stderr.log

+ deepspeed --master_port 49924 --module safe_rlhf.finetune --train_datasets inverse-json::/home/hansirui_1st/jiayi/resist/setting3/safety_data/training/safe/safe_50k.json --model_name_or_path /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-480k-1T --max_length 2048 --trust_remote_code True --epochs 1 --per_device_train_batch_size 4 --per_device_eval_batch_size 4 --gradient_accumulation_steps 8 --gradient_checkpointing --learning_rate 1e-5 --lr_warmup_ratio 0 --weight_decay 0.0 --lr_scheduler_type constant --weight_decay 0.0 --seed 42 --output_dir /aifs4su/hansirui_1st/boyuan/resist/setting3-safety/tinyllama-1T/tinyllama-1T-s3-Q1-50k --log_type wandb --log_run_name tinyllama-1T-s3-Q1-50k --log_project Inverse_Alignment --zero_stage 3 --offload none --bf16 True --tf32 True --save_16bit
[rank1]:[W529 05:08:06.156426766 ProcessGroupNCCL.cpp:4561] [PG ID 0 PG GUID 0 Rank 1]  using GPU 1 to perform barrier as devices used by this process are currently unknown. This can potentially cause a hang if this rank to GPU mapping is incorrect. Specify device_ids in barrier() to force use of a particular device, or call init_process_group() with a device_id.
[rank5]:[W529 05:08:06.163112758 ProcessGroupNCCL.cpp:4561] [PG ID 0 PG GUID 0 Rank 5]  using GPU 5 to perform barrier as devices used by this process are currently unknown. This can potentially cause a hang if this rank to GPU mapping is incorrect. Specify device_ids in barrier() to force use of a particular device, or call init_process_group() with a device_id.
[rank6]:[W529 05:08:06.228977830 ProcessGroupNCCL.cpp:4561] [PG ID 0 PG GUID 0 Rank 6]  using GPU 6 to perform barrier as devices used by this process are currently unknown. This can potentially cause a hang if this rank to GPU mapping is incorrect. Specify device_ids in barrier() to force use of a particular device, or call init_process_group() with a device_id.
[rank3]:[W529 05:08:07.383451943 ProcessGroupNCCL.cpp:4561] [PG ID 0 PG GUID 0 Rank 3]  using GPU 3 to perform barrier as devices used by this process are currently unknown. This can potentially cause a hang if this rank to GPU mapping is incorrect. Specify device_ids in barrier() to force use of a particular device, or call init_process_group() with a device_id.
[rank2]:[W529 05:08:07.402205400 ProcessGroupNCCL.cpp:4561] [PG ID 0 PG GUID 0 Rank 2]  using GPU 2 to perform barrier as devices used by this process are currently unknown. This can potentially cause a hang if this rank to GPU mapping is incorrect. Specify device_ids in barrier() to force use of a particular device, or call init_process_group() with a device_id.
[rank4]:[W529 05:08:07.488685971 ProcessGroupNCCL.cpp:4561] [PG ID 0 PG GUID 0 Rank 4]  using GPU 4 to perform barrier as devices used by this process are currently unknown. This can potentially cause a hang if this rank to GPU mapping is incorrect. Specify device_ids in barrier() to force use of a particular device, or call init_process_group() with a device_id.
[rank0]:[W529 05:08:07.488763379 ProcessGroupNCCL.cpp:4561] [PG ID 0 PG GUID 0 Rank 0]  using GPU 0 to perform barrier as devices used by this process are currently unknown. This can potentially cause a hang if this rank to GPU mapping is incorrect. Specify device_ids in barrier() to force use of a particular device, or call init_process_group() with a device_id.
[rank7]:[W529 05:08:07.491929531 ProcessGroupNCCL.cpp:4561] [PG ID 0 PG GUID 0 Rank 7]  using GPU 7 to perform barrier as devices used by this process are currently unknown. This can potentially cause a hang if this rank to GPU mapping is incorrect. Specify device_ids in barrier() to force use of a particular device, or call init_process_group() with a device_id.
loading configuration file /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-480k-1T/config.json
loading configuration file /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-480k-1T/config.json
loading configuration file /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-480k-1T/config.json
loading configuration file /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-480k-1T/config.json
loading configuration file /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-480k-1T/config.json
loading configuration file /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-480k-1T/config.json
loading configuration file /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-480k-1T/config.json
loading configuration file /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-480k-1T/config.json
Model config LlamaConfig {
  "_name_or_path": "/aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-480k-1T",
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "head_dim": 64,
  "hidden_act": "silu",
  "hidden_size": 2048,
  "initializer_range": 0.02,
  "intermediate_size": 5632,
  "max_position_embeddings": 2048,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 22,
  "num_key_value_heads": 4,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "float32",
  "transformers_version": "4.49.0",
  "use_cache": true,
  "vocab_size": 32000
}

Model config LlamaConfig {
  "_name_or_path": "/aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-480k-1T",
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "head_dim": 64,
  "hidden_act": "silu",
  "hidden_size": 2048,
  "initializer_range": 0.02,
  "intermediate_size": 5632,
  "max_position_embeddings": 2048,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 22,
  "num_key_value_heads": 4,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "float32",
  "transformers_version": "4.49.0",
  "use_cache": true,
  "vocab_size": 32000
}

Model config LlamaConfig {
  "_name_or_path": "/aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-480k-1T",
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "head_dim": 64,
  "hidden_act": "silu",
  "hidden_size": 2048,
  "initializer_range": 0.02,
  "intermediate_size": 5632,
  "max_position_embeddings": 2048,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 22,
  "num_key_value_heads": 4,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "float32",
  "transformers_version": "4.49.0",
  "use_cache": true,
  "vocab_size": 32000
}

Model config LlamaConfig {
  "_name_or_path": "/aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-480k-1T",
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "head_dim": 64,
  "hidden_act": "silu",
  "hidden_size": 2048,
  "initializer_range": 0.02,
  "intermediate_size": 5632,
  "max_position_embeddings": 2048,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 22,
  "num_key_value_heads": 4,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "float32",
  "transformers_version": "4.49.0",
  "use_cache": true,
  "vocab_size": 32000
}

Model config LlamaConfig {
  "_name_or_path": "/aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-480k-1T",
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "head_dim": 64,
  "hidden_act": "silu",
  "hidden_size": 2048,
  "initializer_range": 0.02,
  "intermediate_size": 5632,
  "max_position_embeddings": 2048,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 22,
  "num_key_value_heads": 4,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "float32",
  "transformers_version": "4.49.0",
  "use_cache": true,
  "vocab_size": 32000
}

Model config LlamaConfig {
  "_name_or_path": "/aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-480k-1T",
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "head_dim": 64,
  "hidden_act": "silu",
  "hidden_size": 2048,
  "initializer_range": 0.02,
  "intermediate_size": 5632,
  "max_position_embeddings": 2048,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 22,
  "num_key_value_heads": 4,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "float32",
  "transformers_version": "4.49.0",
  "use_cache": true,
  "vocab_size": 32000
}

Model config LlamaConfig {
  "_name_or_path": "/aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-480k-1T",
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "head_dim": 64,
  "hidden_act": "silu",
  "hidden_size": 2048,
  "initializer_range": 0.02,
  "intermediate_size": 5632,
  "max_position_embeddings": 2048,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 22,
  "num_key_value_heads": 4,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "float32",
  "transformers_version": "4.49.0",
  "use_cache": true,
  "vocab_size": 32000
}

Model config LlamaConfig {
  "_name_or_path": "/aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-480k-1T",
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "head_dim": 64,
  "hidden_act": "silu",
  "hidden_size": 2048,
  "initializer_range": 0.02,
  "intermediate_size": 5632,
  "max_position_embeddings": 2048,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 22,
  "num_key_value_heads": 4,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "float32",
  "transformers_version": "4.49.0",
  "use_cache": true,
  "vocab_size": 32000
}

loading weights file /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-480k-1T/model.safetensors
loading weights file /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-480k-1T/model.safetensors
loading weights file /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-480k-1T/model.safetensors
loading weights file /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-480k-1T/model.safetensors
loading weights file /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-480k-1T/model.safetensors
loading weights file /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-480k-1T/model.safetensors
loading weights file /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-480k-1T/model.safetensors
loading weights file /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-480k-1T/model.safetensors
Will use torch_dtype=torch.float32 as defined in model's config object
Instantiating LlamaForCausalLM model under default dtype torch.float32.
Will use torch_dtype=torch.float32 as defined in model's config object
Instantiating LlamaForCausalLM model under default dtype torch.float32.
Detected DeepSpeed ZeRO-3: activating zero.init() for this model
Will use torch_dtype=torch.float32 as defined in model's config object
Instantiating LlamaForCausalLM model under default dtype torch.float32.
Detected DeepSpeed ZeRO-3: activating zero.init() for this model
Detected DeepSpeed ZeRO-3: activating zero.init() for this model
Will use torch_dtype=torch.float32 as defined in model's config object
Instantiating LlamaForCausalLM model under default dtype torch.float32.
Detected DeepSpeed ZeRO-3: activating zero.init() for this model
Will use torch_dtype=torch.float32 as defined in model's config object
Instantiating LlamaForCausalLM model under default dtype torch.float32.
Will use torch_dtype=torch.float32 as defined in model's config object
Instantiating LlamaForCausalLM model under default dtype torch.float32.
Will use torch_dtype=torch.float32 as defined in model's config object
Detected DeepSpeed ZeRO-3: activating zero.init() for this model
Instantiating LlamaForCausalLM model under default dtype torch.float32.
Detected DeepSpeed ZeRO-3: activating zero.init() for this model
Will use torch_dtype=torch.float32 as defined in model's config object
Detected DeepSpeed ZeRO-3: activating zero.init() for this model
Instantiating LlamaForCausalLM model under default dtype torch.float32.
Detected DeepSpeed ZeRO-3: activating zero.init() for this model
Generate config GenerationConfig {
  "bos_token_id": 1,
  "eos_token_id": 2
}

Generate config GenerationConfig {
  "bos_token_id": 1,
  "eos_token_id": 2
}

Generate config GenerationConfig {
  "bos_token_id": 1,
  "eos_token_id": 2
}

Generate config GenerationConfig {
  "bos_token_id": 1,
  "eos_token_id": 2
}

Generate config GenerationConfig {
  "bos_token_id": 1,
  "eos_token_id": 2
}

Generate config GenerationConfig {
  "bos_token_id": 1,
  "eos_token_id": 2
}

Generate config GenerationConfig {
  "bos_token_id": 1,
  "eos_token_id": 2
}

Generate config GenerationConfig {
  "bos_token_id": 1,
  "eos_token_id": 2
}

All model checkpoint weights were used when initializing LlamaForCausalLM.

All the weights of LlamaForCausalLM were initialized from the model checkpoint at /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-480k-1T.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlamaForCausalLM for predictions without further training.
All model checkpoint weights were used when initializing LlamaForCausalLM.

All the weights of LlamaForCausalLM were initialized from the model checkpoint at /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-480k-1T.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlamaForCausalLM for predictions without further training.
All model checkpoint weights were used when initializing LlamaForCausalLM.

All model checkpoint weights were used when initializing LlamaForCausalLM.

All model checkpoint weights were used when initializing LlamaForCausalLM.

All the weights of LlamaForCausalLM were initialized from the model checkpoint at /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-480k-1T.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlamaForCausalLM for predictions without further training.
All the weights of LlamaForCausalLM were initialized from the model checkpoint at /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-480k-1T.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlamaForCausalLM for predictions without further training.
All the weights of LlamaForCausalLM were initialized from the model checkpoint at /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-480k-1T.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlamaForCausalLM for predictions without further training.
All model checkpoint weights were used when initializing LlamaForCausalLM.

All the weights of LlamaForCausalLM were initialized from the model checkpoint at /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-480k-1T.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlamaForCausalLM for predictions without further training.
loading configuration file /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-480k-1T/generation_config.json
Generate config GenerationConfig {
  "bos_token_id": 1,
  "eos_token_id": 2,
  "max_length": 2048,
  "pad_token_id": 0
}

loading configuration file /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-480k-1T/generation_config.json
loading configuration file /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-480k-1T/generation_config.json
loading configuration file /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-480k-1T/generation_config.json
loading configuration file /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-480k-1T/generation_config.json
Generate config GenerationConfig {
  "bos_token_id": 1,
  "eos_token_id": 2,
  "max_length": 2048,
  "pad_token_id": 0
}

loading configuration file /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-480k-1T/generation_config.json
Generate config GenerationConfig {
  "bos_token_id": 1,
  "eos_token_id": 2,
  "max_length": 2048,
  "pad_token_id": 0
}

Generate config GenerationConfig {
  "bos_token_id": 1,
  "eos_token_id": 2,
  "max_length": 2048,
  "pad_token_id": 0
}

Generate config GenerationConfig {
  "bos_token_id": 1,
  "eos_token_id": 2,
  "max_length": 2048,
  "pad_token_id": 0
}

Generate config GenerationConfig {
  "bos_token_id": 1,
  "eos_token_id": 2,
  "max_length": 2048,
  "pad_token_id": 0
}

All model checkpoint weights were used when initializing LlamaForCausalLM.

All the weights of LlamaForCausalLM were initialized from the model checkpoint at /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-480k-1T.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlamaForCausalLM for predictions without further training.
loading configuration file /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-480k-1T/generation_config.json
Generate config GenerationConfig {
  "bos_token_id": 1,
  "eos_token_id": 2,
  "max_length": 2048,
  "pad_token_id": 0
}

loading file tokenizer.model
loading file tokenizer.json
loading file added_tokens.json
loading file special_tokens_map.json
loading file tokenizer_config.json
loading file chat_template.jinja
loading file tokenizer.model
loading file tokenizer.json
loading file added_tokens.json
loading file special_tokens_map.json
loading file tokenizer_config.json
loading file chat_template.jinja
loading file tokenizer.model
loading file tokenizer.model
loading file tokenizer.json
loading file added_tokens.json
loading file tokenizer.json
loading file special_tokens_map.json
loading file added_tokens.json
loading file tokenizer_config.json
loading file special_tokens_map.json
loading file chat_template.jinja
loading file tokenizer_config.json
loading file chat_template.jinja
loading file tokenizer.model
loading file tokenizer.json
loading file added_tokens.json
loading file special_tokens_map.json
loading file tokenizer_config.json
loading file chat_template.jinja
loading file tokenizer.model
loading file tokenizer.json
loading file added_tokens.json
loading file special_tokens_map.json
loading file tokenizer_config.json
loading file chat_template.jinja
loading file tokenizer.model
loading file tokenizer.json
loading file added_tokens.json
loading file special_tokens_map.json
loading file tokenizer_config.json
loading file chat_template.jinja
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 32001. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 32001. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 32001. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 32001. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 32001. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 32001. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 32001. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
All model checkpoint weights were used when initializing LlamaForCausalLM.

All the weights of LlamaForCausalLM were initialized from the model checkpoint at /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-480k-1T.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlamaForCausalLM for predictions without further training.
loading configuration file /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-480k-1T/generation_config.json
Generate config GenerationConfig {
  "bos_token_id": 1,
  "eos_token_id": 2,
  "max_length": 2048,
  "pad_token_id": 0
}

loading file tokenizer.model
loading file tokenizer.json
loading file added_tokens.json
loading file special_tokens_map.json
loading file tokenizer_config.json
loading file chat_template.jinja
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 32001. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
The new embeddings will be initialized from a multivariate normal distribution that has old embeddings' mean and covariance. As described in this article: https://nlp.stanford.edu/~johnhew/vocab-expansion.html. To disable this, use `mean_resizing=False`
The new embeddings will be initialized from a multivariate normal distribution that has old embeddings' mean and covariance. As described in this article: https://nlp.stanford.edu/~johnhew/vocab-expansion.html. To disable this, use `mean_resizing=False`
The new embeddings will be initialized from a multivariate normal distribution that has old embeddings' mean and covariance. As described in this article: https://nlp.stanford.edu/~johnhew/vocab-expansion.html. To disable this, use `mean_resizing=False`
The new embeddings will be initialized from a multivariate normal distribution that has old embeddings' mean and covariance. As described in this article: https://nlp.stanford.edu/~johnhew/vocab-expansion.html. To disable this, use `mean_resizing=False`
The new embeddings will be initialized from a multivariate normal distribution that has old embeddings' mean and covariance. As described in this article: https://nlp.stanford.edu/~johnhew/vocab-expansion.html. To disable this, use `mean_resizing=False`
The new embeddings will be initialized from a multivariate normal distribution that has old embeddings' mean and covariance. As described in this article: https://nlp.stanford.edu/~johnhew/vocab-expansion.html. To disable this, use `mean_resizing=False`
The new embeddings will be initialized from a multivariate normal distribution that has old embeddings' mean and covariance. As described in this article: https://nlp.stanford.edu/~johnhew/vocab-expansion.html. To disable this, use `mean_resizing=False`
The new embeddings will be initialized from a multivariate normal distribution that has old embeddings' mean and covariance. As described in this article: https://nlp.stanford.edu/~johnhew/vocab-expansion.html. To disable this, use `mean_resizing=False`
The new lm_head weights will be initialized from a multivariate normal distribution that has old embeddings' mean and covariance. As described in this article: https://nlp.stanford.edu/~johnhew/vocab-expansion.html. To disable this, use `mean_resizing=False`
The new lm_head weights will be initialized from a multivariate normal distribution that has old embeddings' mean and covariance. As described in this article: https://nlp.stanford.edu/~johnhew/vocab-expansion.html. To disable this, use `mean_resizing=False`
The new lm_head weights will be initialized from a multivariate normal distribution that has old embeddings' mean and covariance. As described in this article: https://nlp.stanford.edu/~johnhew/vocab-expansion.html. To disable this, use `mean_resizing=False`
The new lm_head weights will be initialized from a multivariate normal distribution that has old embeddings' mean and covariance. As described in this article: https://nlp.stanford.edu/~johnhew/vocab-expansion.html. To disable this, use `mean_resizing=False`
The new lm_head weights will be initialized from a multivariate normal distribution that has old embeddings' mean and covariance. As described in this article: https://nlp.stanford.edu/~johnhew/vocab-expansion.html. To disable this, use `mean_resizing=False`
The new lm_head weights will be initialized from a multivariate normal distribution that has old embeddings' mean and covariance. As described in this article: https://nlp.stanford.edu/~johnhew/vocab-expansion.html. To disable this, use `mean_resizing=False`
The new lm_head weights will be initialized from a multivariate normal distribution that has old embeddings' mean and covariance. As described in this article: https://nlp.stanford.edu/~johnhew/vocab-expansion.html. To disable this, use `mean_resizing=False`
The new lm_head weights will be initialized from a multivariate normal distribution that has old embeddings' mean and covariance. As described in this article: https://nlp.stanford.edu/~johnhew/vocab-expansion.html. To disable this, use `mean_resizing=False`
Using /home/hansirui_1st/.cache/torch_extensions/py311_cu124 as PyTorch extensions root...
Using /home/hansirui_1st/.cache/torch_extensions/py311_cu124 as PyTorch extensions root...
Using /home/hansirui_1st/.cache/torch_extensions/py311_cu124 as PyTorch extensions root...
Using /home/hansirui_1st/.cache/torch_extensions/py311_cu124 as PyTorch extensions root...
Using /home/hansirui_1st/.cache/torch_extensions/py311_cu124 as PyTorch extensions root...
Using /home/hansirui_1st/.cache/torch_extensions/py311_cu124 as PyTorch extensions root...
Using /home/hansirui_1st/.cache/torch_extensions/py311_cu124 as PyTorch extensions root...
Using /home/hansirui_1st/.cache/torch_extensions/py311_cu124 as PyTorch extensions root...
Detected CUDA files, patching ldflags
Emitting ninja build file /home/hansirui_1st/.cache/torch_extensions/py311_cu124/fused_adam/build.ninja...
/aifs4su/hansirui_1st/miniconda3/envs/by-align/lib/python3.11/site-packages/torch/utils/cpp_extension.py:2059: UserWarning: TORCH_CUDA_ARCH_LIST is not set, all archs for visible cards are included for compilation. 
If this is not desired, please set os.environ['TORCH_CUDA_ARCH_LIST'].
  warnings.warn(
Building extension module fused_adam...
Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)
Loading extension module fused_adam...
Loading extension module fused_adam...
Loading extension module fused_adam...
Loading extension module fused_adam...
Loading extension module fused_adam...
Loading extension module fused_adam...
Loading extension module fused_adam...
Loading extension module fused_adam...
wandb: Using wandb-core as the SDK backend.  Please refer to https://wandb.me/wandb-core for more information.
`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`.
`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`.
`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`.
`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`.
`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`.
`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`.
`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`.
wandb: Currently logged in as: xtom to https://api.wandb.ai. Use `wandb login --relogin` to force relogin
wandb: Tracking run with wandb version 0.19.8
wandb: Run data is saved locally in /aifs4su/hansirui_1st/boyuan/resist/setting3-safety/tinyllama-1T/tinyllama-1T-s3-Q1-50k/wandb/run-20250529_050824-f0h70cv5
wandb: Run `wandb offline` to turn off syncing.
wandb: Syncing run tinyllama-1T-s3-Q1-50k
wandb: ⭐️ View project at https://wandb.ai/xtom/Inverse_Alignment
wandb: 🚀 View run at https://wandb.ai/xtom/Inverse_Alignment/runs/f0h70cv5

Training 1/1 epoch:   0%|          | 0/1563 [00:00<?, ?it/s]`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`.

Training 1/1 epoch (loss 2.4782):   0%|          | 0/1563 [00:10<?, ?it/s]
Training 1/1 epoch (loss 2.4782):   0%|          | 1/1563 [00:10<4:37:56, 10.68s/it]
Training 1/1 epoch (loss 2.3928):   0%|          | 1/1563 [00:12<4:37:56, 10.68s/it]
Training 1/1 epoch (loss 2.3928):   0%|          | 2/1563 [00:12<2:29:00,  5.73s/it]
Training 1/1 epoch (loss 2.2977):   0%|          | 2/1563 [00:14<2:29:00,  5.73s/it]
Training 1/1 epoch (loss 2.2977):   0%|          | 3/1563 [00:14<1:37:48,  3.76s/it]
Training 1/1 epoch (loss 2.3725):   0%|          | 3/1563 [00:15<1:37:48,  3.76s/it]
Training 1/1 epoch (loss 2.3725):   0%|          | 4/1563 [00:15<1:12:16,  2.78s/it]
Training 1/1 epoch (loss 2.4576):   0%|          | 4/1563 [00:17<1:12:16,  2.78s/it]
Training 1/1 epoch (loss 2.4576):   0%|          | 5/1563 [00:17<1:00:13,  2.32s/it]
Training 1/1 epoch (loss 2.5388):   0%|          | 5/1563 [00:19<1:00:13,  2.32s/it]
Training 1/1 epoch (loss 2.5388):   0%|          | 6/1563 [00:19<56:23,  2.17s/it]  
Training 1/1 epoch (loss 2.3437):   0%|          | 6/1563 [00:20<56:23,  2.17s/it]
Training 1/1 epoch (loss 2.3437):   0%|          | 7/1563 [00:20<53:52,  2.08s/it]
Training 1/1 epoch (loss 2.3431):   0%|          | 7/1563 [00:23<53:52,  2.08s/it]
Training 1/1 epoch (loss 2.3431):   1%|          | 8/1563 [00:23<54:46,  2.11s/it]
Training 1/1 epoch (loss 2.4155):   1%|          | 8/1563 [00:24<54:46,  2.11s/it]
Training 1/1 epoch (loss 2.4155):   1%|          | 9/1563 [00:24<49:39,  1.92s/it]
Training 1/1 epoch (loss 2.3474):   1%|          | 9/1563 [00:26<49:39,  1.92s/it]
Training 1/1 epoch (loss 2.3474):   1%|          | 10/1563 [00:26<50:35,  1.95s/it]
Training 1/1 epoch (loss 2.2893):   1%|          | 10/1563 [00:27<50:35,  1.95s/it]
Training 1/1 epoch (loss 2.2893):   1%|          | 11/1563 [00:27<41:44,  1.61s/it]
Training 1/1 epoch (loss 2.3665):   1%|          | 11/1563 [00:29<41:44,  1.61s/it]
Training 1/1 epoch (loss 2.3665):   1%|          | 12/1563 [00:29<44:20,  1.72s/it]
Training 1/1 epoch (loss 2.4028):   1%|          | 12/1563 [00:30<44:20,  1.72s/it]
Training 1/1 epoch (loss 2.4028):   1%|          | 13/1563 [00:30<40:58,  1.59s/it]
Training 1/1 epoch (loss 2.2812):   1%|          | 13/1563 [00:32<40:58,  1.59s/it]
Training 1/1 epoch (loss 2.2812):   1%|          | 14/1563 [00:32<45:26,  1.76s/it]
Training 1/1 epoch (loss 2.2366):   1%|          | 14/1563 [00:34<45:26,  1.76s/it]
Training 1/1 epoch (loss 2.2366):   1%|          | 15/1563 [00:34<41:59,  1.63s/it]
Training 1/1 epoch (loss 2.3631):   1%|          | 15/1563 [00:35<41:59,  1.63s/it]
Training 1/1 epoch (loss 2.3631):   1%|          | 16/1563 [00:35<41:52,  1.62s/it]
Training 1/1 epoch (loss 2.4046):   1%|          | 16/1563 [00:37<41:52,  1.62s/it]
Training 1/1 epoch (loss 2.4046):   1%|          | 17/1563 [00:37<41:10,  1.60s/it]
Training 1/1 epoch (loss 2.2033):   1%|          | 17/1563 [00:39<41:10,  1.60s/it]
Training 1/1 epoch (loss 2.2033):   1%|          | 18/1563 [00:39<42:06,  1.64s/it]
Training 1/1 epoch (loss 2.1424):   1%|          | 18/1563 [00:40<42:06,  1.64s/it]
Training 1/1 epoch (loss 2.1424):   1%|          | 19/1563 [00:40<42:01,  1.63s/it]
Training 1/1 epoch (loss 2.1399):   1%|          | 19/1563 [00:42<42:01,  1.63s/it]
Training 1/1 epoch (loss 2.1399):   1%|▏         | 20/1563 [00:42<39:34,  1.54s/it]
Training 1/1 epoch (loss 2.2329):   1%|▏         | 20/1563 [00:44<39:34,  1.54s/it]
Training 1/1 epoch (loss 2.2329):   1%|▏         | 21/1563 [00:44<43:08,  1.68s/it]
Training 1/1 epoch (loss 2.2564):   1%|▏         | 21/1563 [00:45<43:08,  1.68s/it]
Training 1/1 epoch (loss 2.2564):   1%|▏         | 22/1563 [00:45<41:36,  1.62s/it]
Training 1/1 epoch (loss 2.2991):   1%|▏         | 22/1563 [00:46<41:36,  1.62s/it]
Training 1/1 epoch (loss 2.2991):   1%|▏         | 23/1563 [00:46<40:00,  1.56s/it]
Training 1/1 epoch (loss 2.2548):   1%|▏         | 23/1563 [00:49<40:00,  1.56s/it]
Training 1/1 epoch (loss 2.2548):   2%|▏         | 24/1563 [00:49<48:46,  1.90s/it]
Training 1/1 epoch (loss 2.2705):   2%|▏         | 24/1563 [00:50<48:46,  1.90s/it]
Training 1/1 epoch (loss 2.2705):   2%|▏         | 25/1563 [00:50<43:53,  1.71s/it]
Training 1/1 epoch (loss 2.2834):   2%|▏         | 25/1563 [00:52<43:53,  1.71s/it]
Training 1/1 epoch (loss 2.2834):   2%|▏         | 26/1563 [00:52<44:09,  1.72s/it]
Training 1/1 epoch (loss 2.2687):   2%|▏         | 26/1563 [00:54<44:09,  1.72s/it]
Training 1/1 epoch (loss 2.2687):   2%|▏         | 27/1563 [00:54<44:02,  1.72s/it]
Training 1/1 epoch (loss 2.3331):   2%|▏         | 27/1563 [00:56<44:02,  1.72s/it]
Training 1/1 epoch (loss 2.3331):   2%|▏         | 28/1563 [00:56<45:55,  1.80s/it]
Training 1/1 epoch (loss 2.1937):   2%|▏         | 28/1563 [00:57<45:55,  1.80s/it]
Training 1/1 epoch (loss 2.1937):   2%|▏         | 29/1563 [00:57<43:55,  1.72s/it]
Training 1/1 epoch (loss 2.2096):   2%|▏         | 29/1563 [00:59<43:55,  1.72s/it]
Training 1/1 epoch (loss 2.2096):   2%|▏         | 30/1563 [00:59<40:30,  1.59s/it]
Training 1/1 epoch (loss 2.2062):   2%|▏         | 30/1563 [01:00<40:30,  1.59s/it]
Training 1/1 epoch (loss 2.2062):   2%|▏         | 31/1563 [01:00<39:22,  1.54s/it]
Training 1/1 epoch (loss 2.1659):   2%|▏         | 31/1563 [01:02<39:22,  1.54s/it]
Training 1/1 epoch (loss 2.1659):   2%|▏         | 32/1563 [01:02<41:38,  1.63s/it]
Training 1/1 epoch (loss 2.1154):   2%|▏         | 32/1563 [01:03<41:38,  1.63s/it]
Training 1/1 epoch (loss 2.1154):   2%|▏         | 33/1563 [01:03<37:48,  1.48s/it]
Training 1/1 epoch (loss 2.1718):   2%|▏         | 33/1563 [01:05<37:48,  1.48s/it]
Training 1/1 epoch (loss 2.1718):   2%|▏         | 34/1563 [01:05<37:56,  1.49s/it]
Training 1/1 epoch (loss 2.2446):   2%|▏         | 34/1563 [01:06<37:56,  1.49s/it]
Training 1/1 epoch (loss 2.2446):   2%|▏         | 35/1563 [01:06<38:23,  1.51s/it]
Training 1/1 epoch (loss 2.1093):   2%|▏         | 35/1563 [01:08<38:23,  1.51s/it]
Training 1/1 epoch (loss 2.1093):   2%|▏         | 36/1563 [01:08<43:00,  1.69s/it]
Training 1/1 epoch (loss 2.1876):   2%|▏         | 36/1563 [01:10<43:00,  1.69s/it]
Training 1/1 epoch (loss 2.1876):   2%|▏         | 37/1563 [01:10<44:10,  1.74s/it]
Training 1/1 epoch (loss 2.1795):   2%|▏         | 37/1563 [01:12<44:10,  1.74s/it]
Training 1/1 epoch (loss 2.1795):   2%|▏         | 38/1563 [01:12<49:20,  1.94s/it]
Training 1/1 epoch (loss 2.3066):   2%|▏         | 38/1563 [01:14<49:20,  1.94s/it]
Training 1/1 epoch (loss 2.3066):   2%|▏         | 39/1563 [01:14<46:08,  1.82s/it]
Training 1/1 epoch (loss 2.1269):   2%|▏         | 39/1563 [01:17<46:08,  1.82s/it]
Training 1/1 epoch (loss 2.1269):   3%|▎         | 40/1563 [01:17<52:26,  2.07s/it]
Training 1/1 epoch (loss 2.1998):   3%|▎         | 40/1563 [01:18<52:26,  2.07s/it]
Training 1/1 epoch (loss 2.1998):   3%|▎         | 41/1563 [01:18<46:13,  1.82s/it]
Training 1/1 epoch (loss 2.1681):   3%|▎         | 41/1563 [01:20<46:13,  1.82s/it]
Training 1/1 epoch (loss 2.1681):   3%|▎         | 42/1563 [01:20<46:11,  1.82s/it]
Training 1/1 epoch (loss 2.0966):   3%|▎         | 42/1563 [01:22<46:11,  1.82s/it]
Training 1/1 epoch (loss 2.0966):   3%|▎         | 43/1563 [01:22<46:14,  1.83s/it]
Training 1/1 epoch (loss 2.1984):   3%|▎         | 43/1563 [01:23<46:14,  1.83s/it]
Training 1/1 epoch (loss 2.1984):   3%|▎         | 44/1563 [01:23<44:56,  1.78s/it]
Training 1/1 epoch (loss 2.1049):   3%|▎         | 44/1563 [01:25<44:56,  1.78s/it]
Training 1/1 epoch (loss 2.1049):   3%|▎         | 45/1563 [01:25<44:27,  1.76s/it]
Training 1/1 epoch (loss 1.9950):   3%|▎         | 45/1563 [01:27<44:27,  1.76s/it]
Training 1/1 epoch (loss 1.9950):   3%|▎         | 46/1563 [01:27<47:59,  1.90s/it]
Training 1/1 epoch (loss 2.1244):   3%|▎         | 46/1563 [01:28<47:59,  1.90s/it]
Training 1/1 epoch (loss 2.1244):   3%|▎         | 47/1563 [01:28<43:23,  1.72s/it]
Training 1/1 epoch (loss 1.9906):   3%|▎         | 47/1563 [01:30<43:23,  1.72s/it]
Training 1/1 epoch (loss 1.9906):   3%|▎         | 48/1563 [01:30<40:51,  1.62s/it]
Training 1/1 epoch (loss 2.1711):   3%|▎         | 48/1563 [01:32<40:51,  1.62s/it]
Training 1/1 epoch (loss 2.1711):   3%|▎         | 49/1563 [01:32<41:47,  1.66s/it]
Training 1/1 epoch (loss 2.1772):   3%|▎         | 49/1563 [01:33<41:47,  1.66s/it]
Training 1/1 epoch (loss 2.1772):   3%|▎         | 50/1563 [01:33<41:25,  1.64s/it]
Training 1/1 epoch (loss 1.9678):   3%|▎         | 50/1563 [01:35<41:25,  1.64s/it]
Training 1/1 epoch (loss 1.9678):   3%|▎         | 51/1563 [01:35<40:59,  1.63s/it]
Training 1/1 epoch (loss 2.1479):   3%|▎         | 51/1563 [01:36<40:59,  1.63s/it]
Training 1/1 epoch (loss 2.1479):   3%|▎         | 52/1563 [01:36<38:21,  1.52s/it]
Training 1/1 epoch (loss 2.1616):   3%|▎         | 52/1563 [01:38<38:21,  1.52s/it]
Training 1/1 epoch (loss 2.1616):   3%|▎         | 53/1563 [01:38<42:46,  1.70s/it]
Training 1/1 epoch (loss 2.0912):   3%|▎         | 53/1563 [01:41<42:46,  1.70s/it]
Training 1/1 epoch (loss 2.0912):   3%|▎         | 54/1563 [01:41<48:17,  1.92s/it]
Training 1/1 epoch (loss 2.1495):   3%|▎         | 54/1563 [01:43<48:17,  1.92s/it]
Training 1/1 epoch (loss 2.1495):   4%|▎         | 55/1563 [01:43<48:27,  1.93s/it]
Training 1/1 epoch (loss 2.0939):   4%|▎         | 55/1563 [01:45<48:27,  1.93s/it]
Training 1/1 epoch (loss 2.0939):   4%|▎         | 56/1563 [01:45<50:17,  2.00s/it]
Training 1/1 epoch (loss 2.0501):   4%|▎         | 56/1563 [01:46<50:17,  2.00s/it]
Training 1/1 epoch (loss 2.0501):   4%|▎         | 57/1563 [01:46<45:48,  1.82s/it]
Training 1/1 epoch (loss 2.0870):   4%|▎         | 57/1563 [01:49<45:48,  1.82s/it]
Training 1/1 epoch (loss 2.0870):   4%|▎         | 58/1563 [01:49<50:07,  2.00s/it]
Training 1/1 epoch (loss 2.0160):   4%|▎         | 58/1563 [01:50<50:07,  2.00s/it]
Training 1/1 epoch (loss 2.0160):   4%|▍         | 59/1563 [01:50<44:46,  1.79s/it]
Training 1/1 epoch (loss 1.9800):   4%|▍         | 59/1563 [01:52<44:46,  1.79s/it]
Training 1/1 epoch (loss 1.9800):   4%|▍         | 60/1563 [01:52<45:59,  1.84s/it]
Training 1/1 epoch (loss 2.0397):   4%|▍         | 60/1563 [01:53<45:59,  1.84s/it]
Training 1/1 epoch (loss 2.0397):   4%|▍         | 61/1563 [01:53<43:57,  1.76s/it]
Training 1/1 epoch (loss 1.9929):   4%|▍         | 61/1563 [01:56<43:57,  1.76s/it]
Training 1/1 epoch (loss 1.9929):   4%|▍         | 62/1563 [01:56<48:37,  1.94s/it]
Training 1/1 epoch (loss 2.0936):   4%|▍         | 62/1563 [01:58<48:37,  1.94s/it]
Training 1/1 epoch (loss 2.0936):   4%|▍         | 63/1563 [01:58<49:07,  1.96s/it]
Training 1/1 epoch (loss 2.0195):   4%|▍         | 63/1563 [01:59<49:07,  1.96s/it]
Training 1/1 epoch (loss 2.0195):   4%|▍         | 64/1563 [01:59<47:20,  1.90s/it]
Training 1/1 epoch (loss 2.1012):   4%|▍         | 64/1563 [02:02<47:20,  1.90s/it]
Training 1/1 epoch (loss 2.1012):   4%|▍         | 65/1563 [02:02<49:14,  1.97s/it]
Training 1/1 epoch (loss 1.9661):   4%|▍         | 65/1563 [02:04<49:14,  1.97s/it]
Training 1/1 epoch (loss 1.9661):   4%|▍         | 66/1563 [02:04<51:33,  2.07s/it]
Training 1/1 epoch (loss 1.9273):   4%|▍         | 66/1563 [02:05<51:33,  2.07s/it]
Training 1/1 epoch (loss 1.9273):   4%|▍         | 67/1563 [02:05<45:28,  1.82s/it]
Training 1/1 epoch (loss 2.0294):   4%|▍         | 67/1563 [02:06<45:28,  1.82s/it]
Training 1/1 epoch (loss 2.0294):   4%|▍         | 68/1563 [02:06<40:38,  1.63s/it]
Training 1/1 epoch (loss 2.0362):   4%|▍         | 68/1563 [02:09<40:38,  1.63s/it]
Training 1/1 epoch (loss 2.0362):   4%|▍         | 69/1563 [02:09<46:34,  1.87s/it]
Training 1/1 epoch (loss 2.0102):   4%|▍         | 69/1563 [02:10<46:34,  1.87s/it]
Training 1/1 epoch (loss 2.0102):   4%|▍         | 70/1563 [02:10<41:14,  1.66s/it]
Training 1/1 epoch (loss 2.0156):   4%|▍         | 70/1563 [02:12<41:14,  1.66s/it]
Training 1/1 epoch (loss 2.0156):   5%|▍         | 71/1563 [02:12<44:37,  1.79s/it]
Training 1/1 epoch (loss 2.1738):   5%|▍         | 71/1563 [02:14<44:37,  1.79s/it]
Training 1/1 epoch (loss 2.1738):   5%|▍         | 72/1563 [02:14<46:44,  1.88s/it]
Training 1/1 epoch (loss 2.0173):   5%|▍         | 72/1563 [02:16<46:44,  1.88s/it]
Training 1/1 epoch (loss 2.0173):   5%|▍         | 73/1563 [02:16<47:00,  1.89s/it]
Training 1/1 epoch (loss 2.1230):   5%|▍         | 73/1563 [02:17<47:00,  1.89s/it]
Training 1/1 epoch (loss 2.1230):   5%|▍         | 74/1563 [02:17<42:39,  1.72s/it]
Training 1/1 epoch (loss 1.9717):   5%|▍         | 74/1563 [02:19<42:39,  1.72s/it]
Training 1/1 epoch (loss 1.9717):   5%|▍         | 75/1563 [02:19<41:13,  1.66s/it]
Training 1/1 epoch (loss 1.9507):   5%|▍         | 75/1563 [02:20<41:13,  1.66s/it]
Training 1/1 epoch (loss 1.9507):   5%|▍         | 76/1563 [02:20<39:35,  1.60s/it]
Training 1/1 epoch (loss 1.8584):   5%|▍         | 76/1563 [02:23<39:35,  1.60s/it]
Training 1/1 epoch (loss 1.8584):   5%|▍         | 77/1563 [02:23<43:34,  1.76s/it]
Training 1/1 epoch (loss 1.9591):   5%|▍         | 77/1563 [02:24<43:34,  1.76s/it]
Training 1/1 epoch (loss 1.9591):   5%|▍         | 78/1563 [02:24<39:59,  1.62s/it]
Training 1/1 epoch (loss 2.1517):   5%|▍         | 78/1563 [02:26<39:59,  1.62s/it]
Training 1/1 epoch (loss 2.1517):   5%|▌         | 79/1563 [02:26<41:08,  1.66s/it]
Training 1/1 epoch (loss 2.0471):   5%|▌         | 79/1563 [02:28<41:08,  1.66s/it]
Training 1/1 epoch (loss 2.0471):   5%|▌         | 80/1563 [02:28<43:14,  1.75s/it]
Training 1/1 epoch (loss 2.0087):   5%|▌         | 80/1563 [02:30<43:14,  1.75s/it]
Training 1/1 epoch (loss 2.0087):   5%|▌         | 81/1563 [02:30<45:12,  1.83s/it]
Training 1/1 epoch (loss 2.0137):   5%|▌         | 81/1563 [02:32<45:12,  1.83s/it]
Training 1/1 epoch (loss 2.0137):   5%|▌         | 82/1563 [02:32<47:50,  1.94s/it]
Training 1/1 epoch (loss 1.9500):   5%|▌         | 82/1563 [02:34<47:50,  1.94s/it]
Training 1/1 epoch (loss 1.9500):   5%|▌         | 83/1563 [02:34<48:00,  1.95s/it]
Training 1/1 epoch (loss 1.9617):   5%|▌         | 83/1563 [02:35<48:00,  1.95s/it]
Training 1/1 epoch (loss 1.9617):   5%|▌         | 84/1563 [02:35<42:45,  1.73s/it]
Training 1/1 epoch (loss 1.8991):   5%|▌         | 84/1563 [02:37<42:45,  1.73s/it]
Training 1/1 epoch (loss 1.8991):   5%|▌         | 85/1563 [02:37<44:35,  1.81s/it]
Training 1/1 epoch (loss 1.9665):   5%|▌         | 85/1563 [02:38<44:35,  1.81s/it]
Training 1/1 epoch (loss 1.9665):   6%|▌         | 86/1563 [02:38<42:23,  1.72s/it]
Training 1/1 epoch (loss 1.9147):   6%|▌         | 86/1563 [02:40<42:23,  1.72s/it]
Training 1/1 epoch (loss 1.9147):   6%|▌         | 87/1563 [02:40<44:05,  1.79s/it]
Training 1/1 epoch (loss 1.8970):   6%|▌         | 87/1563 [02:43<44:05,  1.79s/it]
Training 1/1 epoch (loss 1.8970):   6%|▌         | 88/1563 [02:43<47:16,  1.92s/it]
Training 1/1 epoch (loss 1.9195):   6%|▌         | 88/1563 [02:45<47:16,  1.92s/it]
Training 1/1 epoch (loss 1.9195):   6%|▌         | 89/1563 [02:45<49:09,  2.00s/it]
Training 1/1 epoch (loss 1.8589):   6%|▌         | 89/1563 [02:47<49:09,  2.00s/it]
Training 1/1 epoch (loss 1.8589):   6%|▌         | 90/1563 [02:47<52:03,  2.12s/it]
Training 1/1 epoch (loss 1.9217):   6%|▌         | 90/1563 [02:50<52:03,  2.12s/it]
Training 1/1 epoch (loss 1.9217):   6%|▌         | 91/1563 [02:50<54:12,  2.21s/it]
Training 1/1 epoch (loss 1.8956):   6%|▌         | 91/1563 [02:51<54:12,  2.21s/it]
Training 1/1 epoch (loss 1.8956):   6%|▌         | 92/1563 [02:51<49:53,  2.04s/it]
Training 1/1 epoch (loss 2.0171):   6%|▌         | 92/1563 [02:53<49:53,  2.04s/it]
Training 1/1 epoch (loss 2.0171):   6%|▌         | 93/1563 [02:53<51:23,  2.10s/it]
Training 1/1 epoch (loss 1.9143):   6%|▌         | 93/1563 [02:55<51:23,  2.10s/it]
Training 1/1 epoch (loss 1.9143):   6%|▌         | 94/1563 [02:55<48:40,  1.99s/it]
Training 1/1 epoch (loss 1.7554):   6%|▌         | 94/1563 [02:56<48:40,  1.99s/it]
Training 1/1 epoch (loss 1.7554):   6%|▌         | 95/1563 [02:56<43:25,  1.77s/it]
Training 1/1 epoch (loss 1.9656):   6%|▌         | 95/1563 [02:59<43:25,  1.77s/it]
Training 1/1 epoch (loss 1.9656):   6%|▌         | 96/1563 [02:59<49:26,  2.02s/it]
Training 1/1 epoch (loss 1.8814):   6%|▌         | 96/1563 [03:02<49:26,  2.02s/it]
Training 1/1 epoch (loss 1.8814):   6%|▌         | 97/1563 [03:02<52:46,  2.16s/it]
Training 1/1 epoch (loss 2.0150):   6%|▌         | 97/1563 [03:03<52:46,  2.16s/it]
Training 1/1 epoch (loss 2.0150):   6%|▋         | 98/1563 [03:03<50:48,  2.08s/it]
Training 1/1 epoch (loss 1.9525):   6%|▋         | 98/1563 [03:05<50:48,  2.08s/it]
Training 1/1 epoch (loss 1.9525):   6%|▋         | 99/1563 [03:05<48:16,  1.98s/it]
Training 1/1 epoch (loss 1.9026):   6%|▋         | 99/1563 [03:07<48:16,  1.98s/it]
Training 1/1 epoch (loss 1.9026):   6%|▋         | 100/1563 [03:07<43:44,  1.79s/it]
Training 1/1 epoch (loss 1.8583):   6%|▋         | 100/1563 [03:09<43:44,  1.79s/it]
Training 1/1 epoch (loss 1.8583):   6%|▋         | 101/1563 [03:09<48:26,  1.99s/it]
Training 1/1 epoch (loss 2.0079):   6%|▋         | 101/1563 [03:11<48:26,  1.99s/it]
Training 1/1 epoch (loss 2.0079):   7%|▋         | 102/1563 [03:11<50:57,  2.09s/it]
Training 1/1 epoch (loss 1.8004):   7%|▋         | 102/1563 [03:13<50:57,  2.09s/it]
Training 1/1 epoch (loss 1.8004):   7%|▋         | 103/1563 [03:13<45:17,  1.86s/it]
Training 1/1 epoch (loss 2.0473):   7%|▋         | 103/1563 [03:14<45:17,  1.86s/it]
Training 1/1 epoch (loss 2.0473):   7%|▋         | 104/1563 [03:14<42:48,  1.76s/it]
Training 1/1 epoch (loss 1.9769):   7%|▋         | 104/1563 [03:17<42:48,  1.76s/it]
Training 1/1 epoch (loss 1.9769):   7%|▋         | 105/1563 [03:17<47:42,  1.96s/it]
Training 1/1 epoch (loss 1.9292):   7%|▋         | 105/1563 [03:18<47:42,  1.96s/it]
Training 1/1 epoch (loss 1.9292):   7%|▋         | 106/1563 [03:18<44:45,  1.84s/it]
Training 1/1 epoch (loss 1.9129):   7%|▋         | 106/1563 [03:20<44:45,  1.84s/it]
Training 1/1 epoch (loss 1.9129):   7%|▋         | 107/1563 [03:20<45:37,  1.88s/it]
Training 1/1 epoch (loss 1.8421):   7%|▋         | 107/1563 [03:22<45:37,  1.88s/it]
Training 1/1 epoch (loss 1.8421):   7%|▋         | 108/1563 [03:22<45:57,  1.89s/it]
Training 1/1 epoch (loss 1.9574):   7%|▋         | 108/1563 [03:24<45:57,  1.89s/it]
Training 1/1 epoch (loss 1.9574):   7%|▋         | 109/1563 [03:24<47:45,  1.97s/it]
Training 1/1 epoch (loss 1.8804):   7%|▋         | 109/1563 [03:25<47:45,  1.97s/it]
Training 1/1 epoch (loss 1.8804):   7%|▋         | 110/1563 [03:25<42:03,  1.74s/it]
Training 1/1 epoch (loss 1.7685):   7%|▋         | 110/1563 [03:26<42:03,  1.74s/it]
Training 1/1 epoch (loss 1.7685):   7%|▋         | 111/1563 [03:26<35:47,  1.48s/it]
Training 1/1 epoch (loss 1.9475):   7%|▋         | 111/1563 [03:28<35:47,  1.48s/it]
Training 1/1 epoch (loss 1.9475):   7%|▋         | 112/1563 [03:28<36:57,  1.53s/it]
Training 1/1 epoch (loss 1.8840):   7%|▋         | 112/1563 [03:29<36:57,  1.53s/it]
Training 1/1 epoch (loss 1.8840):   7%|▋         | 113/1563 [03:29<36:46,  1.52s/it]
Training 1/1 epoch (loss 1.8166):   7%|▋         | 113/1563 [03:32<36:46,  1.52s/it]
Training 1/1 epoch (loss 1.8166):   7%|▋         | 114/1563 [03:32<42:57,  1.78s/it]
Training 1/1 epoch (loss 1.9350):   7%|▋         | 114/1563 [03:34<42:57,  1.78s/it]
Training 1/1 epoch (loss 1.9350):   7%|▋         | 115/1563 [03:34<47:55,  1.99s/it]
Training 1/1 epoch (loss 1.9494):   7%|▋         | 115/1563 [03:36<47:55,  1.99s/it]
Training 1/1 epoch (loss 1.9494):   7%|▋         | 116/1563 [03:36<45:03,  1.87s/it]
Training 1/1 epoch (loss 1.8735):   7%|▋         | 116/1563 [03:37<45:03,  1.87s/it]
Training 1/1 epoch (loss 1.8735):   7%|▋         | 117/1563 [03:37<41:03,  1.70s/it]
Training 1/1 epoch (loss 1.8653):   7%|▋         | 117/1563 [03:39<41:03,  1.70s/it]
Training 1/1 epoch (loss 1.8653):   8%|▊         | 118/1563 [03:39<44:41,  1.86s/it]
Training 1/1 epoch (loss 1.8947):   8%|▊         | 118/1563 [03:41<44:41,  1.86s/it]
Training 1/1 epoch (loss 1.8947):   8%|▊         | 119/1563 [03:41<42:12,  1.75s/it]
Training 1/1 epoch (loss 2.0482):   8%|▊         | 119/1563 [03:42<42:12,  1.75s/it]
Training 1/1 epoch (loss 2.0482):   8%|▊         | 120/1563 [03:42<39:17,  1.63s/it]
Training 1/1 epoch (loss 1.7945):   8%|▊         | 120/1563 [03:44<39:17,  1.63s/it]
Training 1/1 epoch (loss 1.7945):   8%|▊         | 121/1563 [03:44<37:23,  1.56s/it]
Training 1/1 epoch (loss 1.7152):   8%|▊         | 121/1563 [03:46<37:23,  1.56s/it]
Training 1/1 epoch (loss 1.7152):   8%|▊         | 122/1563 [03:46<42:12,  1.76s/it]
Training 1/1 epoch (loss 1.8369):   8%|▊         | 122/1563 [03:48<42:12,  1.76s/it]
Training 1/1 epoch (loss 1.8369):   8%|▊         | 123/1563 [03:48<43:26,  1.81s/it]
Training 1/1 epoch (loss 1.7447):   8%|▊         | 123/1563 [03:50<43:26,  1.81s/it]
Training 1/1 epoch (loss 1.7447):   8%|▊         | 124/1563 [03:50<45:16,  1.89s/it]
Training 1/1 epoch (loss 1.9115):   8%|▊         | 124/1563 [03:52<45:16,  1.89s/it]
Training 1/1 epoch (loss 1.9115):   8%|▊         | 125/1563 [03:52<43:32,  1.82s/it]
Training 1/1 epoch (loss 1.9317):   8%|▊         | 125/1563 [03:54<43:32,  1.82s/it]
Training 1/1 epoch (loss 1.9317):   8%|▊         | 126/1563 [03:54<46:35,  1.95s/it]
Training 1/1 epoch (loss 1.8143):   8%|▊         | 126/1563 [03:56<46:35,  1.95s/it]
Training 1/1 epoch (loss 1.8143):   8%|▊         | 127/1563 [03:56<47:58,  2.00s/it]
Training 1/1 epoch (loss 1.8070):   8%|▊         | 127/1563 [03:58<47:58,  2.00s/it]
Training 1/1 epoch (loss 1.8070):   8%|▊         | 128/1563 [03:58<50:03,  2.09s/it]
Training 1/1 epoch (loss 1.8499):   8%|▊         | 128/1563 [04:01<50:03,  2.09s/it]
Training 1/1 epoch (loss 1.8499):   8%|▊         | 129/1563 [04:01<52:35,  2.20s/it]
Training 1/1 epoch (loss 1.8461):   8%|▊         | 129/1563 [04:02<52:35,  2.20s/it]
Training 1/1 epoch (loss 1.8461):   8%|▊         | 130/1563 [04:02<48:38,  2.04s/it]
Training 1/1 epoch (loss 1.7575):   8%|▊         | 130/1563 [04:04<48:38,  2.04s/it]
Training 1/1 epoch (loss 1.7575):   8%|▊         | 131/1563 [04:04<46:45,  1.96s/it]
Training 1/1 epoch (loss 1.8470):   8%|▊         | 131/1563 [04:06<46:45,  1.96s/it]
Training 1/1 epoch (loss 1.8470):   8%|▊         | 132/1563 [04:06<44:47,  1.88s/it]
Training 1/1 epoch (loss 1.9133):   8%|▊         | 132/1563 [04:08<44:47,  1.88s/it]
Training 1/1 epoch (loss 1.9133):   9%|▊         | 133/1563 [04:08<46:27,  1.95s/it]
Training 1/1 epoch (loss 1.9355):   9%|▊         | 133/1563 [04:10<46:27,  1.95s/it]
Training 1/1 epoch (loss 1.9355):   9%|▊         | 134/1563 [04:10<45:07,  1.89s/it]
Training 1/1 epoch (loss 1.9590):   9%|▊         | 134/1563 [04:12<45:07,  1.89s/it]
Training 1/1 epoch (loss 1.9590):   9%|▊         | 135/1563 [04:12<48:42,  2.05s/it]
Training 1/1 epoch (loss 1.9844):   9%|▊         | 135/1563 [04:14<48:42,  2.05s/it]
Training 1/1 epoch (loss 1.9844):   9%|▊         | 136/1563 [04:14<47:05,  1.98s/it]
Training 1/1 epoch (loss 1.7893):   9%|▊         | 136/1563 [04:15<47:05,  1.98s/it]
Training 1/1 epoch (loss 1.7893):   9%|▉         | 137/1563 [04:15<44:05,  1.86s/it]
Training 1/1 epoch (loss 1.6645):   9%|▉         | 137/1563 [04:17<44:05,  1.86s/it]
Training 1/1 epoch (loss 1.6645):   9%|▉         | 138/1563 [04:17<42:40,  1.80s/it]
Training 1/1 epoch (loss 1.7027):   9%|▉         | 138/1563 [04:19<42:40,  1.80s/it]
Training 1/1 epoch (loss 1.7027):   9%|▉         | 139/1563 [04:19<40:44,  1.72s/it]
Training 1/1 epoch (loss 1.7943):   9%|▉         | 139/1563 [04:20<40:44,  1.72s/it]
Training 1/1 epoch (loss 1.7943):   9%|▉         | 140/1563 [04:20<39:05,  1.65s/it]
Training 1/1 epoch (loss 1.7829):   9%|▉         | 140/1563 [04:23<39:05,  1.65s/it]
Training 1/1 epoch (loss 1.7829):   9%|▉         | 141/1563 [04:23<44:57,  1.90s/it]
Training 1/1 epoch (loss 1.8433):   9%|▉         | 141/1563 [04:24<44:57,  1.90s/it]
Training 1/1 epoch (loss 1.8433):   9%|▉         | 142/1563 [04:24<43:17,  1.83s/it]
Training 1/1 epoch (loss 1.8560):   9%|▉         | 142/1563 [04:26<43:17,  1.83s/it]
Training 1/1 epoch (loss 1.8560):   9%|▉         | 143/1563 [04:26<40:07,  1.70s/it]
Training 1/1 epoch (loss 1.7946):   9%|▉         | 143/1563 [04:28<40:07,  1.70s/it]
Training 1/1 epoch (loss 1.7946):   9%|▉         | 144/1563 [04:28<42:10,  1.78s/it]
Training 1/1 epoch (loss 1.7611):   9%|▉         | 144/1563 [04:30<42:10,  1.78s/it]
Training 1/1 epoch (loss 1.7611):   9%|▉         | 145/1563 [04:30<46:34,  1.97s/it]
Training 1/1 epoch (loss 1.7582):   9%|▉         | 145/1563 [04:32<46:34,  1.97s/it]
Training 1/1 epoch (loss 1.7582):   9%|▉         | 146/1563 [04:32<48:53,  2.07s/it]
Training 1/1 epoch (loss 1.7561):   9%|▉         | 146/1563 [04:34<48:53,  2.07s/it]
Training 1/1 epoch (loss 1.7561):   9%|▉         | 147/1563 [04:34<45:34,  1.93s/it]
Training 1/1 epoch (loss 1.8358):   9%|▉         | 147/1563 [04:36<45:34,  1.93s/it]
Training 1/1 epoch (loss 1.8358):   9%|▉         | 148/1563 [04:36<44:25,  1.88s/it]
Training 1/1 epoch (loss 1.7387):   9%|▉         | 148/1563 [04:38<44:25,  1.88s/it]
Training 1/1 epoch (loss 1.7387):  10%|▉         | 149/1563 [04:38<45:28,  1.93s/it]
Training 1/1 epoch (loss 1.7654):  10%|▉         | 149/1563 [04:39<45:28,  1.93s/it]
Training 1/1 epoch (loss 1.7654):  10%|▉         | 150/1563 [04:39<41:15,  1.75s/it]
Training 1/1 epoch (loss 1.7441):  10%|▉         | 150/1563 [04:41<41:15,  1.75s/it]
Training 1/1 epoch (loss 1.7441):  10%|▉         | 151/1563 [04:41<40:23,  1.72s/it]
Training 1/1 epoch (loss 1.8815):  10%|▉         | 151/1563 [04:42<40:23,  1.72s/it]
Training 1/1 epoch (loss 1.8815):  10%|▉         | 152/1563 [04:42<40:14,  1.71s/it]
Training 1/1 epoch (loss 1.7317):  10%|▉         | 152/1563 [04:43<40:14,  1.71s/it]
Training 1/1 epoch (loss 1.7317):  10%|▉         | 153/1563 [04:43<34:14,  1.46s/it]
Training 1/1 epoch (loss 1.7225):  10%|▉         | 153/1563 [04:45<34:14,  1.46s/it]
Training 1/1 epoch (loss 1.7225):  10%|▉         | 154/1563 [04:45<32:05,  1.37s/it]
Training 1/1 epoch (loss 1.7144):  10%|▉         | 154/1563 [04:47<32:05,  1.37s/it]
Training 1/1 epoch (loss 1.7144):  10%|▉         | 155/1563 [04:47<38:38,  1.65s/it]
Training 1/1 epoch (loss 1.8040):  10%|▉         | 155/1563 [04:49<38:38,  1.65s/it]
Training 1/1 epoch (loss 1.8040):  10%|▉         | 156/1563 [04:49<43:59,  1.88s/it]
Training 1/1 epoch (loss 1.6840):  10%|▉         | 156/1563 [04:51<43:59,  1.88s/it]
Training 1/1 epoch (loss 1.6840):  10%|█         | 157/1563 [04:51<42:51,  1.83s/it]
Training 1/1 epoch (loss 1.7668):  10%|█         | 157/1563 [04:53<42:51,  1.83s/it]
Training 1/1 epoch (loss 1.7668):  10%|█         | 158/1563 [04:53<46:56,  2.00s/it]
Training 1/1 epoch (loss 1.7547):  10%|█         | 158/1563 [04:55<46:56,  2.00s/it]
Training 1/1 epoch (loss 1.7547):  10%|█         | 159/1563 [04:55<43:38,  1.87s/it]
Training 1/1 epoch (loss 1.6929):  10%|█         | 159/1563 [04:57<43:38,  1.87s/it]
Training 1/1 epoch (loss 1.6929):  10%|█         | 160/1563 [04:57<46:20,  1.98s/it]
Training 1/1 epoch (loss 1.8476):  10%|█         | 160/1563 [04:59<46:20,  1.98s/it]
Training 1/1 epoch (loss 1.8476):  10%|█         | 161/1563 [04:59<47:40,  2.04s/it]
Training 1/1 epoch (loss 1.8469):  10%|█         | 161/1563 [05:01<47:40,  2.04s/it]
Training 1/1 epoch (loss 1.8469):  10%|█         | 162/1563 [05:01<46:51,  2.01s/it]
Training 1/1 epoch (loss 1.7283):  10%|█         | 162/1563 [05:03<46:51,  2.01s/it]
Training 1/1 epoch (loss 1.7283):  10%|█         | 163/1563 [05:03<45:28,  1.95s/it]
Training 1/1 epoch (loss 1.6780):  10%|█         | 163/1563 [05:06<45:28,  1.95s/it]
Training 1/1 epoch (loss 1.6780):  10%|█         | 164/1563 [05:06<49:17,  2.11s/it]
Training 1/1 epoch (loss 1.8622):  10%|█         | 164/1563 [05:08<49:17,  2.11s/it]
Training 1/1 epoch (loss 1.8622):  11%|█         | 165/1563 [05:08<48:14,  2.07s/it]
Training 1/1 epoch (loss 1.8283):  11%|█         | 165/1563 [05:10<48:14,  2.07s/it]
Training 1/1 epoch (loss 1.8283):  11%|█         | 166/1563 [05:10<50:55,  2.19s/it]
Training 1/1 epoch (loss 1.6787):  11%|█         | 166/1563 [05:12<50:55,  2.19s/it]
Training 1/1 epoch (loss 1.6787):  11%|█         | 167/1563 [05:12<46:23,  1.99s/it]
Training 1/1 epoch (loss 1.7641):  11%|█         | 167/1563 [05:14<46:23,  1.99s/it]
Training 1/1 epoch (loss 1.7641):  11%|█         | 168/1563 [05:14<47:15,  2.03s/it]
Training 1/1 epoch (loss 1.7884):  11%|█         | 168/1563 [05:15<47:15,  2.03s/it]
Training 1/1 epoch (loss 1.7884):  11%|█         | 169/1563 [05:15<42:50,  1.84s/it]
Training 1/1 epoch (loss 1.7782):  11%|█         | 169/1563 [05:17<42:50,  1.84s/it]
Training 1/1 epoch (loss 1.7782):  11%|█         | 170/1563 [05:17<42:48,  1.84s/it]
Training 1/1 epoch (loss 1.7272):  11%|█         | 170/1563 [05:18<42:48,  1.84s/it]
Training 1/1 epoch (loss 1.7272):  11%|█         | 171/1563 [05:18<36:49,  1.59s/it]
Training 1/1 epoch (loss 1.9029):  11%|█         | 171/1563 [05:20<36:49,  1.59s/it]
Training 1/1 epoch (loss 1.9029):  11%|█         | 172/1563 [05:20<41:12,  1.78s/it]
Training 1/1 epoch (loss 1.8577):  11%|█         | 172/1563 [05:22<41:12,  1.78s/it]
Training 1/1 epoch (loss 1.8577):  11%|█         | 173/1563 [05:22<39:21,  1.70s/it]
Training 1/1 epoch (loss 1.7636):  11%|█         | 173/1563 [05:24<39:21,  1.70s/it]
Training 1/1 epoch (loss 1.7636):  11%|█         | 174/1563 [05:24<42:30,  1.84s/it]
Training 1/1 epoch (loss 1.7478):  11%|█         | 174/1563 [05:25<42:30,  1.84s/it]
Training 1/1 epoch (loss 1.7478):  11%|█         | 175/1563 [05:25<39:29,  1.71s/it]
Training 1/1 epoch (loss 1.6861):  11%|█         | 175/1563 [05:27<39:29,  1.71s/it]
Training 1/1 epoch (loss 1.6861):  11%|█▏        | 176/1563 [05:27<39:28,  1.71s/it]
Training 1/1 epoch (loss 1.7404):  11%|█▏        | 176/1563 [05:29<39:28,  1.71s/it]
Training 1/1 epoch (loss 1.7404):  11%|█▏        | 177/1563 [05:29<40:09,  1.74s/it]
Training 1/1 epoch (loss 1.7273):  11%|█▏        | 177/1563 [05:30<40:09,  1.74s/it]
Training 1/1 epoch (loss 1.7273):  11%|█▏        | 178/1563 [05:30<38:10,  1.65s/it]
Training 1/1 epoch (loss 1.8297):  11%|█▏        | 178/1563 [05:32<38:10,  1.65s/it]
Training 1/1 epoch (loss 1.8297):  11%|█▏        | 179/1563 [05:32<38:54,  1.69s/it]
Training 1/1 epoch (loss 1.7636):  11%|█▏        | 179/1563 [05:34<38:54,  1.69s/it]
Training 1/1 epoch (loss 1.7636):  12%|█▏        | 180/1563 [05:34<38:57,  1.69s/it]
Training 1/1 epoch (loss 1.8000):  12%|█▏        | 180/1563 [05:35<38:57,  1.69s/it]
Training 1/1 epoch (loss 1.8000):  12%|█▏        | 181/1563 [05:35<34:08,  1.48s/it]
Training 1/1 epoch (loss 1.7658):  12%|█▏        | 181/1563 [05:36<34:08,  1.48s/it]
Training 1/1 epoch (loss 1.7658):  12%|█▏        | 182/1563 [05:36<36:13,  1.57s/it]
Training 1/1 epoch (loss 1.7116):  12%|█▏        | 182/1563 [05:38<36:13,  1.57s/it]
Training 1/1 epoch (loss 1.7116):  12%|█▏        | 183/1563 [05:38<37:47,  1.64s/it]
Training 1/1 epoch (loss 1.6300):  12%|█▏        | 183/1563 [05:40<37:47,  1.64s/it]
Training 1/1 epoch (loss 1.6300):  12%|█▏        | 184/1563 [05:40<37:22,  1.63s/it]
Training 1/1 epoch (loss 1.7182):  12%|█▏        | 184/1563 [05:41<37:22,  1.63s/it]
Training 1/1 epoch (loss 1.7182):  12%|█▏        | 185/1563 [05:41<34:39,  1.51s/it]
Training 1/1 epoch (loss 1.8698):  12%|█▏        | 185/1563 [05:43<34:39,  1.51s/it]
Training 1/1 epoch (loss 1.8698):  12%|█▏        | 186/1563 [05:43<35:35,  1.55s/it]
Training 1/1 epoch (loss 1.7162):  12%|█▏        | 186/1563 [05:44<35:35,  1.55s/it]
Training 1/1 epoch (loss 1.7162):  12%|█▏        | 187/1563 [05:44<34:18,  1.50s/it]
Training 1/1 epoch (loss 1.6832):  12%|█▏        | 187/1563 [05:45<34:18,  1.50s/it]
Training 1/1 epoch (loss 1.6832):  12%|█▏        | 188/1563 [05:45<33:26,  1.46s/it]
Training 1/1 epoch (loss 1.5885):  12%|█▏        | 188/1563 [05:47<33:26,  1.46s/it]
Training 1/1 epoch (loss 1.5885):  12%|█▏        | 189/1563 [05:47<31:54,  1.39s/it]
Training 1/1 epoch (loss 1.8497):  12%|█▏        | 189/1563 [05:48<31:54,  1.39s/it]
Training 1/1 epoch (loss 1.8497):  12%|█▏        | 190/1563 [05:48<31:01,  1.36s/it]
Training 1/1 epoch (loss 1.8298):  12%|█▏        | 190/1563 [05:49<31:01,  1.36s/it]
Training 1/1 epoch (loss 1.8298):  12%|█▏        | 191/1563 [05:49<29:54,  1.31s/it]
Training 1/1 epoch (loss 1.7962):  12%|█▏        | 191/1563 [05:51<29:54,  1.31s/it]
Training 1/1 epoch (loss 1.7962):  12%|█▏        | 192/1563 [05:51<32:12,  1.41s/it]
Training 1/1 epoch (loss 1.6356):  12%|█▏        | 192/1563 [05:52<32:12,  1.41s/it]
Training 1/1 epoch (loss 1.6356):  12%|█▏        | 193/1563 [05:52<33:11,  1.45s/it]
Training 1/1 epoch (loss 1.6862):  12%|█▏        | 193/1563 [05:54<33:11,  1.45s/it]
Training 1/1 epoch (loss 1.6862):  12%|█▏        | 194/1563 [05:54<35:18,  1.55s/it]
Training 1/1 epoch (loss 1.7115):  12%|█▏        | 194/1563 [05:55<35:18,  1.55s/it]
Training 1/1 epoch (loss 1.7115):  12%|█▏        | 195/1563 [05:55<34:04,  1.49s/it]
Training 1/1 epoch (loss 1.8669):  12%|█▏        | 195/1563 [05:57<34:04,  1.49s/it]
Training 1/1 epoch (loss 1.8669):  13%|█▎        | 196/1563 [05:57<31:01,  1.36s/it]
Training 1/1 epoch (loss 1.8014):  13%|█▎        | 196/1563 [05:59<31:01,  1.36s/it]
Training 1/1 epoch (loss 1.8014):  13%|█▎        | 197/1563 [05:59<35:50,  1.57s/it]
Training 1/1 epoch (loss 1.7082):  13%|█▎        | 197/1563 [06:00<35:50,  1.57s/it]
Training 1/1 epoch (loss 1.7082):  13%|█▎        | 198/1563 [06:00<34:07,  1.50s/it]
Training 1/1 epoch (loss 1.6977):  13%|█▎        | 198/1563 [06:02<34:07,  1.50s/it]
Training 1/1 epoch (loss 1.6977):  13%|█▎        | 199/1563 [06:02<37:12,  1.64s/it]
Training 1/1 epoch (loss 1.7097):  13%|█▎        | 199/1563 [06:03<37:12,  1.64s/it]
Training 1/1 epoch (loss 1.7097):  13%|█▎        | 200/1563 [06:03<35:41,  1.57s/it]
Training 1/1 epoch (loss 1.7751):  13%|█▎        | 200/1563 [06:06<35:41,  1.57s/it]
Training 1/1 epoch (loss 1.7751):  13%|█▎        | 201/1563 [06:06<41:27,  1.83s/it]
Training 1/1 epoch (loss 1.6647):  13%|█▎        | 201/1563 [06:07<41:27,  1.83s/it]
Training 1/1 epoch (loss 1.6647):  13%|█▎        | 202/1563 [06:07<38:50,  1.71s/it]
Training 1/1 epoch (loss 1.8326):  13%|█▎        | 202/1563 [06:09<38:50,  1.71s/it]
Training 1/1 epoch (loss 1.8326):  13%|█▎        | 203/1563 [06:09<39:04,  1.72s/it]
Training 1/1 epoch (loss 1.6931):  13%|█▎        | 203/1563 [06:10<39:04,  1.72s/it]
Training 1/1 epoch (loss 1.6931):  13%|█▎        | 204/1563 [06:10<36:08,  1.60s/it]
Training 1/1 epoch (loss 1.6116):  13%|█▎        | 204/1563 [06:12<36:08,  1.60s/it]
Training 1/1 epoch (loss 1.6116):  13%|█▎        | 205/1563 [06:12<34:24,  1.52s/it]
Training 1/1 epoch (loss 1.7964):  13%|█▎        | 205/1563 [06:13<34:24,  1.52s/it]
Training 1/1 epoch (loss 1.7964):  13%|█▎        | 206/1563 [06:13<32:02,  1.42s/it]
Training 1/1 epoch (loss 1.7892):  13%|█▎        | 206/1563 [06:14<32:02,  1.42s/it]
Training 1/1 epoch (loss 1.7892):  13%|█▎        | 207/1563 [06:14<33:48,  1.50s/it]
Training 1/1 epoch (loss 1.7373):  13%|█▎        | 207/1563 [06:17<33:48,  1.50s/it]
Training 1/1 epoch (loss 1.7373):  13%|█▎        | 208/1563 [06:17<40:01,  1.77s/it]
Training 1/1 epoch (loss 1.7641):  13%|█▎        | 208/1563 [06:19<40:01,  1.77s/it]
Training 1/1 epoch (loss 1.7641):  13%|█▎        | 209/1563 [06:19<42:55,  1.90s/it]
Training 1/1 epoch (loss 1.7680):  13%|█▎        | 209/1563 [06:20<42:55,  1.90s/it]
Training 1/1 epoch (loss 1.7680):  13%|█▎        | 210/1563 [06:20<36:13,  1.61s/it]
Training 1/1 epoch (loss 1.6811):  13%|█▎        | 210/1563 [06:22<36:13,  1.61s/it]
Training 1/1 epoch (loss 1.6811):  13%|█▎        | 211/1563 [06:22<41:39,  1.85s/it]
Training 1/1 epoch (loss 1.7600):  13%|█▎        | 211/1563 [06:24<41:39,  1.85s/it]
Training 1/1 epoch (loss 1.7600):  14%|█▎        | 212/1563 [06:24<41:01,  1.82s/it]
Training 1/1 epoch (loss 1.6264):  14%|█▎        | 212/1563 [06:26<41:01,  1.82s/it]
Training 1/1 epoch (loss 1.6264):  14%|█▎        | 213/1563 [06:26<42:43,  1.90s/it]
Training 1/1 epoch (loss 1.9319):  14%|█▎        | 213/1563 [06:28<42:43,  1.90s/it]
Training 1/1 epoch (loss 1.9319):  14%|█▎        | 214/1563 [06:28<44:33,  1.98s/it]
Training 1/1 epoch (loss 1.7971):  14%|█▎        | 214/1563 [06:30<44:33,  1.98s/it]
Training 1/1 epoch (loss 1.7971):  14%|█▍        | 215/1563 [06:30<44:48,  1.99s/it]
Training 1/1 epoch (loss 1.7330):  14%|█▍        | 215/1563 [06:32<44:48,  1.99s/it]
Training 1/1 epoch (loss 1.7330):  14%|█▍        | 216/1563 [06:32<43:13,  1.93s/it]
Training 1/1 epoch (loss 1.7113):  14%|█▍        | 216/1563 [06:35<43:13,  1.93s/it]
Training 1/1 epoch (loss 1.7113):  14%|█▍        | 217/1563 [06:35<46:49,  2.09s/it]
Training 1/1 epoch (loss 1.7789):  14%|█▍        | 217/1563 [06:36<46:49,  2.09s/it]
Training 1/1 epoch (loss 1.7789):  14%|█▍        | 218/1563 [06:36<44:31,  1.99s/it]
Training 1/1 epoch (loss 1.7758):  14%|█▍        | 218/1563 [06:38<44:31,  1.99s/it]
Training 1/1 epoch (loss 1.7758):  14%|█▍        | 219/1563 [06:38<44:23,  1.98s/it]
Training 1/1 epoch (loss 1.6428):  14%|█▍        | 219/1563 [06:41<44:23,  1.98s/it]
Training 1/1 epoch (loss 1.6428):  14%|█▍        | 220/1563 [06:41<47:31,  2.12s/it]
Training 1/1 epoch (loss 1.7332):  14%|█▍        | 220/1563 [06:43<47:31,  2.12s/it]
Training 1/1 epoch (loss 1.7332):  14%|█▍        | 221/1563 [06:43<46:48,  2.09s/it]
Training 1/1 epoch (loss 1.6468):  14%|█▍        | 221/1563 [06:44<46:48,  2.09s/it]
Training 1/1 epoch (loss 1.6468):  14%|█▍        | 222/1563 [06:44<41:18,  1.85s/it]
Training 1/1 epoch (loss 1.6322):  14%|█▍        | 222/1563 [06:45<41:18,  1.85s/it]
Training 1/1 epoch (loss 1.6322):  14%|█▍        | 223/1563 [06:45<37:00,  1.66s/it]
Training 1/1 epoch (loss 1.6769):  14%|█▍        | 223/1563 [06:48<37:00,  1.66s/it]
Training 1/1 epoch (loss 1.6769):  14%|█▍        | 224/1563 [06:48<43:44,  1.96s/it]
Training 1/1 epoch (loss 1.8278):  14%|█▍        | 224/1563 [06:49<43:44,  1.96s/it]
Training 1/1 epoch (loss 1.8278):  14%|█▍        | 225/1563 [06:49<40:04,  1.80s/it]
Training 1/1 epoch (loss 1.7969):  14%|█▍        | 225/1563 [06:51<40:04,  1.80s/it]
Training 1/1 epoch (loss 1.7969):  14%|█▍        | 226/1563 [06:51<36:17,  1.63s/it]
Training 1/1 epoch (loss 1.7547):  14%|█▍        | 226/1563 [06:53<36:17,  1.63s/it]
Training 1/1 epoch (loss 1.7547):  15%|█▍        | 227/1563 [06:53<40:35,  1.82s/it]
Training 1/1 epoch (loss 1.7723):  15%|█▍        | 227/1563 [06:54<40:35,  1.82s/it]
Training 1/1 epoch (loss 1.7723):  15%|█▍        | 228/1563 [06:54<38:12,  1.72s/it]
Training 1/1 epoch (loss 1.7627):  15%|█▍        | 228/1563 [06:56<38:12,  1.72s/it]
Training 1/1 epoch (loss 1.7627):  15%|█▍        | 229/1563 [06:56<38:37,  1.74s/it]
Training 1/1 epoch (loss 1.7549):  15%|█▍        | 229/1563 [06:58<38:37,  1.74s/it]
Training 1/1 epoch (loss 1.7549):  15%|█▍        | 230/1563 [06:58<38:37,  1.74s/it]
Training 1/1 epoch (loss 1.8026):  15%|█▍        | 230/1563 [07:00<38:37,  1.74s/it]
Training 1/1 epoch (loss 1.8026):  15%|█▍        | 231/1563 [07:00<40:43,  1.83s/it]
Training 1/1 epoch (loss 1.8208):  15%|█▍        | 231/1563 [07:01<40:43,  1.83s/it]
Training 1/1 epoch (loss 1.8208):  15%|█▍        | 232/1563 [07:01<38:31,  1.74s/it]
Training 1/1 epoch (loss 1.6776):  15%|█▍        | 232/1563 [07:03<38:31,  1.74s/it]
Training 1/1 epoch (loss 1.6776):  15%|█▍        | 233/1563 [07:03<39:02,  1.76s/it]
Training 1/1 epoch (loss 1.7802):  15%|█▍        | 233/1563 [07:05<39:02,  1.76s/it]
Training 1/1 epoch (loss 1.7802):  15%|█▍        | 234/1563 [07:05<38:09,  1.72s/it]
Training 1/1 epoch (loss 1.6333):  15%|█▍        | 234/1563 [07:06<38:09,  1.72s/it]
Training 1/1 epoch (loss 1.6333):  15%|█▌        | 235/1563 [07:06<36:54,  1.67s/it]
Training 1/1 epoch (loss 1.6779):  15%|█▌        | 235/1563 [07:07<36:54,  1.67s/it]
Training 1/1 epoch (loss 1.6779):  15%|█▌        | 236/1563 [07:07<31:17,  1.41s/it]
Training 1/1 epoch (loss 1.7376):  15%|█▌        | 236/1563 [07:09<31:17,  1.41s/it]
Training 1/1 epoch (loss 1.7376):  15%|█▌        | 237/1563 [07:09<34:41,  1.57s/it]
Training 1/1 epoch (loss 1.8180):  15%|█▌        | 237/1563 [07:11<34:41,  1.57s/it]
Training 1/1 epoch (loss 1.8180):  15%|█▌        | 238/1563 [07:11<35:19,  1.60s/it]
Training 1/1 epoch (loss 1.7077):  15%|█▌        | 238/1563 [07:13<35:19,  1.60s/it]
Training 1/1 epoch (loss 1.7077):  15%|█▌        | 239/1563 [07:13<35:39,  1.62s/it]
Training 1/1 epoch (loss 1.6017):  15%|█▌        | 239/1563 [07:14<35:39,  1.62s/it]
Training 1/1 epoch (loss 1.6017):  15%|█▌        | 240/1563 [07:14<36:57,  1.68s/it]
Training 1/1 epoch (loss 1.7150):  15%|█▌        | 240/1563 [07:16<36:57,  1.68s/it]
Training 1/1 epoch (loss 1.7150):  15%|█▌        | 241/1563 [07:16<35:59,  1.63s/it]
Training 1/1 epoch (loss 1.6571):  15%|█▌        | 241/1563 [07:18<35:59,  1.63s/it]
Training 1/1 epoch (loss 1.6571):  15%|█▌        | 242/1563 [07:18<40:19,  1.83s/it]
Training 1/1 epoch (loss 1.6129):  15%|█▌        | 242/1563 [07:20<40:19,  1.83s/it]
Training 1/1 epoch (loss 1.6129):  16%|█▌        | 243/1563 [07:20<40:03,  1.82s/it]
Training 1/1 epoch (loss 1.7117):  16%|█▌        | 243/1563 [07:21<40:03,  1.82s/it]
Training 1/1 epoch (loss 1.7117):  16%|█▌        | 244/1563 [07:21<35:53,  1.63s/it]
Training 1/1 epoch (loss 1.7429):  16%|█▌        | 244/1563 [07:23<35:53,  1.63s/it]
Training 1/1 epoch (loss 1.7429):  16%|█▌        | 245/1563 [07:23<33:56,  1.55s/it]
Training 1/1 epoch (loss 1.7957):  16%|█▌        | 245/1563 [07:25<33:56,  1.55s/it]
Training 1/1 epoch (loss 1.7957):  16%|█▌        | 246/1563 [07:25<37:14,  1.70s/it]
Training 1/1 epoch (loss 1.6957):  16%|█▌        | 246/1563 [07:26<37:14,  1.70s/it]
Training 1/1 epoch (loss 1.6957):  16%|█▌        | 247/1563 [07:26<37:24,  1.71s/it]
Training 1/1 epoch (loss 1.7224):  16%|█▌        | 247/1563 [07:28<37:24,  1.71s/it]
Training 1/1 epoch (loss 1.7224):  16%|█▌        | 248/1563 [07:28<34:58,  1.60s/it]
Training 1/1 epoch (loss 1.6863):  16%|█▌        | 248/1563 [07:29<34:58,  1.60s/it]
Training 1/1 epoch (loss 1.6863):  16%|█▌        | 249/1563 [07:29<32:37,  1.49s/it]
Training 1/1 epoch (loss 1.7770):  16%|█▌        | 249/1563 [07:31<32:37,  1.49s/it]
Training 1/1 epoch (loss 1.7770):  16%|█▌        | 250/1563 [07:31<37:52,  1.73s/it]
Training 1/1 epoch (loss 1.6383):  16%|█▌        | 250/1563 [07:32<37:52,  1.73s/it]
Training 1/1 epoch (loss 1.6383):  16%|█▌        | 251/1563 [07:32<33:30,  1.53s/it]
Training 1/1 epoch (loss 1.6724):  16%|█▌        | 251/1563 [07:35<33:30,  1.53s/it]
Training 1/1 epoch (loss 1.6724):  16%|█▌        | 252/1563 [07:35<39:23,  1.80s/it]
Training 1/1 epoch (loss 1.7567):  16%|█▌        | 252/1563 [07:36<39:23,  1.80s/it]
Training 1/1 epoch (loss 1.7567):  16%|█▌        | 253/1563 [07:36<35:16,  1.62s/it]
Training 1/1 epoch (loss 1.5907):  16%|█▌        | 253/1563 [07:38<35:16,  1.62s/it]
Training 1/1 epoch (loss 1.5907):  16%|█▋        | 254/1563 [07:38<41:07,  1.88s/it]
Training 1/1 epoch (loss 1.6865):  16%|█▋        | 254/1563 [07:40<41:07,  1.88s/it]
Training 1/1 epoch (loss 1.6865):  16%|█▋        | 255/1563 [07:40<36:40,  1.68s/it]
Training 1/1 epoch (loss 1.8102):  16%|█▋        | 255/1563 [07:42<36:40,  1.68s/it]
Training 1/1 epoch (loss 1.8102):  16%|█▋        | 256/1563 [07:42<39:23,  1.81s/it]
Training 1/1 epoch (loss 1.7987):  16%|█▋        | 256/1563 [07:43<39:23,  1.81s/it]
Training 1/1 epoch (loss 1.7987):  16%|█▋        | 257/1563 [07:43<36:35,  1.68s/it]
Training 1/1 epoch (loss 1.7387):  16%|█▋        | 257/1563 [07:45<36:35,  1.68s/it]
Training 1/1 epoch (loss 1.7387):  17%|█▋        | 258/1563 [07:45<37:56,  1.74s/it]
Training 1/1 epoch (loss 1.6953):  17%|█▋        | 258/1563 [07:47<37:56,  1.74s/it]
Training 1/1 epoch (loss 1.6953):  17%|█▋        | 259/1563 [07:47<37:32,  1.73s/it]
Training 1/1 epoch (loss 1.6877):  17%|█▋        | 259/1563 [07:48<37:32,  1.73s/it]
Training 1/1 epoch (loss 1.6877):  17%|█▋        | 260/1563 [07:48<37:44,  1.74s/it]
Training 1/1 epoch (loss 1.6698):  17%|█▋        | 260/1563 [07:51<37:44,  1.74s/it]
Training 1/1 epoch (loss 1.6698):  17%|█▋        | 261/1563 [07:51<40:29,  1.87s/it]
Training 1/1 epoch (loss 1.8029):  17%|█▋        | 261/1563 [07:52<40:29,  1.87s/it]
Training 1/1 epoch (loss 1.8029):  17%|█▋        | 262/1563 [07:52<38:30,  1.78s/it]
Training 1/1 epoch (loss 1.7915):  17%|█▋        | 262/1563 [07:54<38:30,  1.78s/it]
Training 1/1 epoch (loss 1.7915):  17%|█▋        | 263/1563 [07:54<40:01,  1.85s/it]
Training 1/1 epoch (loss 1.7505):  17%|█▋        | 263/1563 [07:56<40:01,  1.85s/it]
Training 1/1 epoch (loss 1.7505):  17%|█▋        | 264/1563 [07:56<38:43,  1.79s/it]
Training 1/1 epoch (loss 1.7101):  17%|█▋        | 264/1563 [07:57<38:43,  1.79s/it]
Training 1/1 epoch (loss 1.7101):  17%|█▋        | 265/1563 [07:57<37:14,  1.72s/it]
Training 1/1 epoch (loss 1.7094):  17%|█▋        | 265/1563 [07:59<37:14,  1.72s/it]
Training 1/1 epoch (loss 1.7094):  17%|█▋        | 266/1563 [07:59<34:29,  1.60s/it]
Training 1/1 epoch (loss 1.6681):  17%|█▋        | 266/1563 [08:00<34:29,  1.60s/it]
Training 1/1 epoch (loss 1.6681):  17%|█▋        | 267/1563 [08:00<29:35,  1.37s/it]
Training 1/1 epoch (loss 1.8272):  17%|█▋        | 267/1563 [08:01<29:35,  1.37s/it]
Training 1/1 epoch (loss 1.8272):  17%|█▋        | 268/1563 [08:01<31:09,  1.44s/it]
Training 1/1 epoch (loss 1.6378):  17%|█▋        | 268/1563 [08:03<31:09,  1.44s/it]
Training 1/1 epoch (loss 1.6378):  17%|█▋        | 269/1563 [08:03<32:38,  1.51s/it]
Training 1/1 epoch (loss 1.7698):  17%|█▋        | 269/1563 [08:04<32:38,  1.51s/it]
Training 1/1 epoch (loss 1.7698):  17%|█▋        | 270/1563 [08:04<31:29,  1.46s/it]
Training 1/1 epoch (loss 1.7017):  17%|█▋        | 270/1563 [08:05<31:29,  1.46s/it]
Training 1/1 epoch (loss 1.7017):  17%|█▋        | 271/1563 [08:05<29:58,  1.39s/it]
Training 1/1 epoch (loss 1.5852):  17%|█▋        | 271/1563 [08:08<29:58,  1.39s/it]
Training 1/1 epoch (loss 1.5852):  17%|█▋        | 272/1563 [08:08<38:38,  1.80s/it]
Training 1/1 epoch (loss 1.7884):  17%|█▋        | 272/1563 [08:10<38:38,  1.80s/it]
Training 1/1 epoch (loss 1.7884):  17%|█▋        | 273/1563 [08:10<42:12,  1.96s/it]
Training 1/1 epoch (loss 1.6836):  17%|█▋        | 273/1563 [08:13<42:12,  1.96s/it]
Training 1/1 epoch (loss 1.6836):  18%|█▊        | 274/1563 [08:13<44:14,  2.06s/it]
Training 1/1 epoch (loss 1.7281):  18%|█▊        | 274/1563 [08:15<44:14,  2.06s/it]
Training 1/1 epoch (loss 1.7281):  18%|█▊        | 275/1563 [08:15<42:57,  2.00s/it]
Training 1/1 epoch (loss 1.7658):  18%|█▊        | 275/1563 [08:16<42:57,  2.00s/it]
Training 1/1 epoch (loss 1.7658):  18%|█▊        | 276/1563 [08:16<37:38,  1.75s/it]
Training 1/1 epoch (loss 1.7969):  18%|█▊        | 276/1563 [08:18<37:38,  1.75s/it]
Training 1/1 epoch (loss 1.7969):  18%|█▊        | 277/1563 [08:18<39:18,  1.83s/it]
Training 1/1 epoch (loss 1.6916):  18%|█▊        | 277/1563 [08:19<39:18,  1.83s/it]
Training 1/1 epoch (loss 1.6916):  18%|█▊        | 278/1563 [08:19<37:26,  1.75s/it]
Training 1/1 epoch (loss 1.6850):  18%|█▊        | 278/1563 [08:20<37:26,  1.75s/it]
Training 1/1 epoch (loss 1.6850):  18%|█▊        | 279/1563 [08:20<33:16,  1.56s/it]
Training 1/1 epoch (loss 1.6971):  18%|█▊        | 279/1563 [08:23<33:16,  1.56s/it]
Training 1/1 epoch (loss 1.6971):  18%|█▊        | 280/1563 [08:23<38:00,  1.78s/it]
Training 1/1 epoch (loss 1.7646):  18%|█▊        | 280/1563 [08:24<38:00,  1.78s/it]
Training 1/1 epoch (loss 1.7646):  18%|█▊        | 281/1563 [08:24<34:34,  1.62s/it]
Training 1/1 epoch (loss 1.6598):  18%|█▊        | 281/1563 [08:26<34:34,  1.62s/it]
Training 1/1 epoch (loss 1.6598):  18%|█▊        | 282/1563 [08:26<36:14,  1.70s/it]
Training 1/1 epoch (loss 1.6963):  18%|█▊        | 282/1563 [08:28<36:14,  1.70s/it]
Training 1/1 epoch (loss 1.6963):  18%|█▊        | 283/1563 [08:28<38:42,  1.81s/it]
Training 1/1 epoch (loss 1.7348):  18%|█▊        | 283/1563 [08:30<38:42,  1.81s/it]
Training 1/1 epoch (loss 1.7348):  18%|█▊        | 284/1563 [08:30<39:07,  1.84s/it]
Training 1/1 epoch (loss 1.6330):  18%|█▊        | 284/1563 [08:32<39:07,  1.84s/it]
Training 1/1 epoch (loss 1.6330):  18%|█▊        | 285/1563 [08:32<40:55,  1.92s/it]
Training 1/1 epoch (loss 1.6543):  18%|█▊        | 285/1563 [08:34<40:55,  1.92s/it]
Training 1/1 epoch (loss 1.6543):  18%|█▊        | 286/1563 [08:34<42:38,  2.00s/it]
Training 1/1 epoch (loss 1.7924):  18%|█▊        | 286/1563 [08:35<42:38,  2.00s/it]
Training 1/1 epoch (loss 1.7924):  18%|█▊        | 287/1563 [08:35<37:22,  1.76s/it]
Training 1/1 epoch (loss 1.6799):  18%|█▊        | 287/1563 [08:38<37:22,  1.76s/it]
Training 1/1 epoch (loss 1.6799):  18%|█▊        | 288/1563 [08:38<40:23,  1.90s/it]
Training 1/1 epoch (loss 1.7346):  18%|█▊        | 288/1563 [08:39<40:23,  1.90s/it]
Training 1/1 epoch (loss 1.7346):  18%|█▊        | 289/1563 [08:39<40:17,  1.90s/it]
Training 1/1 epoch (loss 1.7106):  18%|█▊        | 289/1563 [08:42<40:17,  1.90s/it]
Training 1/1 epoch (loss 1.7106):  19%|█▊        | 290/1563 [08:42<43:29,  2.05s/it]
Training 1/1 epoch (loss 1.7178):  19%|█▊        | 290/1563 [08:43<43:29,  2.05s/it]
Training 1/1 epoch (loss 1.7178):  19%|█▊        | 291/1563 [08:43<38:45,  1.83s/it]
Training 1/1 epoch (loss 1.6727):  19%|█▊        | 291/1563 [08:45<38:45,  1.83s/it]
Training 1/1 epoch (loss 1.6727):  19%|█▊        | 292/1563 [08:45<38:26,  1.81s/it]
Training 1/1 epoch (loss 1.7375):  19%|█▊        | 292/1563 [08:46<38:26,  1.81s/it]
Training 1/1 epoch (loss 1.7375):  19%|█▊        | 293/1563 [08:46<34:31,  1.63s/it]
Training 1/1 epoch (loss 1.8500):  19%|█▊        | 293/1563 [08:49<34:31,  1.63s/it]
Training 1/1 epoch (loss 1.8500):  19%|█▉        | 294/1563 [08:49<39:31,  1.87s/it]
Training 1/1 epoch (loss 1.7360):  19%|█▉        | 294/1563 [08:51<39:31,  1.87s/it]
Training 1/1 epoch (loss 1.7360):  19%|█▉        | 295/1563 [08:51<40:19,  1.91s/it]
Training 1/1 epoch (loss 1.6286):  19%|█▉        | 295/1563 [08:52<40:19,  1.91s/it]
Training 1/1 epoch (loss 1.6286):  19%|█▉        | 296/1563 [08:52<39:53,  1.89s/it]
Training 1/1 epoch (loss 1.8246):  19%|█▉        | 296/1563 [08:54<39:53,  1.89s/it]
Training 1/1 epoch (loss 1.8246):  19%|█▉        | 297/1563 [08:54<35:49,  1.70s/it]
Training 1/1 epoch (loss 1.7648):  19%|█▉        | 297/1563 [08:56<35:49,  1.70s/it]
Training 1/1 epoch (loss 1.7648):  19%|█▉        | 298/1563 [08:56<37:28,  1.78s/it]
Training 1/1 epoch (loss 1.6557):  19%|█▉        | 298/1563 [08:57<37:28,  1.78s/it]
Training 1/1 epoch (loss 1.6557):  19%|█▉        | 299/1563 [08:57<37:05,  1.76s/it]
Training 1/1 epoch (loss 1.7369):  19%|█▉        | 299/1563 [08:59<37:05,  1.76s/it]
Training 1/1 epoch (loss 1.7369):  19%|█▉        | 300/1563 [08:59<37:17,  1.77s/it]
Training 1/1 epoch (loss 1.7802):  19%|█▉        | 300/1563 [09:01<37:17,  1.77s/it]
Training 1/1 epoch (loss 1.7802):  19%|█▉        | 301/1563 [09:01<38:14,  1.82s/it]
Training 1/1 epoch (loss 1.7585):  19%|█▉        | 301/1563 [09:04<38:14,  1.82s/it]
Training 1/1 epoch (loss 1.7585):  19%|█▉        | 302/1563 [09:04<41:58,  2.00s/it]
Training 1/1 epoch (loss 1.6748):  19%|█▉        | 302/1563 [09:05<41:58,  2.00s/it]
Training 1/1 epoch (loss 1.6748):  19%|█▉        | 303/1563 [09:05<37:30,  1.79s/it]
Training 1/1 epoch (loss 1.6896):  19%|█▉        | 303/1563 [09:07<37:30,  1.79s/it]
Training 1/1 epoch (loss 1.6896):  19%|█▉        | 304/1563 [09:07<41:24,  1.97s/it]
Training 1/1 epoch (loss 1.6744):  19%|█▉        | 304/1563 [09:10<41:24,  1.97s/it]
Training 1/1 epoch (loss 1.6744):  20%|█▉        | 305/1563 [09:10<44:49,  2.14s/it]
Training 1/1 epoch (loss 1.7533):  20%|█▉        | 305/1563 [09:12<44:49,  2.14s/it]
Training 1/1 epoch (loss 1.7533):  20%|█▉        | 306/1563 [09:12<44:02,  2.10s/it]
Training 1/1 epoch (loss 1.6824):  20%|█▉        | 306/1563 [09:13<44:02,  2.10s/it]
Training 1/1 epoch (loss 1.6824):  20%|█▉        | 307/1563 [09:13<40:47,  1.95s/it]
Training 1/1 epoch (loss 1.7539):  20%|█▉        | 307/1563 [09:15<40:47,  1.95s/it]
Training 1/1 epoch (loss 1.7539):  20%|█▉        | 308/1563 [09:15<36:26,  1.74s/it]
Training 1/1 epoch (loss 1.7828):  20%|█▉        | 308/1563 [09:16<36:26,  1.74s/it]
Training 1/1 epoch (loss 1.7828):  20%|█▉        | 309/1563 [09:16<35:39,  1.71s/it]
Training 1/1 epoch (loss 1.7594):  20%|█▉        | 309/1563 [09:18<35:39,  1.71s/it]
Training 1/1 epoch (loss 1.7594):  20%|█▉        | 310/1563 [09:18<38:31,  1.84s/it]
Training 1/1 epoch (loss 1.7696):  20%|█▉        | 310/1563 [09:21<38:31,  1.84s/it]
Training 1/1 epoch (loss 1.7696):  20%|█▉        | 311/1563 [09:21<40:35,  1.95s/it]
Training 1/1 epoch (loss 1.6692):  20%|█▉        | 311/1563 [09:22<40:35,  1.95s/it]
Training 1/1 epoch (loss 1.6692):  20%|█▉        | 312/1563 [09:22<38:16,  1.84s/it]
Training 1/1 epoch (loss 1.6528):  20%|█▉        | 312/1563 [09:25<38:16,  1.84s/it]
Training 1/1 epoch (loss 1.6528):  20%|██        | 313/1563 [09:25<42:07,  2.02s/it]
Training 1/1 epoch (loss 1.7409):  20%|██        | 313/1563 [09:26<42:07,  2.02s/it]
Training 1/1 epoch (loss 1.7409):  20%|██        | 314/1563 [09:26<40:13,  1.93s/it]
Training 1/1 epoch (loss 1.7812):  20%|██        | 314/1563 [09:28<40:13,  1.93s/it]
Training 1/1 epoch (loss 1.7812):  20%|██        | 315/1563 [09:28<37:47,  1.82s/it]
Training 1/1 epoch (loss 1.6902):  20%|██        | 315/1563 [09:30<37:47,  1.82s/it]
Training 1/1 epoch (loss 1.6902):  20%|██        | 316/1563 [09:30<39:01,  1.88s/it]
Training 1/1 epoch (loss 1.7452):  20%|██        | 316/1563 [09:31<39:01,  1.88s/it]
Training 1/1 epoch (loss 1.7452):  20%|██        | 317/1563 [09:31<35:16,  1.70s/it]
Training 1/1 epoch (loss 1.6981):  20%|██        | 317/1563 [09:33<35:16,  1.70s/it]
Training 1/1 epoch (loss 1.6981):  20%|██        | 318/1563 [09:33<34:07,  1.64s/it]
Training 1/1 epoch (loss 1.6421):  20%|██        | 318/1563 [09:34<34:07,  1.64s/it]
Training 1/1 epoch (loss 1.6421):  20%|██        | 319/1563 [09:34<34:27,  1.66s/it]
Training 1/1 epoch (loss 1.7360):  20%|██        | 319/1563 [09:36<34:27,  1.66s/it]
Training 1/1 epoch (loss 1.7360):  20%|██        | 320/1563 [09:36<36:29,  1.76s/it]
Training 1/1 epoch (loss 1.7457):  20%|██        | 320/1563 [09:39<36:29,  1.76s/it]
Training 1/1 epoch (loss 1.7457):  21%|██        | 321/1563 [09:39<39:31,  1.91s/it]
Training 1/1 epoch (loss 1.7865):  21%|██        | 321/1563 [09:40<39:31,  1.91s/it]
Training 1/1 epoch (loss 1.7865):  21%|██        | 322/1563 [09:40<36:29,  1.76s/it]
Training 1/1 epoch (loss 1.6334):  21%|██        | 322/1563 [09:42<36:29,  1.76s/it]
Training 1/1 epoch (loss 1.6334):  21%|██        | 323/1563 [09:42<35:36,  1.72s/it]
Training 1/1 epoch (loss 1.6784):  21%|██        | 323/1563 [09:44<35:36,  1.72s/it]
Training 1/1 epoch (loss 1.6784):  21%|██        | 324/1563 [09:44<36:14,  1.76s/it]
Training 1/1 epoch (loss 1.6978):  21%|██        | 324/1563 [09:45<36:14,  1.76s/it]
Training 1/1 epoch (loss 1.6978):  21%|██        | 325/1563 [09:45<36:12,  1.75s/it]
Training 1/1 epoch (loss 1.6747):  21%|██        | 325/1563 [09:47<36:12,  1.75s/it]
Training 1/1 epoch (loss 1.6747):  21%|██        | 326/1563 [09:47<38:33,  1.87s/it]
Training 1/1 epoch (loss 1.7432):  21%|██        | 326/1563 [09:49<38:33,  1.87s/it]
Training 1/1 epoch (loss 1.7432):  21%|██        | 327/1563 [09:49<37:49,  1.84s/it]
Training 1/1 epoch (loss 1.6142):  21%|██        | 327/1563 [09:51<37:49,  1.84s/it]
Training 1/1 epoch (loss 1.6142):  21%|██        | 328/1563 [09:51<37:32,  1.82s/it]
Training 1/1 epoch (loss 1.8085):  21%|██        | 328/1563 [09:53<37:32,  1.82s/it]
Training 1/1 epoch (loss 1.8085):  21%|██        | 329/1563 [09:53<40:53,  1.99s/it]
Training 1/1 epoch (loss 1.7013):  21%|██        | 329/1563 [09:55<40:53,  1.99s/it]
Training 1/1 epoch (loss 1.7013):  21%|██        | 330/1563 [09:55<37:29,  1.82s/it]
Training 1/1 epoch (loss 1.5966):  21%|██        | 330/1563 [09:56<37:29,  1.82s/it]
Training 1/1 epoch (loss 1.5966):  21%|██        | 331/1563 [09:56<35:10,  1.71s/it]
Training 1/1 epoch (loss 1.7563):  21%|██        | 331/1563 [09:58<35:10,  1.71s/it]
Training 1/1 epoch (loss 1.7563):  21%|██        | 332/1563 [09:58<32:57,  1.61s/it]
Training 1/1 epoch (loss 1.7440):  21%|██        | 332/1563 [10:00<32:57,  1.61s/it]
Training 1/1 epoch (loss 1.7440):  21%|██▏       | 333/1563 [10:00<36:19,  1.77s/it]
Training 1/1 epoch (loss 1.6682):  21%|██▏       | 333/1563 [10:01<36:19,  1.77s/it]
Training 1/1 epoch (loss 1.6682):  21%|██▏       | 334/1563 [10:01<34:10,  1.67s/it]
Training 1/1 epoch (loss 1.7259):  21%|██▏       | 334/1563 [10:04<34:10,  1.67s/it]
Training 1/1 epoch (loss 1.7259):  21%|██▏       | 335/1563 [10:04<38:47,  1.90s/it]
Training 1/1 epoch (loss 1.7510):  21%|██▏       | 335/1563 [10:05<38:47,  1.90s/it]
Training 1/1 epoch (loss 1.7510):  21%|██▏       | 336/1563 [10:05<36:22,  1.78s/it]
Training 1/1 epoch (loss 1.7038):  21%|██▏       | 336/1563 [10:07<36:22,  1.78s/it]
Training 1/1 epoch (loss 1.7038):  22%|██▏       | 337/1563 [10:07<37:00,  1.81s/it]
Training 1/1 epoch (loss 1.7411):  22%|██▏       | 337/1563 [10:09<37:00,  1.81s/it]
Training 1/1 epoch (loss 1.7411):  22%|██▏       | 338/1563 [10:09<37:15,  1.83s/it]
Training 1/1 epoch (loss 1.7110):  22%|██▏       | 338/1563 [10:10<37:15,  1.83s/it]
Training 1/1 epoch (loss 1.7110):  22%|██▏       | 339/1563 [10:10<34:23,  1.69s/it]
Training 1/1 epoch (loss 1.7340):  22%|██▏       | 339/1563 [10:12<34:23,  1.69s/it]
Training 1/1 epoch (loss 1.7340):  22%|██▏       | 340/1563 [10:12<36:33,  1.79s/it]
Training 1/1 epoch (loss 1.6772):  22%|██▏       | 340/1563 [10:14<36:33,  1.79s/it]
Training 1/1 epoch (loss 1.6772):  22%|██▏       | 341/1563 [10:14<38:39,  1.90s/it]
Training 1/1 epoch (loss 1.6617):  22%|██▏       | 341/1563 [10:16<38:39,  1.90s/it]
Training 1/1 epoch (loss 1.6617):  22%|██▏       | 342/1563 [10:16<38:10,  1.88s/it]
Training 1/1 epoch (loss 1.7039):  22%|██▏       | 342/1563 [10:18<38:10,  1.88s/it]
Training 1/1 epoch (loss 1.7039):  22%|██▏       | 343/1563 [10:18<39:39,  1.95s/it]
Training 1/1 epoch (loss 1.7177):  22%|██▏       | 343/1563 [10:20<39:39,  1.95s/it]
Training 1/1 epoch (loss 1.7177):  22%|██▏       | 344/1563 [10:20<38:52,  1.91s/it]
Training 1/1 epoch (loss 1.7206):  22%|██▏       | 344/1563 [10:21<38:52,  1.91s/it]
Training 1/1 epoch (loss 1.7206):  22%|██▏       | 345/1563 [10:21<33:47,  1.66s/it]
Training 1/1 epoch (loss 1.8159):  22%|██▏       | 345/1563 [10:23<33:47,  1.66s/it]
Training 1/1 epoch (loss 1.8159):  22%|██▏       | 346/1563 [10:23<33:03,  1.63s/it]
Training 1/1 epoch (loss 1.7007):  22%|██▏       | 346/1563 [10:25<33:03,  1.63s/it]
Training 1/1 epoch (loss 1.7007):  22%|██▏       | 347/1563 [10:25<37:30,  1.85s/it]
Training 1/1 epoch (loss 1.6166):  22%|██▏       | 347/1563 [10:27<37:30,  1.85s/it]
Training 1/1 epoch (loss 1.6166):  22%|██▏       | 348/1563 [10:27<38:43,  1.91s/it]
Training 1/1 epoch (loss 1.6576):  22%|██▏       | 348/1563 [10:29<38:43,  1.91s/it]
Training 1/1 epoch (loss 1.6576):  22%|██▏       | 349/1563 [10:29<37:10,  1.84s/it]
Training 1/1 epoch (loss 1.7562):  22%|██▏       | 349/1563 [10:31<37:10,  1.84s/it]
Training 1/1 epoch (loss 1.7562):  22%|██▏       | 350/1563 [10:31<36:21,  1.80s/it]
Training 1/1 epoch (loss 1.7466):  22%|██▏       | 350/1563 [10:32<36:21,  1.80s/it]
Training 1/1 epoch (loss 1.7466):  22%|██▏       | 351/1563 [10:32<35:17,  1.75s/it]
Training 1/1 epoch (loss 1.7910):  22%|██▏       | 351/1563 [10:34<35:17,  1.75s/it]
Training 1/1 epoch (loss 1.7910):  23%|██▎       | 352/1563 [10:34<34:14,  1.70s/it]
Training 1/1 epoch (loss 1.7441):  23%|██▎       | 352/1563 [10:35<34:14,  1.70s/it]
Training 1/1 epoch (loss 1.7441):  23%|██▎       | 353/1563 [10:35<33:48,  1.68s/it]
Training 1/1 epoch (loss 1.6622):  23%|██▎       | 353/1563 [10:37<33:48,  1.68s/it]
Training 1/1 epoch (loss 1.6622):  23%|██▎       | 354/1563 [10:37<32:54,  1.63s/it]
Training 1/1 epoch (loss 1.6387):  23%|██▎       | 354/1563 [10:39<32:54,  1.63s/it]
Training 1/1 epoch (loss 1.6387):  23%|██▎       | 355/1563 [10:39<36:56,  1.83s/it]
Training 1/1 epoch (loss 1.6799):  23%|██▎       | 355/1563 [10:40<36:56,  1.83s/it]
Training 1/1 epoch (loss 1.6799):  23%|██▎       | 356/1563 [10:40<32:08,  1.60s/it]
Training 1/1 epoch (loss 1.6925):  23%|██▎       | 356/1563 [10:42<32:08,  1.60s/it]
Training 1/1 epoch (loss 1.6925):  23%|██▎       | 357/1563 [10:42<34:46,  1.73s/it]
Training 1/1 epoch (loss 1.5968):  23%|██▎       | 357/1563 [10:44<34:46,  1.73s/it]
Training 1/1 epoch (loss 1.5968):  23%|██▎       | 358/1563 [10:44<34:13,  1.70s/it]
Training 1/1 epoch (loss 1.6935):  23%|██▎       | 358/1563 [10:46<34:13,  1.70s/it]
Training 1/1 epoch (loss 1.6935):  23%|██▎       | 359/1563 [10:46<38:37,  1.92s/it]
Training 1/1 epoch (loss 1.8005):  23%|██▎       | 359/1563 [10:48<38:37,  1.92s/it]
Training 1/1 epoch (loss 1.8005):  23%|██▎       | 360/1563 [10:48<39:07,  1.95s/it]
Training 1/1 epoch (loss 1.6506):  23%|██▎       | 360/1563 [10:50<39:07,  1.95s/it]
Training 1/1 epoch (loss 1.6506):  23%|██▎       | 361/1563 [10:50<34:01,  1.70s/it]
Training 1/1 epoch (loss 1.7692):  23%|██▎       | 361/1563 [10:51<34:01,  1.70s/it]
Training 1/1 epoch (loss 1.7692):  23%|██▎       | 362/1563 [10:51<31:32,  1.58s/it]
Training 1/1 epoch (loss 1.7964):  23%|██▎       | 362/1563 [10:53<31:32,  1.58s/it]
Training 1/1 epoch (loss 1.7964):  23%|██▎       | 363/1563 [10:53<34:31,  1.73s/it]
Training 1/1 epoch (loss 1.7750):  23%|██▎       | 363/1563 [10:55<34:31,  1.73s/it]
Training 1/1 epoch (loss 1.7750):  23%|██▎       | 364/1563 [10:55<39:01,  1.95s/it]
Training 1/1 epoch (loss 1.6640):  23%|██▎       | 364/1563 [10:57<39:01,  1.95s/it]
Training 1/1 epoch (loss 1.6640):  23%|██▎       | 365/1563 [10:57<36:13,  1.81s/it]
Training 1/1 epoch (loss 1.6951):  23%|██▎       | 365/1563 [10:58<36:13,  1.81s/it]
Training 1/1 epoch (loss 1.6951):  23%|██▎       | 366/1563 [10:58<30:20,  1.52s/it]
Training 1/1 epoch (loss 1.6540):  23%|██▎       | 366/1563 [11:00<30:20,  1.52s/it]
Training 1/1 epoch (loss 1.6540):  23%|██▎       | 367/1563 [11:00<33:19,  1.67s/it]
Training 1/1 epoch (loss 1.6884):  23%|██▎       | 367/1563 [11:02<33:19,  1.67s/it]
Training 1/1 epoch (loss 1.6884):  24%|██▎       | 368/1563 [11:02<36:21,  1.83s/it]
Training 1/1 epoch (loss 1.6901):  24%|██▎       | 368/1563 [11:04<36:21,  1.83s/it]
Training 1/1 epoch (loss 1.6901):  24%|██▎       | 369/1563 [11:04<36:17,  1.82s/it]
Training 1/1 epoch (loss 1.7061):  24%|██▎       | 369/1563 [11:05<36:17,  1.82s/it]
Training 1/1 epoch (loss 1.7061):  24%|██▎       | 370/1563 [11:05<35:27,  1.78s/it]
Training 1/1 epoch (loss 1.8156):  24%|██▎       | 370/1563 [11:07<35:27,  1.78s/it]
Training 1/1 epoch (loss 1.8156):  24%|██▎       | 371/1563 [11:07<33:21,  1.68s/it]
Training 1/1 epoch (loss 1.6565):  24%|██▎       | 371/1563 [11:08<33:21,  1.68s/it]
Training 1/1 epoch (loss 1.6565):  24%|██▍       | 372/1563 [11:08<27:57,  1.41s/it]
Training 1/1 epoch (loss 1.6048):  24%|██▍       | 372/1563 [11:09<27:57,  1.41s/it]
Training 1/1 epoch (loss 1.6048):  24%|██▍       | 373/1563 [11:09<28:47,  1.45s/it]
Training 1/1 epoch (loss 1.6725):  24%|██▍       | 373/1563 [11:11<28:47,  1.45s/it]
Training 1/1 epoch (loss 1.6725):  24%|██▍       | 374/1563 [11:11<28:48,  1.45s/it]
Training 1/1 epoch (loss 1.6599):  24%|██▍       | 374/1563 [11:13<28:48,  1.45s/it]
Training 1/1 epoch (loss 1.6599):  24%|██▍       | 375/1563 [11:13<32:33,  1.64s/it]
Training 1/1 epoch (loss 1.7006):  24%|██▍       | 375/1563 [11:15<32:33,  1.64s/it]
Training 1/1 epoch (loss 1.7006):  24%|██▍       | 376/1563 [11:15<33:12,  1.68s/it]
Training 1/1 epoch (loss 1.6139):  24%|██▍       | 376/1563 [11:16<33:12,  1.68s/it]
Training 1/1 epoch (loss 1.6139):  24%|██▍       | 377/1563 [11:16<31:13,  1.58s/it]
Training 1/1 epoch (loss 1.8085):  24%|██▍       | 377/1563 [11:18<31:13,  1.58s/it]
Training 1/1 epoch (loss 1.8085):  24%|██▍       | 378/1563 [11:18<31:44,  1.61s/it]
Training 1/1 epoch (loss 1.6870):  24%|██▍       | 378/1563 [11:20<31:44,  1.61s/it]
Training 1/1 epoch (loss 1.6870):  24%|██▍       | 379/1563 [11:20<36:36,  1.86s/it]
Training 1/1 epoch (loss 1.5751):  24%|██▍       | 379/1563 [11:21<36:36,  1.86s/it]
Training 1/1 epoch (loss 1.5751):  24%|██▍       | 380/1563 [11:21<31:26,  1.59s/it]
Training 1/1 epoch (loss 1.6013):  24%|██▍       | 380/1563 [11:22<31:26,  1.59s/it]
Training 1/1 epoch (loss 1.6013):  24%|██▍       | 381/1563 [11:22<29:01,  1.47s/it]
Training 1/1 epoch (loss 1.7380):  24%|██▍       | 381/1563 [11:24<29:01,  1.47s/it]
Training 1/1 epoch (loss 1.7380):  24%|██▍       | 382/1563 [11:24<28:29,  1.45s/it]
Training 1/1 epoch (loss 1.7110):  24%|██▍       | 382/1563 [11:25<28:29,  1.45s/it]
Training 1/1 epoch (loss 1.7110):  25%|██▍       | 383/1563 [11:25<28:48,  1.46s/it]
Training 1/1 epoch (loss 1.7297):  25%|██▍       | 383/1563 [11:27<28:48,  1.46s/it]
Training 1/1 epoch (loss 1.7297):  25%|██▍       | 384/1563 [11:27<33:15,  1.69s/it]
Training 1/1 epoch (loss 1.7441):  25%|██▍       | 384/1563 [11:29<33:15,  1.69s/it]
Training 1/1 epoch (loss 1.7441):  25%|██▍       | 385/1563 [11:29<34:06,  1.74s/it]
Training 1/1 epoch (loss 1.7248):  25%|██▍       | 385/1563 [11:31<34:06,  1.74s/it]
Training 1/1 epoch (loss 1.7248):  25%|██▍       | 386/1563 [11:31<33:58,  1.73s/it]
Training 1/1 epoch (loss 1.7579):  25%|██▍       | 386/1563 [11:33<33:58,  1.73s/it]
Training 1/1 epoch (loss 1.7579):  25%|██▍       | 387/1563 [11:33<38:24,  1.96s/it]
Training 1/1 epoch (loss 1.7846):  25%|██▍       | 387/1563 [11:35<38:24,  1.96s/it]
Training 1/1 epoch (loss 1.7846):  25%|██▍       | 388/1563 [11:35<35:37,  1.82s/it]
Training 1/1 epoch (loss 1.7152):  25%|██▍       | 388/1563 [11:37<35:37,  1.82s/it]
Training 1/1 epoch (loss 1.7152):  25%|██▍       | 389/1563 [11:37<39:08,  2.00s/it]
Training 1/1 epoch (loss 1.7354):  25%|██▍       | 389/1563 [11:40<39:08,  2.00s/it]
Training 1/1 epoch (loss 1.7354):  25%|██▍       | 390/1563 [11:40<41:38,  2.13s/it]
Training 1/1 epoch (loss 1.6884):  25%|██▍       | 390/1563 [11:42<41:38,  2.13s/it]
Training 1/1 epoch (loss 1.6884):  25%|██▌       | 391/1563 [11:42<41:19,  2.12s/it]
Training 1/1 epoch (loss 1.6540):  25%|██▌       | 391/1563 [11:44<41:19,  2.12s/it]
Training 1/1 epoch (loss 1.6540):  25%|██▌       | 392/1563 [11:44<39:58,  2.05s/it]
Training 1/1 epoch (loss 1.6269):  25%|██▌       | 392/1563 [11:45<39:58,  2.05s/it]
Training 1/1 epoch (loss 1.6269):  25%|██▌       | 393/1563 [11:45<35:46,  1.83s/it]
Training 1/1 epoch (loss 1.5898):  25%|██▌       | 393/1563 [11:46<35:46,  1.83s/it]
Training 1/1 epoch (loss 1.5898):  25%|██▌       | 394/1563 [11:46<31:13,  1.60s/it]
Training 1/1 epoch (loss 1.6165):  25%|██▌       | 394/1563 [11:48<31:13,  1.60s/it]
Training 1/1 epoch (loss 1.6165):  25%|██▌       | 395/1563 [11:48<34:04,  1.75s/it]
Training 1/1 epoch (loss 1.7388):  25%|██▌       | 395/1563 [11:50<34:04,  1.75s/it]
Training 1/1 epoch (loss 1.7388):  25%|██▌       | 396/1563 [11:50<33:25,  1.72s/it]
Training 1/1 epoch (loss 1.6610):  25%|██▌       | 396/1563 [11:51<33:25,  1.72s/it]
Training 1/1 epoch (loss 1.6610):  25%|██▌       | 397/1563 [11:51<33:00,  1.70s/it]
Training 1/1 epoch (loss 1.7739):  25%|██▌       | 397/1563 [11:53<33:00,  1.70s/it]
Training 1/1 epoch (loss 1.7739):  25%|██▌       | 398/1563 [11:53<32:58,  1.70s/it]
Training 1/1 epoch (loss 1.6012):  25%|██▌       | 398/1563 [11:55<32:58,  1.70s/it]
Training 1/1 epoch (loss 1.6012):  26%|██▌       | 399/1563 [11:55<31:05,  1.60s/it]
Training 1/1 epoch (loss 1.7565):  26%|██▌       | 399/1563 [11:57<31:05,  1.60s/it]
Training 1/1 epoch (loss 1.7565):  26%|██▌       | 400/1563 [11:57<34:04,  1.76s/it]
Training 1/1 epoch (loss 1.7228):  26%|██▌       | 400/1563 [11:58<34:04,  1.76s/it]
Training 1/1 epoch (loss 1.7228):  26%|██▌       | 401/1563 [11:58<31:24,  1.62s/it]
Training 1/1 epoch (loss 1.7505):  26%|██▌       | 401/1563 [12:00<31:24,  1.62s/it]
Training 1/1 epoch (loss 1.7505):  26%|██▌       | 402/1563 [12:00<35:42,  1.85s/it]
Training 1/1 epoch (loss 1.6836):  26%|██▌       | 402/1563 [12:02<35:42,  1.85s/it]
Training 1/1 epoch (loss 1.6836):  26%|██▌       | 403/1563 [12:02<37:08,  1.92s/it]
Training 1/1 epoch (loss 1.5435):  26%|██▌       | 403/1563 [12:05<37:08,  1.92s/it]
Training 1/1 epoch (loss 1.5435):  26%|██▌       | 404/1563 [12:05<39:12,  2.03s/it]
Training 1/1 epoch (loss 1.6707):  26%|██▌       | 404/1563 [12:07<39:12,  2.03s/it]
Training 1/1 epoch (loss 1.6707):  26%|██▌       | 405/1563 [12:07<40:46,  2.11s/it]
Training 1/1 epoch (loss 1.7112):  26%|██▌       | 405/1563 [12:09<40:46,  2.11s/it]
Training 1/1 epoch (loss 1.7112):  26%|██▌       | 406/1563 [12:09<38:21,  1.99s/it]
Training 1/1 epoch (loss 1.7265):  26%|██▌       | 406/1563 [12:10<38:21,  1.99s/it]
Training 1/1 epoch (loss 1.7265):  26%|██▌       | 407/1563 [12:10<36:26,  1.89s/it]
Training 1/1 epoch (loss 1.7073):  26%|██▌       | 407/1563 [12:13<36:26,  1.89s/it]
Training 1/1 epoch (loss 1.7073):  26%|██▌       | 408/1563 [12:13<39:34,  2.06s/it]
Training 1/1 epoch (loss 1.6758):  26%|██▌       | 408/1563 [12:15<39:34,  2.06s/it]
Training 1/1 epoch (loss 1.6758):  26%|██▌       | 409/1563 [12:15<40:04,  2.08s/it]
Training 1/1 epoch (loss 1.6973):  26%|██▌       | 409/1563 [12:17<40:04,  2.08s/it]
Training 1/1 epoch (loss 1.6973):  26%|██▌       | 410/1563 [12:17<37:46,  1.97s/it]
Training 1/1 epoch (loss 1.7719):  26%|██▌       | 410/1563 [12:19<37:46,  1.97s/it]
Training 1/1 epoch (loss 1.7719):  26%|██▋       | 411/1563 [12:19<37:37,  1.96s/it]
Training 1/1 epoch (loss 1.6800):  26%|██▋       | 411/1563 [12:20<37:37,  1.96s/it]
Training 1/1 epoch (loss 1.6800):  26%|██▋       | 412/1563 [12:20<36:27,  1.90s/it]
Training 1/1 epoch (loss 1.6354):  26%|██▋       | 412/1563 [12:22<36:27,  1.90s/it]
Training 1/1 epoch (loss 1.6354):  26%|██▋       | 413/1563 [12:22<35:27,  1.85s/it]
Training 1/1 epoch (loss 1.6966):  26%|██▋       | 413/1563 [12:23<35:27,  1.85s/it]
Training 1/1 epoch (loss 1.6966):  26%|██▋       | 414/1563 [12:23<32:08,  1.68s/it]
Training 1/1 epoch (loss 1.7174):  26%|██▋       | 414/1563 [12:25<32:08,  1.68s/it]
Training 1/1 epoch (loss 1.7174):  27%|██▋       | 415/1563 [12:25<31:38,  1.65s/it]
Training 1/1 epoch (loss 1.6653):  27%|██▋       | 415/1563 [12:27<31:38,  1.65s/it]
Training 1/1 epoch (loss 1.6653):  27%|██▋       | 416/1563 [12:27<35:51,  1.88s/it]
Training 1/1 epoch (loss 1.6916):  27%|██▋       | 416/1563 [12:30<35:51,  1.88s/it]
Training 1/1 epoch (loss 1.6916):  27%|██▋       | 417/1563 [12:30<38:45,  2.03s/it]
Training 1/1 epoch (loss 1.6259):  27%|██▋       | 417/1563 [12:31<38:45,  2.03s/it]
Training 1/1 epoch (loss 1.6259):  27%|██▋       | 418/1563 [12:31<34:34,  1.81s/it]
Training 1/1 epoch (loss 1.6287):  27%|██▋       | 418/1563 [12:33<34:34,  1.81s/it]
Training 1/1 epoch (loss 1.6287):  27%|██▋       | 419/1563 [12:33<34:01,  1.78s/it]
Training 1/1 epoch (loss 1.6775):  27%|██▋       | 419/1563 [12:35<34:01,  1.78s/it]
Training 1/1 epoch (loss 1.6775):  27%|██▋       | 420/1563 [12:35<35:53,  1.88s/it]
Training 1/1 epoch (loss 1.6762):  27%|██▋       | 420/1563 [12:37<35:53,  1.88s/it]
Training 1/1 epoch (loss 1.6762):  27%|██▋       | 421/1563 [12:37<37:38,  1.98s/it]
Training 1/1 epoch (loss 1.7498):  27%|██▋       | 421/1563 [12:39<37:38,  1.98s/it]
Training 1/1 epoch (loss 1.7498):  27%|██▋       | 422/1563 [12:39<39:53,  2.10s/it]
Training 1/1 epoch (loss 1.6542):  27%|██▋       | 422/1563 [12:41<39:53,  2.10s/it]
Training 1/1 epoch (loss 1.6542):  27%|██▋       | 423/1563 [12:41<38:35,  2.03s/it]
Training 1/1 epoch (loss 1.7717):  27%|██▋       | 423/1563 [12:43<38:35,  2.03s/it]
Training 1/1 epoch (loss 1.7717):  27%|██▋       | 424/1563 [12:43<35:16,  1.86s/it]
Training 1/1 epoch (loss 1.7090):  27%|██▋       | 424/1563 [12:44<35:16,  1.86s/it]
Training 1/1 epoch (loss 1.7090):  27%|██▋       | 425/1563 [12:44<32:21,  1.71s/it]
Training 1/1 epoch (loss 1.6180):  27%|██▋       | 425/1563 [12:46<32:21,  1.71s/it]
Training 1/1 epoch (loss 1.6180):  27%|██▋       | 426/1563 [12:46<35:32,  1.88s/it]
Training 1/1 epoch (loss 1.8252):  27%|██▋       | 426/1563 [12:48<35:32,  1.88s/it]
Training 1/1 epoch (loss 1.8252):  27%|██▋       | 427/1563 [12:48<31:32,  1.67s/it]
Training 1/1 epoch (loss 1.6115):  27%|██▋       | 427/1563 [12:49<31:32,  1.67s/it]
Training 1/1 epoch (loss 1.6115):  27%|██▋       | 428/1563 [12:49<29:53,  1.58s/it]
Training 1/1 epoch (loss 1.6155):  27%|██▋       | 428/1563 [12:51<29:53,  1.58s/it]
Training 1/1 epoch (loss 1.6155):  27%|██▋       | 429/1563 [12:51<29:56,  1.58s/it]
Training 1/1 epoch (loss 1.6452):  27%|██▋       | 429/1563 [12:53<29:56,  1.58s/it]
Training 1/1 epoch (loss 1.6452):  28%|██▊       | 430/1563 [12:53<31:51,  1.69s/it]
Training 1/1 epoch (loss 1.6406):  28%|██▊       | 430/1563 [12:55<31:51,  1.69s/it]
Training 1/1 epoch (loss 1.6406):  28%|██▊       | 431/1563 [12:55<34:51,  1.85s/it]
Training 1/1 epoch (loss 1.7254):  28%|██▊       | 431/1563 [12:57<34:51,  1.85s/it]
Training 1/1 epoch (loss 1.7254):  28%|██▊       | 432/1563 [12:57<35:06,  1.86s/it]
Training 1/1 epoch (loss 1.6055):  28%|██▊       | 432/1563 [12:59<35:06,  1.86s/it]
Training 1/1 epoch (loss 1.6055):  28%|██▊       | 433/1563 [12:59<38:49,  2.06s/it]
Training 1/1 epoch (loss 1.6683):  28%|██▊       | 433/1563 [13:01<38:49,  2.06s/it]
Training 1/1 epoch (loss 1.6683):  28%|██▊       | 434/1563 [13:01<36:24,  1.93s/it]
Training 1/1 epoch (loss 1.7331):  28%|██▊       | 434/1563 [13:03<36:24,  1.93s/it]
Training 1/1 epoch (loss 1.7331):  28%|██▊       | 435/1563 [13:03<39:37,  2.11s/it]
Training 1/1 epoch (loss 1.7232):  28%|██▊       | 435/1563 [13:06<39:37,  2.11s/it]
Training 1/1 epoch (loss 1.7232):  28%|██▊       | 436/1563 [13:06<41:35,  2.21s/it]
Training 1/1 epoch (loss 1.6922):  28%|██▊       | 436/1563 [13:08<41:35,  2.21s/it]
Training 1/1 epoch (loss 1.6922):  28%|██▊       | 437/1563 [13:08<40:08,  2.14s/it]
Training 1/1 epoch (loss 1.7284):  28%|██▊       | 437/1563 [13:10<40:08,  2.14s/it]
Training 1/1 epoch (loss 1.7284):  28%|██▊       | 438/1563 [13:10<40:38,  2.17s/it]
Training 1/1 epoch (loss 1.6640):  28%|██▊       | 438/1563 [13:11<40:38,  2.17s/it]
Training 1/1 epoch (loss 1.6640):  28%|██▊       | 439/1563 [13:11<35:03,  1.87s/it]
Training 1/1 epoch (loss 1.7515):  28%|██▊       | 439/1563 [13:13<35:03,  1.87s/it]
Training 1/1 epoch (loss 1.7515):  28%|██▊       | 440/1563 [13:13<37:08,  1.98s/it]
Training 1/1 epoch (loss 1.6098):  28%|██▊       | 440/1563 [13:15<37:08,  1.98s/it]
Training 1/1 epoch (loss 1.6098):  28%|██▊       | 441/1563 [13:15<33:47,  1.81s/it]
Training 1/1 epoch (loss 1.6704):  28%|██▊       | 441/1563 [13:17<33:47,  1.81s/it]
Training 1/1 epoch (loss 1.6704):  28%|██▊       | 442/1563 [13:17<34:38,  1.85s/it]
Training 1/1 epoch (loss 1.7471):  28%|██▊       | 442/1563 [13:19<34:38,  1.85s/it]
Training 1/1 epoch (loss 1.7471):  28%|██▊       | 443/1563 [13:19<34:43,  1.86s/it]
Training 1/1 epoch (loss 1.6595):  28%|██▊       | 443/1563 [13:20<34:43,  1.86s/it]
Training 1/1 epoch (loss 1.6595):  28%|██▊       | 444/1563 [13:20<30:40,  1.64s/it]
Training 1/1 epoch (loss 1.6972):  28%|██▊       | 444/1563 [13:21<30:40,  1.64s/it]
Training 1/1 epoch (loss 1.6972):  28%|██▊       | 445/1563 [13:21<28:42,  1.54s/it]
Training 1/1 epoch (loss 1.6720):  28%|██▊       | 445/1563 [13:23<28:42,  1.54s/it]
Training 1/1 epoch (loss 1.6720):  29%|██▊       | 446/1563 [13:23<29:50,  1.60s/it]
Training 1/1 epoch (loss 1.6731):  29%|██▊       | 446/1563 [13:25<29:50,  1.60s/it]
Training 1/1 epoch (loss 1.6731):  29%|██▊       | 447/1563 [13:25<31:10,  1.68s/it]
Training 1/1 epoch (loss 1.7727):  29%|██▊       | 447/1563 [13:27<31:10,  1.68s/it]
Training 1/1 epoch (loss 1.7727):  29%|██▊       | 448/1563 [13:27<35:38,  1.92s/it]
Training 1/1 epoch (loss 1.6564):  29%|██▊       | 448/1563 [13:29<35:38,  1.92s/it]
Training 1/1 epoch (loss 1.6564):  29%|██▊       | 449/1563 [13:29<32:41,  1.76s/it]
Training 1/1 epoch (loss 1.5579):  29%|██▊       | 449/1563 [13:31<32:41,  1.76s/it]
Training 1/1 epoch (loss 1.5579):  29%|██▉       | 450/1563 [13:31<36:24,  1.96s/it]
Training 1/1 epoch (loss 1.7021):  29%|██▉       | 450/1563 [13:33<36:24,  1.96s/it]
Training 1/1 epoch (loss 1.7021):  29%|██▉       | 451/1563 [13:33<36:24,  1.96s/it]
Training 1/1 epoch (loss 1.6070):  29%|██▉       | 451/1563 [13:35<36:24,  1.96s/it]
Training 1/1 epoch (loss 1.6070):  29%|██▉       | 452/1563 [13:35<36:48,  1.99s/it]
Training 1/1 epoch (loss 1.7773):  29%|██▉       | 452/1563 [13:37<36:48,  1.99s/it]
Training 1/1 epoch (loss 1.7773):  29%|██▉       | 453/1563 [13:37<37:20,  2.02s/it]
Training 1/1 epoch (loss 1.6552):  29%|██▉       | 453/1563 [13:39<37:20,  2.02s/it]
Training 1/1 epoch (loss 1.6552):  29%|██▉       | 454/1563 [13:39<34:29,  1.87s/it]
Training 1/1 epoch (loss 1.6731):  29%|██▉       | 454/1563 [13:40<34:29,  1.87s/it]
Training 1/1 epoch (loss 1.6731):  29%|██▉       | 455/1563 [13:40<34:00,  1.84s/it]
Training 1/1 epoch (loss 1.6809):  29%|██▉       | 455/1563 [13:42<34:00,  1.84s/it]
Training 1/1 epoch (loss 1.6809):  29%|██▉       | 456/1563 [13:42<31:59,  1.73s/it]
Training 1/1 epoch (loss 1.7290):  29%|██▉       | 456/1563 [13:44<31:59,  1.73s/it]
Training 1/1 epoch (loss 1.7290):  29%|██▉       | 457/1563 [13:44<32:15,  1.75s/it]
Training 1/1 epoch (loss 1.6374):  29%|██▉       | 457/1563 [13:46<32:15,  1.75s/it]
Training 1/1 epoch (loss 1.6374):  29%|██▉       | 458/1563 [13:46<33:43,  1.83s/it]
Training 1/1 epoch (loss 1.6059):  29%|██▉       | 458/1563 [13:48<33:43,  1.83s/it]
Training 1/1 epoch (loss 1.6059):  29%|██▉       | 459/1563 [13:48<34:20,  1.87s/it]
Training 1/1 epoch (loss 1.6880):  29%|██▉       | 459/1563 [13:50<34:20,  1.87s/it]
Training 1/1 epoch (loss 1.6880):  29%|██▉       | 460/1563 [13:50<36:48,  2.00s/it]
Training 1/1 epoch (loss 1.6848):  29%|██▉       | 460/1563 [13:52<36:48,  2.00s/it]
Training 1/1 epoch (loss 1.6848):  29%|██▉       | 461/1563 [13:52<35:45,  1.95s/it]
Training 1/1 epoch (loss 1.6991):  29%|██▉       | 461/1563 [13:53<35:45,  1.95s/it]
Training 1/1 epoch (loss 1.6991):  30%|██▉       | 462/1563 [13:53<33:53,  1.85s/it]
Training 1/1 epoch (loss 1.5997):  30%|██▉       | 462/1563 [13:55<33:53,  1.85s/it]
Training 1/1 epoch (loss 1.5997):  30%|██▉       | 463/1563 [13:55<33:21,  1.82s/it]
Training 1/1 epoch (loss 1.6830):  30%|██▉       | 463/1563 [13:57<33:21,  1.82s/it]
Training 1/1 epoch (loss 1.6830):  30%|██▉       | 464/1563 [13:57<32:36,  1.78s/it]
Training 1/1 epoch (loss 1.7197):  30%|██▉       | 464/1563 [13:58<32:36,  1.78s/it]
Training 1/1 epoch (loss 1.7197):  30%|██▉       | 465/1563 [13:58<30:53,  1.69s/it]
Training 1/1 epoch (loss 1.5927):  30%|██▉       | 465/1563 [14:00<30:53,  1.69s/it]
Training 1/1 epoch (loss 1.5927):  30%|██▉       | 466/1563 [14:00<30:35,  1.67s/it]
Training 1/1 epoch (loss 1.5880):  30%|██▉       | 466/1563 [14:01<30:35,  1.67s/it]
Training 1/1 epoch (loss 1.5880):  30%|██▉       | 467/1563 [14:01<28:31,  1.56s/it]
Training 1/1 epoch (loss 1.7718):  30%|██▉       | 467/1563 [14:03<28:31,  1.56s/it]
Training 1/1 epoch (loss 1.7718):  30%|██▉       | 468/1563 [14:03<30:07,  1.65s/it]
Training 1/1 epoch (loss 1.6699):  30%|██▉       | 468/1563 [14:04<30:07,  1.65s/it]
Training 1/1 epoch (loss 1.6699):  30%|███       | 469/1563 [14:04<25:47,  1.41s/it]
Training 1/1 epoch (loss 1.6754):  30%|███       | 469/1563 [14:06<25:47,  1.41s/it]
Training 1/1 epoch (loss 1.6754):  30%|███       | 470/1563 [14:06<31:09,  1.71s/it]
Training 1/1 epoch (loss 1.7443):  30%|███       | 470/1563 [14:08<31:09,  1.71s/it]
Training 1/1 epoch (loss 1.7443):  30%|███       | 471/1563 [14:08<29:43,  1.63s/it]
Training 1/1 epoch (loss 1.5825):  30%|███       | 471/1563 [14:10<29:43,  1.63s/it]
Training 1/1 epoch (loss 1.5825):  30%|███       | 472/1563 [14:10<31:30,  1.73s/it]
Training 1/1 epoch (loss 1.7168):  30%|███       | 472/1563 [14:11<31:30,  1.73s/it]
Training 1/1 epoch (loss 1.7168):  30%|███       | 473/1563 [14:11<31:00,  1.71s/it]
Training 1/1 epoch (loss 1.6823):  30%|███       | 473/1563 [14:13<31:00,  1.71s/it]
Training 1/1 epoch (loss 1.6823):  30%|███       | 474/1563 [14:13<31:38,  1.74s/it]
Training 1/1 epoch (loss 1.7014):  30%|███       | 474/1563 [14:15<31:38,  1.74s/it]
Training 1/1 epoch (loss 1.7014):  30%|███       | 475/1563 [14:15<29:27,  1.62s/it]
Training 1/1 epoch (loss 1.7314):  30%|███       | 475/1563 [14:16<29:27,  1.62s/it]
Training 1/1 epoch (loss 1.7314):  30%|███       | 476/1563 [14:16<29:37,  1.63s/it]
Training 1/1 epoch (loss 1.6391):  30%|███       | 476/1563 [14:19<29:37,  1.63s/it]
Training 1/1 epoch (loss 1.6391):  31%|███       | 477/1563 [14:19<33:12,  1.83s/it]
Training 1/1 epoch (loss 1.6254):  31%|███       | 477/1563 [14:20<33:12,  1.83s/it]
Training 1/1 epoch (loss 1.6254):  31%|███       | 478/1563 [14:20<32:45,  1.81s/it]
Training 1/1 epoch (loss 1.7122):  31%|███       | 478/1563 [14:22<32:45,  1.81s/it]
Training 1/1 epoch (loss 1.7122):  31%|███       | 479/1563 [14:22<34:03,  1.89s/it]
Training 1/1 epoch (loss 1.6309):  31%|███       | 479/1563 [14:24<34:03,  1.89s/it]
Training 1/1 epoch (loss 1.6309):  31%|███       | 480/1563 [14:24<34:58,  1.94s/it]
Training 1/1 epoch (loss 1.6302):  31%|███       | 480/1563 [14:26<34:58,  1.94s/it]
Training 1/1 epoch (loss 1.6302):  31%|███       | 481/1563 [14:26<34:44,  1.93s/it]
Training 1/1 epoch (loss 1.7502):  31%|███       | 481/1563 [14:27<34:44,  1.93s/it]
Training 1/1 epoch (loss 1.7502):  31%|███       | 482/1563 [14:27<29:12,  1.62s/it]
Training 1/1 epoch (loss 1.6015):  31%|███       | 482/1563 [14:29<29:12,  1.62s/it]
Training 1/1 epoch (loss 1.6015):  31%|███       | 483/1563 [14:29<31:23,  1.74s/it]
Training 1/1 epoch (loss 1.6475):  31%|███       | 483/1563 [14:31<31:23,  1.74s/it]
Training 1/1 epoch (loss 1.6475):  31%|███       | 484/1563 [14:31<30:36,  1.70s/it]
Training 1/1 epoch (loss 1.6904):  31%|███       | 484/1563 [14:33<30:36,  1.70s/it]
Training 1/1 epoch (loss 1.6904):  31%|███       | 485/1563 [14:33<31:07,  1.73s/it]
Training 1/1 epoch (loss 1.7105):  31%|███       | 485/1563 [14:35<31:07,  1.73s/it]
Training 1/1 epoch (loss 1.7105):  31%|███       | 486/1563 [14:35<34:36,  1.93s/it]
Training 1/1 epoch (loss 1.7278):  31%|███       | 486/1563 [14:37<34:36,  1.93s/it]
Training 1/1 epoch (loss 1.7278):  31%|███       | 487/1563 [14:37<33:36,  1.87s/it]
Training 1/1 epoch (loss 1.7290):  31%|███       | 487/1563 [14:39<33:36,  1.87s/it]
Training 1/1 epoch (loss 1.7290):  31%|███       | 488/1563 [14:39<34:48,  1.94s/it]
Training 1/1 epoch (loss 1.5687):  31%|███       | 488/1563 [14:41<34:48,  1.94s/it]
Training 1/1 epoch (loss 1.5687):  31%|███▏      | 489/1563 [14:41<34:45,  1.94s/it]
Training 1/1 epoch (loss 1.6622):  31%|███▏      | 489/1563 [14:42<34:45,  1.94s/it]
Training 1/1 epoch (loss 1.6622):  31%|███▏      | 490/1563 [14:42<31:40,  1.77s/it]
Training 1/1 epoch (loss 1.6398):  31%|███▏      | 490/1563 [14:44<31:40,  1.77s/it]
Training 1/1 epoch (loss 1.6398):  31%|███▏      | 491/1563 [14:44<32:57,  1.84s/it]
Training 1/1 epoch (loss 1.6745):  31%|███▏      | 491/1563 [14:46<32:57,  1.84s/it]
Training 1/1 epoch (loss 1.6745):  31%|███▏      | 492/1563 [14:46<32:31,  1.82s/it]
Training 1/1 epoch (loss 1.5738):  31%|███▏      | 492/1563 [14:47<32:31,  1.82s/it]
Training 1/1 epoch (loss 1.5738):  32%|███▏      | 493/1563 [14:47<29:22,  1.65s/it]
Training 1/1 epoch (loss 1.6404):  32%|███▏      | 493/1563 [14:49<29:22,  1.65s/it]
Training 1/1 epoch (loss 1.6404):  32%|███▏      | 494/1563 [14:49<29:22,  1.65s/it]
Training 1/1 epoch (loss 1.6904):  32%|███▏      | 494/1563 [14:50<29:22,  1.65s/it]
Training 1/1 epoch (loss 1.6904):  32%|███▏      | 495/1563 [14:50<29:01,  1.63s/it]
Training 1/1 epoch (loss 1.7043):  32%|███▏      | 495/1563 [14:53<29:01,  1.63s/it]
Training 1/1 epoch (loss 1.7043):  32%|███▏      | 496/1563 [14:53<33:52,  1.90s/it]
Training 1/1 epoch (loss 1.6117):  32%|███▏      | 496/1563 [14:55<33:52,  1.90s/it]
Training 1/1 epoch (loss 1.6117):  32%|███▏      | 497/1563 [14:55<33:41,  1.90s/it]
Training 1/1 epoch (loss 1.7268):  32%|███▏      | 497/1563 [14:56<33:41,  1.90s/it]
Training 1/1 epoch (loss 1.7268):  32%|███▏      | 498/1563 [14:56<31:00,  1.75s/it]
Training 1/1 epoch (loss 1.6703):  32%|███▏      | 498/1563 [14:58<31:00,  1.75s/it]
Training 1/1 epoch (loss 1.6703):  32%|███▏      | 499/1563 [14:58<30:45,  1.73s/it]
Training 1/1 epoch (loss 1.6517):  32%|███▏      | 499/1563 [14:59<30:45,  1.73s/it]
Training 1/1 epoch (loss 1.6517):  32%|███▏      | 500/1563 [14:59<27:53,  1.57s/it]
Training 1/1 epoch (loss 1.7144):  32%|███▏      | 500/1563 [15:02<27:53,  1.57s/it]
Training 1/1 epoch (loss 1.7144):  32%|███▏      | 501/1563 [15:02<32:06,  1.81s/it]
Training 1/1 epoch (loss 1.6774):  32%|███▏      | 501/1563 [15:03<32:06,  1.81s/it]
Training 1/1 epoch (loss 1.6774):  32%|███▏      | 502/1563 [15:03<31:45,  1.80s/it]
Training 1/1 epoch (loss 1.7676):  32%|███▏      | 502/1563 [15:05<31:45,  1.80s/it]
Training 1/1 epoch (loss 1.7676):  32%|███▏      | 503/1563 [15:05<32:30,  1.84s/it]
Training 1/1 epoch (loss 1.5886):  32%|███▏      | 503/1563 [15:08<32:30,  1.84s/it]
Training 1/1 epoch (loss 1.5886):  32%|███▏      | 504/1563 [15:08<35:42,  2.02s/it]
Training 1/1 epoch (loss 1.6707):  32%|███▏      | 504/1563 [15:09<35:42,  2.02s/it]
Training 1/1 epoch (loss 1.6707):  32%|███▏      | 505/1563 [15:09<32:49,  1.86s/it]
Training 1/1 epoch (loss 1.6898):  32%|███▏      | 505/1563 [15:11<32:49,  1.86s/it]
Training 1/1 epoch (loss 1.6898):  32%|███▏      | 506/1563 [15:11<31:35,  1.79s/it]
Training 1/1 epoch (loss 1.6758):  32%|███▏      | 506/1563 [15:13<31:35,  1.79s/it]
Training 1/1 epoch (loss 1.6758):  32%|███▏      | 507/1563 [15:13<31:08,  1.77s/it]
Training 1/1 epoch (loss 1.6800):  32%|███▏      | 507/1563 [15:15<31:08,  1.77s/it]
Training 1/1 epoch (loss 1.6800):  33%|███▎      | 508/1563 [15:15<32:20,  1.84s/it]
Training 1/1 epoch (loss 1.6402):  33%|███▎      | 508/1563 [15:16<32:20,  1.84s/it]
Training 1/1 epoch (loss 1.6402):  33%|███▎      | 509/1563 [15:16<29:46,  1.69s/it]
Training 1/1 epoch (loss 1.7250):  33%|███▎      | 509/1563 [15:18<29:46,  1.69s/it]
Training 1/1 epoch (loss 1.7250):  33%|███▎      | 510/1563 [15:18<34:03,  1.94s/it]
Training 1/1 epoch (loss 1.5475):  33%|███▎      | 510/1563 [15:20<34:03,  1.94s/it]
Training 1/1 epoch (loss 1.5475):  33%|███▎      | 511/1563 [15:20<32:41,  1.86s/it]
Training 1/1 epoch (loss 1.6717):  33%|███▎      | 511/1563 [15:23<32:41,  1.86s/it]
Training 1/1 epoch (loss 1.6717):  33%|███▎      | 512/1563 [15:23<37:17,  2.13s/it]
Training 1/1 epoch (loss 1.6228):  33%|███▎      | 512/1563 [15:25<37:17,  2.13s/it]
Training 1/1 epoch (loss 1.6228):  33%|███▎      | 513/1563 [15:25<34:45,  1.99s/it]
Training 1/1 epoch (loss 1.7268):  33%|███▎      | 513/1563 [15:26<34:45,  1.99s/it]
Training 1/1 epoch (loss 1.7268):  33%|███▎      | 514/1563 [15:26<31:49,  1.82s/it]
Training 1/1 epoch (loss 1.7089):  33%|███▎      | 514/1563 [15:27<31:49,  1.82s/it]
Training 1/1 epoch (loss 1.7089):  33%|███▎      | 515/1563 [15:27<29:14,  1.67s/it]
Training 1/1 epoch (loss 1.7020):  33%|███▎      | 515/1563 [15:29<29:14,  1.67s/it]
Training 1/1 epoch (loss 1.7020):  33%|███▎      | 516/1563 [15:29<27:15,  1.56s/it]
Training 1/1 epoch (loss 1.6322):  33%|███▎      | 516/1563 [15:30<27:15,  1.56s/it]
Training 1/1 epoch (loss 1.6322):  33%|███▎      | 517/1563 [15:30<27:01,  1.55s/it]
Training 1/1 epoch (loss 1.5772):  33%|███▎      | 517/1563 [15:32<27:01,  1.55s/it]
Training 1/1 epoch (loss 1.5772):  33%|███▎      | 518/1563 [15:32<29:53,  1.72s/it]
Training 1/1 epoch (loss 1.4700):  33%|███▎      | 518/1563 [15:34<29:53,  1.72s/it]
Training 1/1 epoch (loss 1.4700):  33%|███▎      | 519/1563 [15:34<31:40,  1.82s/it]
Training 1/1 epoch (loss 1.5929):  33%|███▎      | 519/1563 [15:36<31:40,  1.82s/it]
Training 1/1 epoch (loss 1.5929):  33%|███▎      | 520/1563 [15:36<28:49,  1.66s/it]
Training 1/1 epoch (loss 1.7207):  33%|███▎      | 520/1563 [15:37<28:49,  1.66s/it]
Training 1/1 epoch (loss 1.7207):  33%|███▎      | 521/1563 [15:37<29:23,  1.69s/it]
Training 1/1 epoch (loss 1.6859):  33%|███▎      | 521/1563 [15:39<29:23,  1.69s/it]
Training 1/1 epoch (loss 1.6859):  33%|███▎      | 522/1563 [15:39<27:24,  1.58s/it]
Training 1/1 epoch (loss 1.6897):  33%|███▎      | 522/1563 [15:41<27:24,  1.58s/it]
Training 1/1 epoch (loss 1.6897):  33%|███▎      | 523/1563 [15:41<29:29,  1.70s/it]
Training 1/1 epoch (loss 1.6348):  33%|███▎      | 523/1563 [15:42<29:29,  1.70s/it]
Training 1/1 epoch (loss 1.6348):  34%|███▎      | 524/1563 [15:42<27:35,  1.59s/it]
Training 1/1 epoch (loss 1.6418):  34%|███▎      | 524/1563 [15:44<27:35,  1.59s/it]
Training 1/1 epoch (loss 1.6418):  34%|███▎      | 525/1563 [15:44<31:39,  1.83s/it]
Training 1/1 epoch (loss 1.6402):  34%|███▎      | 525/1563 [15:47<31:39,  1.83s/it]
Training 1/1 epoch (loss 1.6402):  34%|███▎      | 526/1563 [15:47<34:08,  1.97s/it]
Training 1/1 epoch (loss 1.6180):  34%|███▎      | 526/1563 [15:48<34:08,  1.97s/it]
Training 1/1 epoch (loss 1.6180):  34%|███▎      | 527/1563 [15:48<32:52,  1.90s/it]
Training 1/1 epoch (loss 1.7272):  34%|███▎      | 527/1563 [15:50<32:52,  1.90s/it]
Training 1/1 epoch (loss 1.7272):  34%|███▍      | 528/1563 [15:50<31:36,  1.83s/it]
Training 1/1 epoch (loss 1.7581):  34%|███▍      | 528/1563 [15:51<31:36,  1.83s/it]
Training 1/1 epoch (loss 1.7581):  34%|███▍      | 529/1563 [15:51<28:54,  1.68s/it]
Training 1/1 epoch (loss 1.6197):  34%|███▍      | 529/1563 [15:53<28:54,  1.68s/it]
Training 1/1 epoch (loss 1.6197):  34%|███▍      | 530/1563 [15:53<30:11,  1.75s/it]
Training 1/1 epoch (loss 1.6270):  34%|███▍      | 530/1563 [15:55<30:11,  1.75s/it]
Training 1/1 epoch (loss 1.6270):  34%|███▍      | 531/1563 [15:55<29:14,  1.70s/it]
Training 1/1 epoch (loss 1.6287):  34%|███▍      | 531/1563 [15:57<29:14,  1.70s/it]
Training 1/1 epoch (loss 1.6287):  34%|███▍      | 532/1563 [15:57<33:19,  1.94s/it]
Training 1/1 epoch (loss 1.6336):  34%|███▍      | 532/1563 [15:59<33:19,  1.94s/it]
Training 1/1 epoch (loss 1.6336):  34%|███▍      | 533/1563 [15:59<33:18,  1.94s/it]
Training 1/1 epoch (loss 1.6294):  34%|███▍      | 533/1563 [16:01<33:18,  1.94s/it]
Training 1/1 epoch (loss 1.6294):  34%|███▍      | 534/1563 [16:01<30:13,  1.76s/it]
Training 1/1 epoch (loss 1.5874):  34%|███▍      | 534/1563 [16:02<30:13,  1.76s/it]
Training 1/1 epoch (loss 1.5874):  34%|███▍      | 535/1563 [16:02<28:42,  1.68s/it]
Training 1/1 epoch (loss 1.7184):  34%|███▍      | 535/1563 [16:04<28:42,  1.68s/it]
Training 1/1 epoch (loss 1.7184):  34%|███▍      | 536/1563 [16:04<29:44,  1.74s/it]
Training 1/1 epoch (loss 1.6159):  34%|███▍      | 536/1563 [16:06<29:44,  1.74s/it]
Training 1/1 epoch (loss 1.6159):  34%|███▍      | 537/1563 [16:06<30:34,  1.79s/it]
Training 1/1 epoch (loss 1.6185):  34%|███▍      | 537/1563 [16:08<30:34,  1.79s/it]
Training 1/1 epoch (loss 1.6185):  34%|███▍      | 538/1563 [16:08<29:25,  1.72s/it]
Training 1/1 epoch (loss 1.6777):  34%|███▍      | 538/1563 [16:09<29:25,  1.72s/it]
Training 1/1 epoch (loss 1.6777):  34%|███▍      | 539/1563 [16:09<28:52,  1.69s/it]
Training 1/1 epoch (loss 1.6430):  34%|███▍      | 539/1563 [16:10<28:52,  1.69s/it]
Training 1/1 epoch (loss 1.6430):  35%|███▍      | 540/1563 [16:10<27:09,  1.59s/it]
Training 1/1 epoch (loss 1.6507):  35%|███▍      | 540/1563 [16:13<27:09,  1.59s/it]
Training 1/1 epoch (loss 1.6507):  35%|███▍      | 541/1563 [16:13<30:59,  1.82s/it]
Training 1/1 epoch (loss 1.6875):  35%|███▍      | 541/1563 [16:15<30:59,  1.82s/it]
Training 1/1 epoch (loss 1.6875):  35%|███▍      | 542/1563 [16:15<30:18,  1.78s/it]
Training 1/1 epoch (loss 1.6306):  35%|███▍      | 542/1563 [16:16<30:18,  1.78s/it]
Training 1/1 epoch (loss 1.6306):  35%|███▍      | 543/1563 [16:16<27:44,  1.63s/it]
Training 1/1 epoch (loss 1.5474):  35%|███▍      | 543/1563 [16:18<27:44,  1.63s/it]
Training 1/1 epoch (loss 1.5474):  35%|███▍      | 544/1563 [16:18<28:59,  1.71s/it]
Training 1/1 epoch (loss 1.6066):  35%|███▍      | 544/1563 [16:20<28:59,  1.71s/it]
Training 1/1 epoch (loss 1.6066):  35%|███▍      | 545/1563 [16:20<31:56,  1.88s/it]
Training 1/1 epoch (loss 1.6449):  35%|███▍      | 545/1563 [16:22<31:56,  1.88s/it]
Training 1/1 epoch (loss 1.6449):  35%|███▍      | 546/1563 [16:22<31:04,  1.83s/it]
Training 1/1 epoch (loss 1.7802):  35%|███▍      | 546/1563 [16:23<31:04,  1.83s/it]
Training 1/1 epoch (loss 1.7802):  35%|███▍      | 547/1563 [16:23<29:49,  1.76s/it]
Training 1/1 epoch (loss 1.6464):  35%|███▍      | 547/1563 [16:24<29:49,  1.76s/it]
Training 1/1 epoch (loss 1.6464):  35%|███▌      | 548/1563 [16:24<25:33,  1.51s/it]
Training 1/1 epoch (loss 1.6260):  35%|███▌      | 548/1563 [16:26<25:33,  1.51s/it]
Training 1/1 epoch (loss 1.6260):  35%|███▌      | 549/1563 [16:26<28:39,  1.70s/it]
Training 1/1 epoch (loss 1.6696):  35%|███▌      | 549/1563 [16:28<28:39,  1.70s/it]
Training 1/1 epoch (loss 1.6696):  35%|███▌      | 550/1563 [16:28<28:51,  1.71s/it]
Training 1/1 epoch (loss 1.6346):  35%|███▌      | 550/1563 [16:30<28:51,  1.71s/it]
Training 1/1 epoch (loss 1.6346):  35%|███▌      | 551/1563 [16:30<30:07,  1.79s/it]
Training 1/1 epoch (loss 1.7106):  35%|███▌      | 551/1563 [16:32<30:07,  1.79s/it]
Training 1/1 epoch (loss 1.7106):  35%|███▌      | 552/1563 [16:32<29:16,  1.74s/it]
Training 1/1 epoch (loss 1.7382):  35%|███▌      | 552/1563 [16:33<29:16,  1.74s/it]
Training 1/1 epoch (loss 1.7382):  35%|███▌      | 553/1563 [16:33<29:30,  1.75s/it]
Training 1/1 epoch (loss 1.7441):  35%|███▌      | 553/1563 [16:35<29:30,  1.75s/it]
Training 1/1 epoch (loss 1.7441):  35%|███▌      | 554/1563 [16:35<30:12,  1.80s/it]
Training 1/1 epoch (loss 1.7252):  35%|███▌      | 554/1563 [16:37<30:12,  1.80s/it]
Training 1/1 epoch (loss 1.7252):  36%|███▌      | 555/1563 [16:37<29:23,  1.75s/it]
Training 1/1 epoch (loss 1.7044):  36%|███▌      | 555/1563 [16:38<29:23,  1.75s/it]
Training 1/1 epoch (loss 1.7044):  36%|███▌      | 556/1563 [16:38<27:11,  1.62s/it]
Training 1/1 epoch (loss 1.6913):  36%|███▌      | 556/1563 [16:41<27:11,  1.62s/it]
Training 1/1 epoch (loss 1.6913):  36%|███▌      | 557/1563 [16:41<30:55,  1.84s/it]
Training 1/1 epoch (loss 1.7591):  36%|███▌      | 557/1563 [16:42<30:55,  1.84s/it]
Training 1/1 epoch (loss 1.7591):  36%|███▌      | 558/1563 [16:42<29:02,  1.73s/it]
Training 1/1 epoch (loss 1.6993):  36%|███▌      | 558/1563 [16:45<29:02,  1.73s/it]
Training 1/1 epoch (loss 1.6993):  36%|███▌      | 559/1563 [16:45<32:12,  1.92s/it]
Training 1/1 epoch (loss 1.6400):  36%|███▌      | 559/1563 [16:47<32:12,  1.92s/it]
Training 1/1 epoch (loss 1.6400):  36%|███▌      | 560/1563 [16:47<33:17,  1.99s/it]
Training 1/1 epoch (loss 1.7200):  36%|███▌      | 560/1563 [16:49<33:17,  1.99s/it]
Training 1/1 epoch (loss 1.7200):  36%|███▌      | 561/1563 [16:49<32:34,  1.95s/it]
Training 1/1 epoch (loss 1.6664):  36%|███▌      | 561/1563 [16:50<32:34,  1.95s/it]
Training 1/1 epoch (loss 1.6664):  36%|███▌      | 562/1563 [16:50<30:43,  1.84s/it]
Training 1/1 epoch (loss 1.6705):  36%|███▌      | 562/1563 [16:51<30:43,  1.84s/it]
Training 1/1 epoch (loss 1.6705):  36%|███▌      | 563/1563 [16:51<25:33,  1.53s/it]
Training 1/1 epoch (loss 1.6435):  36%|███▌      | 563/1563 [16:52<25:33,  1.53s/it]
Training 1/1 epoch (loss 1.6435):  36%|███▌      | 564/1563 [16:52<23:30,  1.41s/it]
Training 1/1 epoch (loss 1.5745):  36%|███▌      | 564/1563 [16:54<23:30,  1.41s/it]
Training 1/1 epoch (loss 1.5745):  36%|███▌      | 565/1563 [16:54<26:26,  1.59s/it]
Training 1/1 epoch (loss 1.6493):  36%|███▌      | 565/1563 [16:56<26:26,  1.59s/it]
Training 1/1 epoch (loss 1.6493):  36%|███▌      | 566/1563 [16:56<25:41,  1.55s/it]
Training 1/1 epoch (loss 1.7000):  36%|███▌      | 566/1563 [16:57<25:41,  1.55s/it]
Training 1/1 epoch (loss 1.7000):  36%|███▋      | 567/1563 [16:57<25:38,  1.54s/it]
Training 1/1 epoch (loss 1.6056):  36%|███▋      | 567/1563 [16:58<25:38,  1.54s/it]
Training 1/1 epoch (loss 1.6056):  36%|███▋      | 568/1563 [16:58<24:43,  1.49s/it]
Training 1/1 epoch (loss 1.5927):  36%|███▋      | 568/1563 [17:00<24:43,  1.49s/it]
Training 1/1 epoch (loss 1.5927):  36%|███▋      | 569/1563 [17:00<26:32,  1.60s/it]
Training 1/1 epoch (loss 1.6927):  36%|███▋      | 569/1563 [17:02<26:32,  1.60s/it]
Training 1/1 epoch (loss 1.6927):  36%|███▋      | 570/1563 [17:02<27:12,  1.64s/it]
Training 1/1 epoch (loss 1.5356):  36%|███▋      | 570/1563 [17:03<27:12,  1.64s/it]
Training 1/1 epoch (loss 1.5356):  37%|███▋      | 571/1563 [17:03<23:29,  1.42s/it]
Training 1/1 epoch (loss 1.6514):  37%|███▋      | 571/1563 [17:04<23:29,  1.42s/it]
Training 1/1 epoch (loss 1.6514):  37%|███▋      | 572/1563 [17:04<23:49,  1.44s/it]
Training 1/1 epoch (loss 1.6676):  37%|███▋      | 572/1563 [17:07<23:49,  1.44s/it]
Training 1/1 epoch (loss 1.6676):  37%|███▋      | 573/1563 [17:07<28:37,  1.73s/it]
Training 1/1 epoch (loss 1.5659):  37%|███▋      | 573/1563 [17:08<28:37,  1.73s/it]
Training 1/1 epoch (loss 1.5659):  37%|███▋      | 574/1563 [17:08<27:53,  1.69s/it]
Training 1/1 epoch (loss 1.7238):  37%|███▋      | 574/1563 [17:10<27:53,  1.69s/it]
Training 1/1 epoch (loss 1.7238):  37%|███▋      | 575/1563 [17:10<28:06,  1.71s/it]
Training 1/1 epoch (loss 1.6032):  37%|███▋      | 575/1563 [17:12<28:06,  1.71s/it]
Training 1/1 epoch (loss 1.6032):  37%|███▋      | 576/1563 [17:12<27:00,  1.64s/it]
Training 1/1 epoch (loss 1.4503):  37%|███▋      | 576/1563 [17:14<27:00,  1.64s/it]
Training 1/1 epoch (loss 1.4503):  37%|███▋      | 577/1563 [17:14<28:46,  1.75s/it]
Training 1/1 epoch (loss 1.6514):  37%|███▋      | 577/1563 [17:15<28:46,  1.75s/it]
Training 1/1 epoch (loss 1.6514):  37%|███▋      | 578/1563 [17:15<29:00,  1.77s/it]
Training 1/1 epoch (loss 1.5911):  37%|███▋      | 578/1563 [17:17<29:00,  1.77s/it]
Training 1/1 epoch (loss 1.5911):  37%|███▋      | 579/1563 [17:17<27:54,  1.70s/it]
Training 1/1 epoch (loss 1.6169):  37%|███▋      | 579/1563 [17:19<27:54,  1.70s/it]
Training 1/1 epoch (loss 1.6169):  37%|███▋      | 580/1563 [17:19<26:46,  1.63s/it]
Training 1/1 epoch (loss 1.6920):  37%|███▋      | 580/1563 [17:20<26:46,  1.63s/it]
Training 1/1 epoch (loss 1.6920):  37%|███▋      | 581/1563 [17:20<24:16,  1.48s/it]
Training 1/1 epoch (loss 1.7449):  37%|███▋      | 581/1563 [17:22<24:16,  1.48s/it]
Training 1/1 epoch (loss 1.7449):  37%|███▋      | 582/1563 [17:22<28:16,  1.73s/it]
Training 1/1 epoch (loss 1.6263):  37%|███▋      | 582/1563 [17:23<28:16,  1.73s/it]
Training 1/1 epoch (loss 1.6263):  37%|███▋      | 583/1563 [17:23<27:18,  1.67s/it]
Training 1/1 epoch (loss 1.7575):  37%|███▋      | 583/1563 [17:25<27:18,  1.67s/it]
Training 1/1 epoch (loss 1.7575):  37%|███▋      | 584/1563 [17:25<27:01,  1.66s/it]
Training 1/1 epoch (loss 1.6094):  37%|███▋      | 584/1563 [17:27<27:01,  1.66s/it]
Training 1/1 epoch (loss 1.6094):  37%|███▋      | 585/1563 [17:27<27:44,  1.70s/it]
Training 1/1 epoch (loss 1.6487):  37%|███▋      | 585/1563 [17:29<27:44,  1.70s/it]
Training 1/1 epoch (loss 1.6487):  37%|███▋      | 586/1563 [17:29<28:32,  1.75s/it]
Training 1/1 epoch (loss 1.6612):  37%|███▋      | 586/1563 [17:30<28:32,  1.75s/it]
Training 1/1 epoch (loss 1.6612):  38%|███▊      | 587/1563 [17:30<25:36,  1.57s/it]
Training 1/1 epoch (loss 1.7406):  38%|███▊      | 587/1563 [17:32<25:36,  1.57s/it]
Training 1/1 epoch (loss 1.7406):  38%|███▊      | 588/1563 [17:32<28:29,  1.75s/it]
Training 1/1 epoch (loss 1.6478):  38%|███▊      | 588/1563 [17:33<28:29,  1.75s/it]
Training 1/1 epoch (loss 1.6478):  38%|███▊      | 589/1563 [17:33<25:53,  1.59s/it]
Training 1/1 epoch (loss 1.6431):  38%|███▊      | 589/1563 [17:35<25:53,  1.59s/it]
Training 1/1 epoch (loss 1.6431):  38%|███▊      | 590/1563 [17:35<26:41,  1.65s/it]
Training 1/1 epoch (loss 1.6039):  38%|███▊      | 590/1563 [17:37<26:41,  1.65s/it]
Training 1/1 epoch (loss 1.6039):  38%|███▊      | 591/1563 [17:37<26:31,  1.64s/it]
Training 1/1 epoch (loss 1.5788):  38%|███▊      | 591/1563 [17:39<26:31,  1.64s/it]
Training 1/1 epoch (loss 1.5788):  38%|███▊      | 592/1563 [17:39<29:05,  1.80s/it]
Training 1/1 epoch (loss 1.6024):  38%|███▊      | 592/1563 [17:40<29:05,  1.80s/it]
Training 1/1 epoch (loss 1.6024):  38%|███▊      | 593/1563 [17:40<25:14,  1.56s/it]
Training 1/1 epoch (loss 1.6676):  38%|███▊      | 593/1563 [17:42<25:14,  1.56s/it]
Training 1/1 epoch (loss 1.6676):  38%|███▊      | 594/1563 [17:42<26:48,  1.66s/it]
Training 1/1 epoch (loss 1.7127):  38%|███▊      | 594/1563 [17:44<26:48,  1.66s/it]
Training 1/1 epoch (loss 1.7127):  38%|███▊      | 595/1563 [17:44<27:18,  1.69s/it]
Training 1/1 epoch (loss 1.7681):  38%|███▊      | 595/1563 [17:44<27:18,  1.69s/it]
Training 1/1 epoch (loss 1.7681):  38%|███▊      | 596/1563 [17:44<23:02,  1.43s/it]
Training 1/1 epoch (loss 1.6559):  38%|███▊      | 596/1563 [17:45<23:02,  1.43s/it]
Training 1/1 epoch (loss 1.6559):  38%|███▊      | 597/1563 [17:45<19:58,  1.24s/it]
Training 1/1 epoch (loss 1.7627):  38%|███▊      | 597/1563 [17:47<19:58,  1.24s/it]
Training 1/1 epoch (loss 1.7627):  38%|███▊      | 598/1563 [17:47<22:54,  1.42s/it]
Training 1/1 epoch (loss 1.6391):  38%|███▊      | 598/1563 [17:49<22:54,  1.42s/it]
Training 1/1 epoch (loss 1.6391):  38%|███▊      | 599/1563 [17:49<25:54,  1.61s/it]
Training 1/1 epoch (loss 1.7545):  38%|███▊      | 599/1563 [17:51<25:54,  1.61s/it]
Training 1/1 epoch (loss 1.7545):  38%|███▊      | 600/1563 [17:51<28:51,  1.80s/it]
Training 1/1 epoch (loss 1.6787):  38%|███▊      | 600/1563 [17:52<28:51,  1.80s/it]
Training 1/1 epoch (loss 1.6787):  38%|███▊      | 601/1563 [17:52<24:45,  1.54s/it]
Training 1/1 epoch (loss 1.6840):  38%|███▊      | 601/1563 [17:53<24:45,  1.54s/it]
Training 1/1 epoch (loss 1.6840):  39%|███▊      | 602/1563 [17:53<22:43,  1.42s/it]
Training 1/1 epoch (loss 1.6116):  39%|███▊      | 602/1563 [17:56<22:43,  1.42s/it]
Training 1/1 epoch (loss 1.6116):  39%|███▊      | 603/1563 [17:56<27:33,  1.72s/it]
Training 1/1 epoch (loss 1.5460):  39%|███▊      | 603/1563 [17:58<27:33,  1.72s/it]
Training 1/1 epoch (loss 1.5460):  39%|███▊      | 604/1563 [17:58<28:39,  1.79s/it]
Training 1/1 epoch (loss 1.6729):  39%|███▊      | 604/1563 [18:00<28:39,  1.79s/it]
Training 1/1 epoch (loss 1.6729):  39%|███▊      | 605/1563 [18:00<29:13,  1.83s/it]
Training 1/1 epoch (loss 1.6821):  39%|███▊      | 605/1563 [18:01<29:13,  1.83s/it]
Training 1/1 epoch (loss 1.6821):  39%|███▉      | 606/1563 [18:01<27:37,  1.73s/it]
Training 1/1 epoch (loss 1.5663):  39%|███▉      | 606/1563 [18:04<27:37,  1.73s/it]
Training 1/1 epoch (loss 1.5663):  39%|███▉      | 607/1563 [18:04<31:18,  1.97s/it]
Training 1/1 epoch (loss 1.5875):  39%|███▉      | 607/1563 [18:05<31:18,  1.97s/it]
Training 1/1 epoch (loss 1.5875):  39%|███▉      | 608/1563 [18:05<28:31,  1.79s/it]
Training 1/1 epoch (loss 1.6572):  39%|███▉      | 608/1563 [18:08<28:31,  1.79s/it]
Training 1/1 epoch (loss 1.6572):  39%|███▉      | 609/1563 [18:08<31:55,  2.01s/it]
Training 1/1 epoch (loss 1.6295):  39%|███▉      | 609/1563 [18:09<31:55,  2.01s/it]
Training 1/1 epoch (loss 1.6295):  39%|███▉      | 610/1563 [18:09<30:43,  1.93s/it]
Training 1/1 epoch (loss 1.7477):  39%|███▉      | 610/1563 [18:11<30:43,  1.93s/it]
Training 1/1 epoch (loss 1.7477):  39%|███▉      | 611/1563 [18:11<28:47,  1.81s/it]
Training 1/1 epoch (loss 1.6639):  39%|███▉      | 611/1563 [18:13<28:47,  1.81s/it]
Training 1/1 epoch (loss 1.6639):  39%|███▉      | 612/1563 [18:13<28:01,  1.77s/it]
Training 1/1 epoch (loss 1.6757):  39%|███▉      | 612/1563 [18:15<28:01,  1.77s/it]
Training 1/1 epoch (loss 1.6757):  39%|███▉      | 613/1563 [18:15<30:40,  1.94s/it]
Training 1/1 epoch (loss 1.6206):  39%|███▉      | 613/1563 [18:16<30:40,  1.94s/it]
Training 1/1 epoch (loss 1.6206):  39%|███▉      | 614/1563 [18:16<27:22,  1.73s/it]
Training 1/1 epoch (loss 1.6931):  39%|███▉      | 614/1563 [18:18<27:22,  1.73s/it]
Training 1/1 epoch (loss 1.6931):  39%|███▉      | 615/1563 [18:18<29:39,  1.88s/it]
Training 1/1 epoch (loss 1.6204):  39%|███▉      | 615/1563 [18:20<29:39,  1.88s/it]
Training 1/1 epoch (loss 1.6204):  39%|███▉      | 616/1563 [18:20<30:30,  1.93s/it]
Training 1/1 epoch (loss 1.7472):  39%|███▉      | 616/1563 [18:22<30:30,  1.93s/it]
Training 1/1 epoch (loss 1.7472):  39%|███▉      | 617/1563 [18:22<29:41,  1.88s/it]
Training 1/1 epoch (loss 1.5807):  39%|███▉      | 617/1563 [18:23<29:41,  1.88s/it]
Training 1/1 epoch (loss 1.5807):  40%|███▉      | 618/1563 [18:23<25:57,  1.65s/it]
Training 1/1 epoch (loss 1.7197):  40%|███▉      | 618/1563 [18:25<25:57,  1.65s/it]
Training 1/1 epoch (loss 1.7197):  40%|███▉      | 619/1563 [18:25<27:52,  1.77s/it]
Training 1/1 epoch (loss 1.6441):  40%|███▉      | 619/1563 [18:27<27:52,  1.77s/it]
Training 1/1 epoch (loss 1.6441):  40%|███▉      | 620/1563 [18:27<26:19,  1.68s/it]
Training 1/1 epoch (loss 1.6782):  40%|███▉      | 620/1563 [18:28<26:19,  1.68s/it]
Training 1/1 epoch (loss 1.6782):  40%|███▉      | 621/1563 [18:28<23:32,  1.50s/it]
Training 1/1 epoch (loss 1.6016):  40%|███▉      | 621/1563 [18:29<23:32,  1.50s/it]
Training 1/1 epoch (loss 1.6016):  40%|███▉      | 622/1563 [18:29<23:06,  1.47s/it]
Training 1/1 epoch (loss 1.5623):  40%|███▉      | 622/1563 [18:30<23:06,  1.47s/it]
Training 1/1 epoch (loss 1.5623):  40%|███▉      | 623/1563 [18:30<21:19,  1.36s/it]
Training 1/1 epoch (loss 1.6991):  40%|███▉      | 623/1563 [18:32<21:19,  1.36s/it]
Training 1/1 epoch (loss 1.6991):  40%|███▉      | 624/1563 [18:32<22:23,  1.43s/it]
Training 1/1 epoch (loss 1.5697):  40%|███▉      | 624/1563 [18:34<22:23,  1.43s/it]
Training 1/1 epoch (loss 1.5697):  40%|███▉      | 625/1563 [18:34<23:50,  1.53s/it]
Training 1/1 epoch (loss 1.7300):  40%|███▉      | 625/1563 [18:35<23:50,  1.53s/it]
Training 1/1 epoch (loss 1.7300):  40%|████      | 626/1563 [18:35<24:41,  1.58s/it]
Training 1/1 epoch (loss 1.6719):  40%|████      | 626/1563 [18:37<24:41,  1.58s/it]
Training 1/1 epoch (loss 1.6719):  40%|████      | 627/1563 [18:37<24:58,  1.60s/it]
Training 1/1 epoch (loss 1.6657):  40%|████      | 627/1563 [18:39<24:58,  1.60s/it]
Training 1/1 epoch (loss 1.6657):  40%|████      | 628/1563 [18:39<25:29,  1.64s/it]
Training 1/1 epoch (loss 1.7835):  40%|████      | 628/1563 [18:40<25:29,  1.64s/it]
Training 1/1 epoch (loss 1.7835):  40%|████      | 629/1563 [18:40<24:45,  1.59s/it]
Training 1/1 epoch (loss 1.7157):  40%|████      | 629/1563 [18:42<24:45,  1.59s/it]
Training 1/1 epoch (loss 1.7157):  40%|████      | 630/1563 [18:42<25:40,  1.65s/it]
Training 1/1 epoch (loss 1.6887):  40%|████      | 630/1563 [18:44<25:40,  1.65s/it]
Training 1/1 epoch (loss 1.6887):  40%|████      | 631/1563 [18:44<27:44,  1.79s/it]
Training 1/1 epoch (loss 1.5641):  40%|████      | 631/1563 [18:46<27:44,  1.79s/it]
Training 1/1 epoch (loss 1.5641):  40%|████      | 632/1563 [18:46<29:05,  1.87s/it]
Training 1/1 epoch (loss 1.6598):  40%|████      | 632/1563 [18:47<29:05,  1.87s/it]
Training 1/1 epoch (loss 1.6598):  40%|████      | 633/1563 [18:47<25:33,  1.65s/it]
Training 1/1 epoch (loss 1.7373):  40%|████      | 633/1563 [18:48<25:33,  1.65s/it]
Training 1/1 epoch (loss 1.7373):  41%|████      | 634/1563 [18:48<22:22,  1.45s/it]
Training 1/1 epoch (loss 1.6001):  41%|████      | 634/1563 [18:51<22:22,  1.45s/it]
Training 1/1 epoch (loss 1.6001):  41%|████      | 635/1563 [18:51<26:54,  1.74s/it]
Training 1/1 epoch (loss 1.6469):  41%|████      | 635/1563 [18:52<26:54,  1.74s/it]
Training 1/1 epoch (loss 1.6469):  41%|████      | 636/1563 [18:52<25:37,  1.66s/it]
Training 1/1 epoch (loss 1.6906):  41%|████      | 636/1563 [18:54<25:37,  1.66s/it]
Training 1/1 epoch (loss 1.6906):  41%|████      | 637/1563 [18:54<26:15,  1.70s/it]
Training 1/1 epoch (loss 1.6140):  41%|████      | 637/1563 [18:56<26:15,  1.70s/it]
Training 1/1 epoch (loss 1.6140):  41%|████      | 638/1563 [18:56<27:09,  1.76s/it]
Training 1/1 epoch (loss 1.5820):  41%|████      | 638/1563 [18:57<27:09,  1.76s/it]
Training 1/1 epoch (loss 1.5820):  41%|████      | 639/1563 [18:57<25:08,  1.63s/it]
Training 1/1 epoch (loss 1.5601):  41%|████      | 639/1563 [18:59<25:08,  1.63s/it]
Training 1/1 epoch (loss 1.5601):  41%|████      | 640/1563 [18:59<24:26,  1.59s/it]
Training 1/1 epoch (loss 1.5812):  41%|████      | 640/1563 [19:01<24:26,  1.59s/it]
Training 1/1 epoch (loss 1.5812):  41%|████      | 641/1563 [19:01<25:49,  1.68s/it]
Training 1/1 epoch (loss 1.5636):  41%|████      | 641/1563 [19:02<25:49,  1.68s/it]
Training 1/1 epoch (loss 1.5636):  41%|████      | 642/1563 [19:02<25:20,  1.65s/it]
Training 1/1 epoch (loss 1.6566):  41%|████      | 642/1563 [19:04<25:20,  1.65s/it]
Training 1/1 epoch (loss 1.6566):  41%|████      | 643/1563 [19:04<24:13,  1.58s/it]
Training 1/1 epoch (loss 1.6329):  41%|████      | 643/1563 [19:05<24:13,  1.58s/it]
Training 1/1 epoch (loss 1.6329):  41%|████      | 644/1563 [19:05<22:22,  1.46s/it]
Training 1/1 epoch (loss 1.6048):  41%|████      | 644/1563 [19:06<22:22,  1.46s/it]
Training 1/1 epoch (loss 1.6048):  41%|████▏     | 645/1563 [19:06<21:17,  1.39s/it]
Training 1/1 epoch (loss 1.6318):  41%|████▏     | 645/1563 [19:08<21:17,  1.39s/it]
Training 1/1 epoch (loss 1.6318):  41%|████▏     | 646/1563 [19:08<22:55,  1.50s/it]
Training 1/1 epoch (loss 1.4926):  41%|████▏     | 646/1563 [19:09<22:55,  1.50s/it]
Training 1/1 epoch (loss 1.4926):  41%|████▏     | 647/1563 [19:09<22:48,  1.49s/it]
Training 1/1 epoch (loss 1.6467):  41%|████▏     | 647/1563 [19:12<22:48,  1.49s/it]
Training 1/1 epoch (loss 1.6467):  41%|████▏     | 648/1563 [19:12<26:36,  1.74s/it]
Training 1/1 epoch (loss 1.6475):  41%|████▏     | 648/1563 [19:13<26:36,  1.74s/it]
Training 1/1 epoch (loss 1.6475):  42%|████▏     | 649/1563 [19:13<25:04,  1.65s/it]
Training 1/1 epoch (loss 1.5796):  42%|████▏     | 649/1563 [19:14<25:04,  1.65s/it]
Training 1/1 epoch (loss 1.5796):  42%|████▏     | 650/1563 [19:14<23:27,  1.54s/it]
Training 1/1 epoch (loss 1.5404):  42%|████▏     | 650/1563 [19:16<23:27,  1.54s/it]
Training 1/1 epoch (loss 1.5404):  42%|████▏     | 651/1563 [19:16<24:39,  1.62s/it]
Training 1/1 epoch (loss 1.5584):  42%|████▏     | 651/1563 [19:18<24:39,  1.62s/it]
Training 1/1 epoch (loss 1.5584):  42%|████▏     | 652/1563 [19:18<24:17,  1.60s/it]
Training 1/1 epoch (loss 1.6908):  42%|████▏     | 652/1563 [19:20<24:17,  1.60s/it]
Training 1/1 epoch (loss 1.6908):  42%|████▏     | 653/1563 [19:20<27:57,  1.84s/it]
Training 1/1 epoch (loss 1.6384):  42%|████▏     | 653/1563 [19:22<27:57,  1.84s/it]
Training 1/1 epoch (loss 1.6384):  42%|████▏     | 654/1563 [19:22<28:14,  1.86s/it]
Training 1/1 epoch (loss 1.6101):  42%|████▏     | 654/1563 [19:24<28:14,  1.86s/it]
Training 1/1 epoch (loss 1.6101):  42%|████▏     | 655/1563 [19:24<27:02,  1.79s/it]
Training 1/1 epoch (loss 1.7053):  42%|████▏     | 655/1563 [19:25<27:02,  1.79s/it]
Training 1/1 epoch (loss 1.7053):  42%|████▏     | 656/1563 [19:25<25:04,  1.66s/it]
Training 1/1 epoch (loss 1.5734):  42%|████▏     | 656/1563 [19:26<25:04,  1.66s/it]
Training 1/1 epoch (loss 1.5734):  42%|████▏     | 657/1563 [19:26<22:35,  1.50s/it]
Training 1/1 epoch (loss 1.7103):  42%|████▏     | 657/1563 [19:28<22:35,  1.50s/it]
Training 1/1 epoch (loss 1.7103):  42%|████▏     | 658/1563 [19:28<24:44,  1.64s/it]
Training 1/1 epoch (loss 1.6936):  42%|████▏     | 658/1563 [19:30<24:44,  1.64s/it]
Training 1/1 epoch (loss 1.6936):  42%|████▏     | 659/1563 [19:30<25:31,  1.69s/it]
Training 1/1 epoch (loss 1.6439):  42%|████▏     | 659/1563 [19:31<25:31,  1.69s/it]
Training 1/1 epoch (loss 1.6439):  42%|████▏     | 660/1563 [19:31<23:05,  1.53s/it]
Training 1/1 epoch (loss 1.6613):  42%|████▏     | 660/1563 [19:33<23:05,  1.53s/it]
Training 1/1 epoch (loss 1.6613):  42%|████▏     | 661/1563 [19:33<23:58,  1.59s/it]
Training 1/1 epoch (loss 1.6504):  42%|████▏     | 661/1563 [19:34<23:58,  1.59s/it]
Training 1/1 epoch (loss 1.6504):  42%|████▏     | 662/1563 [19:34<23:36,  1.57s/it]
Training 1/1 epoch (loss 1.6368):  42%|████▏     | 662/1563 [19:36<23:36,  1.57s/it]
Training 1/1 epoch (loss 1.6368):  42%|████▏     | 663/1563 [19:36<23:19,  1.55s/it]
Training 1/1 epoch (loss 1.6378):  42%|████▏     | 663/1563 [19:37<23:19,  1.55s/it]
Training 1/1 epoch (loss 1.6378):  42%|████▏     | 664/1563 [19:37<22:08,  1.48s/it]
Training 1/1 epoch (loss 1.6274):  42%|████▏     | 664/1563 [19:39<22:08,  1.48s/it]
Training 1/1 epoch (loss 1.6274):  43%|████▎     | 665/1563 [19:39<23:22,  1.56s/it]
Training 1/1 epoch (loss 1.4829):  43%|████▎     | 665/1563 [19:41<23:22,  1.56s/it]
Training 1/1 epoch (loss 1.4829):  43%|████▎     | 666/1563 [19:41<24:33,  1.64s/it]
Training 1/1 epoch (loss 1.6307):  43%|████▎     | 666/1563 [19:42<24:33,  1.64s/it]
Training 1/1 epoch (loss 1.6307):  43%|████▎     | 667/1563 [19:42<23:03,  1.54s/it]
Training 1/1 epoch (loss 1.6391):  43%|████▎     | 667/1563 [19:44<23:03,  1.54s/it]
Training 1/1 epoch (loss 1.6391):  43%|████▎     | 668/1563 [19:44<23:05,  1.55s/it]
Training 1/1 epoch (loss 1.6079):  43%|████▎     | 668/1563 [19:45<23:05,  1.55s/it]
Training 1/1 epoch (loss 1.6079):  43%|████▎     | 669/1563 [19:45<24:14,  1.63s/it]
Training 1/1 epoch (loss 1.6971):  43%|████▎     | 669/1563 [19:47<24:14,  1.63s/it]
Training 1/1 epoch (loss 1.6971):  43%|████▎     | 670/1563 [19:47<22:32,  1.51s/it]
Training 1/1 epoch (loss 1.6931):  43%|████▎     | 670/1563 [19:49<22:32,  1.51s/it]
Training 1/1 epoch (loss 1.6931):  43%|████▎     | 671/1563 [19:49<26:56,  1.81s/it]
Training 1/1 epoch (loss 1.5836):  43%|████▎     | 671/1563 [19:51<26:56,  1.81s/it]
Training 1/1 epoch (loss 1.5836):  43%|████▎     | 672/1563 [19:51<28:17,  1.90s/it]
Training 1/1 epoch (loss 1.6517):  43%|████▎     | 672/1563 [19:53<28:17,  1.90s/it]
Training 1/1 epoch (loss 1.6517):  43%|████▎     | 673/1563 [19:53<25:39,  1.73s/it]
Training 1/1 epoch (loss 1.5527):  43%|████▎     | 673/1563 [19:54<25:39,  1.73s/it]
Training 1/1 epoch (loss 1.5527):  43%|████▎     | 674/1563 [19:54<25:20,  1.71s/it]
Training 1/1 epoch (loss 1.5825):  43%|████▎     | 674/1563 [19:57<25:20,  1.71s/it]
Training 1/1 epoch (loss 1.5825):  43%|████▎     | 675/1563 [19:57<28:50,  1.95s/it]
Training 1/1 epoch (loss 1.6971):  43%|████▎     | 675/1563 [19:59<28:50,  1.95s/it]
Training 1/1 epoch (loss 1.6971):  43%|████▎     | 676/1563 [19:59<29:30,  2.00s/it]
Training 1/1 epoch (loss 1.7286):  43%|████▎     | 676/1563 [20:01<29:30,  2.00s/it]
Training 1/1 epoch (loss 1.7286):  43%|████▎     | 677/1563 [20:01<28:40,  1.94s/it]
Training 1/1 epoch (loss 1.6115):  43%|████▎     | 677/1563 [20:02<28:40,  1.94s/it]
Training 1/1 epoch (loss 1.6115):  43%|████▎     | 678/1563 [20:02<26:19,  1.78s/it]
Training 1/1 epoch (loss 1.7304):  43%|████▎     | 678/1563 [20:03<26:19,  1.78s/it]
Training 1/1 epoch (loss 1.7304):  43%|████▎     | 679/1563 [20:03<24:23,  1.66s/it]
Training 1/1 epoch (loss 1.5767):  43%|████▎     | 679/1563 [20:05<24:23,  1.66s/it]
Training 1/1 epoch (loss 1.5767):  44%|████▎     | 680/1563 [20:05<24:17,  1.65s/it]
Training 1/1 epoch (loss 1.6605):  44%|████▎     | 680/1563 [20:08<24:17,  1.65s/it]
Training 1/1 epoch (loss 1.6605):  44%|████▎     | 681/1563 [20:08<27:48,  1.89s/it]
Training 1/1 epoch (loss 1.4915):  44%|████▎     | 681/1563 [20:09<27:48,  1.89s/it]
Training 1/1 epoch (loss 1.4915):  44%|████▎     | 682/1563 [20:09<26:51,  1.83s/it]
Training 1/1 epoch (loss 1.5979):  44%|████▎     | 682/1563 [20:11<26:51,  1.83s/it]
Training 1/1 epoch (loss 1.5979):  44%|████▎     | 683/1563 [20:11<28:28,  1.94s/it]
Training 1/1 epoch (loss 1.5173):  44%|████▎     | 683/1563 [20:14<28:28,  1.94s/it]
Training 1/1 epoch (loss 1.5173):  44%|████▍     | 684/1563 [20:14<28:51,  1.97s/it]
Training 1/1 epoch (loss 1.5963):  44%|████▍     | 684/1563 [20:15<28:51,  1.97s/it]
Training 1/1 epoch (loss 1.5963):  44%|████▍     | 685/1563 [20:15<27:04,  1.85s/it]
Training 1/1 epoch (loss 1.5136):  44%|████▍     | 685/1563 [20:17<27:04,  1.85s/it]
Training 1/1 epoch (loss 1.5136):  44%|████▍     | 686/1563 [20:17<26:25,  1.81s/it]
Training 1/1 epoch (loss 1.6890):  44%|████▍     | 686/1563 [20:19<26:25,  1.81s/it]
Training 1/1 epoch (loss 1.6890):  44%|████▍     | 687/1563 [20:19<27:54,  1.91s/it]
Training 1/1 epoch (loss 1.6025):  44%|████▍     | 687/1563 [20:22<27:54,  1.91s/it]
Training 1/1 epoch (loss 1.6025):  44%|████▍     | 688/1563 [20:22<31:24,  2.15s/it]
Training 1/1 epoch (loss 1.6062):  44%|████▍     | 688/1563 [20:23<31:24,  2.15s/it]
Training 1/1 epoch (loss 1.6062):  44%|████▍     | 689/1563 [20:23<27:10,  1.87s/it]
Training 1/1 epoch (loss 1.7218):  44%|████▍     | 689/1563 [20:24<27:10,  1.87s/it]
Training 1/1 epoch (loss 1.7218):  44%|████▍     | 690/1563 [20:24<24:32,  1.69s/it]
Training 1/1 epoch (loss 1.6795):  44%|████▍     | 690/1563 [20:25<24:32,  1.69s/it]
Training 1/1 epoch (loss 1.6795):  44%|████▍     | 691/1563 [20:25<21:23,  1.47s/it]
Training 1/1 epoch (loss 1.6778):  44%|████▍     | 691/1563 [20:27<21:23,  1.47s/it]
Training 1/1 epoch (loss 1.6778):  44%|████▍     | 692/1563 [20:27<22:56,  1.58s/it]
Training 1/1 epoch (loss 1.6967):  44%|████▍     | 692/1563 [20:29<22:56,  1.58s/it]
Training 1/1 epoch (loss 1.6967):  44%|████▍     | 693/1563 [20:29<23:02,  1.59s/it]
Training 1/1 epoch (loss 1.6341):  44%|████▍     | 693/1563 [20:30<23:02,  1.59s/it]
Training 1/1 epoch (loss 1.6341):  44%|████▍     | 694/1563 [20:30<24:06,  1.66s/it]
Training 1/1 epoch (loss 1.5900):  44%|████▍     | 694/1563 [20:32<24:06,  1.66s/it]
Training 1/1 epoch (loss 1.5900):  44%|████▍     | 695/1563 [20:32<25:13,  1.74s/it]
Training 1/1 epoch (loss 1.5558):  44%|████▍     | 695/1563 [20:35<25:13,  1.74s/it]
Training 1/1 epoch (loss 1.5558):  45%|████▍     | 696/1563 [20:35<28:10,  1.95s/it]
Training 1/1 epoch (loss 1.6631):  45%|████▍     | 696/1563 [20:36<28:10,  1.95s/it]
Training 1/1 epoch (loss 1.6631):  45%|████▍     | 697/1563 [20:36<26:28,  1.83s/it]
Training 1/1 epoch (loss 1.8010):  45%|████▍     | 697/1563 [20:37<26:28,  1.83s/it]
Training 1/1 epoch (loss 1.8010):  45%|████▍     | 698/1563 [20:37<21:08,  1.47s/it]
Training 1/1 epoch (loss 1.5802):  45%|████▍     | 698/1563 [20:37<21:08,  1.47s/it]
Training 1/1 epoch (loss 1.5802):  45%|████▍     | 699/1563 [20:37<16:11,  1.12s/it]
Training 1/1 epoch (loss 1.6302):  45%|████▍     | 699/1563 [20:38<16:11,  1.12s/it]
Training 1/1 epoch (loss 1.6302):  45%|████▍     | 700/1563 [20:38<12:40,  1.13it/s]
Training 1/1 epoch (loss 1.6299):  45%|████▍     | 700/1563 [20:38<12:40,  1.13it/s]
Training 1/1 epoch (loss 1.6299):  45%|████▍     | 701/1563 [20:38<10:31,  1.37it/s]
Training 1/1 epoch (loss 1.7281):  45%|████▍     | 701/1563 [20:38<10:31,  1.37it/s]
Training 1/1 epoch (loss 1.7281):  45%|████▍     | 702/1563 [20:38<08:56,  1.60it/s]
Training 1/1 epoch (loss 1.6614):  45%|████▍     | 702/1563 [20:39<08:56,  1.60it/s]
Training 1/1 epoch (loss 1.6614):  45%|████▍     | 703/1563 [20:39<07:44,  1.85it/s]
Training 1/1 epoch (loss 1.6042):  45%|████▍     | 703/1563 [20:39<07:44,  1.85it/s]
Training 1/1 epoch (loss 1.6042):  45%|████▌     | 704/1563 [20:39<07:08,  2.01it/s]
Training 1/1 epoch (loss 1.7224):  45%|████▌     | 704/1563 [20:39<07:08,  2.01it/s]
Training 1/1 epoch (loss 1.7224):  45%|████▌     | 705/1563 [20:39<06:35,  2.17it/s]
Training 1/1 epoch (loss 1.6503):  45%|████▌     | 705/1563 [20:40<06:35,  2.17it/s]
Training 1/1 epoch (loss 1.6503):  45%|████▌     | 706/1563 [20:40<06:09,  2.32it/s]
Training 1/1 epoch (loss 1.6574):  45%|████▌     | 706/1563 [20:40<06:09,  2.32it/s]
Training 1/1 epoch (loss 1.6574):  45%|████▌     | 707/1563 [20:40<05:40,  2.51it/s]
Training 1/1 epoch (loss 1.7031):  45%|████▌     | 707/1563 [20:40<05:40,  2.51it/s]
Training 1/1 epoch (loss 1.7031):  45%|████▌     | 708/1563 [20:40<05:29,  2.59it/s]
Training 1/1 epoch (loss 1.6806):  45%|████▌     | 708/1563 [20:41<05:29,  2.59it/s]
Training 1/1 epoch (loss 1.6806):  45%|████▌     | 709/1563 [20:41<05:23,  2.64it/s]
Training 1/1 epoch (loss 1.6482):  45%|████▌     | 709/1563 [20:41<05:23,  2.64it/s]
Training 1/1 epoch (loss 1.6482):  45%|████▌     | 710/1563 [20:41<05:34,  2.55it/s]
Training 1/1 epoch (loss 1.6677):  45%|████▌     | 710/1563 [20:42<05:34,  2.55it/s]
Training 1/1 epoch (loss 1.6677):  45%|████▌     | 711/1563 [20:42<05:20,  2.66it/s]
Training 1/1 epoch (loss 1.6150):  45%|████▌     | 711/1563 [20:42<05:20,  2.66it/s]
Training 1/1 epoch (loss 1.6150):  46%|████▌     | 712/1563 [20:42<05:08,  2.75it/s]
Training 1/1 epoch (loss 1.6518):  46%|████▌     | 712/1563 [20:42<05:08,  2.75it/s]
Training 1/1 epoch (loss 1.6518):  46%|████▌     | 713/1563 [20:42<04:58,  2.85it/s]
Training 1/1 epoch (loss 1.6000):  46%|████▌     | 713/1563 [20:43<04:58,  2.85it/s]
Training 1/1 epoch (loss 1.6000):  46%|████▌     | 714/1563 [20:43<05:07,  2.76it/s]
Training 1/1 epoch (loss 1.6528):  46%|████▌     | 714/1563 [20:43<05:07,  2.76it/s]
Training 1/1 epoch (loss 1.6528):  46%|████▌     | 715/1563 [20:43<05:12,  2.72it/s]
Training 1/1 epoch (loss 1.6298):  46%|████▌     | 715/1563 [20:43<05:12,  2.72it/s]
Training 1/1 epoch (loss 1.6298):  46%|████▌     | 716/1563 [20:43<05:16,  2.67it/s]
Training 1/1 epoch (loss 1.4995):  46%|████▌     | 716/1563 [20:44<05:16,  2.67it/s]
Training 1/1 epoch (loss 1.4995):  46%|████▌     | 717/1563 [20:44<05:02,  2.80it/s]
Training 1/1 epoch (loss 1.6612):  46%|████▌     | 717/1563 [20:44<05:02,  2.80it/s]
Training 1/1 epoch (loss 1.6612):  46%|████▌     | 718/1563 [20:44<04:50,  2.91it/s]
Training 1/1 epoch (loss 1.6169):  46%|████▌     | 718/1563 [20:44<04:50,  2.91it/s]
Training 1/1 epoch (loss 1.6169):  46%|████▌     | 719/1563 [20:44<04:43,  2.97it/s]
Training 1/1 epoch (loss 1.5952):  46%|████▌     | 719/1563 [20:45<04:43,  2.97it/s]
Training 1/1 epoch (loss 1.5952):  46%|████▌     | 720/1563 [20:45<04:55,  2.85it/s]
Training 1/1 epoch (loss 1.6106):  46%|████▌     | 720/1563 [20:45<04:55,  2.85it/s]
Training 1/1 epoch (loss 1.6106):  46%|████▌     | 721/1563 [20:45<05:07,  2.74it/s]
Training 1/1 epoch (loss 1.7358):  46%|████▌     | 721/1563 [20:45<05:07,  2.74it/s]
Training 1/1 epoch (loss 1.7358):  46%|████▌     | 722/1563 [20:45<05:00,  2.80it/s]
Training 1/1 epoch (loss 1.5867):  46%|████▌     | 722/1563 [20:46<05:00,  2.80it/s]
Training 1/1 epoch (loss 1.5867):  46%|████▋     | 723/1563 [20:46<04:54,  2.85it/s]
Training 1/1 epoch (loss 1.6017):  46%|████▋     | 723/1563 [20:46<04:54,  2.85it/s]
Training 1/1 epoch (loss 1.6017):  46%|████▋     | 724/1563 [20:46<04:57,  2.82it/s]
Training 1/1 epoch (loss 1.6324):  46%|████▋     | 724/1563 [20:46<04:57,  2.82it/s]
Training 1/1 epoch (loss 1.6324):  46%|████▋     | 725/1563 [20:46<04:47,  2.92it/s]
Training 1/1 epoch (loss 1.5699):  46%|████▋     | 725/1563 [20:47<04:47,  2.92it/s]
Training 1/1 epoch (loss 1.5699):  46%|████▋     | 726/1563 [20:47<04:47,  2.91it/s]
Training 1/1 epoch (loss 1.6664):  46%|████▋     | 726/1563 [20:47<04:47,  2.91it/s]
Training 1/1 epoch (loss 1.6664):  47%|████▋     | 727/1563 [20:47<05:01,  2.77it/s]
Training 1/1 epoch (loss 1.7116):  47%|████▋     | 727/1563 [20:48<05:01,  2.77it/s]
Training 1/1 epoch (loss 1.7116):  47%|████▋     | 728/1563 [20:48<05:01,  2.77it/s]
Training 1/1 epoch (loss 1.5601):  47%|████▋     | 728/1563 [20:48<05:01,  2.77it/s]
Training 1/1 epoch (loss 1.5601):  47%|████▋     | 729/1563 [20:48<04:50,  2.87it/s]
Training 1/1 epoch (loss 1.6075):  47%|████▋     | 729/1563 [20:48<04:50,  2.87it/s]
Training 1/1 epoch (loss 1.6075):  47%|████▋     | 730/1563 [20:48<04:42,  2.95it/s]
Training 1/1 epoch (loss 1.5422):  47%|████▋     | 730/1563 [20:49<04:42,  2.95it/s]
Training 1/1 epoch (loss 1.5422):  47%|████▋     | 731/1563 [20:49<04:40,  2.97it/s]
Training 1/1 epoch (loss 1.5914):  47%|████▋     | 731/1563 [20:49<04:40,  2.97it/s]
Training 1/1 epoch (loss 1.5914):  47%|████▋     | 732/1563 [20:49<04:37,  2.99it/s]
Training 1/1 epoch (loss 1.5500):  47%|████▋     | 732/1563 [20:49<04:37,  2.99it/s]
Training 1/1 epoch (loss 1.5500):  47%|████▋     | 733/1563 [20:49<04:56,  2.80it/s]
Training 1/1 epoch (loss 1.6647):  47%|████▋     | 733/1563 [20:50<04:56,  2.80it/s]
Training 1/1 epoch (loss 1.6647):  47%|████▋     | 734/1563 [20:50<04:45,  2.90it/s]
Training 1/1 epoch (loss 1.6750):  47%|████▋     | 734/1563 [20:50<04:45,  2.90it/s]
Training 1/1 epoch (loss 1.6750):  47%|████▋     | 735/1563 [20:50<04:38,  2.97it/s]
Training 1/1 epoch (loss 1.6307):  47%|████▋     | 735/1563 [20:50<04:38,  2.97it/s]
Training 1/1 epoch (loss 1.6307):  47%|████▋     | 736/1563 [20:50<04:38,  2.97it/s]
Training 1/1 epoch (loss 1.7553):  47%|████▋     | 736/1563 [20:51<04:38,  2.97it/s]
Training 1/1 epoch (loss 1.7553):  47%|████▋     | 737/1563 [20:51<04:38,  2.97it/s]
Training 1/1 epoch (loss 1.5935):  47%|████▋     | 737/1563 [20:51<04:38,  2.97it/s]
Training 1/1 epoch (loss 1.5935):  47%|████▋     | 738/1563 [20:51<04:40,  2.94it/s]
Training 1/1 epoch (loss 1.5560):  47%|████▋     | 738/1563 [20:51<04:40,  2.94it/s]
Training 1/1 epoch (loss 1.5560):  47%|████▋     | 739/1563 [20:51<04:55,  2.79it/s]
Training 1/1 epoch (loss 1.6281):  47%|████▋     | 739/1563 [20:52<04:55,  2.79it/s]
Training 1/1 epoch (loss 1.6281):  47%|████▋     | 740/1563 [20:52<04:50,  2.84it/s]
Training 1/1 epoch (loss 1.6564):  47%|████▋     | 740/1563 [20:52<04:50,  2.84it/s]
Training 1/1 epoch (loss 1.6564):  47%|████▋     | 741/1563 [20:52<04:43,  2.90it/s]
Training 1/1 epoch (loss 1.5985):  47%|████▋     | 741/1563 [20:52<04:43,  2.90it/s]
Training 1/1 epoch (loss 1.5985):  47%|████▋     | 742/1563 [20:52<04:39,  2.94it/s]
Training 1/1 epoch (loss 1.5824):  47%|████▋     | 742/1563 [20:53<04:39,  2.94it/s]
Training 1/1 epoch (loss 1.5824):  48%|████▊     | 743/1563 [20:53<04:36,  2.97it/s]
Training 1/1 epoch (loss 1.6257):  48%|████▊     | 743/1563 [20:53<04:36,  2.97it/s]
Training 1/1 epoch (loss 1.6257):  48%|████▊     | 744/1563 [20:53<05:05,  2.68it/s]
Training 1/1 epoch (loss 1.6348):  48%|████▊     | 744/1563 [20:54<05:05,  2.68it/s]
Training 1/1 epoch (loss 1.6348):  48%|████▊     | 745/1563 [20:54<05:09,  2.64it/s]
Training 1/1 epoch (loss 1.5024):  48%|████▊     | 745/1563 [20:54<05:09,  2.64it/s]
Training 1/1 epoch (loss 1.5024):  48%|████▊     | 746/1563 [20:54<04:54,  2.78it/s]
Training 1/1 epoch (loss 1.5605):  48%|████▊     | 746/1563 [20:54<04:54,  2.78it/s]
Training 1/1 epoch (loss 1.5605):  48%|████▊     | 747/1563 [20:54<04:45,  2.86it/s]
Training 1/1 epoch (loss 1.4728):  48%|████▊     | 747/1563 [20:54<04:45,  2.86it/s]
Training 1/1 epoch (loss 1.4728):  48%|████▊     | 748/1563 [20:54<04:39,  2.92it/s]
Training 1/1 epoch (loss 1.6930):  48%|████▊     | 748/1563 [20:55<04:39,  2.92it/s]
Training 1/1 epoch (loss 1.6930):  48%|████▊     | 749/1563 [20:55<04:35,  2.96it/s]
Training 1/1 epoch (loss 1.5516):  48%|████▊     | 749/1563 [20:55<04:35,  2.96it/s]
Training 1/1 epoch (loss 1.5516):  48%|████▊     | 750/1563 [20:55<04:50,  2.80it/s]
Training 1/1 epoch (loss 1.6068):  48%|████▊     | 750/1563 [20:56<04:50,  2.80it/s]
Training 1/1 epoch (loss 1.6068):  48%|████▊     | 751/1563 [20:56<04:38,  2.91it/s]
Training 1/1 epoch (loss 1.7443):  48%|████▊     | 751/1563 [20:56<04:38,  2.91it/s]
Training 1/1 epoch (loss 1.7443):  48%|████▊     | 752/1563 [20:56<04:38,  2.91it/s]
Training 1/1 epoch (loss 1.6505):  48%|████▊     | 752/1563 [20:56<04:38,  2.91it/s]
Training 1/1 epoch (loss 1.6505):  48%|████▊     | 753/1563 [20:56<04:31,  2.99it/s]
Training 1/1 epoch (loss 1.6918):  48%|████▊     | 753/1563 [20:57<04:31,  2.99it/s]
Training 1/1 epoch (loss 1.6918):  48%|████▊     | 754/1563 [20:57<04:26,  3.04it/s]
Training 1/1 epoch (loss 1.6519):  48%|████▊     | 754/1563 [20:57<04:26,  3.04it/s]
Training 1/1 epoch (loss 1.6519):  48%|████▊     | 755/1563 [20:57<04:31,  2.98it/s]
Training 1/1 epoch (loss 1.5048):  48%|████▊     | 755/1563 [20:57<04:31,  2.98it/s]
Training 1/1 epoch (loss 1.5048):  48%|████▊     | 756/1563 [20:57<04:39,  2.89it/s]
Training 1/1 epoch (loss 1.5836):  48%|████▊     | 756/1563 [20:58<04:39,  2.89it/s]
Training 1/1 epoch (loss 1.5836):  48%|████▊     | 757/1563 [20:58<04:36,  2.91it/s]
Training 1/1 epoch (loss 1.6390):  48%|████▊     | 757/1563 [20:58<04:36,  2.91it/s]
Training 1/1 epoch (loss 1.6390):  48%|████▊     | 758/1563 [20:58<04:49,  2.78it/s]
Training 1/1 epoch (loss 1.6834):  48%|████▊     | 758/1563 [20:58<04:49,  2.78it/s]
Training 1/1 epoch (loss 1.6834):  49%|████▊     | 759/1563 [20:58<04:41,  2.86it/s]
Training 1/1 epoch (loss 1.6416):  49%|████▊     | 759/1563 [20:59<04:41,  2.86it/s]
Training 1/1 epoch (loss 1.6416):  49%|████▊     | 760/1563 [20:59<04:46,  2.80it/s]
Training 1/1 epoch (loss 1.6301):  49%|████▊     | 760/1563 [20:59<04:46,  2.80it/s]
Training 1/1 epoch (loss 1.6301):  49%|████▊     | 761/1563 [20:59<04:47,  2.79it/s]
Training 1/1 epoch (loss 1.6489):  49%|████▊     | 761/1563 [20:59<04:47,  2.79it/s]
Training 1/1 epoch (loss 1.6489):  49%|████▉     | 762/1563 [20:59<04:57,  2.69it/s]
Training 1/1 epoch (loss 1.5901):  49%|████▉     | 762/1563 [21:00<04:57,  2.69it/s]
Training 1/1 epoch (loss 1.5901):  49%|████▉     | 763/1563 [21:00<04:42,  2.83it/s]
Training 1/1 epoch (loss 1.6630):  49%|████▉     | 763/1563 [21:00<04:42,  2.83it/s]
Training 1/1 epoch (loss 1.6630):  49%|████▉     | 764/1563 [21:00<04:36,  2.89it/s]
Training 1/1 epoch (loss 1.6239):  49%|████▉     | 764/1563 [21:00<04:36,  2.89it/s]
Training 1/1 epoch (loss 1.6239):  49%|████▉     | 765/1563 [21:00<04:33,  2.92it/s]
Training 1/1 epoch (loss 1.7187):  49%|████▉     | 765/1563 [21:01<04:33,  2.92it/s]
Training 1/1 epoch (loss 1.7187):  49%|████▉     | 766/1563 [21:01<04:37,  2.87it/s]
Training 1/1 epoch (loss 1.6824):  49%|████▉     | 766/1563 [21:01<04:37,  2.87it/s]
Training 1/1 epoch (loss 1.6824):  49%|████▉     | 767/1563 [21:01<04:47,  2.77it/s]
Training 1/1 epoch (loss 1.7095):  49%|████▉     | 767/1563 [21:02<04:47,  2.77it/s]
Training 1/1 epoch (loss 1.7095):  49%|████▉     | 768/1563 [21:02<04:53,  2.71it/s]
Training 1/1 epoch (loss 1.6096):  49%|████▉     | 768/1563 [21:02<04:53,  2.71it/s]
Training 1/1 epoch (loss 1.6096):  49%|████▉     | 769/1563 [21:02<04:39,  2.84it/s]
Training 1/1 epoch (loss 1.5862):  49%|████▉     | 769/1563 [21:02<04:39,  2.84it/s]
Training 1/1 epoch (loss 1.5862):  49%|████▉     | 770/1563 [21:02<04:43,  2.80it/s]
Training 1/1 epoch (loss 1.5533):  49%|████▉     | 770/1563 [21:03<04:43,  2.80it/s]
Training 1/1 epoch (loss 1.5533):  49%|████▉     | 771/1563 [21:03<04:48,  2.74it/s]
Training 1/1 epoch (loss 1.6359):  49%|████▉     | 771/1563 [21:03<04:48,  2.74it/s]
Training 1/1 epoch (loss 1.6359):  49%|████▉     | 772/1563 [21:03<05:27,  2.42it/s]
Training 1/1 epoch (loss 1.5989):  49%|████▉     | 772/1563 [21:04<05:27,  2.42it/s]
Training 1/1 epoch (loss 1.5989):  49%|████▉     | 773/1563 [21:04<05:37,  2.34it/s]
Training 1/1 epoch (loss 1.6201):  49%|████▉     | 773/1563 [21:04<05:37,  2.34it/s]
Training 1/1 epoch (loss 1.6201):  50%|████▉     | 774/1563 [21:04<05:17,  2.48it/s]
Training 1/1 epoch (loss 1.5561):  50%|████▉     | 774/1563 [21:04<05:17,  2.48it/s]
Training 1/1 epoch (loss 1.5561):  50%|████▉     | 775/1563 [21:04<05:06,  2.57it/s]
Training 1/1 epoch (loss 1.5773):  50%|████▉     | 775/1563 [21:05<05:06,  2.57it/s]
Training 1/1 epoch (loss 1.5773):  50%|████▉     | 776/1563 [21:05<05:07,  2.56it/s]
Training 1/1 epoch (loss 1.6846):  50%|████▉     | 776/1563 [21:05<05:07,  2.56it/s]
Training 1/1 epoch (loss 1.6846):  50%|████▉     | 777/1563 [21:05<05:02,  2.60it/s]
Training 1/1 epoch (loss 1.5857):  50%|████▉     | 777/1563 [21:05<05:02,  2.60it/s]
Training 1/1 epoch (loss 1.5857):  50%|████▉     | 778/1563 [21:05<05:02,  2.59it/s]
Training 1/1 epoch (loss 1.6045):  50%|████▉     | 778/1563 [21:06<05:02,  2.59it/s]
Training 1/1 epoch (loss 1.6045):  50%|████▉     | 779/1563 [21:06<05:14,  2.49it/s]
Training 1/1 epoch (loss 1.6648):  50%|████▉     | 779/1563 [21:06<05:14,  2.49it/s]
Training 1/1 epoch (loss 1.6648):  50%|████▉     | 780/1563 [21:06<05:12,  2.51it/s]
Training 1/1 epoch (loss 1.4895):  50%|████▉     | 780/1563 [21:07<05:12,  2.51it/s]
Training 1/1 epoch (loss 1.4895):  50%|████▉     | 781/1563 [21:07<05:04,  2.57it/s]
Training 1/1 epoch (loss 1.7101):  50%|████▉     | 781/1563 [21:07<05:04,  2.57it/s]
Training 1/1 epoch (loss 1.7101):  50%|█████     | 782/1563 [21:07<05:34,  2.33it/s]
Training 1/1 epoch (loss 1.6072):  50%|█████     | 782/1563 [21:08<05:34,  2.33it/s]
Training 1/1 epoch (loss 1.6072):  50%|█████     | 783/1563 [21:08<05:38,  2.30it/s]
Training 1/1 epoch (loss 1.6226):  50%|█████     | 783/1563 [21:08<05:38,  2.30it/s]
Training 1/1 epoch (loss 1.6226):  50%|█████     | 784/1563 [21:08<05:52,  2.21it/s]
Training 1/1 epoch (loss 1.4335):  50%|█████     | 784/1563 [21:09<05:52,  2.21it/s]
Training 1/1 epoch (loss 1.4335):  50%|█████     | 785/1563 [21:09<06:25,  2.02it/s]
Training 1/1 epoch (loss 1.6361):  50%|█████     | 785/1563 [21:10<06:25,  2.02it/s]
Training 1/1 epoch (loss 1.6361):  50%|█████     | 786/1563 [21:10<11:13,  1.15it/s]
Training 1/1 epoch (loss 1.5891):  50%|█████     | 786/1563 [21:11<11:13,  1.15it/s]
Training 1/1 epoch (loss 1.5891):  50%|█████     | 787/1563 [21:11<09:24,  1.37it/s]
Training 1/1 epoch (loss 1.5651):  50%|█████     | 787/1563 [21:11<09:24,  1.37it/s]
Training 1/1 epoch (loss 1.5651):  50%|█████     | 788/1563 [21:11<08:00,  1.61it/s]
Training 1/1 epoch (loss 1.6795):  50%|█████     | 788/1563 [21:12<08:00,  1.61it/s]
Training 1/1 epoch (loss 1.6795):  50%|█████     | 789/1563 [21:12<07:02,  1.83it/s]
Training 1/1 epoch (loss 1.6453):  50%|█████     | 789/1563 [21:12<07:02,  1.83it/s]
Training 1/1 epoch (loss 1.6453):  51%|█████     | 790/1563 [21:12<06:27,  2.00it/s]
Training 1/1 epoch (loss 1.5750):  51%|█████     | 790/1563 [21:12<06:27,  2.00it/s]
Training 1/1 epoch (loss 1.5750):  51%|█████     | 791/1563 [21:12<05:43,  2.25it/s]
Training 1/1 epoch (loss 1.6967):  51%|█████     | 791/1563 [21:13<05:43,  2.25it/s]
Training 1/1 epoch (loss 1.6967):  51%|█████     | 792/1563 [21:13<05:16,  2.44it/s]
Training 1/1 epoch (loss 1.6390):  51%|█████     | 792/1563 [21:13<05:16,  2.44it/s]
Training 1/1 epoch (loss 1.6390):  51%|█████     | 793/1563 [21:13<04:59,  2.57it/s]
Training 1/1 epoch (loss 1.6641):  51%|█████     | 793/1563 [21:13<04:59,  2.57it/s]
Training 1/1 epoch (loss 1.6641):  51%|█████     | 794/1563 [21:13<04:52,  2.63it/s]
Training 1/1 epoch (loss 1.6042):  51%|█████     | 794/1563 [21:14<04:52,  2.63it/s]
Training 1/1 epoch (loss 1.6042):  51%|█████     | 795/1563 [21:14<04:57,  2.58it/s]
Training 1/1 epoch (loss 1.5993):  51%|█████     | 795/1563 [21:14<04:57,  2.58it/s]
Training 1/1 epoch (loss 1.5993):  51%|█████     | 796/1563 [21:14<05:04,  2.52it/s]
Training 1/1 epoch (loss 1.6133):  51%|█████     | 796/1563 [21:14<05:04,  2.52it/s]
Training 1/1 epoch (loss 1.6133):  51%|█████     | 797/1563 [21:14<04:45,  2.68it/s]
Training 1/1 epoch (loss 1.7162):  51%|█████     | 797/1563 [21:15<04:45,  2.68it/s]
Training 1/1 epoch (loss 1.7162):  51%|█████     | 798/1563 [21:15<04:33,  2.80it/s]
Training 1/1 epoch (loss 1.6538):  51%|█████     | 798/1563 [21:15<04:33,  2.80it/s]
Training 1/1 epoch (loss 1.6538):  51%|█████     | 799/1563 [21:15<04:29,  2.84it/s]
Training 1/1 epoch (loss 1.6729):  51%|█████     | 799/1563 [21:15<04:29,  2.84it/s]
Training 1/1 epoch (loss 1.6729):  51%|█████     | 800/1563 [21:15<04:24,  2.89it/s]
Training 1/1 epoch (loss 1.5884):  51%|█████     | 800/1563 [21:16<04:24,  2.89it/s]
Training 1/1 epoch (loss 1.5884):  51%|█████     | 801/1563 [21:16<04:19,  2.93it/s]
Training 1/1 epoch (loss 1.6427):  51%|█████     | 801/1563 [21:16<04:19,  2.93it/s]
Training 1/1 epoch (loss 1.6427):  51%|█████▏    | 802/1563 [21:16<04:29,  2.82it/s]
Training 1/1 epoch (loss 1.5743):  51%|█████▏    | 802/1563 [21:16<04:29,  2.82it/s]
Training 1/1 epoch (loss 1.5743):  51%|█████▏    | 803/1563 [21:16<04:16,  2.96it/s]
Training 1/1 epoch (loss 1.6185):  51%|█████▏    | 803/1563 [21:17<04:16,  2.96it/s]
Training 1/1 epoch (loss 1.6185):  51%|█████▏    | 804/1563 [21:17<04:35,  2.75it/s]
Training 1/1 epoch (loss 1.6343):  51%|█████▏    | 804/1563 [21:17<04:35,  2.75it/s]
Training 1/1 epoch (loss 1.6343):  52%|█████▏    | 805/1563 [21:17<05:01,  2.51it/s]
Training 1/1 epoch (loss 1.4300):  52%|█████▏    | 805/1563 [21:18<05:01,  2.51it/s]
Training 1/1 epoch (loss 1.4300):  52%|█████▏    | 806/1563 [21:18<05:14,  2.41it/s]
Training 1/1 epoch (loss 1.6844):  52%|█████▏    | 806/1563 [21:18<05:14,  2.41it/s]
Training 1/1 epoch (loss 1.6844):  52%|█████▏    | 807/1563 [21:18<04:59,  2.52it/s]
Training 1/1 epoch (loss 1.5993):  52%|█████▏    | 807/1563 [21:19<04:59,  2.52it/s]
Training 1/1 epoch (loss 1.5993):  52%|█████▏    | 808/1563 [21:19<04:54,  2.56it/s]
Training 1/1 epoch (loss 1.6618):  52%|█████▏    | 808/1563 [21:20<04:54,  2.56it/s]
Training 1/1 epoch (loss 1.6618):  52%|█████▏    | 809/1563 [21:20<07:46,  1.62it/s]
Training 1/1 epoch (loss 1.6163):  52%|█████▏    | 809/1563 [21:20<07:46,  1.62it/s]
Training 1/1 epoch (loss 1.6163):  52%|█████▏    | 810/1563 [21:20<07:27,  1.68it/s]
Training 1/1 epoch (loss 1.4824):  52%|█████▏    | 810/1563 [21:21<07:27,  1.68it/s]
Training 1/1 epoch (loss 1.4824):  52%|█████▏    | 811/1563 [21:21<07:38,  1.64it/s]
Training 1/1 epoch (loss 1.5061):  52%|█████▏    | 811/1563 [21:22<07:38,  1.64it/s]
Training 1/1 epoch (loss 1.5061):  52%|█████▏    | 812/1563 [21:22<08:53,  1.41it/s]
Training 1/1 epoch (loss 1.5754):  52%|█████▏    | 812/1563 [21:23<08:53,  1.41it/s]
Training 1/1 epoch (loss 1.5754):  52%|█████▏    | 813/1563 [21:23<08:59,  1.39it/s]
Training 1/1 epoch (loss 1.7377):  52%|█████▏    | 813/1563 [21:23<08:59,  1.39it/s]
Training 1/1 epoch (loss 1.7377):  52%|█████▏    | 814/1563 [21:23<08:46,  1.42it/s]
Training 1/1 epoch (loss 1.6317):  52%|█████▏    | 814/1563 [21:24<08:46,  1.42it/s]
Training 1/1 epoch (loss 1.6317):  52%|█████▏    | 815/1563 [21:24<09:08,  1.36it/s]
Training 1/1 epoch (loss 1.5323):  52%|█████▏    | 815/1563 [21:25<09:08,  1.36it/s]
Training 1/1 epoch (loss 1.5323):  52%|█████▏    | 816/1563 [21:25<09:45,  1.28it/s]
Training 1/1 epoch (loss 1.6490):  52%|█████▏    | 816/1563 [21:26<09:45,  1.28it/s]
Training 1/1 epoch (loss 1.6490):  52%|█████▏    | 817/1563 [21:26<09:57,  1.25it/s]
Training 1/1 epoch (loss 1.6150):  52%|█████▏    | 817/1563 [21:26<09:57,  1.25it/s]
Training 1/1 epoch (loss 1.6150):  52%|█████▏    | 818/1563 [21:26<08:52,  1.40it/s]
Training 1/1 epoch (loss 1.5726):  52%|█████▏    | 818/1563 [21:27<08:52,  1.40it/s]
Training 1/1 epoch (loss 1.5726):  52%|█████▏    | 819/1563 [21:27<08:07,  1.53it/s]
Training 1/1 epoch (loss 1.6527):  52%|█████▏    | 819/1563 [21:27<08:07,  1.53it/s]
Training 1/1 epoch (loss 1.6527):  52%|█████▏    | 820/1563 [21:27<07:22,  1.68it/s]
Training 1/1 epoch (loss 1.6462):  52%|█████▏    | 820/1563 [21:28<07:22,  1.68it/s]
Training 1/1 epoch (loss 1.6462):  53%|█████▎    | 821/1563 [21:28<06:44,  1.83it/s]
Training 1/1 epoch (loss 1.6190):  53%|█████▎    | 821/1563 [21:28<06:44,  1.83it/s]
Training 1/1 epoch (loss 1.6190):  53%|█████▎    | 822/1563 [21:28<07:32,  1.64it/s]
Training 1/1 epoch (loss 1.5314):  53%|█████▎    | 822/1563 [21:29<07:32,  1.64it/s]
Training 1/1 epoch (loss 1.5314):  53%|█████▎    | 823/1563 [21:29<06:47,  1.82it/s]
Training 1/1 epoch (loss 1.6557):  53%|█████▎    | 823/1563 [21:30<06:47,  1.82it/s]
Training 1/1 epoch (loss 1.6557):  53%|█████▎    | 824/1563 [21:30<08:17,  1.48it/s]
Training 1/1 epoch (loss 1.6364):  53%|█████▎    | 824/1563 [21:31<08:17,  1.48it/s]
Training 1/1 epoch (loss 1.6364):  53%|█████▎    | 825/1563 [21:31<10:28,  1.17it/s]
Training 1/1 epoch (loss 1.5175):  53%|█████▎    | 825/1563 [21:32<10:28,  1.17it/s]
Training 1/1 epoch (loss 1.5175):  53%|█████▎    | 826/1563 [21:32<12:02,  1.02it/s]
Training 1/1 epoch (loss 1.6490):  53%|█████▎    | 826/1563 [21:35<12:02,  1.02it/s]
Training 1/1 epoch (loss 1.6490):  53%|█████▎    | 827/1563 [21:35<17:26,  1.42s/it]
Training 1/1 epoch (loss 1.5380):  53%|█████▎    | 827/1563 [21:36<17:26,  1.42s/it]
Training 1/1 epoch (loss 1.5380):  53%|█████▎    | 828/1563 [21:36<18:01,  1.47s/it]
Training 1/1 epoch (loss 1.5973):  53%|█████▎    | 828/1563 [21:38<18:01,  1.47s/it]
Training 1/1 epoch (loss 1.5973):  53%|█████▎    | 829/1563 [21:38<18:39,  1.53s/it]
Training 1/1 epoch (loss 1.5426):  53%|█████▎    | 829/1563 [21:40<18:39,  1.53s/it]
Training 1/1 epoch (loss 1.5426):  53%|█████▎    | 830/1563 [21:40<20:34,  1.68s/it]
Training 1/1 epoch (loss 1.6244):  53%|█████▎    | 830/1563 [21:42<20:34,  1.68s/it]
Training 1/1 epoch (loss 1.6244):  53%|█████▎    | 831/1563 [21:42<19:31,  1.60s/it]
Training 1/1 epoch (loss 1.6424):  53%|█████▎    | 831/1563 [21:43<19:31,  1.60s/it]
Training 1/1 epoch (loss 1.6424):  53%|█████▎    | 832/1563 [21:43<20:00,  1.64s/it]
Training 1/1 epoch (loss 1.6040):  53%|█████▎    | 832/1563 [21:46<20:00,  1.64s/it]
Training 1/1 epoch (loss 1.6040):  53%|█████▎    | 833/1563 [21:46<22:51,  1.88s/it]
Training 1/1 epoch (loss 1.6590):  53%|█████▎    | 833/1563 [21:48<22:51,  1.88s/it]
Training 1/1 epoch (loss 1.6590):  53%|█████▎    | 834/1563 [21:48<24:00,  1.98s/it]
Training 1/1 epoch (loss 1.6432):  53%|█████▎    | 834/1563 [21:49<24:00,  1.98s/it]
Training 1/1 epoch (loss 1.6432):  53%|█████▎    | 835/1563 [21:49<20:06,  1.66s/it]
Training 1/1 epoch (loss 1.7308):  53%|█████▎    | 835/1563 [21:50<20:06,  1.66s/it]
Training 1/1 epoch (loss 1.7308):  53%|█████▎    | 836/1563 [21:50<17:00,  1.40s/it]
Training 1/1 epoch (loss 1.6294):  53%|█████▎    | 836/1563 [21:50<17:00,  1.40s/it]
Training 1/1 epoch (loss 1.6294):  54%|█████▎    | 837/1563 [21:50<14:31,  1.20s/it]
Training 1/1 epoch (loss 1.6379):  54%|█████▎    | 837/1563 [21:51<14:31,  1.20s/it]
Training 1/1 epoch (loss 1.6379):  54%|█████▎    | 838/1563 [21:51<12:49,  1.06s/it]
Training 1/1 epoch (loss 1.5625):  54%|█████▎    | 838/1563 [21:51<12:49,  1.06s/it]
Training 1/1 epoch (loss 1.5625):  54%|█████▎    | 839/1563 [21:51<10:13,  1.18it/s]
Training 1/1 epoch (loss 1.6375):  54%|█████▎    | 839/1563 [21:52<10:13,  1.18it/s]
Training 1/1 epoch (loss 1.6375):  54%|█████▎    | 840/1563 [21:52<08:26,  1.43it/s]
Training 1/1 epoch (loss 1.6799):  54%|█████▎    | 840/1563 [21:52<08:26,  1.43it/s]
Training 1/1 epoch (loss 1.6799):  54%|█████▍    | 841/1563 [21:52<07:13,  1.67it/s]
Training 1/1 epoch (loss 1.6222):  54%|█████▍    | 841/1563 [21:53<07:13,  1.67it/s]
Training 1/1 epoch (loss 1.6222):  54%|█████▍    | 842/1563 [21:53<07:50,  1.53it/s]
Training 1/1 epoch (loss 1.5702):  54%|█████▍    | 842/1563 [21:53<07:50,  1.53it/s]
Training 1/1 epoch (loss 1.5702):  54%|█████▍    | 843/1563 [21:53<06:34,  1.82it/s]
Training 1/1 epoch (loss 1.7266):  54%|█████▍    | 843/1563 [21:54<06:34,  1.82it/s]
Training 1/1 epoch (loss 1.7266):  54%|█████▍    | 844/1563 [21:54<05:40,  2.11it/s]
Training 1/1 epoch (loss 1.5581):  54%|█████▍    | 844/1563 [21:54<05:40,  2.11it/s]
Training 1/1 epoch (loss 1.5581):  54%|█████▍    | 845/1563 [21:54<05:07,  2.34it/s]
Training 1/1 epoch (loss 1.5275):  54%|█████▍    | 845/1563 [21:54<05:07,  2.34it/s]
Training 1/1 epoch (loss 1.5275):  54%|█████▍    | 846/1563 [21:54<04:59,  2.40it/s]
Training 1/1 epoch (loss 1.5519):  54%|█████▍    | 846/1563 [21:55<04:59,  2.40it/s]
Training 1/1 epoch (loss 1.5519):  54%|█████▍    | 847/1563 [21:55<06:07,  1.95it/s]
Training 1/1 epoch (loss 1.6192):  54%|█████▍    | 847/1563 [21:56<06:07,  1.95it/s]
Training 1/1 epoch (loss 1.6192):  54%|█████▍    | 848/1563 [21:56<09:28,  1.26it/s]
Training 1/1 epoch (loss 1.5474):  54%|█████▍    | 848/1563 [21:58<09:28,  1.26it/s]
Training 1/1 epoch (loss 1.5474):  54%|█████▍    | 849/1563 [21:58<12:50,  1.08s/it]
Training 1/1 epoch (loss 1.5799):  54%|█████▍    | 849/1563 [21:59<12:50,  1.08s/it]
Training 1/1 epoch (loss 1.5799):  54%|█████▍    | 850/1563 [21:59<13:04,  1.10s/it]
Training 1/1 epoch (loss 1.6850):  54%|█████▍    | 850/1563 [22:01<13:04,  1.10s/it]
Training 1/1 epoch (loss 1.6850):  54%|█████▍    | 851/1563 [22:01<16:36,  1.40s/it]
Training 1/1 epoch (loss 1.6834):  54%|█████▍    | 851/1563 [22:02<16:36,  1.40s/it]
Training 1/1 epoch (loss 1.6834):  55%|█████▍    | 852/1563 [22:02<15:14,  1.29s/it]
Training 1/1 epoch (loss 1.5638):  55%|█████▍    | 852/1563 [22:03<15:14,  1.29s/it]
Training 1/1 epoch (loss 1.5638):  55%|█████▍    | 853/1563 [22:03<13:32,  1.14s/it]
Training 1/1 epoch (loss 1.5293):  55%|█████▍    | 853/1563 [22:04<13:32,  1.14s/it]
Training 1/1 epoch (loss 1.5293):  55%|█████▍    | 854/1563 [22:04<11:58,  1.01s/it]
Training 1/1 epoch (loss 1.5753):  55%|█████▍    | 854/1563 [22:05<11:58,  1.01s/it]
Training 1/1 epoch (loss 1.5753):  55%|█████▍    | 855/1563 [22:05<10:50,  1.09it/s]
Training 1/1 epoch (loss 1.7033):  55%|█████▍    | 855/1563 [22:05<10:50,  1.09it/s]
Training 1/1 epoch (loss 1.7033):  55%|█████▍    | 856/1563 [22:05<09:56,  1.19it/s]
Training 1/1 epoch (loss 1.5879):  55%|█████▍    | 856/1563 [22:06<09:56,  1.19it/s]
Training 1/1 epoch (loss 1.5879):  55%|█████▍    | 857/1563 [22:06<08:44,  1.35it/s]
Training 1/1 epoch (loss 1.5984):  55%|█████▍    | 857/1563 [22:06<08:44,  1.35it/s]
Training 1/1 epoch (loss 1.5984):  55%|█████▍    | 858/1563 [22:06<07:36,  1.54it/s]
Training 1/1 epoch (loss 1.6151):  55%|█████▍    | 858/1563 [22:07<07:36,  1.54it/s]
Training 1/1 epoch (loss 1.6151):  55%|█████▍    | 859/1563 [22:07<06:55,  1.69it/s]
Training 1/1 epoch (loss 1.7118):  55%|█████▍    | 859/1563 [22:07<06:55,  1.69it/s]
Training 1/1 epoch (loss 1.7118):  55%|█████▌    | 860/1563 [22:07<06:37,  1.77it/s]
Training 1/1 epoch (loss 1.6061):  55%|█████▌    | 860/1563 [22:08<06:37,  1.77it/s]
Training 1/1 epoch (loss 1.6061):  55%|█████▌    | 861/1563 [22:08<06:53,  1.70it/s]
Training 1/1 epoch (loss 1.6323):  55%|█████▌    | 861/1563 [22:10<06:53,  1.70it/s]
Training 1/1 epoch (loss 1.6323):  55%|█████▌    | 862/1563 [22:10<11:08,  1.05it/s]
Training 1/1 epoch (loss 1.6529):  55%|█████▌    | 862/1563 [22:11<11:08,  1.05it/s]
Training 1/1 epoch (loss 1.6529):  55%|█████▌    | 863/1563 [22:11<13:12,  1.13s/it]
Training 1/1 epoch (loss 1.5646):  55%|█████▌    | 863/1563 [22:12<13:12,  1.13s/it]
Training 1/1 epoch (loss 1.5646):  55%|█████▌    | 864/1563 [22:12<12:52,  1.11s/it]
Training 1/1 epoch (loss 1.6774):  55%|█████▌    | 864/1563 [22:14<12:52,  1.11s/it]
Training 1/1 epoch (loss 1.6774):  55%|█████▌    | 865/1563 [22:14<14:21,  1.23s/it]
Training 1/1 epoch (loss 1.6352):  55%|█████▌    | 865/1563 [22:16<14:21,  1.23s/it]
Training 1/1 epoch (loss 1.6352):  55%|█████▌    | 866/1563 [22:16<15:55,  1.37s/it]
Training 1/1 epoch (loss 1.5731):  55%|█████▌    | 866/1563 [22:17<15:55,  1.37s/it]
Training 1/1 epoch (loss 1.5731):  55%|█████▌    | 867/1563 [22:17<16:06,  1.39s/it]
Training 1/1 epoch (loss 1.6286):  55%|█████▌    | 867/1563 [22:19<16:06,  1.39s/it]
Training 1/1 epoch (loss 1.6286):  56%|█████▌    | 868/1563 [22:19<18:08,  1.57s/it]
Training 1/1 epoch (loss 1.5378):  56%|█████▌    | 868/1563 [22:20<18:08,  1.57s/it]
Training 1/1 epoch (loss 1.5378):  56%|█████▌    | 869/1563 [22:20<16:36,  1.44s/it]
Training 1/1 epoch (loss 1.6486):  56%|█████▌    | 869/1563 [22:22<16:36,  1.44s/it]
Training 1/1 epoch (loss 1.6486):  56%|█████▌    | 870/1563 [22:22<17:39,  1.53s/it]
Training 1/1 epoch (loss 1.6170):  56%|█████▌    | 870/1563 [22:23<17:39,  1.53s/it]
Training 1/1 epoch (loss 1.6170):  56%|█████▌    | 871/1563 [22:23<16:31,  1.43s/it]
Training 1/1 epoch (loss 1.5357):  56%|█████▌    | 871/1563 [22:25<16:31,  1.43s/it]
Training 1/1 epoch (loss 1.5357):  56%|█████▌    | 872/1563 [22:25<17:39,  1.53s/it]
Training 1/1 epoch (loss 1.6357):  56%|█████▌    | 872/1563 [22:27<17:39,  1.53s/it]
Training 1/1 epoch (loss 1.6357):  56%|█████▌    | 873/1563 [22:27<19:26,  1.69s/it]
Training 1/1 epoch (loss 1.5764):  56%|█████▌    | 873/1563 [22:29<19:26,  1.69s/it]
Training 1/1 epoch (loss 1.5764):  56%|█████▌    | 874/1563 [22:29<19:43,  1.72s/it]
Training 1/1 epoch (loss 1.5844):  56%|█████▌    | 874/1563 [22:30<19:43,  1.72s/it]
Training 1/1 epoch (loss 1.5844):  56%|█████▌    | 875/1563 [22:30<19:58,  1.74s/it]
Training 1/1 epoch (loss 1.7956):  56%|█████▌    | 875/1563 [22:32<19:58,  1.74s/it]
Training 1/1 epoch (loss 1.7956):  56%|█████▌    | 876/1563 [22:32<19:09,  1.67s/it]
Training 1/1 epoch (loss 1.5672):  56%|█████▌    | 876/1563 [22:34<19:09,  1.67s/it]
Training 1/1 epoch (loss 1.5672):  56%|█████▌    | 877/1563 [22:34<19:20,  1.69s/it]
Training 1/1 epoch (loss 1.6432):  56%|█████▌    | 877/1563 [22:35<19:20,  1.69s/it]
Training 1/1 epoch (loss 1.6432):  56%|█████▌    | 878/1563 [22:35<17:55,  1.57s/it]
Training 1/1 epoch (loss 1.6410):  56%|█████▌    | 878/1563 [22:37<17:55,  1.57s/it]
Training 1/1 epoch (loss 1.6410):  56%|█████▌    | 879/1563 [22:37<17:57,  1.58s/it]
Training 1/1 epoch (loss 1.6709):  56%|█████▌    | 879/1563 [22:39<17:57,  1.58s/it]
Training 1/1 epoch (loss 1.6709):  56%|█████▋    | 880/1563 [22:39<19:22,  1.70s/it]
Training 1/1 epoch (loss 1.6186):  56%|█████▋    | 880/1563 [22:40<19:22,  1.70s/it]
Training 1/1 epoch (loss 1.6186):  56%|█████▋    | 881/1563 [22:40<19:55,  1.75s/it]
Training 1/1 epoch (loss 1.5927):  56%|█████▋    | 881/1563 [22:43<19:55,  1.75s/it]
Training 1/1 epoch (loss 1.5927):  56%|█████▋    | 882/1563 [22:43<22:11,  1.96s/it]
Training 1/1 epoch (loss 1.7004):  56%|█████▋    | 882/1563 [22:45<22:11,  1.96s/it]
Training 1/1 epoch (loss 1.7004):  56%|█████▋    | 883/1563 [22:45<22:19,  1.97s/it]
Training 1/1 epoch (loss 1.5688):  56%|█████▋    | 883/1563 [22:47<22:19,  1.97s/it]
Training 1/1 epoch (loss 1.5688):  57%|█████▋    | 884/1563 [22:47<22:26,  1.98s/it]
Training 1/1 epoch (loss 1.6271):  57%|█████▋    | 884/1563 [22:49<22:26,  1.98s/it]
Training 1/1 epoch (loss 1.6271):  57%|█████▋    | 885/1563 [22:49<24:16,  2.15s/it]
Training 1/1 epoch (loss 1.5318):  57%|█████▋    | 885/1563 [22:51<24:16,  2.15s/it]
Training 1/1 epoch (loss 1.5318):  57%|█████▋    | 886/1563 [22:51<22:58,  2.04s/it]
Training 1/1 epoch (loss 1.7119):  57%|█████▋    | 886/1563 [22:54<22:58,  2.04s/it]
Training 1/1 epoch (loss 1.7119):  57%|█████▋    | 887/1563 [22:54<24:22,  2.16s/it]
Training 1/1 epoch (loss 1.5863):  57%|█████▋    | 887/1563 [22:55<24:22,  2.16s/it]
Training 1/1 epoch (loss 1.5863):  57%|█████▋    | 888/1563 [22:55<21:08,  1.88s/it]
Training 1/1 epoch (loss 1.6499):  57%|█████▋    | 888/1563 [22:56<21:08,  1.88s/it]
Training 1/1 epoch (loss 1.6499):  57%|█████▋    | 889/1563 [22:56<19:06,  1.70s/it]
Training 1/1 epoch (loss 1.6309):  57%|█████▋    | 889/1563 [22:57<19:06,  1.70s/it]
Training 1/1 epoch (loss 1.6309):  57%|█████▋    | 890/1563 [22:57<16:49,  1.50s/it]
Training 1/1 epoch (loss 1.6548):  57%|█████▋    | 890/1563 [22:59<16:49,  1.50s/it]
Training 1/1 epoch (loss 1.6548):  57%|█████▋    | 891/1563 [22:59<18:28,  1.65s/it]
Training 1/1 epoch (loss 1.6469):  57%|█████▋    | 891/1563 [23:00<18:28,  1.65s/it]
Training 1/1 epoch (loss 1.6469):  57%|█████▋    | 892/1563 [23:00<17:23,  1.56s/it]
Training 1/1 epoch (loss 1.5372):  57%|█████▋    | 892/1563 [23:02<17:23,  1.56s/it]
Training 1/1 epoch (loss 1.5372):  57%|█████▋    | 893/1563 [23:02<16:36,  1.49s/it]
Training 1/1 epoch (loss 1.6041):  57%|█████▋    | 893/1563 [23:03<16:36,  1.49s/it]
Training 1/1 epoch (loss 1.6041):  57%|█████▋    | 894/1563 [23:03<16:54,  1.52s/it]
Training 1/1 epoch (loss 1.6889):  57%|█████▋    | 894/1563 [23:05<16:54,  1.52s/it]
Training 1/1 epoch (loss 1.6889):  57%|█████▋    | 895/1563 [23:05<15:44,  1.41s/it]
Training 1/1 epoch (loss 1.5732):  57%|█████▋    | 895/1563 [23:07<15:44,  1.41s/it]
Training 1/1 epoch (loss 1.5732):  57%|█████▋    | 896/1563 [23:07<18:08,  1.63s/it]
Training 1/1 epoch (loss 1.6899):  57%|█████▋    | 896/1563 [23:08<18:08,  1.63s/it]
Training 1/1 epoch (loss 1.6899):  57%|█████▋    | 897/1563 [23:08<17:58,  1.62s/it]
Training 1/1 epoch (loss 1.6503):  57%|█████▋    | 897/1563 [23:10<17:58,  1.62s/it]
Training 1/1 epoch (loss 1.6503):  57%|█████▋    | 898/1563 [23:10<18:15,  1.65s/it]
Training 1/1 epoch (loss 1.5961):  57%|█████▋    | 898/1563 [23:12<18:15,  1.65s/it]
Training 1/1 epoch (loss 1.5961):  58%|█████▊    | 899/1563 [23:12<18:57,  1.71s/it]
Training 1/1 epoch (loss 1.7093):  58%|█████▊    | 899/1563 [23:14<18:57,  1.71s/it]
Training 1/1 epoch (loss 1.7093):  58%|█████▊    | 900/1563 [23:14<19:16,  1.74s/it]
Training 1/1 epoch (loss 1.5421):  58%|█████▊    | 900/1563 [23:15<19:16,  1.74s/it]
Training 1/1 epoch (loss 1.5421):  58%|█████▊    | 901/1563 [23:15<17:32,  1.59s/it]
Training 1/1 epoch (loss 1.5642):  58%|█████▊    | 901/1563 [23:17<17:32,  1.59s/it]
Training 1/1 epoch (loss 1.5642):  58%|█████▊    | 902/1563 [23:17<18:47,  1.71s/it]
Training 1/1 epoch (loss 1.6610):  58%|█████▊    | 902/1563 [23:19<18:47,  1.71s/it]
Training 1/1 epoch (loss 1.6610):  58%|█████▊    | 903/1563 [23:19<19:07,  1.74s/it]
Training 1/1 epoch (loss 1.5503):  58%|█████▊    | 903/1563 [23:21<19:07,  1.74s/it]
Training 1/1 epoch (loss 1.5503):  58%|█████▊    | 904/1563 [23:21<19:21,  1.76s/it]
Training 1/1 epoch (loss 1.6616):  58%|█████▊    | 904/1563 [23:22<19:21,  1.76s/it]
Training 1/1 epoch (loss 1.6616):  58%|█████▊    | 905/1563 [23:22<17:22,  1.58s/it]
Training 1/1 epoch (loss 1.7245):  58%|█████▊    | 905/1563 [23:23<17:22,  1.58s/it]
Training 1/1 epoch (loss 1.7245):  58%|█████▊    | 906/1563 [23:23<16:17,  1.49s/it]
Training 1/1 epoch (loss 1.5682):  58%|█████▊    | 906/1563 [23:24<16:17,  1.49s/it]
Training 1/1 epoch (loss 1.5682):  58%|█████▊    | 907/1563 [23:24<15:25,  1.41s/it]
Training 1/1 epoch (loss 1.6745):  58%|█████▊    | 907/1563 [23:26<15:25,  1.41s/it]
Training 1/1 epoch (loss 1.6745):  58%|█████▊    | 908/1563 [23:26<17:05,  1.57s/it]
Training 1/1 epoch (loss 1.5534):  58%|█████▊    | 908/1563 [23:27<17:05,  1.57s/it]
Training 1/1 epoch (loss 1.5534):  58%|█████▊    | 909/1563 [23:27<15:50,  1.45s/it]
Training 1/1 epoch (loss 1.6521):  58%|█████▊    | 909/1563 [23:30<15:50,  1.45s/it]
Training 1/1 epoch (loss 1.6521):  58%|█████▊    | 910/1563 [23:30<19:03,  1.75s/it]
Training 1/1 epoch (loss 1.6678):  58%|█████▊    | 910/1563 [23:32<19:03,  1.75s/it]
Training 1/1 epoch (loss 1.6678):  58%|█████▊    | 911/1563 [23:32<19:55,  1.83s/it]
Training 1/1 epoch (loss 1.5540):  58%|█████▊    | 911/1563 [23:34<19:55,  1.83s/it]
Training 1/1 epoch (loss 1.5540):  58%|█████▊    | 912/1563 [23:34<22:23,  2.06s/it]
Training 1/1 epoch (loss 1.6426):  58%|█████▊    | 912/1563 [23:36<22:23,  2.06s/it]
Training 1/1 epoch (loss 1.6426):  58%|█████▊    | 913/1563 [23:36<22:25,  2.07s/it]
Training 1/1 epoch (loss 1.4786):  58%|█████▊    | 913/1563 [23:39<22:25,  2.07s/it]
Training 1/1 epoch (loss 1.4786):  58%|█████▊    | 914/1563 [23:39<22:15,  2.06s/it]
Training 1/1 epoch (loss 1.7107):  58%|█████▊    | 914/1563 [23:41<22:15,  2.06s/it]
Training 1/1 epoch (loss 1.7107):  59%|█████▊    | 915/1563 [23:41<23:24,  2.17s/it]
Training 1/1 epoch (loss 1.5617):  59%|█████▊    | 915/1563 [23:42<23:24,  2.17s/it]
Training 1/1 epoch (loss 1.5617):  59%|█████▊    | 916/1563 [23:42<20:09,  1.87s/it]
Training 1/1 epoch (loss 1.5542):  59%|█████▊    | 916/1563 [23:44<20:09,  1.87s/it]
Training 1/1 epoch (loss 1.5542):  59%|█████▊    | 917/1563 [23:44<19:49,  1.84s/it]
Training 1/1 epoch (loss 1.5374):  59%|█████▊    | 917/1563 [23:46<19:49,  1.84s/it]
Training 1/1 epoch (loss 1.5374):  59%|█████▊    | 918/1563 [23:46<20:02,  1.86s/it]
Training 1/1 epoch (loss 1.7507):  59%|█████▊    | 918/1563 [23:48<20:02,  1.86s/it]
Training 1/1 epoch (loss 1.7507):  59%|█████▉    | 919/1563 [23:48<19:36,  1.83s/it]
Training 1/1 epoch (loss 1.6757):  59%|█████▉    | 919/1563 [23:49<19:36,  1.83s/it]
Training 1/1 epoch (loss 1.6757):  59%|█████▉    | 920/1563 [23:49<18:30,  1.73s/it]
Training 1/1 epoch (loss 1.5129):  59%|█████▉    | 920/1563 [23:52<18:30,  1.73s/it]
Training 1/1 epoch (loss 1.5129):  59%|█████▉    | 921/1563 [23:52<20:53,  1.95s/it]
Training 1/1 epoch (loss 1.6228):  59%|█████▉    | 921/1563 [23:53<20:53,  1.95s/it]
Training 1/1 epoch (loss 1.6228):  59%|█████▉    | 922/1563 [23:53<19:33,  1.83s/it]
Training 1/1 epoch (loss 1.5916):  59%|█████▉    | 922/1563 [23:55<19:33,  1.83s/it]
Training 1/1 epoch (loss 1.5916):  59%|█████▉    | 923/1563 [23:55<18:49,  1.77s/it]
Training 1/1 epoch (loss 1.5963):  59%|█████▉    | 923/1563 [23:56<18:49,  1.77s/it]
Training 1/1 epoch (loss 1.5963):  59%|█████▉    | 924/1563 [23:56<17:44,  1.67s/it]
Training 1/1 epoch (loss 1.5459):  59%|█████▉    | 924/1563 [23:59<17:44,  1.67s/it]
Training 1/1 epoch (loss 1.5459):  59%|█████▉    | 925/1563 [23:59<20:32,  1.93s/it]
Training 1/1 epoch (loss 1.5969):  59%|█████▉    | 925/1563 [24:01<20:32,  1.93s/it]
Training 1/1 epoch (loss 1.5969):  59%|█████▉    | 926/1563 [24:01<22:06,  2.08s/it]
Training 1/1 epoch (loss 1.5831):  59%|█████▉    | 926/1563 [24:03<22:06,  2.08s/it]
Training 1/1 epoch (loss 1.5831):  59%|█████▉    | 927/1563 [24:03<20:37,  1.95s/it]
Training 1/1 epoch (loss 1.5425):  59%|█████▉    | 927/1563 [24:05<20:37,  1.95s/it]
Training 1/1 epoch (loss 1.5425):  59%|█████▉    | 928/1563 [24:05<20:49,  1.97s/it]
Training 1/1 epoch (loss 1.7486):  59%|█████▉    | 928/1563 [24:06<20:49,  1.97s/it]
Training 1/1 epoch (loss 1.7486):  59%|█████▉    | 929/1563 [24:06<17:56,  1.70s/it]
Training 1/1 epoch (loss 1.6295):  59%|█████▉    | 929/1563 [24:08<17:56,  1.70s/it]
Training 1/1 epoch (loss 1.6295):  60%|█████▉    | 930/1563 [24:08<19:02,  1.80s/it]
Training 1/1 epoch (loss 1.5828):  60%|█████▉    | 930/1563 [24:10<19:02,  1.80s/it]
Training 1/1 epoch (loss 1.5828):  60%|█████▉    | 931/1563 [24:10<20:19,  1.93s/it]
Training 1/1 epoch (loss 1.5978):  60%|█████▉    | 931/1563 [24:12<20:19,  1.93s/it]
Training 1/1 epoch (loss 1.5978):  60%|█████▉    | 932/1563 [24:12<20:35,  1.96s/it]
Training 1/1 epoch (loss 1.6023):  60%|█████▉    | 932/1563 [24:13<20:35,  1.96s/it]
Training 1/1 epoch (loss 1.6023):  60%|█████▉    | 933/1563 [24:13<18:39,  1.78s/it]
Training 1/1 epoch (loss 1.6607):  60%|█████▉    | 933/1563 [24:15<18:39,  1.78s/it]
Training 1/1 epoch (loss 1.6607):  60%|█████▉    | 934/1563 [24:15<16:45,  1.60s/it]
Training 1/1 epoch (loss 1.5809):  60%|█████▉    | 934/1563 [24:16<16:45,  1.60s/it]
Training 1/1 epoch (loss 1.5809):  60%|█████▉    | 935/1563 [24:16<14:59,  1.43s/it]
Training 1/1 epoch (loss 1.5741):  60%|█████▉    | 935/1563 [24:18<14:59,  1.43s/it]
Training 1/1 epoch (loss 1.5741):  60%|█████▉    | 936/1563 [24:18<16:22,  1.57s/it]
Training 1/1 epoch (loss 1.5267):  60%|█████▉    | 936/1563 [24:20<16:22,  1.57s/it]
Training 1/1 epoch (loss 1.5267):  60%|█████▉    | 937/1563 [24:20<18:14,  1.75s/it]
Training 1/1 epoch (loss 1.5927):  60%|█████▉    | 937/1563 [24:22<18:14,  1.75s/it]
Training 1/1 epoch (loss 1.5927):  60%|██████    | 938/1563 [24:22<19:20,  1.86s/it]
Training 1/1 epoch (loss 1.5326):  60%|██████    | 938/1563 [24:24<19:20,  1.86s/it]
Training 1/1 epoch (loss 1.5326):  60%|██████    | 939/1563 [24:24<19:56,  1.92s/it]
Training 1/1 epoch (loss 1.5817):  60%|██████    | 939/1563 [24:25<19:56,  1.92s/it]
Training 1/1 epoch (loss 1.5817):  60%|██████    | 940/1563 [24:25<17:28,  1.68s/it]
Training 1/1 epoch (loss 1.5120):  60%|██████    | 940/1563 [24:27<17:28,  1.68s/it]
Training 1/1 epoch (loss 1.5120):  60%|██████    | 941/1563 [24:27<18:07,  1.75s/it]
Training 1/1 epoch (loss 1.6075):  60%|██████    | 941/1563 [24:28<18:07,  1.75s/it]
Training 1/1 epoch (loss 1.6075):  60%|██████    | 942/1563 [24:28<16:57,  1.64s/it]
Training 1/1 epoch (loss 1.6275):  60%|██████    | 942/1563 [24:30<16:57,  1.64s/it]
Training 1/1 epoch (loss 1.6275):  60%|██████    | 943/1563 [24:30<16:59,  1.64s/it]
Training 1/1 epoch (loss 1.6098):  60%|██████    | 943/1563 [24:32<16:59,  1.64s/it]
Training 1/1 epoch (loss 1.6098):  60%|██████    | 944/1563 [24:32<18:52,  1.83s/it]
Training 1/1 epoch (loss 1.5562):  60%|██████    | 944/1563 [24:35<18:52,  1.83s/it]
Training 1/1 epoch (loss 1.5562):  60%|██████    | 945/1563 [24:35<20:26,  1.98s/it]
Training 1/1 epoch (loss 1.5872):  60%|██████    | 945/1563 [24:36<20:26,  1.98s/it]
Training 1/1 epoch (loss 1.5872):  61%|██████    | 946/1563 [24:36<19:54,  1.94s/it]
Training 1/1 epoch (loss 1.7368):  61%|██████    | 946/1563 [24:38<19:54,  1.94s/it]
Training 1/1 epoch (loss 1.7368):  61%|██████    | 947/1563 [24:38<20:18,  1.98s/it]
Training 1/1 epoch (loss 1.5874):  61%|██████    | 947/1563 [24:40<20:18,  1.98s/it]
Training 1/1 epoch (loss 1.5874):  61%|██████    | 948/1563 [24:40<19:09,  1.87s/it]
Training 1/1 epoch (loss 1.4966):  61%|██████    | 948/1563 [24:42<19:09,  1.87s/it]
Training 1/1 epoch (loss 1.4966):  61%|██████    | 949/1563 [24:42<19:46,  1.93s/it]
Training 1/1 epoch (loss 1.5692):  61%|██████    | 949/1563 [24:44<19:46,  1.93s/it]
Training 1/1 epoch (loss 1.5692):  61%|██████    | 950/1563 [24:44<19:03,  1.87s/it]
Training 1/1 epoch (loss 1.5923):  61%|██████    | 950/1563 [24:46<19:03,  1.87s/it]
Training 1/1 epoch (loss 1.5923):  61%|██████    | 951/1563 [24:46<18:17,  1.79s/it]
Training 1/1 epoch (loss 1.6214):  61%|██████    | 951/1563 [24:48<18:17,  1.79s/it]
Training 1/1 epoch (loss 1.6214):  61%|██████    | 952/1563 [24:48<19:54,  1.96s/it]
Training 1/1 epoch (loss 1.5624):  61%|██████    | 952/1563 [24:49<19:54,  1.96s/it]
Training 1/1 epoch (loss 1.5624):  61%|██████    | 953/1563 [24:49<17:52,  1.76s/it]
Training 1/1 epoch (loss 1.6873):  61%|██████    | 953/1563 [24:51<17:52,  1.76s/it]
Training 1/1 epoch (loss 1.6873):  61%|██████    | 954/1563 [24:51<17:04,  1.68s/it]
Training 1/1 epoch (loss 1.4946):  61%|██████    | 954/1563 [24:53<17:04,  1.68s/it]
Training 1/1 epoch (loss 1.4946):  61%|██████    | 955/1563 [24:53<18:48,  1.86s/it]
Training 1/1 epoch (loss 1.6531):  61%|██████    | 955/1563 [24:54<18:48,  1.86s/it]
Training 1/1 epoch (loss 1.6531):  61%|██████    | 956/1563 [24:54<16:07,  1.59s/it]
Training 1/1 epoch (loss 1.5741):  61%|██████    | 956/1563 [24:55<16:07,  1.59s/it]
Training 1/1 epoch (loss 1.5741):  61%|██████    | 957/1563 [24:55<15:17,  1.51s/it]
Training 1/1 epoch (loss 1.4656):  61%|██████    | 957/1563 [24:57<15:17,  1.51s/it]
Training 1/1 epoch (loss 1.4656):  61%|██████▏   | 958/1563 [24:57<16:12,  1.61s/it]
Training 1/1 epoch (loss 1.6343):  61%|██████▏   | 958/1563 [24:58<16:12,  1.61s/it]
Training 1/1 epoch (loss 1.6343):  61%|██████▏   | 959/1563 [24:58<15:10,  1.51s/it]
Training 1/1 epoch (loss 1.6493):  61%|██████▏   | 959/1563 [24:59<15:10,  1.51s/it]
Training 1/1 epoch (loss 1.6493):  61%|██████▏   | 960/1563 [24:59<13:47,  1.37s/it]
Training 1/1 epoch (loss 1.6907):  61%|██████▏   | 960/1563 [25:02<13:47,  1.37s/it]
Training 1/1 epoch (loss 1.6907):  61%|██████▏   | 961/1563 [25:02<16:40,  1.66s/it]
Training 1/1 epoch (loss 1.5960):  61%|██████▏   | 961/1563 [25:04<16:40,  1.66s/it]
Training 1/1 epoch (loss 1.5960):  62%|██████▏   | 962/1563 [25:04<17:16,  1.72s/it]
Training 1/1 epoch (loss 1.6204):  62%|██████▏   | 962/1563 [25:06<17:16,  1.72s/it]
Training 1/1 epoch (loss 1.6204):  62%|██████▏   | 963/1563 [25:06<18:31,  1.85s/it]
Training 1/1 epoch (loss 1.5922):  62%|██████▏   | 963/1563 [25:07<18:31,  1.85s/it]
Training 1/1 epoch (loss 1.5922):  62%|██████▏   | 964/1563 [25:07<16:40,  1.67s/it]
Training 1/1 epoch (loss 1.6296):  62%|██████▏   | 964/1563 [25:09<16:40,  1.67s/it]
Training 1/1 epoch (loss 1.6296):  62%|██████▏   | 965/1563 [25:09<16:26,  1.65s/it]
Training 1/1 epoch (loss 1.7278):  62%|██████▏   | 965/1563 [25:11<16:26,  1.65s/it]
Training 1/1 epoch (loss 1.7278):  62%|██████▏   | 966/1563 [25:11<17:20,  1.74s/it]
Training 1/1 epoch (loss 1.5258):  62%|██████▏   | 966/1563 [25:12<17:20,  1.74s/it]
Training 1/1 epoch (loss 1.5258):  62%|██████▏   | 967/1563 [25:12<16:33,  1.67s/it]
Training 1/1 epoch (loss 1.6301):  62%|██████▏   | 967/1563 [25:14<16:33,  1.67s/it]
Training 1/1 epoch (loss 1.6301):  62%|██████▏   | 968/1563 [25:14<16:10,  1.63s/it]
Training 1/1 epoch (loss 1.4069):  62%|██████▏   | 968/1563 [25:15<16:10,  1.63s/it]
Training 1/1 epoch (loss 1.4069):  62%|██████▏   | 969/1563 [25:15<16:52,  1.70s/it]
Training 1/1 epoch (loss 1.6634):  62%|██████▏   | 969/1563 [25:17<16:52,  1.70s/it]
Training 1/1 epoch (loss 1.6634):  62%|██████▏   | 970/1563 [25:17<16:24,  1.66s/it]
Training 1/1 epoch (loss 1.6001):  62%|██████▏   | 970/1563 [25:18<16:24,  1.66s/it]
Training 1/1 epoch (loss 1.6001):  62%|██████▏   | 971/1563 [25:18<14:20,  1.45s/it]
Training 1/1 epoch (loss 1.5123):  62%|██████▏   | 971/1563 [25:20<14:20,  1.45s/it]
Training 1/1 epoch (loss 1.5123):  62%|██████▏   | 972/1563 [25:20<15:23,  1.56s/it]
Training 1/1 epoch (loss 1.6109):  62%|██████▏   | 972/1563 [25:21<15:23,  1.56s/it]
Training 1/1 epoch (loss 1.6109):  62%|██████▏   | 973/1563 [25:21<15:12,  1.55s/it]
Training 1/1 epoch (loss 1.5364):  62%|██████▏   | 973/1563 [25:23<15:12,  1.55s/it]
Training 1/1 epoch (loss 1.5364):  62%|██████▏   | 974/1563 [25:23<14:38,  1.49s/it]
Training 1/1 epoch (loss 1.5585):  62%|██████▏   | 974/1563 [25:25<14:38,  1.49s/it]
Training 1/1 epoch (loss 1.5585):  62%|██████▏   | 975/1563 [25:25<17:31,  1.79s/it]
Training 1/1 epoch (loss 1.6555):  62%|██████▏   | 975/1563 [25:27<17:31,  1.79s/it]
Training 1/1 epoch (loss 1.6555):  62%|██████▏   | 976/1563 [25:27<16:55,  1.73s/it]
Training 1/1 epoch (loss 1.5269):  62%|██████▏   | 976/1563 [25:28<16:55,  1.73s/it]
Training 1/1 epoch (loss 1.5269):  63%|██████▎   | 977/1563 [25:28<15:18,  1.57s/it]
Training 1/1 epoch (loss 1.6337):  63%|██████▎   | 977/1563 [25:29<15:18,  1.57s/it]
Training 1/1 epoch (loss 1.6337):  63%|██████▎   | 978/1563 [25:29<15:09,  1.56s/it]
Training 1/1 epoch (loss 1.5394):  63%|██████▎   | 978/1563 [25:31<15:09,  1.56s/it]
Training 1/1 epoch (loss 1.5394):  63%|██████▎   | 979/1563 [25:31<14:33,  1.50s/it]
Training 1/1 epoch (loss 1.6516):  63%|██████▎   | 979/1563 [25:32<14:33,  1.50s/it]
Training 1/1 epoch (loss 1.6516):  63%|██████▎   | 980/1563 [25:32<14:47,  1.52s/it]
Training 1/1 epoch (loss 1.7402):  63%|██████▎   | 980/1563 [25:35<14:47,  1.52s/it]
Training 1/1 epoch (loss 1.7402):  63%|██████▎   | 981/1563 [25:35<16:45,  1.73s/it]
Training 1/1 epoch (loss 1.5921):  63%|██████▎   | 981/1563 [25:36<16:45,  1.73s/it]
Training 1/1 epoch (loss 1.5921):  63%|██████▎   | 982/1563 [25:36<16:58,  1.75s/it]
Training 1/1 epoch (loss 1.6839):  63%|██████▎   | 982/1563 [25:38<16:58,  1.75s/it]
Training 1/1 epoch (loss 1.6839):  63%|██████▎   | 983/1563 [25:38<16:18,  1.69s/it]
Training 1/1 epoch (loss 1.6992):  63%|██████▎   | 983/1563 [25:39<16:18,  1.69s/it]
Training 1/1 epoch (loss 1.6992):  63%|██████▎   | 984/1563 [25:39<15:10,  1.57s/it]
Training 1/1 epoch (loss 1.6478):  63%|██████▎   | 984/1563 [25:42<15:10,  1.57s/it]
Training 1/1 epoch (loss 1.6478):  63%|██████▎   | 985/1563 [25:42<17:41,  1.84s/it]
Training 1/1 epoch (loss 1.7797):  63%|██████▎   | 985/1563 [25:44<17:41,  1.84s/it]
Training 1/1 epoch (loss 1.7797):  63%|██████▎   | 986/1563 [25:44<19:12,  2.00s/it]
Training 1/1 epoch (loss 1.4420):  63%|██████▎   | 986/1563 [25:45<19:12,  2.00s/it]
Training 1/1 epoch (loss 1.4420):  63%|██████▎   | 987/1563 [25:45<16:13,  1.69s/it]
Training 1/1 epoch (loss 1.5493):  63%|██████▎   | 987/1563 [25:46<16:13,  1.69s/it]
Training 1/1 epoch (loss 1.5493):  63%|██████▎   | 988/1563 [25:46<14:41,  1.53s/it]
Training 1/1 epoch (loss 1.6185):  63%|██████▎   | 988/1563 [25:47<14:41,  1.53s/it]
Training 1/1 epoch (loss 1.6185):  63%|██████▎   | 989/1563 [25:47<13:42,  1.43s/it]
Training 1/1 epoch (loss 1.6530):  63%|██████▎   | 989/1563 [25:49<13:42,  1.43s/it]
Training 1/1 epoch (loss 1.6530):  63%|██████▎   | 990/1563 [25:49<14:40,  1.54s/it]
Training 1/1 epoch (loss 1.5944):  63%|██████▎   | 990/1563 [25:51<14:40,  1.54s/it]
Training 1/1 epoch (loss 1.5944):  63%|██████▎   | 991/1563 [25:51<16:13,  1.70s/it]
Training 1/1 epoch (loss 1.5502):  63%|██████▎   | 991/1563 [25:53<16:13,  1.70s/it]
Training 1/1 epoch (loss 1.5502):  63%|██████▎   | 992/1563 [25:53<16:29,  1.73s/it]
Training 1/1 epoch (loss 1.6800):  63%|██████▎   | 992/1563 [25:55<16:29,  1.73s/it]
Training 1/1 epoch (loss 1.6800):  64%|██████▎   | 993/1563 [25:55<17:43,  1.87s/it]
Training 1/1 epoch (loss 1.5176):  64%|██████▎   | 993/1563 [25:56<17:43,  1.87s/it]
Training 1/1 epoch (loss 1.5176):  64%|██████▎   | 994/1563 [25:56<15:43,  1.66s/it]
Training 1/1 epoch (loss 1.5543):  64%|██████▎   | 994/1563 [25:58<15:43,  1.66s/it]
Training 1/1 epoch (loss 1.5543):  64%|██████▎   | 995/1563 [25:58<16:29,  1.74s/it]
Training 1/1 epoch (loss 1.5258):  64%|██████▎   | 995/1563 [26:00<16:29,  1.74s/it]
Training 1/1 epoch (loss 1.5258):  64%|██████▎   | 996/1563 [26:00<14:49,  1.57s/it]
Training 1/1 epoch (loss 1.6612):  64%|██████▎   | 996/1563 [26:02<14:49,  1.57s/it]
Training 1/1 epoch (loss 1.6612):  64%|██████▍   | 997/1563 [26:02<17:16,  1.83s/it]
Training 1/1 epoch (loss 1.5775):  64%|██████▍   | 997/1563 [26:03<17:16,  1.83s/it]
Training 1/1 epoch (loss 1.5775):  64%|██████▍   | 998/1563 [26:03<14:55,  1.59s/it]
Training 1/1 epoch (loss 1.5693):  64%|██████▍   | 998/1563 [26:05<14:55,  1.59s/it]
Training 1/1 epoch (loss 1.5693):  64%|██████▍   | 999/1563 [26:05<17:11,  1.83s/it]
Training 1/1 epoch (loss 1.4555):  64%|██████▍   | 999/1563 [26:07<17:11,  1.83s/it]
Training 1/1 epoch (loss 1.4555):  64%|██████▍   | 1000/1563 [26:07<15:38,  1.67s/it]
Training 1/1 epoch (loss 1.6524):  64%|██████▍   | 1000/1563 [26:09<15:38,  1.67s/it]
Training 1/1 epoch (loss 1.6524):  64%|██████▍   | 1001/1563 [26:09<17:31,  1.87s/it]
Training 1/1 epoch (loss 1.5550):  64%|██████▍   | 1001/1563 [26:11<17:31,  1.87s/it]
Training 1/1 epoch (loss 1.5550):  64%|██████▍   | 1002/1563 [26:11<17:24,  1.86s/it]
Training 1/1 epoch (loss 1.5881):  64%|██████▍   | 1002/1563 [26:12<17:24,  1.86s/it]
Training 1/1 epoch (loss 1.5881):  64%|██████▍   | 1003/1563 [26:12<16:29,  1.77s/it]
Training 1/1 epoch (loss 1.7481):  64%|██████▍   | 1003/1563 [26:15<16:29,  1.77s/it]
Training 1/1 epoch (loss 1.7481):  64%|██████▍   | 1004/1563 [26:15<18:10,  1.95s/it]
Training 1/1 epoch (loss 1.6477):  64%|██████▍   | 1004/1563 [26:16<18:10,  1.95s/it]
Training 1/1 epoch (loss 1.6477):  64%|██████▍   | 1005/1563 [26:16<16:24,  1.76s/it]
Training 1/1 epoch (loss 1.5666):  64%|██████▍   | 1005/1563 [26:18<16:24,  1.76s/it]
Training 1/1 epoch (loss 1.5666):  64%|██████▍   | 1006/1563 [26:18<18:01,  1.94s/it]
Training 1/1 epoch (loss 1.5903):  64%|██████▍   | 1006/1563 [26:20<18:01,  1.94s/it]
Training 1/1 epoch (loss 1.5903):  64%|██████▍   | 1007/1563 [26:20<17:50,  1.93s/it]
Training 1/1 epoch (loss 1.6156):  64%|██████▍   | 1007/1563 [26:22<17:50,  1.93s/it]
Training 1/1 epoch (loss 1.6156):  64%|██████▍   | 1008/1563 [26:22<18:19,  1.98s/it]
Training 1/1 epoch (loss 1.5345):  64%|██████▍   | 1008/1563 [26:24<18:19,  1.98s/it]
Training 1/1 epoch (loss 1.5345):  65%|██████▍   | 1009/1563 [26:24<17:52,  1.94s/it]
Training 1/1 epoch (loss 1.6326):  65%|██████▍   | 1009/1563 [26:26<17:52,  1.94s/it]
Training 1/1 epoch (loss 1.6326):  65%|██████▍   | 1010/1563 [26:26<18:21,  1.99s/it]
Training 1/1 epoch (loss 1.6208):  65%|██████▍   | 1010/1563 [26:29<18:21,  1.99s/it]
Training 1/1 epoch (loss 1.6208):  65%|██████▍   | 1011/1563 [26:29<18:36,  2.02s/it]
Training 1/1 epoch (loss 1.6111):  65%|██████▍   | 1011/1563 [26:31<18:36,  2.02s/it]
Training 1/1 epoch (loss 1.6111):  65%|██████▍   | 1012/1563 [26:31<18:48,  2.05s/it]
Training 1/1 epoch (loss 1.6332):  65%|██████▍   | 1012/1563 [26:32<18:48,  2.05s/it]
Training 1/1 epoch (loss 1.6332):  65%|██████▍   | 1013/1563 [26:32<16:41,  1.82s/it]
Training 1/1 epoch (loss 1.5596):  65%|██████▍   | 1013/1563 [26:33<16:41,  1.82s/it]
Training 1/1 epoch (loss 1.5596):  65%|██████▍   | 1014/1563 [26:33<15:48,  1.73s/it]
Training 1/1 epoch (loss 1.5916):  65%|██████▍   | 1014/1563 [26:35<15:48,  1.73s/it]
Training 1/1 epoch (loss 1.5916):  65%|██████▍   | 1015/1563 [26:35<14:49,  1.62s/it]
Training 1/1 epoch (loss 1.5573):  65%|██████▍   | 1015/1563 [26:38<14:49,  1.62s/it]
Training 1/1 epoch (loss 1.5573):  65%|██████▌   | 1016/1563 [26:38<17:41,  1.94s/it]
Training 1/1 epoch (loss 1.5860):  65%|██████▌   | 1016/1563 [26:39<17:41,  1.94s/it]
Training 1/1 epoch (loss 1.5860):  65%|██████▌   | 1017/1563 [26:39<16:41,  1.83s/it]
Training 1/1 epoch (loss 1.5891):  65%|██████▌   | 1017/1563 [26:41<16:41,  1.83s/it]
Training 1/1 epoch (loss 1.5891):  65%|██████▌   | 1018/1563 [26:41<15:39,  1.72s/it]
Training 1/1 epoch (loss 1.4698):  65%|██████▌   | 1018/1563 [26:42<15:39,  1.72s/it]
Training 1/1 epoch (loss 1.4698):  65%|██████▌   | 1019/1563 [26:42<15:25,  1.70s/it]
Training 1/1 epoch (loss 1.5475):  65%|██████▌   | 1019/1563 [26:44<15:25,  1.70s/it]
Training 1/1 epoch (loss 1.5475):  65%|██████▌   | 1020/1563 [26:44<14:55,  1.65s/it]
Training 1/1 epoch (loss 1.7190):  65%|██████▌   | 1020/1563 [26:45<14:55,  1.65s/it]
Training 1/1 epoch (loss 1.7190):  65%|██████▌   | 1021/1563 [26:45<14:34,  1.61s/it]
Training 1/1 epoch (loss 1.6715):  65%|██████▌   | 1021/1563 [26:47<14:34,  1.61s/it]
Training 1/1 epoch (loss 1.6715):  65%|██████▌   | 1022/1563 [26:47<14:27,  1.60s/it]
Training 1/1 epoch (loss 1.5820):  65%|██████▌   | 1022/1563 [26:49<14:27,  1.60s/it]
Training 1/1 epoch (loss 1.5820):  65%|██████▌   | 1023/1563 [26:49<15:38,  1.74s/it]
Training 1/1 epoch (loss 1.5760):  65%|██████▌   | 1023/1563 [26:51<15:38,  1.74s/it]
Training 1/1 epoch (loss 1.5760):  66%|██████▌   | 1024/1563 [26:51<15:49,  1.76s/it]
Training 1/1 epoch (loss 1.5693):  66%|██████▌   | 1024/1563 [26:52<15:49,  1.76s/it]
Training 1/1 epoch (loss 1.5693):  66%|██████▌   | 1025/1563 [26:52<15:18,  1.71s/it]
Training 1/1 epoch (loss 1.6578):  66%|██████▌   | 1025/1563 [26:55<15:18,  1.71s/it]
Training 1/1 epoch (loss 1.6578):  66%|██████▌   | 1026/1563 [26:55<17:12,  1.92s/it]
Training 1/1 epoch (loss 1.5860):  66%|██████▌   | 1026/1563 [26:56<17:12,  1.92s/it]
Training 1/1 epoch (loss 1.5860):  66%|██████▌   | 1027/1563 [26:56<15:38,  1.75s/it]
Training 1/1 epoch (loss 1.6074):  66%|██████▌   | 1027/1563 [26:58<15:38,  1.75s/it]
Training 1/1 epoch (loss 1.6074):  66%|██████▌   | 1028/1563 [26:58<16:14,  1.82s/it]
Training 1/1 epoch (loss 1.5825):  66%|██████▌   | 1028/1563 [26:59<16:14,  1.82s/it]
Training 1/1 epoch (loss 1.5825):  66%|██████▌   | 1029/1563 [26:59<14:51,  1.67s/it]
Training 1/1 epoch (loss 1.5254):  66%|██████▌   | 1029/1563 [27:01<14:51,  1.67s/it]
Training 1/1 epoch (loss 1.5254):  66%|██████▌   | 1030/1563 [27:01<15:37,  1.76s/it]
Training 1/1 epoch (loss 1.5486):  66%|██████▌   | 1030/1563 [27:03<15:37,  1.76s/it]
Training 1/1 epoch (loss 1.5486):  66%|██████▌   | 1031/1563 [27:03<14:04,  1.59s/it]
Training 1/1 epoch (loss 1.5689):  66%|██████▌   | 1031/1563 [27:04<14:04,  1.59s/it]
Training 1/1 epoch (loss 1.5689):  66%|██████▌   | 1032/1563 [27:04<14:44,  1.67s/it]
Training 1/1 epoch (loss 1.6389):  66%|██████▌   | 1032/1563 [27:06<14:44,  1.67s/it]
Training 1/1 epoch (loss 1.6389):  66%|██████▌   | 1033/1563 [27:06<13:36,  1.54s/it]
Training 1/1 epoch (loss 1.6808):  66%|██████▌   | 1033/1563 [27:07<13:36,  1.54s/it]
Training 1/1 epoch (loss 1.6808):  66%|██████▌   | 1034/1563 [27:07<12:59,  1.47s/it]
Training 1/1 epoch (loss 1.6457):  66%|██████▌   | 1034/1563 [27:09<12:59,  1.47s/it]
Training 1/1 epoch (loss 1.6457):  66%|██████▌   | 1035/1563 [27:09<13:46,  1.57s/it]
Training 1/1 epoch (loss 1.6168):  66%|██████▌   | 1035/1563 [27:11<13:46,  1.57s/it]
Training 1/1 epoch (loss 1.6168):  66%|██████▋   | 1036/1563 [27:11<14:30,  1.65s/it]
Training 1/1 epoch (loss 1.5192):  66%|██████▋   | 1036/1563 [27:12<14:30,  1.65s/it]
Training 1/1 epoch (loss 1.5192):  66%|██████▋   | 1037/1563 [27:12<14:10,  1.62s/it]
Training 1/1 epoch (loss 1.6063):  66%|██████▋   | 1037/1563 [27:14<14:10,  1.62s/it]
Training 1/1 epoch (loss 1.6063):  66%|██████▋   | 1038/1563 [27:14<14:20,  1.64s/it]
Training 1/1 epoch (loss 1.5013):  66%|██████▋   | 1038/1563 [27:16<14:20,  1.64s/it]
Training 1/1 epoch (loss 1.5013):  66%|██████▋   | 1039/1563 [27:16<15:03,  1.72s/it]
Training 1/1 epoch (loss 1.5817):  66%|██████▋   | 1039/1563 [27:17<15:03,  1.72s/it]
Training 1/1 epoch (loss 1.5817):  67%|██████▋   | 1040/1563 [27:17<14:46,  1.70s/it]
Training 1/1 epoch (loss 1.6513):  67%|██████▋   | 1040/1563 [27:19<14:46,  1.70s/it]
Training 1/1 epoch (loss 1.6513):  67%|██████▋   | 1041/1563 [27:19<14:22,  1.65s/it]
Training 1/1 epoch (loss 1.6229):  67%|██████▋   | 1041/1563 [27:20<14:22,  1.65s/it]
Training 1/1 epoch (loss 1.6229):  67%|██████▋   | 1042/1563 [27:20<12:52,  1.48s/it]
Training 1/1 epoch (loss 1.5048):  67%|██████▋   | 1042/1563 [27:22<12:52,  1.48s/it]
Training 1/1 epoch (loss 1.5048):  67%|██████▋   | 1043/1563 [27:22<13:05,  1.51s/it]
Training 1/1 epoch (loss 1.6308):  67%|██████▋   | 1043/1563 [27:23<13:05,  1.51s/it]
Training 1/1 epoch (loss 1.6308):  67%|██████▋   | 1044/1563 [27:23<13:19,  1.54s/it]
Training 1/1 epoch (loss 1.5681):  67%|██████▋   | 1044/1563 [27:25<13:19,  1.54s/it]
Training 1/1 epoch (loss 1.5681):  67%|██████▋   | 1045/1563 [27:25<13:44,  1.59s/it]
Training 1/1 epoch (loss 1.6329):  67%|██████▋   | 1045/1563 [27:26<13:44,  1.59s/it]
Training 1/1 epoch (loss 1.6329):  67%|██████▋   | 1046/1563 [27:26<13:25,  1.56s/it]
Training 1/1 epoch (loss 1.6456):  67%|██████▋   | 1046/1563 [27:28<13:25,  1.56s/it]
Training 1/1 epoch (loss 1.6456):  67%|██████▋   | 1047/1563 [27:28<13:36,  1.58s/it]
Training 1/1 epoch (loss 1.7347):  67%|██████▋   | 1047/1563 [27:31<13:36,  1.58s/it]
Training 1/1 epoch (loss 1.7347):  67%|██████▋   | 1048/1563 [27:31<16:11,  1.89s/it]
Training 1/1 epoch (loss 1.6032):  67%|██████▋   | 1048/1563 [27:32<16:11,  1.89s/it]
Training 1/1 epoch (loss 1.6032):  67%|██████▋   | 1049/1563 [27:32<15:21,  1.79s/it]
Training 1/1 epoch (loss 1.5181):  67%|██████▋   | 1049/1563 [27:33<15:21,  1.79s/it]
Training 1/1 epoch (loss 1.5181):  67%|██████▋   | 1050/1563 [27:33<13:40,  1.60s/it]
Training 1/1 epoch (loss 1.5362):  67%|██████▋   | 1050/1563 [27:35<13:40,  1.60s/it]
Training 1/1 epoch (loss 1.5362):  67%|██████▋   | 1051/1563 [27:35<12:37,  1.48s/it]
Training 1/1 epoch (loss 1.5558):  67%|██████▋   | 1051/1563 [27:36<12:37,  1.48s/it]
Training 1/1 epoch (loss 1.5558):  67%|██████▋   | 1052/1563 [27:36<12:11,  1.43s/it]
Training 1/1 epoch (loss 1.4220):  67%|██████▋   | 1052/1563 [27:37<12:11,  1.43s/it]
Training 1/1 epoch (loss 1.4220):  67%|██████▋   | 1053/1563 [27:37<12:07,  1.43s/it]
Training 1/1 epoch (loss 1.6120):  67%|██████▋   | 1053/1563 [27:39<12:07,  1.43s/it]
Training 1/1 epoch (loss 1.6120):  67%|██████▋   | 1054/1563 [27:39<12:36,  1.49s/it]
Training 1/1 epoch (loss 1.6625):  67%|██████▋   | 1054/1563 [27:40<12:36,  1.49s/it]
Training 1/1 epoch (loss 1.6625):  67%|██████▋   | 1055/1563 [27:40<11:58,  1.41s/it]
Training 1/1 epoch (loss 1.5365):  67%|██████▋   | 1055/1563 [27:42<11:58,  1.41s/it]
Training 1/1 epoch (loss 1.5365):  68%|██████▊   | 1056/1563 [27:42<12:52,  1.52s/it]
Training 1/1 epoch (loss 1.5319):  68%|██████▊   | 1056/1563 [27:43<12:52,  1.52s/it]
Training 1/1 epoch (loss 1.5319):  68%|██████▊   | 1057/1563 [27:43<12:46,  1.52s/it]
Training 1/1 epoch (loss 1.5598):  68%|██████▊   | 1057/1563 [27:45<12:46,  1.52s/it]
Training 1/1 epoch (loss 1.5598):  68%|██████▊   | 1058/1563 [27:45<14:01,  1.67s/it]
Training 1/1 epoch (loss 1.5509):  68%|██████▊   | 1058/1563 [27:47<14:01,  1.67s/it]
Training 1/1 epoch (loss 1.5509):  68%|██████▊   | 1059/1563 [27:47<13:06,  1.56s/it]
Training 1/1 epoch (loss 1.4792):  68%|██████▊   | 1059/1563 [27:48<13:06,  1.56s/it]
Training 1/1 epoch (loss 1.4792):  68%|██████▊   | 1060/1563 [27:48<13:29,  1.61s/it]
Training 1/1 epoch (loss 1.6054):  68%|██████▊   | 1060/1563 [27:50<13:29,  1.61s/it]
Training 1/1 epoch (loss 1.6054):  68%|██████▊   | 1061/1563 [27:50<12:27,  1.49s/it]
Training 1/1 epoch (loss 1.5769):  68%|██████▊   | 1061/1563 [27:52<12:27,  1.49s/it]
Training 1/1 epoch (loss 1.5769):  68%|██████▊   | 1062/1563 [27:52<14:28,  1.73s/it]
Training 1/1 epoch (loss 1.6202):  68%|██████▊   | 1062/1563 [27:53<14:28,  1.73s/it]
Training 1/1 epoch (loss 1.6202):  68%|██████▊   | 1063/1563 [27:53<13:44,  1.65s/it]
Training 1/1 epoch (loss 1.6606):  68%|██████▊   | 1063/1563 [27:55<13:44,  1.65s/it]
Training 1/1 epoch (loss 1.6606):  68%|██████▊   | 1064/1563 [27:55<13:08,  1.58s/it]
Training 1/1 epoch (loss 1.5268):  68%|██████▊   | 1064/1563 [27:57<13:08,  1.58s/it]
Training 1/1 epoch (loss 1.5268):  68%|██████▊   | 1065/1563 [27:57<14:08,  1.70s/it]
Training 1/1 epoch (loss 1.5504):  68%|██████▊   | 1065/1563 [27:59<14:08,  1.70s/it]
Training 1/1 epoch (loss 1.5504):  68%|██████▊   | 1066/1563 [27:59<14:52,  1.80s/it]
Training 1/1 epoch (loss 1.6087):  68%|██████▊   | 1066/1563 [28:00<14:52,  1.80s/it]
Training 1/1 epoch (loss 1.6087):  68%|██████▊   | 1067/1563 [28:00<13:04,  1.58s/it]
Training 1/1 epoch (loss 1.5111):  68%|██████▊   | 1067/1563 [28:02<13:04,  1.58s/it]
Training 1/1 epoch (loss 1.5111):  68%|██████▊   | 1068/1563 [28:02<13:50,  1.68s/it]
Training 1/1 epoch (loss 1.5786):  68%|██████▊   | 1068/1563 [28:03<13:50,  1.68s/it]
Training 1/1 epoch (loss 1.5786):  68%|██████▊   | 1069/1563 [28:03<13:04,  1.59s/it]
Training 1/1 epoch (loss 1.4551):  68%|██████▊   | 1069/1563 [28:04<13:04,  1.59s/it]
Training 1/1 epoch (loss 1.4551):  68%|██████▊   | 1070/1563 [28:04<12:01,  1.46s/it]
Training 1/1 epoch (loss 1.6053):  68%|██████▊   | 1070/1563 [28:06<12:01,  1.46s/it]
Training 1/1 epoch (loss 1.6053):  69%|██████▊   | 1071/1563 [28:06<13:05,  1.60s/it]
Training 1/1 epoch (loss 1.5134):  69%|██████▊   | 1071/1563 [28:08<13:05,  1.60s/it]
Training 1/1 epoch (loss 1.5134):  69%|██████▊   | 1072/1563 [28:08<14:04,  1.72s/it]
Training 1/1 epoch (loss 1.6019):  69%|██████▊   | 1072/1563 [28:10<14:04,  1.72s/it]
Training 1/1 epoch (loss 1.6019):  69%|██████▊   | 1073/1563 [28:10<13:51,  1.70s/it]
Training 1/1 epoch (loss 1.5496):  69%|██████▊   | 1073/1563 [28:12<13:51,  1.70s/it]
Training 1/1 epoch (loss 1.5496):  69%|██████▊   | 1074/1563 [28:12<14:15,  1.75s/it]
Training 1/1 epoch (loss 1.5363):  69%|██████▊   | 1074/1563 [28:13<14:15,  1.75s/it]
Training 1/1 epoch (loss 1.5363):  69%|██████▉   | 1075/1563 [28:13<12:52,  1.58s/it]
Training 1/1 epoch (loss 1.4970):  69%|██████▉   | 1075/1563 [28:15<12:52,  1.58s/it]
Training 1/1 epoch (loss 1.4970):  69%|██████▉   | 1076/1563 [28:15<14:10,  1.75s/it]
Training 1/1 epoch (loss 1.6210):  69%|██████▉   | 1076/1563 [28:16<14:10,  1.75s/it]
Training 1/1 epoch (loss 1.6210):  69%|██████▉   | 1077/1563 [28:16<12:31,  1.55s/it]
Training 1/1 epoch (loss 1.5829):  69%|██████▉   | 1077/1563 [28:17<12:31,  1.55s/it]
Training 1/1 epoch (loss 1.5829):  69%|██████▉   | 1078/1563 [28:17<11:37,  1.44s/it]
Training 1/1 epoch (loss 1.5332):  69%|██████▉   | 1078/1563 [28:19<11:37,  1.44s/it]
Training 1/1 epoch (loss 1.5332):  69%|██████▉   | 1079/1563 [28:19<11:29,  1.42s/it]
Training 1/1 epoch (loss 1.6309):  69%|██████▉   | 1079/1563 [28:21<11:29,  1.42s/it]
Training 1/1 epoch (loss 1.6309):  69%|██████▉   | 1080/1563 [28:21<13:29,  1.67s/it]
Training 1/1 epoch (loss 1.6129):  69%|██████▉   | 1080/1563 [28:23<13:29,  1.67s/it]
Training 1/1 epoch (loss 1.6129):  69%|██████▉   | 1081/1563 [28:23<13:32,  1.69s/it]
Training 1/1 epoch (loss 1.5442):  69%|██████▉   | 1081/1563 [28:24<13:32,  1.69s/it]
Training 1/1 epoch (loss 1.5442):  69%|██████▉   | 1082/1563 [28:24<13:34,  1.69s/it]
Training 1/1 epoch (loss 1.5638):  69%|██████▉   | 1082/1563 [28:26<13:34,  1.69s/it]
Training 1/1 epoch (loss 1.5638):  69%|██████▉   | 1083/1563 [28:26<13:01,  1.63s/it]
Training 1/1 epoch (loss 1.5469):  69%|██████▉   | 1083/1563 [28:28<13:01,  1.63s/it]
Training 1/1 epoch (loss 1.5469):  69%|██████▉   | 1084/1563 [28:28<13:39,  1.71s/it]
Training 1/1 epoch (loss 1.5190):  69%|██████▉   | 1084/1563 [28:29<13:39,  1.71s/it]
Training 1/1 epoch (loss 1.5190):  69%|██████▉   | 1085/1563 [28:29<12:56,  1.62s/it]
Training 1/1 epoch (loss 1.4708):  69%|██████▉   | 1085/1563 [28:31<12:56,  1.62s/it]
Training 1/1 epoch (loss 1.4708):  69%|██████▉   | 1086/1563 [28:31<12:46,  1.61s/it]
Training 1/1 epoch (loss 1.6043):  69%|██████▉   | 1086/1563 [28:32<12:46,  1.61s/it]
Training 1/1 epoch (loss 1.6043):  70%|██████▉   | 1087/1563 [28:32<12:45,  1.61s/it]
Training 1/1 epoch (loss 1.5559):  70%|██████▉   | 1087/1563 [28:35<12:45,  1.61s/it]
Training 1/1 epoch (loss 1.5559):  70%|██████▉   | 1088/1563 [28:35<14:18,  1.81s/it]
Training 1/1 epoch (loss 1.5125):  70%|██████▉   | 1088/1563 [28:36<14:18,  1.81s/it]
Training 1/1 epoch (loss 1.5125):  70%|██████▉   | 1089/1563 [28:36<13:36,  1.72s/it]
Training 1/1 epoch (loss 1.6795):  70%|██████▉   | 1089/1563 [28:37<13:36,  1.72s/it]
Training 1/1 epoch (loss 1.6795):  70%|██████▉   | 1090/1563 [28:37<12:03,  1.53s/it]
Training 1/1 epoch (loss 1.4483):  70%|██████▉   | 1090/1563 [28:39<12:03,  1.53s/it]
Training 1/1 epoch (loss 1.4483):  70%|██████▉   | 1091/1563 [28:39<13:01,  1.66s/it]
Training 1/1 epoch (loss 1.5785):  70%|██████▉   | 1091/1563 [28:40<13:01,  1.66s/it]
Training 1/1 epoch (loss 1.5785):  70%|██████▉   | 1092/1563 [28:40<11:05,  1.41s/it]
Training 1/1 epoch (loss 1.6033):  70%|██████▉   | 1092/1563 [28:42<11:05,  1.41s/it]
Training 1/1 epoch (loss 1.6033):  70%|██████▉   | 1093/1563 [28:42<11:45,  1.50s/it]
Training 1/1 epoch (loss 1.5694):  70%|██████▉   | 1093/1563 [28:44<11:45,  1.50s/it]
Training 1/1 epoch (loss 1.5694):  70%|██████▉   | 1094/1563 [28:44<12:28,  1.60s/it]
Training 1/1 epoch (loss 1.5165):  70%|██████▉   | 1094/1563 [28:46<12:28,  1.60s/it]
Training 1/1 epoch (loss 1.5165):  70%|███████   | 1095/1563 [28:46<13:46,  1.77s/it]
Training 1/1 epoch (loss 1.5548):  70%|███████   | 1095/1563 [28:48<13:46,  1.77s/it]
Training 1/1 epoch (loss 1.5548):  70%|███████   | 1096/1563 [28:48<14:08,  1.82s/it]
Training 1/1 epoch (loss 1.5253):  70%|███████   | 1096/1563 [28:49<14:08,  1.82s/it]
Training 1/1 epoch (loss 1.5253):  70%|███████   | 1097/1563 [28:49<13:40,  1.76s/it]
Training 1/1 epoch (loss 1.4921):  70%|███████   | 1097/1563 [28:51<13:40,  1.76s/it]
Training 1/1 epoch (loss 1.4921):  70%|███████   | 1098/1563 [28:51<13:29,  1.74s/it]
Training 1/1 epoch (loss 1.5856):  70%|███████   | 1098/1563 [28:54<13:29,  1.74s/it]
Training 1/1 epoch (loss 1.5856):  70%|███████   | 1099/1563 [28:54<15:11,  1.96s/it]
Training 1/1 epoch (loss 1.4902):  70%|███████   | 1099/1563 [28:56<15:11,  1.96s/it]
Training 1/1 epoch (loss 1.4902):  70%|███████   | 1100/1563 [28:56<15:24,  2.00s/it]
Training 1/1 epoch (loss 1.6002):  70%|███████   | 1100/1563 [28:58<15:24,  2.00s/it]
Training 1/1 epoch (loss 1.6002):  70%|███████   | 1101/1563 [28:58<15:18,  1.99s/it]
Training 1/1 epoch (loss 1.5706):  70%|███████   | 1101/1563 [29:00<15:18,  1.99s/it]
Training 1/1 epoch (loss 1.5706):  71%|███████   | 1102/1563 [29:00<15:05,  1.97s/it]
Training 1/1 epoch (loss 1.5558):  71%|███████   | 1102/1563 [29:01<15:05,  1.97s/it]
Training 1/1 epoch (loss 1.5558):  71%|███████   | 1103/1563 [29:01<14:25,  1.88s/it]
Training 1/1 epoch (loss 1.6267):  71%|███████   | 1103/1563 [29:03<14:25,  1.88s/it]
Training 1/1 epoch (loss 1.6267):  71%|███████   | 1104/1563 [29:03<13:20,  1.74s/it]
Training 1/1 epoch (loss 1.6426):  71%|███████   | 1104/1563 [29:04<13:20,  1.74s/it]
Training 1/1 epoch (loss 1.6426):  71%|███████   | 1105/1563 [29:04<12:38,  1.66s/it]
Training 1/1 epoch (loss 1.5071):  71%|███████   | 1105/1563 [29:05<12:38,  1.66s/it]
Training 1/1 epoch (loss 1.5071):  71%|███████   | 1106/1563 [29:05<11:51,  1.56s/it]
Training 1/1 epoch (loss 1.6021):  71%|███████   | 1106/1563 [29:07<11:51,  1.56s/it]
Training 1/1 epoch (loss 1.6021):  71%|███████   | 1107/1563 [29:07<10:58,  1.44s/it]
Training 1/1 epoch (loss 1.4158):  71%|███████   | 1107/1563 [29:08<10:58,  1.44s/it]
Training 1/1 epoch (loss 1.4158):  71%|███████   | 1108/1563 [29:08<11:35,  1.53s/it]
Training 1/1 epoch (loss 1.4919):  71%|███████   | 1108/1563 [29:10<11:35,  1.53s/it]
Training 1/1 epoch (loss 1.4919):  71%|███████   | 1109/1563 [29:10<12:39,  1.67s/it]
Training 1/1 epoch (loss 1.6083):  71%|███████   | 1109/1563 [29:11<12:39,  1.67s/it]
Training 1/1 epoch (loss 1.6083):  71%|███████   | 1110/1563 [29:11<10:47,  1.43s/it]
Training 1/1 epoch (loss 1.6122):  71%|███████   | 1110/1563 [29:13<10:47,  1.43s/it]
Training 1/1 epoch (loss 1.6122):  71%|███████   | 1111/1563 [29:13<12:07,  1.61s/it]
Training 1/1 epoch (loss 1.4778):  71%|███████   | 1111/1563 [29:15<12:07,  1.61s/it]
Training 1/1 epoch (loss 1.4778):  71%|███████   | 1112/1563 [29:15<13:26,  1.79s/it]
Training 1/1 epoch (loss 1.5645):  71%|███████   | 1112/1563 [29:17<13:26,  1.79s/it]
Training 1/1 epoch (loss 1.5645):  71%|███████   | 1113/1563 [29:17<13:12,  1.76s/it]
Training 1/1 epoch (loss 1.6198):  71%|███████   | 1113/1563 [29:19<13:12,  1.76s/it]
Training 1/1 epoch (loss 1.6198):  71%|███████▏  | 1114/1563 [29:19<12:57,  1.73s/it]
Training 1/1 epoch (loss 1.6099):  71%|███████▏  | 1114/1563 [29:21<12:57,  1.73s/it]
Training 1/1 epoch (loss 1.6099):  71%|███████▏  | 1115/1563 [29:21<13:47,  1.85s/it]
Training 1/1 epoch (loss 1.5947):  71%|███████▏  | 1115/1563 [29:22<13:47,  1.85s/it]
Training 1/1 epoch (loss 1.5947):  71%|███████▏  | 1116/1563 [29:22<12:17,  1.65s/it]
Training 1/1 epoch (loss 1.7438):  71%|███████▏  | 1116/1563 [29:24<12:17,  1.65s/it]
Training 1/1 epoch (loss 1.7438):  71%|███████▏  | 1117/1563 [29:24<13:18,  1.79s/it]
Training 1/1 epoch (loss 1.6474):  71%|███████▏  | 1117/1563 [29:25<13:18,  1.79s/it]
Training 1/1 epoch (loss 1.6474):  72%|███████▏  | 1118/1563 [29:25<11:52,  1.60s/it]
Training 1/1 epoch (loss 1.5235):  72%|███████▏  | 1118/1563 [29:26<11:52,  1.60s/it]
Training 1/1 epoch (loss 1.5235):  72%|███████▏  | 1119/1563 [29:26<10:21,  1.40s/it]
Training 1/1 epoch (loss 1.5361):  72%|███████▏  | 1119/1563 [29:28<10:21,  1.40s/it]
Training 1/1 epoch (loss 1.5361):  72%|███████▏  | 1120/1563 [29:28<10:40,  1.45s/it]
Training 1/1 epoch (loss 1.5711):  72%|███████▏  | 1120/1563 [29:30<10:40,  1.45s/it]
Training 1/1 epoch (loss 1.5711):  72%|███████▏  | 1121/1563 [29:30<12:39,  1.72s/it]
Training 1/1 epoch (loss 1.6188):  72%|███████▏  | 1121/1563 [29:32<12:39,  1.72s/it]
Training 1/1 epoch (loss 1.6188):  72%|███████▏  | 1122/1563 [29:32<13:14,  1.80s/it]
Training 1/1 epoch (loss 1.5286):  72%|███████▏  | 1122/1563 [29:35<13:14,  1.80s/it]
Training 1/1 epoch (loss 1.5286):  72%|███████▏  | 1123/1563 [29:35<14:36,  1.99s/it]
Training 1/1 epoch (loss 1.5728):  72%|███████▏  | 1123/1563 [29:37<14:36,  1.99s/it]
Training 1/1 epoch (loss 1.5728):  72%|███████▏  | 1124/1563 [29:37<14:22,  1.97s/it]
Training 1/1 epoch (loss 1.5628):  72%|███████▏  | 1124/1563 [29:38<14:22,  1.97s/it]
Training 1/1 epoch (loss 1.5628):  72%|███████▏  | 1125/1563 [29:38<12:47,  1.75s/it]
Training 1/1 epoch (loss 1.5865):  72%|███████▏  | 1125/1563 [29:40<12:47,  1.75s/it]
Training 1/1 epoch (loss 1.5865):  72%|███████▏  | 1126/1563 [29:40<12:55,  1.77s/it]
Training 1/1 epoch (loss 1.5343):  72%|███████▏  | 1126/1563 [29:42<12:55,  1.77s/it]
Training 1/1 epoch (loss 1.5343):  72%|███████▏  | 1127/1563 [29:42<14:31,  2.00s/it]
Training 1/1 epoch (loss 1.5646):  72%|███████▏  | 1127/1563 [29:44<14:31,  2.00s/it]
Training 1/1 epoch (loss 1.5646):  72%|███████▏  | 1128/1563 [29:44<14:14,  1.97s/it]
Training 1/1 epoch (loss 1.5956):  72%|███████▏  | 1128/1563 [29:45<14:14,  1.97s/it]
Training 1/1 epoch (loss 1.5956):  72%|███████▏  | 1129/1563 [29:45<12:07,  1.68s/it]
Training 1/1 epoch (loss 1.5309):  72%|███████▏  | 1129/1563 [29:47<12:07,  1.68s/it]
Training 1/1 epoch (loss 1.5309):  72%|███████▏  | 1130/1563 [29:47<12:34,  1.74s/it]
Training 1/1 epoch (loss 1.5820):  72%|███████▏  | 1130/1563 [29:49<12:34,  1.74s/it]
Training 1/1 epoch (loss 1.5820):  72%|███████▏  | 1131/1563 [29:49<12:56,  1.80s/it]
Training 1/1 epoch (loss 1.5951):  72%|███████▏  | 1131/1563 [29:51<12:56,  1.80s/it]
Training 1/1 epoch (loss 1.5951):  72%|███████▏  | 1132/1563 [29:51<12:54,  1.80s/it]
Training 1/1 epoch (loss 1.5135):  72%|███████▏  | 1132/1563 [29:52<12:54,  1.80s/it]
Training 1/1 epoch (loss 1.5135):  72%|███████▏  | 1133/1563 [29:52<12:26,  1.74s/it]
Training 1/1 epoch (loss 1.5846):  72%|███████▏  | 1133/1563 [29:53<12:26,  1.74s/it]
Training 1/1 epoch (loss 1.5846):  73%|███████▎  | 1134/1563 [29:53<11:17,  1.58s/it]
Training 1/1 epoch (loss 1.4995):  73%|███████▎  | 1134/1563 [29:55<11:17,  1.58s/it]
Training 1/1 epoch (loss 1.4995):  73%|███████▎  | 1135/1563 [29:55<11:55,  1.67s/it]
Training 1/1 epoch (loss 1.5569):  73%|███████▎  | 1135/1563 [29:58<11:55,  1.67s/it]
Training 1/1 epoch (loss 1.5569):  73%|███████▎  | 1136/1563 [29:58<13:09,  1.85s/it]
Training 1/1 epoch (loss 1.5305):  73%|███████▎  | 1136/1563 [30:00<13:09,  1.85s/it]
Training 1/1 epoch (loss 1.5305):  73%|███████▎  | 1137/1563 [30:00<13:58,  1.97s/it]
Training 1/1 epoch (loss 1.5535):  73%|███████▎  | 1137/1563 [30:02<13:58,  1.97s/it]
Training 1/1 epoch (loss 1.5535):  73%|███████▎  | 1138/1563 [30:02<14:56,  2.11s/it]
Training 1/1 epoch (loss 1.5880):  73%|███████▎  | 1138/1563 [30:04<14:56,  2.11s/it]
Training 1/1 epoch (loss 1.5880):  73%|███████▎  | 1139/1563 [30:04<13:26,  1.90s/it]
Training 1/1 epoch (loss 1.5975):  73%|███████▎  | 1139/1563 [30:06<13:26,  1.90s/it]
Training 1/1 epoch (loss 1.5975):  73%|███████▎  | 1140/1563 [30:06<14:26,  2.05s/it]
Training 1/1 epoch (loss 1.6251):  73%|███████▎  | 1140/1563 [30:07<14:26,  2.05s/it]
Training 1/1 epoch (loss 1.6251):  73%|███████▎  | 1141/1563 [30:07<12:39,  1.80s/it]
Training 1/1 epoch (loss 1.5159):  73%|███████▎  | 1141/1563 [30:09<12:39,  1.80s/it]
Training 1/1 epoch (loss 1.5159):  73%|███████▎  | 1142/1563 [30:09<11:43,  1.67s/it]
Training 1/1 epoch (loss 1.6133):  73%|███████▎  | 1142/1563 [30:10<11:43,  1.67s/it]
Training 1/1 epoch (loss 1.6133):  73%|███████▎  | 1143/1563 [30:10<11:31,  1.65s/it]
Training 1/1 epoch (loss 1.6112):  73%|███████▎  | 1143/1563 [30:12<11:31,  1.65s/it]
Training 1/1 epoch (loss 1.6112):  73%|███████▎  | 1144/1563 [30:12<12:34,  1.80s/it]
Training 1/1 epoch (loss 1.5841):  73%|███████▎  | 1144/1563 [30:14<12:34,  1.80s/it]
Training 1/1 epoch (loss 1.5841):  73%|███████▎  | 1145/1563 [30:14<13:04,  1.88s/it]
Training 1/1 epoch (loss 1.5232):  73%|███████▎  | 1145/1563 [30:16<13:04,  1.88s/it]
Training 1/1 epoch (loss 1.5232):  73%|███████▎  | 1146/1563 [30:16<13:17,  1.91s/it]
Training 1/1 epoch (loss 1.5675):  73%|███████▎  | 1146/1563 [30:18<13:17,  1.91s/it]
Training 1/1 epoch (loss 1.5675):  73%|███████▎  | 1147/1563 [30:18<12:40,  1.83s/it]
Training 1/1 epoch (loss 1.6910):  73%|███████▎  | 1147/1563 [30:19<12:40,  1.83s/it]
Training 1/1 epoch (loss 1.6910):  73%|███████▎  | 1148/1563 [30:19<11:21,  1.64s/it]
Training 1/1 epoch (loss 1.6133):  73%|███████▎  | 1148/1563 [30:21<11:21,  1.64s/it]
Training 1/1 epoch (loss 1.6133):  74%|███████▎  | 1149/1563 [30:21<12:20,  1.79s/it]
Training 1/1 epoch (loss 1.4759):  74%|███████▎  | 1149/1563 [30:23<12:20,  1.79s/it]
Training 1/1 epoch (loss 1.4759):  74%|███████▎  | 1150/1563 [30:23<11:50,  1.72s/it]
Training 1/1 epoch (loss 1.5454):  74%|███████▎  | 1150/1563 [30:25<11:50,  1.72s/it]
Training 1/1 epoch (loss 1.5454):  74%|███████▎  | 1151/1563 [30:25<12:45,  1.86s/it]
Training 1/1 epoch (loss 1.5510):  74%|███████▎  | 1151/1563 [30:28<12:45,  1.86s/it]
Training 1/1 epoch (loss 1.5510):  74%|███████▎  | 1152/1563 [30:28<13:42,  2.00s/it]
Training 1/1 epoch (loss 1.5554):  74%|███████▎  | 1152/1563 [30:30<13:42,  2.00s/it]
Training 1/1 epoch (loss 1.5554):  74%|███████▍  | 1153/1563 [30:30<13:54,  2.04s/it]
Training 1/1 epoch (loss 1.5979):  74%|███████▍  | 1153/1563 [30:31<13:54,  2.04s/it]
Training 1/1 epoch (loss 1.5979):  74%|███████▍  | 1154/1563 [30:31<11:43,  1.72s/it]
Training 1/1 epoch (loss 1.6131):  74%|███████▍  | 1154/1563 [30:32<11:43,  1.72s/it]
Training 1/1 epoch (loss 1.6131):  74%|███████▍  | 1155/1563 [30:32<10:49,  1.59s/it]
Training 1/1 epoch (loss 1.6045):  74%|███████▍  | 1155/1563 [30:33<10:49,  1.59s/it]
Training 1/1 epoch (loss 1.6045):  74%|███████▍  | 1156/1563 [30:33<10:36,  1.56s/it]
Training 1/1 epoch (loss 1.6044):  74%|███████▍  | 1156/1563 [30:35<10:36,  1.56s/it]
Training 1/1 epoch (loss 1.6044):  74%|███████▍  | 1157/1563 [30:35<11:03,  1.63s/it]
Training 1/1 epoch (loss 1.5679):  74%|███████▍  | 1157/1563 [30:37<11:03,  1.63s/it]
Training 1/1 epoch (loss 1.5679):  74%|███████▍  | 1158/1563 [30:37<11:08,  1.65s/it]
Training 1/1 epoch (loss 1.5664):  74%|███████▍  | 1158/1563 [30:39<11:08,  1.65s/it]
Training 1/1 epoch (loss 1.5664):  74%|███████▍  | 1159/1563 [30:39<11:47,  1.75s/it]
Training 1/1 epoch (loss 1.6358):  74%|███████▍  | 1159/1563 [30:40<11:47,  1.75s/it]
Training 1/1 epoch (loss 1.6358):  74%|███████▍  | 1160/1563 [30:40<11:12,  1.67s/it]
Training 1/1 epoch (loss 1.5498):  74%|███████▍  | 1160/1563 [30:42<11:12,  1.67s/it]
Training 1/1 epoch (loss 1.5498):  74%|███████▍  | 1161/1563 [30:42<10:33,  1.58s/it]
Training 1/1 epoch (loss 1.5372):  74%|███████▍  | 1161/1563 [30:43<10:33,  1.58s/it]
Training 1/1 epoch (loss 1.5372):  74%|███████▍  | 1162/1563 [30:43<10:27,  1.56s/it]
Training 1/1 epoch (loss 1.5122):  74%|███████▍  | 1162/1563 [30:45<10:27,  1.56s/it]
Training 1/1 epoch (loss 1.5122):  74%|███████▍  | 1163/1563 [30:45<10:47,  1.62s/it]
Training 1/1 epoch (loss 1.6463):  74%|███████▍  | 1163/1563 [30:47<10:47,  1.62s/it]
Training 1/1 epoch (loss 1.6463):  74%|███████▍  | 1164/1563 [30:47<11:25,  1.72s/it]
Training 1/1 epoch (loss 1.6286):  74%|███████▍  | 1164/1563 [30:50<11:25,  1.72s/it]
Training 1/1 epoch (loss 1.6286):  75%|███████▍  | 1165/1563 [30:50<13:01,  1.96s/it]
Training 1/1 epoch (loss 1.6589):  75%|███████▍  | 1165/1563 [30:51<13:01,  1.96s/it]
Training 1/1 epoch (loss 1.6589):  75%|███████▍  | 1166/1563 [30:51<12:07,  1.83s/it]
Training 1/1 epoch (loss 1.5938):  75%|███████▍  | 1166/1563 [30:53<12:07,  1.83s/it]
Training 1/1 epoch (loss 1.5938):  75%|███████▍  | 1167/1563 [30:53<12:22,  1.88s/it]
Training 1/1 epoch (loss 1.5417):  75%|███████▍  | 1167/1563 [30:55<12:22,  1.88s/it]
Training 1/1 epoch (loss 1.5417):  75%|███████▍  | 1168/1563 [30:55<12:29,  1.90s/it]
Training 1/1 epoch (loss 1.4863):  75%|███████▍  | 1168/1563 [30:57<12:29,  1.90s/it]
Training 1/1 epoch (loss 1.4863):  75%|███████▍  | 1169/1563 [30:57<12:17,  1.87s/it]
Training 1/1 epoch (loss 1.5754):  75%|███████▍  | 1169/1563 [30:58<12:17,  1.87s/it]
Training 1/1 epoch (loss 1.5754):  75%|███████▍  | 1170/1563 [30:58<10:10,  1.55s/it]
Training 1/1 epoch (loss 1.4557):  75%|███████▍  | 1170/1563 [30:59<10:10,  1.55s/it]
Training 1/1 epoch (loss 1.4557):  75%|███████▍  | 1171/1563 [30:59<09:59,  1.53s/it]
Training 1/1 epoch (loss 1.5589):  75%|███████▍  | 1171/1563 [31:01<09:59,  1.53s/it]
Training 1/1 epoch (loss 1.5589):  75%|███████▍  | 1172/1563 [31:01<10:02,  1.54s/it]
Training 1/1 epoch (loss 1.4827):  75%|███████▍  | 1172/1563 [31:02<10:02,  1.54s/it]
Training 1/1 epoch (loss 1.4827):  75%|███████▌  | 1173/1563 [31:02<10:08,  1.56s/it]
Training 1/1 epoch (loss 1.6016):  75%|███████▌  | 1173/1563 [31:04<10:08,  1.56s/it]
Training 1/1 epoch (loss 1.6016):  75%|███████▌  | 1174/1563 [31:04<10:31,  1.62s/it]
Training 1/1 epoch (loss 1.5025):  75%|███████▌  | 1174/1563 [31:06<10:31,  1.62s/it]
Training 1/1 epoch (loss 1.5025):  75%|███████▌  | 1175/1563 [31:06<10:48,  1.67s/it]
Training 1/1 epoch (loss 1.5546):  75%|███████▌  | 1175/1563 [31:08<10:48,  1.67s/it]
Training 1/1 epoch (loss 1.5546):  75%|███████▌  | 1176/1563 [31:08<12:30,  1.94s/it]
Training 1/1 epoch (loss 1.4161):  75%|███████▌  | 1176/1563 [31:10<12:30,  1.94s/it]
Training 1/1 epoch (loss 1.4161):  75%|███████▌  | 1177/1563 [31:10<12:44,  1.98s/it]
Training 1/1 epoch (loss 1.4871):  75%|███████▌  | 1177/1563 [31:12<12:44,  1.98s/it]
Training 1/1 epoch (loss 1.4871):  75%|███████▌  | 1178/1563 [31:12<11:39,  1.82s/it]
Training 1/1 epoch (loss 1.6263):  75%|███████▌  | 1178/1563 [31:14<11:39,  1.82s/it]
Training 1/1 epoch (loss 1.6263):  75%|███████▌  | 1179/1563 [31:14<13:02,  2.04s/it]
Training 1/1 epoch (loss 1.5650):  75%|███████▌  | 1179/1563 [31:16<13:02,  2.04s/it]
Training 1/1 epoch (loss 1.5650):  75%|███████▌  | 1180/1563 [31:16<11:39,  1.83s/it]
Training 1/1 epoch (loss 1.5660):  75%|███████▌  | 1180/1563 [31:18<11:39,  1.83s/it]
Training 1/1 epoch (loss 1.5660):  76%|███████▌  | 1181/1563 [31:18<12:14,  1.92s/it]
Training 1/1 epoch (loss 1.5929):  76%|███████▌  | 1181/1563 [31:19<12:14,  1.92s/it]
Training 1/1 epoch (loss 1.5929):  76%|███████▌  | 1182/1563 [31:19<10:57,  1.73s/it]
Training 1/1 epoch (loss 1.5982):  76%|███████▌  | 1182/1563 [31:21<10:57,  1.73s/it]
Training 1/1 epoch (loss 1.5982):  76%|███████▌  | 1183/1563 [31:21<11:03,  1.75s/it]
Training 1/1 epoch (loss 1.4035):  76%|███████▌  | 1183/1563 [31:22<11:03,  1.75s/it]
Training 1/1 epoch (loss 1.4035):  76%|███████▌  | 1184/1563 [31:22<10:07,  1.60s/it]
Training 1/1 epoch (loss 1.5796):  76%|███████▌  | 1184/1563 [31:24<10:07,  1.60s/it]
Training 1/1 epoch (loss 1.5796):  76%|███████▌  | 1185/1563 [31:24<10:04,  1.60s/it]
Training 1/1 epoch (loss 1.5995):  76%|███████▌  | 1185/1563 [31:26<10:04,  1.60s/it]
Training 1/1 epoch (loss 1.5995):  76%|███████▌  | 1186/1563 [31:26<10:46,  1.71s/it]
Training 1/1 epoch (loss 1.4757):  76%|███████▌  | 1186/1563 [31:28<10:46,  1.71s/it]
Training 1/1 epoch (loss 1.4757):  76%|███████▌  | 1187/1563 [31:28<12:08,  1.94s/it]
Training 1/1 epoch (loss 1.5466):  76%|███████▌  | 1187/1563 [31:30<12:08,  1.94s/it]
Training 1/1 epoch (loss 1.5466):  76%|███████▌  | 1188/1563 [31:30<11:29,  1.84s/it]
Training 1/1 epoch (loss 1.6965):  76%|███████▌  | 1188/1563 [31:31<11:29,  1.84s/it]
Training 1/1 epoch (loss 1.6965):  76%|███████▌  | 1189/1563 [31:31<10:25,  1.67s/it]
Training 1/1 epoch (loss 1.4955):  76%|███████▌  | 1189/1563 [31:34<10:25,  1.67s/it]
Training 1/1 epoch (loss 1.4955):  76%|███████▌  | 1190/1563 [31:34<11:52,  1.91s/it]
Training 1/1 epoch (loss 1.5742):  76%|███████▌  | 1190/1563 [31:35<11:52,  1.91s/it]
Training 1/1 epoch (loss 1.5742):  76%|███████▌  | 1191/1563 [31:35<11:09,  1.80s/it]
Training 1/1 epoch (loss 1.6796):  76%|███████▌  | 1191/1563 [31:38<11:09,  1.80s/it]
Training 1/1 epoch (loss 1.6796):  76%|███████▋  | 1192/1563 [31:38<12:21,  2.00s/it]
Training 1/1 epoch (loss 1.6765):  76%|███████▋  | 1192/1563 [31:40<12:21,  2.00s/it]
Training 1/1 epoch (loss 1.6765):  76%|███████▋  | 1193/1563 [31:40<12:35,  2.04s/it]
Training 1/1 epoch (loss 1.5696):  76%|███████▋  | 1193/1563 [31:41<12:35,  2.04s/it]
Training 1/1 epoch (loss 1.5696):  76%|███████▋  | 1194/1563 [31:41<10:36,  1.72s/it]
Training 1/1 epoch (loss 1.6211):  76%|███████▋  | 1194/1563 [31:43<10:36,  1.72s/it]
Training 1/1 epoch (loss 1.6211):  76%|███████▋  | 1195/1563 [31:43<10:46,  1.76s/it]
Training 1/1 epoch (loss 1.4935):  76%|███████▋  | 1195/1563 [31:45<10:46,  1.76s/it]
Training 1/1 epoch (loss 1.4935):  77%|███████▋  | 1196/1563 [31:45<11:59,  1.96s/it]
Training 1/1 epoch (loss 1.5533):  77%|███████▋  | 1196/1563 [31:47<11:59,  1.96s/it]
Training 1/1 epoch (loss 1.5533):  77%|███████▋  | 1197/1563 [31:47<11:36,  1.90s/it]
Training 1/1 epoch (loss 1.4815):  77%|███████▋  | 1197/1563 [31:48<11:36,  1.90s/it]
Training 1/1 epoch (loss 1.4815):  77%|███████▋  | 1198/1563 [31:48<10:59,  1.81s/it]
Training 1/1 epoch (loss 1.5885):  77%|███████▋  | 1198/1563 [31:49<10:59,  1.81s/it]
Training 1/1 epoch (loss 1.5885):  77%|███████▋  | 1199/1563 [31:49<09:39,  1.59s/it]
Training 1/1 epoch (loss 1.5963):  77%|███████▋  | 1199/1563 [31:51<09:39,  1.59s/it]
Training 1/1 epoch (loss 1.5963):  77%|███████▋  | 1200/1563 [31:51<09:54,  1.64s/it]
Training 1/1 epoch (loss 1.5755):  77%|███████▋  | 1200/1563 [31:53<09:54,  1.64s/it]
Training 1/1 epoch (loss 1.5755):  77%|███████▋  | 1201/1563 [31:53<09:20,  1.55s/it]
Training 1/1 epoch (loss 1.6318):  77%|███████▋  | 1201/1563 [31:54<09:20,  1.55s/it]
Training 1/1 epoch (loss 1.6318):  77%|███████▋  | 1202/1563 [31:54<09:22,  1.56s/it]
Training 1/1 epoch (loss 1.6167):  77%|███████▋  | 1202/1563 [31:55<09:22,  1.56s/it]
Training 1/1 epoch (loss 1.6167):  77%|███████▋  | 1203/1563 [31:55<08:15,  1.38s/it]
Training 1/1 epoch (loss 1.5391):  77%|███████▋  | 1203/1563 [31:57<08:15,  1.38s/it]
Training 1/1 epoch (loss 1.5391):  77%|███████▋  | 1204/1563 [31:57<08:42,  1.46s/it]
Training 1/1 epoch (loss 1.6076):  77%|███████▋  | 1204/1563 [31:59<08:42,  1.46s/it]
Training 1/1 epoch (loss 1.6076):  77%|███████▋  | 1205/1563 [31:59<09:21,  1.57s/it]
Training 1/1 epoch (loss 1.5311):  77%|███████▋  | 1205/1563 [32:01<09:21,  1.57s/it]
Training 1/1 epoch (loss 1.5311):  77%|███████▋  | 1206/1563 [32:01<10:30,  1.77s/it]
Training 1/1 epoch (loss 1.5742):  77%|███████▋  | 1206/1563 [32:02<10:30,  1.77s/it]
Training 1/1 epoch (loss 1.5742):  77%|███████▋  | 1207/1563 [32:02<09:56,  1.68s/it]
Training 1/1 epoch (loss 1.5631):  77%|███████▋  | 1207/1563 [32:04<09:56,  1.68s/it]
Training 1/1 epoch (loss 1.5631):  77%|███████▋  | 1208/1563 [32:04<10:41,  1.81s/it]
Training 1/1 epoch (loss 1.5459):  77%|███████▋  | 1208/1563 [32:06<10:41,  1.81s/it]
Training 1/1 epoch (loss 1.5459):  77%|███████▋  | 1209/1563 [32:06<10:51,  1.84s/it]
Training 1/1 epoch (loss 1.6449):  77%|███████▋  | 1209/1563 [32:08<10:51,  1.84s/it]
Training 1/1 epoch (loss 1.6449):  77%|███████▋  | 1210/1563 [32:08<10:06,  1.72s/it]
Training 1/1 epoch (loss 1.6599):  77%|███████▋  | 1210/1563 [32:10<10:06,  1.72s/it]
Training 1/1 epoch (loss 1.6599):  77%|███████▋  | 1211/1563 [32:10<11:15,  1.92s/it]
Training 1/1 epoch (loss 1.5450):  77%|███████▋  | 1211/1563 [32:12<11:15,  1.92s/it]
Training 1/1 epoch (loss 1.5450):  78%|███████▊  | 1212/1563 [32:12<10:41,  1.83s/it]
Training 1/1 epoch (loss 1.5070):  78%|███████▊  | 1212/1563 [32:13<10:41,  1.83s/it]
Training 1/1 epoch (loss 1.5070):  78%|███████▊  | 1213/1563 [32:13<09:55,  1.70s/it]
Training 1/1 epoch (loss 1.4974):  78%|███████▊  | 1213/1563 [32:15<09:55,  1.70s/it]
Training 1/1 epoch (loss 1.4974):  78%|███████▊  | 1214/1563 [32:15<09:45,  1.68s/it]
Training 1/1 epoch (loss 1.5184):  78%|███████▊  | 1214/1563 [32:16<09:45,  1.68s/it]
Training 1/1 epoch (loss 1.5184):  78%|███████▊  | 1215/1563 [32:16<09:05,  1.57s/it]
Training 1/1 epoch (loss 1.5431):  78%|███████▊  | 1215/1563 [32:18<09:05,  1.57s/it]
Training 1/1 epoch (loss 1.5431):  78%|███████▊  | 1216/1563 [32:18<08:59,  1.56s/it]
Training 1/1 epoch (loss 1.5488):  78%|███████▊  | 1216/1563 [32:19<08:59,  1.56s/it]
Training 1/1 epoch (loss 1.5488):  78%|███████▊  | 1217/1563 [32:19<08:31,  1.48s/it]
Training 1/1 epoch (loss 1.5425):  78%|███████▊  | 1217/1563 [32:21<08:31,  1.48s/it]
Training 1/1 epoch (loss 1.5425):  78%|███████▊  | 1218/1563 [32:21<08:52,  1.54s/it]
Training 1/1 epoch (loss 1.6208):  78%|███████▊  | 1218/1563 [32:23<08:52,  1.54s/it]
Training 1/1 epoch (loss 1.6208):  78%|███████▊  | 1219/1563 [32:23<10:22,  1.81s/it]
Training 1/1 epoch (loss 1.6187):  78%|███████▊  | 1219/1563 [32:24<10:22,  1.81s/it]
Training 1/1 epoch (loss 1.6187):  78%|███████▊  | 1220/1563 [32:24<09:36,  1.68s/it]
Training 1/1 epoch (loss 1.6427):  78%|███████▊  | 1220/1563 [32:26<09:36,  1.68s/it]
Training 1/1 epoch (loss 1.6427):  78%|███████▊  | 1221/1563 [32:26<09:07,  1.60s/it]
Training 1/1 epoch (loss 1.3449):  78%|███████▊  | 1221/1563 [32:28<09:07,  1.60s/it]
Training 1/1 epoch (loss 1.3449):  78%|███████▊  | 1222/1563 [32:28<09:43,  1.71s/it]
Training 1/1 epoch (loss 1.6389):  78%|███████▊  | 1222/1563 [32:29<09:43,  1.71s/it]
Training 1/1 epoch (loss 1.6389):  78%|███████▊  | 1223/1563 [32:29<08:33,  1.51s/it]
Training 1/1 epoch (loss 1.7048):  78%|███████▊  | 1223/1563 [32:31<08:33,  1.51s/it]
Training 1/1 epoch (loss 1.7048):  78%|███████▊  | 1224/1563 [32:31<08:54,  1.58s/it]
Training 1/1 epoch (loss 1.6315):  78%|███████▊  | 1224/1563 [32:32<08:54,  1.58s/it]
Training 1/1 epoch (loss 1.6315):  78%|███████▊  | 1225/1563 [32:32<09:18,  1.65s/it]
Training 1/1 epoch (loss 1.5597):  78%|███████▊  | 1225/1563 [32:34<09:18,  1.65s/it]
Training 1/1 epoch (loss 1.5597):  78%|███████▊  | 1226/1563 [32:34<09:22,  1.67s/it]
Training 1/1 epoch (loss 1.5436):  78%|███████▊  | 1226/1563 [32:36<09:22,  1.67s/it]
Training 1/1 epoch (loss 1.5436):  79%|███████▊  | 1227/1563 [32:36<09:07,  1.63s/it]
Training 1/1 epoch (loss 1.5001):  79%|███████▊  | 1227/1563 [32:37<09:07,  1.63s/it]
Training 1/1 epoch (loss 1.5001):  79%|███████▊  | 1228/1563 [32:37<08:35,  1.54s/it]
Training 1/1 epoch (loss 1.5536):  79%|███████▊  | 1228/1563 [32:39<08:35,  1.54s/it]
Training 1/1 epoch (loss 1.5536):  79%|███████▊  | 1229/1563 [32:39<09:01,  1.62s/it]
Training 1/1 epoch (loss 1.5312):  79%|███████▊  | 1229/1563 [32:40<09:01,  1.62s/it]
Training 1/1 epoch (loss 1.5312):  79%|███████▊  | 1230/1563 [32:40<08:57,  1.61s/it]
Training 1/1 epoch (loss 1.5808):  79%|███████▊  | 1230/1563 [32:43<08:57,  1.61s/it]
Training 1/1 epoch (loss 1.5808):  79%|███████▉  | 1231/1563 [32:43<10:25,  1.89s/it]
Training 1/1 epoch (loss 1.4356):  79%|███████▉  | 1231/1563 [32:45<10:25,  1.89s/it]
Training 1/1 epoch (loss 1.4356):  79%|███████▉  | 1232/1563 [32:45<10:12,  1.85s/it]
Training 1/1 epoch (loss 1.5260):  79%|███████▉  | 1232/1563 [32:46<10:12,  1.85s/it]
Training 1/1 epoch (loss 1.5260):  79%|███████▉  | 1233/1563 [32:46<10:13,  1.86s/it]
Training 1/1 epoch (loss 1.5742):  79%|███████▉  | 1233/1563 [32:48<10:13,  1.86s/it]
Training 1/1 epoch (loss 1.5742):  79%|███████▉  | 1234/1563 [32:48<09:02,  1.65s/it]
Training 1/1 epoch (loss 1.5834):  79%|███████▉  | 1234/1563 [32:49<09:02,  1.65s/it]
Training 1/1 epoch (loss 1.5834):  79%|███████▉  | 1235/1563 [32:49<09:10,  1.68s/it]
Training 1/1 epoch (loss 1.5604):  79%|███████▉  | 1235/1563 [32:51<09:10,  1.68s/it]
Training 1/1 epoch (loss 1.5604):  79%|███████▉  | 1236/1563 [32:51<09:45,  1.79s/it]
Training 1/1 epoch (loss 1.5269):  79%|███████▉  | 1236/1563 [32:53<09:45,  1.79s/it]
Training 1/1 epoch (loss 1.5269):  79%|███████▉  | 1237/1563 [32:53<09:03,  1.67s/it]
Training 1/1 epoch (loss 1.4902):  79%|███████▉  | 1237/1563 [32:54<09:03,  1.67s/it]
Training 1/1 epoch (loss 1.4902):  79%|███████▉  | 1238/1563 [32:54<08:25,  1.56s/it]
Training 1/1 epoch (loss 1.5374):  79%|███████▉  | 1238/1563 [32:56<08:25,  1.56s/it]
Training 1/1 epoch (loss 1.5374):  79%|███████▉  | 1239/1563 [32:56<08:48,  1.63s/it]
Training 1/1 epoch (loss 1.5974):  79%|███████▉  | 1239/1563 [32:58<08:48,  1.63s/it]
Training 1/1 epoch (loss 1.5974):  79%|███████▉  | 1240/1563 [32:58<08:51,  1.65s/it]
Training 1/1 epoch (loss 1.4305):  79%|███████▉  | 1240/1563 [33:00<08:51,  1.65s/it]
Training 1/1 epoch (loss 1.4305):  79%|███████▉  | 1241/1563 [33:00<09:25,  1.76s/it]
Training 1/1 epoch (loss 1.5775):  79%|███████▉  | 1241/1563 [33:01<09:25,  1.76s/it]
Training 1/1 epoch (loss 1.5775):  79%|███████▉  | 1242/1563 [33:01<09:05,  1.70s/it]
Training 1/1 epoch (loss 1.4242):  79%|███████▉  | 1242/1563 [33:03<09:05,  1.70s/it]
Training 1/1 epoch (loss 1.4242):  80%|███████▉  | 1243/1563 [33:03<08:48,  1.65s/it]
Training 1/1 epoch (loss 1.5610):  80%|███████▉  | 1243/1563 [33:05<08:48,  1.65s/it]
Training 1/1 epoch (loss 1.5610):  80%|███████▉  | 1244/1563 [33:05<09:52,  1.86s/it]
Training 1/1 epoch (loss 1.5503):  80%|███████▉  | 1244/1563 [33:07<09:52,  1.86s/it]
Training 1/1 epoch (loss 1.5503):  80%|███████▉  | 1245/1563 [33:07<09:25,  1.78s/it]
Training 1/1 epoch (loss 1.5672):  80%|███████▉  | 1245/1563 [33:08<09:25,  1.78s/it]
Training 1/1 epoch (loss 1.5672):  80%|███████▉  | 1246/1563 [33:08<09:24,  1.78s/it]
Training 1/1 epoch (loss 1.6122):  80%|███████▉  | 1246/1563 [33:10<09:24,  1.78s/it]
Training 1/1 epoch (loss 1.6122):  80%|███████▉  | 1247/1563 [33:10<09:09,  1.74s/it]
Training 1/1 epoch (loss 1.4761):  80%|███████▉  | 1247/1563 [33:12<09:09,  1.74s/it]
Training 1/1 epoch (loss 1.4761):  80%|███████▉  | 1248/1563 [33:12<08:59,  1.71s/it]
Training 1/1 epoch (loss 1.5586):  80%|███████▉  | 1248/1563 [33:13<08:59,  1.71s/it]
Training 1/1 epoch (loss 1.5586):  80%|███████▉  | 1249/1563 [33:13<08:52,  1.69s/it]
Training 1/1 epoch (loss 1.4811):  80%|███████▉  | 1249/1563 [33:15<08:52,  1.69s/it]
Training 1/1 epoch (loss 1.4811):  80%|███████▉  | 1250/1563 [33:15<08:37,  1.65s/it]
Training 1/1 epoch (loss 1.5119):  80%|███████▉  | 1250/1563 [33:16<08:37,  1.65s/it]
Training 1/1 epoch (loss 1.5119):  80%|████████  | 1251/1563 [33:16<07:51,  1.51s/it]
Training 1/1 epoch (loss 1.5354):  80%|████████  | 1251/1563 [33:18<07:51,  1.51s/it]
Training 1/1 epoch (loss 1.5354):  80%|████████  | 1252/1563 [33:18<08:14,  1.59s/it]
Training 1/1 epoch (loss 1.5670):  80%|████████  | 1252/1563 [33:20<08:14,  1.59s/it]
Training 1/1 epoch (loss 1.5670):  80%|████████  | 1253/1563 [33:20<08:56,  1.73s/it]
Training 1/1 epoch (loss 1.4722):  80%|████████  | 1253/1563 [33:22<08:56,  1.73s/it]
Training 1/1 epoch (loss 1.4722):  80%|████████  | 1254/1563 [33:22<09:17,  1.81s/it]
Training 1/1 epoch (loss 1.5545):  80%|████████  | 1254/1563 [33:24<09:17,  1.81s/it]
Training 1/1 epoch (loss 1.5545):  80%|████████  | 1255/1563 [33:24<10:12,  1.99s/it]
Training 1/1 epoch (loss 1.4668):  80%|████████  | 1255/1563 [33:27<10:12,  1.99s/it]
Training 1/1 epoch (loss 1.4668):  80%|████████  | 1256/1563 [33:27<10:30,  2.06s/it]
Training 1/1 epoch (loss 1.6266):  80%|████████  | 1256/1563 [33:29<10:30,  2.06s/it]
Training 1/1 epoch (loss 1.6266):  80%|████████  | 1257/1563 [33:29<10:54,  2.14s/it]
Training 1/1 epoch (loss 1.4788):  80%|████████  | 1257/1563 [33:30<10:54,  2.14s/it]
Training 1/1 epoch (loss 1.4788):  80%|████████  | 1258/1563 [33:30<09:01,  1.78s/it]
Training 1/1 epoch (loss 1.7039):  80%|████████  | 1258/1563 [33:32<09:01,  1.78s/it]
Training 1/1 epoch (loss 1.7039):  81%|████████  | 1259/1563 [33:32<09:14,  1.82s/it]
Training 1/1 epoch (loss 1.6287):  81%|████████  | 1259/1563 [33:34<09:14,  1.82s/it]
Training 1/1 epoch (loss 1.6287):  81%|████████  | 1260/1563 [33:34<09:20,  1.85s/it]
Training 1/1 epoch (loss 1.5416):  81%|████████  | 1260/1563 [33:35<09:20,  1.85s/it]
Training 1/1 epoch (loss 1.5416):  81%|████████  | 1261/1563 [33:35<08:35,  1.71s/it]
Training 1/1 epoch (loss 1.5669):  81%|████████  | 1261/1563 [33:37<08:35,  1.71s/it]
Training 1/1 epoch (loss 1.5669):  81%|████████  | 1262/1563 [33:37<08:55,  1.78s/it]
Training 1/1 epoch (loss 1.5650):  81%|████████  | 1262/1563 [33:39<08:55,  1.78s/it]
Training 1/1 epoch (loss 1.5650):  81%|████████  | 1263/1563 [33:39<09:26,  1.89s/it]
Training 1/1 epoch (loss 1.6376):  81%|████████  | 1263/1563 [33:41<09:26,  1.89s/it]
Training 1/1 epoch (loss 1.6376):  81%|████████  | 1264/1563 [33:41<09:59,  2.01s/it]
Training 1/1 epoch (loss 1.5949):  81%|████████  | 1264/1563 [33:43<09:59,  2.01s/it]
Training 1/1 epoch (loss 1.5949):  81%|████████  | 1265/1563 [33:43<09:46,  1.97s/it]
Training 1/1 epoch (loss 1.4761):  81%|████████  | 1265/1563 [33:45<09:46,  1.97s/it]
Training 1/1 epoch (loss 1.4761):  81%|████████  | 1266/1563 [33:45<08:42,  1.76s/it]
Training 1/1 epoch (loss 1.5266):  81%|████████  | 1266/1563 [33:46<08:42,  1.76s/it]
Training 1/1 epoch (loss 1.5266):  81%|████████  | 1267/1563 [33:46<08:42,  1.77s/it]
Training 1/1 epoch (loss 1.4920):  81%|████████  | 1267/1563 [33:48<08:42,  1.77s/it]
Training 1/1 epoch (loss 1.4920):  81%|████████  | 1268/1563 [33:48<08:09,  1.66s/it]
Training 1/1 epoch (loss 1.6193):  81%|████████  | 1268/1563 [33:50<08:09,  1.66s/it]
Training 1/1 epoch (loss 1.6193):  81%|████████  | 1269/1563 [33:50<08:17,  1.69s/it]
Training 1/1 epoch (loss 1.5463):  81%|████████  | 1269/1563 [33:52<08:17,  1.69s/it]
Training 1/1 epoch (loss 1.5463):  81%|████████▏ | 1270/1563 [33:52<09:20,  1.91s/it]
Training 1/1 epoch (loss 1.6419):  81%|████████▏ | 1270/1563 [33:53<09:20,  1.91s/it]
Training 1/1 epoch (loss 1.6419):  81%|████████▏ | 1271/1563 [33:53<08:34,  1.76s/it]
Training 1/1 epoch (loss 1.5421):  81%|████████▏ | 1271/1563 [33:55<08:34,  1.76s/it]
Training 1/1 epoch (loss 1.5421):  81%|████████▏ | 1272/1563 [33:55<07:57,  1.64s/it]
Training 1/1 epoch (loss 1.6592):  81%|████████▏ | 1272/1563 [33:57<07:57,  1.64s/it]
Training 1/1 epoch (loss 1.6592):  81%|████████▏ | 1273/1563 [33:57<08:25,  1.74s/it]
Training 1/1 epoch (loss 1.6392):  81%|████████▏ | 1273/1563 [33:58<08:25,  1.74s/it]
Training 1/1 epoch (loss 1.6392):  82%|████████▏ | 1274/1563 [33:58<08:07,  1.69s/it]
Training 1/1 epoch (loss 1.6064):  82%|████████▏ | 1274/1563 [34:00<08:07,  1.69s/it]
Training 1/1 epoch (loss 1.6064):  82%|████████▏ | 1275/1563 [34:00<07:53,  1.64s/it]
Training 1/1 epoch (loss 1.6205):  82%|████████▏ | 1275/1563 [34:02<07:53,  1.64s/it]
Training 1/1 epoch (loss 1.6205):  82%|████████▏ | 1276/1563 [34:02<08:44,  1.83s/it]
Training 1/1 epoch (loss 1.4298):  82%|████████▏ | 1276/1563 [34:04<08:44,  1.83s/it]
Training 1/1 epoch (loss 1.4298):  82%|████████▏ | 1277/1563 [34:04<09:08,  1.92s/it]
Training 1/1 epoch (loss 1.5807):  82%|████████▏ | 1277/1563 [34:06<09:08,  1.92s/it]
Training 1/1 epoch (loss 1.5807):  82%|████████▏ | 1278/1563 [34:06<09:34,  2.02s/it]
Training 1/1 epoch (loss 1.4942):  82%|████████▏ | 1278/1563 [34:09<09:34,  2.02s/it]
Training 1/1 epoch (loss 1.4942):  82%|████████▏ | 1279/1563 [34:09<09:38,  2.04s/it]
Training 1/1 epoch (loss 1.4067):  82%|████████▏ | 1279/1563 [34:11<09:38,  2.04s/it]
Training 1/1 epoch (loss 1.4067):  82%|████████▏ | 1280/1563 [34:11<10:32,  2.24s/it]
Training 1/1 epoch (loss 1.5387):  82%|████████▏ | 1280/1563 [34:13<10:32,  2.24s/it]
Training 1/1 epoch (loss 1.5387):  82%|████████▏ | 1281/1563 [34:13<09:18,  1.98s/it]
Training 1/1 epoch (loss 1.6451):  82%|████████▏ | 1281/1563 [34:14<09:18,  1.98s/it]
Training 1/1 epoch (loss 1.6451):  82%|████████▏ | 1282/1563 [34:14<08:48,  1.88s/it]
Training 1/1 epoch (loss 1.5181):  82%|████████▏ | 1282/1563 [34:16<08:48,  1.88s/it]
Training 1/1 epoch (loss 1.5181):  82%|████████▏ | 1283/1563 [34:16<08:35,  1.84s/it]
Training 1/1 epoch (loss 1.6480):  82%|████████▏ | 1283/1563 [34:18<08:35,  1.84s/it]
Training 1/1 epoch (loss 1.6480):  82%|████████▏ | 1284/1563 [34:18<09:21,  2.01s/it]
Training 1/1 epoch (loss 1.4852):  82%|████████▏ | 1284/1563 [34:20<09:21,  2.01s/it]
Training 1/1 epoch (loss 1.4852):  82%|████████▏ | 1285/1563 [34:20<09:19,  2.01s/it]
Training 1/1 epoch (loss 1.5208):  82%|████████▏ | 1285/1563 [34:23<09:19,  2.01s/it]
Training 1/1 epoch (loss 1.5208):  82%|████████▏ | 1286/1563 [34:23<09:45,  2.11s/it]
Training 1/1 epoch (loss 1.5891):  82%|████████▏ | 1286/1563 [34:25<09:45,  2.11s/it]
Training 1/1 epoch (loss 1.5891):  82%|████████▏ | 1287/1563 [34:25<09:18,  2.02s/it]
Training 1/1 epoch (loss 1.4608):  82%|████████▏ | 1287/1563 [34:27<09:18,  2.02s/it]
Training 1/1 epoch (loss 1.4608):  82%|████████▏ | 1288/1563 [34:27<09:39,  2.11s/it]
Training 1/1 epoch (loss 1.5932):  82%|████████▏ | 1288/1563 [34:29<09:39,  2.11s/it]
Training 1/1 epoch (loss 1.5932):  82%|████████▏ | 1289/1563 [34:29<09:22,  2.05s/it]
Training 1/1 epoch (loss 1.5642):  82%|████████▏ | 1289/1563 [34:31<09:22,  2.05s/it]
Training 1/1 epoch (loss 1.5642):  83%|████████▎ | 1290/1563 [34:31<08:58,  1.97s/it]
Training 1/1 epoch (loss 1.6445):  83%|████████▎ | 1290/1563 [34:33<08:58,  1.97s/it]
Training 1/1 epoch (loss 1.6445):  83%|████████▎ | 1291/1563 [34:33<09:21,  2.07s/it]
Training 1/1 epoch (loss 1.5393):  83%|████████▎ | 1291/1563 [34:34<09:21,  2.07s/it]
Training 1/1 epoch (loss 1.5393):  83%|████████▎ | 1292/1563 [34:34<08:18,  1.84s/it]
Training 1/1 epoch (loss 1.5789):  83%|████████▎ | 1292/1563 [34:36<08:18,  1.84s/it]
Training 1/1 epoch (loss 1.5789):  83%|████████▎ | 1293/1563 [34:36<08:10,  1.82s/it]
Training 1/1 epoch (loss 1.6085):  83%|████████▎ | 1293/1563 [34:38<08:10,  1.82s/it]
Training 1/1 epoch (loss 1.6085):  83%|████████▎ | 1294/1563 [34:38<08:45,  1.95s/it]
Training 1/1 epoch (loss 1.6357):  83%|████████▎ | 1294/1563 [34:40<08:45,  1.95s/it]
Training 1/1 epoch (loss 1.6357):  83%|████████▎ | 1295/1563 [34:40<07:56,  1.78s/it]
Training 1/1 epoch (loss 1.5933):  83%|████████▎ | 1295/1563 [34:41<07:56,  1.78s/it]
Training 1/1 epoch (loss 1.5933):  83%|████████▎ | 1296/1563 [34:41<07:51,  1.77s/it]
Training 1/1 epoch (loss 1.6326):  83%|████████▎ | 1296/1563 [34:43<07:51,  1.77s/it]
Training 1/1 epoch (loss 1.6326):  83%|████████▎ | 1297/1563 [34:43<07:30,  1.69s/it]
Training 1/1 epoch (loss 1.5077):  83%|████████▎ | 1297/1563 [34:44<07:30,  1.69s/it]
Training 1/1 epoch (loss 1.5077):  83%|████████▎ | 1298/1563 [34:44<07:18,  1.65s/it]
Training 1/1 epoch (loss 1.6522):  83%|████████▎ | 1298/1563 [34:46<07:18,  1.65s/it]
Training 1/1 epoch (loss 1.6522):  83%|████████▎ | 1299/1563 [34:46<07:40,  1.74s/it]
Training 1/1 epoch (loss 1.5859):  83%|████████▎ | 1299/1563 [34:48<07:40,  1.74s/it]
Training 1/1 epoch (loss 1.5859):  83%|████████▎ | 1300/1563 [34:48<07:52,  1.80s/it]
Training 1/1 epoch (loss 1.5587):  83%|████████▎ | 1300/1563 [34:50<07:52,  1.80s/it]
Training 1/1 epoch (loss 1.5587):  83%|████████▎ | 1301/1563 [34:50<07:45,  1.78s/it]
Training 1/1 epoch (loss 1.5381):  83%|████████▎ | 1301/1563 [34:52<07:45,  1.78s/it]
Training 1/1 epoch (loss 1.5381):  83%|████████▎ | 1302/1563 [34:52<07:32,  1.73s/it]
Training 1/1 epoch (loss 1.5564):  83%|████████▎ | 1302/1563 [34:53<07:32,  1.73s/it]
Training 1/1 epoch (loss 1.5564):  83%|████████▎ | 1303/1563 [34:53<07:09,  1.65s/it]
Training 1/1 epoch (loss 1.5723):  83%|████████▎ | 1303/1563 [34:55<07:09,  1.65s/it]
Training 1/1 epoch (loss 1.5723):  83%|████████▎ | 1304/1563 [34:55<07:54,  1.83s/it]
Training 1/1 epoch (loss 1.4853):  83%|████████▎ | 1304/1563 [34:57<07:54,  1.83s/it]
Training 1/1 epoch (loss 1.4853):  83%|████████▎ | 1305/1563 [34:57<07:08,  1.66s/it]
Training 1/1 epoch (loss 1.4728):  83%|████████▎ | 1305/1563 [34:59<07:08,  1.66s/it]
Training 1/1 epoch (loss 1.4728):  84%|████████▎ | 1306/1563 [34:59<07:53,  1.84s/it]
Training 1/1 epoch (loss 1.6140):  84%|████████▎ | 1306/1563 [35:00<07:53,  1.84s/it]
Training 1/1 epoch (loss 1.6140):  84%|████████▎ | 1307/1563 [35:00<07:00,  1.64s/it]
Training 1/1 epoch (loss 1.4878):  84%|████████▎ | 1307/1563 [35:02<07:00,  1.64s/it]
Training 1/1 epoch (loss 1.4878):  84%|████████▎ | 1308/1563 [35:02<06:59,  1.64s/it]
Training 1/1 epoch (loss 1.5799):  84%|████████▎ | 1308/1563 [35:04<06:59,  1.64s/it]
Training 1/1 epoch (loss 1.5799):  84%|████████▎ | 1309/1563 [35:04<07:34,  1.79s/it]
Training 1/1 epoch (loss 1.5702):  84%|████████▎ | 1309/1563 [35:06<07:34,  1.79s/it]
Training 1/1 epoch (loss 1.5702):  84%|████████▍ | 1310/1563 [35:06<07:59,  1.90s/it]
Training 1/1 epoch (loss 1.6775):  84%|████████▍ | 1310/1563 [35:08<07:59,  1.90s/it]
Training 1/1 epoch (loss 1.6775):  84%|████████▍ | 1311/1563 [35:08<07:56,  1.89s/it]
Training 1/1 epoch (loss 1.5850):  84%|████████▍ | 1311/1563 [35:10<07:56,  1.89s/it]
Training 1/1 epoch (loss 1.5850):  84%|████████▍ | 1312/1563 [35:10<07:33,  1.81s/it]
Training 1/1 epoch (loss 1.5066):  84%|████████▍ | 1312/1563 [35:12<07:33,  1.81s/it]
Training 1/1 epoch (loss 1.5066):  84%|████████▍ | 1313/1563 [35:12<07:52,  1.89s/it]
Training 1/1 epoch (loss 1.6267):  84%|████████▍ | 1313/1563 [35:14<07:52,  1.89s/it]
Training 1/1 epoch (loss 1.6267):  84%|████████▍ | 1314/1563 [35:14<08:33,  2.06s/it]
Training 1/1 epoch (loss 1.4755):  84%|████████▍ | 1314/1563 [35:16<08:33,  2.06s/it]
Training 1/1 epoch (loss 1.4755):  84%|████████▍ | 1315/1563 [35:16<07:46,  1.88s/it]
Training 1/1 epoch (loss 1.5492):  84%|████████▍ | 1315/1563 [35:17<07:46,  1.88s/it]
Training 1/1 epoch (loss 1.5492):  84%|████████▍ | 1316/1563 [35:17<07:23,  1.80s/it]
Training 1/1 epoch (loss 1.6022):  84%|████████▍ | 1316/1563 [35:19<07:23,  1.80s/it]
Training 1/1 epoch (loss 1.6022):  84%|████████▍ | 1317/1563 [35:19<07:10,  1.75s/it]
Training 1/1 epoch (loss 1.6135):  84%|████████▍ | 1317/1563 [35:21<07:10,  1.75s/it]
Training 1/1 epoch (loss 1.6135):  84%|████████▍ | 1318/1563 [35:21<07:10,  1.76s/it]
Training 1/1 epoch (loss 1.5304):  84%|████████▍ | 1318/1563 [35:23<07:10,  1.76s/it]
Training 1/1 epoch (loss 1.5304):  84%|████████▍ | 1319/1563 [35:23<07:28,  1.84s/it]
Training 1/1 epoch (loss 1.5886):  84%|████████▍ | 1319/1563 [35:24<07:28,  1.84s/it]
Training 1/1 epoch (loss 1.5886):  84%|████████▍ | 1320/1563 [35:24<07:17,  1.80s/it]
Training 1/1 epoch (loss 1.5341):  84%|████████▍ | 1320/1563 [35:26<07:17,  1.80s/it]
Training 1/1 epoch (loss 1.5341):  85%|████████▍ | 1321/1563 [35:26<07:00,  1.74s/it]
Training 1/1 epoch (loss 1.5865):  85%|████████▍ | 1321/1563 [35:28<07:00,  1.74s/it]
Training 1/1 epoch (loss 1.5865):  85%|████████▍ | 1322/1563 [35:28<07:43,  1.92s/it]
Training 1/1 epoch (loss 1.6343):  85%|████████▍ | 1322/1563 [35:31<07:43,  1.92s/it]
Training 1/1 epoch (loss 1.6343):  85%|████████▍ | 1323/1563 [35:31<08:22,  2.09s/it]
Training 1/1 epoch (loss 1.5661):  85%|████████▍ | 1323/1563 [35:33<08:22,  2.09s/it]
Training 1/1 epoch (loss 1.5661):  85%|████████▍ | 1324/1563 [35:33<08:11,  2.06s/it]
Training 1/1 epoch (loss 1.5623):  85%|████████▍ | 1324/1563 [35:34<08:11,  2.06s/it]
Training 1/1 epoch (loss 1.5623):  85%|████████▍ | 1325/1563 [35:34<07:21,  1.85s/it]
Training 1/1 epoch (loss 1.6150):  85%|████████▍ | 1325/1563 [35:36<07:21,  1.85s/it]
Training 1/1 epoch (loss 1.6150):  85%|████████▍ | 1326/1563 [35:36<07:28,  1.89s/it]
Training 1/1 epoch (loss 1.4608):  85%|████████▍ | 1326/1563 [35:38<07:28,  1.89s/it]
Training 1/1 epoch (loss 1.4608):  85%|████████▍ | 1327/1563 [35:38<07:36,  1.93s/it]
Training 1/1 epoch (loss 1.6166):  85%|████████▍ | 1327/1563 [35:40<07:36,  1.93s/it]
Training 1/1 epoch (loss 1.6166):  85%|████████▍ | 1328/1563 [35:40<07:06,  1.82s/it]
Training 1/1 epoch (loss 1.6093):  85%|████████▍ | 1328/1563 [35:42<07:06,  1.82s/it]
Training 1/1 epoch (loss 1.6093):  85%|████████▌ | 1329/1563 [35:42<07:41,  1.97s/it]
Training 1/1 epoch (loss 1.6507):  85%|████████▌ | 1329/1563 [35:44<07:41,  1.97s/it]
Training 1/1 epoch (loss 1.6507):  85%|████████▌ | 1330/1563 [35:44<08:02,  2.07s/it]
Training 1/1 epoch (loss 1.5204):  85%|████████▌ | 1330/1563 [35:46<08:02,  2.07s/it]
Training 1/1 epoch (loss 1.5204):  85%|████████▌ | 1331/1563 [35:46<08:06,  2.10s/it]
Training 1/1 epoch (loss 1.5530):  85%|████████▌ | 1331/1563 [35:48<08:06,  2.10s/it]
Training 1/1 epoch (loss 1.5530):  85%|████████▌ | 1332/1563 [35:48<07:10,  1.86s/it]
Training 1/1 epoch (loss 1.5358):  85%|████████▌ | 1332/1563 [35:50<07:10,  1.86s/it]
Training 1/1 epoch (loss 1.5358):  85%|████████▌ | 1333/1563 [35:50<07:51,  2.05s/it]
Training 1/1 epoch (loss 1.5461):  85%|████████▌ | 1333/1563 [35:52<07:51,  2.05s/it]
Training 1/1 epoch (loss 1.5461):  85%|████████▌ | 1334/1563 [35:52<07:30,  1.97s/it]
Training 1/1 epoch (loss 1.5437):  85%|████████▌ | 1334/1563 [35:54<07:30,  1.97s/it]
Training 1/1 epoch (loss 1.5437):  85%|████████▌ | 1335/1563 [35:54<07:27,  1.96s/it]
Training 1/1 epoch (loss 1.5062):  85%|████████▌ | 1335/1563 [35:56<07:27,  1.96s/it]
Training 1/1 epoch (loss 1.5062):  85%|████████▌ | 1336/1563 [35:56<07:05,  1.87s/it]
Training 1/1 epoch (loss 1.5716):  85%|████████▌ | 1336/1563 [35:57<07:05,  1.87s/it]
Training 1/1 epoch (loss 1.5716):  86%|████████▌ | 1337/1563 [35:57<06:56,  1.84s/it]
Training 1/1 epoch (loss 1.5446):  86%|████████▌ | 1337/1563 [36:00<06:56,  1.84s/it]
Training 1/1 epoch (loss 1.5446):  86%|████████▌ | 1338/1563 [36:00<07:28,  1.99s/it]
Training 1/1 epoch (loss 1.4955):  86%|████████▌ | 1338/1563 [36:02<07:28,  1.99s/it]
Training 1/1 epoch (loss 1.4955):  86%|████████▌ | 1339/1563 [36:02<08:00,  2.14s/it]
Training 1/1 epoch (loss 1.6611):  86%|████████▌ | 1339/1563 [36:04<08:00,  2.14s/it]
Training 1/1 epoch (loss 1.6611):  86%|████████▌ | 1340/1563 [36:04<07:15,  1.95s/it]
Training 1/1 epoch (loss 1.4475):  86%|████████▌ | 1340/1563 [36:06<07:15,  1.95s/it]
Training 1/1 epoch (loss 1.4475):  86%|████████▌ | 1341/1563 [36:06<07:41,  2.08s/it]
Training 1/1 epoch (loss 1.4748):  86%|████████▌ | 1341/1563 [36:08<07:41,  2.08s/it]
Training 1/1 epoch (loss 1.4748):  86%|████████▌ | 1342/1563 [36:08<07:39,  2.08s/it]
Training 1/1 epoch (loss 1.5766):  86%|████████▌ | 1342/1563 [36:10<07:39,  2.08s/it]
Training 1/1 epoch (loss 1.5766):  86%|████████▌ | 1343/1563 [36:10<07:45,  2.12s/it]
Training 1/1 epoch (loss 1.5743):  86%|████████▌ | 1343/1563 [36:12<07:45,  2.12s/it]
Training 1/1 epoch (loss 1.5743):  86%|████████▌ | 1344/1563 [36:12<07:40,  2.10s/it]
Training 1/1 epoch (loss 1.5198):  86%|████████▌ | 1344/1563 [36:14<07:40,  2.10s/it]
Training 1/1 epoch (loss 1.5198):  86%|████████▌ | 1345/1563 [36:14<07:19,  2.01s/it]
Training 1/1 epoch (loss 1.5403):  86%|████████▌ | 1345/1563 [36:16<07:19,  2.01s/it]
Training 1/1 epoch (loss 1.5403):  86%|████████▌ | 1346/1563 [36:16<07:02,  1.95s/it]
Training 1/1 epoch (loss 1.6333):  86%|████████▌ | 1346/1563 [36:18<07:02,  1.95s/it]
Training 1/1 epoch (loss 1.6333):  86%|████████▌ | 1347/1563 [36:18<07:32,  2.10s/it]
Training 1/1 epoch (loss 1.5476):  86%|████████▌ | 1347/1563 [36:20<07:32,  2.10s/it]
Training 1/1 epoch (loss 1.5476):  86%|████████▌ | 1348/1563 [36:20<06:45,  1.88s/it]
Training 1/1 epoch (loss 1.5611):  86%|████████▌ | 1348/1563 [36:22<06:45,  1.88s/it]
Training 1/1 epoch (loss 1.5611):  86%|████████▋ | 1349/1563 [36:22<07:19,  2.05s/it]
Training 1/1 epoch (loss 1.6265):  86%|████████▋ | 1349/1563 [36:24<07:19,  2.05s/it]
Training 1/1 epoch (loss 1.6265):  86%|████████▋ | 1350/1563 [36:24<06:21,  1.79s/it]
Training 1/1 epoch (loss 1.5605):  86%|████████▋ | 1350/1563 [36:25<06:21,  1.79s/it]
Training 1/1 epoch (loss 1.5605):  86%|████████▋ | 1351/1563 [36:25<06:26,  1.82s/it]
Training 1/1 epoch (loss 1.5793):  86%|████████▋ | 1351/1563 [36:27<06:26,  1.82s/it]
Training 1/1 epoch (loss 1.5793):  87%|████████▋ | 1352/1563 [36:27<06:29,  1.84s/it]
Training 1/1 epoch (loss 1.4544):  87%|████████▋ | 1352/1563 [36:29<06:29,  1.84s/it]
Training 1/1 epoch (loss 1.4544):  87%|████████▋ | 1353/1563 [36:29<06:10,  1.76s/it]
Training 1/1 epoch (loss 1.5903):  87%|████████▋ | 1353/1563 [36:31<06:10,  1.76s/it]
Training 1/1 epoch (loss 1.5903):  87%|████████▋ | 1354/1563 [36:31<06:01,  1.73s/it]
Training 1/1 epoch (loss 1.5661):  87%|████████▋ | 1354/1563 [36:32<06:01,  1.73s/it]
Training 1/1 epoch (loss 1.5661):  87%|████████▋ | 1355/1563 [36:32<06:01,  1.74s/it]
Training 1/1 epoch (loss 1.5867):  87%|████████▋ | 1355/1563 [36:34<06:01,  1.74s/it]
Training 1/1 epoch (loss 1.5867):  87%|████████▋ | 1356/1563 [36:34<06:24,  1.86s/it]
Training 1/1 epoch (loss 1.4293):  87%|████████▋ | 1356/1563 [36:36<06:24,  1.86s/it]
Training 1/1 epoch (loss 1.4293):  87%|████████▋ | 1357/1563 [36:36<05:47,  1.69s/it]
Training 1/1 epoch (loss 1.5101):  87%|████████▋ | 1357/1563 [36:38<05:47,  1.69s/it]
Training 1/1 epoch (loss 1.5101):  87%|████████▋ | 1358/1563 [36:38<06:08,  1.80s/it]
Training 1/1 epoch (loss 1.5606):  87%|████████▋ | 1358/1563 [36:39<06:08,  1.80s/it]
Training 1/1 epoch (loss 1.5606):  87%|████████▋ | 1359/1563 [36:39<05:55,  1.74s/it]
Training 1/1 epoch (loss 1.6378):  87%|████████▋ | 1359/1563 [36:41<05:55,  1.74s/it]
Training 1/1 epoch (loss 1.6378):  87%|████████▋ | 1360/1563 [36:41<06:11,  1.83s/it]
Training 1/1 epoch (loss 1.5603):  87%|████████▋ | 1360/1563 [36:43<06:11,  1.83s/it]
Training 1/1 epoch (loss 1.5603):  87%|████████▋ | 1361/1563 [36:43<05:27,  1.62s/it]
Training 1/1 epoch (loss 1.4943):  87%|████████▋ | 1361/1563 [36:44<05:27,  1.62s/it]
Training 1/1 epoch (loss 1.4943):  87%|████████▋ | 1362/1563 [36:44<05:02,  1.51s/it]
Training 1/1 epoch (loss 1.5891):  87%|████████▋ | 1362/1563 [36:46<05:02,  1.51s/it]
Training 1/1 epoch (loss 1.5891):  87%|████████▋ | 1363/1563 [36:46<05:17,  1.59s/it]
Training 1/1 epoch (loss 1.4878):  87%|████████▋ | 1363/1563 [36:47<05:17,  1.59s/it]
Training 1/1 epoch (loss 1.4878):  87%|████████▋ | 1364/1563 [36:47<05:21,  1.61s/it]
Training 1/1 epoch (loss 1.5786):  87%|████████▋ | 1364/1563 [36:50<05:21,  1.61s/it]
Training 1/1 epoch (loss 1.5786):  87%|████████▋ | 1365/1563 [36:50<06:06,  1.85s/it]
Training 1/1 epoch (loss 1.5553):  87%|████████▋ | 1365/1563 [36:52<06:06,  1.85s/it]
Training 1/1 epoch (loss 1.5553):  87%|████████▋ | 1366/1563 [36:52<06:15,  1.91s/it]
Training 1/1 epoch (loss 1.5829):  87%|████████▋ | 1366/1563 [36:53<06:15,  1.91s/it]
Training 1/1 epoch (loss 1.5829):  87%|████████▋ | 1367/1563 [36:53<06:01,  1.84s/it]
Training 1/1 epoch (loss 1.7079):  87%|████████▋ | 1367/1563 [36:55<06:01,  1.84s/it]
Training 1/1 epoch (loss 1.7079):  88%|████████▊ | 1368/1563 [36:55<06:09,  1.90s/it]
Training 1/1 epoch (loss 1.5586):  88%|████████▊ | 1368/1563 [36:57<06:09,  1.90s/it]
Training 1/1 epoch (loss 1.5586):  88%|████████▊ | 1369/1563 [36:57<06:17,  1.95s/it]
Training 1/1 epoch (loss 1.5831):  88%|████████▊ | 1369/1563 [36:59<06:17,  1.95s/it]
Training 1/1 epoch (loss 1.5831):  88%|████████▊ | 1370/1563 [36:59<06:07,  1.90s/it]
Training 1/1 epoch (loss 1.5383):  88%|████████▊ | 1370/1563 [37:01<06:07,  1.90s/it]
Training 1/1 epoch (loss 1.5383):  88%|████████▊ | 1371/1563 [37:01<05:41,  1.78s/it]
Training 1/1 epoch (loss 1.7248):  88%|████████▊ | 1371/1563 [37:02<05:41,  1.78s/it]
Training 1/1 epoch (loss 1.7248):  88%|████████▊ | 1372/1563 [37:02<05:03,  1.59s/it]
Training 1/1 epoch (loss 1.4351):  88%|████████▊ | 1372/1563 [37:04<05:03,  1.59s/it]
Training 1/1 epoch (loss 1.4351):  88%|████████▊ | 1373/1563 [37:04<05:25,  1.72s/it]
Training 1/1 epoch (loss 1.5970):  88%|████████▊ | 1373/1563 [37:06<05:25,  1.72s/it]
Training 1/1 epoch (loss 1.5970):  88%|████████▊ | 1374/1563 [37:06<05:30,  1.75s/it]
Training 1/1 epoch (loss 1.6188):  88%|████████▊ | 1374/1563 [37:08<05:30,  1.75s/it]
Training 1/1 epoch (loss 1.6188):  88%|████████▊ | 1375/1563 [37:08<06:08,  1.96s/it]
Training 1/1 epoch (loss 1.6196):  88%|████████▊ | 1375/1563 [37:10<06:08,  1.96s/it]
Training 1/1 epoch (loss 1.6196):  88%|████████▊ | 1376/1563 [37:10<05:53,  1.89s/it]
Training 1/1 epoch (loss 1.5985):  88%|████████▊ | 1376/1563 [37:12<05:53,  1.89s/it]
Training 1/1 epoch (loss 1.5985):  88%|████████▊ | 1377/1563 [37:12<05:43,  1.85s/it]
Training 1/1 epoch (loss 1.4026):  88%|████████▊ | 1377/1563 [37:13<05:43,  1.85s/it]
Training 1/1 epoch (loss 1.4026):  88%|████████▊ | 1378/1563 [37:13<05:21,  1.74s/it]
Training 1/1 epoch (loss 1.5130):  88%|████████▊ | 1378/1563 [37:15<05:21,  1.74s/it]
Training 1/1 epoch (loss 1.5130):  88%|████████▊ | 1379/1563 [37:15<05:34,  1.82s/it]
Training 1/1 epoch (loss 1.5330):  88%|████████▊ | 1379/1563 [37:17<05:34,  1.82s/it]
Training 1/1 epoch (loss 1.5330):  88%|████████▊ | 1380/1563 [37:17<05:55,  1.94s/it]
Training 1/1 epoch (loss 1.5487):  88%|████████▊ | 1380/1563 [37:19<05:55,  1.94s/it]
Training 1/1 epoch (loss 1.5487):  88%|████████▊ | 1381/1563 [37:19<05:29,  1.81s/it]
Training 1/1 epoch (loss 1.6119):  88%|████████▊ | 1381/1563 [37:20<05:29,  1.81s/it]
Training 1/1 epoch (loss 1.6119):  88%|████████▊ | 1382/1563 [37:20<05:08,  1.70s/it]
Training 1/1 epoch (loss 1.5166):  88%|████████▊ | 1382/1563 [37:21<05:08,  1.70s/it]
Training 1/1 epoch (loss 1.5166):  88%|████████▊ | 1383/1563 [37:21<04:30,  1.50s/it]
Training 1/1 epoch (loss 1.5832):  88%|████████▊ | 1383/1563 [37:23<04:30,  1.50s/it]
Training 1/1 epoch (loss 1.5832):  89%|████████▊ | 1384/1563 [37:23<04:48,  1.61s/it]
Training 1/1 epoch (loss 1.5055):  89%|████████▊ | 1384/1563 [37:25<04:48,  1.61s/it]
Training 1/1 epoch (loss 1.5055):  89%|████████▊ | 1385/1563 [37:25<04:52,  1.64s/it]
Training 1/1 epoch (loss 1.5345):  89%|████████▊ | 1385/1563 [37:26<04:52,  1.64s/it]
Training 1/1 epoch (loss 1.5345):  89%|████████▊ | 1386/1563 [37:26<04:31,  1.53s/it]
Training 1/1 epoch (loss 1.5492):  89%|████████▊ | 1386/1563 [37:28<04:31,  1.53s/it]
Training 1/1 epoch (loss 1.5492):  89%|████████▊ | 1387/1563 [37:28<04:37,  1.57s/it]
Training 1/1 epoch (loss 1.6548):  89%|████████▊ | 1387/1563 [37:30<04:37,  1.57s/it]
Training 1/1 epoch (loss 1.6548):  89%|████████▉ | 1388/1563 [37:30<04:54,  1.68s/it]
Training 1/1 epoch (loss 1.5080):  89%|████████▉ | 1388/1563 [37:32<04:54,  1.68s/it]
Training 1/1 epoch (loss 1.5080):  89%|████████▉ | 1389/1563 [37:32<04:56,  1.70s/it]
Training 1/1 epoch (loss 1.5842):  89%|████████▉ | 1389/1563 [37:33<04:56,  1.70s/it]
Training 1/1 epoch (loss 1.5842):  89%|████████▉ | 1390/1563 [37:33<04:56,  1.71s/it]
Training 1/1 epoch (loss 1.4638):  89%|████████▉ | 1390/1563 [37:35<04:56,  1.71s/it]
Training 1/1 epoch (loss 1.4638):  89%|████████▉ | 1391/1563 [37:35<04:49,  1.68s/it]
Training 1/1 epoch (loss 1.5242):  89%|████████▉ | 1391/1563 [37:37<04:49,  1.68s/it]
Training 1/1 epoch (loss 1.5242):  89%|████████▉ | 1392/1563 [37:37<04:56,  1.74s/it]
Training 1/1 epoch (loss 1.5911):  89%|████████▉ | 1392/1563 [37:39<04:56,  1.74s/it]
Training 1/1 epoch (loss 1.5911):  89%|████████▉ | 1393/1563 [37:39<05:04,  1.79s/it]
Training 1/1 epoch (loss 1.5003):  89%|████████▉ | 1393/1563 [37:40<05:04,  1.79s/it]
Training 1/1 epoch (loss 1.5003):  89%|████████▉ | 1394/1563 [37:40<04:52,  1.73s/it]
Training 1/1 epoch (loss 1.5186):  89%|████████▉ | 1394/1563 [37:43<04:52,  1.73s/it]
Training 1/1 epoch (loss 1.5186):  89%|████████▉ | 1395/1563 [37:43<05:25,  1.94s/it]
Training 1/1 epoch (loss 1.6131):  89%|████████▉ | 1395/1563 [37:44<05:25,  1.94s/it]
Training 1/1 epoch (loss 1.6131):  89%|████████▉ | 1396/1563 [37:44<04:53,  1.76s/it]
Training 1/1 epoch (loss 1.5399):  89%|████████▉ | 1396/1563 [37:46<04:53,  1.76s/it]
Training 1/1 epoch (loss 1.5399):  89%|████████▉ | 1397/1563 [37:46<05:15,  1.90s/it]
Training 1/1 epoch (loss 1.6210):  89%|████████▉ | 1397/1563 [37:48<05:15,  1.90s/it]
Training 1/1 epoch (loss 1.6210):  89%|████████▉ | 1398/1563 [37:48<04:41,  1.71s/it]
Training 1/1 epoch (loss 1.5895):  89%|████████▉ | 1398/1563 [37:49<04:41,  1.71s/it]
Training 1/1 epoch (loss 1.5895):  90%|████████▉ | 1399/1563 [37:49<04:35,  1.68s/it]
Training 1/1 epoch (loss 1.4685):  90%|████████▉ | 1399/1563 [37:51<04:35,  1.68s/it]
Training 1/1 epoch (loss 1.4685):  90%|████████▉ | 1400/1563 [37:51<04:47,  1.76s/it]
Training 1/1 epoch (loss 1.5532):  90%|████████▉ | 1400/1563 [37:53<04:47,  1.76s/it]
Training 1/1 epoch (loss 1.5532):  90%|████████▉ | 1401/1563 [37:53<04:40,  1.73s/it]
Training 1/1 epoch (loss 1.4875):  90%|████████▉ | 1401/1563 [37:54<04:40,  1.73s/it]
Training 1/1 epoch (loss 1.4875):  90%|████████▉ | 1402/1563 [37:54<04:11,  1.56s/it]
Training 1/1 epoch (loss 1.4051):  90%|████████▉ | 1402/1563 [37:56<04:11,  1.56s/it]
Training 1/1 epoch (loss 1.4051):  90%|████████▉ | 1403/1563 [37:56<04:49,  1.81s/it]
Training 1/1 epoch (loss 1.5159):  90%|████████▉ | 1403/1563 [37:58<04:49,  1.81s/it]
Training 1/1 epoch (loss 1.5159):  90%|████████▉ | 1404/1563 [37:58<04:27,  1.68s/it]
Training 1/1 epoch (loss 1.5057):  90%|████████▉ | 1404/1563 [37:59<04:27,  1.68s/it]
Training 1/1 epoch (loss 1.5057):  90%|████████▉ | 1405/1563 [37:59<04:27,  1.70s/it]
Training 1/1 epoch (loss 1.5420):  90%|████████▉ | 1405/1563 [38:01<04:27,  1.70s/it]
Training 1/1 epoch (loss 1.5420):  90%|████████▉ | 1406/1563 [38:01<03:58,  1.52s/it]
Training 1/1 epoch (loss 1.5001):  90%|████████▉ | 1406/1563 [38:02<03:58,  1.52s/it]
Training 1/1 epoch (loss 1.5001):  90%|█████████ | 1407/1563 [38:02<03:45,  1.45s/it]
Training 1/1 epoch (loss 1.6015):  90%|█████████ | 1407/1563 [38:04<03:45,  1.45s/it]
Training 1/1 epoch (loss 1.6015):  90%|█████████ | 1408/1563 [38:04<04:12,  1.63s/it]
Training 1/1 epoch (loss 1.4591):  90%|█████████ | 1408/1563 [38:05<04:12,  1.63s/it]
Training 1/1 epoch (loss 1.4591):  90%|█████████ | 1409/1563 [38:05<04:01,  1.57s/it]
Training 1/1 epoch (loss 1.4729):  90%|█████████ | 1409/1563 [38:07<04:01,  1.57s/it]
Training 1/1 epoch (loss 1.4729):  90%|█████████ | 1410/1563 [38:07<04:10,  1.64s/it]
Training 1/1 epoch (loss 1.5387):  90%|█████████ | 1410/1563 [38:09<04:10,  1.64s/it]
Training 1/1 epoch (loss 1.5387):  90%|█████████ | 1411/1563 [38:09<04:10,  1.65s/it]
Training 1/1 epoch (loss 1.5492):  90%|█████████ | 1411/1563 [38:11<04:10,  1.65s/it]
Training 1/1 epoch (loss 1.5492):  90%|█████████ | 1412/1563 [38:11<04:17,  1.70s/it]
Training 1/1 epoch (loss 1.4750):  90%|█████████ | 1412/1563 [38:12<04:17,  1.70s/it]
Training 1/1 epoch (loss 1.4750):  90%|█████████ | 1413/1563 [38:12<04:02,  1.62s/it]
Training 1/1 epoch (loss 1.4714):  90%|█████████ | 1413/1563 [38:13<04:02,  1.62s/it]
Training 1/1 epoch (loss 1.4714):  90%|█████████ | 1414/1563 [38:13<03:51,  1.55s/it]
Training 1/1 epoch (loss 1.6558):  90%|█████████ | 1414/1563 [38:16<03:51,  1.55s/it]
Training 1/1 epoch (loss 1.6558):  91%|█████████ | 1415/1563 [38:16<04:30,  1.83s/it]
Training 1/1 epoch (loss 1.5085):  91%|█████████ | 1415/1563 [38:18<04:30,  1.83s/it]
Training 1/1 epoch (loss 1.5085):  91%|█████████ | 1416/1563 [38:18<04:40,  1.91s/it]
Training 1/1 epoch (loss 1.4846):  91%|█████████ | 1416/1563 [38:20<04:40,  1.91s/it]
Training 1/1 epoch (loss 1.4846):  91%|█████████ | 1417/1563 [38:20<04:50,  1.99s/it]
Training 1/1 epoch (loss 1.5502):  91%|█████████ | 1417/1563 [38:22<04:50,  1.99s/it]
Training 1/1 epoch (loss 1.5502):  91%|█████████ | 1418/1563 [38:22<04:53,  2.02s/it]
Training 1/1 epoch (loss 1.5164):  91%|█████████ | 1418/1563 [38:23<04:53,  2.02s/it]
Training 1/1 epoch (loss 1.5164):  91%|█████████ | 1419/1563 [38:23<04:10,  1.74s/it]
Training 1/1 epoch (loss 1.5228):  91%|█████████ | 1419/1563 [38:24<04:10,  1.74s/it]
Training 1/1 epoch (loss 1.5228):  91%|█████████ | 1420/1563 [38:24<03:42,  1.55s/it]
Training 1/1 epoch (loss 1.7003):  91%|█████████ | 1420/1563 [38:26<03:42,  1.55s/it]
Training 1/1 epoch (loss 1.7003):  91%|█████████ | 1421/1563 [38:26<03:56,  1.66s/it]
Training 1/1 epoch (loss 1.5131):  91%|█████████ | 1421/1563 [38:28<03:56,  1.66s/it]
Training 1/1 epoch (loss 1.5131):  91%|█████████ | 1422/1563 [38:28<04:01,  1.71s/it]
Training 1/1 epoch (loss 1.5120):  91%|█████████ | 1422/1563 [38:30<04:01,  1.71s/it]
Training 1/1 epoch (loss 1.5120):  91%|█████████ | 1423/1563 [38:30<04:17,  1.84s/it]
Training 1/1 epoch (loss 1.6164):  91%|█████████ | 1423/1563 [38:32<04:17,  1.84s/it]
Training 1/1 epoch (loss 1.6164):  91%|█████████ | 1424/1563 [38:32<04:10,  1.81s/it]
Training 1/1 epoch (loss 1.5131):  91%|█████████ | 1424/1563 [38:34<04:10,  1.81s/it]
Training 1/1 epoch (loss 1.5131):  91%|█████████ | 1425/1563 [38:34<04:32,  1.98s/it]
Training 1/1 epoch (loss 1.5690):  91%|█████████ | 1425/1563 [38:36<04:32,  1.98s/it]
Training 1/1 epoch (loss 1.5690):  91%|█████████ | 1426/1563 [38:36<04:16,  1.87s/it]
Training 1/1 epoch (loss 1.5242):  91%|█████████ | 1426/1563 [38:38<04:16,  1.87s/it]
Training 1/1 epoch (loss 1.5242):  91%|█████████▏| 1427/1563 [38:38<04:09,  1.84s/it]
Training 1/1 epoch (loss 1.6244):  91%|█████████▏| 1427/1563 [38:40<04:09,  1.84s/it]
Training 1/1 epoch (loss 1.6244):  91%|█████████▏| 1428/1563 [38:40<04:07,  1.83s/it]
Training 1/1 epoch (loss 1.5098):  91%|█████████▏| 1428/1563 [38:41<04:07,  1.83s/it]
Training 1/1 epoch (loss 1.5098):  91%|█████████▏| 1429/1563 [38:41<03:48,  1.70s/it]
Training 1/1 epoch (loss 1.4637):  91%|█████████▏| 1429/1563 [38:43<03:48,  1.70s/it]
Training 1/1 epoch (loss 1.4637):  91%|█████████▏| 1430/1563 [38:43<03:42,  1.67s/it]
Training 1/1 epoch (loss 1.6522):  91%|█████████▏| 1430/1563 [38:44<03:42,  1.67s/it]
Training 1/1 epoch (loss 1.6522):  92%|█████████▏| 1431/1563 [38:44<03:26,  1.56s/it]
Training 1/1 epoch (loss 1.6032):  92%|█████████▏| 1431/1563 [38:46<03:26,  1.56s/it]
Training 1/1 epoch (loss 1.6032):  92%|█████████▏| 1432/1563 [38:46<03:37,  1.66s/it]
Training 1/1 epoch (loss 1.6055):  92%|█████████▏| 1432/1563 [38:47<03:37,  1.66s/it]
Training 1/1 epoch (loss 1.6055):  92%|█████████▏| 1433/1563 [38:47<03:24,  1.57s/it]
Training 1/1 epoch (loss 1.5314):  92%|█████████▏| 1433/1563 [38:49<03:24,  1.57s/it]
Training 1/1 epoch (loss 1.5314):  92%|█████████▏| 1434/1563 [38:49<03:32,  1.65s/it]
Training 1/1 epoch (loss 1.5945):  92%|█████████▏| 1434/1563 [38:51<03:32,  1.65s/it]
Training 1/1 epoch (loss 1.5945):  92%|█████████▏| 1435/1563 [38:51<03:58,  1.87s/it]
Training 1/1 epoch (loss 1.6092):  92%|█████████▏| 1435/1563 [38:53<03:58,  1.87s/it]
Training 1/1 epoch (loss 1.6092):  92%|█████████▏| 1436/1563 [38:53<03:38,  1.72s/it]
Training 1/1 epoch (loss 1.5960):  92%|█████████▏| 1436/1563 [38:55<03:38,  1.72s/it]
Training 1/1 epoch (loss 1.5960):  92%|█████████▏| 1437/1563 [38:55<04:01,  1.92s/it]
Training 1/1 epoch (loss 1.5735):  92%|█████████▏| 1437/1563 [38:57<04:01,  1.92s/it]
Training 1/1 epoch (loss 1.5735):  92%|█████████▏| 1438/1563 [38:57<03:41,  1.78s/it]
Training 1/1 epoch (loss 1.6203):  92%|█████████▏| 1438/1563 [38:58<03:41,  1.78s/it]
Training 1/1 epoch (loss 1.6203):  92%|█████████▏| 1439/1563 [38:58<03:33,  1.72s/it]
Training 1/1 epoch (loss 1.5643):  92%|█████████▏| 1439/1563 [39:00<03:33,  1.72s/it]
Training 1/1 epoch (loss 1.5643):  92%|█████████▏| 1440/1563 [39:00<03:18,  1.61s/it]
Training 1/1 epoch (loss 1.5062):  92%|█████████▏| 1440/1563 [39:01<03:18,  1.61s/it]
Training 1/1 epoch (loss 1.5062):  92%|█████████▏| 1441/1563 [39:01<02:57,  1.45s/it]
Training 1/1 epoch (loss 1.3604):  92%|█████████▏| 1441/1563 [39:03<02:57,  1.45s/it]
Training 1/1 epoch (loss 1.3604):  92%|█████████▏| 1442/1563 [39:03<03:11,  1.58s/it]
Training 1/1 epoch (loss 1.5526):  92%|█████████▏| 1442/1563 [39:04<03:11,  1.58s/it]
Training 1/1 epoch (loss 1.5526):  92%|█████████▏| 1443/1563 [39:04<03:02,  1.52s/it]
Training 1/1 epoch (loss 1.5269):  92%|█████████▏| 1443/1563 [39:06<03:02,  1.52s/it]
Training 1/1 epoch (loss 1.5269):  92%|█████████▏| 1444/1563 [39:06<03:07,  1.58s/it]
Training 1/1 epoch (loss 1.4810):  92%|█████████▏| 1444/1563 [39:08<03:07,  1.58s/it]
Training 1/1 epoch (loss 1.4810):  92%|█████████▏| 1445/1563 [39:08<03:20,  1.70s/it]
Training 1/1 epoch (loss 1.5343):  92%|█████████▏| 1445/1563 [39:09<03:20,  1.70s/it]
Training 1/1 epoch (loss 1.5343):  93%|█████████▎| 1446/1563 [39:09<03:14,  1.66s/it]
Training 1/1 epoch (loss 1.6185):  93%|█████████▎| 1446/1563 [39:11<03:14,  1.66s/it]
Training 1/1 epoch (loss 1.6185):  93%|█████████▎| 1447/1563 [39:11<03:22,  1.75s/it]
Training 1/1 epoch (loss 1.6200):  93%|█████████▎| 1447/1563 [39:13<03:22,  1.75s/it]
Training 1/1 epoch (loss 1.6200):  93%|█████████▎| 1448/1563 [39:13<03:14,  1.69s/it]
Training 1/1 epoch (loss 1.7273):  93%|█████████▎| 1448/1563 [39:14<03:14,  1.69s/it]
Training 1/1 epoch (loss 1.7273):  93%|█████████▎| 1449/1563 [39:14<03:15,  1.71s/it]
Training 1/1 epoch (loss 1.5813):  93%|█████████▎| 1449/1563 [39:16<03:15,  1.71s/it]
Training 1/1 epoch (loss 1.5813):  93%|█████████▎| 1450/1563 [39:16<02:56,  1.56s/it]
Training 1/1 epoch (loss 1.4603):  93%|█████████▎| 1450/1563 [39:18<02:56,  1.56s/it]
Training 1/1 epoch (loss 1.4603):  93%|█████████▎| 1451/1563 [39:18<03:11,  1.71s/it]
Training 1/1 epoch (loss 1.5061):  93%|█████████▎| 1451/1563 [39:20<03:11,  1.71s/it]
Training 1/1 epoch (loss 1.5061):  93%|█████████▎| 1452/1563 [39:20<03:20,  1.81s/it]
Training 1/1 epoch (loss 1.5159):  93%|█████████▎| 1452/1563 [39:22<03:20,  1.81s/it]
Training 1/1 epoch (loss 1.5159):  93%|█████████▎| 1453/1563 [39:22<03:18,  1.80s/it]
Training 1/1 epoch (loss 1.5244):  93%|█████████▎| 1453/1563 [39:24<03:18,  1.80s/it]
Training 1/1 epoch (loss 1.5244):  93%|█████████▎| 1454/1563 [39:24<03:27,  1.90s/it]
Training 1/1 epoch (loss 1.4565):  93%|█████████▎| 1454/1563 [39:25<03:27,  1.90s/it]
Training 1/1 epoch (loss 1.4565):  93%|█████████▎| 1455/1563 [39:25<03:18,  1.84s/it]
Training 1/1 epoch (loss 1.5530):  93%|█████████▎| 1455/1563 [39:27<03:18,  1.84s/it]
Training 1/1 epoch (loss 1.5530):  93%|█████████▎| 1456/1563 [39:27<03:00,  1.68s/it]
Training 1/1 epoch (loss 1.5756):  93%|█████████▎| 1456/1563 [39:28<03:00,  1.68s/it]
Training 1/1 epoch (loss 1.5756):  93%|█████████▎| 1457/1563 [39:28<02:57,  1.67s/it]
Training 1/1 epoch (loss 1.6876):  93%|█████████▎| 1457/1563 [39:30<02:57,  1.67s/it]
Training 1/1 epoch (loss 1.6876):  93%|█████████▎| 1458/1563 [39:30<02:57,  1.69s/it]
Training 1/1 epoch (loss 1.5261):  93%|█████████▎| 1458/1563 [39:32<02:57,  1.69s/it]
Training 1/1 epoch (loss 1.5261):  93%|█████████▎| 1459/1563 [39:32<02:54,  1.68s/it]
Training 1/1 epoch (loss 1.5854):  93%|█████████▎| 1459/1563 [39:33<02:54,  1.68s/it]
Training 1/1 epoch (loss 1.5854):  93%|█████████▎| 1460/1563 [39:33<02:41,  1.57s/it]
Training 1/1 epoch (loss 1.5629):  93%|█████████▎| 1460/1563 [39:35<02:41,  1.57s/it]
Training 1/1 epoch (loss 1.5629):  93%|█████████▎| 1461/1563 [39:35<02:42,  1.59s/it]
Training 1/1 epoch (loss 1.5019):  93%|█████████▎| 1461/1563 [39:37<02:42,  1.59s/it]
Training 1/1 epoch (loss 1.5019):  94%|█████████▎| 1462/1563 [39:37<02:46,  1.65s/it]
Training 1/1 epoch (loss 1.5659):  94%|█████████▎| 1462/1563 [39:38<02:46,  1.65s/it]
Training 1/1 epoch (loss 1.5659):  94%|█████████▎| 1463/1563 [39:38<02:53,  1.74s/it]
Training 1/1 epoch (loss 1.5474):  94%|█████████▎| 1463/1563 [39:41<02:53,  1.74s/it]
Training 1/1 epoch (loss 1.5474):  94%|█████████▎| 1464/1563 [39:41<03:13,  1.96s/it]
Training 1/1 epoch (loss 1.5639):  94%|█████████▎| 1464/1563 [39:42<03:13,  1.96s/it]
Training 1/1 epoch (loss 1.5639):  94%|█████████▎| 1465/1563 [39:42<03:00,  1.84s/it]
Training 1/1 epoch (loss 1.6633):  94%|█████████▎| 1465/1563 [39:44<03:00,  1.84s/it]
Training 1/1 epoch (loss 1.6633):  94%|█████████▍| 1466/1563 [39:44<02:46,  1.72s/it]
Training 1/1 epoch (loss 1.6391):  94%|█████████▍| 1466/1563 [39:46<02:46,  1.72s/it]
Training 1/1 epoch (loss 1.6391):  94%|█████████▍| 1467/1563 [39:46<02:42,  1.70s/it]
Training 1/1 epoch (loss 1.4604):  94%|█████████▍| 1467/1563 [39:47<02:42,  1.70s/it]
Training 1/1 epoch (loss 1.4604):  94%|█████████▍| 1468/1563 [39:47<02:34,  1.62s/it]
Training 1/1 epoch (loss 1.5788):  94%|█████████▍| 1468/1563 [39:49<02:34,  1.62s/it]
Training 1/1 epoch (loss 1.5788):  94%|█████████▍| 1469/1563 [39:49<02:43,  1.74s/it]
Training 1/1 epoch (loss 1.6496):  94%|█████████▍| 1469/1563 [39:51<02:43,  1.74s/it]
Training 1/1 epoch (loss 1.6496):  94%|█████████▍| 1470/1563 [39:51<02:49,  1.83s/it]
Training 1/1 epoch (loss 1.6207):  94%|█████████▍| 1470/1563 [39:52<02:49,  1.83s/it]
Training 1/1 epoch (loss 1.6207):  94%|█████████▍| 1471/1563 [39:52<02:30,  1.64s/it]
Training 1/1 epoch (loss 1.5088):  94%|█████████▍| 1471/1563 [39:54<02:30,  1.64s/it]
Training 1/1 epoch (loss 1.5088):  94%|█████████▍| 1472/1563 [39:54<02:27,  1.62s/it]
Training 1/1 epoch (loss 1.5248):  94%|█████████▍| 1472/1563 [39:56<02:27,  1.62s/it]
Training 1/1 epoch (loss 1.5248):  94%|█████████▍| 1473/1563 [39:56<02:33,  1.71s/it]
Training 1/1 epoch (loss 1.5937):  94%|█████████▍| 1473/1563 [39:58<02:33,  1.71s/it]
Training 1/1 epoch (loss 1.5937):  94%|█████████▍| 1474/1563 [39:58<02:47,  1.88s/it]
Training 1/1 epoch (loss 1.5075):  94%|█████████▍| 1474/1563 [40:00<02:47,  1.88s/it]
Training 1/1 epoch (loss 1.5075):  94%|█████████▍| 1475/1563 [40:00<02:50,  1.94s/it]
Training 1/1 epoch (loss 1.5595):  94%|█████████▍| 1475/1563 [40:02<02:50,  1.94s/it]
Training 1/1 epoch (loss 1.5595):  94%|█████████▍| 1476/1563 [40:02<02:36,  1.80s/it]
Training 1/1 epoch (loss 1.4925):  94%|█████████▍| 1476/1563 [40:03<02:36,  1.80s/it]
Training 1/1 epoch (loss 1.4925):  94%|█████████▍| 1477/1563 [40:03<02:28,  1.72s/it]
Training 1/1 epoch (loss 1.4924):  94%|█████████▍| 1477/1563 [40:05<02:28,  1.72s/it]
Training 1/1 epoch (loss 1.4924):  95%|█████████▍| 1478/1563 [40:05<02:33,  1.81s/it]
Training 1/1 epoch (loss 1.4982):  95%|█████████▍| 1478/1563 [40:07<02:33,  1.81s/it]
Training 1/1 epoch (loss 1.4982):  95%|█████████▍| 1479/1563 [40:07<02:44,  1.96s/it]
Training 1/1 epoch (loss 1.5138):  95%|█████████▍| 1479/1563 [40:10<02:44,  1.96s/it]
Training 1/1 epoch (loss 1.5138):  95%|█████████▍| 1480/1563 [40:10<02:49,  2.04s/it]
Training 1/1 epoch (loss 1.6070):  95%|█████████▍| 1480/1563 [40:11<02:49,  2.04s/it]
Training 1/1 epoch (loss 1.6070):  95%|█████████▍| 1481/1563 [40:11<02:38,  1.94s/it]
Training 1/1 epoch (loss 1.4837):  95%|█████████▍| 1481/1563 [40:13<02:38,  1.94s/it]
Training 1/1 epoch (loss 1.4837):  95%|█████████▍| 1482/1563 [40:13<02:24,  1.78s/it]
Training 1/1 epoch (loss 1.5480):  95%|█████████▍| 1482/1563 [40:14<02:24,  1.78s/it]
Training 1/1 epoch (loss 1.5480):  95%|█████████▍| 1483/1563 [40:14<02:13,  1.66s/it]
Training 1/1 epoch (loss 1.5031):  95%|█████████▍| 1483/1563 [40:16<02:13,  1.66s/it]
Training 1/1 epoch (loss 1.5031):  95%|█████████▍| 1484/1563 [40:16<02:22,  1.81s/it]
Training 1/1 epoch (loss 1.5300):  95%|█████████▍| 1484/1563 [40:18<02:22,  1.81s/it]
Training 1/1 epoch (loss 1.5300):  95%|█████████▌| 1485/1563 [40:18<02:15,  1.73s/it]
Training 1/1 epoch (loss 1.4817):  95%|█████████▌| 1485/1563 [40:20<02:15,  1.73s/it]
Training 1/1 epoch (loss 1.4817):  95%|█████████▌| 1486/1563 [40:20<02:16,  1.78s/it]
Training 1/1 epoch (loss 1.6484):  95%|█████████▌| 1486/1563 [40:21<02:16,  1.78s/it]
Training 1/1 epoch (loss 1.6484):  95%|█████████▌| 1487/1563 [40:21<02:07,  1.67s/it]
Training 1/1 epoch (loss 1.4696):  95%|█████████▌| 1487/1563 [40:23<02:07,  1.67s/it]
Training 1/1 epoch (loss 1.4696):  95%|█████████▌| 1488/1563 [40:23<02:11,  1.75s/it]
Training 1/1 epoch (loss 1.4966):  95%|█████████▌| 1488/1563 [40:26<02:11,  1.75s/it]
Training 1/1 epoch (loss 1.4966):  95%|█████████▌| 1489/1563 [40:26<02:25,  1.96s/it]
Training 1/1 epoch (loss 1.6346):  95%|█████████▌| 1489/1563 [40:28<02:25,  1.96s/it]
Training 1/1 epoch (loss 1.6346):  95%|█████████▌| 1490/1563 [40:28<02:25,  2.00s/it]
Training 1/1 epoch (loss 1.4835):  95%|█████████▌| 1490/1563 [40:29<02:25,  2.00s/it]
Training 1/1 epoch (loss 1.4835):  95%|█████████▌| 1491/1563 [40:29<02:19,  1.94s/it]
Training 1/1 epoch (loss 1.4934):  95%|█████████▌| 1491/1563 [40:31<02:19,  1.94s/it]
Training 1/1 epoch (loss 1.4934):  95%|█████████▌| 1492/1563 [40:31<02:08,  1.81s/it]
Training 1/1 epoch (loss 1.5729):  95%|█████████▌| 1492/1563 [40:33<02:08,  1.81s/it]
Training 1/1 epoch (loss 1.5729):  96%|█████████▌| 1493/1563 [40:33<02:08,  1.83s/it]
Training 1/1 epoch (loss 1.5735):  96%|█████████▌| 1493/1563 [40:34<02:08,  1.83s/it]
Training 1/1 epoch (loss 1.5735):  96%|█████████▌| 1494/1563 [40:34<01:57,  1.70s/it]
Training 1/1 epoch (loss 1.4777):  96%|█████████▌| 1494/1563 [40:36<01:57,  1.70s/it]
Training 1/1 epoch (loss 1.4777):  96%|█████████▌| 1495/1563 [40:36<01:55,  1.70s/it]
Training 1/1 epoch (loss 1.5641):  96%|█████████▌| 1495/1563 [40:38<01:55,  1.70s/it]
Training 1/1 epoch (loss 1.5641):  96%|█████████▌| 1496/1563 [40:38<01:51,  1.66s/it]
Training 1/1 epoch (loss 1.4738):  96%|█████████▌| 1496/1563 [40:39<01:51,  1.66s/it]
Training 1/1 epoch (loss 1.4738):  96%|█████████▌| 1497/1563 [40:39<01:47,  1.63s/it]
Training 1/1 epoch (loss 1.5862):  96%|█████████▌| 1497/1563 [40:41<01:47,  1.63s/it]
Training 1/1 epoch (loss 1.5862):  96%|█████████▌| 1498/1563 [40:41<01:51,  1.72s/it]
Training 1/1 epoch (loss 1.5015):  96%|█████████▌| 1498/1563 [40:44<01:51,  1.72s/it]
Training 1/1 epoch (loss 1.5015):  96%|█████████▌| 1499/1563 [40:44<02:05,  1.96s/it]
Training 1/1 epoch (loss 1.3891):  96%|█████████▌| 1499/1563 [40:45<02:05,  1.96s/it]
Training 1/1 epoch (loss 1.3891):  96%|█████████▌| 1500/1563 [40:45<01:52,  1.79s/it]
Training 1/1 epoch (loss 1.5074):  96%|█████████▌| 1500/1563 [40:47<01:52,  1.79s/it]
Training 1/1 epoch (loss 1.5074):  96%|█████████▌| 1501/1563 [40:47<02:03,  2.00s/it]
Training 1/1 epoch (loss 1.6277):  96%|█████████▌| 1501/1563 [40:49<02:03,  2.00s/it]
Training 1/1 epoch (loss 1.6277):  96%|█████████▌| 1502/1563 [40:49<02:01,  1.99s/it]
Training 1/1 epoch (loss 1.5430):  96%|█████████▌| 1502/1563 [40:52<02:01,  1.99s/it]
Training 1/1 epoch (loss 1.5430):  96%|█████████▌| 1503/1563 [40:52<02:05,  2.10s/it]
Training 1/1 epoch (loss 1.5412):  96%|█████████▌| 1503/1563 [40:53<02:05,  2.10s/it]
Training 1/1 epoch (loss 1.5412):  96%|█████████▌| 1504/1563 [40:53<01:57,  2.00s/it]
Training 1/1 epoch (loss 1.4844):  96%|█████████▌| 1504/1563 [40:55<01:57,  2.00s/it]
Training 1/1 epoch (loss 1.4844):  96%|█████████▋| 1505/1563 [40:55<01:48,  1.88s/it]
Training 1/1 epoch (loss 1.5431):  96%|█████████▋| 1505/1563 [40:56<01:48,  1.88s/it]
Training 1/1 epoch (loss 1.5431):  96%|█████████▋| 1506/1563 [40:56<01:36,  1.70s/it]
Training 1/1 epoch (loss 1.5799):  96%|█████████▋| 1506/1563 [40:58<01:36,  1.70s/it]
Training 1/1 epoch (loss 1.5799):  96%|█████████▋| 1507/1563 [40:58<01:34,  1.69s/it]
Training 1/1 epoch (loss 1.4788):  96%|█████████▋| 1507/1563 [41:00<01:34,  1.69s/it]
Training 1/1 epoch (loss 1.4788):  96%|█████████▋| 1508/1563 [41:00<01:44,  1.90s/it]
Training 1/1 epoch (loss 1.5463):  96%|█████████▋| 1508/1563 [41:03<01:44,  1.90s/it]
Training 1/1 epoch (loss 1.5463):  97%|█████████▋| 1509/1563 [41:03<01:51,  2.07s/it]
Training 1/1 epoch (loss 1.5536):  97%|█████████▋| 1509/1563 [41:04<01:51,  2.07s/it]
Training 1/1 epoch (loss 1.5536):  97%|█████████▋| 1510/1563 [41:04<01:37,  1.83s/it]
Training 1/1 epoch (loss 1.5866):  97%|█████████▋| 1510/1563 [41:06<01:37,  1.83s/it]
Training 1/1 epoch (loss 1.5866):  97%|█████████▋| 1511/1563 [41:06<01:39,  1.92s/it]
Training 1/1 epoch (loss 1.5175):  97%|█████████▋| 1511/1563 [41:09<01:39,  1.92s/it]
Training 1/1 epoch (loss 1.5175):  97%|█████████▋| 1512/1563 [41:09<01:51,  2.18s/it]
Training 1/1 epoch (loss 1.5014):  97%|█████████▋| 1512/1563 [41:11<01:51,  2.18s/it]
Training 1/1 epoch (loss 1.5014):  97%|█████████▋| 1513/1563 [41:11<01:46,  2.13s/it]
Training 1/1 epoch (loss 1.5454):  97%|█████████▋| 1513/1563 [41:13<01:46,  2.13s/it]
Training 1/1 epoch (loss 1.5454):  97%|█████████▋| 1514/1563 [41:13<01:35,  1.96s/it]
Training 1/1 epoch (loss 1.5638):  97%|█████████▋| 1514/1563 [41:15<01:35,  1.96s/it]
Training 1/1 epoch (loss 1.5638):  97%|█████████▋| 1515/1563 [41:15<01:35,  2.00s/it]
Training 1/1 epoch (loss 1.4972):  97%|█████████▋| 1515/1563 [41:17<01:35,  2.00s/it]
Training 1/1 epoch (loss 1.4972):  97%|█████████▋| 1516/1563 [41:17<01:32,  1.98s/it]
Training 1/1 epoch (loss 1.5307):  97%|█████████▋| 1516/1563 [41:19<01:32,  1.98s/it]
Training 1/1 epoch (loss 1.5307):  97%|█████████▋| 1517/1563 [41:19<01:30,  1.97s/it]
Training 1/1 epoch (loss 1.4196):  97%|█████████▋| 1517/1563 [41:20<01:30,  1.97s/it]
Training 1/1 epoch (loss 1.4196):  97%|█████████▋| 1518/1563 [41:20<01:23,  1.86s/it]
Training 1/1 epoch (loss 1.5340):  97%|█████████▋| 1518/1563 [41:22<01:23,  1.86s/it]
Training 1/1 epoch (loss 1.5340):  97%|█████████▋| 1519/1563 [41:22<01:16,  1.75s/it]
Training 1/1 epoch (loss 1.4240):  97%|█████████▋| 1519/1563 [41:24<01:16,  1.75s/it]
Training 1/1 epoch (loss 1.4240):  97%|█████████▋| 1520/1563 [41:24<01:21,  1.88s/it]
Training 1/1 epoch (loss 1.4708):  97%|█████████▋| 1520/1563 [41:25<01:21,  1.88s/it]
Training 1/1 epoch (loss 1.4708):  97%|█████████▋| 1521/1563 [41:25<01:13,  1.74s/it]
Training 1/1 epoch (loss 1.5975):  97%|█████████▋| 1521/1563 [41:27<01:13,  1.74s/it]
Training 1/1 epoch (loss 1.5975):  97%|█████████▋| 1522/1563 [41:27<01:08,  1.68s/it]
Training 1/1 epoch (loss 1.5884):  97%|█████████▋| 1522/1563 [41:28<01:08,  1.68s/it]
Training 1/1 epoch (loss 1.5884):  97%|█████████▋| 1523/1563 [41:28<01:04,  1.61s/it]
Training 1/1 epoch (loss 1.5947):  97%|█████████▋| 1523/1563 [41:30<01:04,  1.61s/it]
Training 1/1 epoch (loss 1.5947):  98%|█████████▊| 1524/1563 [41:30<01:06,  1.71s/it]
Training 1/1 epoch (loss 1.6047):  98%|█████████▊| 1524/1563 [41:32<01:06,  1.71s/it]
Training 1/1 epoch (loss 1.6047):  98%|█████████▊| 1525/1563 [41:32<01:00,  1.59s/it]
Training 1/1 epoch (loss 1.4569):  98%|█████████▊| 1525/1563 [41:33<01:00,  1.59s/it]
Training 1/1 epoch (loss 1.4569):  98%|█████████▊| 1526/1563 [41:33<00:55,  1.50s/it]
Training 1/1 epoch (loss 1.4617):  98%|█████████▊| 1526/1563 [41:35<00:55,  1.50s/it]
Training 1/1 epoch (loss 1.4617):  98%|█████████▊| 1527/1563 [41:35<00:56,  1.57s/it]
Training 1/1 epoch (loss 1.5920):  98%|█████████▊| 1527/1563 [41:37<00:56,  1.57s/it]
Training 1/1 epoch (loss 1.5920):  98%|█████████▊| 1528/1563 [41:37<01:02,  1.78s/it]
Training 1/1 epoch (loss 1.5137):  98%|█████████▊| 1528/1563 [41:38<01:02,  1.78s/it]
Training 1/1 epoch (loss 1.5137):  98%|█████████▊| 1529/1563 [41:38<00:57,  1.70s/it]
Training 1/1 epoch (loss 1.6578):  98%|█████████▊| 1529/1563 [41:40<00:57,  1.70s/it]
Training 1/1 epoch (loss 1.6578):  98%|█████████▊| 1530/1563 [41:40<00:57,  1.73s/it]
Training 1/1 epoch (loss 1.5274):  98%|█████████▊| 1530/1563 [41:42<00:57,  1.73s/it]
Training 1/1 epoch (loss 1.5274):  98%|█████████▊| 1531/1563 [41:42<00:58,  1.82s/it]
Training 1/1 epoch (loss 1.6535):  98%|█████████▊| 1531/1563 [41:44<00:58,  1.82s/it]
Training 1/1 epoch (loss 1.6535):  98%|█████████▊| 1532/1563 [41:44<00:52,  1.70s/it]
Training 1/1 epoch (loss 1.5437):  98%|█████████▊| 1532/1563 [41:46<00:52,  1.70s/it]
Training 1/1 epoch (loss 1.5437):  98%|█████████▊| 1533/1563 [41:46<00:53,  1.79s/it]
Training 1/1 epoch (loss 1.5714):  98%|█████████▊| 1533/1563 [41:47<00:53,  1.79s/it]
Training 1/1 epoch (loss 1.5714):  98%|█████████▊| 1534/1563 [41:47<00:51,  1.78s/it]
Training 1/1 epoch (loss 1.4978):  98%|█████████▊| 1534/1563 [41:49<00:51,  1.78s/it]
Training 1/1 epoch (loss 1.4978):  98%|█████████▊| 1535/1563 [41:49<00:49,  1.76s/it]
Training 1/1 epoch (loss 1.6911):  98%|█████████▊| 1535/1563 [41:51<00:49,  1.76s/it]
Training 1/1 epoch (loss 1.6911):  98%|█████████▊| 1536/1563 [41:51<00:45,  1.69s/it]
Training 1/1 epoch (loss 1.5552):  98%|█████████▊| 1536/1563 [41:52<00:45,  1.69s/it]
Training 1/1 epoch (loss 1.5552):  98%|█████████▊| 1537/1563 [41:52<00:40,  1.56s/it]
Training 1/1 epoch (loss 1.5253):  98%|█████████▊| 1537/1563 [41:53<00:40,  1.56s/it]
Training 1/1 epoch (loss 1.5253):  98%|█████████▊| 1538/1563 [41:53<00:37,  1.51s/it]
Training 1/1 epoch (loss 1.5827):  98%|█████████▊| 1538/1563 [41:55<00:37,  1.51s/it]
Training 1/1 epoch (loss 1.5827):  98%|█████████▊| 1539/1563 [41:55<00:36,  1.53s/it]
Training 1/1 epoch (loss 1.5289):  98%|█████████▊| 1539/1563 [41:56<00:36,  1.53s/it]
Training 1/1 epoch (loss 1.5289):  99%|█████████▊| 1540/1563 [41:56<00:35,  1.55s/it]
Training 1/1 epoch (loss 1.5936):  99%|█████████▊| 1540/1563 [41:58<00:35,  1.55s/it]
Training 1/1 epoch (loss 1.5936):  99%|█████████▊| 1541/1563 [41:58<00:36,  1.66s/it]
Training 1/1 epoch (loss 1.5494):  99%|█████████▊| 1541/1563 [42:00<00:36,  1.66s/it]
Training 1/1 epoch (loss 1.5494):  99%|█████████▊| 1542/1563 [42:00<00:32,  1.52s/it]
Training 1/1 epoch (loss 1.6090):  99%|█████████▊| 1542/1563 [42:02<00:32,  1.52s/it]
Training 1/1 epoch (loss 1.6090):  99%|█████████▊| 1543/1563 [42:02<00:36,  1.81s/it]
Training 1/1 epoch (loss 1.5101):  99%|█████████▊| 1543/1563 [42:04<00:36,  1.81s/it]
Training 1/1 epoch (loss 1.5101):  99%|█████████▉| 1544/1563 [42:04<00:33,  1.77s/it]
Training 1/1 epoch (loss 1.4341):  99%|█████████▉| 1544/1563 [42:06<00:33,  1.77s/it]
Training 1/1 epoch (loss 1.4341):  99%|█████████▉| 1545/1563 [42:06<00:32,  1.83s/it]
Training 1/1 epoch (loss 1.5332):  99%|█████████▉| 1545/1563 [42:07<00:32,  1.83s/it]
Training 1/1 epoch (loss 1.5332):  99%|█████████▉| 1546/1563 [42:07<00:30,  1.79s/it]
Training 1/1 epoch (loss 1.5551):  99%|█████████▉| 1546/1563 [42:10<00:30,  1.79s/it]
Training 1/1 epoch (loss 1.5551):  99%|█████████▉| 1547/1563 [42:10<00:30,  1.90s/it]
Training 1/1 epoch (loss 1.4410):  99%|█████████▉| 1547/1563 [42:11<00:30,  1.90s/it]
Training 1/1 epoch (loss 1.4410):  99%|█████████▉| 1548/1563 [42:11<00:28,  1.87s/it]
Training 1/1 epoch (loss 1.5564):  99%|█████████▉| 1548/1563 [42:13<00:28,  1.87s/it]
Training 1/1 epoch (loss 1.5564):  99%|█████████▉| 1549/1563 [42:13<00:26,  1.86s/it]
Training 1/1 epoch (loss 1.6096):  99%|█████████▉| 1549/1563 [42:15<00:26,  1.86s/it]
Training 1/1 epoch (loss 1.6096):  99%|█████████▉| 1550/1563 [42:15<00:23,  1.81s/it]
Training 1/1 epoch (loss 1.5366):  99%|█████████▉| 1550/1563 [42:16<00:23,  1.81s/it]
Training 1/1 epoch (loss 1.5366):  99%|█████████▉| 1551/1563 [42:16<00:19,  1.66s/it]
Training 1/1 epoch (loss 1.5916):  99%|█████████▉| 1551/1563 [42:18<00:19,  1.66s/it]
Training 1/1 epoch (loss 1.5916):  99%|█████████▉| 1552/1563 [42:18<00:19,  1.77s/it]
Training 1/1 epoch (loss 1.6632):  99%|█████████▉| 1552/1563 [42:20<00:19,  1.77s/it]
Training 1/1 epoch (loss 1.6632):  99%|█████████▉| 1553/1563 [42:20<00:16,  1.64s/it]
Training 1/1 epoch (loss 1.5903):  99%|█████████▉| 1553/1563 [42:21<00:16,  1.64s/it]
Training 1/1 epoch (loss 1.5903):  99%|█████████▉| 1554/1563 [42:21<00:14,  1.59s/it]
Training 1/1 epoch (loss 1.5654):  99%|█████████▉| 1554/1563 [42:23<00:14,  1.59s/it]
Training 1/1 epoch (loss 1.5654):  99%|█████████▉| 1555/1563 [42:23<00:13,  1.65s/it]
Training 1/1 epoch (loss 1.6286):  99%|█████████▉| 1555/1563 [42:25<00:13,  1.65s/it]
Training 1/1 epoch (loss 1.6286): 100%|█████████▉| 1556/1563 [42:25<00:12,  1.81s/it]
Training 1/1 epoch (loss 1.5978): 100%|█████████▉| 1556/1563 [42:26<00:12,  1.81s/it]
Training 1/1 epoch (loss 1.5978): 100%|█████████▉| 1557/1563 [42:26<00:10,  1.69s/it]
Training 1/1 epoch (loss 1.5106): 100%|█████████▉| 1557/1563 [42:28<00:10,  1.69s/it]
Training 1/1 epoch (loss 1.5106): 100%|█████████▉| 1558/1563 [42:28<00:08,  1.77s/it]
Training 1/1 epoch (loss 1.3888): 100%|█████████▉| 1558/1563 [42:30<00:08,  1.77s/it]
Training 1/1 epoch (loss 1.3888): 100%|█████████▉| 1559/1563 [42:30<00:06,  1.64s/it]
Training 1/1 epoch (loss 1.5644): 100%|█████████▉| 1559/1563 [42:31<00:06,  1.64s/it]
Training 1/1 epoch (loss 1.5644): 100%|█████████▉| 1560/1563 [42:31<00:04,  1.48s/it]
Training 1/1 epoch (loss 1.4964): 100%|█████████▉| 1560/1563 [42:32<00:04,  1.48s/it]
Training 1/1 epoch (loss 1.4964): 100%|█████████▉| 1561/1563 [42:32<00:02,  1.46s/it]
Training 1/1 epoch (loss 1.5924): 100%|█████████▉| 1561/1563 [42:34<00:02,  1.46s/it]
Training 1/1 epoch (loss 1.5924): 100%|█████████▉| 1562/1563 [42:34<00:01,  1.52s/it]
Training 1/1 epoch (loss 1.6350): 100%|█████████▉| 1562/1563 [42:36<00:01,  1.52s/it]
Training 1/1 epoch (loss 1.6350): 100%|██████████| 1563/1563 [42:36<00:00,  1.55s/it]
Training 1/1 epoch (loss 1.6350): 100%|██████████| 1563/1563 [42:36<00:00,  1.64s/it]
tokenizer config file saved in /aifs4su/hansirui_1st/boyuan/resist/setting3-safety/tinyllama-1T/tinyllama-1T-s3-Q1-50k/tokenizer_config.json
Special tokens file saved in /aifs4su/hansirui_1st/boyuan/resist/setting3-safety/tinyllama-1T/tinyllama-1T-s3-Q1-50k/special_tokens_map.json
wandb: ERROR Problem finishing run
Exception ignored in atexit callback: <bound method rank_zero_only.<locals>.wrapper of <safe_rlhf.logger.Logger object at 0x15511874a6d0>>
Traceback (most recent call last):
  File "/home/hansirui_1st/jiayi/resist/setting3/safe_rlhf/utils.py", line 212, in wrapper
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/home/hansirui_1st/jiayi/resist/setting3/safe_rlhf/logger.py", line 183, in close
    self.wandb.finish()
  File "/aifs4su/hansirui_1st/miniconda3/envs/by-align/lib/python3.11/site-packages/wandb/sdk/wandb_run.py", line 449, in wrapper
    return func(self, *args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/aifs4su/hansirui_1st/miniconda3/envs/by-align/lib/python3.11/site-packages/wandb/sdk/wandb_run.py", line 391, in wrapper
    return func(self, *args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/aifs4su/hansirui_1st/miniconda3/envs/by-align/lib/python3.11/site-packages/wandb/sdk/wandb_run.py", line 2106, in finish
    return self._finish(exit_code)
           ^^^^^^^^^^^^^^^^^^^^^^^
  File "/aifs4su/hansirui_1st/miniconda3/envs/by-align/lib/python3.11/site-packages/wandb/sdk/wandb_run.py", line 2127, in _finish
    self._atexit_cleanup(exit_code=exit_code)
  File "/aifs4su/hansirui_1st/miniconda3/envs/by-align/lib/python3.11/site-packages/wandb/sdk/wandb_run.py", line 2352, in _atexit_cleanup
    self._on_finish()
  File "/aifs4su/hansirui_1st/miniconda3/envs/by-align/lib/python3.11/site-packages/wandb/sdk/wandb_run.py", line 2609, in _on_finish
    wait_with_progress(
  File "/aifs4su/hansirui_1st/miniconda3/envs/by-align/lib/python3.11/site-packages/wandb/sdk/mailbox/wait_with_progress.py", line 24, in wait_with_progress
    return wait_all_with_progress(
           ^^^^^^^^^^^^^^^^^^^^^^^
  File "/aifs4su/hansirui_1st/miniconda3/envs/by-align/lib/python3.11/site-packages/wandb/sdk/mailbox/wait_with_progress.py", line 87, in wait_all_with_progress
    return asyncio_compat.run(progress_loop_with_timeout)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/aifs4su/hansirui_1st/miniconda3/envs/by-align/lib/python3.11/site-packages/wandb/sdk/lib/asyncio_compat.py", line 27, in run
    future = executor.submit(runner.run, fn)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/aifs4su/hansirui_1st/miniconda3/envs/by-align/lib/python3.11/concurrent/futures/thread.py", line 169, in submit
    raise RuntimeError('cannot schedule new futures after '
RuntimeError: cannot schedule new futures after interpreter shutdown