File size: 27,621 Bytes
5ad996b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 |
[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
|