| [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%|█▍ | 1/7 [00:02<00:15, 2.53s/it] Loading checkpoint shards: 29%|██▊ | 2/7 [00:04<00:12, 2.48s/it] Loading checkpoint shards: 43%|████▎ | 3/7 [00:08<00:12, 3.15s/it] Loading checkpoint shards: 57%|█████▋ | 4/7 [00:09<00:06, 2.27s/it] Loading checkpoint shards: 71%|███████▏ | 5/7 [00:17<00:08, 4.27s/it] Loading checkpoint shards: 86%|████████▌ | 6/7 [00:18<00:03, 3.18s/it] Loading checkpoint shards: 100%|██████████| 7/7 [00:19<00:00, 2.53s/it] Loading checkpoint shards: 100%|██████████| 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 | |
| '请': 55073 -> -100 | |
| '找出': 40369 -> -100 | |
| '下面': 33182 -> -100 | |
| '文本': 36704 -> -100 | |
| '中的': 31697 -> -100 | |
| 'position': 6523 -> -100 | |
| '：': 31211 -> -100 | |
| '艺术': 31835 -> -100 | |
| '是': 54532 -> -100 | |
| '相同的': 38815 -> -100 | |
| '，': 31123 -> -100 | |
| '音乐': 32000 -> -100 | |
| '美术': 33020 -> -100 | |
| '体育': 32214 -> -100 | |
| '三': 54645 -> -100 | |
| '样': 54741 -> -100 | |
| '都是': 31700 -> -100 | |
| '艺术': 31835 -> -100 | |
| '。，': 37843 -> -100 | |
| '三': 54645 -> -100 | |
| '样': 54741 -> -100 | |
| '艺术': 31835 -> -100 | |
| '都是': 31700 -> -100 | |
| '靠': 55518 -> -100 | |
| '感觉': 32044 -> -100 | |
| '的': 54530 -> -100 | |
| '。': 31155 -> -100 | |
| '感觉': 32044 -> -100 | |
| '好玩': 42814 -> -100 | |
| '起来': 31841 -> -100 | |
| '就很': 40030 -> -100 | |
| '轻松': 33550 -> -100 | |
| '，': 31123 -> -100 | |
| '所以': 31672 -> -100 | |
| '叫做': 35528 -> -100 | |
| '玩': 55409 -> -100 | |
| '艺术': 31835 -> -100 | |
| '。': 31155 -> -100 | |
| '没': 54721 -> -100 | |
| '感觉': 32044 -> -100 | |
| '找不到': 37779 -> -100 | |
| '北': 54760 -> -100 | |
| '的': 54530 -> -100 | |
| '干脆': 43396 -> -100 | |
| '别': 54835 -> -100 | |
| '玩': 55409 -> -100 | |
| '了': 54537 -> -100 | |
| '！': 31404 -> -100 | |
| '，': 31123 -> -100 | |
| '香港': 31776 -> -100 | |
| '电影': 31867 -> -100 | |
| '国语': 54385 -> -100 | |
| '配音': 40392 -> -100 | |
| '名家': 40465 -> -100 | |
| '周': 54896 -> -100 | |
| '思': 54872 -> -100 | |
| '平': 54678 -> -100 | |
| '，': 31123 -> -100 | |
| '代表作': 43527 -> -100 | |
| '有': 54536 -> -100 | |
| 'TVB': 42671 -> -100 | |
| '《': 54611 -> -100 | |
| '上海': 31770 -> -100 | |
| '滩': 56928 -> -100 | |
| '》': 54612 -> -100 | |
| '周': 54896 -> -100 | |
| '润': 55826 -> -100 | |
| '发': 54559 -> -100 | |
| '等': 54609 -> -100 | |
| '香港': 37944 -> 37944 | |
| '电影': 31867 -> 31867 | |
| '国语': 54385 -> 54385 | |
| '配音': 40392 -> 40392 | |
| '名家': 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%|▏ | 2/100 [00:25<20:33, 12.59s/it] {'loss': 0.787, 'learning_rate': 0.0196, 'epoch': 0.03} | |
| 2%|▏ | 2/100 [00:25<20:33, 12.59s/it] 3%|▎ | 3/100 [00:37<19:50, 12.27s/it] {'loss': 1.0047, 'learning_rate': 0.0194, 'epoch': 0.04} | |
| 3%|▎ | 3/100 [00:37<19:50, 12.27s/it] 4%|▍ | 4/100 [00:49<19:25, 12.14s/it] {'loss': 0.8688, 'learning_rate': 0.0192, 'epoch': 0.05} | |
| 4%|▍ | 4/100 [00:49<19:25, 12.14s/it] 5%|▌ | 5/100 [01:01<19:09, 12.10s/it] {'loss': 0.7173, 'learning_rate': 0.019, 'epoch': 0.06} | |
| 5%|▌ | 5/100 [01:01<19:09, 12.10s/it] 6%|▌ | 6/100 [01:13<18:55, 12.08s/it] {'loss': 0.5175, 'learning_rate': 0.0188, 'epoch': 0.08} | |
| 6%|▌ | 6/100 [01:13<18:55, 12.08s/it] 7%|▋ | 7/100 [01:25<18:45, 12.11s/it] {'loss': 0.7559, 'learning_rate': 0.018600000000000002, 'epoch': 0.09} | |
| 7%|▋ | 7/100 [01:25<18:45, 12.11s/it] 8%|▊ | 8/100 [01:37<18:35, 12.13s/it] {'loss': 0.9278, 'learning_rate': 0.0184, 'epoch': 0.1} | |
| 8%|▊ | 8/100 [01:37<18:35, 12.13s/it] 9%|▉ | 9/100 [01:49<18:25, 12.15s/it] {'loss': 0.6011, 'learning_rate': 0.0182, 'epoch': 0.11} | |
| 9%|▉ | 9/100 [01:49<18:25, 12.15s/it] 10%|█ | 10/100 [02:02<18:13, 12.15s/it] {'loss': 0.8014, 'learning_rate': 0.018000000000000002, 'epoch': 0.13} | |
| 10%|█ | 10/100 [02:02<18:13, 12.15s/it] 11%|█ | 11/100 [02:14<18:01, 12.16s/it] {'loss': 1.2581, 'learning_rate': 0.0178, 'epoch': 0.14} | |
| 11%|█ | 11/100 [02:14<18:01, 12.16s/it] 12%|█▏ | 12/100 [02:26<17:51, 12.18s/it] {'loss': 0.9886, 'learning_rate': 0.0176, 'epoch': 0.15} | |
| 12%|█▏ | 12/100 [02:26<17:51, 12.18s/it] 13%|█▎ | 13/100 [02:38<17:39, 12.18s/it] {'loss': 0.7866, 'learning_rate': 0.0174, 'epoch': 0.17} | |
| 13%|█▎ | 13/100 [02:38<17:39, 12.18s/it] 14%|█▍ | 14/100 [02:50<17:28, 12.19s/it] {'loss': 0.936, 'learning_rate': 0.0172, 'epoch': 0.18} | |
| 14%|█▍ | 14/100 [02:50<17:28, 12.19s/it] 15%|█▌ | 15/100 [03:03<17:17, 12.20s/it] {'loss': 1.0503, 'learning_rate': 0.017, 'epoch': 0.19} | |
| 15%|█▌ | 15/100 [03:03<17:17, 12.20s/it] 16%|█▌ | 16/100 [03:15<17:04, 12.20s/it] {'loss': 0.5689, 'learning_rate': 0.0168, 'epoch': 0.2} | |
| 16%|█▌ | 16/100 [03:15<17:04, 12.20s/it] 17%|█▋ | 17/100 [03:27<16:52, 12.20s/it] {'loss': 0.8576, 'learning_rate': 0.0166, 'epoch': 0.22} | |
| 17%|█▋ | 17/100 [03:27<16:52, 12.20s/it] 18%|█▊ | 18/100 [03:39<16:39, 12.19s/it] {'loss': 1.0946, 'learning_rate': 0.016399999999999998, 'epoch': 0.23} | |
| 18%|█▊ | 18/100 [03:39<16:39, 12.19s/it] 19%|█▉ | 19/100 [03:51<16:27, 12.19s/it] {'loss': 0.9075, 'learning_rate': 0.016200000000000003, 'epoch': 0.24} | |
| 19%|█▉ | 19/100 [03:51<16:27, 12.19s/it] 20%|██ | 20/100 [04:04<16:14, 12.18s/it] {'loss': 1.1441, 'learning_rate': 0.016, 'epoch': 0.25} | |
| 20%|██ | 20/100 [04:04<16:14, 12.18s/it] 21%|██ | 21/100 [04:16<16:01, 12.17s/it] {'loss': 0.7794, 'learning_rate': 0.0158, 'epoch': 0.27} | |
| 21%|██ | 21/100 [04:16<16:01, 12.17s/it] 22%|██▏ | 22/100 [04:28<15:50, 12.18s/it] {'loss': 0.9574, 'learning_rate': 0.015600000000000001, 'epoch': 0.28} | |
| 22%|██▏ | 22/100 [04:28<15:50, 12.18s/it] 23%|██▎ | 23/100 [04:40<15:37, 12.18s/it] {'loss': 0.8937, 'learning_rate': 0.0154, 'epoch': 0.29} | |
| 23%|██▎ | 23/100 [04:40<15:37, 12.18s/it] 24%|██▍ | 24/100 [04:52<15:25, 12.17s/it] {'loss': 0.709, 'learning_rate': 0.0152, 'epoch': 0.31} | |
| 24%|██▍ | 24/100 [04:52<15:25, 12.17s/it] 25%|██▌ | 25/100 [05:04<15:13, 12.18s/it] {'loss': 0.8731, 'learning_rate': 0.015, 'epoch': 0.32} | |
| 25%|██▌ | 25/100 [05:04<15:13, 12.18s/it] 26%|██▌ | 26/100 [05:17<15:00, 12.17s/it] {'loss': 0.719, 'learning_rate': 0.0148, 'epoch': 0.33} | |
| 26%|██▌ | 26/100 [05:17<15:00, 12.17s/it] 27%|██▋ | 27/100 [05:29<14:49, 12.18s/it] {'loss': 0.7419, 'learning_rate': 0.0146, 'epoch': 0.34} | |
| 27%|██▋ | 27/100 [05:29<14:49, 12.18s/it] 28%|██▊ | 28/100 [05:41<14:36, 12.17s/it] {'loss': 0.9224, 'learning_rate': 0.0144, 'epoch': 0.36} | |
| 28%|██▊ | 28/100 [05:41<14:36, 12.17s/it] 29%|██▉ | 29/100 [05:53<14:25, 12.19s/it] {'loss': 1.0802, 'learning_rate': 0.014199999999999999, 'epoch': 0.37} | |
| 29%|██▉ | 29/100 [05:53<14:25, 12.19s/it] 30%|███ | 30/100 [06:05<14:13, 12.19s/it] {'loss': 0.8187, 'learning_rate': 0.013999999999999999, 'epoch': 0.38} | |
| 30%|███ | 30/100 [06:05<14:13, 12.19s/it] 31%|███ | 31/100 [06:17<14:00, 12.18s/it] {'loss': 0.615, 'learning_rate': 0.0138, 'epoch': 0.39} | |
| 31%|███ | 31/100 [06:17<14:00, 12.18s/it] 32%|███▏ | 32/100 [06:30<13:48, 12.18s/it] {'loss': 0.5214, 'learning_rate': 0.013600000000000001, 'epoch': 0.41} | |
| 32%|███▏ | 32/100 [06:30<13:48, 12.18s/it] 33%|███▎ | 33/100 [06:42<13:36, 12.18s/it] {'loss': 0.649, 'learning_rate': 0.0134, 'epoch': 0.42} | |
| 33%|███▎ | 33/100 [06:42<13:36, 12.18s/it] 34%|███▍ | 34/100 [06:54<13:24, 12.18s/it] {'loss': 0.6523, 'learning_rate': 0.013200000000000002, 'epoch': 0.43} | |
| 34%|███▍ | 34/100 [06:54<13:24, 12.18s/it] 35%|███▌ | 35/100 [07:06<13:10, 12.16s/it] {'loss': 0.7002, 'learning_rate': 0.013000000000000001, 'epoch': 0.45} | |
| 35%|███▌ | 35/100 [07:06<13:10, 12.16s/it] 36%|███▌ | 36/100 [07:18<12:57, 12.16s/it] {'loss': 0.6161, 'learning_rate': 0.0128, 'epoch': 0.46} | |
| 36%|███▌ | 36/100 [07:18<12:57, 12.16s/it] 37%|███▋ | 37/100 [07:30<12:46, 12.17s/it] {'loss': 1.0374, 'learning_rate': 0.0126, 'epoch': 0.47} | |
| 37%|███▋ | 37/100 [07:30<12:46, 12.17s/it] 38%|███▊ | 38/100 [07:43<12:34, 12.17s/it] {'loss': 1.0328, 'learning_rate': 0.0124, 'epoch': 0.48} | |
| 38%|███▊ | 38/100 [07:43<12:34, 12.17s/it] 39%|███▉ | 39/100 [07:55<12:22, 12.17s/it] {'loss': 0.7637, 'learning_rate': 0.0122, 'epoch': 0.5} | |
| 39%|███▉ | 39/100 [07:55<12:22, 12.17s/it] 40%|████ | 40/100 [08:07<12:10, 12.17s/it] {'loss': 0.6332, 'learning_rate': 0.012, 'epoch': 0.51} | |
| 40%|████ | 40/100 [08:07<12:10, 12.17s/it] 41%|████ | 41/100 [08:19<11:58, 12.18s/it] {'loss': 0.74, 'learning_rate': 0.0118, 'epoch': 0.52} | |
| 41%|████ | 41/100 [08:19<11:58, 12.18s/it] 42%|████▏ | 42/100 [08:31<11:46, 12.17s/it] {'loss': 0.7284, 'learning_rate': 0.0116, 'epoch': 0.53} | |
| 42%|████▏ | 42/100 [08:31<11:46, 12.17s/it] 43%|████▎ | 43/100 [08:44<11:34, 12.18s/it] {'loss': 0.9198, 'learning_rate': 0.011399999999999999, 'epoch': 0.55} | |
| 43%|████▎ | 43/100 [08:44<11:34, 12.18s/it] 44%|████▍ | 44/100 [08:56<11:21, 12.17s/it] {'loss': 0.626, 'learning_rate': 0.011200000000000002, 'epoch': 0.56} | |
| 44%|████▍ | 44/100 [08:56<11:21, 12.17s/it] 45%|████▌ | 45/100 [09:08<11:09, 12.17s/it] {'loss': 0.628, 'learning_rate': 0.011000000000000001, 'epoch': 0.57} | |
| 45%|████▌ | 45/100 [09:08<11:09, 12.17s/it] 46%|████▌ | 46/100 [09:20<10:57, 12.18s/it] {'loss': 0.5322, 'learning_rate': 0.0108, 'epoch': 0.59} | |
| 46%|████▌ | 46/100 [09:20<10:57, 12.18s/it] 47%|████▋ | 47/100 [09:32<10:44, 12.17s/it] {'loss': 0.7844, 'learning_rate': 0.0106, 'epoch': 0.6} | |
| 47%|████▋ | 47/100 [09:32<10:44, 12.17s/it] 48%|████▊ | 48/100 [09:44<10:33, 12.18s/it] {'loss': 0.5957, 'learning_rate': 0.010400000000000001, 'epoch': 0.61} | |
| 48%|████▊ | 48/100 [09:44<10:33, 12.18s/it] 49%|████▉ | 49/100 [09:57<10:21, 12.19s/it] {'loss': 0.6681, 'learning_rate': 0.0102, 'epoch': 0.62} | |
| 49%|████▉ | 49/100 [09:57<10:21, 12.19s/it] 50%|█████ | 50/100 [10:09<10:09, 12.18s/it] {'loss': 0.8281, 'learning_rate': 0.01, 'epoch': 0.64} | |
| 50%|█████ | 50/100 [10:09<10:09, 12.18s/it] 51%|█████ | 51/100 [10:21<09:56, 12.17s/it] {'loss': 0.5284, 'learning_rate': 0.0098, 'epoch': 0.65} | |
| 51%|█████ | 51/100 [10:21<09:56, 12.17s/it] 52%|█████▏ | 52/100 [10:33<09:44, 12.18s/it] {'loss': 0.8251, 'learning_rate': 0.0096, 'epoch': 0.66} | |
| 52%|█████▏ | 52/100 [10:33<09:44, 12.18s/it] 53%|█████▎ | 53/100 [10:45<09:32, 12.19s/it] {'loss': 0.9845, 'learning_rate': 0.0094, 'epoch': 0.67} | |
| 53%|█████▎ | 53/100 [10:45<09:32, 12.19s/it] 54%|█████▍ | 54/100 [10:58<09:20, 12.18s/it] {'loss': 0.9525, 'learning_rate': 0.0092, 'epoch': 0.69} | |
| 54%|█████▍ | 54/100 [10:58<09:20, 12.18s/it] 55%|█████▌ | 55/100 [11:10<09:08, 12.18s/it] {'loss': 0.9454, 'learning_rate': 0.009000000000000001, 'epoch': 0.7} | |
| 55%|█████▌ | 55/100 [11:10<09:08, 12.18s/it] 56%|█████▌ | 56/100 [11:22<08:56, 12.19s/it] {'loss': 0.4058, 'learning_rate': 0.0088, 'epoch': 0.71} | |
| 56%|█████▌ | 56/100 [11:22<08:56, 12.19s/it] 57%|█████▋ | 57/100 [11:34<08:43, 12.18s/it] {'loss': 0.5435, 'learning_rate': 0.0086, 'epoch': 0.73} | |
| 57%|█████▋ | 57/100 [11:34<08:43, 12.18s/it] 58%|█████▊ | 58/100 [11:46<08:31, 12.18s/it] {'loss': 0.6892, 'learning_rate': 0.0084, 'epoch': 0.74} | |
| 58%|█████▊ | 58/100 [11:46<08:31, 12.18s/it] 59%|█████▉ | 59/100 [11:58<08:19, 12.18s/it] {'loss': 0.6426, 'learning_rate': 0.008199999999999999, 'epoch': 0.75} | |
| 59%|█████▉ | 59/100 [11:58<08:19, 12.18s/it] 60%|██████ | 60/100 [12:11<08:07, 12.18s/it] {'loss': 0.9414, 'learning_rate': 0.008, 'epoch': 0.76} | |
| 60%|██████ | 60/100 [12:11<08:07, 12.18s/it] 61%|██████ | 61/100 [12:23<07:55, 12.19s/it] {'loss': 0.7945, 'learning_rate': 0.0078000000000000005, 'epoch': 0.78} | |
| 61%|██████ | 61/100 [12:23<07:55, 12.19s/it] 62%|██████▏ | 62/100 [12:35<07:42, 12.18s/it] {'loss': 0.6295, 'learning_rate': 0.0076, 'epoch': 0.79} | |
| 62%|██████▏ | 62/100 [12:35<07:42, 12.18s/it] 63%|██████▎ | 63/100 [12:47<07:30, 12.18s/it] {'loss': 0.7888, 'learning_rate': 0.0074, 'epoch': 0.8} | |
| 63%|██████▎ | 63/100 [12:47<07:30, 12.18s/it] 64%|██████▍ | 64/100 [12:59<07:18, 12.18s/it] {'loss': 0.5454, 'learning_rate': 0.0072, 'epoch': 0.81} | |
| 64%|██████▍ | 64/100 [12:59<07:18, 12.18s/it] 65%|██████▌ | 65/100 [13:12<07:06, 12.18s/it] {'loss': 0.711, 'learning_rate': 0.006999999999999999, 'epoch': 0.83} | |
| 65%|██████▌ | 65/100 [13:12<07:06, 12.18s/it] 66%|██████▌ | 66/100 [13:24<06:54, 12.18s/it] {'loss': 0.713, 'learning_rate': 0.0068000000000000005, 'epoch': 0.84} | |
| 66%|██████▌ | 66/100 [13:24<06:54, 12.18s/it] 67%|██████▋ | 67/100 [13:36<06:42, 12.19s/it] {'loss': 0.6058, 'learning_rate': 0.006600000000000001, 'epoch': 0.85} | |
| 67%|██████▋ | 67/100 [13:36<06:42, 12.19s/it] 68%|██████▊ | 68/100 [13:48<06:29, 12.17s/it] {'loss': 0.8203, 'learning_rate': 0.0064, 'epoch': 0.87} | |
| 68%|██████▊ | 68/100 [13:48<06:29, 12.17s/it] 69%|██████▉ | 69/100 [14:00<06:17, 12.16s/it] {'loss': 0.8275, 'learning_rate': 0.0062, 'epoch': 0.88} | |
| 69%|██████▉ | 69/100 [14:00<06:17, 12.16s/it] 70%|███████ | 70/100 [14:12<06:04, 12.16s/it] {'loss': 0.4923, 'learning_rate': 0.006, 'epoch': 0.89} | |
| 70%|███████ | 70/100 [14:12<06:04, 12.16s/it] 71%|███████ | 71/100 [14:25<05:52, 12.16s/it] {'loss': 0.5219, 'learning_rate': 0.0058, 'epoch': 0.9} | |
| 71%|███████ | 71/100 [14:25<05:52, 12.16s/it] 72%|███████▏ | 72/100 [14:37<05:41, 12.19s/it] {'loss': 0.9954, 'learning_rate': 0.005600000000000001, 'epoch': 0.92} | |
| 72%|███████▏ | 72/100 [14:37<05:41, 12.19s/it] 73%|███████▎ | 73/100 [14:49<05:28, 12.18s/it] {'loss': 0.6206, 'learning_rate': 0.0054, 'epoch': 0.93} | |
| 73%|███████▎ | 73/100 [14:49<05:28, 12.18s/it] 74%|███████▍ | 74/100 [15:01<05:16, 12.18s/it] {'loss': 0.6064, 'learning_rate': 0.005200000000000001, 'epoch': 0.94} | |
| 74%|███████▍ | 74/100 [15:01<05:16, 12.18s/it] 75%|███████▌ | 75/100 [15:13<05:04, 12.19s/it] {'loss': 0.6584, 'learning_rate': 0.005, 'epoch': 0.95} | |
| 75%|███████▌ | 75/100 [15:13<05:04, 12.19s/it] 76%|███████▌ | 76/100 [15:26<04:52, 12.19s/it] {'loss': 0.8461, 'learning_rate': 0.0048, 'epoch': 0.97} | |
| 76%|███████▌ | 76/100 [15:26<04:52, 12.19s/it] 77%|███████▋ | 77/100 [15:38<04:40, 12.19s/it] {'loss': 0.9615, 'learning_rate': 0.0046, 'epoch': 0.98} | |
| 77%|███████▋ | 77/100 [15:38<04:40, 12.19s/it] 78%|███████▊ | 78/100 [15:50<04:28, 12.19s/it] {'loss': 0.6508, 'learning_rate': 0.0044, 'epoch': 0.99} | |
| 78%|███████▊ | 78/100 [15:50<04:28, 12.19s/it] 79%|███████▉ | 79/100 [16:02<04:16, 12.20s/it] {'loss': 1.0089, 'learning_rate': 0.0042, 'epoch': 1.01} | |
| 79%|███████▉ | 79/100 [16:02<04:16, 12.20s/it] 80%|████████ | 80/100 [16:14<04:03, 12.17s/it] {'loss': 0.7515, 'learning_rate': 0.004, 'epoch': 1.02} | |
| 80%|████████ | 80/100 [16:14<04:03, 12.17s/it] 81%|████████ | 81/100 [16:26<03:51, 12.18s/it] {'loss': 0.4172, 'learning_rate': 0.0038, 'epoch': 1.03} | |
| 81%|████████ | 81/100 [16:26<03:51, 12.18s/it] 82%|████████▏ | 82/100 [16:39<03:39, 12.18s/it] {'loss': 0.7634, 'learning_rate': 0.0036, 'epoch': 1.04} | |
| 82%|████████▏ | 82/100 [16:39<03:39, 12.18s/it] 83%|████████▎ | 83/100 [16:51<03:26, 12.16s/it] {'loss': 0.585, 'learning_rate': 0.0034000000000000002, 'epoch': 1.06} | |
| 83%|████████▎ | 83/100 [16:51<03:26, 12.16s/it] 84%|████████▍ | 84/100 [17:03<03:14, 12.18s/it] {'loss': 0.7668, 'learning_rate': 0.0032, 'epoch': 1.07} | |
| 84%|████████▍ | 84/100 [17:03<03:14, 12.18s/it] 85%|████████▌ | 85/100 [17:15<03:02, 12.18s/it] {'loss': 0.5403, 'learning_rate': 0.003, 'epoch': 1.08} | |
| 85%|████████▌ | 85/100 [17:15<03:02, 12.18s/it] 86%|████████▌ | 86/100 [17:27<02:50, 12.18s/it] {'loss': 0.5995, 'learning_rate': 0.0028000000000000004, 'epoch': 1.09} | |
| 86%|████████▌ | 86/100 [17:27<02:50, 12.18s/it] 87%|████████▋ | 87/100 [17:39<02:38, 12.18s/it] {'loss': 0.4515, 'learning_rate': 0.0026000000000000003, 'epoch': 1.11} | |
| 87%|████████▋ | 87/100 [17:39<02:38, 12.18s/it] 88%|████████▊ | 88/100 [17:52<02:26, 12.18s/it] {'loss': 0.6288, 'learning_rate': 0.0024, 'epoch': 1.12} | |
| 88%|████████▊ | 88/100 [17:52<02:26, 12.18s/it] 89%|████████▉ | 89/100 [18:04<02:13, 12.18s/it] {'loss': 0.7387, 'learning_rate': 0.0022, 'epoch': 1.13} | |
| 89%|████████▉ | 89/100 [18:04<02:13, 12.18s/it] 90%|█████████ | 90/100 [18:16<02:01, 12.18s/it] {'loss': 0.6517, 'learning_rate': 0.002, 'epoch': 1.15} | |
| 90%|█████████ | 90/100 [18:16<02:01, 12.18s/it] 91%|█████████ | 91/100 [18:28<01:49, 12.18s/it] {'loss': 0.5389, 'learning_rate': 0.0018, 'epoch': 1.16} | |
| 91%|█████████ | 91/100 [18:28<01:49, 12.18s/it] 92%|█████████▏| 92/100 [18:40<01:37, 12.20s/it] {'loss': 0.4433, 'learning_rate': 0.0016, 'epoch': 1.17} | |
| 92%|█████████▏| 92/100 [18:40<01:37, 12.20s/it] 93%|█████████▎| 93/100 [18:53<01:25, 12.21s/it] {'loss': 0.6643, 'learning_rate': 0.0014000000000000002, 'epoch': 1.18} | |
| 93%|█████████▎| 93/100 [18:53<01:25, 12.21s/it] 94%|█████████▍| 94/100 [19:05<01:13, 12.19s/it] {'loss': 0.5825, 'learning_rate': 0.0012, 'epoch': 1.2} | |
| 94%|█████████▍| 94/100 [19:05<01:13, 12.19s/it] 95%|█████████▌| 95/100 [19:17<01:00, 12.18s/it] {'loss': 0.7709, 'learning_rate': 0.001, 'epoch': 1.21} | |
| 95%|█████████▌| 95/100 [19:17<01:00, 12.18s/it] 96%|█████████▌| 96/100 [19:29<00:48, 12.18s/it] {'loss': 0.562, 'learning_rate': 0.0008, 'epoch': 1.22} | |
| 96%|█████████▌| 96/100 [19:29<00:48, 12.18s/it] 97%|█████████▋| 97/100 [19:41<00:36, 12.19s/it] {'loss': 0.5581, 'learning_rate': 0.0006, 'epoch': 1.23} | |
| 97%|█████████▋| 97/100 [19:41<00:36, 12.19s/it] 98%|█████████▊| 98/100 [19:54<00:24, 12.19s/it] {'loss': 0.4679, 'learning_rate': 0.0004, 'epoch': 1.25} | |
| 98%|█████████▊| 98/100 [19:54<00:24, 12.19s/it] 99%|█████████▉| 99/100 [20:06<00:12, 12.18s/it] {'loss': 0.5063, 'learning_rate': 0.0002, 'epoch': 1.26} | |
| 99%|█████████▉| 99/100 [20:06<00:12, 12.18s/it] 100%|██████████| 100/100 [20:18<00:00, 12.19s/it] {'loss': 0.5527, 'learning_rate': 0.0, 'epoch': 1.27} | |
| 100%|██████████| 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%|██████████| 100/100 [20:18<00:00, 12.19s/it] 100%|██████████| 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 | |