File size: 95,916 Bytes
8048f3a |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 |
Using the `WANDB_DISABLED` environment variable is deprecated and will be removed in v5. Use the --report_to flag to control the integrations used for logging result (for instance --report_to none).
02/05/2024 17:21:05 - WARNING - __main__ - Process rank: 0, device: cuda:0, n_gpu: 1, distributed training: False, 16-bits training: False
02/05/2024 17:21:05 - INFO - __main__ - Training/evaluation parameters Seq2SeqTrainingArguments(
_n_gpu=1,
adafactor=False,
adam_beta1=0.9,
adam_beta2=0.999,
adam_epsilon=1e-08,
auto_find_batch_size=False,
bf16=False,
bf16_full_eval=False,
data_seed=None,
dataloader_drop_last=False,
dataloader_num_workers=0,
dataloader_persistent_workers=False,
dataloader_pin_memory=True,
ddp_backend=None,
ddp_broadcast_buffers=None,
ddp_bucket_cap_mb=None,
ddp_find_unused_parameters=None,
ddp_timeout=1800,
debug=[],
deepspeed=None,
disable_tqdm=False,
dispatch_batches=None,
do_eval=False,
do_predict=True,
do_train=False,
eval_accumulation_steps=None,
eval_delay=0,
eval_steps=None,
evaluation_strategy=no,
fp16=False,
fp16_backend=auto,
fp16_full_eval=False,
fp16_opt_level=O1,
fsdp=[],
fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_grad_ckpt': False},
fsdp_min_num_params=0,
fsdp_transformer_layer_cls_to_wrap=None,
full_determinism=False,
generation_config=None,
generation_max_length=None,
generation_num_beams=2,
gradient_accumulation_steps=1,
gradient_checkpointing=False,
gradient_checkpointing_kwargs=None,
greater_is_better=None,
group_by_length=True,
half_precision_backend=auto,
hub_always_push=False,
hub_model_id=None,
hub_private_repo=False,
hub_strategy=every_save,
hub_token=<HUB_TOKEN>,
ignore_data_skip=False,
include_inputs_for_metrics=False,
include_num_input_tokens_seen=False,
include_tokens_per_second=False,
jit_mode_eval=False,
label_names=None,
label_smoothing_factor=0.0,
learning_rate=5e-05,
length_column_name=input_length,
load_best_model_at_end=False,
local_rank=0,
log_level=passive,
log_level_replica=warning,
log_on_each_node=True,
logging_dir=/beegfs/scratch/user/blee/project_3/models/NLU.mt5-base.task_type-1.fine_tune.gpu_a100-40g+.node-1x1.bsz-64.epochs-22.metric-ema.metric_lang-all/checkpoint-30407/eval/cascaded_SLU/runs/Feb05_17-21-05_chasma-02,
logging_first_step=False,
logging_nan_inf_filter=True,
logging_steps=500,
logging_strategy=steps,
lr_scheduler_kwargs={},
lr_scheduler_type=linear,
max_grad_norm=1.0,
max_steps=-1,
metric_for_best_model=None,
mp_parameters=,
neftune_noise_alpha=None,
no_cuda=False,
num_train_epochs=3.0,
optim=adamw_torch,
optim_args=None,
output_dir=/beegfs/scratch/user/blee/project_3/models/NLU.mt5-base.task_type-1.fine_tune.gpu_a100-40g+.node-1x1.bsz-64.epochs-22.metric-ema.metric_lang-all/checkpoint-30407/eval/cascaded_SLU,
overwrite_output_dir=False,
past_index=-1,
per_device_eval_batch_size=32,
per_device_train_batch_size=8,
predict_with_generate=True,
prediction_loss_only=False,
push_to_hub=False,
push_to_hub_model_id=None,
push_to_hub_organization=None,
push_to_hub_token=<PUSH_TO_HUB_TOKEN>,
ray_scope=last,
remove_unused_columns=True,
report_to=[],
resume_from_checkpoint=None,
run_name=/beegfs/scratch/user/blee/project_3/models/NLU.mt5-base.task_type-1.fine_tune.gpu_a100-40g+.node-1x1.bsz-64.epochs-22.metric-ema.metric_lang-all/checkpoint-30407/eval/cascaded_SLU,
save_on_each_node=False,
save_only_model=False,
save_safetensors=True,
save_steps=500,
save_strategy=steps,
save_total_limit=None,
seed=42,
skip_memory_metrics=True,
sortish_sampler=False,
split_batches=False,
tf32=None,
torch_compile=False,
torch_compile_backend=None,
torch_compile_mode=None,
torchdynamo=None,
tpu_metrics_debug=False,
tpu_num_cores=None,
use_cpu=False,
use_ipex=False,
use_legacy_prediction_loop=False,
use_mps_device=False,
warmup_ratio=0.0,
warmup_steps=0,
weight_decay=0.0,
)
Loading Dataset Infos from /beegfs/scratch/user/blee/hugging-face/models/modules/datasets_modules/datasets/speech_massive_cascaded/f36c9e4210ec02a91ee05c9fa785d90aec211ba2025363c65b643c68e109b293
02/05/2024 17:21:05 - INFO - datasets.info - Loading Dataset Infos from /beegfs/scratch/user/blee/hugging-face/models/modules/datasets_modules/datasets/speech_massive_cascaded/f36c9e4210ec02a91ee05c9fa785d90aec211ba2025363c65b643c68e109b293
Overwrite dataset info from restored data version if exists.
02/05/2024 17:21:05 - INFO - datasets.builder - Overwrite dataset info from restored data version if exists.
Loading Dataset info from /beegfs/scratch/user/blee/hugging-face/models/datasets/speech_massive_cascaded/multilingual-test/1.0.0/f36c9e4210ec02a91ee05c9fa785d90aec211ba2025363c65b643c68e109b293
02/05/2024 17:21:05 - INFO - datasets.info - Loading Dataset info from /beegfs/scratch/user/blee/hugging-face/models/datasets/speech_massive_cascaded/multilingual-test/1.0.0/f36c9e4210ec02a91ee05c9fa785d90aec211ba2025363c65b643c68e109b293
Found cached dataset speech_massive_cascaded (/beegfs/scratch/user/blee/hugging-face/models/datasets/speech_massive_cascaded/multilingual-test/1.0.0/f36c9e4210ec02a91ee05c9fa785d90aec211ba2025363c65b643c68e109b293)
02/05/2024 17:21:05 - INFO - datasets.builder - Found cached dataset speech_massive_cascaded (/beegfs/scratch/user/blee/hugging-face/models/datasets/speech_massive_cascaded/multilingual-test/1.0.0/f36c9e4210ec02a91ee05c9fa785d90aec211ba2025363c65b643c68e109b293)
Loading Dataset info from /beegfs/scratch/user/blee/hugging-face/models/datasets/speech_massive_cascaded/multilingual-test/1.0.0/f36c9e4210ec02a91ee05c9fa785d90aec211ba2025363c65b643c68e109b293
02/05/2024 17:21:05 - INFO - datasets.info - Loading Dataset info from /beegfs/scratch/user/blee/hugging-face/models/datasets/speech_massive_cascaded/multilingual-test/1.0.0/f36c9e4210ec02a91ee05c9fa785d90aec211ba2025363c65b643c68e109b293
[INFO|configuration_utils.py:737] 2024-02-05 17:21:05,923 >> loading configuration file /beegfs/scratch/user/blee/project_3/models/NLU.mt5-base.task_type-1.fine_tune.gpu_a100-40g+.node-1x1.bsz-64.epochs-22.metric-ema.metric_lang-all/checkpoint-30407/config.json
[INFO|configuration_utils.py:802] 2024-02-05 17:21:05,933 >> Model config MT5Config {
"_name_or_path": "/beegfs/scratch/user/blee/project_3/models/NLU.mt5-base.task_type-1.fine_tune.gpu_a100-40g+.node-1x1.bsz-64.epochs-22.metric-ema.metric_lang-all/checkpoint-30407",
"architectures": [
"MT5ForConditionalGeneration"
],
"classifier_dropout": 0.0,
"d_ff": 2048,
"d_kv": 64,
"d_model": 768,
"decoder_start_token_id": 0,
"dense_act_fn": "gelu_new",
"dropout": 0.2,
"dropout_rate": 0.1,
"eos_token_id": 1,
"feed_forward_proj": "gated-gelu",
"initializer_factor": 1.0,
"is_encoder_decoder": true,
"is_gated_act": true,
"layer_norm_epsilon": 1e-06,
"model_type": "mt5",
"num_decoder_layers": 12,
"num_heads": 12,
"num_layers": 12,
"output_past": true,
"pad_token_id": 0,
"relative_attention_max_distance": 128,
"relative_attention_num_buckets": 32,
"tie_word_embeddings": false,
"tokenizer_class": "T5Tokenizer",
"torch_dtype": "float32",
"transformers_version": "4.37.0.dev0",
"use_cache": true,
"vocab_size": 250112
}
[INFO|tokenization_utils_base.py:2024] 2024-02-05 17:21:05,935 >> loading file spiece.model
[INFO|tokenization_utils_base.py:2024] 2024-02-05 17:21:05,935 >> loading file tokenizer.json
[INFO|tokenization_utils_base.py:2024] 2024-02-05 17:21:05,935 >> loading file added_tokens.json
[INFO|tokenization_utils_base.py:2024] 2024-02-05 17:21:05,936 >> loading file special_tokens_map.json
[INFO|tokenization_utils_base.py:2024] 2024-02-05 17:21:05,936 >> loading file tokenizer_config.json
[INFO|modeling_utils.py:3373] 2024-02-05 17:21:06,419 >> loading weights file /beegfs/scratch/user/blee/project_3/models/NLU.mt5-base.task_type-1.fine_tune.gpu_a100-40g+.node-1x1.bsz-64.epochs-22.metric-ema.metric_lang-all/checkpoint-30407/model.safetensors
[INFO|configuration_utils.py:826] 2024-02-05 17:21:06,574 >> Generate config GenerationConfig {
"decoder_start_token_id": 0,
"eos_token_id": 1,
"pad_token_id": 0
}
[INFO|modeling_utils.py:4224] 2024-02-05 17:21:11,310 >> All model checkpoint weights were used when initializing MT5ForConditionalGeneration.
[INFO|modeling_utils.py:4232] 2024-02-05 17:21:11,310 >> All the weights of MT5ForConditionalGeneration were initialized from the model checkpoint at /beegfs/scratch/user/blee/project_3/models/NLU.mt5-base.task_type-1.fine_tune.gpu_a100-40g+.node-1x1.bsz-64.epochs-22.metric-ema.metric_lang-all/checkpoint-30407.
If your task is similar to the task the model of the checkpoint was trained on, you can already use MT5ForConditionalGeneration for predictions without further training.
[INFO|configuration_utils.py:779] 2024-02-05 17:21:11,318 >> loading configuration file /beegfs/scratch/user/blee/project_3/models/NLU.mt5-base.task_type-1.fine_tune.gpu_a100-40g+.node-1x1.bsz-64.epochs-22.metric-ema.metric_lang-all/checkpoint-30407/generation_config.json
[INFO|configuration_utils.py:826] 2024-02-05 17:21:11,318 >> Generate config GenerationConfig {
"decoder_start_token_id": 0,
"eos_token_id": 1,
"pad_token_id": 0
}
Loading cached processed dataset at /beegfs/scratch/user/blee/hugging-face/models/datasets/speech_massive_cascaded/multilingual-test/1.0.0/f36c9e4210ec02a91ee05c9fa785d90aec211ba2025363c65b643c68e109b293/cache-a28263cfb71413f6.arrow
02/05/2024 17:21:11 - INFO - datasets.arrow_dataset - Loading cached processed dataset at /beegfs/scratch/user/blee/hugging-face/models/datasets/speech_massive_cascaded/multilingual-test/1.0.0/f36c9e4210ec02a91ee05c9fa785d90aec211ba2025363c65b643c68e109b293/cache-a28263cfb71413f6.arrow
Loading cached processed dataset at /beegfs/scratch/user/blee/hugging-face/models/datasets/speech_massive_cascaded/multilingual-test/1.0.0/f36c9e4210ec02a91ee05c9fa785d90aec211ba2025363c65b643c68e109b293/cache-0f6b9ba1cc4e5fb1.arrow
02/05/2024 17:21:11 - INFO - datasets.arrow_dataset - Loading cached processed dataset at /beegfs/scratch/user/blee/hugging-face/models/datasets/speech_massive_cascaded/multilingual-test/1.0.0/f36c9e4210ec02a91ee05c9fa785d90aec211ba2025363c65b643c68e109b293/cache-0f6b9ba1cc4e5fb1.arrow
Loading cached processed dataset at /beegfs/scratch/user/blee/hugging-face/models/datasets/speech_massive_cascaded/multilingual-test/1.0.0/f36c9e4210ec02a91ee05c9fa785d90aec211ba2025363c65b643c68e109b293/cache-cd10216b4341f1a2.arrow
02/05/2024 17:21:11 - INFO - datasets.arrow_dataset - Loading cached processed dataset at /beegfs/scratch/user/blee/hugging-face/models/datasets/speech_massive_cascaded/multilingual-test/1.0.0/f36c9e4210ec02a91ee05c9fa785d90aec211ba2025363c65b643c68e109b293/cache-cd10216b4341f1a2.arrow
Loading cached processed dataset at /beegfs/scratch/user/blee/hugging-face/models/datasets/speech_massive_cascaded/multilingual-test/1.0.0/f36c9e4210ec02a91ee05c9fa785d90aec211ba2025363c65b643c68e109b293/cache-cf09cb968cef4c56.arrow
02/05/2024 17:21:11 - INFO - datasets.arrow_dataset - Loading cached processed dataset at /beegfs/scratch/user/blee/hugging-face/models/datasets/speech_massive_cascaded/multilingual-test/1.0.0/f36c9e4210ec02a91ee05c9fa785d90aec211ba2025363c65b643c68e109b293/cache-cf09cb968cef4c56.arrow
Loading cached processed dataset at /beegfs/scratch/user/blee/hugging-face/models/datasets/speech_massive_cascaded/multilingual-test/1.0.0/f36c9e4210ec02a91ee05c9fa785d90aec211ba2025363c65b643c68e109b293/cache-b372c4d6e9ad447f.arrow
02/05/2024 17:21:11 - INFO - datasets.arrow_dataset - Loading cached processed dataset at /beegfs/scratch/user/blee/hugging-face/models/datasets/speech_massive_cascaded/multilingual-test/1.0.0/f36c9e4210ec02a91ee05c9fa785d90aec211ba2025363c65b643c68e109b293/cache-b372c4d6e9ad447f.arrow
Loading cached processed dataset at /beegfs/scratch/user/blee/hugging-face/models/datasets/speech_massive_cascaded/multilingual-test/1.0.0/f36c9e4210ec02a91ee05c9fa785d90aec211ba2025363c65b643c68e109b293/cache-5e85733ab0d7983c.arrow
02/05/2024 17:21:11 - INFO - datasets.arrow_dataset - Loading cached processed dataset at /beegfs/scratch/user/blee/hugging-face/models/datasets/speech_massive_cascaded/multilingual-test/1.0.0/f36c9e4210ec02a91ee05c9fa785d90aec211ba2025363c65b643c68e109b293/cache-5e85733ab0d7983c.arrow
Loading cached processed dataset at /beegfs/scratch/user/blee/hugging-face/models/datasets/speech_massive_cascaded/multilingual-test/1.0.0/f36c9e4210ec02a91ee05c9fa785d90aec211ba2025363c65b643c68e109b293/cache-3498127f38d0e88c.arrow
02/05/2024 17:21:11 - INFO - datasets.arrow_dataset - Loading cached processed dataset at /beegfs/scratch/user/blee/hugging-face/models/datasets/speech_massive_cascaded/multilingual-test/1.0.0/f36c9e4210ec02a91ee05c9fa785d90aec211ba2025363c65b643c68e109b293/cache-3498127f38d0e88c.arrow
Loading cached processed dataset at /beegfs/scratch/user/blee/hugging-face/models/datasets/speech_massive_cascaded/multilingual-test/1.0.0/f36c9e4210ec02a91ee05c9fa785d90aec211ba2025363c65b643c68e109b293/cache-5031b1ae09c119f0.arrow
02/05/2024 17:21:11 - INFO - datasets.arrow_dataset - Loading cached processed dataset at /beegfs/scratch/user/blee/hugging-face/models/datasets/speech_massive_cascaded/multilingual-test/1.0.0/f36c9e4210ec02a91ee05c9fa785d90aec211ba2025363c65b643c68e109b293/cache-5031b1ae09c119f0.arrow
Loading cached processed dataset at /beegfs/scratch/user/blee/hugging-face/models/datasets/speech_massive_cascaded/multilingual-test/1.0.0/f36c9e4210ec02a91ee05c9fa785d90aec211ba2025363c65b643c68e109b293/cache-afad46b8cc76fbde.arrow
02/05/2024 17:21:11 - INFO - datasets.arrow_dataset - Loading cached processed dataset at /beegfs/scratch/user/blee/hugging-face/models/datasets/speech_massive_cascaded/multilingual-test/1.0.0/f36c9e4210ec02a91ee05c9fa785d90aec211ba2025363c65b643c68e109b293/cache-afad46b8cc76fbde.arrow
Loading cached processed dataset at /beegfs/scratch/user/blee/hugging-face/models/datasets/speech_massive_cascaded/multilingual-test/1.0.0/f36c9e4210ec02a91ee05c9fa785d90aec211ba2025363c65b643c68e109b293/cache-44bbdcb1f95b0505.arrow
02/05/2024 17:21:11 - INFO - datasets.arrow_dataset - Loading cached processed dataset at /beegfs/scratch/user/blee/hugging-face/models/datasets/speech_massive_cascaded/multilingual-test/1.0.0/f36c9e4210ec02a91ee05c9fa785d90aec211ba2025363c65b643c68e109b293/cache-44bbdcb1f95b0505.arrow
Loading cached processed dataset at /beegfs/scratch/user/blee/hugging-face/models/datasets/speech_massive_cascaded/multilingual-test/1.0.0/f36c9e4210ec02a91ee05c9fa785d90aec211ba2025363c65b643c68e109b293/cache-649defd19aa00c44.arrow
02/05/2024 17:21:11 - INFO - datasets.arrow_dataset - Loading cached processed dataset at /beegfs/scratch/user/blee/hugging-face/models/datasets/speech_massive_cascaded/multilingual-test/1.0.0/f36c9e4210ec02a91ee05c9fa785d90aec211ba2025363c65b643c68e109b293/cache-649defd19aa00c44.arrow
Loading cached processed dataset at /beegfs/scratch/user/blee/hugging-face/models/datasets/speech_massive_cascaded/multilingual-test/1.0.0/f36c9e4210ec02a91ee05c9fa785d90aec211ba2025363c65b643c68e109b293/cache-bc58b34f0f2e6d55.arrow
02/05/2024 17:21:11 - INFO - datasets.arrow_dataset - Loading cached processed dataset at /beegfs/scratch/user/blee/hugging-face/models/datasets/speech_massive_cascaded/multilingual-test/1.0.0/f36c9e4210ec02a91ee05c9fa785d90aec211ba2025363c65b643c68e109b293/cache-bc58b34f0f2e6d55.arrow
02/05/2024 17:21:28 - WARNING - accelerate.utils.other - Detected kernel version 4.18.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher.
02/05/2024 17:21:28 - INFO - __main__ - *** Predict ***
02/05/2024 17:21:28 - INFO - __main__ - *** test_ar_SA ***
[INFO|trainer.py:718] 2024-02-05 17:21:28,574 >> The following columns in the test set don't have a corresponding argument in `MT5ForConditionalGeneration.forward` and have been ignored: intent_str, id, annot_utt. If intent_str, id, annot_utt are not expected by `MT5ForConditionalGeneration.forward`, you can safely ignore this message.
[INFO|trainer.py:3199] 2024-02-05 17:21:28,584 >> ***** Running Prediction *****
[INFO|trainer.py:3201] 2024-02-05 17:21:28,584 >> Num examples = 2974
[INFO|trainer.py:3204] 2024-02-05 17:21:28,584 >> Batch size = 32
[WARNING|logging.py:314] 2024-02-05 17:21:28,589 >> You're using a T5TokenizerFast tokenizer. Please note that with a fast tokenizer, using the `__call__` method is faster than using a method to encode the text followed by a call to the `pad` method to get a padded encoding.
0%| | 0/93 [00:00<?, ?it/s]
2%|▏ | 2/93 [00:00<00:18, 5.03it/s]
3%|▎ | 3/93 [00:00<00:23, 3.91it/s]
4%|▍ | 4/93 [00:01<00:29, 2.97it/s]
5%|▌ | 5/93 [00:01<00:35, 2.50it/s]
6%|▋ | 6/93 [00:02<00:33, 2.59it/s]
8%|▊ | 7/93 [00:02<00:35, 2.41it/s]
9%|▊ | 8/93 [00:02<00:33, 2.53it/s]
10%|▉ | 9/93 [00:03<00:33, 2.49it/s]
11%|█ | 10/93 [00:03<00:32, 2.54it/s]
12%|█▏ | 11/93 [00:04<00:32, 2.49it/s]
13%|█▎ | 12/93 [00:04<00:31, 2.57it/s]
14%|█▍ | 13/93 [00:04<00:30, 2.62it/s]
15%|█▌ | 14/93 [00:05<00:31, 2.54it/s]
16%|█▌ | 15/93 [00:05<00:32, 2.42it/s]
17%|█▋ | 16/93 [00:06<00:34, 2.21it/s]
18%|█▊ | 17/93 [00:06<00:34, 2.18it/s]
19%|█▉ | 18/93 [00:07<00:33, 2.26it/s]
20%|██ | 19/93 [00:07<00:31, 2.39it/s]
22%|██▏ | 20/93 [00:07<00:29, 2.45it/s]
23%|██▎ | 21/93 [00:08<00:28, 2.50it/s]
24%|██▎ | 22/93 [00:08<00:32, 2.20it/s]
25%|██▍ | 23/93 [00:09<00:31, 2.25it/s]
26%|██▌ | 24/93 [00:09<00:31, 2.21it/s]
27%|██▋ | 25/93 [00:10<00:29, 2.27it/s]
28%|██▊ | 26/93 [00:10<00:30, 2.21it/s]
29%|██▉ | 27/93 [00:11<00:29, 2.21it/s]
30%|███ | 28/93 [00:13<01:01, 1.06it/s]
31%|███ | 29/93 [00:13<00:50, 1.27it/s]
32%|███▏ | 30/93 [00:13<00:41, 1.50it/s]
33%|███▎ | 31/93 [00:14<00:37, 1.66it/s]
34%|███▍ | 32/93 [00:14<00:33, 1.79it/s]
35%|███▌ | 33/93 [00:15<00:31, 1.92it/s]
37%|███▋ | 34/93 [00:15<00:28, 2.11it/s]
38%|███▊ | 35/93 [00:16<00:24, 2.32it/s]
39%|███▊ | 36/93 [00:16<00:24, 2.35it/s]
40%|███▉ | 37/93 [00:16<00:24, 2.29it/s]
41%|████ | 38/93 [00:17<00:25, 2.15it/s]
42%|████▏ | 39/93 [00:17<00:25, 2.16it/s]
43%|████▎ | 40/93 [00:18<00:23, 2.28it/s]
44%|████▍ | 41/93 [00:18<00:22, 2.29it/s]
45%|████▌ | 42/93 [00:19<00:21, 2.36it/s]
46%|████▌ | 43/93 [00:19<00:20, 2.49it/s]
47%|████▋ | 44/93 [00:19<00:18, 2.64it/s]
48%|████▊ | 45/93 [00:20<00:18, 2.55it/s]
49%|████▉ | 46/93 [00:20<00:19, 2.43it/s]
51%|█████ | 47/93 [00:21<00:19, 2.30it/s]
52%|█████▏ | 48/93 [00:21<00:20, 2.18it/s]
53%|█████▎ | 49/93 [00:22<00:19, 2.30it/s]
54%|█████▍ | 50/93 [00:22<00:18, 2.34it/s]
55%|█████▍ | 51/93 [00:23<00:20, 2.03it/s]
56%|█████▌ | 52/93 [00:23<00:19, 2.13it/s]
57%|█████▋ | 53/93 [00:23<00:17, 2.26it/s]
58%|█████▊ | 54/93 [00:24<00:17, 2.23it/s]
59%|█████▉ | 55/93 [00:24<00:17, 2.22it/s]
60%|██████ | 56/93 [00:25<00:16, 2.30it/s]
61%|██████▏ | 57/93 [00:25<00:15, 2.37it/s]
62%|██████▏ | 58/93 [00:26<00:15, 2.33it/s]
63%|██████▎ | 59/93 [00:26<00:13, 2.49it/s]
65%|██████▍ | 60/93 [00:26<00:12, 2.65it/s]
66%|██████▌ | 61/93 [00:27<00:13, 2.41it/s]
67%|██████▋ | 62/93 [00:27<00:12, 2.48it/s]
68%|██████▊ | 63/93 [00:27<00:11, 2.65it/s]
69%|██████▉ | 64/93 [00:28<00:10, 2.68it/s]
70%|██████▉ | 65/93 [00:28<00:10, 2.64it/s]
71%|███████ | 66/93 [00:29<00:10, 2.58it/s]
72%|███████▏ | 67/93 [00:29<00:10, 2.59it/s]
73%|███████▎ | 68/93 [00:29<00:09, 2.60it/s]
74%|███████▍ | 69/93 [00:30<00:09, 2.43it/s]
75%|███████▌ | 70/93 [00:30<00:09, 2.37it/s]
76%|███████▋ | 71/93 [00:31<00:09, 2.24it/s]
77%|███████▋ | 72/93 [00:31<00:09, 2.21it/s]
78%|███████▊ | 73/93 [00:32<00:08, 2.32it/s]
80%|███████▉ | 74/93 [00:32<00:08, 2.32it/s]
81%|████████ | 75/93 [00:32<00:07, 2.36it/s]
82%|████████▏ | 76/93 [00:33<00:06, 2.46it/s]
83%|████████▎ | 77/93 [00:33<00:06, 2.57it/s]
84%|████████▍ | 78/93 [00:34<00:05, 2.61it/s]
85%|████████▍ | 79/93 [00:34<00:05, 2.46it/s]
86%|████████▌ | 80/93 [00:34<00:05, 2.39it/s]
87%|████████▋ | 81/93 [00:35<00:05, 2.35it/s]
88%|████████▊ | 82/93 [00:35<00:04, 2.50it/s]
89%|████████▉ | 83/93 [00:36<00:03, 2.54it/s]
90%|█████████ | 84/93 [00:36<00:03, 2.57it/s]
91%|█████████▏| 85/93 [00:36<00:03, 2.30it/s]
92%|█████████▏| 86/93 [00:37<00:03, 2.16it/s]
94%|█████████▎| 87/93 [00:37<00:02, 2.27it/s]
95%|█████████▍| 88/93 [00:38<00:02, 2.43it/s]
96%|█████████▌| 89/93 [00:38<00:01, 2.39it/s]
97%|█████████▋| 90/93 [00:39<00:01, 2.32it/s]
98%|█████████▊| 91/93 [00:39<00:00, 2.13it/s]
99%|█████████▉| 92/93 [00:40<00:00, 2.09it/s]
100%|██████████| 93/93 [00:40<00:00, 2.25it/s]
100%|██████████| 93/93 [00:40<00:00, 2.28it/s]
***** predict_test_ar_SA metrics *****
predict_ex_match_acc = 0.4455
predict_ex_match_acc_stderr = 0.0091
predict_intent_acc = 0.7061
predict_intent_acc_stderr = 0.0084
predict_loss = 0.5896
predict_runtime = 0:00:41.80
predict_samples = 2974
predict_samples_per_second = 71.142
predict_slot_micro_f1 = 0.5994
predict_slot_micro_f1_stderr = 0.0039
predict_steps_per_second = 2.225
02/05/2024 17:22:10 - INFO - __main__ - *** test_de_DE ***
[INFO|trainer.py:718] 2024-02-05 17:22:10,606 >> The following columns in the test set don't have a corresponding argument in `MT5ForConditionalGeneration.forward` and have been ignored: intent_str, id, annot_utt. If intent_str, id, annot_utt are not expected by `MT5ForConditionalGeneration.forward`, you can safely ignore this message.
[INFO|trainer.py:3199] 2024-02-05 17:22:10,609 >> ***** Running Prediction *****
[INFO|trainer.py:3201] 2024-02-05 17:22:10,610 >> Num examples = 2974
[INFO|trainer.py:3204] 2024-02-05 17:22:10,610 >> Batch size = 32
0%| | 0/93 [00:00<?, ?it/s]
2%|▏ | 2/93 [00:00<00:18, 4.88it/s]
3%|▎ | 3/93 [00:00<00:23, 3.78it/s]
4%|▍ | 4/93 [00:01<00:31, 2.80it/s]
5%|▌ | 5/93 [00:01<00:31, 2.77it/s]
6%|▋ | 6/93 [00:01<00:30, 2.84it/s]
8%|▊ | 7/93 [00:02<00:32, 2.63it/s]
9%|▊ | 8/93 [00:02<00:32, 2.64it/s]
10%|▉ | 9/93 [00:03<00:33, 2.52it/s]
11%|█ | 10/93 [00:03<00:30, 2.68it/s]
12%|█▏ | 11/93 [00:03<00:31, 2.64it/s]
13%|█▎ | 12/93 [00:04<00:32, 2.51it/s]
14%|█▍ | 13/93 [00:04<00:30, 2.61it/s]
15%|█▌ | 14/93 [00:05<00:30, 2.62it/s]
16%|█▌ | 15/93 [00:05<00:33, 2.33it/s]
17%|█▋ | 16/93 [00:06<00:35, 2.19it/s]
18%|█▊ | 17/93 [00:06<00:35, 2.16it/s]
19%|█▉ | 18/93 [00:07<00:33, 2.25it/s]
20%|██ | 19/93 [00:07<00:33, 2.24it/s]
22%|██▏ | 20/93 [00:07<00:32, 2.28it/s]
23%|██▎ | 21/93 [00:08<00:31, 2.32it/s]
24%|██▎ | 22/93 [00:08<00:34, 2.06it/s]
25%|██▍ | 23/93 [00:09<00:34, 2.04it/s]
26%|██▌ | 24/93 [00:09<00:32, 2.14it/s]
27%|██▋ | 25/93 [00:10<00:30, 2.20it/s]
28%|██▊ | 26/93 [00:10<00:29, 2.24it/s]
29%|██▉ | 27/93 [00:11<00:28, 2.34it/s]
30%|███ | 28/93 [00:13<01:00, 1.07it/s]
31%|███ | 29/93 [00:13<00:48, 1.31it/s]
32%|███▏ | 30/93 [00:14<00:42, 1.48it/s]
33%|███▎ | 31/93 [00:14<00:36, 1.72it/s]
34%|███▍ | 32/93 [00:14<00:33, 1.83it/s]
35%|███▌ | 33/93 [00:15<00:32, 1.83it/s]
37%|███▋ | 34/93 [00:15<00:29, 2.00it/s]
38%|███▊ | 35/93 [00:16<00:28, 2.00it/s]
39%|███▊ | 36/93 [00:16<00:26, 2.11it/s]
40%|███▉ | 37/93 [00:17<00:25, 2.18it/s]
41%|████ | 38/93 [00:17<00:24, 2.24it/s]
42%|████▏ | 39/93 [00:18<00:25, 2.15it/s]
43%|████▎ | 40/93 [00:18<00:23, 2.25it/s]
44%|████▍ | 41/93 [00:18<00:22, 2.35it/s]
45%|████▌ | 42/93 [00:19<00:21, 2.34it/s]
46%|████▌ | 43/93 [00:19<00:21, 2.37it/s]
47%|████▋ | 44/93 [00:20<00:19, 2.46it/s]
48%|████▊ | 45/93 [00:20<00:19, 2.42it/s]
49%|████▉ | 46/93 [00:20<00:18, 2.51it/s]
51%|█████ | 47/93 [00:21<00:17, 2.61it/s]
52%|█████▏ | 48/93 [00:21<00:17, 2.52it/s]
53%|█████▎ | 49/93 [00:22<00:17, 2.49it/s]
54%|█████▍ | 50/93 [00:22<00:18, 2.26it/s]
55%|█████▍ | 51/93 [00:23<00:18, 2.23it/s]
56%|█████▌ | 52/93 [00:23<00:20, 1.98it/s]
57%|█████▋ | 53/93 [00:24<00:19, 2.09it/s]
58%|█████▊ | 54/93 [00:24<00:17, 2.20it/s]
59%|█████▉ | 55/93 [00:24<00:16, 2.32it/s]
60%|██████ | 56/93 [00:25<00:15, 2.45it/s]
61%|██████▏ | 57/93 [00:25<00:15, 2.37it/s]
62%|██████▏ | 58/93 [00:26<00:15, 2.30it/s]
63%|██████▎ | 59/93 [00:26<00:14, 2.36it/s]
65%|██████▍ | 60/93 [00:26<00:13, 2.40it/s]
66%|██████▌ | 61/93 [00:27<00:14, 2.23it/s]
67%|██████▋ | 62/93 [00:27<00:13, 2.22it/s]
68%|██████▊ | 63/93 [00:28<00:13, 2.27it/s]
69%|██████▉ | 64/93 [00:28<00:13, 2.15it/s]
70%|██████▉ | 65/93 [00:29<00:11, 2.35it/s]
71%|███████ | 66/93 [00:29<00:11, 2.40it/s]
72%|███████▏ | 67/93 [00:29<00:10, 2.44it/s]
73%|███████▎ | 68/93 [00:30<00:10, 2.40it/s]
74%|███████▍ | 69/93 [00:30<00:10, 2.23it/s]
75%|███████▌ | 70/93 [00:31<00:10, 2.15it/s]
76%|███████▋ | 71/93 [00:31<00:10, 2.10it/s]
77%|███████▋ | 72/93 [00:32<00:10, 2.00it/s]
78%|███████▊ | 73/93 [00:32<00:09, 2.09it/s]
80%|███████▉ | 74/93 [00:33<00:08, 2.12it/s]
81%|████████ | 75/93 [00:33<00:08, 2.12it/s]
82%|████████▏ | 76/93 [00:34<00:08, 2.11it/s]
83%|████████▎ | 77/93 [00:34<00:07, 2.17it/s]
84%|████████▍ | 78/93 [00:35<00:08, 1.76it/s]
85%|████████▍ | 79/93 [00:36<00:07, 1.88it/s]
86%|████████▌ | 80/93 [00:36<00:06, 1.97it/s]
87%|████████▋ | 81/93 [00:36<00:05, 2.13it/s]
88%|████████▊ | 82/93 [00:37<00:05, 2.19it/s]
89%|████████▉ | 83/93 [00:37<00:04, 2.28it/s]
90%|█████████ | 84/93 [00:38<00:03, 2.32it/s]
91%|█████████▏| 85/93 [00:38<00:03, 2.36it/s]
92%|█████████▏| 86/93 [00:38<00:02, 2.36it/s]
94%|█████████▎| 87/93 [00:39<00:02, 2.36it/s]
95%|█████████▍| 88/93 [00:39<00:02, 2.45it/s]
96%|█████████▌| 89/93 [00:40<00:01, 2.41it/s]
97%|█████████▋| 90/93 [00:40<00:01, 2.46it/s]
98%|█████████▊| 91/93 [00:41<00:00, 2.23it/s]
99%|█████████▉| 92/93 [00:41<00:00, 2.34it/s]
100%|██████████| 93/93 [00:41<00:00, 2.43it/s]
100%|██████████| 93/93 [00:42<00:00, 2.20it/s]
***** predict_test_de_DE metrics *****
predict_ex_match_acc = 0.5662
predict_ex_match_acc_stderr = 0.0091
predict_intent_acc = 0.8366
predict_intent_acc_stderr = 0.0068
predict_loss = 0.4835
predict_runtime = 0:00:42.68
predict_samples = 2974
predict_samples_per_second = 69.67
predict_slot_micro_f1 = 0.6886
predict_slot_micro_f1_stderr = 0.0033
predict_steps_per_second = 2.179
02/05/2024 17:22:53 - INFO - __main__ - *** test_es_ES ***
[INFO|trainer.py:718] 2024-02-05 17:22:53,532 >> The following columns in the test set don't have a corresponding argument in `MT5ForConditionalGeneration.forward` and have been ignored: intent_str, id, annot_utt. If intent_str, id, annot_utt are not expected by `MT5ForConditionalGeneration.forward`, you can safely ignore this message.
[INFO|trainer.py:3199] 2024-02-05 17:22:53,534 >> ***** Running Prediction *****
[INFO|trainer.py:3201] 2024-02-05 17:22:53,534 >> Num examples = 2974
[INFO|trainer.py:3204] 2024-02-05 17:22:53,535 >> Batch size = 32
0%| | 0/93 [00:00<?, ?it/s]
2%|▏ | 2/93 [00:00<00:19, 4.60it/s]
3%|▎ | 3/93 [00:00<00:28, 3.15it/s]
4%|▍ | 4/93 [00:01<00:35, 2.48it/s]
5%|▌ | 5/93 [00:01<00:38, 2.30it/s]
6%|▋ | 6/93 [00:02<00:37, 2.32it/s]
8%|▊ | 7/93 [00:02<00:37, 2.28it/s]
9%|▊ | 8/93 [00:03<00:35, 2.38it/s]
10%|▉ | 9/93 [00:03<00:35, 2.37it/s]
11%|█ | 10/93 [00:04<00:34, 2.40it/s]
12%|█▏ | 11/93 [00:04<00:35, 2.30it/s]
13%|█▎ | 12/93 [00:05<00:37, 2.15it/s]
14%|█▍ | 13/93 [00:05<00:36, 2.17it/s]
15%|█▌ | 14/93 [00:05<00:36, 2.19it/s]
16%|█▌ | 15/93 [00:06<00:38, 2.03it/s]
17%|█▋ | 16/93 [00:07<00:39, 1.95it/s]
18%|█▊ | 17/93 [00:07<00:37, 2.02it/s]
19%|█▉ | 18/93 [00:07<00:35, 2.10it/s]
20%|██ | 19/93 [00:08<00:35, 2.10it/s]
22%|██▏ | 20/93 [00:08<00:33, 2.19it/s]
23%|██▎ | 21/93 [00:09<00:32, 2.20it/s]
24%|██▎ | 22/93 [00:10<00:37, 1.87it/s]
25%|██▍ | 23/93 [00:10<00:37, 1.87it/s]
26%|██▌ | 24/93 [00:11<00:35, 1.93it/s]
27%|██▋ | 25/93 [00:11<00:33, 2.03it/s]
28%|██▊ | 26/93 [00:11<00:32, 2.06it/s]
29%|██▉ | 27/93 [00:12<00:31, 2.08it/s]
30%|███ | 28/93 [00:14<01:03, 1.03it/s]
31%|███ | 29/93 [00:14<00:52, 1.22it/s]
32%|███▏ | 30/93 [00:15<00:45, 1.39it/s]
33%|███▎ | 31/93 [00:15<00:38, 1.61it/s]
34%|███▍ | 32/93 [00:16<00:37, 1.63it/s]
35%|███▌ | 33/93 [00:17<00:39, 1.53it/s]
37%|███▋ | 34/93 [00:17<00:34, 1.70it/s]
38%|███▊ | 35/93 [00:18<00:32, 1.80it/s]
39%|███▊ | 36/93 [00:18<00:31, 1.82it/s]
40%|███▉ | 37/93 [00:19<00:32, 1.71it/s]
41%|████ | 38/93 [00:19<00:32, 1.72it/s]
42%|████▏ | 39/93 [00:20<00:29, 1.81it/s]
43%|████▎ | 40/93 [00:20<00:28, 1.88it/s]
44%|████▍ | 41/93 [00:21<00:25, 2.01it/s]
45%|████▌ | 42/93 [00:21<00:24, 2.07it/s]
46%|████▌ | 43/93 [00:22<00:22, 2.19it/s]
47%|████▋ | 44/93 [00:22<00:21, 2.29it/s]
48%|████▊ | 45/93 [00:23<00:21, 2.19it/s]
49%|████▉ | 46/93 [00:23<00:23, 2.00it/s]
51%|█████ | 47/93 [00:23<00:21, 2.16it/s]
52%|█████▏ | 48/93 [00:24<00:24, 1.84it/s]
53%|█████▎ | 49/93 [00:25<00:21, 2.00it/s]
54%|█████▍ | 50/93 [00:25<00:21, 1.97it/s]
55%|█████▍ | 51/93 [00:26<00:20, 2.07it/s]
56%|█████▌ | 52/93 [00:26<00:22, 1.80it/s]
57%|█████▋ | 53/93 [00:27<00:20, 1.95it/s]
58%|█████▊ | 54/93 [00:27<00:19, 2.02it/s]
59%|█████▉ | 55/93 [00:28<00:17, 2.11it/s]
60%|██████ | 56/93 [00:28<00:17, 2.13it/s]
61%|██████▏ | 57/93 [00:29<00:18, 2.00it/s]
62%|██████▏ | 58/93 [00:29<00:17, 2.06it/s]
63%|██████▎ | 59/93 [00:30<00:17, 1.97it/s]
65%|██████▍ | 60/93 [00:30<00:15, 2.13it/s]
66%|██████▌ | 61/93 [00:31<00:15, 2.08it/s]
67%|██████▋ | 62/93 [00:31<00:15, 2.00it/s]
68%|██████▊ | 63/93 [00:31<00:13, 2.16it/s]
69%|██████▉ | 64/93 [00:32<00:12, 2.27it/s]
70%|██████▉ | 65/93 [00:32<00:12, 2.32it/s]
71%|███████ | 66/93 [00:33<00:11, 2.39it/s]
72%|███████▏ | 67/93 [00:33<00:13, 1.94it/s]
73%|███████▎ | 68/93 [00:34<00:13, 1.87it/s]
74%|███████▍ | 69/93 [00:34<00:12, 1.87it/s]
75%|███████▌ | 70/93 [00:35<00:12, 1.89it/s]
76%|███████▋ | 71/93 [00:36<00:12, 1.81it/s]
77%|███████▋ | 72/93 [00:36<00:10, 1.93it/s]
78%|███████▊ | 73/93 [00:36<00:09, 2.05it/s]
80%|███████▉ | 74/93 [00:37<00:09, 2.01it/s]
81%|████████ | 75/93 [00:38<00:09, 1.95it/s]
82%|████████▏ | 76/93 [00:38<00:09, 1.84it/s]
83%|████████▎ | 77/93 [00:39<00:08, 1.81it/s]
84%|████████▍ | 78/93 [00:41<00:14, 1.00it/s]
85%|████████▍ | 79/93 [00:41<00:11, 1.21it/s]
86%|████████▌ | 80/93 [00:42<00:09, 1.34it/s]
87%|████████▋ | 81/93 [00:42<00:07, 1.51it/s]
88%|████████▊ | 82/93 [00:43<00:06, 1.67it/s]
89%|████████▉ | 83/93 [00:43<00:05, 1.82it/s]
90%|█████████ | 84/93 [00:44<00:04, 1.89it/s]
91%|█████████▏| 85/93 [00:44<00:04, 1.91it/s]
92%|█████████▏| 86/93 [00:45<00:03, 1.90it/s]
94%|█████████▎| 87/93 [00:45<00:03, 2.00it/s]
95%|█████████▍| 88/93 [00:45<00:02, 2.16it/s]
96%|█████████▌| 89/93 [00:46<00:01, 2.05it/s]
97%|█████████▋| 90/93 [00:46<00:01, 2.14it/s]
98%|█████████▊| 91/93 [00:47<00:00, 2.02it/s]
99%|█████████▉| 92/93 [00:47<00:00, 2.02it/s]
100%|██████████| 93/93 [00:48<00:00, 2.20it/s]
100%|██████████| 93/93 [00:48<00:00, 1.91it/s]
***** predict_test_es_ES metrics *****
predict_ex_match_acc = 0.6009
predict_ex_match_acc_stderr = 0.009
predict_intent_acc = 0.8521
predict_intent_acc_stderr = 0.0065
predict_loss = 0.2917
predict_runtime = 0:00:49.03
predict_samples = 2974
predict_samples_per_second = 60.649
predict_slot_micro_f1 = 0.7136
predict_slot_micro_f1_stderr = 0.0031
predict_steps_per_second = 1.897
02/05/2024 17:23:42 - INFO - __main__ - *** test_fr_FR ***
[INFO|trainer.py:718] 2024-02-05 17:23:42,811 >> The following columns in the test set don't have a corresponding argument in `MT5ForConditionalGeneration.forward` and have been ignored: intent_str, id, annot_utt. If intent_str, id, annot_utt are not expected by `MT5ForConditionalGeneration.forward`, you can safely ignore this message.
[INFO|trainer.py:3199] 2024-02-05 17:23:42,813 >> ***** Running Prediction *****
[INFO|trainer.py:3201] 2024-02-05 17:23:42,814 >> Num examples = 2974
[INFO|trainer.py:3204] 2024-02-05 17:23:42,814 >> Batch size = 32
0%| | 0/93 [00:00<?, ?it/s]
2%|▏ | 2/93 [00:00<00:19, 4.61it/s]
3%|▎ | 3/93 [00:00<00:29, 3.00it/s]
4%|▍ | 4/93 [00:01<00:36, 2.47it/s]
5%|▌ | 5/93 [00:02<00:40, 2.18it/s]
6%|▋ | 6/93 [00:02<00:39, 2.19it/s]
8%|▊ | 7/93 [00:02<00:40, 2.12it/s]
9%|▊ | 8/93 [00:03<00:38, 2.18it/s]
10%|▉ | 9/93 [00:03<00:38, 2.18it/s]
11%|█ | 10/93 [00:04<00:37, 2.24it/s]
12%|█▏ | 11/93 [00:04<00:38, 2.11it/s]
13%|█▎ | 12/93 [00:05<00:38, 2.08it/s]
14%|█▍ | 13/93 [00:05<00:38, 2.05it/s]
15%|█▌ | 14/93 [00:06<00:39, 2.01it/s]
16%|█▌ | 15/93 [00:06<00:40, 1.91it/s]
17%|█▋ | 16/93 [00:07<00:41, 1.85it/s]
18%|█▊ | 17/93 [00:08<00:42, 1.78it/s]
19%|█▉ | 18/93 [00:08<00:39, 1.90it/s]
20%|██ | 19/93 [00:09<00:37, 1.99it/s]
22%|██▏ | 20/93 [00:09<00:36, 1.98it/s]
23%|██▎ | 21/93 [00:09<00:34, 2.07it/s]
24%|██▎ | 22/93 [00:10<00:37, 1.91it/s]
25%|██▍ | 23/93 [00:11<00:37, 1.84it/s]
26%|██▌ | 24/93 [00:11<00:38, 1.80it/s]
27%|██▋ | 25/93 [00:12<00:37, 1.83it/s]
28%|██▊ | 26/93 [00:12<00:34, 1.92it/s]
29%|██▉ | 27/93 [00:13<00:33, 1.96it/s]
30%|███ | 28/93 [00:15<01:05, 1.00s/it]
31%|███ | 29/93 [00:15<00:53, 1.20it/s]
32%|███▏ | 30/93 [00:16<00:45, 1.37it/s]
33%|███▎ | 31/93 [00:16<00:39, 1.57it/s]
34%|███▍ | 32/93 [00:17<00:36, 1.67it/s]
35%|███▌ | 33/93 [00:17<00:33, 1.80it/s]
37%|███▋ | 34/93 [00:18<00:30, 1.95it/s]
38%|███▊ | 35/93 [00:18<00:31, 1.83it/s]
39%|███▊ | 36/93 [00:19<00:30, 1.86it/s]
40%|███▉ | 37/93 [00:19<00:30, 1.85it/s]
41%|████ | 38/93 [00:20<00:30, 1.80it/s]
42%|████▏ | 39/93 [00:20<00:29, 1.84it/s]
43%|████▎ | 40/93 [00:21<00:28, 1.87it/s]
44%|████▍ | 41/93 [00:21<00:27, 1.90it/s]
45%|████▌ | 42/93 [00:22<00:26, 1.96it/s]
46%|████▌ | 43/93 [00:22<00:25, 1.94it/s]
47%|████▋ | 44/93 [00:23<00:23, 2.06it/s]
48%|████▊ | 45/93 [00:23<00:23, 2.05it/s]
49%|████▉ | 46/93 [00:24<00:22, 2.11it/s]
51%|█████ | 47/93 [00:24<00:21, 2.13it/s]
52%|█████▏ | 48/93 [00:25<00:23, 1.88it/s]
53%|█████▎ | 49/93 [00:25<00:23, 1.86it/s]
54%|█████▍ | 50/93 [00:26<00:23, 1.87it/s]
55%|█████▍ | 51/93 [00:26<00:21, 1.93it/s]
56%|█████▌ | 52/93 [00:27<00:24, 1.66it/s]
57%|█████▋ | 53/93 [00:28<00:21, 1.83it/s]
58%|█████▊ | 54/93 [00:28<00:20, 1.92it/s]
59%|█████▉ | 55/93 [00:29<00:19, 1.94it/s]
60%|██████ | 56/93 [00:29<00:18, 1.96it/s]
61%|██████▏ | 57/93 [00:30<00:17, 2.00it/s]
62%|██████▏ | 58/93 [00:30<00:17, 1.99it/s]
63%|██████▎ | 59/93 [00:31<00:16, 2.03it/s]
65%|██████▍ | 60/93 [00:31<00:15, 2.13it/s]
66%|██████▌ | 61/93 [00:32<00:16, 1.98it/s]
67%|██████▋ | 62/93 [00:32<00:15, 1.97it/s]
68%|██████▊ | 63/93 [00:32<00:14, 2.10it/s]
69%|██████▉ | 64/93 [00:33<00:13, 2.21it/s]
70%|██████▉ | 65/93 [00:33<00:12, 2.28it/s]
71%|███████ | 66/93 [00:34<00:11, 2.27it/s]
72%|███████▏ | 67/93 [00:34<00:11, 2.22it/s]
73%|███████▎ | 68/93 [00:35<00:12, 1.93it/s]
74%|███████▍ | 69/93 [00:35<00:12, 1.89it/s]
75%|███████▌ | 70/93 [00:36<00:12, 1.85it/s]
76%|███████▋ | 71/93 [00:38<00:21, 1.01it/s]
77%|███████▋ | 72/93 [00:39<00:17, 1.17it/s]
78%|███████▊ | 73/93 [00:39<00:14, 1.38it/s]
80%|███████▉ | 74/93 [00:40<00:12, 1.51it/s]
81%|████████ | 75/93 [00:40<00:11, 1.56it/s]
82%|████████▏ | 76/93 [00:41<00:10, 1.59it/s]
83%|████████▎ | 77/93 [00:41<00:09, 1.67it/s]
84%|████████▍ | 78/93 [00:42<00:09, 1.64it/s]
85%|████████▍ | 79/93 [00:42<00:07, 1.76it/s]
86%|████████▌ | 80/93 [00:43<00:07, 1.80it/s]
87%|████████▋ | 81/93 [00:43<00:06, 1.90it/s]
88%|████████▊ | 82/93 [00:44<00:05, 1.99it/s]
89%|████████▉ | 83/93 [00:44<00:04, 2.11it/s]
90%|█████████ | 84/93 [00:45<00:04, 2.13it/s]
91%|█████████▏| 85/93 [00:45<00:03, 2.04it/s]
92%|█████████▏| 86/93 [00:46<00:03, 2.07it/s]
94%|█████████▎| 87/93 [00:46<00:02, 2.12it/s]
95%|█████████▍| 88/93 [00:47<00:02, 2.19it/s]
96%|█████████▌| 89/93 [00:47<00:01, 2.10it/s]
97%|█████████▋| 90/93 [00:48<00:01, 2.12it/s]
98%|█████████▊| 91/93 [00:48<00:01, 1.95it/s]
99%|█████████▉| 92/93 [00:49<00:00, 1.85it/s]
100%|██████████| 93/93 [00:49<00:00, 2.04it/s]
100%|██████████| 93/93 [00:49<00:00, 1.87it/s]
***** predict_test_fr_FR metrics *****
predict_ex_match_acc = 0.459
predict_ex_match_acc_stderr = 0.0091
predict_intent_acc = 0.8366
predict_intent_acc_stderr = 0.0068
predict_loss = 0.675
predict_runtime = 0:00:50.38
predict_samples = 2974
predict_samples_per_second = 59.028
predict_slot_micro_f1 = 0.5132
predict_slot_micro_f1_stderr = 0.0034
predict_steps_per_second = 1.846
02/05/2024 17:24:33 - INFO - __main__ - *** test_hu_HU ***
[INFO|trainer.py:718] 2024-02-05 17:24:33,448 >> The following columns in the test set don't have a corresponding argument in `MT5ForConditionalGeneration.forward` and have been ignored: intent_str, id, annot_utt. If intent_str, id, annot_utt are not expected by `MT5ForConditionalGeneration.forward`, you can safely ignore this message.
[INFO|trainer.py:3199] 2024-02-05 17:24:33,451 >> ***** Running Prediction *****
[INFO|trainer.py:3201] 2024-02-05 17:24:33,451 >> Num examples = 2974
[INFO|trainer.py:3204] 2024-02-05 17:24:33,451 >> Batch size = 32
0%| | 0/93 [00:00<?, ?it/s]
2%|▏ | 2/93 [00:00<00:15, 5.73it/s]
3%|▎ | 3/93 [00:00<00:22, 4.04it/s]
4%|▍ | 4/93 [00:01<00:33, 2.66it/s]
5%|▌ | 5/93 [00:01<00:33, 2.64it/s]
6%|▋ | 6/93 [00:02<00:31, 2.76it/s]
8%|▊ | 7/93 [00:02<00:32, 2.64it/s]
9%|▊ | 8/93 [00:02<00:31, 2.68it/s]
10%|▉ | 9/93 [00:03<00:31, 2.66it/s]
11%|█ | 10/93 [00:03<00:31, 2.60it/s]
12%|█▏ | 11/93 [00:03<00:30, 2.65it/s]
13%|█▎ | 12/93 [00:04<00:31, 2.56it/s]
14%|█▍ | 13/93 [00:04<00:32, 2.45it/s]
15%|█▌ | 14/93 [00:05<00:32, 2.42it/s]
16%|█▌ | 15/93 [00:05<00:31, 2.49it/s]
17%|█▋ | 16/93 [00:06<00:35, 2.15it/s]
18%|█▊ | 17/93 [00:06<00:35, 2.14it/s]
19%|█▉ | 18/93 [00:07<00:33, 2.21it/s]
20%|██ | 19/93 [00:07<00:31, 2.37it/s]
22%|██▏ | 20/93 [00:07<00:29, 2.48it/s]
23%|██▎ | 21/93 [00:08<00:29, 2.47it/s]
24%|██▎ | 22/93 [00:08<00:28, 2.48it/s]
25%|██▍ | 23/93 [00:09<00:29, 2.35it/s]
26%|██▌ | 24/93 [00:09<00:30, 2.26it/s]
27%|██▋ | 25/93 [00:10<00:29, 2.27it/s]
28%|██▊ | 26/93 [00:10<00:28, 2.37it/s]
29%|██▉ | 27/93 [00:10<00:26, 2.46it/s]
30%|███ | 28/93 [00:12<00:59, 1.08it/s]
31%|███ | 29/93 [00:13<00:48, 1.32it/s]
32%|███▏ | 30/93 [00:13<00:43, 1.46it/s]
33%|███▎ | 31/93 [00:14<00:36, 1.70it/s]
34%|███▍ | 32/93 [00:14<00:34, 1.75it/s]
35%|███▌ | 33/93 [00:15<00:33, 1.80it/s]
37%|███▋ | 34/93 [00:15<00:30, 1.92it/s]
38%|███▊ | 35/93 [00:16<00:28, 2.05it/s]
39%|███▊ | 36/93 [00:16<00:26, 2.13it/s]
40%|███▉ | 37/93 [00:16<00:25, 2.20it/s]
41%|████ | 38/93 [00:17<00:25, 2.16it/s]
42%|████▏ | 39/93 [00:17<00:25, 2.13it/s]
43%|████▎ | 40/93 [00:18<00:23, 2.23it/s]
44%|████▍ | 41/93 [00:18<00:22, 2.31it/s]
45%|████▌ | 42/93 [00:19<00:21, 2.39it/s]
46%|████▌ | 43/93 [00:19<00:20, 2.47it/s]
47%|████▋ | 44/93 [00:19<00:21, 2.24it/s]
48%|████▊ | 45/93 [00:20<00:21, 2.24it/s]
49%|████▉ | 46/93 [00:20<00:21, 2.20it/s]
51%|█████ | 47/93 [00:21<00:19, 2.32it/s]
52%|█████▏ | 48/93 [00:21<00:19, 2.33it/s]
53%|█████▎ | 49/93 [00:22<00:18, 2.44it/s]
54%|█████▍ | 50/93 [00:22<00:17, 2.48it/s]
55%|█████▍ | 51/93 [00:22<00:16, 2.50it/s]
56%|█████▌ | 52/93 [00:23<00:16, 2.46it/s]
57%|█████▋ | 53/93 [00:23<00:16, 2.40it/s]
58%|█████▊ | 54/93 [00:24<00:16, 2.34it/s]
59%|█████▉ | 55/93 [00:24<00:15, 2.42it/s]
60%|██████ | 56/93 [00:24<00:14, 2.51it/s]
61%|██████▏ | 57/93 [00:25<00:14, 2.45it/s]
62%|██████▏ | 58/93 [00:25<00:13, 2.53it/s]
63%|██████▎ | 59/93 [00:26<00:13, 2.61it/s]
65%|██████▍ | 60/93 [00:26<00:12, 2.66it/s]
66%|██████▌ | 61/93 [00:26<00:13, 2.32it/s]
67%|██████▋ | 62/93 [00:27<00:12, 2.39it/s]
68%|██████▊ | 63/93 [00:27<00:12, 2.44it/s]
69%|██████▉ | 64/93 [00:28<00:13, 2.15it/s]
70%|██████▉ | 65/93 [00:28<00:12, 2.33it/s]
71%|███████ | 66/93 [00:29<00:11, 2.37it/s]
72%|███████▏ | 67/93 [00:29<00:10, 2.44it/s]
73%|███████▎ | 68/93 [00:29<00:11, 2.24it/s]
74%|███████▍ | 69/93 [00:30<00:11, 2.11it/s]
75%|███████▌ | 70/93 [00:30<00:10, 2.19it/s]
76%|███████▋ | 71/93 [00:31<00:11, 1.97it/s]
77%|███████▋ | 72/93 [00:31<00:09, 2.10it/s]
78%|███████▊ | 73/93 [00:32<00:09, 2.21it/s]
80%|███████▉ | 74/93 [00:32<00:08, 2.24it/s]
81%|████████ | 75/93 [00:33<00:08, 2.21it/s]
82%|████████▏ | 76/93 [00:33<00:07, 2.28it/s]
83%|████████▎ | 77/93 [00:34<00:06, 2.29it/s]
84%|████████▍ | 78/93 [00:34<00:06, 2.24it/s]
85%|████████▍ | 79/93 [00:35<00:06, 2.15it/s]
86%|████████▌ | 80/93 [00:35<00:06, 2.11it/s]
87%|████████▋ | 81/93 [00:35<00:05, 2.26it/s]
88%|████████▊ | 82/93 [00:36<00:04, 2.20it/s]
89%|████████▉ | 83/93 [00:36<00:04, 2.20it/s]
90%|█████████ | 84/93 [00:37<00:03, 2.30it/s]
91%|█████████▏| 85/93 [00:37<00:03, 2.18it/s]
92%|█████████▏| 86/93 [00:38<00:03, 1.97it/s]
94%|█████████▎| 87/93 [00:38<00:02, 2.07it/s]
95%|█████████▍| 88/93 [00:39<00:02, 2.24it/s]
96%|█████████▌| 89/93 [00:39<00:01, 2.16it/s]
97%|█████████▋| 90/93 [00:40<00:01, 2.28it/s]
98%|█████████▊| 91/93 [00:40<00:00, 2.15it/s]
99%|█████████▉| 92/93 [00:41<00:00, 2.16it/s]
100%|██████████| 93/93 [00:41<00:00, 2.37it/s]
100%|██████████| 93/93 [00:41<00:00, 2.23it/s]
***** predict_test_hu_HU metrics *****
predict_ex_match_acc = 0.273
predict_ex_match_acc_stderr = 0.0082
predict_intent_acc = 0.5454
predict_intent_acc_stderr = 0.0091
predict_loss = 0.7601
predict_runtime = 0:00:42.04
predict_samples = 2974
predict_samples_per_second = 70.741
predict_slot_micro_f1 = 0.5011
predict_slot_micro_f1_stderr = 0.0038
predict_steps_per_second = 2.212
02/05/2024 17:25:15 - INFO - __main__ - *** test_ko_KR ***
[INFO|trainer.py:718] 2024-02-05 17:25:15,739 >> The following columns in the test set don't have a corresponding argument in `MT5ForConditionalGeneration.forward` and have been ignored: intent_str, id, annot_utt. If intent_str, id, annot_utt are not expected by `MT5ForConditionalGeneration.forward`, you can safely ignore this message.
[INFO|trainer.py:3199] 2024-02-05 17:25:15,741 >> ***** Running Prediction *****
[INFO|trainer.py:3201] 2024-02-05 17:25:15,742 >> Num examples = 2974
[INFO|trainer.py:3204] 2024-02-05 17:25:15,742 >> Batch size = 32
0%| | 0/93 [00:00<?, ?it/s]
2%|▏ | 2/93 [00:00<00:18, 4.96it/s]
3%|▎ | 3/93 [00:00<00:21, 4.19it/s]
4%|▍ | 4/93 [00:01<00:25, 3.42it/s]
5%|▌ | 5/93 [00:01<00:26, 3.33it/s]
6%|▋ | 6/93 [00:01<00:25, 3.36it/s]
8%|▊ | 7/93 [00:02<00:26, 3.19it/s]
9%|▊ | 8/93 [00:02<00:27, 3.12it/s]
10%|▉ | 9/93 [00:02<00:27, 3.05it/s]
11%|█ | 10/93 [00:03<00:27, 3.04it/s]
12%|█▏ | 11/93 [00:03<00:27, 3.01it/s]
13%|█▎ | 12/93 [00:03<00:28, 2.83it/s]
14%|█▍ | 13/93 [00:04<00:29, 2.70it/s]
15%|█▌ | 14/93 [00:04<00:28, 2.79it/s]
16%|█▌ | 15/93 [00:04<00:28, 2.70it/s]
17%|█▋ | 16/93 [00:05<00:28, 2.75it/s]
18%|█▊ | 17/93 [00:05<00:27, 2.76it/s]
19%|█▉ | 18/93 [00:06<00:28, 2.68it/s]
20%|██ | 19/93 [00:06<00:27, 2.70it/s]
22%|██▏ | 20/93 [00:06<00:27, 2.67it/s]
23%|██▎ | 21/93 [00:07<00:26, 2.75it/s]
24%|██▎ | 22/93 [00:07<00:25, 2.75it/s]
25%|██▍ | 23/93 [00:07<00:25, 2.71it/s]
26%|██▌ | 24/93 [00:08<00:24, 2.83it/s]
27%|██▋ | 25/93 [00:08<00:24, 2.75it/s]
28%|██▊ | 26/93 [00:08<00:25, 2.63it/s]
29%|██▉ | 27/93 [00:09<00:24, 2.73it/s]
30%|███ | 28/93 [00:09<00:24, 2.62it/s]
31%|███ | 29/93 [00:10<00:23, 2.72it/s]
32%|███▏ | 30/93 [00:10<00:23, 2.72it/s]
33%|███▎ | 31/93 [00:10<00:22, 2.78it/s]
34%|███▍ | 32/93 [00:11<00:23, 2.63it/s]
35%|███▌ | 33/93 [00:11<00:22, 2.66it/s]
37%|███▋ | 34/93 [00:11<00:21, 2.76it/s]
38%|███▊ | 35/93 [00:12<00:23, 2.45it/s]
39%|███▊ | 36/93 [00:12<00:22, 2.58it/s]
40%|███▉ | 37/93 [00:13<00:21, 2.66it/s]
41%|████ | 38/93 [00:13<00:21, 2.60it/s]
42%|████▏ | 39/93 [00:13<00:21, 2.55it/s]
43%|████▎ | 40/93 [00:14<00:20, 2.59it/s]
44%|████▍ | 41/93 [00:14<00:19, 2.66it/s]
45%|████▌ | 42/93 [00:14<00:18, 2.75it/s]
46%|████▌ | 43/93 [00:15<00:18, 2.68it/s]
47%|████▋ | 44/93 [00:15<00:18, 2.71it/s]
48%|████▊ | 45/93 [00:16<00:17, 2.79it/s]
49%|████▉ | 46/93 [00:16<00:16, 2.87it/s]
51%|█████ | 47/93 [00:16<00:16, 2.86it/s]
52%|█████▏ | 48/93 [00:17<00:16, 2.77it/s]
53%|█████▎ | 49/93 [00:17<00:15, 2.87it/s]
54%|█████▍ | 50/93 [00:17<00:15, 2.80it/s]
55%|█████▍ | 51/93 [00:18<00:14, 2.82it/s]
56%|█████▌ | 52/93 [00:18<00:15, 2.68it/s]
57%|█████▋ | 53/93 [00:18<00:15, 2.62it/s]
58%|█████▊ | 54/93 [00:19<00:14, 2.71it/s]
59%|█████▉ | 55/93 [00:19<00:13, 2.80it/s]
60%|██████ | 56/93 [00:20<00:13, 2.75it/s]
61%|██████▏ | 57/93 [00:20<00:13, 2.65it/s]
62%|██████▏ | 58/93 [00:20<00:12, 2.71it/s]
63%|██████▎ | 59/93 [00:21<00:12, 2.74it/s]
65%|██████▍ | 60/93 [00:21<00:11, 2.81it/s]
66%|██████▌ | 61/93 [00:21<00:11, 2.67it/s]
67%|██████▋ | 62/93 [00:22<00:11, 2.76it/s]
68%|██████▊ | 63/93 [00:22<00:10, 2.88it/s]
69%|██████▉ | 64/93 [00:22<00:10, 2.85it/s]
70%|██████▉ | 65/93 [00:23<00:09, 2.88it/s]
71%|███████ | 66/93 [00:23<00:09, 2.96it/s]
72%|███████▏ | 67/93 [00:24<00:09, 2.68it/s]
73%|███████▎ | 68/93 [00:24<00:09, 2.63it/s]
74%|███████▍ | 69/93 [00:24<00:08, 2.81it/s]
75%|███████▌ | 70/93 [00:25<00:08, 2.73it/s]
76%|███████▋ | 71/93 [00:25<00:08, 2.59it/s]
77%|███████▋ | 72/93 [00:25<00:08, 2.58it/s]
78%|███████▊ | 73/93 [00:26<00:07, 2.68it/s]
80%|███████▉ | 74/93 [00:26<00:07, 2.53it/s]
81%|████████ | 75/93 [00:27<00:07, 2.51it/s]
82%|████████▏ | 76/93 [00:27<00:06, 2.58it/s]
83%|████████▎ | 77/93 [00:27<00:05, 2.68it/s]
84%|████████▍ | 78/93 [00:28<00:05, 2.63it/s]
85%|████████▍ | 79/93 [00:28<00:05, 2.65it/s]
86%|████████▌ | 80/93 [00:28<00:04, 2.73it/s]
87%|████████▋ | 81/93 [00:29<00:04, 2.79it/s]
88%|████████▊ | 82/93 [00:29<00:04, 2.67it/s]
89%|████████▉ | 83/93 [00:30<00:03, 2.66it/s]
90%|█████████ | 84/93 [00:30<00:03, 2.72it/s]
91%|█████████▏| 85/93 [00:30<00:03, 2.61it/s]
92%|█████████▏| 86/93 [00:31<00:02, 2.61it/s]
94%|█████████▎| 87/93 [00:31<00:02, 2.77it/s]
95%|█████████▍| 88/93 [00:31<00:01, 2.84it/s]
96%|█████████▌| 89/93 [00:32<00:01, 2.82it/s]
97%|█████████▋| 90/93 [00:32<00:01, 2.74it/s]
98%|█████████▊| 91/93 [00:32<00:00, 2.75it/s]
99%|█████████▉| 92/93 [00:33<00:00, 2.74it/s]
100%|██████████| 93/93 [00:33<00:00, 2.73it/s]
100%|██████████| 93/93 [00:33<00:00, 2.74it/s]
***** predict_test_ko_KR metrics *****
predict_ex_match_acc = 0.0333
predict_ex_match_acc_stderr = 0.0033
predict_intent_acc = 0.0568
predict_intent_acc_stderr = 0.0042
predict_loss = 1.5014
predict_runtime = 0:00:34.26
predict_samples = 2974
predict_samples_per_second = 86.783
predict_slot_micro_f1 = 0.1925
predict_slot_micro_f1_stderr = 0.0033
predict_steps_per_second = 2.714
02/05/2024 17:25:50 - INFO - __main__ - *** test_nl_NL ***
[INFO|trainer.py:718] 2024-02-05 17:25:50,247 >> The following columns in the test set don't have a corresponding argument in `MT5ForConditionalGeneration.forward` and have been ignored: intent_str, id, annot_utt. If intent_str, id, annot_utt are not expected by `MT5ForConditionalGeneration.forward`, you can safely ignore this message.
[INFO|trainer.py:3199] 2024-02-05 17:25:50,249 >> ***** Running Prediction *****
[INFO|trainer.py:3201] 2024-02-05 17:25:50,250 >> Num examples = 2974
[INFO|trainer.py:3204] 2024-02-05 17:25:50,250 >> Batch size = 32
0%| | 0/93 [00:00<?, ?it/s]
2%|▏ | 2/93 [00:00<00:20, 4.52it/s]
3%|▎ | 3/93 [00:00<00:31, 2.82it/s]
4%|▍ | 4/93 [00:01<00:33, 2.64it/s]
5%|▌ | 5/93 [00:01<00:33, 2.63it/s]
6%|▋ | 6/93 [00:02<00:33, 2.56it/s]
8%|▊ | 7/93 [00:02<00:35, 2.41it/s]
9%|▊ | 8/93 [00:03<00:35, 2.39it/s]
10%|▉ | 9/93 [00:03<00:36, 2.32it/s]
11%|█ | 10/93 [00:04<00:36, 2.25it/s]
12%|█▏ | 11/93 [00:04<00:37, 2.21it/s]
13%|█▎ | 12/93 [00:04<00:37, 2.17it/s]
14%|█▍ | 13/93 [00:05<00:36, 2.18it/s]
15%|█▌ | 14/93 [00:05<00:35, 2.25it/s]
16%|█▌ | 15/93 [00:06<00:39, 1.99it/s]
17%|█▋ | 16/93 [00:07<00:40, 1.91it/s]
18%|█▊ | 17/93 [00:07<00:40, 1.88it/s]
19%|█▉ | 18/93 [00:08<00:37, 1.97it/s]
20%|██ | 19/93 [00:08<00:36, 2.05it/s]
22%|██▏ | 20/93 [00:08<00:34, 2.10it/s]
23%|██▎ | 21/93 [00:09<00:32, 2.19it/s]
24%|██▎ | 22/93 [00:09<00:36, 1.96it/s]
25%|██▍ | 23/93 [00:10<00:34, 2.02it/s]
26%|██▌ | 24/93 [00:10<00:34, 2.00it/s]
27%|██▋ | 25/93 [00:11<00:33, 2.04it/s]
28%|██▊ | 26/93 [00:11<00:31, 2.10it/s]
29%|██▉ | 27/93 [00:12<00:30, 2.18it/s]
30%|███ | 28/93 [00:14<01:01, 1.05it/s]
31%|███ | 29/93 [00:14<00:49, 1.29it/s]
32%|███▏ | 30/93 [00:15<00:42, 1.47it/s]
33%|███▎ | 31/93 [00:15<00:37, 1.64it/s]
34%|███▍ | 32/93 [00:16<00:35, 1.74it/s]
35%|███▌ | 33/93 [00:16<00:34, 1.74it/s]
37%|███▋ | 34/93 [00:17<00:30, 1.93it/s]
38%|███▊ | 35/93 [00:17<00:29, 1.95it/s]
39%|███▊ | 36/93 [00:18<00:27, 2.04it/s]
40%|███▉ | 37/93 [00:18<00:26, 2.08it/s]
41%|████ | 38/93 [00:19<00:30, 1.78it/s]
42%|████▏ | 39/93 [00:19<00:30, 1.78it/s]
43%|████▎ | 40/93 [00:20<00:27, 1.93it/s]
44%|████▍ | 41/93 [00:20<00:24, 2.09it/s]
45%|████▌ | 42/93 [00:21<00:23, 2.16it/s]
46%|████▌ | 43/93 [00:21<00:22, 2.27it/s]
47%|████▋ | 44/93 [00:21<00:21, 2.32it/s]
48%|████▊ | 45/93 [00:22<00:21, 2.28it/s]
49%|████▉ | 46/93 [00:22<00:20, 2.29it/s]
51%|█████ | 47/93 [00:23<00:19, 2.39it/s]
52%|█████▏ | 48/93 [00:23<00:18, 2.37it/s]
53%|█████▎ | 49/93 [00:23<00:18, 2.38it/s]
54%|█████▍ | 50/93 [00:24<00:17, 2.41it/s]
55%|█████▍ | 51/93 [00:24<00:19, 2.18it/s]
56%|█████▌ | 52/93 [00:25<00:19, 2.10it/s]
57%|█████▋ | 53/93 [00:25<00:19, 2.07it/s]
58%|█████▊ | 54/93 [00:26<00:18, 2.14it/s]
59%|█████▉ | 55/93 [00:26<00:16, 2.30it/s]
60%|██████ | 56/93 [00:27<00:15, 2.36it/s]
61%|██████▏ | 57/93 [00:27<00:15, 2.33it/s]
62%|██████▏ | 58/93 [00:28<00:15, 2.25it/s]
63%|██████▎ | 59/93 [00:28<00:14, 2.27it/s]
65%|██████▍ | 60/93 [00:28<00:14, 2.34it/s]
66%|██████▌ | 61/93 [00:29<00:14, 2.15it/s]
67%|██████▋ | 62/93 [00:29<00:14, 2.14it/s]
68%|██████▊ | 63/93 [00:30<00:13, 2.27it/s]
69%|██████▉ | 64/93 [00:30<00:13, 2.15it/s]
70%|██████▉ | 65/93 [00:31<00:12, 2.32it/s]
71%|███████ | 66/93 [00:31<00:11, 2.33it/s]
72%|███████▏ | 67/93 [00:31<00:10, 2.36it/s]
73%|███████▎ | 68/93 [00:32<00:11, 2.27it/s]
74%|███████▍ | 69/93 [00:33<00:11, 2.10it/s]
75%|███████▌ | 70/93 [00:33<00:10, 2.13it/s]
76%|███████▋ | 71/93 [00:34<00:11, 1.93it/s]
77%|███████▋ | 72/93 [00:34<00:10, 1.91it/s]
78%|███████▊ | 73/93 [00:35<00:09, 2.04it/s]
80%|███████▉ | 74/93 [00:35<00:09, 1.97it/s]
81%|████████ | 75/93 [00:36<00:09, 1.96it/s]
82%|████████▏ | 76/93 [00:36<00:08, 2.11it/s]
83%|████████▎ | 77/93 [00:36<00:07, 2.14it/s]
84%|████████▍ | 78/93 [00:37<00:07, 1.98it/s]
85%|████████▍ | 79/93 [00:38<00:07, 1.95it/s]
86%|████████▌ | 80/93 [00:38<00:06, 2.01it/s]
87%|████████▋ | 81/93 [00:38<00:05, 2.12it/s]
88%|████████▊ | 82/93 [00:39<00:05, 2.17it/s]
89%|████████▉ | 83/93 [00:39<00:04, 2.14it/s]
90%|█████████ | 84/93 [00:40<00:04, 2.19it/s]
91%|█████████▏| 85/93 [00:40<00:03, 2.26it/s]
92%|█████████▏| 86/93 [00:41<00:03, 2.13it/s]
94%|█████████▎| 87/93 [00:41<00:02, 2.21it/s]
95%|█████████▍| 88/93 [00:42<00:02, 2.30it/s]
96%|█████████▌| 89/93 [00:42<00:01, 2.17it/s]
97%|█████████▋| 90/93 [00:43<00:01, 2.13it/s]
98%|█████████▊| 91/93 [00:43<00:00, 2.04it/s]
99%|█████████▉| 92/93 [00:44<00:00, 2.08it/s]
100%|██████████| 93/93 [00:44<00:00, 2.16it/s]
100%|██████████| 93/93 [00:44<00:00, 2.08it/s]
***** predict_test_nl_NL metrics *****
predict_ex_match_acc = 0.5928
predict_ex_match_acc_stderr = 0.009
predict_intent_acc = 0.8578
predict_intent_acc_stderr = 0.0064
predict_loss = 0.473
predict_runtime = 0:00:45.28
predict_samples = 2974
predict_samples_per_second = 65.673
predict_slot_micro_f1 = 0.6919
predict_slot_micro_f1_stderr = 0.0032
predict_steps_per_second = 2.054
02/05/2024 17:26:35 - INFO - __main__ - *** test_pl_PL ***
[INFO|trainer.py:718] 2024-02-05 17:26:35,766 >> The following columns in the test set don't have a corresponding argument in `MT5ForConditionalGeneration.forward` and have been ignored: intent_str, id, annot_utt. If intent_str, id, annot_utt are not expected by `MT5ForConditionalGeneration.forward`, you can safely ignore this message.
[INFO|trainer.py:3199] 2024-02-05 17:26:35,768 >> ***** Running Prediction *****
[INFO|trainer.py:3201] 2024-02-05 17:26:35,769 >> Num examples = 2974
[INFO|trainer.py:3204] 2024-02-05 17:26:35,769 >> Batch size = 32
0%| | 0/93 [00:00<?, ?it/s]
2%|▏ | 2/93 [00:00<00:16, 5.51it/s]
3%|▎ | 3/93 [00:00<00:25, 3.49it/s]
4%|▍ | 4/93 [00:01<00:30, 2.94it/s]
5%|▌ | 5/93 [00:01<00:32, 2.73it/s]
6%|▋ | 6/93 [00:02<00:32, 2.68it/s]
8%|▊ | 7/93 [00:02<00:33, 2.55it/s]
9%|▊ | 8/93 [00:03<00:38, 2.22it/s]
10%|▉ | 9/93 [00:03<00:39, 2.10it/s]
11%|█ | 10/93 [00:03<00:37, 2.21it/s]
12%|█▏ | 11/93 [00:04<00:38, 2.14it/s]
13%|█▎ | 12/93 [00:04<00:34, 2.32it/s]
14%|█▍ | 13/93 [00:05<00:33, 2.36it/s]
15%|█▌ | 14/93 [00:05<00:32, 2.45it/s]
16%|█▌ | 15/93 [00:06<00:33, 2.36it/s]
17%|█▋ | 16/93 [00:06<00:32, 2.35it/s]
18%|█▊ | 17/93 [00:06<00:32, 2.35it/s]
19%|█▉ | 18/93 [00:07<00:32, 2.34it/s]
20%|██ | 19/93 [00:07<00:32, 2.30it/s]
22%|██▏ | 20/93 [00:08<00:33, 2.15it/s]
23%|██▎ | 21/93 [00:08<00:32, 2.22it/s]
24%|██▎ | 22/93 [00:09<00:30, 2.32it/s]
25%|██▍ | 23/93 [00:09<00:29, 2.37it/s]
26%|██▌ | 24/93 [00:09<00:28, 2.43it/s]
27%|██▋ | 25/93 [00:10<00:27, 2.48it/s]
28%|██▊ | 26/93 [00:10<00:26, 2.50it/s]
29%|██▉ | 27/93 [00:11<00:26, 2.51it/s]
30%|███ | 28/93 [00:11<00:26, 2.41it/s]
31%|███ | 29/93 [00:12<00:27, 2.30it/s]
32%|███▏ | 30/93 [00:12<00:26, 2.39it/s]
33%|███▎ | 31/93 [00:12<00:25, 2.40it/s]
34%|███▍ | 32/93 [00:13<00:24, 2.45it/s]
35%|███▌ | 33/93 [00:13<00:24, 2.41it/s]
37%|███▋ | 34/93 [00:13<00:23, 2.56it/s]
38%|███▊ | 35/93 [00:14<00:23, 2.47it/s]
39%|███▊ | 36/93 [00:14<00:25, 2.25it/s]
40%|███▉ | 37/93 [00:15<00:26, 2.12it/s]
41%|████ | 38/93 [00:15<00:25, 2.15it/s]
42%|████▏ | 39/93 [00:16<00:24, 2.21it/s]
43%|████▎ | 40/93 [00:16<00:24, 2.13it/s]
44%|████▍ | 41/93 [00:18<00:50, 1.04it/s]
45%|████▌ | 42/93 [00:19<00:41, 1.22it/s]
46%|████▌ | 43/93 [00:19<00:33, 1.48it/s]
47%|████▋ | 44/93 [00:20<00:28, 1.72it/s]
48%|████▊ | 45/93 [00:20<00:26, 1.81it/s]
49%|████▉ | 46/93 [00:21<00:24, 1.92it/s]
51%|█████ | 47/93 [00:21<00:21, 2.10it/s]
52%|█████▏ | 48/93 [00:21<00:20, 2.20it/s]
53%|█████▎ | 49/93 [00:22<00:20, 2.20it/s]
54%|█████▍ | 50/93 [00:22<00:18, 2.26it/s]
55%|█████▍ | 51/93 [00:23<00:18, 2.28it/s]
56%|█████▌ | 52/93 [00:23<00:17, 2.35it/s]
57%|█████▋ | 53/93 [00:24<00:17, 2.32it/s]
58%|█████▊ | 54/93 [00:24<00:16, 2.41it/s]
59%|█████▉ | 55/93 [00:24<00:15, 2.45it/s]
60%|██████ | 56/93 [00:25<00:16, 2.27it/s]
61%|██████▏ | 57/93 [00:25<00:15, 2.28it/s]
62%|██████▏ | 58/93 [00:26<00:14, 2.33it/s]
63%|██████▎ | 59/93 [00:26<00:14, 2.40it/s]
65%|██████▍ | 60/93 [00:26<00:14, 2.35it/s]
66%|██████▌ | 61/93 [00:27<00:14, 2.24it/s]
67%|██████▋ | 62/93 [00:27<00:13, 2.25it/s]
68%|██████▊ | 63/93 [00:28<00:12, 2.34it/s]
69%|██████▉ | 64/93 [00:28<00:11, 2.48it/s]
70%|██████▉ | 65/93 [00:29<00:12, 2.33it/s]
71%|███████ | 66/93 [00:29<00:12, 2.17it/s]
72%|███████▏ | 67/93 [00:30<00:11, 2.23it/s]
73%|███████▎ | 68/93 [00:30<00:10, 2.32it/s]
74%|███████▍ | 69/93 [00:30<00:10, 2.24it/s]
75%|███████▌ | 70/93 [00:33<00:21, 1.07it/s]
76%|███████▋ | 71/93 [00:33<00:17, 1.25it/s]
77%|███████▋ | 72/93 [00:33<00:14, 1.44it/s]
78%|███████▊ | 73/93 [00:34<00:12, 1.66it/s]
80%|███████▉ | 74/93 [00:34<00:10, 1.89it/s]
81%|████████ | 75/93 [00:35<00:08, 2.05it/s]
82%|████████▏ | 76/93 [00:35<00:08, 2.07it/s]
83%|████████▎ | 77/93 [00:36<00:08, 1.91it/s]
84%|████████▍ | 78/93 [00:36<00:07, 2.05it/s]
85%|████████▍ | 79/93 [00:37<00:06, 2.09it/s]
86%|████████▌ | 80/93 [00:37<00:06, 2.12it/s]
87%|████████▋ | 81/93 [00:38<00:06, 1.98it/s]
88%|████████▊ | 82/93 [00:38<00:05, 2.11it/s]
89%|████████▉ | 83/93 [00:38<00:04, 2.22it/s]
90%|█████████ | 84/93 [00:39<00:03, 2.44it/s]
91%|█████████▏| 85/93 [00:39<00:03, 2.36it/s]
92%|█████████▏| 86/93 [00:40<00:03, 2.32it/s]
94%|█████████▎| 87/93 [00:40<00:02, 2.25it/s]
95%|█████████▍| 88/93 [00:41<00:02, 2.30it/s]
96%|█████████▌| 89/93 [00:41<00:01, 2.38it/s]
97%|█████████▋| 90/93 [00:41<00:01, 2.22it/s]
98%|█████████▊| 91/93 [00:42<00:00, 2.14it/s]
99%|█████████▉| 92/93 [00:42<00:00, 2.13it/s]
100%|██████████| 93/93 [00:43<00:00, 2.27it/s]
100%|██████████| 93/93 [00:43<00:00, 2.13it/s]
***** predict_test_pl_PL metrics *****
predict_ex_match_acc = 0.5128
predict_ex_match_acc_stderr = 0.0092
predict_intent_acc = 0.7993
predict_intent_acc_stderr = 0.0073
predict_loss = 0.3891
predict_runtime = 0:00:44.14
predict_samples = 2974
predict_samples_per_second = 67.369
predict_slot_micro_f1 = 0.6636
predict_slot_micro_f1_stderr = 0.0036
predict_steps_per_second = 2.107
02/05/2024 17:27:20 - INFO - __main__ - *** test_pt_PT ***
[INFO|trainer.py:718] 2024-02-05 17:27:20,151 >> The following columns in the test set don't have a corresponding argument in `MT5ForConditionalGeneration.forward` and have been ignored: intent_str, id, annot_utt. If intent_str, id, annot_utt are not expected by `MT5ForConditionalGeneration.forward`, you can safely ignore this message.
[INFO|trainer.py:3199] 2024-02-05 17:27:20,153 >> ***** Running Prediction *****
[INFO|trainer.py:3201] 2024-02-05 17:27:20,153 >> Num examples = 2974
[INFO|trainer.py:3204] 2024-02-05 17:27:20,153 >> Batch size = 32
0%| | 0/93 [00:00<?, ?it/s]
2%|▏ | 2/93 [00:00<00:18, 4.85it/s]
3%|▎ | 3/93 [00:00<00:31, 2.85it/s]
4%|▍ | 4/93 [00:01<00:33, 2.66it/s]
5%|▌ | 5/93 [00:01<00:35, 2.47it/s]
6%|▋ | 6/93 [00:02<00:42, 2.07it/s]
8%|▊ | 7/93 [00:03<00:44, 1.92it/s]
9%|▊ | 8/93 [00:03<00:44, 1.93it/s]
10%|▉ | 9/93 [00:04<00:42, 1.97it/s]
11%|█ | 10/93 [00:04<00:41, 1.98it/s]
12%|█▏ | 11/93 [00:05<00:44, 1.83it/s]
13%|█▎ | 12/93 [00:05<00:40, 1.99it/s]
14%|█▍ | 13/93 [00:06<00:39, 2.00it/s]
15%|█▌ | 14/93 [00:06<00:37, 2.13it/s]
16%|█▌ | 15/93 [00:07<00:37, 2.05it/s]
17%|█▋ | 16/93 [00:07<00:38, 2.01it/s]
18%|█▊ | 17/93 [00:07<00:36, 2.09it/s]
19%|█▉ | 18/93 [00:08<00:34, 2.16it/s]
20%|██ | 19/93 [00:08<00:35, 2.09it/s]
22%|██▏ | 20/93 [00:09<00:36, 1.99it/s]
23%|██▎ | 21/93 [00:09<00:34, 2.06it/s]
24%|██▎ | 22/93 [00:10<00:33, 2.15it/s]
25%|██▍ | 23/93 [00:10<00:32, 2.16it/s]
26%|██▌ | 24/93 [00:11<00:31, 2.17it/s]
27%|██▋ | 25/93 [00:11<00:31, 2.17it/s]
28%|██▊ | 26/93 [00:12<00:29, 2.26it/s]
29%|██▉ | 27/93 [00:12<00:33, 1.97it/s]
30%|███ | 28/93 [00:13<00:34, 1.89it/s]
31%|███ | 29/93 [00:13<00:32, 1.96it/s]
32%|███▏ | 30/93 [00:14<00:29, 2.14it/s]
33%|███▎ | 31/93 [00:14<00:27, 2.22it/s]
34%|███▍ | 32/93 [00:15<00:27, 2.19it/s]
35%|███▌ | 33/93 [00:15<00:29, 2.02it/s]
37%|███▋ | 34/93 [00:16<00:30, 1.91it/s]
38%|███▊ | 35/93 [00:18<00:58, 1.01s/it]
39%|███▊ | 36/93 [00:18<00:49, 1.16it/s]
40%|███▉ | 37/93 [00:19<00:41, 1.36it/s]
41%|████ | 38/93 [00:19<00:36, 1.51it/s]
42%|████▏ | 39/93 [00:20<00:32, 1.66it/s]
43%|████▎ | 40/93 [00:20<00:30, 1.72it/s]
44%|████▍ | 41/93 [00:21<00:29, 1.79it/s]
45%|████▌ | 42/93 [00:21<00:28, 1.81it/s]
46%|████▌ | 43/93 [00:22<00:26, 1.89it/s]
47%|████▋ | 44/93 [00:22<00:26, 1.84it/s]
48%|████▊ | 45/93 [00:23<00:26, 1.82it/s]
49%|████▉ | 46/93 [00:24<00:26, 1.77it/s]
51%|█████ | 47/93 [00:24<00:23, 1.94it/s]
52%|█████▏ | 48/93 [00:24<00:22, 2.03it/s]
53%|█████▎ | 49/93 [00:25<00:21, 2.05it/s]
54%|█████▍ | 50/93 [00:25<00:20, 2.05it/s]
55%|█████▍ | 51/93 [00:26<00:20, 2.02it/s]
56%|█████▌ | 52/93 [00:27<00:24, 1.68it/s]
57%|█████▋ | 53/93 [00:27<00:25, 1.58it/s]
58%|█████▊ | 54/93 [00:28<00:23, 1.65it/s]
59%|█████▉ | 55/93 [00:28<00:20, 1.82it/s]
60%|██████ | 56/93 [00:29<00:19, 1.87it/s]
61%|██████▏ | 57/93 [00:29<00:18, 1.96it/s]
62%|██████▏ | 58/93 [00:30<00:17, 1.95it/s]
63%|██████▎ | 59/93 [00:30<00:16, 2.07it/s]
65%|██████▍ | 60/93 [00:31<00:15, 2.14it/s]
66%|██████▌ | 61/93 [00:31<00:16, 1.92it/s]
67%|██████▋ | 62/93 [00:32<00:15, 1.95it/s]
68%|██████▊ | 63/93 [00:33<00:16, 1.84it/s]
69%|██████▉ | 64/93 [00:33<00:15, 1.92it/s]
70%|██████▉ | 65/93 [00:33<00:13, 2.02it/s]
71%|███████ | 66/93 [00:34<00:13, 2.07it/s]
72%|███████▏ | 67/93 [00:34<00:12, 2.04it/s]
73%|███████▎ | 68/93 [00:35<00:12, 2.05it/s]
74%|███████▍ | 69/93 [00:35<00:11, 2.11it/s]
75%|███████▌ | 70/93 [00:36<00:11, 2.09it/s]
76%|███████▋ | 71/93 [00:36<00:10, 2.12it/s]
77%|███████▋ | 72/93 [00:37<00:09, 2.21it/s]
78%|███████▊ | 73/93 [00:37<00:09, 2.22it/s]
80%|███████▉ | 74/93 [00:38<00:08, 2.18it/s]
81%|████████ | 75/93 [00:38<00:07, 2.27it/s]
82%|████████▏ | 76/93 [00:38<00:07, 2.14it/s]
83%|████████▎ | 77/93 [00:39<00:07, 2.13it/s]
84%|████████▍ | 78/93 [00:40<00:07, 1.97it/s]
85%|████████▍ | 79/93 [00:40<00:07, 1.98it/s]
86%|████████▌ | 80/93 [00:41<00:06, 2.02it/s]
87%|████████▋ | 81/93 [00:41<00:05, 2.10it/s]
88%|████████▊ | 82/93 [00:42<00:05, 1.95it/s]
89%|████████▉ | 83/93 [00:42<00:04, 2.02it/s]
90%|█████████ | 84/93 [00:42<00:04, 2.08it/s]
91%|█████████▏| 85/93 [00:43<00:03, 2.20it/s]
92%|█████████▏| 86/93 [00:43<00:02, 2.34it/s]
94%|█████████▎| 87/93 [00:44<00:02, 2.25it/s]
95%|█████████▍| 88/93 [00:44<00:02, 2.21it/s]
96%|█████████▌| 89/93 [00:45<00:01, 2.18it/s]
97%|█████████▋| 90/93 [00:45<00:01, 2.03it/s]
98%|█████████▊| 91/93 [00:46<00:00, 2.04it/s]
99%|█████████▉| 92/93 [00:46<00:00, 2.03it/s]
100%|██████████| 93/93 [00:47<00:00, 2.16it/s]
100%|██████████| 93/93 [00:47<00:00, 1.96it/s]
***** predict_test_pt_PT metrics *****
predict_ex_match_acc = 0.498
predict_ex_match_acc_stderr = 0.0092
predict_intent_acc = 0.8268
predict_intent_acc_stderr = 0.0069
predict_loss = 0.5365
predict_runtime = 0:00:47.90
predict_samples = 2974
predict_samples_per_second = 62.079
predict_slot_micro_f1 = 0.5705
predict_slot_micro_f1_stderr = 0.0034
predict_steps_per_second = 1.941
02/05/2024 17:28:08 - INFO - __main__ - *** test_ru_RU ***
[INFO|trainer.py:718] 2024-02-05 17:28:08,307 >> The following columns in the test set don't have a corresponding argument in `MT5ForConditionalGeneration.forward` and have been ignored: intent_str, id, annot_utt. If intent_str, id, annot_utt are not expected by `MT5ForConditionalGeneration.forward`, you can safely ignore this message.
[INFO|trainer.py:3199] 2024-02-05 17:28:08,309 >> ***** Running Prediction *****
[INFO|trainer.py:3201] 2024-02-05 17:28:08,310 >> Num examples = 2974
[INFO|trainer.py:3204] 2024-02-05 17:28:08,310 >> Batch size = 32
0%| | 0/93 [00:00<?, ?it/s]
2%|▏ | 2/93 [00:00<00:17, 5.13it/s]
3%|▎ | 3/93 [00:00<00:25, 3.52it/s]
4%|▍ | 4/93 [00:01<00:32, 2.74it/s]
5%|▌ | 5/93 [00:01<00:32, 2.73it/s]
6%|▋ | 6/93 [00:02<00:31, 2.78it/s]
8%|▊ | 7/93 [00:02<00:35, 2.44it/s]
9%|▊ | 8/93 [00:02<00:33, 2.50it/s]
10%|▉ | 9/93 [00:03<00:32, 2.57it/s]
11%|█ | 10/93 [00:03<00:32, 2.59it/s]
12%|█▏ | 11/93 [00:04<00:34, 2.40it/s]
13%|█▎ | 12/93 [00:04<00:34, 2.36it/s]
14%|█▍ | 13/93 [00:04<00:32, 2.48it/s]
15%|█▌ | 14/93 [00:05<00:31, 2.50it/s]
16%|█▌ | 15/93 [00:05<00:34, 2.26it/s]
17%|█▋ | 16/93 [00:06<00:37, 2.07it/s]
18%|█▊ | 17/93 [00:06<00:37, 2.01it/s]
19%|█▉ | 18/93 [00:07<00:35, 2.12it/s]
20%|██ | 19/93 [00:07<00:32, 2.25it/s]
22%|██▏ | 20/93 [00:08<00:31, 2.31it/s]
23%|██▎ | 21/93 [00:08<00:29, 2.45it/s]
24%|██▎ | 22/93 [00:08<00:28, 2.49it/s]
25%|██▍ | 23/93 [00:09<00:29, 2.34it/s]
26%|██▌ | 24/93 [00:09<00:28, 2.42it/s]
27%|██▋ | 25/93 [00:10<00:30, 2.24it/s]
28%|██▊ | 26/93 [00:10<00:28, 2.31it/s]
29%|██▉ | 27/93 [00:11<00:29, 2.22it/s]
30%|███ | 28/93 [00:13<01:01, 1.05it/s]
31%|███ | 29/93 [00:13<00:49, 1.28it/s]
32%|███▏ | 30/93 [00:14<00:42, 1.49it/s]
33%|███▎ | 31/93 [00:14<00:36, 1.68it/s]
34%|███▍ | 32/93 [00:15<00:38, 1.59it/s]
35%|███▌ | 33/93 [00:15<00:33, 1.77it/s]
37%|███▋ | 34/93 [00:16<00:32, 1.84it/s]
38%|███▊ | 35/93 [00:16<00:30, 1.90it/s]
39%|███▊ | 36/93 [00:17<00:27, 2.04it/s]
40%|███▉ | 37/93 [00:17<00:28, 2.00it/s]
41%|████ | 38/93 [00:18<00:28, 1.95it/s]
42%|████▏ | 39/93 [00:18<00:27, 1.95it/s]
43%|████▎ | 40/93 [00:19<00:25, 2.10it/s]
44%|████▍ | 41/93 [00:19<00:23, 2.18it/s]
45%|████▌ | 42/93 [00:19<00:21, 2.34it/s]
46%|████▌ | 43/93 [00:20<00:19, 2.50it/s]
47%|████▋ | 44/93 [00:20<00:19, 2.52it/s]
48%|████▊ | 45/93 [00:20<00:19, 2.48it/s]
49%|████▉ | 46/93 [00:21<00:19, 2.44it/s]
51%|█████ | 47/93 [00:21<00:18, 2.55it/s]
52%|█████▏ | 48/93 [00:22<00:20, 2.23it/s]
53%|█████▎ | 49/93 [00:22<00:18, 2.39it/s]
54%|█████▍ | 50/93 [00:23<00:18, 2.26it/s]
55%|█████▍ | 51/93 [00:23<00:20, 2.09it/s]
56%|█████▌ | 52/93 [00:24<00:21, 1.93it/s]
57%|█████▋ | 53/93 [00:24<00:19, 2.09it/s]
58%|█████▊ | 54/93 [00:25<00:18, 2.14it/s]
59%|█████▉ | 55/93 [00:25<00:16, 2.30it/s]
60%|██████ | 56/93 [00:25<00:16, 2.31it/s]
61%|██████▏ | 57/93 [00:26<00:15, 2.36it/s]
62%|██████▏ | 58/93 [00:26<00:15, 2.27it/s]
63%|██████▎ | 59/93 [00:27<00:14, 2.31it/s]
65%|██████▍ | 60/93 [00:27<00:13, 2.42it/s]
66%|██████▌ | 61/93 [00:28<00:13, 2.31it/s]
67%|██████▋ | 62/93 [00:28<00:13, 2.34it/s]
68%|██████▊ | 63/93 [00:28<00:12, 2.41it/s]
69%|██████▉ | 64/93 [00:29<00:12, 2.40it/s]
70%|██████▉ | 65/93 [00:29<00:11, 2.45it/s]
71%|███████ | 66/93 [00:30<00:11, 2.42it/s]
72%|███████▏ | 67/93 [00:30<00:10, 2.37it/s]
73%|███████▎ | 68/93 [00:31<00:10, 2.27it/s]
74%|███████▍ | 69/93 [00:31<00:10, 2.19it/s]
75%|███████▌ | 70/93 [00:31<00:10, 2.17it/s]
76%|███████▋ | 71/93 [00:32<00:10, 2.04it/s]
77%|███████▋ | 72/93 [00:32<00:09, 2.16it/s]
78%|███████▊ | 73/93 [00:33<00:08, 2.31it/s]
80%|███████▉ | 74/93 [00:33<00:08, 2.28it/s]
81%|████████ | 75/93 [00:34<00:08, 2.23it/s]
82%|████████▏ | 76/93 [00:34<00:07, 2.19it/s]
83%|████████▎ | 77/93 [00:35<00:07, 2.14it/s]
84%|████████▍ | 78/93 [00:35<00:07, 1.99it/s]
85%|████████▍ | 79/93 [00:36<00:07, 1.96it/s]
86%|████████▌ | 80/93 [00:36<00:06, 1.97it/s]
87%|████████▋ | 81/93 [00:37<00:05, 2.15it/s]
88%|████████▊ | 82/93 [00:37<00:04, 2.24it/s]
89%|████████▉ | 83/93 [00:38<00:04, 2.21it/s]
90%|█████████ | 84/93 [00:38<00:03, 2.30it/s]
91%|█████████▏| 85/93 [00:38<00:03, 2.31it/s]
92%|█████████▏| 86/93 [00:39<00:03, 2.22it/s]
94%|█████████▎| 87/93 [00:39<00:02, 2.23it/s]
95%|█████████▍| 88/93 [00:40<00:02, 2.27it/s]
96%|█████████▌| 89/93 [00:40<00:01, 2.27it/s]
97%|█████████▋| 90/93 [00:41<00:01, 2.28it/s]
98%|█████████▊| 91/93 [00:41<00:00, 2.08it/s]
99%|█████████▉| 92/93 [00:42<00:00, 2.12it/s]
100%|██████████| 93/93 [00:42<00:00, 2.29it/s]
100%|██████████| 93/93 [00:42<00:00, 2.18it/s]
***** predict_test_ru_RU metrics *****
predict_ex_match_acc = 0.6113
predict_ex_match_acc_stderr = 0.0089
predict_intent_acc = 0.8557
predict_intent_acc_stderr = 0.0064
predict_loss = 0.3015
predict_runtime = 0:00:43.16
predict_samples = 2974
predict_samples_per_second = 68.898
predict_slot_micro_f1 = 0.7306
predict_slot_micro_f1_stderr = 0.0034
predict_steps_per_second = 2.154
02/05/2024 17:28:51 - INFO - __main__ - *** test_tr_TR ***
[INFO|trainer.py:718] 2024-02-05 17:28:51,715 >> The following columns in the test set don't have a corresponding argument in `MT5ForConditionalGeneration.forward` and have been ignored: intent_str, id, annot_utt. If intent_str, id, annot_utt are not expected by `MT5ForConditionalGeneration.forward`, you can safely ignore this message.
[INFO|trainer.py:3199] 2024-02-05 17:28:51,718 >> ***** Running Prediction *****
[INFO|trainer.py:3201] 2024-02-05 17:28:51,718 >> Num examples = 2974
[INFO|trainer.py:3204] 2024-02-05 17:28:51,718 >> Batch size = 32
0%| | 0/93 [00:00<?, ?it/s]
2%|▏ | 2/93 [00:00<00:18, 4.87it/s]
3%|▎ | 3/93 [00:00<00:27, 3.28it/s]
4%|▍ | 4/93 [00:01<00:30, 2.90it/s]
5%|▌ | 5/93 [00:01<00:32, 2.72it/s]
6%|▋ | 6/93 [00:02<00:30, 2.81it/s]
8%|▊ | 7/93 [00:02<00:33, 2.54it/s]
9%|▊ | 8/93 [00:02<00:32, 2.65it/s]
10%|▉ | 9/93 [00:03<00:36, 2.33it/s]
11%|█ | 10/93 [00:03<00:34, 2.39it/s]
12%|█▏ | 11/93 [00:04<00:35, 2.30it/s]
13%|█▎ | 12/93 [00:04<00:33, 2.40it/s]
14%|█▍ | 13/93 [00:04<00:32, 2.48it/s]
15%|█▌ | 14/93 [00:05<00:32, 2.44it/s]
16%|█▌ | 15/93 [00:05<00:35, 2.20it/s]
17%|█▋ | 16/93 [00:06<00:38, 2.01it/s]
18%|█▊ | 17/93 [00:07<00:39, 1.93it/s]
19%|█▉ | 18/93 [00:07<00:38, 1.92it/s]
20%|██ | 19/93 [00:07<00:34, 2.14it/s]
22%|██▏ | 20/93 [00:08<00:32, 2.26it/s]
23%|██▎ | 21/93 [00:08<00:31, 2.29it/s]
24%|██▎ | 22/93 [00:09<00:34, 2.03it/s]
25%|██▍ | 23/93 [00:09<00:33, 2.08it/s]
26%|██▌ | 24/93 [00:10<00:30, 2.26it/s]
27%|██▋ | 25/93 [00:10<00:29, 2.30it/s]
28%|██▊ | 26/93 [00:11<00:27, 2.42it/s]
29%|██▉ | 27/93 [00:11<00:26, 2.47it/s]
30%|███ | 28/93 [00:13<00:59, 1.10it/s]
31%|███ | 29/93 [00:13<00:48, 1.33it/s]
32%|███▏ | 30/93 [00:14<00:41, 1.52it/s]
33%|███▎ | 31/93 [00:14<00:34, 1.79it/s]
34%|███▍ | 32/93 [00:15<00:31, 1.92it/s]
35%|███▌ | 33/93 [00:15<00:29, 2.06it/s]
37%|███▋ | 34/93 [00:15<00:26, 2.25it/s]
38%|███▊ | 35/93 [00:16<00:25, 2.23it/s]
39%|███▊ | 36/93 [00:16<00:24, 2.29it/s]
40%|███▉ | 37/93 [00:17<00:24, 2.24it/s]
41%|████ | 38/93 [00:17<00:26, 2.10it/s]
42%|████▏ | 39/93 [00:18<00:25, 2.15it/s]
43%|████▎ | 40/93 [00:18<00:23, 2.25it/s]
44%|████▍ | 41/93 [00:18<00:22, 2.32it/s]
45%|████▌ | 42/93 [00:19<00:22, 2.31it/s]
46%|████▌ | 43/93 [00:19<00:20, 2.39it/s]
47%|████▋ | 44/93 [00:20<00:20, 2.35it/s]
48%|████▊ | 45/93 [00:20<00:21, 2.25it/s]
49%|████▉ | 46/93 [00:21<00:22, 2.11it/s]
51%|█████ | 47/93 [00:21<00:20, 2.29it/s]
52%|█████▏ | 48/93 [00:21<00:19, 2.33it/s]
53%|█████▎ | 49/93 [00:22<00:18, 2.36it/s]
54%|█████▍ | 50/93 [00:22<00:17, 2.49it/s]
55%|█████▍ | 51/93 [00:23<00:17, 2.42it/s]
56%|█████▌ | 52/93 [00:23<00:18, 2.16it/s]
57%|█████▋ | 53/93 [00:24<00:18, 2.17it/s]
58%|█████▊ | 54/93 [00:24<00:17, 2.25it/s]
59%|█████▉ | 55/93 [00:25<00:15, 2.38it/s]
60%|██████ | 56/93 [00:25<00:14, 2.48it/s]
61%|██████▏ | 57/93 [00:25<00:14, 2.46it/s]
62%|██████▏ | 58/93 [00:26<00:13, 2.51it/s]
63%|██████▎ | 59/93 [00:26<00:12, 2.62it/s]
65%|██████▍ | 60/93 [00:26<00:13, 2.45it/s]
66%|██████▌ | 61/93 [00:27<00:14, 2.16it/s]
67%|██████▋ | 62/93 [00:27<00:13, 2.24it/s]
68%|██████▊ | 63/93 [00:28<00:12, 2.35it/s]
69%|██████▉ | 64/93 [00:28<00:12, 2.37it/s]
70%|██████▉ | 65/93 [00:29<00:11, 2.42it/s]
71%|███████ | 66/93 [00:29<00:11, 2.40it/s]
72%|███████▏ | 67/93 [00:29<00:10, 2.42it/s]
73%|███████▎ | 68/93 [00:30<00:10, 2.28it/s]
74%|███████▍ | 69/93 [00:31<00:11, 2.16it/s]
75%|███████▌ | 70/93 [00:31<00:10, 2.22it/s]
76%|███████▋ | 71/93 [00:32<00:10, 2.00it/s]
77%|███████▋ | 72/93 [00:32<00:09, 2.16it/s]
78%|███████▊ | 73/93 [00:32<00:08, 2.24it/s]
80%|███████▉ | 74/93 [00:33<00:08, 2.23it/s]
81%|████████ | 75/93 [00:33<00:08, 2.19it/s]
82%|████████▏ | 76/93 [00:34<00:07, 2.21it/s]
83%|████████▎ | 77/93 [00:34<00:06, 2.34it/s]
84%|████████▍ | 78/93 [00:34<00:06, 2.44it/s]
85%|████████▍ | 79/93 [00:35<00:05, 2.35it/s]
86%|████████▌ | 80/93 [00:35<00:05, 2.22it/s]
87%|████████▋ | 81/93 [00:36<00:05, 2.33it/s]
88%|████████▊ | 82/93 [00:36<00:04, 2.33it/s]
89%|████████▉ | 83/93 [00:37<00:04, 2.19it/s]
90%|█████████ | 84/93 [00:37<00:04, 2.24it/s]
91%|█████████▏| 85/93 [00:38<00:03, 2.29it/s]
92%|█████████▏| 86/93 [00:38<00:03, 2.32it/s]
94%|█████████▎| 87/93 [00:38<00:02, 2.41it/s]
95%|█████████▍| 88/93 [00:39<00:02, 2.45it/s]
96%|█████████▌| 89/93 [00:39<00:01, 2.33it/s]
97%|█████████▋| 90/93 [00:40<00:01, 2.33it/s]
98%|█████████▊| 91/93 [00:40<00:00, 2.21it/s]
99%|█████████▉| 92/93 [00:41<00:00, 2.21it/s]
100%|██████████| 93/93 [00:41<00:00, 2.41it/s]
100%|██████████| 93/93 [00:41<00:00, 2.23it/s]
***** predict_test_tr_TR metrics *****
predict_ex_match_acc = 0.4445
predict_ex_match_acc_stderr = 0.0091
predict_intent_acc = 0.7579
predict_intent_acc_stderr = 0.0079
predict_loss = 0.614
predict_runtime = 0:00:42.08
predict_samples = 2974
predict_samples_per_second = 70.668
predict_slot_micro_f1 = 0.6036
predict_slot_micro_f1_stderr = 0.0038
predict_steps_per_second = 2.21
02/05/2024 17:29:34 - INFO - __main__ - *** test_vi_VN ***
[INFO|trainer.py:718] 2024-02-05 17:29:34,025 >> The following columns in the test set don't have a corresponding argument in `MT5ForConditionalGeneration.forward` and have been ignored: intent_str, id, annot_utt. If intent_str, id, annot_utt are not expected by `MT5ForConditionalGeneration.forward`, you can safely ignore this message.
[INFO|trainer.py:3199] 2024-02-05 17:29:34,027 >> ***** Running Prediction *****
[INFO|trainer.py:3201] 2024-02-05 17:29:34,028 >> Num examples = 2974
[INFO|trainer.py:3204] 2024-02-05 17:29:34,028 >> Batch size = 32
0%| | 0/93 [00:00<?, ?it/s]
2%|▏ | 2/93 [00:00<00:21, 4.24it/s]
3%|▎ | 3/93 [00:00<00:28, 3.19it/s]
4%|▍ | 4/93 [00:01<00:36, 2.42it/s]
5%|▌ | 5/93 [00:02<00:41, 2.14it/s]
6%|▋ | 6/93 [00:02<00:41, 2.11it/s]
8%|▊ | 7/93 [00:03<00:42, 2.01it/s]
9%|▊ | 8/93 [00:03<00:43, 1.96it/s]
10%|▉ | 9/93 [00:04<00:40, 2.06it/s]
11%|█ | 10/93 [00:04<00:44, 1.88it/s]
12%|█▏ | 11/93 [00:05<00:43, 1.87it/s]
13%|█▎ | 12/93 [00:05<00:44, 1.83it/s]
14%|█▍ | 13/93 [00:06<00:47, 1.69it/s]
15%|█▌ | 14/93 [00:07<00:46, 1.70it/s]
16%|█▌ | 15/93 [00:07<00:49, 1.58it/s]
17%|█▋ | 16/93 [00:08<00:52, 1.48it/s]
18%|█▊ | 17/93 [00:09<00:50, 1.51it/s]
19%|█▉ | 18/93 [00:10<00:53, 1.40it/s]
20%|██ | 19/93 [00:10<00:49, 1.51it/s]
22%|██▏ | 20/93 [00:11<00:44, 1.63it/s]
23%|██▎ | 21/93 [00:11<00:42, 1.69it/s]
24%|██▎ | 22/93 [00:12<00:44, 1.60it/s]
25%|██▍ | 23/93 [00:12<00:42, 1.63it/s]
26%|██▌ | 24/93 [00:13<00:39, 1.73it/s]
27%|██▋ | 25/93 [00:14<00:40, 1.66it/s]
28%|██▊ | 26/93 [00:14<00:38, 1.74it/s]
29%|██▉ | 27/93 [00:15<00:45, 1.46it/s]
30%|███ | 28/93 [00:17<01:13, 1.13s/it]
31%|███ | 29/93 [00:18<00:58, 1.09it/s]
32%|███▏ | 30/93 [00:18<00:54, 1.15it/s]
33%|███▎ | 31/93 [00:19<00:47, 1.31it/s]
34%|███▍ | 32/93 [00:20<00:43, 1.39it/s]
35%|███▌ | 33/93 [00:20<00:40, 1.48it/s]
37%|███▋ | 34/93 [00:21<00:37, 1.56it/s]
38%|███▊ | 35/93 [00:21<00:36, 1.60it/s]
39%|███▊ | 36/93 [00:22<00:39, 1.45it/s]
40%|███▉ | 37/93 [00:23<00:36, 1.53it/s]
41%|████ | 38/93 [00:23<00:35, 1.54it/s]
42%|████▏ | 39/93 [00:25<00:57, 1.07s/it]
43%|████▎ | 40/93 [00:26<00:50, 1.06it/s]
44%|████▍ | 41/93 [00:27<00:43, 1.20it/s]
45%|████▌ | 42/93 [00:27<00:38, 1.33it/s]
46%|████▌ | 43/93 [00:28<00:35, 1.42it/s]
47%|████▋ | 44/93 [00:28<00:30, 1.61it/s]
48%|████▊ | 45/93 [00:29<00:30, 1.56it/s]
49%|████▉ | 46/93 [00:30<00:30, 1.52it/s]
51%|█████ | 47/93 [00:30<00:33, 1.37it/s]
52%|█████▏ | 48/93 [00:31<00:34, 1.31it/s]
53%|█████▎ | 49/93 [00:32<00:29, 1.47it/s]
54%|█████▍ | 50/93 [00:32<00:26, 1.60it/s]
55%|█████▍ | 51/93 [00:34<00:44, 1.07s/it]
56%|█████▌ | 52/93 [00:35<00:39, 1.03it/s]
57%|█████▋ | 53/93 [00:36<00:33, 1.21it/s]
58%|█████▊ | 54/93 [00:36<00:29, 1.32it/s]
59%|█████▉ | 55/93 [00:37<00:26, 1.44it/s]
60%|██████ | 56/93 [00:37<00:22, 1.61it/s]
61%|██████▏ | 57/93 [00:38<00:21, 1.71it/s]
62%|██████▏ | 58/93 [00:38<00:21, 1.64it/s]
63%|██████▎ | 59/93 [00:39<00:22, 1.53it/s]
65%|██████▍ | 60/93 [00:40<00:19, 1.68it/s]
66%|██████▌ | 61/93 [00:40<00:19, 1.61it/s]
67%|██████▋ | 62/93 [00:41<00:19, 1.61it/s]
68%|██████▊ | 63/93 [00:42<00:20, 1.47it/s]
69%|██████▉ | 64/93 [00:42<00:18, 1.61it/s]
70%|██████▉ | 65/93 [00:43<00:17, 1.63it/s]
71%|███████ | 66/93 [00:43<00:17, 1.55it/s]
72%|███████▏ | 67/93 [00:44<00:16, 1.61it/s]
73%|███████▎ | 68/93 [00:45<00:14, 1.72it/s]
74%|███████▍ | 69/93 [00:45<00:14, 1.66it/s]
75%|███████▌ | 70/93 [00:46<00:13, 1.76it/s]
76%|███████▋ | 71/93 [00:48<00:22, 1.01s/it]
77%|███████▋ | 72/93 [00:48<00:18, 1.14it/s]
78%|███████▊ | 73/93 [00:49<00:15, 1.30it/s]
80%|███████▉ | 74/93 [00:49<00:13, 1.41it/s]
81%|████████ | 75/93 [00:51<00:19, 1.11s/it]
82%|████████▏ | 76/93 [00:52<00:15, 1.07it/s]
83%|████████▎ | 77/93 [00:53<00:13, 1.19it/s]
84%|████████▍ | 78/93 [00:53<00:11, 1.32it/s]
85%|████████▍ | 79/93 [00:54<00:09, 1.43it/s]
86%|████████▌ | 80/93 [00:54<00:08, 1.49it/s]
87%|████████▋ | 81/93 [00:55<00:07, 1.53it/s]
88%|████████▊ | 82/93 [00:55<00:06, 1.65it/s]
89%|████████▉ | 83/93 [00:56<00:05, 1.69it/s]
90%|█████████ | 84/93 [00:56<00:05, 1.79it/s]
91%|█████████▏| 85/93 [00:57<00:04, 1.63it/s]
92%|█████████▏| 86/93 [00:58<00:04, 1.60it/s]
94%|█████████▎| 87/93 [00:58<00:03, 1.70it/s]
95%|█████████▍| 88/93 [00:59<00:02, 1.79it/s]
96%|█████████▌| 89/93 [00:59<00:02, 1.78it/s]
97%|█████████▋| 90/93 [01:00<00:01, 1.81it/s]
98%|█████████▊| 91/93 [01:01<00:01, 1.68it/s]
99%|█████████▉| 92/93 [01:01<00:00, 1.74it/s]
100%|██████████| 93/93 [01:02<00:00, 1.77it/s]
100%|██████████| 93/93 [01:02<00:00, 1.49it/s]
***** predict_test_vi_VN metrics *****
predict_ex_match_acc = 0.1416
predict_ex_match_acc_stderr = 0.0064
predict_intent_acc = 0.3584
predict_intent_acc_stderr = 0.0088
predict_loss = 0.6596
predict_runtime = 0:01:03.04
predict_samples = 2974
predict_samples_per_second = 47.174
predict_slot_micro_f1 = 0.3368
predict_slot_micro_f1_stderr = 0.0029
predict_steps_per_second = 1.475
|