run_experiment.log

[2025-07-10 21:00:34,178][__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: 4
    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 21:00:38,379][__main__][INFO] - GPU 0: NVIDIA RTX A6000 | TDP ≈ 300 W
[2025-07-10 21:00:38,379][__main__][INFO] - Starting the Fine Tuning training process.
[2025-07-10 21:00:44,523][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 21:00:44,527][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 21:00:44,962][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 21:00:44,963][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 21:00:44,963][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 21:00:44,963][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 21:00:44,963][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 21:00:44,963][transformers.tokenization_utils_base][INFO] - loading file chat_template.jinja from cache at None
[2025-07-10 21:00:45,253][__main__][INFO] - Tokenizer function parameters- Padding:longest; Truncation: True; Use Full Context: False
[2025-07-10 21:00:46,121][__main__][INFO] - 
Token statistics for 'train' split:
[2025-07-10 21:00:46,122][__main__][INFO] -   Total examples: 500
[2025-07-10 21:00:46,122][__main__][INFO] -   Min tokens: 512
[2025-07-10 21:00:46,122][__main__][INFO] -   Max tokens: 512
[2025-07-10 21:00:46,122][__main__][INFO] -   Avg tokens: 512.00
[2025-07-10 21:00:46,122][__main__][INFO] -   Std tokens: 0.00
[2025-07-10 21:00:46,233][__main__][INFO] - 
Token statistics for 'validation' split:
[2025-07-10 21:00:46,233][__main__][INFO] -   Total examples: 132
[2025-07-10 21:00:46,233][__main__][INFO] -   Min tokens: 512
[2025-07-10 21:00:46,233][__main__][INFO] -   Max tokens: 512
[2025-07-10 21:00:46,233][__main__][INFO] -   Avg tokens: 512.00
[2025-07-10 21:00:46,233][__main__][INFO] -   Std tokens: 0.00
[2025-07-10 21:00:46,348][__main__][INFO] - 
Token statistics for 'test' split:
[2025-07-10 21:00:46,348][__main__][INFO] -   Total examples: 138
[2025-07-10 21:00:46,348][__main__][INFO] -   Min tokens: 512
[2025-07-10 21:00:46,348][__main__][INFO] -   Max tokens: 512
[2025-07-10 21:00:46,348][__main__][INFO] -   Avg tokens: 512.00
[2025-07-10 21:00:46,348][__main__][INFO] -   Std tokens: 0.00
[2025-07-10 21:00:46,348][__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 21:00:46,348][__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 21:00:46,677][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 21:00:46,678][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 21:00:47,103][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 21:00:47,104][transformers.modeling_utils][INFO] - Will use torch_dtype=torch.bfloat16 as defined in model's config object
[2025-07-10 21:00:47,104][transformers.modeling_utils][INFO] - Instantiating DebertaV2ForSequenceClassification model under default dtype torch.bfloat16.
[2025-07-10 21:00:47,365][transformers.safetensors_conversion][INFO] - Attempting to create safetensors variant
[2025-07-10 21:00:48,063][transformers.safetensors_conversion][INFO] - Attempting to convert .bin model on the fly to safetensors.
[2025-07-10 21:09:05,558][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 21:09:05,559][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 21:09:05,574][transformers.training_args][INFO] - PyTorch: setting up devices
[2025-07-10 21:09:05,596][__main__][INFO] - Total steps: 620. Number of warmup steps: 62
[2025-07-10 21:09:05,606][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 21:09:05,631][transformers.trainer][INFO] - Using auto half precision backend
[2025-07-10 21:09:05,634][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `DebertaV2ForSequenceClassification.forward` and have been ignored: reference, id_prompt, id, grades, prompt, essay_year, essay_text, supporting_text. If reference, id_prompt, id, grades, prompt, essay_year, essay_text, supporting_text are not expected by `DebertaV2ForSequenceClassification.forward`,  you can safely ignore this message.
[2025-07-10 21:09:05,645][transformers.trainer][INFO] - 
***** Running Evaluation *****
[2025-07-10 21:09:05,645][transformers.trainer][INFO] -   Num examples = 132
[2025-07-10 21:09:05,645][transformers.trainer][INFO] -   Batch size = 4
[2025-07-10 21:09:14,755][transformers.trainer][INFO] - The following columns in the Training set don't have a corresponding argument in `DebertaV2ForSequenceClassification.forward` and have been ignored: reference, id_prompt, id, grades, prompt, essay_year, essay_text, supporting_text. If reference, id_prompt, id, grades, prompt, essay_year, essay_text, supporting_text are not expected by `DebertaV2ForSequenceClassification.forward`,  you can safely ignore this message.
[2025-07-10 21:09:14,784][transformers.trainer][INFO] - ***** Running training *****
[2025-07-10 21:09:14,784][transformers.trainer][INFO] -   Num examples = 500
[2025-07-10 21:09:14,784][transformers.trainer][INFO] -   Num Epochs = 20
[2025-07-10 21:09:14,784][transformers.trainer][INFO] -   Instantaneous batch size per device = 4
[2025-07-10 21:09:14,784][transformers.trainer][INFO] -   Total train batch size (w. parallel, distributed & accumulation) = 16
[2025-07-10 21:09:14,784][transformers.trainer][INFO] -   Gradient Accumulation steps = 4
[2025-07-10 21:09:14,784][transformers.trainer][INFO] -   Total optimization steps = 640
[2025-07-10 21:09:14,786][transformers.trainer][INFO] -   Number of trainable parameters = 1,566,919,686
[2025-07-10 21:16:09,277][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `DebertaV2ForSequenceClassification.forward` and have been ignored: reference, id_prompt, id, grades, prompt, essay_year, essay_text, supporting_text. If reference, id_prompt, id, grades, prompt, essay_year, essay_text, supporting_text are not expected by `DebertaV2ForSequenceClassification.forward`,  you can safely ignore this message.
[2025-07-10 21:16:09,281][transformers.trainer][INFO] - 
***** Running Evaluation *****
[2025-07-10 21:16:09,281][transformers.trainer][INFO] -   Num examples = 132
[2025-07-10 21:16:09,281][transformers.trainer][INFO] -   Batch size = 4
[2025-07-10 21:16:17,735][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-10/21-00-34/results/checkpoint-32
[2025-07-10 21:16:17,737][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-10/21-00-34/results/checkpoint-32/config.json
[2025-07-10 21:16:22,808][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-10/21-00-34/results/checkpoint-32/model.safetensors
[2025-07-10 21:23:25,609][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `DebertaV2ForSequenceClassification.forward` and have been ignored: reference, id_prompt, id, grades, prompt, essay_year, essay_text, supporting_text. If reference, id_prompt, id, grades, prompt, essay_year, essay_text, supporting_text are not expected by `DebertaV2ForSequenceClassification.forward`,  you can safely ignore this message.
[2025-07-10 21:23:25,613][transformers.trainer][INFO] - 
***** Running Evaluation *****
[2025-07-10 21:23:25,613][transformers.trainer][INFO] -   Num examples = 132
[2025-07-10 21:23:25,613][transformers.trainer][INFO] -   Batch size = 4
[2025-07-10 21:23:34,061][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-10/21-00-34/results/checkpoint-64
[2025-07-10 21:23:34,063][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-10/21-00-34/results/checkpoint-64/config.json
[2025-07-10 21:23:41,883][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-10/21-00-34/results/checkpoint-64/model.safetensors
[2025-07-10 21:30:46,980][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `DebertaV2ForSequenceClassification.forward` and have been ignored: reference, id_prompt, id, grades, prompt, essay_year, essay_text, supporting_text. If reference, id_prompt, id, grades, prompt, essay_year, essay_text, supporting_text are not expected by `DebertaV2ForSequenceClassification.forward`,  you can safely ignore this message.
[2025-07-10 21:30:46,986][transformers.trainer][INFO] - 
***** Running Evaluation *****
[2025-07-10 21:30:46,987][transformers.trainer][INFO] -   Num examples = 132
[2025-07-10 21:30:46,987][transformers.trainer][INFO] -   Batch size = 4
[2025-07-10 21:30:55,465][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-10/21-00-34/results/checkpoint-96
[2025-07-10 21:30:55,468][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-10/21-00-34/results/checkpoint-96/config.json
[2025-07-10 21:31:06,174][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-10/21-00-34/results/checkpoint-96/model.safetensors
[2025-07-10 21:31:14,395][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-10/21-00-34/results/checkpoint-32] due to args.save_total_limit
[2025-07-10 21:31:14,883][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-10/21-00-34/results/checkpoint-64] due to args.save_total_limit
[2025-07-10 21:38:11,663][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `DebertaV2ForSequenceClassification.forward` and have been ignored: reference, id_prompt, id, grades, prompt, essay_year, essay_text, supporting_text. If reference, id_prompt, id, grades, prompt, essay_year, essay_text, supporting_text are not expected by `DebertaV2ForSequenceClassification.forward`,  you can safely ignore this message.
[2025-07-10 21:38:11,667][transformers.trainer][INFO] - 
***** Running Evaluation *****
[2025-07-10 21:38:11,668][transformers.trainer][INFO] -   Num examples = 132
[2025-07-10 21:38:11,668][transformers.trainer][INFO] -   Batch size = 4
[2025-07-10 21:38:20,154][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-10/21-00-34/results/checkpoint-128
[2025-07-10 21:38:20,156][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-10/21-00-34/results/checkpoint-128/config.json
[2025-07-10 21:38:25,954][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-10/21-00-34/results/checkpoint-128/model.safetensors
[2025-07-10 21:45:27,943][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `DebertaV2ForSequenceClassification.forward` and have been ignored: reference, id_prompt, id, grades, prompt, essay_year, essay_text, supporting_text. If reference, id_prompt, id, grades, prompt, essay_year, essay_text, supporting_text are not expected by `DebertaV2ForSequenceClassification.forward`,  you can safely ignore this message.
[2025-07-10 21:45:27,947][transformers.trainer][INFO] - 
***** Running Evaluation *****
[2025-07-10 21:45:27,947][transformers.trainer][INFO] -   Num examples = 132
[2025-07-10 21:45:27,947][transformers.trainer][INFO] -   Batch size = 4
[2025-07-10 21:45:36,427][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-10/21-00-34/results/checkpoint-160
[2025-07-10 21:45:36,430][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-10/21-00-34/results/checkpoint-160/config.json
[2025-07-10 21:45:41,780][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-10/21-00-34/results/checkpoint-160/model.safetensors
[2025-07-10 21:45:49,415][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-10/21-00-34/results/checkpoint-96] due to args.save_total_limit
[2025-07-10 21:45:50,073][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-10/21-00-34/results/checkpoint-128] due to args.save_total_limit
[2025-07-10 21:52:46,069][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `DebertaV2ForSequenceClassification.forward` and have been ignored: reference, id_prompt, id, grades, prompt, essay_year, essay_text, supporting_text. If reference, id_prompt, id, grades, prompt, essay_year, essay_text, supporting_text are not expected by `DebertaV2ForSequenceClassification.forward`,  you can safely ignore this message.
[2025-07-10 21:52:46,073][transformers.trainer][INFO] - 
***** Running Evaluation *****
[2025-07-10 21:52:46,073][transformers.trainer][INFO] -   Num examples = 132
[2025-07-10 21:52:46,073][transformers.trainer][INFO] -   Batch size = 4
[2025-07-10 21:52:54,526][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-10/21-00-34/results/checkpoint-192
[2025-07-10 21:52:54,529][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-10/21-00-34/results/checkpoint-192/config.json
[2025-07-10 21:52:59,508][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-10/21-00-34/results/checkpoint-192/model.safetensors
[2025-07-10 22:00:02,238][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `DebertaV2ForSequenceClassification.forward` and have been ignored: reference, id_prompt, id, grades, prompt, essay_year, essay_text, supporting_text. If reference, id_prompt, id, grades, prompt, essay_year, essay_text, supporting_text are not expected by `DebertaV2ForSequenceClassification.forward`,  you can safely ignore this message.
[2025-07-10 22:00:02,242][transformers.trainer][INFO] - 
***** Running Evaluation *****
[2025-07-10 22:00:02,242][transformers.trainer][INFO] -   Num examples = 132
[2025-07-10 22:00:02,242][transformers.trainer][INFO] -   Batch size = 4
[2025-07-10 22:00:10,700][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-10/21-00-34/results/checkpoint-224
[2025-07-10 22:00:10,702][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-10/21-00-34/results/checkpoint-224/config.json
[2025-07-10 22:00:15,749][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-10/21-00-34/results/checkpoint-224/model.safetensors
[2025-07-10 22:00:23,204][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-10/21-00-34/results/checkpoint-192] due to args.save_total_limit
[2025-07-10 22:07:19,184][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `DebertaV2ForSequenceClassification.forward` and have been ignored: reference, id_prompt, id, grades, prompt, essay_year, essay_text, supporting_text. If reference, id_prompt, id, grades, prompt, essay_year, essay_text, supporting_text are not expected by `DebertaV2ForSequenceClassification.forward`,  you can safely ignore this message.
[2025-07-10 22:07:19,188][transformers.trainer][INFO] - 
***** Running Evaluation *****
[2025-07-10 22:07:19,188][transformers.trainer][INFO] -   Num examples = 132
[2025-07-10 22:07:19,188][transformers.trainer][INFO] -   Batch size = 4
[2025-07-10 22:07:27,637][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-10/21-00-34/results/checkpoint-256
[2025-07-10 22:07:27,639][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-10/21-00-34/results/checkpoint-256/config.json
[2025-07-10 22:07:33,184][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-10/21-00-34/results/checkpoint-256/model.safetensors
[2025-07-10 22:07:42,239][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-10/21-00-34/results/checkpoint-160] due to args.save_total_limit
[2025-07-10 22:07:42,866][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-10/21-00-34/results/checkpoint-224] due to args.save_total_limit
[2025-07-10 22:14:38,764][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `DebertaV2ForSequenceClassification.forward` and have been ignored: reference, id_prompt, id, grades, prompt, essay_year, essay_text, supporting_text. If reference, id_prompt, id, grades, prompt, essay_year, essay_text, supporting_text are not expected by `DebertaV2ForSequenceClassification.forward`,  you can safely ignore this message.
[2025-07-10 22:14:38,768][transformers.trainer][INFO] - 
***** Running Evaluation *****
[2025-07-10 22:14:38,769][transformers.trainer][INFO] -   Num examples = 132
[2025-07-10 22:14:38,769][transformers.trainer][INFO] -   Batch size = 4
[2025-07-10 22:14:47,232][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-10/21-00-34/results/checkpoint-288
[2025-07-10 22:14:47,234][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-10/21-00-34/results/checkpoint-288/config.json
[2025-07-10 22:14:51,991][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-10/21-00-34/results/checkpoint-288/model.safetensors
[2025-07-10 22:21:53,270][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `DebertaV2ForSequenceClassification.forward` and have been ignored: reference, id_prompt, id, grades, prompt, essay_year, essay_text, supporting_text. If reference, id_prompt, id, grades, prompt, essay_year, essay_text, supporting_text are not expected by `DebertaV2ForSequenceClassification.forward`,  you can safely ignore this message.
[2025-07-10 22:21:53,273][transformers.trainer][INFO] - 
***** Running Evaluation *****
[2025-07-10 22:21:53,273][transformers.trainer][INFO] -   Num examples = 132
[2025-07-10 22:21:53,273][transformers.trainer][INFO] -   Batch size = 4
[2025-07-10 22:22:01,730][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-10/21-00-34/results/checkpoint-320
[2025-07-10 22:22:01,732][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-10/21-00-34/results/checkpoint-320/config.json
[2025-07-10 22:22:06,384][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-10/21-00-34/results/checkpoint-320/model.safetensors
[2025-07-10 22:22:12,662][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-10/21-00-34/results/checkpoint-288] due to args.save_total_limit
[2025-07-10 22:29:08,744][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `DebertaV2ForSequenceClassification.forward` and have been ignored: reference, id_prompt, id, grades, prompt, essay_year, essay_text, supporting_text. If reference, id_prompt, id, grades, prompt, essay_year, essay_text, supporting_text are not expected by `DebertaV2ForSequenceClassification.forward`,  you can safely ignore this message.
[2025-07-10 22:29:08,748][transformers.trainer][INFO] - 
***** Running Evaluation *****
[2025-07-10 22:29:08,748][transformers.trainer][INFO] -   Num examples = 132
[2025-07-10 22:29:08,748][transformers.trainer][INFO] -   Batch size = 4
[2025-07-10 22:29:17,203][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-10/21-00-34/results/checkpoint-352
[2025-07-10 22:29:17,205][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-10/21-00-34/results/checkpoint-352/config.json
[2025-07-10 22:29:21,912][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-10/21-00-34/results/checkpoint-352/model.safetensors
[2025-07-10 22:29:27,810][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-10/21-00-34/results/checkpoint-320] due to args.save_total_limit
[2025-07-10 22:36:23,856][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `DebertaV2ForSequenceClassification.forward` and have been ignored: reference, id_prompt, id, grades, prompt, essay_year, essay_text, supporting_text. If reference, id_prompt, id, grades, prompt, essay_year, essay_text, supporting_text are not expected by `DebertaV2ForSequenceClassification.forward`,  you can safely ignore this message.
[2025-07-10 22:36:23,860][transformers.trainer][INFO] - 
***** Running Evaluation *****
[2025-07-10 22:36:23,860][transformers.trainer][INFO] -   Num examples = 132
[2025-07-10 22:36:23,860][transformers.trainer][INFO] -   Batch size = 4
[2025-07-10 22:36:32,307][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-10/21-00-34/results/checkpoint-384
[2025-07-10 22:36:32,309][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-10/21-00-34/results/checkpoint-384/config.json
[2025-07-10 22:36:37,031][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-10/21-00-34/results/checkpoint-384/model.safetensors
[2025-07-10 22:36:44,659][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-10/21-00-34/results/checkpoint-352] due to args.save_total_limit
[2025-07-10 22:43:40,734][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `DebertaV2ForSequenceClassification.forward` and have been ignored: reference, id_prompt, id, grades, prompt, essay_year, essay_text, supporting_text. If reference, id_prompt, id, grades, prompt, essay_year, essay_text, supporting_text are not expected by `DebertaV2ForSequenceClassification.forward`,  you can safely ignore this message.
[2025-07-10 22:43:40,766][transformers.trainer][INFO] - 
***** Running Evaluation *****
[2025-07-10 22:43:40,766][transformers.trainer][INFO] -   Num examples = 132
[2025-07-10 22:43:40,766][transformers.trainer][INFO] -   Batch size = 4
[2025-07-10 22:43:49,269][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-10/21-00-34/results/checkpoint-416
[2025-07-10 22:43:49,277][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-10/21-00-34/results/checkpoint-416/config.json
[2025-07-10 22:43:57,223][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-10/21-00-34/results/checkpoint-416/model.safetensors
[2025-07-10 22:44:04,347][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-10/21-00-34/results/checkpoint-384] due to args.save_total_limit
[2025-07-10 22:44:05,014][transformers.trainer][INFO] - 

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


[2025-07-10 22:44:05,015][transformers.trainer][INFO] - Loading best model from /workspace/jbcs2025/outputs/2025-07-10/21-00-34/results/checkpoint-256 (score: 0.36503067484662566).
[2025-07-10 22:44:09,842][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-10/21-00-34/results/checkpoint-416] due to args.save_total_limit
[2025-07-10 22:44:11,298][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `DebertaV2ForSequenceClassification.forward` and have been ignored: reference, id_prompt, id, grades, prompt, essay_year, essay_text, supporting_text. If reference, id_prompt, id, grades, prompt, essay_year, essay_text, supporting_text are not expected by `DebertaV2ForSequenceClassification.forward`,  you can safely ignore this message.
[2025-07-10 22:44:11,302][transformers.trainer][INFO] - 
***** Running Evaluation *****
[2025-07-10 22:44:11,302][transformers.trainer][INFO] -   Num examples = 132
[2025-07-10 22:44:11,302][transformers.trainer][INFO] -   Batch size = 4
[2025-07-10 22:44:19,687][__main__][INFO] - Training completed successfully.
[2025-07-10 22:44:19,687][__main__][INFO] - Running on Test
[2025-07-10 22:44:19,688][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `DebertaV2ForSequenceClassification.forward` and have been ignored: reference, id_prompt, id, grades, prompt, essay_year, essay_text, supporting_text. If reference, id_prompt, id, grades, prompt, essay_year, essay_text, supporting_text are not expected by `DebertaV2ForSequenceClassification.forward`,  you can safely ignore this message.
[2025-07-10 22:44:19,690][transformers.trainer][INFO] - 
***** Running Evaluation *****
[2025-07-10 22:44:19,690][transformers.trainer][INFO] -   Num examples = 138
[2025-07-10 22:44:19,690][transformers.trainer][INFO] -   Batch size = 4
[2025-07-10 22:44:28,434][__main__][INFO] - Test metrics: {'eval_loss': 2.2709360122680664, 'eval_model_preparation_time': 0.0072, 'eval_accuracy': 0.1956521739130435, 'eval_RMSE': 76.7453912131782, 'eval_QWK': 0.028976674608011566, 'eval_HDIV': 0.16666666666666663, 'eval_Macro_F1': 0.1530071129978623, 'eval_Micro_F1': 0.1956521739130435, 'eval_Weighted_F1': 0.1712828232958547, 'eval_TP_0': 4, 'eval_TN_0': 106, 'eval_FP_0': 10, 'eval_FN_0': 18, 'eval_TP_1': 1, 'eval_TN_1': 93, 'eval_FP_1': 13, 'eval_FN_1': 31, 'eval_TP_2': 14, 'eval_TN_2': 58, 'eval_FP_2': 56, 'eval_FN_2': 10, 'eval_TP_3': 3, 'eval_TN_3': 104, 'eval_FP_3': 9, 'eval_FN_3': 22, 'eval_TP_4': 5, 'eval_TN_4': 91, 'eval_FP_4': 15, 'eval_FN_4': 27, 'eval_TP_5': 0, 'eval_TN_5': 127, 'eval_FP_5': 8, 'eval_FN_5': 3, 'eval_runtime': 8.7342, 'eval_samples_per_second': 15.8, 'eval_steps_per_second': 4.007, 'epoch': 13.0}
[2025-07-10 22:44:28,435][transformers.trainer][INFO] - Saving model checkpoint to ./results/best_model
[2025-07-10 22:44:28,437][transformers.configuration_utils][INFO] - Configuration saved in ./results/best_model/config.json
[2025-07-10 22:44:33,352][transformers.modeling_utils][INFO] - Model weights saved in ./results/best_model/model.safetensors
[2025-07-10 22:44:33,356][transformers.tokenization_utils_base][INFO] - tokenizer config file saved in ./results/best_model/tokenizer_config.json
[2025-07-10 22:44:33,356][transformers.tokenization_utils_base][INFO] - Special tokens file saved in ./results/best_model/special_tokens_map.json
[2025-07-10 22:44:33,388][__main__][INFO] - Model and tokenizer saved to ./results/best_model
[2025-07-10 22:44:33,529][__main__][INFO] - Fine Tuning Finished.
[2025-07-10 22:44:34,045][__main__][INFO] - Total emissions: 0.1475 kg CO2eq