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: PORTULAN/albertina-1b5-portuguese-ptbr-encoder
+metrics:
+- accuracy
+- qwk
+library_name: transformers
+model-index:
+  - name: albertina-1b5-portuguese-ptbr-encoder-encoder_classification-C1-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: 0.4968802779669244
+          - name: QWK
+            type: qwk
+            value: 0.6826328310864394
+          - name: Weighted Macro F1
+            type: f1
+            value: 0.7116672747290037
+---
+# Model ID: albertina-1b5-portuguese-ptbr-encoder-encoder_classification-C1-essay_only
+## Results
+|                  |   test_data |
+|:-----------------|------------:|
+| eval_accuracy    |  0.702899   |
+| eval_RMSE        | 25.9319     |
+| eval_QWK         |  0.682633   |
+| eval_Macro_F1    |  0.49688    |
+| eval_Weighted_F1 |  0.711667   |
+| eval_Micro_F1    |  0.702899   |
+| eval_HDIV        |  0.00724638 |
+        

config.json

@@ -0,0 +1,54 @@
+{
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "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
+}

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
+2025-07-10T17:08:59,jbcs2025,7fb4d199-6f0f-4619-b491-03e14cbeafbd,albertina-1b5-portuguese-ptbr-encoder-encoder_classification-C1-essay_only,4549.216668849986,0.10359822916253514,2.2772762148680895e-05,50.27055555555555,239.75622680535508,58.0,0.05155944090119914,0.30703561368385035,0.07201820222251853,0.430613256807568,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
+1.892467737197876,0.0074,0.11363636363636363,99.39209163101397,-0.012651078730374188,0.3787878787878788,0.08164568509396096,0.11363636363636363,0.13984674329501917,0,111,20,1,0,88,44,0,1,112,13,6,0,93,0,39,9,60,9,54,5,79,31,17,8.8626,14.894,3.723,-1,validation_before_training,2025-07-10 16:02:29,albertina-1b5-portuguese-ptbr-encoder-encoder_classification-C1-essay_only
+1.0570592880249023,0.0074,0.6439393939393939,25.34608929251695,0.6863342898134864,0.0,0.4506612692740875,0.6439393939393939,0.6292028652552237,0,131,0,1,0,132,0,0,4,119,6,3,20,85,8,19,53,42,27,10,8,104,6,14,8.4519,15.618,3.904,9.0,validation_after_training,2025-07-10 16:02:29,albertina-1b5-portuguese-ptbr-encoder-encoder_classification-C1-essay_only
+0.9303792119026184,0.0074,0.7028985507246377,25.931906372573962,0.6826328310864394,0.007246376811594235,0.49688027796692447,0.7028985507246377,0.7116672747290037,0,137,0,1,0,138,0,0,6,122,6,4,45,65,7,21,40,71,16,11,6,116,12,4,8.7537,15.765,3.998,9.0,test_results,2025-07-10 16:02:29,albertina-1b5-portuguese-ptbr-encoder-encoder_classification-C1-essay_only

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ccf1f1486296e6656aff978b8d27ed922e9151c1c19c1447996f895e767e052
+size 3133938428

run_experiment.log

@@ -0,0 +1,305 @@
+[2025-07-10 15:53:06,842][__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: 0
+    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 15:53:10,740][__main__][INFO] - GPU 0: NVIDIA RTX A6000 | TDP ≈ 300 W
+[2025-07-10 15:53:10,740][__main__][INFO] - Starting the Fine Tuning training process.
+[2025-07-10 15:53:15,881][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 15:53:15,884][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 15:53:16,306][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 15:53:16,307][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 15:53:16,307][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 15:53:16,307][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 15:53:16,307][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 15:53:16,307][transformers.tokenization_utils_base][INFO] - loading file chat_template.jinja from cache at None
+[2025-07-10 15:53:16,570][__main__][INFO] - Tokenizer function parameters- Padding:longest; Truncation: True; Use Full Context: False
+[2025-07-10 15:53:16,972][__main__][INFO] - 
+Token statistics for 'train' split:
+[2025-07-10 15:53:16,972][__main__][INFO] -   Total examples: 500
+[2025-07-10 15:53:16,972][__main__][INFO] -   Min tokens: 512
+[2025-07-10 15:53:16,972][__main__][INFO] -   Max tokens: 512
+[2025-07-10 15:53:16,972][__main__][INFO] -   Avg tokens: 512.00
+[2025-07-10 15:53:16,972][__main__][INFO] -   Std tokens: 0.00
+[2025-07-10 15:53:17,067][__main__][INFO] - 
+Token statistics for 'validation' split:
+[2025-07-10 15:53:17,067][__main__][INFO] -   Total examples: 132
+[2025-07-10 15:53:17,067][__main__][INFO] -   Min tokens: 512
+[2025-07-10 15:53:17,067][__main__][INFO] -   Max tokens: 512
+[2025-07-10 15:53:17,067][__main__][INFO] -   Avg tokens: 512.00
+[2025-07-10 15:53:17,067][__main__][INFO] -   Std tokens: 0.00
+[2025-07-10 15:53:17,166][__main__][INFO] - 
+Token statistics for 'test' split:
+[2025-07-10 15:53:17,166][__main__][INFO] -   Total examples: 138
+[2025-07-10 15:53:17,167][__main__][INFO] -   Min tokens: 512
+[2025-07-10 15:53:17,167][__main__][INFO] -   Max tokens: 512
+[2025-07-10 15:53:17,167][__main__][INFO] -   Avg tokens: 512.00
+[2025-07-10 15:53:17,167][__main__][INFO] -   Std tokens: 0.00
+[2025-07-10 15:53:17,167][__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 15:53:17,167][__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 15:53:17,431][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 15:53:17,432][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 15:53:17,820][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 15:53:17,821][transformers.modeling_utils][INFO] - Will use torch_dtype=torch.bfloat16 as defined in model's config object
+[2025-07-10 15:53:17,821][transformers.modeling_utils][INFO] - Instantiating DebertaV2ForSequenceClassification model under default dtype torch.bfloat16.
+[2025-07-10 15:53:18,201][transformers.safetensors_conversion][INFO] - Attempting to create safetensors variant
+[2025-07-10 15:53:18,665][transformers.safetensors_conversion][INFO] - Attempting to convert .bin model on the fly to safetensors.
+[2025-07-10 16:02:29,595][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 16:02:29,595][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 16:02:29,613][transformers.training_args][INFO] - PyTorch: setting up devices
+[2025-07-10 16:02:29,639][__main__][INFO] - Total steps: 620. Number of warmup steps: 62
+[2025-07-10 16:02:29,649][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 16:02:29,676][transformers.trainer][INFO] - Using auto half precision backend
+[2025-07-10 16:02:29,678][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `DebertaV2ForSequenceClassification.forward` and have been ignored: prompt, id, essay_year, id_prompt, supporting_text, reference, essay_text, grades. If prompt, id, essay_year, id_prompt, supporting_text, reference, essay_text, grades are not expected by `DebertaV2ForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-10 16:02:29,689][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-10 16:02:29,689][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-10 16:02:29,690][transformers.trainer][INFO] -   Batch size = 4
+[2025-07-10 16:02:38,845][transformers.trainer][INFO] - The following columns in the Training set don't have a corresponding argument in `DebertaV2ForSequenceClassification.forward` and have been ignored: prompt, id, essay_year, id_prompt, supporting_text, reference, essay_text, grades. If prompt, id, essay_year, id_prompt, supporting_text, reference, essay_text, grades are not expected by `DebertaV2ForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-10 16:02:38,876][transformers.trainer][INFO] - ***** Running training *****
+[2025-07-10 16:02:38,876][transformers.trainer][INFO] -   Num examples = 500
+[2025-07-10 16:02:38,876][transformers.trainer][INFO] -   Num Epochs = 20
+[2025-07-10 16:02:38,876][transformers.trainer][INFO] -   Instantaneous batch size per device = 4
+[2025-07-10 16:02:38,876][transformers.trainer][INFO] -   Total train batch size (w. parallel, distributed & accumulation) = 16
+[2025-07-10 16:02:38,876][transformers.trainer][INFO] -   Gradient Accumulation steps = 4
+[2025-07-10 16:02:38,876][transformers.trainer][INFO] -   Total optimization steps = 640
+[2025-07-10 16:02:38,878][transformers.trainer][INFO] -   Number of trainable parameters = 1,566,919,686
+[2025-07-10 16:09:32,605][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `DebertaV2ForSequenceClassification.forward` and have been ignored: prompt, id, essay_year, id_prompt, supporting_text, reference, essay_text, grades. If prompt, id, essay_year, id_prompt, supporting_text, reference, essay_text, grades are not expected by `DebertaV2ForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-10 16:09:32,609][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-10 16:09:32,609][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-10 16:09:32,609][transformers.trainer][INFO] -   Batch size = 4
+[2025-07-10 16:09:41,083][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-10/15-53-06/results/checkpoint-32
+[2025-07-10 16:09:41,085][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-10/15-53-06/results/checkpoint-32/config.json
+[2025-07-10 16:09:46,899][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-10/15-53-06/results/checkpoint-32/model.safetensors
+[2025-07-10 16:16:50,105][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `DebertaV2ForSequenceClassification.forward` and have been ignored: prompt, id, essay_year, id_prompt, supporting_text, reference, essay_text, grades. If prompt, id, essay_year, id_prompt, supporting_text, reference, essay_text, grades are not expected by `DebertaV2ForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-10 16:16:50,109][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-10 16:16:50,110][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-10 16:16:50,110][transformers.trainer][INFO] -   Batch size = 4
+[2025-07-10 16:16:58,598][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-10/15-53-06/results/checkpoint-64
+[2025-07-10 16:16:58,601][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-10/15-53-06/results/checkpoint-64/config.json
+[2025-07-10 16:17:05,052][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-10/15-53-06/results/checkpoint-64/model.safetensors
+[2025-07-10 16:17:13,233][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-10/15-53-06/results/checkpoint-32] due to args.save_total_limit
+[2025-07-10 16:24:09,684][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `DebertaV2ForSequenceClassification.forward` and have been ignored: prompt, id, essay_year, id_prompt, supporting_text, reference, essay_text, grades. If prompt, id, essay_year, id_prompt, supporting_text, reference, essay_text, grades are not expected by `DebertaV2ForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-10 16:24:09,688][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-10 16:24:09,688][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-10 16:24:09,688][transformers.trainer][INFO] -   Batch size = 4
+[2025-07-10 16:24:18,146][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-10/15-53-06/results/checkpoint-96
+[2025-07-10 16:24:18,148][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-10/15-53-06/results/checkpoint-96/config.json
+[2025-07-10 16:24:23,608][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-10/15-53-06/results/checkpoint-96/model.safetensors
+[2025-07-10 16:24:30,971][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-10/15-53-06/results/checkpoint-64] due to args.save_total_limit
+[2025-07-10 16:31:27,837][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `DebertaV2ForSequenceClassification.forward` and have been ignored: prompt, id, essay_year, id_prompt, supporting_text, reference, essay_text, grades. If prompt, id, essay_year, id_prompt, supporting_text, reference, essay_text, grades are not expected by `DebertaV2ForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-10 16:31:27,841][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-10 16:31:27,842][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-10 16:31:27,842][transformers.trainer][INFO] -   Batch size = 4
+[2025-07-10 16:31:36,301][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-10/15-53-06/results/checkpoint-128
+[2025-07-10 16:31:36,304][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-10/15-53-06/results/checkpoint-128/config.json
+[2025-07-10 16:31:43,337][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-10/15-53-06/results/checkpoint-128/model.safetensors
+[2025-07-10 16:31:49,743][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-10/15-53-06/results/checkpoint-96] due to args.save_total_limit
+[2025-07-10 16:38:52,376][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `DebertaV2ForSequenceClassification.forward` and have been ignored: prompt, id, essay_year, id_prompt, supporting_text, reference, essay_text, grades. If prompt, id, essay_year, id_prompt, supporting_text, reference, essay_text, grades are not expected by `DebertaV2ForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-10 16:38:52,380][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-10 16:38:52,380][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-10 16:38:52,380][transformers.trainer][INFO] -   Batch size = 4
+[2025-07-10 16:39:00,857][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-10/15-53-06/results/checkpoint-160
+[2025-07-10 16:39:00,862][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-10/15-53-06/results/checkpoint-160/config.json
+[2025-07-10 16:39:10,224][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-10/15-53-06/results/checkpoint-160/model.safetensors
+[2025-07-10 16:46:16,187][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `DebertaV2ForSequenceClassification.forward` and have been ignored: prompt, id, essay_year, id_prompt, supporting_text, reference, essay_text, grades. If prompt, id, essay_year, id_prompt, supporting_text, reference, essay_text, grades are not expected by `DebertaV2ForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-10 16:46:16,213][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-10 16:46:16,214][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-10 16:46:16,214][transformers.trainer][INFO] -   Batch size = 4
+[2025-07-10 16:46:24,732][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-10/15-53-06/results/checkpoint-192
+[2025-07-10 16:46:24,736][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-10/15-53-06/results/checkpoint-192/config.json
+[2025-07-10 16:46:31,956][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-10/15-53-06/results/checkpoint-192/model.safetensors
+[2025-07-10 16:46:38,914][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-10/15-53-06/results/checkpoint-160] due to args.save_total_limit
+[2025-07-10 16:53:35,545][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `DebertaV2ForSequenceClassification.forward` and have been ignored: prompt, id, essay_year, id_prompt, supporting_text, reference, essay_text, grades. If prompt, id, essay_year, id_prompt, supporting_text, reference, essay_text, grades are not expected by `DebertaV2ForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-10 16:53:35,550][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-10 16:53:35,550][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-10 16:53:35,550][transformers.trainer][INFO] -   Batch size = 4
+[2025-07-10 16:53:44,013][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-10/15-53-06/results/checkpoint-224
+[2025-07-10 16:53:44,015][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-10/15-53-06/results/checkpoint-224/config.json
+[2025-07-10 16:53:48,622][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-10/15-53-06/results/checkpoint-224/model.safetensors
+[2025-07-10 16:53:55,055][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-10/15-53-06/results/checkpoint-192] due to args.save_total_limit
+[2025-07-10 17:00:51,991][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `DebertaV2ForSequenceClassification.forward` and have been ignored: prompt, id, essay_year, id_prompt, supporting_text, reference, essay_text, grades. If prompt, id, essay_year, id_prompt, supporting_text, reference, essay_text, grades are not expected by `DebertaV2ForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-10 17:00:51,995][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-10 17:00:51,995][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-10 17:00:51,995][transformers.trainer][INFO] -   Batch size = 4
+[2025-07-10 17:01:00,444][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-10/15-53-06/results/checkpoint-256
+[2025-07-10 17:01:00,447][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-10/15-53-06/results/checkpoint-256/config.json
+[2025-07-10 17:01:05,603][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-10/15-53-06/results/checkpoint-256/model.safetensors
+[2025-07-10 17:01:12,787][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-10/15-53-06/results/checkpoint-224] due to args.save_total_limit
+[2025-07-10 17:08:09,449][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `DebertaV2ForSequenceClassification.forward` and have been ignored: prompt, id, essay_year, id_prompt, supporting_text, reference, essay_text, grades. If prompt, id, essay_year, id_prompt, supporting_text, reference, essay_text, grades are not expected by `DebertaV2ForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-10 17:08:09,456][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-10 17:08:09,456][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-10 17:08:09,456][transformers.trainer][INFO] -   Batch size = 4
+[2025-07-10 17:08:17,939][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-10/15-53-06/results/checkpoint-288
+[2025-07-10 17:08:17,941][transformers.configuration_utils][INFO] - Configuration saved in /workspace/jbcs2025/outputs/2025-07-10/15-53-06/results/checkpoint-288/config.json
+[2025-07-10 17:08:24,232][transformers.modeling_utils][INFO] - Model weights saved in /workspace/jbcs2025/outputs/2025-07-10/15-53-06/results/checkpoint-288/model.safetensors
+[2025-07-10 17:08:33,143][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-10/15-53-06/results/checkpoint-256] due to args.save_total_limit
+[2025-07-10 17:08:33,643][transformers.trainer][INFO] - 
+
+Training completed. Do not forget to share your model on huggingface.co/models =)
+
+
+[2025-07-10 17:08:33,644][transformers.trainer][INFO] - Loading best model from /workspace/jbcs2025/outputs/2025-07-10/15-53-06/results/checkpoint-128 (score: 0.6863342898134864).
+[2025-07-10 17:08:36,030][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-10/15-53-06/results/checkpoint-288] due to args.save_total_limit
+[2025-07-10 17:08:36,692][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `DebertaV2ForSequenceClassification.forward` and have been ignored: prompt, id, essay_year, id_prompt, supporting_text, reference, essay_text, grades. If prompt, id, essay_year, id_prompt, supporting_text, reference, essay_text, grades are not expected by `DebertaV2ForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-10 17:08:36,696][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-10 17:08:36,696][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-10 17:08:36,696][transformers.trainer][INFO] -   Batch size = 4
+[2025-07-10 17:08:45,160][__main__][INFO] - Training completed successfully.
+[2025-07-10 17:08:45,160][__main__][INFO] - Running on Test
+[2025-07-10 17:08:45,161][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `DebertaV2ForSequenceClassification.forward` and have been ignored: prompt, id, essay_year, id_prompt, supporting_text, reference, essay_text, grades. If prompt, id, essay_year, id_prompt, supporting_text, reference, essay_text, grades are not expected by `DebertaV2ForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-10 17:08:45,164][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-10 17:08:45,164][transformers.trainer][INFO] -   Num examples = 138
+[2025-07-10 17:08:45,164][transformers.trainer][INFO] -   Batch size = 4
+[2025-07-10 17:08:53,928][__main__][INFO] - Test metrics: {'eval_loss': 0.9303792119026184, 'eval_model_preparation_time': 0.0074, 'eval_accuracy': 0.7028985507246377, 'eval_RMSE': 25.931906372573962, 'eval_QWK': 0.6826328310864394, 'eval_HDIV': 0.007246376811594235, 'eval_Macro_F1': 0.49688027796692447, 'eval_Micro_F1': 0.7028985507246377, 'eval_Weighted_F1': 0.7116672747290037, 'eval_TP_0': 0, 'eval_TN_0': 137, 'eval_FP_0': 0, 'eval_FN_0': 1, 'eval_TP_1': 0, 'eval_TN_1': 138, 'eval_FP_1': 0, 'eval_FN_1': 0, 'eval_TP_2': 6, 'eval_TN_2': 122, 'eval_FP_2': 6, 'eval_FN_2': 4, 'eval_TP_3': 45, 'eval_TN_3': 65, 'eval_FP_3': 7, 'eval_FN_3': 21, 'eval_TP_4': 40, 'eval_TN_4': 71, 'eval_FP_4': 16, 'eval_FN_4': 11, 'eval_TP_5': 6, 'eval_TN_5': 116, 'eval_FP_5': 12, 'eval_FN_5': 4, 'eval_runtime': 8.7537, 'eval_samples_per_second': 15.765, 'eval_steps_per_second': 3.998, 'epoch': 9.0}
+[2025-07-10 17:08:53,929][transformers.trainer][INFO] - Saving model checkpoint to ./results/best_model
+[2025-07-10 17:08:53,931][transformers.configuration_utils][INFO] - Configuration saved in ./results/best_model/config.json
+[2025-07-10 17:08:58,786][transformers.modeling_utils][INFO] - Model weights saved in ./results/best_model/model.safetensors
+[2025-07-10 17:08:58,789][transformers.tokenization_utils_base][INFO] - tokenizer config file saved in ./results/best_model/tokenizer_config.json
+[2025-07-10 17:08:58,789][transformers.tokenization_utils_base][INFO] - Special tokens file saved in ./results/best_model/special_tokens_map.json
+[2025-07-10 17:08:58,816][__main__][INFO] - Model and tokenizer saved to ./results/best_model
+[2025-07-10 17:08:58,940][__main__][INFO] - Fine Tuning Finished.
+[2025-07-10 17:08:59,455][__main__][INFO] - Total emissions: 0.1036 kg CO2eq

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cf94482fd02c284d5af1194f8d9537d3c5a6676656bebb88ad94465b29991aa
+size 5777