-36-14/results/checkpoint-32/config.json
[2025-07-10 19:53:47,612][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-10/19-36-14/results/checkpoint-32/model.safetensors
[2025-07-10 20:00:50,376][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `DebertaV2ForSequenceClassification.forward` and have been ignored: id, id_prompt, essay_text, grades, reference, supporting_text, prompt, essay_year. If id, id_prompt, essay_text, grades, reference, supporting_text, prompt, essay_year are not expected by `DebertaV2ForSequenceClassification.forward`,  you can safely ignore this message.
[2025-07-10 20:00:50,380][transformers.trainer][INFO] - 
***** Running Evaluation *****
[2025-07-10 20:00:50,380][transformers.trainer][INFO] -   Num examples = 132
[2025-07-10 20:00:50,380][transformers.trainer][INFO] -   Batch size = 4
[2025-07-10 20:00:58,848][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-10/19-36-14/results/checkpoint-64
[2025-07-10 20:00:58,851][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-10/19-36-14/results/checkpoint-64/config.json
[2025-07-10 20:01:05,840][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-10/19-36-14/results/checkpoint-64/model.safetensors
[2025-07-10 20:01:14,738][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-10/19-36-14/results/checkpoint-32] due to args.save_total_limit
[2025-07-10 20:08:11,024][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `DebertaV2ForSequenceClassification.forward` and have been ignored: id, id_prompt, essay_text, grades, reference, supporting_text, prompt, essay_year. If id, id_prompt, essay_text, grades, reference, supporting_text, prompt, essay_year are not expected by `DebertaV2ForSequenceClassification.forward`,  you can safely ignore this message.
[2025-07-10 20:08:11,028][transformers.trainer][INFO] - 
***** Running Evaluation *****
[2025-07-10 20:08:11,028][transformers.trainer][INFO] -   Num examples = 132
[2025-07-10 20:08:11,028][transformers.trainer][INFO] -   Batch size = 4
[2025-07-10 20:08:19,486][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-10/19-36-14/results/checkpoint-96
[2025-07-10 20:08:19,488][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-10/19-36-14/results/checkpoint-96/config.json
[2025-07-10 20:08:25,452][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-10/19-36-14/results/checkpoint-96/model.safetensors
[2025-07-10 20:08:31,426][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-10/19-36-14/results/checkpoint-64] due to args.save_total_limit
[2025-07-10 20:15:28,017][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `DebertaV2ForSequenceClassification.forward` and have been ignored: id, id_prompt, essay_text, grades, reference, supporting_text, prompt, essay_year. If id, id_prompt, essay_text, grades, reference, supporting_text, prompt, essay_year are not expected by `DebertaV2ForSequenceClassification.forward`,  you can safely ignore this message.
[2025-07-10 20:15:28,020][transformers.trainer][INFO] - 
***** Running Evaluation *****
[2025-07-10 20:15:28,021][transformers.trainer][INFO] -   Num examples = 132
[2025-07-10 20:15:28,021][transformers.trainer][INFO] -   Batch size = 4
[2025-07-10 20:15:36,480][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-10/19-36-14/results/checkpoint-128
[2025-07-10 20:15:36,483][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-10/19-36-14/results/checkpoint-128/config.json
[2025-07-10 20:15:42,131][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-10/19-36-14/results/checkpoint-128/model.safetensors
[2025-07-10 20:15:48,299][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-10/19-36-14/results/checkpoint-96] due to args.save_total_limit
[2025-07-10 20:22:51,284][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `DebertaV2ForSequenceClassification.forward` and have been ignored: id, id_prompt, essay_text, grades, reference, supporting_text, prompt, essay_year. If id, id_prompt, essay_text, grades, reference, supporting_text, prompt, essay_year are not expected by `DebertaV2ForSequenceClassification.forward`,  you can safely ignore this message.
[2025-07-10 20:22:51,288][transformers.trainer][INFO] - 
***** Running Evaluation *****
[2025-07-10 20:22:51,289][transformers.trainer][INFO] -   Num examples = 132
[2025-07-10 20:22:51,289][transformers.trainer][INFO] -   Batch size = 4
[2025-07-10 20:22:59,747][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-10/19-36-14/results/checkpoint-160
[2025-07-10 20:22:59,749][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-10/19-36-14/results/checkpoint-160/config.json
[2025-07-10 20:23:05,082][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-10/19-36-14/results/checkpoint-160/model.safetensors
[2025-07-10 20:23:11,794][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-10/19-36-14/results/checkpoint-128] due to args.save_total_limit
[2025-07-10 20:30:08,320][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `DebertaV2ForSequenceClassification.forward` and have been ignored: id, id_prompt, essay_text, grades, reference, supporting_text, prompt, essay_year. If id, id_prompt, essay_text, grades, reference, supporting_text, prompt, essay_year are not expected by `DebertaV2ForSequenceClassification.forward`,  you can safely ignore this message.
[2025-07-10 20:30:08,324][transformers.trainer][INFO] - 
***** Running Evaluation *****
[2025-07-10 20:30:08,324][transformers.trainer][INFO] -   Num examples = 132
[2025-07-10 20:30:08,324][transformers.trainer][INFO] -   Batch size = 4
[2025-07-10 20:30:16,781][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-10/19-36-14/results/checkpoint-192
[2025-07-10 20:30:16,783][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-10/19-36-14/results/checkpoint-192/config.json
[2025-07-10 20:30:23,491][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-10/19-36-14/results/checkpoint-192/model.safetensors
[2025-07-10 20:37:29,068][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `DebertaV2ForSequenceClassification.forward` and have been ignored: id, id_prompt, essay_text, grades, reference, supporting_text, prompt, essay_year. If id, id_prompt, essay_text, grades, reference, supporting_text, prompt, essay_year are not expected by `DebertaV2ForSequenceClassification.forward`,  you can safely ignore this message.
[2025-07-10 20:37:29,088][transformers.trainer][INFO] - 
***** Running Evaluation *****
[2025-07-10 20:37:29,088][transformers.trainer][INFO] -   Num examples = 132
[2025-07-10 20:37:29,088][transformers.trainer][INFO] -   Batch size = 4
[2025-07-10 20:37:37,590][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-10/19-36-14/results/checkpoint-224
[2025-07-10 20:37:37,595][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-10/19-36-14/results/checkpoint-224/config.json
[2025-07-10 20:37:44,875][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-10/19-36-14/results/checkpoint-224/model.safetensors
[2025-07-10 20:37:54,540][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-10/19-36-14/results/checkpoint-192] due to args.save_total_limit
[2025-07-10 20:44:51,754][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `DebertaV2ForSequenceClassification.forward` and have been ignored: id, id_prompt, essay_text, grades, reference, supporting_text, prompt, essay_year. If id, id_prompt, essay_text, grades, reference, supporting_text, prompt, essay_year are not expected by `DebertaV2ForSequenceClassification.forward`,  you can safely ignore this message.
[2025-07-10 20:44:51,758][transformers.trainer][INFO] - 
***** Running Evaluation *****
[2025-07-10 20:44:51,759][transformers.trainer][INFO] -   Num examples = 132
[2025-07-10 20:44:51,759][transformers.trainer][INFO] -   Batch size = 4
[2025-07-10 20:45:00,246][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-10/19-36-14/results/checkpoint-256
[2025-07-10 20:45:00,249][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-10/19-36-14/results/checkpoint-256/config.json
[2025-07-10 20:45:06,783][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-10/19-36-14/results/checkpoint-256/model.safetensors
[2025-07-10 20:45:18,812][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-10/19-36-14/results/checkpoint-224] due to args.save_total_limit
[2025-07-10 20:52:15,059][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `DebertaV2ForSequenceClassification.forward` and have been ignored: id, id_prompt, essay_text, grades, reference, supporting_text, prompt, essay_year. If id, id_prompt, essay_text, grades, reference, supporting_text, prompt, essay_year are not expected by `DebertaV2ForSequenceClassification.forward`,  you can safely ignore this message.
[2025-07-10 20:52:15,063][transformers.trainer][INFO] - 
***** Running Evaluation *****
[2025-07-10 20:52:15,063][transformers.trainer][INFO] -   Num examples = 132
[2025-07-10 20:52:15,063][transformers.trainer][INFO] -   Batch size = 4
[2025-07-10 20:52:23,551][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-10/19-36-14/results/checkpoint-288
[2025-07-10 20:52:23,555][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-10/19-36-14/results/checkpoint-288/config.json
[2025-07-10 20:52:29,282][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-10/19-36-14/results/checkpoint-288/model.safetensors
[2025-07-10 20:52:35,051][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-10/19-36-14/results/checkpoint-256] due to args.save_total_limit
[2025-07-10 20:59:31,445][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `DebertaV2ForSequenceClassification.forward` and have been ignored: id, id_prompt, essay_text, grades, reference, supporting_text, prompt, essay_year. If id, id_prompt, essay_text, grades, reference, supporting_text, prompt, essay_year are not expected by `DebertaV2ForSequenceClassification.forward`,  you can safely ignore this message.
[2025-07-10 20:59:31,449][transformers.trainer][INFO] - 
***** Running Evaluation *****
[2025-07-10 20:59:31,449][transformers.trainer][INFO] -   Num examples = 132
[2025-07-10 20:59:31,449][transformers.trainer][INFO] -   Batch size = 4
[2025-07-10 20:59:39,922][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-10/19-36-14/results/checkpoint-320
[2025-07-10 20:59:39,924][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-10/19-36-14/results/checkpoint-320/config.json
[2025-07-10 20:59:45,701][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-10/19-36-14/results/checkpoint-320/model.safetensors
[2025-07-10 20:59:53,104][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-10/19-36-14/results/checkpoint-288] due to args.save_total_limit
[2025-07-10 20:59:53,579][transformers.trainer][INFO] - 

Training completed. Do not forget to share your model on huggingface.co/models =)


[2025-07-10 20:59:53,580][transformers.trainer][INFO] - Loading best model from /workspace/jbcs2025/outputs/2025-07-10/19-36-14/results/checkpoint-160 (score: 0.48744007670182166).
[2025-07-10 20:59:55,299][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-10/19-36-14/results/checkpoint-320] due to args.save_total_limit
[2025-07-10 20:59:55,974][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `DebertaV2ForSequenceClassification.forward` and have been ignored: id, id_prompt, essay_text, grades, reference, supporting_text, prompt, essay_year. If id, id_prompt, essay_text, grades, reference, supporting_text, prompt, essay_year are not expected by `DebertaV2ForSequenceClassification.forward`,  you can safely ignore this message.
[2025-07-10 20:59:55,979][transformers.trainer][INFO] - 
***** Running Evaluation *****
[2025-07-10 20:59:55,979][transformers.trainer][INFO] -   Num examples = 132
[2025-07-10 20:59:55,979][transformers.trainer][INFO] -   Batch size = 4
[2025-07-10 21:00:04,467][__main__][INFO] - Training completed successfully.
[2025-07-10 21:00:04,467][__main__][INFO] - Running on Test
[2025-07-10 21:00:04,468][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `DebertaV2ForSequenceClassification.forward` and have been ignored: id, id_prompt, essay_text, grades, reference, supporting_text, prompt, essay_year. If id, id_prompt, essay_text, grades, reference, supporting_text, prompt, essay_year are not expected by `DebertaV2ForSequenceClassification.forward`,  you can safely ignore this message.
[2025-07-10 21:00:04,471][transformers.trainer][INFO] - 
***** Running Evaluation *****
[2025-07-10 21:00:04,471][transformers.trainer][INFO] -   Num examples = 138
[2025-07-10 21:00:04,472][transformers.trainer][INFO] -   Batch size = 4
[2025-07-10 21:00:13,251][__main__][INFO] - Test metrics: {'eval_loss': 1.2863404750823975, 'eval_model_preparation_time': 0.0072, 'eval_accuracy': 0.6014492753623188, 'eval_RMSE': 27.662562992324986, 'eval_QWK': 0.543046357615894, 'eval_HDIV': 0.007246376811594235, 'eval_Macro_F1': 0.2974558904383466, 'eval_Micro_F1': 0.6014492753623188, 'eval_Weighted_F1': 0.5920471313301213, 'eval_TP_0': 0, 'eval_TN_0': 137, 'eval_FP_0': 0, 'eval_FN_0': 1, 'eval_TP_1': 0, 'eval_TN_1': 137, 'eval_FP_1': 0, 'eval_FN_1': 1, 'eval_TP_2': 3, 'eval_TN_2': 122, 'eval_FP_2': 7, 'eval_FN_2': 6, 'eval_TP_3': 60, 'eval_TN_3': 36, 'eval_FP_3': 26, 'eval_FN_3': 16, 'eval_TP_4': 18, 'eval_TN_4': 78, 'eval_FP_4': 14, 'eval_FN_4': 28, 'eval_TP_5': 2, 'eval_TN_5': 125, 'eval_FP_5': 8, 'eval_FN_5': 3, 'eval_runtime': 8.7703, 'eval_samples_per_second': 15.735, 'eval_steps_per_second': 3.991, 'epoch': 10.0}
[2025-07-10 21:00:13,252][transformers.trainer][INFO] - Saving model checkpoint to ./results/best_model
[2025-07-10 21:00:13,254][transformers.configuration_utils][INFO] - Configuration saved in ./results/best_model/config.json
[2025-07-10 21:00:18,583][transformers.modeling_utils][INFO] - Model weights saved in ./results/best_model/model.safetensors
[2025-07-10 21:00:18,588][transformers.tokenization_utils_base][INFO] - tokenizer config file saved in ./results/best_model/tokenizer_config.json
[2025-07-10 21:00:18,588][transformers.tokenization_utils_base][INFO] - Special tokens file saved in ./results/best_model/special_tokens_map.json
[2025-07-10 21:00:18,617][__main__][INFO] - Model and tokenizer saved to ./results/best_model
[2025-07-10 21:00:18,754][__main__][INFO] - Fine Tuning Finished.
[2025-07-10 21:00:19,271][__main__][INFO] - Total emissions: 0.1150 kg CO2eq