File size: 37,690 Bytes
c4fdd18 |
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 |
[2024-01-26 12:54:39,523] torch.distributed.run: [WARNING] master_addr is only used for static rdzv_backend and when rdzv_endpoint is not specified.
01/26/2024 12:54:44 - WARNING - __main__ - Process rank: 0, device: cuda:0, n_gpu: 1distributed training: True, 16-bits training: False
01/26/2024 12:54:44 - 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=False,
ddp_timeout=1800,
debug=[],
deepspeed=None,
disable_tqdm=False,
dispatch_batches=None,
do_eval=False,
do_predict=False,
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=None,
gradient_accumulation_steps=32,
gradient_checkpointing=False,
gradient_checkpointing_kwargs=None,
greater_is_better=None,
group_by_length=False,
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=0.02,
length_column_name=length,
load_best_model_at_end=False,
local_rank=0,
log_level=passive,
log_level_replica=warning,
log_on_each_node=True,
logging_dir=output/privacy_detection_pt-20240126-125436-128-2e-2/runs/Jan26_12-54-44_ubuntu1804,
logging_first_step=False,
logging_nan_inf_filter=True,
logging_steps=1.0,
logging_strategy=steps,
lr_scheduler_kwargs={},
lr_scheduler_type=linear,
max_grad_norm=1.0,
max_steps=100,
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=output/privacy_detection_pt-20240126-125436-128-2e-2,
overwrite_output_dir=False,
past_index=-1,
per_device_eval_batch_size=8,
per_device_train_batch_size=1,
predict_with_generate=False,
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=True,
run_name=output/privacy_detection_pt-20240126-125436-128-2e-2,
save_on_each_node=False,
save_only_model=False,
save_safetensors=False,
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,
)
[INFO|configuration_utils.py:729] 2024-01-26 12:54:45,398 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--THUDM--chatglm3-6b/snapshots/37f2196f481f8989ea443be625d05f97043652ea/config.json
[INFO|configuration_utils.py:729] 2024-01-26 12:54:45,957 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--THUDM--chatglm3-6b/snapshots/37f2196f481f8989ea443be625d05f97043652ea/config.json
[INFO|configuration_utils.py:792] 2024-01-26 12:54:45,960 >> Model config ChatGLMConfig {
"_name_or_path": "THUDM/chatglm3-6b",
"add_bias_linear": false,
"add_qkv_bias": true,
"apply_query_key_layer_scaling": true,
"apply_residual_connection_post_layernorm": false,
"architectures": [
"ChatGLMModel"
],
"attention_dropout": 0.0,
"attention_softmax_in_fp32": true,
"auto_map": {
"AutoConfig": "THUDM/chatglm3-6b--configuration_chatglm.ChatGLMConfig",
"AutoModel": "THUDM/chatglm3-6b--modeling_chatglm.ChatGLMForConditionalGeneration",
"AutoModelForCausalLM": "THUDM/chatglm3-6b--modeling_chatglm.ChatGLMForConditionalGeneration",
"AutoModelForSeq2SeqLM": "THUDM/chatglm3-6b--modeling_chatglm.ChatGLMForConditionalGeneration",
"AutoModelForSequenceClassification": "THUDM/chatglm3-6b--modeling_chatglm.ChatGLMForSequenceClassification"
},
"bias_dropout_fusion": true,
"classifier_dropout": null,
"eos_token_id": 2,
"ffn_hidden_size": 13696,
"fp32_residual_connection": false,
"hidden_dropout": 0.0,
"hidden_size": 4096,
"kv_channels": 128,
"layernorm_epsilon": 1e-05,
"model_type": "chatglm",
"multi_query_attention": true,
"multi_query_group_num": 2,
"num_attention_heads": 32,
"num_layers": 28,
"original_rope": true,
"pad_token_id": 0,
"padded_vocab_size": 65024,
"post_layer_norm": true,
"pre_seq_len": null,
"prefix_projection": false,
"quantization_bit": 0,
"rmsnorm": true,
"seq_length": 8192,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.37.1",
"use_cache": true,
"vocab_size": 65024
}
[INFO|tokenization_utils_base.py:2027] 2024-01-26 12:54:46,519 >> loading file tokenizer.model from cache at /root/.cache/huggingface/hub/models--THUDM--chatglm3-6b/snapshots/37f2196f481f8989ea443be625d05f97043652ea/tokenizer.model
[INFO|tokenization_utils_base.py:2027] 2024-01-26 12:54:46,519 >> loading file added_tokens.json from cache at None
[INFO|tokenization_utils_base.py:2027] 2024-01-26 12:54:46,519 >> loading file special_tokens_map.json from cache at None
[INFO|tokenization_utils_base.py:2027] 2024-01-26 12:54:46,519 >> loading file tokenizer_config.json from cache at /root/.cache/huggingface/hub/models--THUDM--chatglm3-6b/snapshots/37f2196f481f8989ea443be625d05f97043652ea/tokenizer_config.json
[INFO|tokenization_utils_base.py:2027] 2024-01-26 12:54:46,519 >> loading file tokenizer.json from cache at None
[INFO|modeling_utils.py:3478] 2024-01-26 12:54:47,170 >> loading weights file model.safetensors from cache at /root/.cache/huggingface/hub/models--THUDM--chatglm3-6b/snapshots/37f2196f481f8989ea443be625d05f97043652ea/model.safetensors.index.json
[INFO|configuration_utils.py:826] 2024-01-26 12:54:47,177 >> Generate config GenerationConfig {
"eos_token_id": 2,
"pad_token_id": 0,
"use_cache": false
}
Loading checkpoint shards: 0%| | 0/7 [00:00<?, ?it/s]
Loading checkpoint shards: 14%|โโ | 1/7 [00:02<00:15, 2.53s/it]
Loading checkpoint shards: 29%|โโโ | 2/7 [00:04<00:12, 2.48s/it]
Loading checkpoint shards: 43%|โโโโโ | 3/7 [00:08<00:12, 3.15s/it]
Loading checkpoint shards: 57%|โโโโโโ | 4/7 [00:09<00:06, 2.27s/it]
Loading checkpoint shards: 71%|โโโโโโโโ | 5/7 [00:17<00:08, 4.27s/it]
Loading checkpoint shards: 86%|โโโโโโโโโ | 6/7 [00:18<00:03, 3.18s/it]
Loading checkpoint shards: 100%|โโโโโโโโโโ| 7/7 [00:19<00:00, 2.53s/it]
Loading checkpoint shards: 100%|โโโโโโโโโโ| 7/7 [00:19<00:00, 2.84s/it]
[INFO|modeling_utils.py:4352] 2024-01-26 12:55:07,172 >> All model checkpoint weights were used when initializing ChatGLMForConditionalGeneration.
[WARNING|modeling_utils.py:4354] 2024-01-26 12:55:07,173 >> Some weights of ChatGLMForConditionalGeneration were not initialized from the model checkpoint at THUDM/chatglm3-6b and are newly initialized: ['transformer.prefix_encoder.embedding.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
[INFO|modeling_utils.py:3897] 2024-01-26 12:55:07,458 >> Generation config file not found, using a generation config created from the model config.
Sanity Check >>>>>>>>>>>>>
'[gMASK]': 64790 -> -100
'sop': 64792 -> -100
'': 30910 -> -100
'่ฏท': 55073 -> -100
'ๆพๅบ': 40369 -> -100
'ไธ้ข': 33182 -> -100
'ๆๆฌ': 36704 -> -100
'ไธญ็': 31697 -> -100
'position': 6523 -> -100
'๏ผ': 31211 -> -100
'่บๆฏ': 31835 -> -100
'ๆฏ': 54532 -> -100
'็ธๅ็': 38815 -> -100
'๏ผ': 31123 -> -100
'้ณไน': 32000 -> -100
'็พๆฏ': 33020 -> -100
'ไฝ่ฒ': 32214 -> -100
'ไธ': 54645 -> -100
'ๆ ท': 54741 -> -100
'้ฝๆฏ': 31700 -> -100
'่บๆฏ': 31835 -> -100
'ใ๏ผ': 37843 -> -100
'ไธ': 54645 -> -100
'ๆ ท': 54741 -> -100
'่บๆฏ': 31835 -> -100
'้ฝๆฏ': 31700 -> -100
'้ ': 55518 -> -100
'ๆ่ง': 32044 -> -100
'็': 54530 -> -100
'ใ': 31155 -> -100
'ๆ่ง': 32044 -> -100
'ๅฅฝ็ฉ': 42814 -> -100
'่ตทๆฅ': 31841 -> -100
'ๅฐฑๅพ': 40030 -> -100
'่ฝปๆพ': 33550 -> -100
'๏ผ': 31123 -> -100
'ๆไปฅ': 31672 -> -100
'ๅซๅ': 35528 -> -100
'็ฉ': 55409 -> -100
'่บๆฏ': 31835 -> -100
'ใ': 31155 -> -100
'ๆฒก': 54721 -> -100
'ๆ่ง': 32044 -> -100
'ๆพไธๅฐ': 37779 -> -100
'ๅ': 54760 -> -100
'็': 54530 -> -100
'ๅนฒ่': 43396 -> -100
'ๅซ': 54835 -> -100
'็ฉ': 55409 -> -100
'ไบ': 54537 -> -100
'๏ผ': 31404 -> -100
'๏ผ': 31123 -> -100
'้ฆๆธฏ': 31776 -> -100
'็ตๅฝฑ': 31867 -> -100
'ๅฝ่ฏญ': 54385 -> -100
'้
้ณ': 40392 -> -100
'ๅๅฎถ': 40465 -> -100
'ๅจ': 54896 -> -100
'ๆ': 54872 -> -100
'ๅนณ': 54678 -> -100
'๏ผ': 31123 -> -100
'ไปฃ่กจไฝ': 43527 -> -100
'ๆ': 54536 -> -100
'TVB': 42671 -> -100
'ใ': 54611 -> -100
'ไธๆตท': 31770 -> -100
'ๆปฉ': 56928 -> -100
'ใ': 54612 -> -100
'ๅจ': 54896 -> -100
'ๆถฆ': 55826 -> -100
'ๅ': 54559 -> -100
'็ญ': 54609 -> -100
'้ฆๆธฏ': 37944 -> 37944
'็ตๅฝฑ': 31867 -> 31867
'ๅฝ่ฏญ': 54385 -> 54385
'้
้ณ': 40392 -> 40392
'ๅๅฎถ': 40465 -> 40465
'': 2 -> 2
<<<<<<<<<<<<< Sanity Check
01/26/2024 12:55:08 - WARNING - accelerate.utils.other - Detected kernel version 5.4.0, 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.
[INFO|trainer.py:522] 2024-01-26 12:55:20,019 >> max_steps is given, it will override any value given in num_train_epochs
[WARNING|modeling_utils.py:2134] 2024-01-26 12:55:20,020 >> You are using an old version of the checkpointing format that is deprecated (We will also silently ignore `gradient_checkpointing_kwargs` in case you passed it).Please update to the new format on your modeling file. To use the new format, you need to completely remove the definition of the method `_set_gradient_checkpointing` in your model.
[INFO|trainer.py:1721] 2024-01-26 12:55:21,544 >> ***** Running training *****
[INFO|trainer.py:1722] 2024-01-26 12:55:21,544 >> Num examples = 2,515
[INFO|trainer.py:1723] 2024-01-26 12:55:21,544 >> Num Epochs = 2
[INFO|trainer.py:1724] 2024-01-26 12:55:21,544 >> Instantaneous batch size per device = 1
[INFO|trainer.py:1727] 2024-01-26 12:55:21,544 >> Total train batch size (w. parallel, distributed & accumulation) = 32
[INFO|trainer.py:1728] 2024-01-26 12:55:21,544 >> Gradient Accumulation steps = 32
[INFO|trainer.py:1729] 2024-01-26 12:55:21,544 >> Total optimization steps = 100
[INFO|trainer.py:1730] 2024-01-26 12:55:21,545 >> Number of trainable parameters = 1,835,008
0%| | 0/100 [00:00<?, ?it/s]/home/vipuser/miniconda3/envs/GLM/lib/python3.10/site-packages/torch/utils/checkpoint.py:429: UserWarning: torch.utils.checkpoint: please pass in use_reentrant=True or use_reentrant=False explicitly. The default value of use_reentrant will be updated to be False in the future. To maintain current behavior, pass use_reentrant=True. It is recommended that you use use_reentrant=False. Refer to docs for more details on the differences between the two variants.
warnings.warn(
1%| | 1/100 [00:13<22:36, 13.70s/it]
{'loss': 0.8181, 'learning_rate': 0.0198, 'epoch': 0.01}
1%| | 1/100 [00:13<22:36, 13.70s/it]
2%|โ | 2/100 [00:25<20:33, 12.59s/it]
{'loss': 0.787, 'learning_rate': 0.0196, 'epoch': 0.03}
2%|โ | 2/100 [00:25<20:33, 12.59s/it]
3%|โ | 3/100 [00:37<19:50, 12.27s/it]
{'loss': 1.0047, 'learning_rate': 0.0194, 'epoch': 0.04}
3%|โ | 3/100 [00:37<19:50, 12.27s/it]
4%|โ | 4/100 [00:49<19:25, 12.14s/it]
{'loss': 0.8688, 'learning_rate': 0.0192, 'epoch': 0.05}
4%|โ | 4/100 [00:49<19:25, 12.14s/it]
5%|โ | 5/100 [01:01<19:09, 12.10s/it]
{'loss': 0.7173, 'learning_rate': 0.019, 'epoch': 0.06}
5%|โ | 5/100 [01:01<19:09, 12.10s/it]
6%|โ | 6/100 [01:13<18:55, 12.08s/it]
{'loss': 0.5175, 'learning_rate': 0.0188, 'epoch': 0.08}
6%|โ | 6/100 [01:13<18:55, 12.08s/it]
7%|โ | 7/100 [01:25<18:45, 12.11s/it]
{'loss': 0.7559, 'learning_rate': 0.018600000000000002, 'epoch': 0.09}
7%|โ | 7/100 [01:25<18:45, 12.11s/it]
8%|โ | 8/100 [01:37<18:35, 12.13s/it]
{'loss': 0.9278, 'learning_rate': 0.0184, 'epoch': 0.1}
8%|โ | 8/100 [01:37<18:35, 12.13s/it]
9%|โ | 9/100 [01:49<18:25, 12.15s/it]
{'loss': 0.6011, 'learning_rate': 0.0182, 'epoch': 0.11}
9%|โ | 9/100 [01:49<18:25, 12.15s/it]
10%|โ | 10/100 [02:02<18:13, 12.15s/it]
{'loss': 0.8014, 'learning_rate': 0.018000000000000002, 'epoch': 0.13}
10%|โ | 10/100 [02:02<18:13, 12.15s/it]
11%|โ | 11/100 [02:14<18:01, 12.16s/it]
{'loss': 1.2581, 'learning_rate': 0.0178, 'epoch': 0.14}
11%|โ | 11/100 [02:14<18:01, 12.16s/it]
12%|โโ | 12/100 [02:26<17:51, 12.18s/it]
{'loss': 0.9886, 'learning_rate': 0.0176, 'epoch': 0.15}
12%|โโ | 12/100 [02:26<17:51, 12.18s/it]
13%|โโ | 13/100 [02:38<17:39, 12.18s/it]
{'loss': 0.7866, 'learning_rate': 0.0174, 'epoch': 0.17}
13%|โโ | 13/100 [02:38<17:39, 12.18s/it]
14%|โโ | 14/100 [02:50<17:28, 12.19s/it]
{'loss': 0.936, 'learning_rate': 0.0172, 'epoch': 0.18}
14%|โโ | 14/100 [02:50<17:28, 12.19s/it]
15%|โโ | 15/100 [03:03<17:17, 12.20s/it]
{'loss': 1.0503, 'learning_rate': 0.017, 'epoch': 0.19}
15%|โโ | 15/100 [03:03<17:17, 12.20s/it]
16%|โโ | 16/100 [03:15<17:04, 12.20s/it]
{'loss': 0.5689, 'learning_rate': 0.0168, 'epoch': 0.2}
16%|โโ | 16/100 [03:15<17:04, 12.20s/it]
17%|โโ | 17/100 [03:27<16:52, 12.20s/it]
{'loss': 0.8576, 'learning_rate': 0.0166, 'epoch': 0.22}
17%|โโ | 17/100 [03:27<16:52, 12.20s/it]
18%|โโ | 18/100 [03:39<16:39, 12.19s/it]
{'loss': 1.0946, 'learning_rate': 0.016399999999999998, 'epoch': 0.23}
18%|โโ | 18/100 [03:39<16:39, 12.19s/it]
19%|โโ | 19/100 [03:51<16:27, 12.19s/it]
{'loss': 0.9075, 'learning_rate': 0.016200000000000003, 'epoch': 0.24}
19%|โโ | 19/100 [03:51<16:27, 12.19s/it]
20%|โโ | 20/100 [04:04<16:14, 12.18s/it]
{'loss': 1.1441, 'learning_rate': 0.016, 'epoch': 0.25}
20%|โโ | 20/100 [04:04<16:14, 12.18s/it]
21%|โโ | 21/100 [04:16<16:01, 12.17s/it]
{'loss': 0.7794, 'learning_rate': 0.0158, 'epoch': 0.27}
21%|โโ | 21/100 [04:16<16:01, 12.17s/it]
22%|โโโ | 22/100 [04:28<15:50, 12.18s/it]
{'loss': 0.9574, 'learning_rate': 0.015600000000000001, 'epoch': 0.28}
22%|โโโ | 22/100 [04:28<15:50, 12.18s/it]
23%|โโโ | 23/100 [04:40<15:37, 12.18s/it]
{'loss': 0.8937, 'learning_rate': 0.0154, 'epoch': 0.29}
23%|โโโ | 23/100 [04:40<15:37, 12.18s/it]
24%|โโโ | 24/100 [04:52<15:25, 12.17s/it]
{'loss': 0.709, 'learning_rate': 0.0152, 'epoch': 0.31}
24%|โโโ | 24/100 [04:52<15:25, 12.17s/it]
25%|โโโ | 25/100 [05:04<15:13, 12.18s/it]
{'loss': 0.8731, 'learning_rate': 0.015, 'epoch': 0.32}
25%|โโโ | 25/100 [05:04<15:13, 12.18s/it]
26%|โโโ | 26/100 [05:17<15:00, 12.17s/it]
{'loss': 0.719, 'learning_rate': 0.0148, 'epoch': 0.33}
26%|โโโ | 26/100 [05:17<15:00, 12.17s/it]
27%|โโโ | 27/100 [05:29<14:49, 12.18s/it]
{'loss': 0.7419, 'learning_rate': 0.0146, 'epoch': 0.34}
27%|โโโ | 27/100 [05:29<14:49, 12.18s/it]
28%|โโโ | 28/100 [05:41<14:36, 12.17s/it]
{'loss': 0.9224, 'learning_rate': 0.0144, 'epoch': 0.36}
28%|โโโ | 28/100 [05:41<14:36, 12.17s/it]
29%|โโโ | 29/100 [05:53<14:25, 12.19s/it]
{'loss': 1.0802, 'learning_rate': 0.014199999999999999, 'epoch': 0.37}
29%|โโโ | 29/100 [05:53<14:25, 12.19s/it]
30%|โโโ | 30/100 [06:05<14:13, 12.19s/it]
{'loss': 0.8187, 'learning_rate': 0.013999999999999999, 'epoch': 0.38}
30%|โโโ | 30/100 [06:05<14:13, 12.19s/it]
31%|โโโ | 31/100 [06:17<14:00, 12.18s/it]
{'loss': 0.615, 'learning_rate': 0.0138, 'epoch': 0.39}
31%|โโโ | 31/100 [06:17<14:00, 12.18s/it]
32%|โโโโ | 32/100 [06:30<13:48, 12.18s/it]
{'loss': 0.5214, 'learning_rate': 0.013600000000000001, 'epoch': 0.41}
32%|โโโโ | 32/100 [06:30<13:48, 12.18s/it]
33%|โโโโ | 33/100 [06:42<13:36, 12.18s/it]
{'loss': 0.649, 'learning_rate': 0.0134, 'epoch': 0.42}
33%|โโโโ | 33/100 [06:42<13:36, 12.18s/it]
34%|โโโโ | 34/100 [06:54<13:24, 12.18s/it]
{'loss': 0.6523, 'learning_rate': 0.013200000000000002, 'epoch': 0.43}
34%|โโโโ | 34/100 [06:54<13:24, 12.18s/it]
35%|โโโโ | 35/100 [07:06<13:10, 12.16s/it]
{'loss': 0.7002, 'learning_rate': 0.013000000000000001, 'epoch': 0.45}
35%|โโโโ | 35/100 [07:06<13:10, 12.16s/it]
36%|โโโโ | 36/100 [07:18<12:57, 12.16s/it]
{'loss': 0.6161, 'learning_rate': 0.0128, 'epoch': 0.46}
36%|โโโโ | 36/100 [07:18<12:57, 12.16s/it]
37%|โโโโ | 37/100 [07:30<12:46, 12.17s/it]
{'loss': 1.0374, 'learning_rate': 0.0126, 'epoch': 0.47}
37%|โโโโ | 37/100 [07:30<12:46, 12.17s/it]
38%|โโโโ | 38/100 [07:43<12:34, 12.17s/it]
{'loss': 1.0328, 'learning_rate': 0.0124, 'epoch': 0.48}
38%|โโโโ | 38/100 [07:43<12:34, 12.17s/it]
39%|โโโโ | 39/100 [07:55<12:22, 12.17s/it]
{'loss': 0.7637, 'learning_rate': 0.0122, 'epoch': 0.5}
39%|โโโโ | 39/100 [07:55<12:22, 12.17s/it]
40%|โโโโ | 40/100 [08:07<12:10, 12.17s/it]
{'loss': 0.6332, 'learning_rate': 0.012, 'epoch': 0.51}
40%|โโโโ | 40/100 [08:07<12:10, 12.17s/it]
41%|โโโโ | 41/100 [08:19<11:58, 12.18s/it]
{'loss': 0.74, 'learning_rate': 0.0118, 'epoch': 0.52}
41%|โโโโ | 41/100 [08:19<11:58, 12.18s/it]
42%|โโโโโ | 42/100 [08:31<11:46, 12.17s/it]
{'loss': 0.7284, 'learning_rate': 0.0116, 'epoch': 0.53}
42%|โโโโโ | 42/100 [08:31<11:46, 12.17s/it]
43%|โโโโโ | 43/100 [08:44<11:34, 12.18s/it]
{'loss': 0.9198, 'learning_rate': 0.011399999999999999, 'epoch': 0.55}
43%|โโโโโ | 43/100 [08:44<11:34, 12.18s/it]
44%|โโโโโ | 44/100 [08:56<11:21, 12.17s/it]
{'loss': 0.626, 'learning_rate': 0.011200000000000002, 'epoch': 0.56}
44%|โโโโโ | 44/100 [08:56<11:21, 12.17s/it]
45%|โโโโโ | 45/100 [09:08<11:09, 12.17s/it]
{'loss': 0.628, 'learning_rate': 0.011000000000000001, 'epoch': 0.57}
45%|โโโโโ | 45/100 [09:08<11:09, 12.17s/it]
46%|โโโโโ | 46/100 [09:20<10:57, 12.18s/it]
{'loss': 0.5322, 'learning_rate': 0.0108, 'epoch': 0.59}
46%|โโโโโ | 46/100 [09:20<10:57, 12.18s/it]
47%|โโโโโ | 47/100 [09:32<10:44, 12.17s/it]
{'loss': 0.7844, 'learning_rate': 0.0106, 'epoch': 0.6}
47%|โโโโโ | 47/100 [09:32<10:44, 12.17s/it]
48%|โโโโโ | 48/100 [09:44<10:33, 12.18s/it]
{'loss': 0.5957, 'learning_rate': 0.010400000000000001, 'epoch': 0.61}
48%|โโโโโ | 48/100 [09:44<10:33, 12.18s/it]
49%|โโโโโ | 49/100 [09:57<10:21, 12.19s/it]
{'loss': 0.6681, 'learning_rate': 0.0102, 'epoch': 0.62}
49%|โโโโโ | 49/100 [09:57<10:21, 12.19s/it]
50%|โโโโโ | 50/100 [10:09<10:09, 12.18s/it]
{'loss': 0.8281, 'learning_rate': 0.01, 'epoch': 0.64}
50%|โโโโโ | 50/100 [10:09<10:09, 12.18s/it]
51%|โโโโโ | 51/100 [10:21<09:56, 12.17s/it]
{'loss': 0.5284, 'learning_rate': 0.0098, 'epoch': 0.65}
51%|โโโโโ | 51/100 [10:21<09:56, 12.17s/it]
52%|โโโโโโ | 52/100 [10:33<09:44, 12.18s/it]
{'loss': 0.8251, 'learning_rate': 0.0096, 'epoch': 0.66}
52%|โโโโโโ | 52/100 [10:33<09:44, 12.18s/it]
53%|โโโโโโ | 53/100 [10:45<09:32, 12.19s/it]
{'loss': 0.9845, 'learning_rate': 0.0094, 'epoch': 0.67}
53%|โโโโโโ | 53/100 [10:45<09:32, 12.19s/it]
54%|โโโโโโ | 54/100 [10:58<09:20, 12.18s/it]
{'loss': 0.9525, 'learning_rate': 0.0092, 'epoch': 0.69}
54%|โโโโโโ | 54/100 [10:58<09:20, 12.18s/it]
55%|โโโโโโ | 55/100 [11:10<09:08, 12.18s/it]
{'loss': 0.9454, 'learning_rate': 0.009000000000000001, 'epoch': 0.7}
55%|โโโโโโ | 55/100 [11:10<09:08, 12.18s/it]
56%|โโโโโโ | 56/100 [11:22<08:56, 12.19s/it]
{'loss': 0.4058, 'learning_rate': 0.0088, 'epoch': 0.71}
56%|โโโโโโ | 56/100 [11:22<08:56, 12.19s/it]
57%|โโโโโโ | 57/100 [11:34<08:43, 12.18s/it]
{'loss': 0.5435, 'learning_rate': 0.0086, 'epoch': 0.73}
57%|โโโโโโ | 57/100 [11:34<08:43, 12.18s/it]
58%|โโโโโโ | 58/100 [11:46<08:31, 12.18s/it]
{'loss': 0.6892, 'learning_rate': 0.0084, 'epoch': 0.74}
58%|โโโโโโ | 58/100 [11:46<08:31, 12.18s/it]
59%|โโโโโโ | 59/100 [11:58<08:19, 12.18s/it]
{'loss': 0.6426, 'learning_rate': 0.008199999999999999, 'epoch': 0.75}
59%|โโโโโโ | 59/100 [11:58<08:19, 12.18s/it]
60%|โโโโโโ | 60/100 [12:11<08:07, 12.18s/it]
{'loss': 0.9414, 'learning_rate': 0.008, 'epoch': 0.76}
60%|โโโโโโ | 60/100 [12:11<08:07, 12.18s/it]
61%|โโโโโโ | 61/100 [12:23<07:55, 12.19s/it]
{'loss': 0.7945, 'learning_rate': 0.0078000000000000005, 'epoch': 0.78}
61%|โโโโโโ | 61/100 [12:23<07:55, 12.19s/it]
62%|โโโโโโโ | 62/100 [12:35<07:42, 12.18s/it]
{'loss': 0.6295, 'learning_rate': 0.0076, 'epoch': 0.79}
62%|โโโโโโโ | 62/100 [12:35<07:42, 12.18s/it]
63%|โโโโโโโ | 63/100 [12:47<07:30, 12.18s/it]
{'loss': 0.7888, 'learning_rate': 0.0074, 'epoch': 0.8}
63%|โโโโโโโ | 63/100 [12:47<07:30, 12.18s/it]
64%|โโโโโโโ | 64/100 [12:59<07:18, 12.18s/it]
{'loss': 0.5454, 'learning_rate': 0.0072, 'epoch': 0.81}
64%|โโโโโโโ | 64/100 [12:59<07:18, 12.18s/it]
65%|โโโโโโโ | 65/100 [13:12<07:06, 12.18s/it]
{'loss': 0.711, 'learning_rate': 0.006999999999999999, 'epoch': 0.83}
65%|โโโโโโโ | 65/100 [13:12<07:06, 12.18s/it]
66%|โโโโโโโ | 66/100 [13:24<06:54, 12.18s/it]
{'loss': 0.713, 'learning_rate': 0.0068000000000000005, 'epoch': 0.84}
66%|โโโโโโโ | 66/100 [13:24<06:54, 12.18s/it]
67%|โโโโโโโ | 67/100 [13:36<06:42, 12.19s/it]
{'loss': 0.6058, 'learning_rate': 0.006600000000000001, 'epoch': 0.85}
67%|โโโโโโโ | 67/100 [13:36<06:42, 12.19s/it]
68%|โโโโโโโ | 68/100 [13:48<06:29, 12.17s/it]
{'loss': 0.8203, 'learning_rate': 0.0064, 'epoch': 0.87}
68%|โโโโโโโ | 68/100 [13:48<06:29, 12.17s/it]
69%|โโโโโโโ | 69/100 [14:00<06:17, 12.16s/it]
{'loss': 0.8275, 'learning_rate': 0.0062, 'epoch': 0.88}
69%|โโโโโโโ | 69/100 [14:00<06:17, 12.16s/it]
70%|โโโโโโโ | 70/100 [14:12<06:04, 12.16s/it]
{'loss': 0.4923, 'learning_rate': 0.006, 'epoch': 0.89}
70%|โโโโโโโ | 70/100 [14:12<06:04, 12.16s/it]
71%|โโโโโโโ | 71/100 [14:25<05:52, 12.16s/it]
{'loss': 0.5219, 'learning_rate': 0.0058, 'epoch': 0.9}
71%|โโโโโโโ | 71/100 [14:25<05:52, 12.16s/it]
72%|โโโโโโโโ | 72/100 [14:37<05:41, 12.19s/it]
{'loss': 0.9954, 'learning_rate': 0.005600000000000001, 'epoch': 0.92}
72%|โโโโโโโโ | 72/100 [14:37<05:41, 12.19s/it]
73%|โโโโโโโโ | 73/100 [14:49<05:28, 12.18s/it]
{'loss': 0.6206, 'learning_rate': 0.0054, 'epoch': 0.93}
73%|โโโโโโโโ | 73/100 [14:49<05:28, 12.18s/it]
74%|โโโโโโโโ | 74/100 [15:01<05:16, 12.18s/it]
{'loss': 0.6064, 'learning_rate': 0.005200000000000001, 'epoch': 0.94}
74%|โโโโโโโโ | 74/100 [15:01<05:16, 12.18s/it]
75%|โโโโโโโโ | 75/100 [15:13<05:04, 12.19s/it]
{'loss': 0.6584, 'learning_rate': 0.005, 'epoch': 0.95}
75%|โโโโโโโโ | 75/100 [15:13<05:04, 12.19s/it]
76%|โโโโโโโโ | 76/100 [15:26<04:52, 12.19s/it]
{'loss': 0.8461, 'learning_rate': 0.0048, 'epoch': 0.97}
76%|โโโโโโโโ | 76/100 [15:26<04:52, 12.19s/it]
77%|โโโโโโโโ | 77/100 [15:38<04:40, 12.19s/it]
{'loss': 0.9615, 'learning_rate': 0.0046, 'epoch': 0.98}
77%|โโโโโโโโ | 77/100 [15:38<04:40, 12.19s/it]
78%|โโโโโโโโ | 78/100 [15:50<04:28, 12.19s/it]
{'loss': 0.6508, 'learning_rate': 0.0044, 'epoch': 0.99}
78%|โโโโโโโโ | 78/100 [15:50<04:28, 12.19s/it]
79%|โโโโโโโโ | 79/100 [16:02<04:16, 12.20s/it]
{'loss': 1.0089, 'learning_rate': 0.0042, 'epoch': 1.01}
79%|โโโโโโโโ | 79/100 [16:02<04:16, 12.20s/it]
80%|โโโโโโโโ | 80/100 [16:14<04:03, 12.17s/it]
{'loss': 0.7515, 'learning_rate': 0.004, 'epoch': 1.02}
80%|โโโโโโโโ | 80/100 [16:14<04:03, 12.17s/it]
81%|โโโโโโโโ | 81/100 [16:26<03:51, 12.18s/it]
{'loss': 0.4172, 'learning_rate': 0.0038, 'epoch': 1.03}
81%|โโโโโโโโ | 81/100 [16:26<03:51, 12.18s/it]
82%|โโโโโโโโโ | 82/100 [16:39<03:39, 12.18s/it]
{'loss': 0.7634, 'learning_rate': 0.0036, 'epoch': 1.04}
82%|โโโโโโโโโ | 82/100 [16:39<03:39, 12.18s/it]
83%|โโโโโโโโโ | 83/100 [16:51<03:26, 12.16s/it]
{'loss': 0.585, 'learning_rate': 0.0034000000000000002, 'epoch': 1.06}
83%|โโโโโโโโโ | 83/100 [16:51<03:26, 12.16s/it]
84%|โโโโโโโโโ | 84/100 [17:03<03:14, 12.18s/it]
{'loss': 0.7668, 'learning_rate': 0.0032, 'epoch': 1.07}
84%|โโโโโโโโโ | 84/100 [17:03<03:14, 12.18s/it]
85%|โโโโโโโโโ | 85/100 [17:15<03:02, 12.18s/it]
{'loss': 0.5403, 'learning_rate': 0.003, 'epoch': 1.08}
85%|โโโโโโโโโ | 85/100 [17:15<03:02, 12.18s/it]
86%|โโโโโโโโโ | 86/100 [17:27<02:50, 12.18s/it]
{'loss': 0.5995, 'learning_rate': 0.0028000000000000004, 'epoch': 1.09}
86%|โโโโโโโโโ | 86/100 [17:27<02:50, 12.18s/it]
87%|โโโโโโโโโ | 87/100 [17:39<02:38, 12.18s/it]
{'loss': 0.4515, 'learning_rate': 0.0026000000000000003, 'epoch': 1.11}
87%|โโโโโโโโโ | 87/100 [17:39<02:38, 12.18s/it]
88%|โโโโโโโโโ | 88/100 [17:52<02:26, 12.18s/it]
{'loss': 0.6288, 'learning_rate': 0.0024, 'epoch': 1.12}
88%|โโโโโโโโโ | 88/100 [17:52<02:26, 12.18s/it]
89%|โโโโโโโโโ | 89/100 [18:04<02:13, 12.18s/it]
{'loss': 0.7387, 'learning_rate': 0.0022, 'epoch': 1.13}
89%|โโโโโโโโโ | 89/100 [18:04<02:13, 12.18s/it]
90%|โโโโโโโโโ | 90/100 [18:16<02:01, 12.18s/it]
{'loss': 0.6517, 'learning_rate': 0.002, 'epoch': 1.15}
90%|โโโโโโโโโ | 90/100 [18:16<02:01, 12.18s/it]
91%|โโโโโโโโโ | 91/100 [18:28<01:49, 12.18s/it]
{'loss': 0.5389, 'learning_rate': 0.0018, 'epoch': 1.16}
91%|โโโโโโโโโ | 91/100 [18:28<01:49, 12.18s/it]
92%|โโโโโโโโโโ| 92/100 [18:40<01:37, 12.20s/it]
{'loss': 0.4433, 'learning_rate': 0.0016, 'epoch': 1.17}
92%|โโโโโโโโโโ| 92/100 [18:40<01:37, 12.20s/it]
93%|โโโโโโโโโโ| 93/100 [18:53<01:25, 12.21s/it]
{'loss': 0.6643, 'learning_rate': 0.0014000000000000002, 'epoch': 1.18}
93%|โโโโโโโโโโ| 93/100 [18:53<01:25, 12.21s/it]
94%|โโโโโโโโโโ| 94/100 [19:05<01:13, 12.19s/it]
{'loss': 0.5825, 'learning_rate': 0.0012, 'epoch': 1.2}
94%|โโโโโโโโโโ| 94/100 [19:05<01:13, 12.19s/it]
95%|โโโโโโโโโโ| 95/100 [19:17<01:00, 12.18s/it]
{'loss': 0.7709, 'learning_rate': 0.001, 'epoch': 1.21}
95%|โโโโโโโโโโ| 95/100 [19:17<01:00, 12.18s/it]
96%|โโโโโโโโโโ| 96/100 [19:29<00:48, 12.18s/it]
{'loss': 0.562, 'learning_rate': 0.0008, 'epoch': 1.22}
96%|โโโโโโโโโโ| 96/100 [19:29<00:48, 12.18s/it]
97%|โโโโโโโโโโ| 97/100 [19:41<00:36, 12.19s/it]
{'loss': 0.5581, 'learning_rate': 0.0006, 'epoch': 1.23}
97%|โโโโโโโโโโ| 97/100 [19:41<00:36, 12.19s/it]
98%|โโโโโโโโโโ| 98/100 [19:54<00:24, 12.19s/it]
{'loss': 0.4679, 'learning_rate': 0.0004, 'epoch': 1.25}
98%|โโโโโโโโโโ| 98/100 [19:54<00:24, 12.19s/it]
99%|โโโโโโโโโโ| 99/100 [20:06<00:12, 12.18s/it]
{'loss': 0.5063, 'learning_rate': 0.0002, 'epoch': 1.26}
99%|โโโโโโโโโโ| 99/100 [20:06<00:12, 12.18s/it]
100%|โโโโโโโโโโ| 100/100 [20:18<00:00, 12.19s/it]
{'loss': 0.5527, 'learning_rate': 0.0, 'epoch': 1.27}
100%|โโโโโโโโโโ| 100/100 [20:18<00:00, 12.19s/it][INFO|trainer.py:1962] 2024-01-26 13:15:40,013 >>
Training completed. Do not forget to share your model on huggingface.co/models =)
{'train_runtime': 1218.4689, 'train_samples_per_second': 2.626, 'train_steps_per_second': 0.082, 'train_loss': 0.7395605874061585, 'epoch': 1.27}
100%|โโโโโโโโโโ| 100/100 [20:18<00:00, 12.19s/it]
100%|โโโโโโโโโโ| 100/100 [20:18<00:00, 12.18s/it]
Saving PrefixEncoder
[INFO|configuration_utils.py:473] 2024-01-26 13:15:40,038 >> Configuration saved in output/privacy_detection_pt-20240126-125436-128-2e-2/config.json
[INFO|configuration_utils.py:594] 2024-01-26 13:15:40,039 >> Configuration saved in output/privacy_detection_pt-20240126-125436-128-2e-2/generation_config.json
[INFO|modeling_utils.py:2495] 2024-01-26 13:15:40,068 >> Model weights saved in output/privacy_detection_pt-20240126-125436-128-2e-2/pytorch_model.bin
[INFO|tokenization_utils_base.py:2433] 2024-01-26 13:15:40,069 >> tokenizer config file saved in output/privacy_detection_pt-20240126-125436-128-2e-2/tokenizer_config.json
[INFO|tokenization_utils_base.py:2442] 2024-01-26 13:15:40,069 >> Special tokens file saved in output/privacy_detection_pt-20240126-125436-128-2e-2/special_tokens_map.json
|