stderr.log

+ deepspeed --master_port 25931 --module safe_rlhf.finetune --train_datasets inverse-json::/home/hansirui_1st/jiayi/resist/imdb_data/train/pos/10000/train.json --model_name_or_path /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-1431k-3T --max_length 512 --trust_remote_code True --epochs 1 --per_device_train_batch_size 1 --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/jiayi/setting3-imdb/tinyllama-3T/tinyllama-3T-s3-Q1-10000 --log_type wandb --log_run_name imdb-tinyllama-3T-s3-Q1-10000 --log_project Inverse_Alignment_IMDb --zero_stage 3 --offload none --bf16 True --tf32 True --save_16bit
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used
[rank4]:[W527 20:22:59.642662794 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.
[rank1]:[W527 20:23:00.660061403 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.
[rank0]:[W527 20:23:00.681287585 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.
[rank6]:[W527 20:23:00.682936166 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.
[rank5]:[W527 20:23:00.686569890 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.
[rank7]:[W527 20:23:00.691523446 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.
[rank3]:[W527 20:23:00.701841157 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]:[W527 20:23:00.712500378 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.
loading configuration file /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-1431k-3T/config.json
loading configuration file /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-1431k-3T/config.json
loading configuration file /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-1431k-3T/config.json
loading configuration file /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-1431k-3T/config.json
loading configuration file /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-1431k-3T/config.json
loading configuration file /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-1431k-3T/config.json
loading configuration file /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-1431k-3T/config.json
loading configuration file /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-1431k-3T/config.json
Model config LlamaConfig {
  "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": "4.52.1",
  "use_cache": true,
  "vocab_size": 32000
}

Model config LlamaConfig {
  "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": "4.52.1",
  "use_cache": true,
  "vocab_size": 32000
}

Model config LlamaConfig {
  "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": "4.52.1",
  "use_cache": true,
  "vocab_size": 32000
}

Model config LlamaConfig {
  "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": "4.52.1",
  "use_cache": true,
  "vocab_size": 32000
}

Model config LlamaConfig {
  "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": "4.52.1",
  "use_cache": true,
  "vocab_size": 32000
}

Model config LlamaConfig {
  "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": "4.52.1",
  "use_cache": true,
  "vocab_size": 32000
}

Model config LlamaConfig {
  "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": "4.52.1",
  "use_cache": true,
  "vocab_size": 32000
}

Model config LlamaConfig {
  "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": "4.52.1",
  "use_cache": true,
  "vocab_size": 32000
}

loading weights file /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-1431k-3T/model.safetensors
loading weights file /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-1431k-3T/model.safetensors
loading weights file /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-1431k-3T/model.safetensors
loading weights file /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-1431k-3T/model.safetensors
loading weights file /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-1431k-3T/model.safetensors
loading weights file /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-1431k-3T/model.safetensors
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
Will use torch_dtype=torch.float32 as defined in model's config object
Instantiating LlamaForCausalLM model under default dtype torch.float32.
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
Will use torch_dtype=torch.float32 as defined in model's config object
Instantiating LlamaForCausalLM model under default dtype torch.float32.
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.
loading weights file /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-1431k-3T/model.safetensors
Detected DeepSpeed ZeRO-3: activating zero.init() for this model
loading weights file /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-1431k-3T/model.safetensors
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
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-1431k-3T.
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-1431k-3T.
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-1431k-3T.
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-1431k-3T/generation_config.json
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-1431k-3T.
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-1431k-3T/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-1431k-3T/generation_config.json
All model checkpoint weights were used when initializing LlamaForCausalLM.

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

All the weights of LlamaForCausalLM were initialized from the model checkpoint at /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-1431k-3T.
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-1431k-3T.
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-1431k-3T.
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-1431k-3T/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-1431k-3T/generation_config.json
loading configuration file /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-1431k-3T/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
}

loading configuration file /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-1431k-3T/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.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 tokenizer.json
loading file added_tokens.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
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-1431k-3T.
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-1431k-3T/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/jy-resist/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...
`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 0.19.11
wandb: Run data is saved locally in /aifs4su/hansirui_1st/jiayi/setting3-imdb/tinyllama-3T/tinyllama-3T-s3-Q1-10000/wandb/run-20250527_202314-j30d8uyq
wandb: Run `wandb offline` to turn off syncing.
wandb: Syncing run imdb-tinyllama-3T-s3-Q1-10000
wandb: ⭐️ View project at https://wandb.ai/xtom/Inverse_Alignment_IMDb
wandb: 🚀 View run at https://wandb.ai/xtom/Inverse_Alignment_IMDb/runs/j30d8uyq

Training 1/1 epoch:   0%|          | 0/1250 [00:00<?, ?it/s]`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`.

Training 1/1 epoch (loss 2.6895):   0%|          | 0/1250 [00:08<?, ?it/s]
Training 1/1 epoch (loss 2.6895):   0%|          | 1/1250 [00:08<2:56:03,  8.46s/it]
Training 1/1 epoch (loss 2.7344):   0%|          | 1/1250 [00:10<2:56:03,  8.46s/it]
Training 1/1 epoch (loss 2.7344):   0%|          | 2/1250 [00:10<1:39:30,  4.78s/it]
Training 1/1 epoch (loss 2.6357):   0%|          | 2/1250 [00:12<1:39:30,  4.78s/it]
Training 1/1 epoch (loss 2.6357):   0%|          | 3/1250 [00:12<1:11:50,  3.46s/it]
Training 1/1 epoch (loss 2.9972):   0%|          | 3/1250 [00:13<1:11:50,  3.46s/it]
Training 1/1 epoch (loss 2.9972):   0%|          | 4/1250 [00:13<54:33,  2.63s/it]  
Training 1/1 epoch (loss 2.7498):   0%|          | 4/1250 [00:14<54:33,  2.63s/it]
Training 1/1 epoch (loss 2.7498):   0%|          | 5/1250 [00:14<42:12,  2.03s/it]
Training 1/1 epoch (loss 2.9447):   0%|          | 5/1250 [00:16<42:12,  2.03s/it]
Training 1/1 epoch (loss 2.9447):   0%|          | 6/1250 [00:16<41:11,  1.99s/it]
Training 1/1 epoch (loss 2.7219):   0%|          | 6/1250 [00:18<41:11,  1.99s/it]
Training 1/1 epoch (loss 2.7219):   1%|          | 7/1250 [00:18<37:49,  1.83s/it]
Training 1/1 epoch (loss 2.6385):   1%|          | 7/1250 [00:18<37:49,  1.83s/it]
Training 1/1 epoch (loss 2.6385):   1%|          | 8/1250 [00:18<30:25,  1.47s/it]
Training 1/1 epoch (loss 2.7001):   1%|          | 8/1250 [00:21<30:25,  1.47s/it]
Training 1/1 epoch (loss 2.7001):   1%|          | 9/1250 [00:21<36:40,  1.77s/it]
Training 1/1 epoch (loss 2.4852):   1%|          | 9/1250 [00:22<36:40,  1.77s/it]
Training 1/1 epoch (loss 2.4852):   1%|          | 10/1250 [00:22<31:07,  1.51s/it]
Training 1/1 epoch (loss 2.7661):   1%|          | 10/1250 [00:23<31:07,  1.51s/it]
Training 1/1 epoch (loss 2.7661):   1%|          | 11/1250 [00:23<28:09,  1.36s/it]
Training 1/1 epoch (loss 2.7108):   1%|          | 11/1250 [00:24<28:09,  1.36s/it]
Training 1/1 epoch (loss 2.7108):   1%|          | 12/1250 [00:24<28:51,  1.40s/it]
Training 1/1 epoch (loss 2.6189):   1%|          | 12/1250 [00:25<28:51,  1.40s/it]
Training 1/1 epoch (loss 2.6189):   1%|          | 13/1250 [00:25<26:25,  1.28s/it]
Training 1/1 epoch (loss 2.4735):   1%|          | 13/1250 [00:27<26:25,  1.28s/it]
Training 1/1 epoch (loss 2.4735):   1%|          | 14/1250 [00:27<27:29,  1.33s/it]
Training 1/1 epoch (loss 2.7584):   1%|          | 14/1250 [00:29<27:29,  1.33s/it]
Training 1/1 epoch (loss 2.7584):   1%|          | 15/1250 [00:29<30:27,  1.48s/it]
Training 1/1 epoch (loss 2.6672):   1%|          | 15/1250 [00:29<30:27,  1.48s/it]
Training 1/1 epoch (loss 2.6672):   1%|▏         | 16/1250 [00:29<25:37,  1.25s/it]
Training 1/1 epoch (loss 2.7078):   1%|▏         | 16/1250 [00:30<25:37,  1.25s/it]
Training 1/1 epoch (loss 2.7078):   1%|▏         | 17/1250 [00:30<23:16,  1.13s/it]
Training 1/1 epoch (loss 2.7807):   1%|▏         | 17/1250 [00:32<23:16,  1.13s/it]
Training 1/1 epoch (loss 2.7807):   1%|▏         | 18/1250 [00:32<26:22,  1.28s/it]
Training 1/1 epoch (loss 2.7497):   1%|▏         | 18/1250 [00:32<26:22,  1.28s/it]
Training 1/1 epoch (loss 2.7497):   2%|▏         | 19/1250 [00:32<22:18,  1.09s/it]
Training 1/1 epoch (loss 2.7083):   2%|▏         | 19/1250 [00:34<22:18,  1.09s/it]
Training 1/1 epoch (loss 2.7083):   2%|▏         | 20/1250 [00:34<27:02,  1.32s/it]
Training 1/1 epoch (loss 2.6306):   2%|▏         | 20/1250 [00:35<27:02,  1.32s/it]
Training 1/1 epoch (loss 2.6306):   2%|▏         | 21/1250 [00:35<25:33,  1.25s/it]
Training 1/1 epoch (loss 2.8995):   2%|▏         | 21/1250 [00:36<25:33,  1.25s/it]
Training 1/1 epoch (loss 2.8995):   2%|▏         | 22/1250 [00:36<22:33,  1.10s/it]
Training 1/1 epoch (loss 2.7049):   2%|▏         | 22/1250 [00:37<22:33,  1.10s/it]
Training 1/1 epoch (loss 2.7049):   2%|▏         | 23/1250 [00:37<22:54,  1.12s/it]
Training 1/1 epoch (loss 2.4003):   2%|▏         | 23/1250 [00:39<22:54,  1.12s/it]
Training 1/1 epoch (loss 2.4003):   2%|▏         | 24/1250 [00:39<27:25,  1.34s/it]
Training 1/1 epoch (loss 2.5756):   2%|▏         | 24/1250 [00:40<27:25,  1.34s/it]
Training 1/1 epoch (loss 2.5756):   2%|▏         | 25/1250 [00:40<23:53,  1.17s/it]
Training 1/1 epoch (loss 2.5142):   2%|▏         | 25/1250 [00:41<23:53,  1.17s/it]
Training 1/1 epoch (loss 2.5142):   2%|▏         | 26/1250 [00:41<25:27,  1.25s/it]
Training 1/1 epoch (loss 2.7769):   2%|▏         | 26/1250 [00:43<25:27,  1.25s/it]
Training 1/1 epoch (loss 2.7769):   2%|▏         | 27/1250 [00:43<28:32,  1.40s/it]
Training 1/1 epoch (loss 2.6898):   2%|▏         | 27/1250 [00:44<28:32,  1.40s/it]
Training 1/1 epoch (loss 2.6898):   2%|▏         | 28/1250 [00:44<27:37,  1.36s/it]
Training 1/1 epoch (loss 2.7262):   2%|▏         | 28/1250 [00:46<27:37,  1.36s/it]
Training 1/1 epoch (loss 2.7262):   2%|▏         | 29/1250 [00:46<30:02,  1.48s/it]
Training 1/1 epoch (loss 2.7273):   2%|▏         | 29/1250 [00:47<30:02,  1.48s/it]
Training 1/1 epoch (loss 2.7273):   2%|▏         | 30/1250 [00:47<26:47,  1.32s/it]
Training 1/1 epoch (loss 2.8782):   2%|▏         | 30/1250 [00:48<26:47,  1.32s/it]
Training 1/1 epoch (loss 2.8782):   2%|▏         | 31/1250 [00:48<25:31,  1.26s/it]
Training 1/1 epoch (loss 2.7278):   2%|▏         | 31/1250 [00:50<25:31,  1.26s/it]
Training 1/1 epoch (loss 2.7278):   3%|▎         | 32/1250 [00:50<30:05,  1.48s/it]
Training 1/1 epoch (loss 2.7458):   3%|▎         | 32/1250 [00:52<30:05,  1.48s/it]
Training 1/1 epoch (loss 2.7458):   3%|▎         | 33/1250 [00:52<28:45,  1.42s/it]
Training 1/1 epoch (loss 2.5771):   3%|▎         | 33/1250 [00:54<28:45,  1.42s/it]
Training 1/1 epoch (loss 2.5771):   3%|▎         | 34/1250 [00:54<33:50,  1.67s/it]
Training 1/1 epoch (loss 2.6981):   3%|▎         | 34/1250 [00:56<33:50,  1.67s/it]
Training 1/1 epoch (loss 2.6981):   3%|▎         | 35/1250 [00:56<38:57,  1.92s/it]
Training 1/1 epoch (loss 2.6769):   3%|▎         | 35/1250 [00:57<38:57,  1.92s/it]
Training 1/1 epoch (loss 2.6769):   3%|▎         | 36/1250 [00:57<29:58,  1.48s/it]
Training 1/1 epoch (loss 2.5012):   3%|▎         | 36/1250 [00:59<29:58,  1.48s/it]
Training 1/1 epoch (loss 2.5012):   3%|▎         | 37/1250 [00:59<32:40,  1.62s/it]
Training 1/1 epoch (loss 2.4744):   3%|▎         | 37/1250 [01:00<32:40,  1.62s/it]
Training 1/1 epoch (loss 2.4744):   3%|▎         | 38/1250 [01:00<33:00,  1.63s/it]
Training 1/1 epoch (loss 2.8530):   3%|▎         | 38/1250 [01:01<33:00,  1.63s/it]
Training 1/1 epoch (loss 2.8530):   3%|▎         | 39/1250 [01:01<26:29,  1.31s/it]
Training 1/1 epoch (loss 2.5973):   3%|▎         | 39/1250 [01:04<26:29,  1.31s/it]
Training 1/1 epoch (loss 2.5973):   3%|▎         | 40/1250 [01:04<34:33,  1.71s/it]
Training 1/1 epoch (loss 2.6672):   3%|▎         | 40/1250 [01:06<34:33,  1.71s/it]
Training 1/1 epoch (loss 2.6672):   3%|▎         | 41/1250 [01:06<39:08,  1.94s/it]
Training 1/1 epoch (loss 2.5157):   3%|▎         | 41/1250 [01:06<39:08,  1.94s/it]
Training 1/1 epoch (loss 2.5157):   3%|▎         | 42/1250 [01:06<29:54,  1.49s/it]
Training 1/1 epoch (loss 2.6115):   3%|▎         | 42/1250 [01:08<29:54,  1.49s/it]
Training 1/1 epoch (loss 2.6115):   3%|▎         | 43/1250 [01:08<30:22,  1.51s/it]
Training 1/1 epoch (loss 2.6442):   3%|▎         | 43/1250 [01:10<30:22,  1.51s/it]
Training 1/1 epoch (loss 2.6442):   4%|▎         | 44/1250 [01:10<35:52,  1.78s/it]
Training 1/1 epoch (loss 2.6178):   4%|▎         | 44/1250 [01:11<35:52,  1.78s/it]
Training 1/1 epoch (loss 2.6178):   4%|▎         | 45/1250 [01:11<27:52,  1.39s/it]
Training 1/1 epoch (loss 2.4632):   4%|▎         | 45/1250 [01:13<27:52,  1.39s/it]
Training 1/1 epoch (loss 2.4632):   4%|▎         | 46/1250 [01:13<32:05,  1.60s/it]
Training 1/1 epoch (loss 2.6651):   4%|▎         | 46/1250 [01:15<32:05,  1.60s/it]
Training 1/1 epoch (loss 2.6651):   4%|▍         | 47/1250 [01:15<35:32,  1.77s/it]
Training 1/1 epoch (loss 2.7233):   4%|▍         | 47/1250 [01:16<35:32,  1.77s/it]
Training 1/1 epoch (loss 2.7233):   4%|▍         | 48/1250 [01:16<28:05,  1.40s/it]
Training 1/1 epoch (loss 2.5598):   4%|▍         | 48/1250 [01:18<28:05,  1.40s/it]
Training 1/1 epoch (loss 2.5598):   4%|▍         | 49/1250 [01:18<30:43,  1.54s/it]
Training 1/1 epoch (loss 2.6908):   4%|▍         | 49/1250 [01:19<30:43,  1.54s/it]
Training 1/1 epoch (loss 2.6908):   4%|▍         | 50/1250 [01:19<31:22,  1.57s/it]
Training 1/1 epoch (loss 2.6063):   4%|▍         | 50/1250 [01:20<31:22,  1.57s/it]
Training 1/1 epoch (loss 2.6063):   4%|▍         | 51/1250 [01:20<24:43,  1.24s/it]
Training 1/1 epoch (loss 2.6327):   4%|▍         | 51/1250 [01:22<24:43,  1.24s/it]
Training 1/1 epoch (loss 2.6327):   4%|▍         | 52/1250 [01:22<32:22,  1.62s/it]
Training 1/1 epoch (loss 2.6822):   4%|▍         | 52/1250 [01:23<32:22,  1.62s/it]
Training 1/1 epoch (loss 2.6822):   4%|▍         | 53/1250 [01:23<29:05,  1.46s/it]
Training 1/1 epoch (loss 2.4893):   4%|▍         | 53/1250 [01:24<29:05,  1.46s/it]
Training 1/1 epoch (loss 2.4893):   4%|▍         | 54/1250 [01:24<23:39,  1.19s/it]
Training 1/1 epoch (loss 2.5229):   4%|▍         | 54/1250 [01:26<23:39,  1.19s/it]
Training 1/1 epoch (loss 2.5229):   4%|▍         | 55/1250 [01:26<28:09,  1.41s/it]
Training 1/1 epoch (loss 2.5454):   4%|▍         | 55/1250 [01:28<28:09,  1.41s/it]
Training 1/1 epoch (loss 2.5454):   4%|▍         | 56/1250 [01:28<32:29,  1.63s/it]
Training 1/1 epoch (loss 2.5369):   4%|▍         | 56/1250 [01:29<32:29,  1.63s/it]
Training 1/1 epoch (loss 2.5369):   5%|▍         | 57/1250 [01:29<28:53,  1.45s/it]
Training 1/1 epoch (loss 2.3972):   5%|▍         | 57/1250 [01:31<28:53,  1.45s/it]
Training 1/1 epoch (loss 2.3972):   5%|▍         | 58/1250 [01:31<34:33,  1.74s/it]
Training 1/1 epoch (loss 2.4651):   5%|▍         | 58/1250 [01:33<34:33,  1.74s/it]
Training 1/1 epoch (loss 2.4651):   5%|▍         | 59/1250 [01:33<31:38,  1.59s/it]
Training 1/1 epoch (loss 2.6384):   5%|▍         | 59/1250 [01:34<31:38,  1.59s/it]
Training 1/1 epoch (loss 2.6384):   5%|▍         | 60/1250 [01:34<28:26,  1.43s/it]
Training 1/1 epoch (loss 2.4940):   5%|▍         | 60/1250 [01:35<28:26,  1.43s/it]
Training 1/1 epoch (loss 2.4940):   5%|▍         | 61/1250 [01:35<30:48,  1.55s/it]
Training 1/1 epoch (loss 2.6199):   5%|▍         | 61/1250 [01:37<30:48,  1.55s/it]
Training 1/1 epoch (loss 2.6199):   5%|▍         | 62/1250 [01:37<29:39,  1.50s/it]
Training 1/1 epoch (loss 2.7417):   5%|▍         | 62/1250 [01:39<29:39,  1.50s/it]
Training 1/1 epoch (loss 2.7417):   5%|▌         | 63/1250 [01:39<35:30,  1.79s/it]
Training 1/1 epoch (loss 2.8153):   5%|▌         | 63/1250 [01:41<35:30,  1.79s/it]
Training 1/1 epoch (loss 2.8153):   5%|▌         | 64/1250 [01:41<35:50,  1.81s/it]
Training 1/1 epoch (loss 2.6814):   5%|▌         | 64/1250 [01:42<35:50,  1.81s/it]
Training 1/1 epoch (loss 2.6814):   5%|▌         | 65/1250 [01:42<27:49,  1.41s/it]
Training 1/1 epoch (loss 2.5319):   5%|▌         | 65/1250 [01:43<27:49,  1.41s/it]
Training 1/1 epoch (loss 2.5319):   5%|▌         | 66/1250 [01:43<28:27,  1.44s/it]
Training 1/1 epoch (loss 2.5994):   5%|▌         | 66/1250 [01:45<28:27,  1.44s/it]
Training 1/1 epoch (loss 2.5994):   5%|▌         | 67/1250 [01:45<28:59,  1.47s/it]
Training 1/1 epoch (loss 2.6963):   5%|▌         | 67/1250 [01:45<28:59,  1.47s/it]
Training 1/1 epoch (loss 2.6963):   5%|▌         | 68/1250 [01:45<23:37,  1.20s/it]
Training 1/1 epoch (loss 2.5470):   5%|▌         | 68/1250 [01:47<23:37,  1.20s/it]
Training 1/1 epoch (loss 2.5470):   6%|▌         | 69/1250 [01:47<24:11,  1.23s/it]
Training 1/1 epoch (loss 2.6826):   6%|▌         | 69/1250 [01:49<24:11,  1.23s/it]
Training 1/1 epoch (loss 2.6826):   6%|▌         | 70/1250 [01:49<28:58,  1.47s/it]
Training 1/1 epoch (loss 2.5648):   6%|▌         | 70/1250 [01:49<28:58,  1.47s/it]
Training 1/1 epoch (loss 2.5648):   6%|▌         | 71/1250 [01:49<24:45,  1.26s/it]
Training 1/1 epoch (loss 2.5215):   6%|▌         | 71/1250 [01:52<24:45,  1.26s/it]
Training 1/1 epoch (loss 2.5215):   6%|▌         | 72/1250 [01:52<32:32,  1.66s/it]
Training 1/1 epoch (loss 2.7345):   6%|▌         | 72/1250 [01:54<32:32,  1.66s/it]
Training 1/1 epoch (loss 2.7345):   6%|▌         | 73/1250 [01:54<31:49,  1.62s/it]
Training 1/1 epoch (loss 2.6594):   6%|▌         | 73/1250 [01:55<31:49,  1.62s/it]
Training 1/1 epoch (loss 2.6594):   6%|▌         | 74/1250 [01:55<31:55,  1.63s/it]
Training 1/1 epoch (loss 2.5403):   6%|▌         | 74/1250 [01:57<31:55,  1.63s/it]
Training 1/1 epoch (loss 2.5403):   6%|▌         | 75/1250 [01:57<31:40,  1.62s/it]
Training 1/1 epoch (loss 2.6318):   6%|▌         | 75/1250 [01:58<31:40,  1.62s/it]
Training 1/1 epoch (loss 2.6318):   6%|▌         | 76/1250 [01:58<28:49,  1.47s/it]
Training 1/1 epoch (loss 2.5235):   6%|▌         | 76/1250 [01:59<28:49,  1.47s/it]
Training 1/1 epoch (loss 2.5235):   6%|▌         | 77/1250 [01:59<26:41,  1.37s/it]
Training 1/1 epoch (loss 2.7579):   6%|▌         | 77/1250 [02:01<26:41,  1.37s/it]
Training 1/1 epoch (loss 2.7579):   6%|▌         | 78/1250 [02:01<29:48,  1.53s/it]
Training 1/1 epoch (loss 2.5993):   6%|▌         | 78/1250 [02:02<29:48,  1.53s/it]
Training 1/1 epoch (loss 2.5993):   6%|▋         | 79/1250 [02:02<27:51,  1.43s/it]
Training 1/1 epoch (loss 2.5968):   6%|▋         | 79/1250 [02:04<27:51,  1.43s/it]
Training 1/1 epoch (loss 2.5968):   6%|▋         | 80/1250 [02:04<28:26,  1.46s/it]
Training 1/1 epoch (loss 2.6585):   6%|▋         | 80/1250 [02:05<28:26,  1.46s/it]
Training 1/1 epoch (loss 2.6585):   6%|▋         | 81/1250 [02:05<27:35,  1.42s/it]
Training 1/1 epoch (loss 2.7149):   6%|▋         | 81/1250 [02:07<27:35,  1.42s/it]
Training 1/1 epoch (loss 2.7149):   7%|▋         | 82/1250 [02:07<31:25,  1.61s/it]
Training 1/1 epoch (loss 2.7487):   7%|▋         | 82/1250 [02:08<31:25,  1.61s/it]
Training 1/1 epoch (loss 2.7487):   7%|▋         | 83/1250 [02:08<27:18,  1.40s/it]
Training 1/1 epoch (loss 2.5938):   7%|▋         | 83/1250 [02:09<27:18,  1.40s/it]
Training 1/1 epoch (loss 2.5938):   7%|▋         | 84/1250 [02:09<25:39,  1.32s/it]
Training 1/1 epoch (loss 2.4955):   7%|▋         | 84/1250 [02:11<25:39,  1.32s/it]
Training 1/1 epoch (loss 2.4955):   7%|▋         | 85/1250 [02:11<28:40,  1.48s/it]
Training 1/1 epoch (loss 2.5313):   7%|▋         | 85/1250 [02:13<28:40,  1.48s/it]
Training 1/1 epoch (loss 2.5313):   7%|▋         | 86/1250 [02:13<30:53,  1.59s/it]
Training 1/1 epoch (loss 2.7306):   7%|▋         | 86/1250 [02:13<30:53,  1.59s/it]
Training 1/1 epoch (loss 2.7306):   7%|▋         | 87/1250 [02:13<24:41,  1.27s/it]
Training 1/1 epoch (loss 2.5057):   7%|▋         | 87/1250 [02:15<24:41,  1.27s/it]
Training 1/1 epoch (loss 2.5057):   7%|▋         | 88/1250 [02:15<29:39,  1.53s/it]
Training 1/1 epoch (loss 2.6186):   7%|▋         | 88/1250 [02:17<29:39,  1.53s/it]
Training 1/1 epoch (loss 2.6186):   7%|▋         | 89/1250 [02:17<28:49,  1.49s/it]
Training 1/1 epoch (loss 2.8304):   7%|▋         | 89/1250 [02:17<28:49,  1.49s/it]
Training 1/1 epoch (loss 2.8304):   7%|▋         | 90/1250 [02:17<23:24,  1.21s/it]
Training 1/1 epoch (loss 2.4773):   7%|▋         | 90/1250 [02:18<23:24,  1.21s/it]
Training 1/1 epoch (loss 2.4773):   7%|▋         | 91/1250 [02:18<22:30,  1.17s/it]
Training 1/1 epoch (loss 2.5533):   7%|▋         | 91/1250 [02:20<22:30,  1.17s/it]
Training 1/1 epoch (loss 2.5533):   7%|▋         | 92/1250 [02:20<26:51,  1.39s/it]
Training 1/1 epoch (loss 2.5505):   7%|▋         | 92/1250 [02:21<26:51,  1.39s/it]
Training 1/1 epoch (loss 2.5505):   7%|▋         | 93/1250 [02:21<23:17,  1.21s/it]
Training 1/1 epoch (loss 2.5337):   7%|▋         | 93/1250 [02:23<23:17,  1.21s/it]
Training 1/1 epoch (loss 2.5337):   8%|▊         | 94/1250 [02:23<29:44,  1.54s/it]
Training 1/1 epoch (loss 2.5630):   8%|▊         | 94/1250 [02:26<29:44,  1.54s/it]
Training 1/1 epoch (loss 2.5630):   8%|▊         | 95/1250 [02:26<34:49,  1.81s/it]
Training 1/1 epoch (loss 2.6254):   8%|▊         | 95/1250 [02:27<34:49,  1.81s/it]
Training 1/1 epoch (loss 2.6254):   8%|▊         | 96/1250 [02:27<28:32,  1.48s/it]
Training 1/1 epoch (loss 2.5093):   8%|▊         | 96/1250 [02:28<28:32,  1.48s/it]
Training 1/1 epoch (loss 2.5093):   8%|▊         | 97/1250 [02:28<29:03,  1.51s/it]
Training 1/1 epoch (loss 2.5464):   8%|▊         | 97/1250 [02:29<29:03,  1.51s/it]
Training 1/1 epoch (loss 2.5464):   8%|▊         | 98/1250 [02:29<26:06,  1.36s/it]
Training 1/1 epoch (loss 2.6155):   8%|▊         | 98/1250 [02:30<26:06,  1.36s/it]
Training 1/1 epoch (loss 2.6155):   8%|▊         | 99/1250 [02:30<23:25,  1.22s/it]
Training 1/1 epoch (loss 2.8116):   8%|▊         | 99/1250 [02:32<23:25,  1.22s/it]
Training 1/1 epoch (loss 2.8116):   8%|▊         | 100/1250 [02:32<25:55,  1.35s/it]
Training 1/1 epoch (loss 2.6058):   8%|▊         | 100/1250 [02:33<25:55,  1.35s/it]
Training 1/1 epoch (loss 2.6058):   8%|▊         | 101/1250 [02:33<24:56,  1.30s/it]
Training 1/1 epoch (loss 2.5238):   8%|▊         | 101/1250 [02:34<24:56,  1.30s/it]
Training 1/1 epoch (loss 2.5238):   8%|▊         | 102/1250 [02:34<25:49,  1.35s/it]
Training 1/1 epoch (loss 2.5948):   8%|▊         | 102/1250 [02:36<25:49,  1.35s/it]
Training 1/1 epoch (loss 2.5948):   8%|▊         | 103/1250 [02:36<27:30,  1.44s/it]
Training 1/1 epoch (loss 2.7258):   8%|▊         | 103/1250 [02:37<27:30,  1.44s/it]
Training 1/1 epoch (loss 2.7258):   8%|▊         | 104/1250 [02:37<25:39,  1.34s/it]
Training 1/1 epoch (loss 2.5715):   8%|▊         | 104/1250 [02:39<25:39,  1.34s/it]
Training 1/1 epoch (loss 2.5715):   8%|▊         | 105/1250 [02:39<30:08,  1.58s/it]
Training 1/1 epoch (loss 2.5886):   8%|▊         | 105/1250 [02:41<30:08,  1.58s/it]
Training 1/1 epoch (loss 2.5886):   8%|▊         | 106/1250 [02:41<31:24,  1.65s/it]
Training 1/1 epoch (loss 2.5757):   8%|▊         | 106/1250 [02:42<31:24,  1.65s/it]
Training 1/1 epoch (loss 2.5757):   9%|▊         | 107/1250 [02:42<24:57,  1.31s/it]
Training 1/1 epoch (loss 2.7386):   9%|▊         | 107/1250 [02:44<24:57,  1.31s/it]
Training 1/1 epoch (loss 2.7386):   9%|▊         | 108/1250 [02:44<31:18,  1.65s/it]
Training 1/1 epoch (loss 2.6917):   9%|▊         | 108/1250 [02:46<31:18,  1.65s/it]
Training 1/1 epoch (loss 2.6917):   9%|▊         | 109/1250 [02:46<31:23,  1.65s/it]
Training 1/1 epoch (loss 2.6011):   9%|▊         | 109/1250 [02:46<31:23,  1.65s/it]
Training 1/1 epoch (loss 2.6011):   9%|▉         | 110/1250 [02:46<25:31,  1.34s/it]
Training 1/1 epoch (loss 2.6944):   9%|▉         | 110/1250 [02:49<25:31,  1.34s/it]
Training 1/1 epoch (loss 2.6944):   9%|▉         | 111/1250 [02:49<30:28,  1.61s/it]
Training 1/1 epoch (loss 2.5051):   9%|▉         | 111/1250 [02:51<30:28,  1.61s/it]
Training 1/1 epoch (loss 2.5051):   9%|▉         | 112/1250 [02:51<32:35,  1.72s/it]
Training 1/1 epoch (loss 2.4703):   9%|▉         | 112/1250 [02:52<32:35,  1.72s/it]
Training 1/1 epoch (loss 2.4703):   9%|▉         | 113/1250 [02:52<31:40,  1.67s/it]
Training 1/1 epoch (loss 2.4521):   9%|▉         | 113/1250 [02:54<31:40,  1.67s/it]
Training 1/1 epoch (loss 2.4521):   9%|▉         | 114/1250 [02:54<30:36,  1.62s/it]
Training 1/1 epoch (loss 2.5111):   9%|▉         | 114/1250 [02:55<30:36,  1.62s/it]
Training 1/1 epoch (loss 2.5111):   9%|▉         | 115/1250 [02:55<28:16,  1.50s/it]
Training 1/1 epoch (loss 2.5967):   9%|▉         | 115/1250 [02:56<28:16,  1.50s/it]
Training 1/1 epoch (loss 2.5967):   9%|▉         | 116/1250 [02:56<25:41,  1.36s/it]
Training 1/1 epoch (loss 2.5230):   9%|▉         | 116/1250 [02:57<25:41,  1.36s/it]
Training 1/1 epoch (loss 2.5230):   9%|▉         | 117/1250 [02:57<26:51,  1.42s/it]
Training 1/1 epoch (loss 2.5070):   9%|▉         | 117/1250 [02:58<26:51,  1.42s/it]
Training 1/1 epoch (loss 2.5070):   9%|▉         | 118/1250 [02:58<22:59,  1.22s/it]
Training 1/1 epoch (loss 2.5612):   9%|▉         | 118/1250 [03:00<22:59,  1.22s/it]
Training 1/1 epoch (loss 2.5612):  10%|▉         | 119/1250 [03:00<24:41,  1.31s/it]
Training 1/1 epoch (loss 2.7372):  10%|▉         | 119/1250 [03:02<24:41,  1.31s/it]
Training 1/1 epoch (loss 2.7372):  10%|▉         | 120/1250 [03:02<29:32,  1.57s/it]
Training 1/1 epoch (loss 2.6908):  10%|▉         | 120/1250 [03:02<29:32,  1.57s/it]
Training 1/1 epoch (loss 2.6908):  10%|▉         | 121/1250 [03:02<24:08,  1.28s/it]
Training 1/1 epoch (loss 2.4961):  10%|▉         | 121/1250 [03:04<24:08,  1.28s/it]
Training 1/1 epoch (loss 2.4961):  10%|▉         | 122/1250 [03:04<24:24,  1.30s/it]
Training 1/1 epoch (loss 2.6315):  10%|▉         | 122/1250 [03:05<24:24,  1.30s/it]
Training 1/1 epoch (loss 2.6315):  10%|▉         | 123/1250 [03:05<25:33,  1.36s/it]
Training 1/1 epoch (loss 2.4585):  10%|▉         | 123/1250 [03:06<25:33,  1.36s/it]
Training 1/1 epoch (loss 2.4585):  10%|▉         | 124/1250 [03:06<23:31,  1.25s/it]
Training 1/1 epoch (loss 2.4177):  10%|▉         | 124/1250 [03:08<23:31,  1.25s/it]
Training 1/1 epoch (loss 2.4177):  10%|█         | 125/1250 [03:08<26:32,  1.42s/it]
Training 1/1 epoch (loss 2.6298):  10%|█         | 125/1250 [03:10<26:32,  1.42s/it]
Training 1/1 epoch (loss 2.6298):  10%|█         | 126/1250 [03:10<28:41,  1.53s/it]
Training 1/1 epoch (loss 2.4514):  10%|█         | 126/1250 [03:11<28:41,  1.53s/it]
Training 1/1 epoch (loss 2.4514):  10%|█         | 127/1250 [03:11<27:17,  1.46s/it]
Training 1/1 epoch (loss 2.6429):  10%|█         | 127/1250 [03:12<27:17,  1.46s/it]
Training 1/1 epoch (loss 2.6429):  10%|█         | 128/1250 [03:12<21:52,  1.17s/it]
Training 1/1 epoch (loss 2.5333):  10%|█         | 128/1250 [03:13<21:52,  1.17s/it]
Training 1/1 epoch (loss 2.5333):  10%|█         | 129/1250 [03:13<20:59,  1.12s/it]
Training 1/1 epoch (loss 2.5523):  10%|█         | 129/1250 [03:14<20:59,  1.12s/it]
Training 1/1 epoch (loss 2.5523):  10%|█         | 130/1250 [03:14<21:52,  1.17s/it]
Training 1/1 epoch (loss 2.7132):  10%|█         | 130/1250 [03:16<21:52,  1.17s/it]
Training 1/1 epoch (loss 2.7132):  10%|█         | 131/1250 [03:16<24:43,  1.33s/it]
Training 1/1 epoch (loss 2.7097):  10%|█         | 131/1250 [03:17<24:43,  1.33s/it]
Training 1/1 epoch (loss 2.7097):  11%|█         | 132/1250 [03:17<24:16,  1.30s/it]
Training 1/1 epoch (loss 2.6387):  11%|█         | 132/1250 [03:18<24:16,  1.30s/it]
Training 1/1 epoch (loss 2.6387):  11%|█         | 133/1250 [03:18<25:38,  1.38s/it]
Training 1/1 epoch (loss 2.7275):  11%|█         | 133/1250 [03:20<25:38,  1.38s/it]
Training 1/1 epoch (loss 2.7275):  11%|█         | 134/1250 [03:20<25:21,  1.36s/it]
Training 1/1 epoch (loss 2.6526):  11%|█         | 134/1250 [03:21<25:21,  1.36s/it]
Training 1/1 epoch (loss 2.6526):  11%|█         | 135/1250 [03:21<23:01,  1.24s/it]
Training 1/1 epoch (loss 2.6057):  11%|█         | 135/1250 [03:22<23:01,  1.24s/it]
Training 1/1 epoch (loss 2.6057):  11%|█         | 136/1250 [03:22<23:36,  1.27s/it]
Training 1/1 epoch (loss 2.5167):  11%|█         | 136/1250 [03:24<23:36,  1.27s/it]
Training 1/1 epoch (loss 2.5167):  11%|█         | 137/1250 [03:24<28:44,  1.55s/it]
Training 1/1 epoch (loss 2.4851):  11%|█         | 137/1250 [03:25<28:44,  1.55s/it]
Training 1/1 epoch (loss 2.4851):  11%|█         | 138/1250 [03:25<23:53,  1.29s/it]
Training 1/1 epoch (loss 2.7420):  11%|█         | 138/1250 [03:27<23:53,  1.29s/it]
Training 1/1 epoch (loss 2.7420):  11%|█         | 139/1250 [03:27<30:15,  1.63s/it]
Training 1/1 epoch (loss 2.6645):  11%|█         | 139/1250 [03:30<30:15,  1.63s/it]
Training 1/1 epoch (loss 2.6645):  11%|█         | 140/1250 [03:30<34:25,  1.86s/it]
Training 1/1 epoch (loss 2.5382):  11%|█         | 140/1250 [03:30<34:25,  1.86s/it]
Training 1/1 epoch (loss 2.5382):  11%|█▏        | 141/1250 [03:30<26:26,  1.43s/it]
Training 1/1 epoch (loss 2.6845):  11%|█▏        | 141/1250 [03:33<26:26,  1.43s/it]
Training 1/1 epoch (loss 2.6845):  11%|█▏        | 142/1250 [03:33<31:15,  1.69s/it]
Training 1/1 epoch (loss 2.6086):  11%|█▏        | 142/1250 [03:34<31:15,  1.69s/it]
Training 1/1 epoch (loss 2.6086):  11%|█▏        | 143/1250 [03:34<30:05,  1.63s/it]
Training 1/1 epoch (loss 2.7442):  11%|█▏        | 143/1250 [03:35<30:05,  1.63s/it]
Training 1/1 epoch (loss 2.7442):  12%|█▏        | 144/1250 [03:35<26:14,  1.42s/it]
Training 1/1 epoch (loss 2.6195):  12%|█▏        | 144/1250 [03:37<26:14,  1.42s/it]
Training 1/1 epoch (loss 2.6195):  12%|█▏        | 145/1250 [03:37<27:33,  1.50s/it]
Training 1/1 epoch (loss 2.7169):  12%|█▏        | 145/1250 [03:38<27:33,  1.50s/it]
Training 1/1 epoch (loss 2.7169):  12%|█▏        | 146/1250 [03:38<25:18,  1.38s/it]
Training 1/1 epoch (loss 2.5402):  12%|█▏        | 146/1250 [03:39<25:18,  1.38s/it]
Training 1/1 epoch (loss 2.5402):  12%|█▏        | 147/1250 [03:39<24:28,  1.33s/it]
Training 1/1 epoch (loss 2.6608):  12%|█▏        | 147/1250 [03:41<24:28,  1.33s/it]
Training 1/1 epoch (loss 2.6608):  12%|█▏        | 148/1250 [03:41<27:34,  1.50s/it]
Training 1/1 epoch (loss 2.5834):  12%|█▏        | 148/1250 [03:42<27:34,  1.50s/it]
Training 1/1 epoch (loss 2.5834):  12%|█▏        | 149/1250 [03:42<25:25,  1.39s/it]
Training 1/1 epoch (loss 2.8507):  12%|█▏        | 149/1250 [03:43<25:25,  1.39s/it]
Training 1/1 epoch (loss 2.8507):  12%|█▏        | 150/1250 [03:43<21:57,  1.20s/it]
Training 1/1 epoch (loss 2.6130):  12%|█▏        | 150/1250 [03:45<21:57,  1.20s/it]
Training 1/1 epoch (loss 2.6130):  12%|█▏        | 151/1250 [03:45<26:07,  1.43s/it]
Training 1/1 epoch (loss 2.6731):  12%|█▏        | 151/1250 [03:46<26:07,  1.43s/it]
Training 1/1 epoch (loss 2.6731):  12%|█▏        | 152/1250 [03:46<25:29,  1.39s/it]
Training 1/1 epoch (loss 2.8082):  12%|█▏        | 152/1250 [03:47<25:29,  1.39s/it]
Training 1/1 epoch (loss 2.8082):  12%|█▏        | 153/1250 [03:47<25:32,  1.40s/it]
Training 1/1 epoch (loss 2.7212):  12%|█▏        | 153/1250 [03:49<25:32,  1.40s/it]
Training 1/1 epoch (loss 2.7212):  12%|█▏        | 154/1250 [03:49<24:53,  1.36s/it]
Training 1/1 epoch (loss 2.6458):  12%|█▏        | 154/1250 [03:50<24:53,  1.36s/it]
Training 1/1 epoch (loss 2.6458):  12%|█▏        | 155/1250 [03:50<22:42,  1.24s/it]
Training 1/1 epoch (loss 2.7682):  12%|█▏        | 155/1250 [03:51<22:42,  1.24s/it]
Training 1/1 epoch (loss 2.7682):  12%|█▏        | 156/1250 [03:51<24:57,  1.37s/it]
Training 1/1 epoch (loss 2.7527):  12%|█▏        | 156/1250 [03:54<24:57,  1.37s/it]
Training 1/1 epoch (loss 2.7527):  13%|█▎        | 157/1250 [03:54<29:55,  1.64s/it]
Training 1/1 epoch (loss 2.7489):  13%|█▎        | 157/1250 [03:55<29:55,  1.64s/it]
Training 1/1 epoch (loss 2.7489):  13%|█▎        | 158/1250 [03:55<26:58,  1.48s/it]
Training 1/1 epoch (loss 2.8730):  13%|█▎        | 158/1250 [03:57<26:58,  1.48s/it]
Training 1/1 epoch (loss 2.8730):  13%|█▎        | 159/1250 [03:57<29:42,  1.63s/it]
Training 1/1 epoch (loss 2.6000):  13%|█▎        | 159/1250 [03:59<29:42,  1.63s/it]
Training 1/1 epoch (loss 2.6000):  13%|█▎        | 160/1250 [03:59<31:38,  1.74s/it]
Training 1/1 epoch (loss 2.6196):  13%|█▎        | 160/1250 [03:59<31:38,  1.74s/it]
Training 1/1 epoch (loss 2.6196):  13%|█▎        | 161/1250 [03:59<26:15,  1.45s/it]
Training 1/1 epoch (loss 2.5049):  13%|█▎        | 161/1250 [04:02<26:15,  1.45s/it]
Training 1/1 epoch (loss 2.5049):  13%|█▎        | 162/1250 [04:02<30:15,  1.67s/it]
Training 1/1 epoch (loss 2.6809):  13%|█▎        | 162/1250 [04:04<30:15,  1.67s/it]
Training 1/1 epoch (loss 2.6809):  13%|█▎        | 163/1250 [04:04<31:31,  1.74s/it]
Training 1/1 epoch (loss 2.4809):  13%|█▎        | 163/1250 [04:04<31:31,  1.74s/it]
Training 1/1 epoch (loss 2.4809):  13%|█▎        | 164/1250 [04:04<25:02,  1.38s/it]
Training 1/1 epoch (loss 2.5805):  13%|█▎        | 164/1250 [04:07<25:02,  1.38s/it]
Training 1/1 epoch (loss 2.5805):  13%|█▎        | 165/1250 [04:07<30:42,  1.70s/it]
Training 1/1 epoch (loss 2.5779):  13%|█▎        | 165/1250 [04:08<30:42,  1.70s/it]
Training 1/1 epoch (loss 2.5779):  13%|█▎        | 166/1250 [04:08<29:51,  1.65s/it]
Training 1/1 epoch (loss 2.5566):  13%|█▎        | 166/1250 [04:09<29:51,  1.65s/it]
Training 1/1 epoch (loss 2.5566):  13%|█▎        | 167/1250 [04:09<23:08,  1.28s/it]
Training 1/1 epoch (loss 2.5927):  13%|█▎        | 167/1250 [04:10<23:08,  1.28s/it]
Training 1/1 epoch (loss 2.5927):  13%|█▎        | 168/1250 [04:10<26:33,  1.47s/it]
Training 1/1 epoch (loss 2.6260):  13%|█▎        | 168/1250 [04:12<26:33,  1.47s/it]
Training 1/1 epoch (loss 2.6260):  14%|█▎        | 169/1250 [04:12<28:15,  1.57s/it]
Training 1/1 epoch (loss 2.6720):  14%|█▎        | 169/1250 [04:13<28:15,  1.57s/it]
Training 1/1 epoch (loss 2.6720):  14%|█▎        | 170/1250 [04:13<24:43,  1.37s/it]
Training 1/1 epoch (loss 2.6212):  14%|█▎        | 170/1250 [04:14<24:43,  1.37s/it]
Training 1/1 epoch (loss 2.6212):  14%|█▎        | 171/1250 [04:14<24:31,  1.36s/it]
Training 1/1 epoch (loss 2.5141):  14%|█▎        | 171/1250 [04:16<24:31,  1.36s/it]
Training 1/1 epoch (loss 2.5141):  14%|█▍        | 172/1250 [04:16<26:19,  1.46s/it]
Training 1/1 epoch (loss 2.4364):  14%|█▍        | 172/1250 [04:17<26:19,  1.46s/it]
Training 1/1 epoch (loss 2.4364):  14%|█▍        | 173/1250 [04:17<23:37,  1.32s/it]
Training 1/1 epoch (loss 2.7576):  14%|█▍        | 173/1250 [04:19<23:37,  1.32s/it]
Training 1/1 epoch (loss 2.7576):  14%|█▍        | 174/1250 [04:19<25:37,  1.43s/it]
Training 1/1 epoch (loss 2.7910):  14%|█▍        | 174/1250 [04:20<25:37,  1.43s/it]
Training 1/1 epoch (loss 2.7910):  14%|█▍        | 175/1250 [04:20<23:30,  1.31s/it]
Training 1/1 epoch (loss 2.5759):  14%|█▍        | 175/1250 [04:21<23:30,  1.31s/it]
Training 1/1 epoch (loss 2.5759):  14%|█▍        | 176/1250 [04:21<24:35,  1.37s/it]
Training 1/1 epoch (loss 2.8340):  14%|█▍        | 176/1250 [04:24<24:35,  1.37s/it]
Training 1/1 epoch (loss 2.8340):  14%|█▍        | 177/1250 [04:24<29:29,  1.65s/it]
Training 1/1 epoch (loss 2.6586):  14%|█▍        | 177/1250 [04:24<29:29,  1.65s/it]
Training 1/1 epoch (loss 2.6586):  14%|█▍        | 178/1250 [04:24<22:38,  1.27s/it]
Training 1/1 epoch (loss 2.8715):  14%|█▍        | 178/1250 [04:26<22:38,  1.27s/it]
Training 1/1 epoch (loss 2.8715):  14%|█▍        | 179/1250 [04:26<27:07,  1.52s/it]
Training 1/1 epoch (loss 2.7768):  14%|█▍        | 179/1250 [04:28<27:07,  1.52s/it]
Training 1/1 epoch (loss 2.7768):  14%|█▍        | 180/1250 [04:28<29:22,  1.65s/it]
Training 1/1 epoch (loss 2.8022):  14%|█▍        | 180/1250 [04:29<29:22,  1.65s/it]
Training 1/1 epoch (loss 2.8022):  14%|█▍        | 181/1250 [04:29<23:29,  1.32s/it]
Training 1/1 epoch (loss 2.6742):  14%|█▍        | 181/1250 [04:31<23:29,  1.32s/it]
Training 1/1 epoch (loss 2.6742):  15%|█▍        | 182/1250 [04:31<27:49,  1.56s/it]
Training 1/1 epoch (loss 2.7101):  15%|█▍        | 182/1250 [04:32<27:49,  1.56s/it]
Training 1/1 epoch (loss 2.7101):  15%|█▍        | 183/1250 [04:32<27:46,  1.56s/it]
Training 1/1 epoch (loss 2.6604):  15%|█▍        | 183/1250 [04:33<27:46,  1.56s/it]
Training 1/1 epoch (loss 2.6604):  15%|█▍        | 184/1250 [04:33<23:09,  1.30s/it]
Training 1/1 epoch (loss 2.5734):  15%|█▍        | 184/1250 [04:35<23:09,  1.30s/it]
Training 1/1 epoch (loss 2.5734):  15%|█▍        | 185/1250 [04:35<23:58,  1.35s/it]
Training 1/1 epoch (loss 2.6561):  15%|█▍        | 185/1250 [04:36<23:58,  1.35s/it]
Training 1/1 epoch (loss 2.6561):  15%|█▍        | 186/1250 [04:36<25:26,  1.43s/it]
Training 1/1 epoch (loss 2.7225):  15%|█▍        | 186/1250 [04:37<25:26,  1.43s/it]
Training 1/1 epoch (loss 2.7225):  15%|█▍        | 187/1250 [04:37<20:48,  1.17s/it]
Training 1/1 epoch (loss 2.4615):  15%|█▍        | 187/1250 [04:38<20:48,  1.17s/it]
Training 1/1 epoch (loss 2.4615):  15%|█▌        | 188/1250 [04:38<23:44,  1.34s/it]
Training 1/1 epoch (loss 2.5255):  15%|█▌        | 188/1250 [04:40<23:44,  1.34s/it]
Training 1/1 epoch (loss 2.5255):  15%|█▌        | 189/1250 [04:40<24:42,  1.40s/it]
Training 1/1 epoch (loss 2.5048):  15%|█▌        | 189/1250 [04:41<24:42,  1.40s/it]
Training 1/1 epoch (loss 2.5048):  15%|█▌        | 190/1250 [04:41<22:26,  1.27s/it]
Training 1/1 epoch (loss 2.6060):  15%|█▌        | 190/1250 [04:43<22:26,  1.27s/it]
Training 1/1 epoch (loss 2.6060):  15%|█▌        | 191/1250 [04:43<24:20,  1.38s/it]
Training 1/1 epoch (loss 2.8505):  15%|█▌        | 191/1250 [04:44<24:20,  1.38s/it]
Training 1/1 epoch (loss 2.8505):  15%|█▌        | 192/1250 [04:44<25:16,  1.43s/it]
Training 1/1 epoch (loss 2.6298):  15%|█▌        | 192/1250 [04:45<25:16,  1.43s/it]
Training 1/1 epoch (loss 2.6298):  15%|█▌        | 193/1250 [04:45<23:48,  1.35s/it]
Training 1/1 epoch (loss 2.7686):  15%|█▌        | 193/1250 [04:47<23:48,  1.35s/it]
Training 1/1 epoch (loss 2.7686):  16%|█▌        | 194/1250 [04:47<24:44,  1.41s/it]
Training 1/1 epoch (loss 2.6273):  16%|█▌        | 194/1250 [04:48<24:44,  1.41s/it]
Training 1/1 epoch (loss 2.6273):  16%|█▌        | 195/1250 [04:48<23:18,  1.33s/it]
Training 1/1 epoch (loss 2.4896):  16%|█▌        | 195/1250 [04:49<23:18,  1.33s/it]
Training 1/1 epoch (loss 2.4896):  16%|█▌        | 196/1250 [04:49<24:01,  1.37s/it]
Training 1/1 epoch (loss 2.5446):  16%|█▌        | 196/1250 [04:52<24:01,  1.37s/it]
Training 1/1 epoch (loss 2.5446):  16%|█▌        | 197/1250 [04:52<28:29,  1.62s/it]
Training 1/1 epoch (loss 2.7473):  16%|█▌        | 197/1250 [04:52<28:29,  1.62s/it]
Training 1/1 epoch (loss 2.7473):  16%|█▌        | 198/1250 [04:52<24:08,  1.38s/it]
Training 1/1 epoch (loss 2.6832):  16%|█▌        | 198/1250 [04:54<24:08,  1.38s/it]
Training 1/1 epoch (loss 2.6832):  16%|█▌        | 199/1250 [04:54<25:46,  1.47s/it]
Training 1/1 epoch (loss 2.6156):  16%|█▌        | 199/1250 [04:56<25:46,  1.47s/it]
Training 1/1 epoch (loss 2.6156):  16%|█▌        | 200/1250 [04:56<29:48,  1.70s/it]
Training 1/1 epoch (loss 2.7322):  16%|█▌        | 200/1250 [04:57<29:48,  1.70s/it]
Training 1/1 epoch (loss 2.7322):  16%|█▌        | 201/1250 [04:57<24:15,  1.39s/it]
Training 1/1 epoch (loss 2.5959):  16%|█▌        | 201/1250 [04:59<24:15,  1.39s/it]
Training 1/1 epoch (loss 2.5959):  16%|█▌        | 202/1250 [04:59<29:09,  1.67s/it]
Training 1/1 epoch (loss 2.5177):  16%|█▌        | 202/1250 [05:01<29:09,  1.67s/it]
Training 1/1 epoch (loss 2.5177):  16%|█▌        | 203/1250 [05:01<28:13,  1.62s/it]
Training 1/1 epoch (loss 2.5243):  16%|█▌        | 203/1250 [05:02<28:13,  1.62s/it]
Training 1/1 epoch (loss 2.5243):  16%|█▋        | 204/1250 [05:02<23:27,  1.35s/it]
Training 1/1 epoch (loss 2.5084):  16%|█▋        | 204/1250 [05:03<23:27,  1.35s/it]
Training 1/1 epoch (loss 2.5084):  16%|█▋        | 205/1250 [05:03<25:42,  1.48s/it]
Training 1/1 epoch (loss 2.8023):  16%|█▋        | 205/1250 [05:05<25:42,  1.48s/it]
Training 1/1 epoch (loss 2.8023):  16%|█▋        | 206/1250 [05:05<25:00,  1.44s/it]
Training 1/1 epoch (loss 2.6461):  16%|█▋        | 206/1250 [05:05<25:00,  1.44s/it]
Training 1/1 epoch (loss 2.6461):  17%|█▋        | 207/1250 [05:05<21:07,  1.22s/it]
Training 1/1 epoch (loss 2.6567):  17%|█▋        | 207/1250 [05:08<21:07,  1.22s/it]
Training 1/1 epoch (loss 2.6567):  17%|█▋        | 208/1250 [05:08<25:43,  1.48s/it]
Training 1/1 epoch (loss 2.6318):  17%|█▋        | 208/1250 [05:09<25:43,  1.48s/it]
Training 1/1 epoch (loss 2.6318):  17%|█▋        | 209/1250 [05:09<24:45,  1.43s/it]
Training 1/1 epoch (loss 2.6482):  17%|█▋        | 209/1250 [05:09<24:45,  1.43s/it]
Training 1/1 epoch (loss 2.6482):  17%|█▋        | 210/1250 [05:09<20:31,  1.18s/it]
Training 1/1 epoch (loss 2.6710):  17%|█▋        | 210/1250 [05:11<20:31,  1.18s/it]
Training 1/1 epoch (loss 2.6710):  17%|█▋        | 211/1250 [05:11<22:49,  1.32s/it]
Training 1/1 epoch (loss 2.8160):  17%|█▋        | 211/1250 [05:12<22:49,  1.32s/it]
Training 1/1 epoch (loss 2.8160):  17%|█▋        | 212/1250 [05:12<21:05,  1.22s/it]
Training 1/1 epoch (loss 2.5953):  17%|█▋        | 212/1250 [05:13<21:05,  1.22s/it]
Training 1/1 epoch (loss 2.5953):  17%|█▋        | 213/1250 [05:13<21:47,  1.26s/it]
Training 1/1 epoch (loss 2.4638):  17%|█▋        | 213/1250 [05:15<21:47,  1.26s/it]
Training 1/1 epoch (loss 2.4638):  17%|█▋        | 214/1250 [05:15<23:17,  1.35s/it]
Training 1/1 epoch (loss 2.4792):  17%|█▋        | 214/1250 [05:16<23:17,  1.35s/it]
Training 1/1 epoch (loss 2.4792):  17%|█▋        | 215/1250 [05:16<21:21,  1.24s/it]
Training 1/1 epoch (loss 2.3677):  17%|█▋        | 215/1250 [05:17<21:21,  1.24s/it]
Training 1/1 epoch (loss 2.3677):  17%|█▋        | 216/1250 [05:17<22:45,  1.32s/it]
Training 1/1 epoch (loss 2.4528):  17%|█▋        | 216/1250 [05:20<22:45,  1.32s/it]
Training 1/1 epoch (loss 2.4528):  17%|█▋        | 217/1250 [05:20<28:27,  1.65s/it]
Training 1/1 epoch (loss 2.6955):  17%|█▋        | 217/1250 [05:21<28:27,  1.65s/it]
Training 1/1 epoch (loss 2.6955):  17%|█▋        | 218/1250 [05:21<24:35,  1.43s/it]
Training 1/1 epoch (loss 2.7063):  17%|█▋        | 218/1250 [05:23<24:35,  1.43s/it]
Training 1/1 epoch (loss 2.7063):  18%|█▊        | 219/1250 [05:23<26:19,  1.53s/it]
Training 1/1 epoch (loss 2.4764):  18%|█▊        | 219/1250 [05:24<26:19,  1.53s/it]
Training 1/1 epoch (loss 2.4764):  18%|█▊        | 220/1250 [05:24<28:18,  1.65s/it]
Training 1/1 epoch (loss 2.5192):  18%|█▊        | 220/1250 [05:25<28:18,  1.65s/it]
Training 1/1 epoch (loss 2.5192):  18%|█▊        | 221/1250 [05:25<22:31,  1.31s/it]
Training 1/1 epoch (loss 2.6507):  18%|█▊        | 221/1250 [05:27<22:31,  1.31s/it]
Training 1/1 epoch (loss 2.6507):  18%|█▊        | 222/1250 [05:27<26:50,  1.57s/it]
Training 1/1 epoch (loss 2.5295):  18%|█▊        | 222/1250 [05:29<26:50,  1.57s/it]
Training 1/1 epoch (loss 2.5295):  18%|█▊        | 223/1250 [05:29<27:28,  1.60s/it]
Training 1/1 epoch (loss 2.5683):  18%|█▊        | 223/1250 [05:30<27:28,  1.60s/it]
Training 1/1 epoch (loss 2.5683):  18%|█▊        | 224/1250 [05:30<24:55,  1.46s/it]
Training 1/1 epoch (loss 2.4135):  18%|█▊        | 224/1250 [05:32<24:55,  1.46s/it]
Training 1/1 epoch (loss 2.4135):  18%|█▊        | 225/1250 [05:32<29:44,  1.74s/it]
Training 1/1 epoch (loss 2.5973):  18%|█▊        | 225/1250 [05:34<29:44,  1.74s/it]
Training 1/1 epoch (loss 2.5973):  18%|█▊        | 226/1250 [05:34<30:13,  1.77s/it]
Training 1/1 epoch (loss 2.7840):  18%|█▊        | 226/1250 [05:35<30:13,  1.77s/it]
Training 1/1 epoch (loss 2.7840):  18%|█▊        | 227/1250 [05:35<25:06,  1.47s/it]
Training 1/1 epoch (loss 2.7061):  18%|█▊        | 227/1250 [05:37<25:06,  1.47s/it]
Training 1/1 epoch (loss 2.7061):  18%|█▊        | 228/1250 [05:37<28:08,  1.65s/it]
Training 1/1 epoch (loss 2.6362):  18%|█▊        | 228/1250 [05:39<28:08,  1.65s/it]
Training 1/1 epoch (loss 2.6362):  18%|█▊        | 229/1250 [05:39<28:10,  1.66s/it]
Training 1/1 epoch (loss 2.5504):  18%|█▊        | 229/1250 [05:39<28:10,  1.66s/it]
Training 1/1 epoch (loss 2.5504):  18%|█▊        | 230/1250 [05:39<22:29,  1.32s/it]
Training 1/1 epoch (loss 2.7516):  18%|█▊        | 230/1250 [05:41<22:29,  1.32s/it]
Training 1/1 epoch (loss 2.7516):  18%|█▊        | 231/1250 [05:41<26:16,  1.55s/it]
Training 1/1 epoch (loss 2.7772):  18%|█▊        | 231/1250 [05:43<26:16,  1.55s/it]
Training 1/1 epoch (loss 2.7772):  19%|█▊        | 232/1250 [05:43<25:55,  1.53s/it]
Training 1/1 epoch (loss 2.6560):  19%|█▊        | 232/1250 [05:45<25:55,  1.53s/it]
Training 1/1 epoch (loss 2.6560):  19%|█▊        | 233/1250 [05:45<26:49,  1.58s/it]
Training 1/1 epoch (loss 2.6433):  19%|█▊        | 233/1250 [05:46<26:49,  1.58s/it]
Training 1/1 epoch (loss 2.6433):  19%|█▊        | 234/1250 [05:46<28:04,  1.66s/it]
Training 1/1 epoch (loss 2.6847):  19%|█▊        | 234/1250 [05:47<28:04,  1.66s/it]
Training 1/1 epoch (loss 2.6847):  19%|█▉        | 235/1250 [05:47<22:16,  1.32s/it]
Training 1/1 epoch (loss 2.6686):  19%|█▉        | 235/1250 [05:48<22:16,  1.32s/it]
Training 1/1 epoch (loss 2.6686):  19%|█▉        | 236/1250 [05:48<23:15,  1.38s/it]
Training 1/1 epoch (loss 2.4901):  19%|█▉        | 236/1250 [05:50<23:15,  1.38s/it]
Training 1/1 epoch (loss 2.4901):  19%|█▉        | 237/1250 [05:50<26:30,  1.57s/it]
Training 1/1 epoch (loss 2.6159):  19%|█▉        | 237/1250 [05:51<26:30,  1.57s/it]
Training 1/1 epoch (loss 2.6159):  19%|█▉        | 238/1250 [05:51<20:58,  1.24s/it]
Training 1/1 epoch (loss 2.5147):  19%|█▉        | 238/1250 [05:52<20:58,  1.24s/it]
Training 1/1 epoch (loss 2.5147):  19%|█▉        | 239/1250 [05:52<21:26,  1.27s/it]
Training 1/1 epoch (loss 2.5738):  19%|█▉        | 239/1250 [05:54<21:26,  1.27s/it]
Training 1/1 epoch (loss 2.5738):  19%|█▉        | 240/1250 [05:54<25:59,  1.54s/it]
Training 1/1 epoch (loss 2.4772):  19%|█▉        | 240/1250 [05:55<25:59,  1.54s/it]
Training 1/1 epoch (loss 2.4772):  19%|█▉        | 241/1250 [05:55<22:04,  1.31s/it]
Training 1/1 epoch (loss 2.6071):  19%|█▉        | 241/1250 [05:57<22:04,  1.31s/it]
Training 1/1 epoch (loss 2.6071):  19%|█▉        | 242/1250 [05:57<25:56,  1.54s/it]
Training 1/1 epoch (loss 2.4817):  19%|█▉        | 242/1250 [05:59<25:56,  1.54s/it]
Training 1/1 epoch (loss 2.4817):  19%|█▉        | 243/1250 [05:59<24:19,  1.45s/it]
Training 1/1 epoch (loss 2.4051):  19%|█▉        | 243/1250 [05:59<24:19,  1.45s/it]
Training 1/1 epoch (loss 2.4051):  20%|█▉        | 244/1250 [05:59<20:53,  1.25s/it]
Training 1/1 epoch (loss 2.5612):  20%|█▉        | 244/1250 [06:02<20:53,  1.25s/it]
Training 1/1 epoch (loss 2.5612):  20%|█▉        | 245/1250 [06:02<26:57,  1.61s/it]
Training 1/1 epoch (loss 2.6350):  20%|█▉        | 245/1250 [06:03<26:57,  1.61s/it]
Training 1/1 epoch (loss 2.6350):  20%|█▉        | 246/1250 [06:03<25:38,  1.53s/it]
Training 1/1 epoch (loss 2.5225):  20%|█▉        | 246/1250 [06:06<25:38,  1.53s/it]
Training 1/1 epoch (loss 2.5225):  20%|█▉        | 247/1250 [06:06<30:35,  1.83s/it]
Training 1/1 epoch (loss 2.5179):  20%|█▉        | 247/1250 [06:07<30:35,  1.83s/it]
Training 1/1 epoch (loss 2.5179):  20%|█▉        | 248/1250 [06:07<29:08,  1.75s/it]
Training 1/1 epoch (loss 2.7152):  20%|█▉        | 248/1250 [06:08<29:08,  1.75s/it]
Training 1/1 epoch (loss 2.7152):  20%|█▉        | 249/1250 [06:08<23:23,  1.40s/it]
Training 1/1 epoch (loss 2.6878):  20%|█▉        | 249/1250 [06:09<23:23,  1.40s/it]
Training 1/1 epoch (loss 2.6878):  20%|██        | 250/1250 [06:09<23:59,  1.44s/it]
Training 1/1 epoch (loss 2.5125):  20%|██        | 250/1250 [06:11<23:59,  1.44s/it]
Training 1/1 epoch (loss 2.5125):  20%|██        | 251/1250 [06:11<25:48,  1.55s/it]
Training 1/1 epoch (loss 2.6733):  20%|██        | 251/1250 [06:11<25:48,  1.55s/it]
Training 1/1 epoch (loss 2.6733):  20%|██        | 252/1250 [06:11<19:59,  1.20s/it]
Training 1/1 epoch (loss 2.5993):  20%|██        | 252/1250 [06:14<19:59,  1.20s/it]
Training 1/1 epoch (loss 2.5993):  20%|██        | 253/1250 [06:14<25:26,  1.53s/it]
Training 1/1 epoch (loss 2.6995):  20%|██        | 253/1250 [06:15<25:26,  1.53s/it]
Training 1/1 epoch (loss 2.6995):  20%|██        | 254/1250 [06:15<24:21,  1.47s/it]
Training 1/1 epoch (loss 2.6003):  20%|██        | 254/1250 [06:16<24:21,  1.47s/it]
Training 1/1 epoch (loss 2.6003):  20%|██        | 255/1250 [06:16<20:01,  1.21s/it]
Training 1/1 epoch (loss 2.6789):  20%|██        | 255/1250 [06:18<20:01,  1.21s/it]
Training 1/1 epoch (loss 2.6789):  20%|██        | 256/1250 [06:18<23:43,  1.43s/it]
Training 1/1 epoch (loss 2.6560):  20%|██        | 256/1250 [06:19<23:43,  1.43s/it]
Training 1/1 epoch (loss 2.6560):  21%|██        | 257/1250 [06:19<22:12,  1.34s/it]
Training 1/1 epoch (loss 2.6079):  21%|██        | 257/1250 [06:21<22:12,  1.34s/it]
Training 1/1 epoch (loss 2.6079):  21%|██        | 258/1250 [06:21<27:57,  1.69s/it]
Training 1/1 epoch (loss 2.5981):  21%|██        | 258/1250 [06:23<27:57,  1.69s/it]
Training 1/1 epoch (loss 2.5981):  21%|██        | 259/1250 [06:23<30:06,  1.82s/it]
Training 1/1 epoch (loss 2.6281):  21%|██        | 259/1250 [06:24<30:06,  1.82s/it]
Training 1/1 epoch (loss 2.6281):  21%|██        | 260/1250 [06:24<23:18,  1.41s/it]
Training 1/1 epoch (loss 2.5308):  21%|██        | 260/1250 [06:26<23:18,  1.41s/it]
Training 1/1 epoch (loss 2.5308):  21%|██        | 261/1250 [06:26<25:59,  1.58s/it]
Training 1/1 epoch (loss 2.5638):  21%|██        | 261/1250 [06:27<25:59,  1.58s/it]
Training 1/1 epoch (loss 2.5638):  21%|██        | 262/1250 [06:27<24:09,  1.47s/it]
Training 1/1 epoch (loss 2.5609):  21%|██        | 262/1250 [06:28<24:09,  1.47s/it]
Training 1/1 epoch (loss 2.5609):  21%|██        | 263/1250 [06:28<20:22,  1.24s/it]
Training 1/1 epoch (loss 2.3152):  21%|██        | 263/1250 [06:30<20:22,  1.24s/it]
Training 1/1 epoch (loss 2.3152):  21%|██        | 264/1250 [06:30<25:35,  1.56s/it]
Training 1/1 epoch (loss 2.6688):  21%|██        | 264/1250 [06:33<25:35,  1.56s/it]
Training 1/1 epoch (loss 2.6688):  21%|██        | 265/1250 [06:33<30:05,  1.83s/it]
Training 1/1 epoch (loss 2.6196):  21%|██        | 265/1250 [06:33<30:05,  1.83s/it]
Training 1/1 epoch (loss 2.6196):  21%|██▏       | 266/1250 [06:33<24:30,  1.49s/it]
Training 1/1 epoch (loss 2.6876):  21%|██▏       | 266/1250 [06:36<24:30,  1.49s/it]
Training 1/1 epoch (loss 2.6876):  21%|██▏       | 267/1250 [06:36<28:57,  1.77s/it]
Training 1/1 epoch (loss 2.6644):  21%|██▏       | 267/1250 [06:37<28:57,  1.77s/it]
Training 1/1 epoch (loss 2.6644):  21%|██▏       | 268/1250 [06:37<26:51,  1.64s/it]
Training 1/1 epoch (loss 2.6001):  21%|██▏       | 268/1250 [06:38<26:51,  1.64s/it]
Training 1/1 epoch (loss 2.6001):  22%|██▏       | 269/1250 [06:38<21:25,  1.31s/it]
Training 1/1 epoch (loss 2.5625):  22%|██▏       | 269/1250 [06:40<21:25,  1.31s/it]
Training 1/1 epoch (loss 2.5625):  22%|██▏       | 270/1250 [06:40<26:07,  1.60s/it]
Training 1/1 epoch (loss 2.4593):  22%|██▏       | 270/1250 [06:42<26:07,  1.60s/it]
Training 1/1 epoch (loss 2.4593):  22%|██▏       | 271/1250 [06:42<26:37,  1.63s/it]
Training 1/1 epoch (loss 2.3700):  22%|██▏       | 271/1250 [06:42<26:37,  1.63s/it]
Training 1/1 epoch (loss 2.3700):  22%|██▏       | 272/1250 [06:42<23:08,  1.42s/it]
Training 1/1 epoch (loss 2.5599):  22%|██▏       | 272/1250 [06:45<23:08,  1.42s/it]
Training 1/1 epoch (loss 2.5599):  22%|██▏       | 273/1250 [06:45<26:44,  1.64s/it]
Training 1/1 epoch (loss 2.6491):  22%|██▏       | 273/1250 [06:46<26:44,  1.64s/it]
Training 1/1 epoch (loss 2.6491):  22%|██▏       | 274/1250 [06:46<24:37,  1.51s/it]
Training 1/1 epoch (loss 2.6812):  22%|██▏       | 274/1250 [06:47<24:37,  1.51s/it]
Training 1/1 epoch (loss 2.6812):  22%|██▏       | 275/1250 [06:47<21:38,  1.33s/it]
Training 1/1 epoch (loss 2.6862):  22%|██▏       | 275/1250 [06:48<21:38,  1.33s/it]
Training 1/1 epoch (loss 2.6862):  22%|██▏       | 276/1250 [06:48<22:27,  1.38s/it]
Training 1/1 epoch (loss 2.5880):  22%|██▏       | 276/1250 [06:49<22:27,  1.38s/it]
Training 1/1 epoch (loss 2.5880):  22%|██▏       | 277/1250 [06:49<19:43,  1.22s/it]
Training 1/1 epoch (loss 2.7165):  22%|██▏       | 277/1250 [06:51<19:43,  1.22s/it]
Training 1/1 epoch (loss 2.7165):  22%|██▏       | 278/1250 [06:51<22:40,  1.40s/it]
Training 1/1 epoch (loss 2.7984):  22%|██▏       | 278/1250 [06:53<22:40,  1.40s/it]
Training 1/1 epoch (loss 2.7984):  22%|██▏       | 279/1250 [06:53<26:01,  1.61s/it]
Training 1/1 epoch (loss 2.5445):  22%|██▏       | 279/1250 [06:53<26:01,  1.61s/it]
Training 1/1 epoch (loss 2.5445):  22%|██▏       | 280/1250 [06:53<20:34,  1.27s/it]
Training 1/1 epoch (loss 2.7172):  22%|██▏       | 280/1250 [06:55<20:34,  1.27s/it]
Training 1/1 epoch (loss 2.7172):  22%|██▏       | 281/1250 [06:55<22:12,  1.38s/it]
Training 1/1 epoch (loss 2.5838):  22%|██▏       | 281/1250 [06:57<22:12,  1.38s/it]
Training 1/1 epoch (loss 2.5838):  23%|██▎       | 282/1250 [06:57<24:52,  1.54s/it]
Training 1/1 epoch (loss 2.5956):  23%|██▎       | 282/1250 [06:58<24:52,  1.54s/it]
Training 1/1 epoch (loss 2.5956):  23%|██▎       | 283/1250 [06:58<20:31,  1.27s/it]
Training 1/1 epoch (loss 2.7378):  23%|██▎       | 283/1250 [06:59<20:31,  1.27s/it]
Training 1/1 epoch (loss 2.7378):  23%|██▎       | 284/1250 [06:59<22:29,  1.40s/it]
Training 1/1 epoch (loss 2.6273):  23%|██▎       | 284/1250 [07:01<22:29,  1.40s/it]
Training 1/1 epoch (loss 2.6273):  23%|██▎       | 285/1250 [07:01<23:03,  1.43s/it]
Training 1/1 epoch (loss 2.4468):  23%|██▎       | 285/1250 [07:02<23:03,  1.43s/it]
Training 1/1 epoch (loss 2.4468):  23%|██▎       | 286/1250 [07:02<21:48,  1.36s/it]
Training 1/1 epoch (loss 2.5782):  23%|██▎       | 286/1250 [07:04<21:48,  1.36s/it]
Training 1/1 epoch (loss 2.5782):  23%|██▎       | 287/1250 [07:04<22:53,  1.43s/it]
Training 1/1 epoch (loss 2.6086):  23%|██▎       | 287/1250 [07:05<22:53,  1.43s/it]
Training 1/1 epoch (loss 2.6086):  23%|██▎       | 288/1250 [07:05<23:59,  1.50s/it]
Training 1/1 epoch (loss 2.5192):  23%|██▎       | 288/1250 [07:07<23:59,  1.50s/it]
Training 1/1 epoch (loss 2.5192):  23%|██▎       | 289/1250 [07:07<23:46,  1.48s/it]
Training 1/1 epoch (loss 2.4951):  23%|██▎       | 289/1250 [07:09<23:46,  1.48s/it]
Training 1/1 epoch (loss 2.4951):  23%|██▎       | 290/1250 [07:09<28:13,  1.76s/it]
Training 1/1 epoch (loss 2.5562):  23%|██▎       | 290/1250 [07:10<28:13,  1.76s/it]
Training 1/1 epoch (loss 2.5562):  23%|██▎       | 291/1250 [07:10<24:00,  1.50s/it]
Training 1/1 epoch (loss 2.7603):  23%|██▎       | 291/1250 [07:12<24:00,  1.50s/it]
Training 1/1 epoch (loss 2.7603):  23%|██▎       | 292/1250 [07:12<25:48,  1.62s/it]
Training 1/1 epoch (loss 2.7137):  23%|██▎       | 292/1250 [07:13<25:48,  1.62s/it]
Training 1/1 epoch (loss 2.7137):  23%|██▎       | 293/1250 [07:13<24:19,  1.53s/it]
Training 1/1 epoch (loss 2.5779):  23%|██▎       | 293/1250 [07:14<24:19,  1.53s/it]
Training 1/1 epoch (loss 2.5779):  24%|██▎       | 294/1250 [07:14<19:34,  1.23s/it]
Training 1/1 epoch (loss 2.5600):  24%|██▎       | 294/1250 [07:16<19:34,  1.23s/it]
Training 1/1 epoch (loss 2.5600):  24%|██▎       | 295/1250 [07:16<22:56,  1.44s/it]
Training 1/1 epoch (loss 2.6078):  24%|██▎       | 295/1250 [07:18<22:56,  1.44s/it]
Training 1/1 epoch (loss 2.6078):  24%|██▎       | 296/1250 [07:18<25:20,  1.59s/it]
Training 1/1 epoch (loss 2.5779):  24%|██▎       | 296/1250 [07:19<25:20,  1.59s/it]
Training 1/1 epoch (loss 2.5779):  24%|██▍       | 297/1250 [07:19<24:04,  1.52s/it]
Training 1/1 epoch (loss 2.6552):  24%|██▍       | 297/1250 [07:21<24:04,  1.52s/it]
Training 1/1 epoch (loss 2.6552):  24%|██▍       | 298/1250 [07:21<24:55,  1.57s/it]
Training 1/1 epoch (loss 2.5353):  24%|██▍       | 298/1250 [07:22<24:55,  1.57s/it]
Training 1/1 epoch (loss 2.5353):  24%|██▍       | 299/1250 [07:22<21:09,  1.33s/it]
Training 1/1 epoch (loss 2.6761):  24%|██▍       | 299/1250 [07:23<21:09,  1.33s/it]
Training 1/1 epoch (loss 2.6761):  24%|██▍       | 300/1250 [07:23<21:01,  1.33s/it]
Training 1/1 epoch (loss 2.5656):  24%|██▍       | 300/1250 [07:24<21:01,  1.33s/it]
Training 1/1 epoch (loss 2.5656):  24%|██▍       | 301/1250 [07:24<21:38,  1.37s/it]
Training 1/1 epoch (loss 2.4238):  24%|██▍       | 301/1250 [07:25<21:38,  1.37s/it]
Training 1/1 epoch (loss 2.4238):  24%|██▍       | 302/1250 [07:25<17:27,  1.11s/it]
Training 1/1 epoch (loss 2.3293):  24%|██▍       | 302/1250 [07:27<17:27,  1.11s/it]
Training 1/1 epoch (loss 2.3293):  24%|██▍       | 303/1250 [07:27<23:31,  1.49s/it]
Training 1/1 epoch (loss 2.7249):  24%|██▍       | 303/1250 [07:29<23:31,  1.49s/it]
Training 1/1 epoch (loss 2.7249):  24%|██▍       | 304/1250 [07:29<27:20,  1.73s/it]
Training 1/1 epoch (loss 2.7654):  24%|██▍       | 304/1250 [07:31<27:20,  1.73s/it]
Training 1/1 epoch (loss 2.7654):  24%|██▍       | 305/1250 [07:31<24:43,  1.57s/it]
Training 1/1 epoch (loss 2.7577):  24%|██▍       | 305/1250 [07:33<24:43,  1.57s/it]
Training 1/1 epoch (loss 2.7577):  24%|██▍       | 306/1250 [07:33<29:09,  1.85s/it]
Training 1/1 epoch (loss 2.6189):  24%|██▍       | 306/1250 [07:35<29:09,  1.85s/it]
Training 1/1 epoch (loss 2.6189):  25%|██▍       | 307/1250 [07:35<27:41,  1.76s/it]
Training 1/1 epoch (loss 2.5382):  25%|██▍       | 307/1250 [07:36<27:41,  1.76s/it]
Training 1/1 epoch (loss 2.5382):  25%|██▍       | 308/1250 [07:36<26:11,  1.67s/it]
Training 1/1 epoch (loss 2.5121):  25%|██▍       | 308/1250 [07:38<26:11,  1.67s/it]
Training 1/1 epoch (loss 2.5121):  25%|██▍       | 309/1250 [07:38<26:33,  1.69s/it]
Training 1/1 epoch (loss 2.5264):  25%|██▍       | 309/1250 [07:39<26:33,  1.69s/it]
Training 1/1 epoch (loss 2.5264):  25%|██▍       | 310/1250 [07:39<22:56,  1.46s/it]
Training 1/1 epoch (loss 2.6667):  25%|██▍       | 310/1250 [07:41<22:56,  1.46s/it]
Training 1/1 epoch (loss 2.6667):  25%|██▍       | 311/1250 [07:41<24:36,  1.57s/it]
Training 1/1 epoch (loss 2.4802):  25%|██▍       | 311/1250 [07:43<24:36,  1.57s/it]
Training 1/1 epoch (loss 2.4802):  25%|██▍       | 312/1250 [07:43<27:37,  1.77s/it]
Training 1/1 epoch (loss 2.3413):  25%|██▍       | 312/1250 [07:44<27:37,  1.77s/it]
Training 1/1 epoch (loss 2.3413):  25%|██▌       | 313/1250 [07:44<22:13,  1.42s/it]
Training 1/1 epoch (loss 2.5338):  25%|██▌       | 313/1250 [07:45<22:13,  1.42s/it]
Training 1/1 epoch (loss 2.5338):  25%|██▌       | 314/1250 [07:45<22:20,  1.43s/it]
Training 1/1 epoch (loss 2.6837):  25%|██▌       | 314/1250 [07:46<22:20,  1.43s/it]
Training 1/1 epoch (loss 2.6837):  25%|██▌       | 315/1250 [07:46<20:56,  1.34s/it]
Training 1/1 epoch (loss 2.5422):  25%|██▌       | 315/1250 [07:47<20:56,  1.34s/it]
Training 1/1 epoch (loss 2.5422):  25%|██▌       | 316/1250 [07:47<17:21,  1.12s/it]
Training 1/1 epoch (loss 2.6326):  25%|██▌       | 316/1250 [07:49<17:21,  1.12s/it]
Training 1/1 epoch (loss 2.6326):  25%|██▌       | 317/1250 [07:49<21:11,  1.36s/it]
Training 1/1 epoch (loss 2.7725):  25%|██▌       | 317/1250 [07:50<21:11,  1.36s/it]
Training 1/1 epoch (loss 2.7725):  25%|██▌       | 318/1250 [07:50<22:23,  1.44s/it]
Training 1/1 epoch (loss 2.4994):  25%|██▌       | 318/1250 [07:51<22:23,  1.44s/it]
Training 1/1 epoch (loss 2.4994):  26%|██▌       | 319/1250 [07:51<19:00,  1.23s/it]
Training 1/1 epoch (loss 2.6697):  26%|██▌       | 319/1250 [07:53<19:00,  1.23s/it]
Training 1/1 epoch (loss 2.6697):  26%|██▌       | 320/1250 [07:53<24:49,  1.60s/it]
Training 1/1 epoch (loss 2.5395):  26%|██▌       | 320/1250 [07:55<24:49,  1.60s/it]
Training 1/1 epoch (loss 2.5395):  26%|██▌       | 321/1250 [07:55<23:37,  1.53s/it]
Training 1/1 epoch (loss 2.6640):  26%|██▌       | 321/1250 [07:56<23:37,  1.53s/it]
Training 1/1 epoch (loss 2.6640):  26%|██▌       | 322/1250 [07:56<21:38,  1.40s/it]
Training 1/1 epoch (loss 2.4870):  26%|██▌       | 322/1250 [07:58<21:38,  1.40s/it]
Training 1/1 epoch (loss 2.4870):  26%|██▌       | 323/1250 [07:58<24:05,  1.56s/it]
Training 1/1 epoch (loss 2.7707):  26%|██▌       | 323/1250 [07:59<24:05,  1.56s/it]
Training 1/1 epoch (loss 2.7707):  26%|██▌       | 324/1250 [07:59<20:04,  1.30s/it]
Training 1/1 epoch (loss 2.3809):  26%|██▌       | 324/1250 [08:00<20:04,  1.30s/it]
Training 1/1 epoch (loss 2.3809):  26%|██▌       | 325/1250 [08:00<20:13,  1.31s/it]
Training 1/1 epoch (loss 2.6545):  26%|██▌       | 325/1250 [08:01<20:13,  1.31s/it]
Training 1/1 epoch (loss 2.6545):  26%|██▌       | 326/1250 [08:01<20:10,  1.31s/it]
Training 1/1 epoch (loss 2.5101):  26%|██▌       | 326/1250 [08:02<20:10,  1.31s/it]
Training 1/1 epoch (loss 2.5101):  26%|██▌       | 327/1250 [08:02<17:25,  1.13s/it]
Training 1/1 epoch (loss 2.3084):  26%|██▌       | 327/1250 [08:04<17:25,  1.13s/it]
Training 1/1 epoch (loss 2.3084):  26%|██▌       | 328/1250 [08:04<21:04,  1.37s/it]
Training 1/1 epoch (loss 2.8567):  26%|██▌       | 328/1250 [08:05<21:04,  1.37s/it]
Training 1/1 epoch (loss 2.8567):  26%|██▋       | 329/1250 [08:05<22:22,  1.46s/it]
Training 1/1 epoch (loss 2.4954):  26%|██▋       | 329/1250 [08:06<22:22,  1.46s/it]
Training 1/1 epoch (loss 2.4954):  26%|██▋       | 330/1250 [08:06<19:41,  1.28s/it]
Training 1/1 epoch (loss 2.5785):  26%|██▋       | 330/1250 [08:08<19:41,  1.28s/it]
Training 1/1 epoch (loss 2.5785):  26%|██▋       | 331/1250 [08:08<19:02,  1.24s/it]
Training 1/1 epoch (loss 2.7224):  26%|██▋       | 331/1250 [08:09<19:02,  1.24s/it]
Training 1/1 epoch (loss 2.7224):  27%|██▋       | 332/1250 [08:09<18:13,  1.19s/it]
Training 1/1 epoch (loss 2.5375):  27%|██▋       | 332/1250 [08:10<18:13,  1.19s/it]
Training 1/1 epoch (loss 2.5375):  27%|██▋       | 333/1250 [08:10<19:48,  1.30s/it]
Training 1/1 epoch (loss 2.7098):  27%|██▋       | 333/1250 [08:11<19:48,  1.30s/it]
Training 1/1 epoch (loss 2.7098):  27%|██▋       | 334/1250 [08:11<20:07,  1.32s/it]
Training 1/1 epoch (loss 2.5793):  27%|██▋       | 334/1250 [08:12<20:07,  1.32s/it]
Training 1/1 epoch (loss 2.5793):  27%|██▋       | 335/1250 [08:12<16:49,  1.10s/it]
Training 1/1 epoch (loss 2.7352):  27%|██▋       | 335/1250 [08:15<16:49,  1.10s/it]
Training 1/1 epoch (loss 2.7352):  27%|██▋       | 336/1250 [08:15<24:28,  1.61s/it]
Training 1/1 epoch (loss 2.9033):  27%|██▋       | 336/1250 [08:17<24:28,  1.61s/it]
Training 1/1 epoch (loss 2.9033):  27%|██▋       | 337/1250 [08:17<26:59,  1.77s/it]
Training 1/1 epoch (loss 2.6548):  27%|██▋       | 337/1250 [08:18<26:59,  1.77s/it]
Training 1/1 epoch (loss 2.6548):  27%|██▋       | 338/1250 [08:18<21:12,  1.40s/it]
Training 1/1 epoch (loss 2.6761):  27%|██▋       | 338/1250 [08:19<21:12,  1.40s/it]
Training 1/1 epoch (loss 2.6761):  27%|██▋       | 339/1250 [08:19<23:39,  1.56s/it]
Training 1/1 epoch (loss 2.6127):  27%|██▋       | 339/1250 [08:22<23:39,  1.56s/it]
Training 1/1 epoch (loss 2.6127):  27%|██▋       | 340/1250 [08:22<27:18,  1.80s/it]
Training 1/1 epoch (loss 2.4530):  27%|██▋       | 340/1250 [08:23<27:18,  1.80s/it]
Training 1/1 epoch (loss 2.4530):  27%|██▋       | 341/1250 [08:23<22:23,  1.48s/it]
Training 1/1 epoch (loss 2.5442):  27%|██▋       | 341/1250 [08:24<22:23,  1.48s/it]
Training 1/1 epoch (loss 2.5442):  27%|██▋       | 342/1250 [08:24<21:29,  1.42s/it]
Training 1/1 epoch (loss 2.4876):  27%|██▋       | 342/1250 [08:25<21:29,  1.42s/it]
Training 1/1 epoch (loss 2.4876):  27%|██▋       | 343/1250 [08:25<21:10,  1.40s/it]
Training 1/1 epoch (loss 2.6410):  27%|██▋       | 343/1250 [08:26<21:10,  1.40s/it]
Training 1/1 epoch (loss 2.6410):  28%|██▊       | 344/1250 [08:26<17:27,  1.16s/it]
Training 1/1 epoch (loss 2.5860):  28%|██▊       | 344/1250 [08:28<17:27,  1.16s/it]
Training 1/1 epoch (loss 2.5860):  28%|██▊       | 345/1250 [08:28<22:28,  1.49s/it]
Training 1/1 epoch (loss 2.5541):  28%|██▊       | 345/1250 [08:30<22:28,  1.49s/it]
Training 1/1 epoch (loss 2.5541):  28%|██▊       | 346/1250 [08:30<22:55,  1.52s/it]
Training 1/1 epoch (loss 2.6330):  28%|██▊       | 346/1250 [08:30<22:55,  1.52s/it]
Training 1/1 epoch (loss 2.6330):  28%|██▊       | 347/1250 [08:30<19:15,  1.28s/it]
Training 1/1 epoch (loss 2.7124):  28%|██▊       | 347/1250 [08:32<19:15,  1.28s/it]
Training 1/1 epoch (loss 2.7124):  28%|██▊       | 348/1250 [08:32<20:38,  1.37s/it]
Training 1/1 epoch (loss 2.5615):  28%|██▊       | 348/1250 [08:34<20:38,  1.37s/it]
Training 1/1 epoch (loss 2.5615):  28%|██▊       | 349/1250 [08:34<24:11,  1.61s/it]
Training 1/1 epoch (loss 2.6647):  28%|██▊       | 349/1250 [08:35<24:11,  1.61s/it]
Training 1/1 epoch (loss 2.6647):  28%|██▊       | 350/1250 [08:35<20:26,  1.36s/it]
Training 1/1 epoch (loss 2.5803):  28%|██▊       | 350/1250 [08:37<20:26,  1.36s/it]
Training 1/1 epoch (loss 2.5803):  28%|██▊       | 351/1250 [08:37<22:13,  1.48s/it]
Training 1/1 epoch (loss 2.7046):  28%|██▊       | 351/1250 [08:38<22:13,  1.48s/it]
Training 1/1 epoch (loss 2.7046):  28%|██▊       | 352/1250 [08:38<21:52,  1.46s/it]
Training 1/1 epoch (loss 2.7857):  28%|██▊       | 352/1250 [08:40<21:52,  1.46s/it]
Training 1/1 epoch (loss 2.7857):  28%|██▊       | 353/1250 [08:40<22:34,  1.51s/it]
Training 1/1 epoch (loss 2.6357):  28%|██▊       | 353/1250 [08:42<22:34,  1.51s/it]
Training 1/1 epoch (loss 2.6357):  28%|██▊       | 354/1250 [08:42<24:15,  1.62s/it]
Training 1/1 epoch (loss 2.4520):  28%|██▊       | 354/1250 [08:43<24:15,  1.62s/it]
Training 1/1 epoch (loss 2.4520):  28%|██▊       | 355/1250 [08:43<21:38,  1.45s/it]
Training 1/1 epoch (loss 2.5976):  28%|██▊       | 355/1250 [08:44<21:38,  1.45s/it]
Training 1/1 epoch (loss 2.5976):  28%|██▊       | 356/1250 [08:44<21:54,  1.47s/it]
Training 1/1 epoch (loss 2.7423):  28%|██▊       | 356/1250 [08:46<21:54,  1.47s/it]
Training 1/1 epoch (loss 2.7423):  29%|██▊       | 357/1250 [08:46<22:32,  1.52s/it]
Training 1/1 epoch (loss 2.7117):  29%|██▊       | 357/1250 [08:46<22:32,  1.52s/it]
Training 1/1 epoch (loss 2.7117):  29%|██▊       | 358/1250 [08:46<17:53,  1.20s/it]
Training 1/1 epoch (loss 2.6029):  29%|██▊       | 358/1250 [08:48<17:53,  1.20s/it]
Training 1/1 epoch (loss 2.6029):  29%|██▊       | 359/1250 [08:48<20:32,  1.38s/it]
Training 1/1 epoch (loss 2.4152):  29%|██▊       | 359/1250 [08:50<20:32,  1.38s/it]
Training 1/1 epoch (loss 2.4152):  29%|██▉       | 360/1250 [08:50<20:50,  1.40s/it]
Training 1/1 epoch (loss 2.5098):  29%|██▉       | 360/1250 [08:50<20:50,  1.40s/it]
Training 1/1 epoch (loss 2.5098):  29%|██▉       | 361/1250 [08:50<17:53,  1.21s/it]
Training 1/1 epoch (loss 2.6053):  29%|██▉       | 361/1250 [08:52<17:53,  1.21s/it]
Training 1/1 epoch (loss 2.6053):  29%|██▉       | 362/1250 [08:52<22:10,  1.50s/it]
Training 1/1 epoch (loss 2.6451):  29%|██▉       | 362/1250 [08:54<22:10,  1.50s/it]
Training 1/1 epoch (loss 2.6451):  29%|██▉       | 363/1250 [08:54<21:41,  1.47s/it]
Training 1/1 epoch (loss 2.7097):  29%|██▉       | 363/1250 [08:55<21:41,  1.47s/it]
Training 1/1 epoch (loss 2.7097):  29%|██▉       | 364/1250 [08:55<18:39,  1.26s/it]
Training 1/1 epoch (loss 2.5016):  29%|██▉       | 364/1250 [08:57<18:39,  1.26s/it]
Training 1/1 epoch (loss 2.5016):  29%|██▉       | 365/1250 [08:57<22:17,  1.51s/it]
Training 1/1 epoch (loss 2.3725):  29%|██▉       | 365/1250 [08:58<22:17,  1.51s/it]
Training 1/1 epoch (loss 2.3725):  29%|██▉       | 366/1250 [08:58<23:26,  1.59s/it]
Training 1/1 epoch (loss 2.4695):  29%|██▉       | 366/1250 [08:59<23:26,  1.59s/it]
Training 1/1 epoch (loss 2.4695):  29%|██▉       | 367/1250 [08:59<19:51,  1.35s/it]
Training 1/1 epoch (loss 2.5351):  29%|██▉       | 367/1250 [09:01<19:51,  1.35s/it]
Training 1/1 epoch (loss 2.5351):  29%|██▉       | 368/1250 [09:01<19:45,  1.34s/it]
Training 1/1 epoch (loss 2.6431):  29%|██▉       | 368/1250 [09:02<19:45,  1.34s/it]
Training 1/1 epoch (loss 2.6431):  30%|██▉       | 369/1250 [09:02<18:02,  1.23s/it]
Training 1/1 epoch (loss 2.7314):  30%|██▉       | 369/1250 [09:04<18:02,  1.23s/it]
Training 1/1 epoch (loss 2.7314):  30%|██▉       | 370/1250 [09:04<22:41,  1.55s/it]
Training 1/1 epoch (loss 2.5126):  30%|██▉       | 370/1250 [09:06<22:41,  1.55s/it]
Training 1/1 epoch (loss 2.5126):  30%|██▉       | 371/1250 [09:06<24:31,  1.67s/it]
Training 1/1 epoch (loss 2.5577):  30%|██▉       | 371/1250 [09:07<24:31,  1.67s/it]
Training 1/1 epoch (loss 2.5577):  30%|██▉       | 372/1250 [09:07<20:49,  1.42s/it]
Training 1/1 epoch (loss 2.5325):  30%|██▉       | 372/1250 [09:08<20:49,  1.42s/it]
Training 1/1 epoch (loss 2.5325):  30%|██▉       | 373/1250 [09:08<20:39,  1.41s/it]
Training 1/1 epoch (loss 2.3176):  30%|██▉       | 373/1250 [09:11<20:39,  1.41s/it]
Training 1/1 epoch (loss 2.3176):  30%|██▉       | 374/1250 [09:11<25:10,  1.72s/it]
Training 1/1 epoch (loss 2.6262):  30%|██▉       | 374/1250 [09:11<25:10,  1.72s/it]
Training 1/1 epoch (loss 2.6262):  30%|███       | 375/1250 [09:11<20:00,  1.37s/it]
Training 1/1 epoch (loss 2.7935):  30%|███       | 375/1250 [09:14<20:00,  1.37s/it]
Training 1/1 epoch (loss 2.7935):  30%|███       | 376/1250 [09:14<25:21,  1.74s/it]
Training 1/1 epoch (loss 2.7203):  30%|███       | 376/1250 [09:15<25:21,  1.74s/it]
Training 1/1 epoch (loss 2.7203):  30%|███       | 377/1250 [09:15<23:34,  1.62s/it]
Training 1/1 epoch (loss 2.5729):  30%|███       | 377/1250 [09:16<23:34,  1.62s/it]
Training 1/1 epoch (loss 2.5729):  30%|███       | 378/1250 [09:16<21:32,  1.48s/it]
Training 1/1 epoch (loss 2.4096):  30%|███       | 378/1250 [09:18<21:32,  1.48s/it]
Training 1/1 epoch (loss 2.4096):  30%|███       | 379/1250 [09:18<23:12,  1.60s/it]
Training 1/1 epoch (loss 2.6214):  30%|███       | 379/1250 [09:19<23:12,  1.60s/it]
Training 1/1 epoch (loss 2.6214):  30%|███       | 380/1250 [09:19<20:59,  1.45s/it]
Training 1/1 epoch (loss 2.6523):  30%|███       | 380/1250 [09:21<20:59,  1.45s/it]
Training 1/1 epoch (loss 2.6523):  30%|███       | 381/1250 [09:21<20:43,  1.43s/it]
Training 1/1 epoch (loss 2.7056):  30%|███       | 381/1250 [09:22<20:43,  1.43s/it]
Training 1/1 epoch (loss 2.7056):  31%|███       | 382/1250 [09:22<20:32,  1.42s/it]
Training 1/1 epoch (loss 2.5801):  31%|███       | 382/1250 [09:23<20:32,  1.42s/it]
Training 1/1 epoch (loss 2.5801):  31%|███       | 383/1250 [09:23<17:36,  1.22s/it]
Training 1/1 epoch (loss 2.4524):  31%|███       | 383/1250 [09:25<17:36,  1.22s/it]
Training 1/1 epoch (loss 2.4524):  31%|███       | 384/1250 [09:25<23:37,  1.64s/it]
Training 1/1 epoch (loss 2.5614):  31%|███       | 384/1250 [09:27<23:37,  1.64s/it]
Training 1/1 epoch (loss 2.5614):  31%|███       | 385/1250 [09:27<23:10,  1.61s/it]
Training 1/1 epoch (loss 2.4120):  31%|███       | 385/1250 [09:28<23:10,  1.61s/it]
Training 1/1 epoch (loss 2.4120):  31%|███       | 386/1250 [09:28<20:31,  1.43s/it]
Training 1/1 epoch (loss 2.4607):  31%|███       | 386/1250 [09:29<20:31,  1.43s/it]
Training 1/1 epoch (loss 2.4607):  31%|███       | 387/1250 [09:29<21:08,  1.47s/it]
Training 1/1 epoch (loss 2.5548):  31%|███       | 387/1250 [09:32<21:08,  1.47s/it]
Training 1/1 epoch (loss 2.5548):  31%|███       | 388/1250 [09:32<25:35,  1.78s/it]
Training 1/1 epoch (loss 2.6726):  31%|███       | 388/1250 [09:33<25:35,  1.78s/it]
Training 1/1 epoch (loss 2.6726):  31%|███       | 389/1250 [09:33<21:37,  1.51s/it]
Training 1/1 epoch (loss 2.5596):  31%|███       | 389/1250 [09:34<21:37,  1.51s/it]
Training 1/1 epoch (loss 2.5596):  31%|███       | 390/1250 [09:34<22:12,  1.55s/it]
Training 1/1 epoch (loss 2.7853):  31%|███       | 390/1250 [09:36<22:12,  1.55s/it]
Training 1/1 epoch (loss 2.7853):  31%|███▏      | 391/1250 [09:36<22:01,  1.54s/it]
Training 1/1 epoch (loss 2.6251):  31%|███▏      | 391/1250 [09:38<22:01,  1.54s/it]
Training 1/1 epoch (loss 2.6251):  31%|███▏      | 392/1250 [09:38<25:42,  1.80s/it]
Training 1/1 epoch (loss 2.6902):  31%|███▏      | 392/1250 [09:40<25:42,  1.80s/it]
Training 1/1 epoch (loss 2.6902):  31%|███▏      | 393/1250 [09:40<23:59,  1.68s/it]
Training 1/1 epoch (loss 2.4547):  31%|███▏      | 393/1250 [09:40<23:59,  1.68s/it]
Training 1/1 epoch (loss 2.4547):  32%|███▏      | 394/1250 [09:40<18:51,  1.32s/it]
Training 1/1 epoch (loss 2.3229):  32%|███▏      | 394/1250 [09:42<18:51,  1.32s/it]
Training 1/1 epoch (loss 2.3229):  32%|███▏      | 395/1250 [09:42<20:20,  1.43s/it]
Training 1/1 epoch (loss 2.5291):  32%|███▏      | 395/1250 [09:44<20:20,  1.43s/it]
Training 1/1 epoch (loss 2.5291):  32%|███▏      | 396/1250 [09:44<24:04,  1.69s/it]
Training 1/1 epoch (loss 2.3587):  32%|███▏      | 396/1250 [09:45<24:04,  1.69s/it]
Training 1/1 epoch (loss 2.3587):  32%|███▏      | 397/1250 [09:45<20:53,  1.47s/it]
Training 1/1 epoch (loss 2.3998):  32%|███▏      | 397/1250 [09:47<20:53,  1.47s/it]
Training 1/1 epoch (loss 2.3998):  32%|███▏      | 398/1250 [09:47<23:49,  1.68s/it]
Training 1/1 epoch (loss 2.6377):  32%|███▏      | 398/1250 [09:48<23:49,  1.68s/it]
Training 1/1 epoch (loss 2.6377):  32%|███▏      | 399/1250 [09:48<20:42,  1.46s/it]
Training 1/1 epoch (loss 2.6170):  32%|███▏      | 399/1250 [09:49<20:42,  1.46s/it]
Training 1/1 epoch (loss 2.6170):  32%|███▏      | 400/1250 [09:49<19:29,  1.38s/it]
Training 1/1 epoch (loss 2.4228):  32%|███▏      | 400/1250 [09:51<19:29,  1.38s/it]
Training 1/1 epoch (loss 2.4228):  32%|███▏      | 401/1250 [09:51<18:52,  1.33s/it]
Training 1/1 epoch (loss 2.7312):  32%|███▏      | 401/1250 [09:52<18:52,  1.33s/it]
Training 1/1 epoch (loss 2.7312):  32%|███▏      | 402/1250 [09:52<18:18,  1.30s/it]
Training 1/1 epoch (loss 2.6724):  32%|███▏      | 402/1250 [09:53<18:18,  1.30s/it]
Training 1/1 epoch (loss 2.6724):  32%|███▏      | 403/1250 [09:53<16:53,  1.20s/it]
Training 1/1 epoch (loss 2.4254):  32%|███▏      | 403/1250 [09:55<16:53,  1.20s/it]
Training 1/1 epoch (loss 2.4254):  32%|███▏      | 404/1250 [09:55<19:40,  1.40s/it]
Training 1/1 epoch (loss 2.5950):  32%|███▏      | 404/1250 [09:55<19:40,  1.40s/it]
Training 1/1 epoch (loss 2.5950):  32%|███▏      | 405/1250 [09:55<16:29,  1.17s/it]
Training 1/1 epoch (loss 2.5874):  32%|███▏      | 405/1250 [09:57<16:29,  1.17s/it]
Training 1/1 epoch (loss 2.5874):  32%|███▏      | 406/1250 [09:57<18:54,  1.34s/it]
Training 1/1 epoch (loss 2.4829):  32%|███▏      | 406/1250 [09:59<18:54,  1.34s/it]
Training 1/1 epoch (loss 2.4829):  33%|███▎      | 407/1250 [09:59<22:34,  1.61s/it]
Training 1/1 epoch (loss 2.6153):  33%|███▎      | 407/1250 [10:00<22:34,  1.61s/it]
Training 1/1 epoch (loss 2.6153):  33%|███▎      | 408/1250 [10:00<19:08,  1.36s/it]
Training 1/1 epoch (loss 2.7196):  33%|███▎      | 408/1250 [10:02<19:08,  1.36s/it]
Training 1/1 epoch (loss 2.7196):  33%|███▎      | 409/1250 [10:02<19:12,  1.37s/it]
Training 1/1 epoch (loss 2.7338):  33%|███▎      | 409/1250 [10:03<19:12,  1.37s/it]
Training 1/1 epoch (loss 2.7338):  33%|███▎      | 410/1250 [10:03<19:02,  1.36s/it]
Training 1/1 epoch (loss 2.5394):  33%|███▎      | 410/1250 [10:04<19:02,  1.36s/it]
Training 1/1 epoch (loss 2.5394):  33%|███▎      | 411/1250 [10:04<16:05,  1.15s/it]
Training 1/1 epoch (loss 2.3797):  33%|███▎      | 411/1250 [10:06<16:05,  1.15s/it]
Training 1/1 epoch (loss 2.3797):  33%|███▎      | 412/1250 [10:06<20:35,  1.47s/it]
Training 1/1 epoch (loss 2.5171):  33%|███▎      | 412/1250 [10:08<20:35,  1.47s/it]
Training 1/1 epoch (loss 2.5171):  33%|███▎      | 413/1250 [10:08<24:57,  1.79s/it]
Training 1/1 epoch (loss 2.6820):  33%|███▎      | 413/1250 [10:09<24:57,  1.79s/it]
Training 1/1 epoch (loss 2.6820):  33%|███▎      | 414/1250 [10:09<19:18,  1.39s/it]
Training 1/1 epoch (loss 2.5399):  33%|███▎      | 414/1250 [10:10<19:18,  1.39s/it]
Training 1/1 epoch (loss 2.5399):  33%|███▎      | 415/1250 [10:10<20:46,  1.49s/it]
Training 1/1 epoch (loss 2.6981):  33%|███▎      | 415/1250 [10:13<20:46,  1.49s/it]
Training 1/1 epoch (loss 2.6981):  33%|███▎      | 416/1250 [10:13<23:40,  1.70s/it]
Training 1/1 epoch (loss 2.7274):  33%|███▎      | 416/1250 [10:14<23:40,  1.70s/it]
Training 1/1 epoch (loss 2.7274):  33%|███▎      | 417/1250 [10:14<21:45,  1.57s/it]
Training 1/1 epoch (loss 2.6189):  33%|███▎      | 417/1250 [10:16<21:45,  1.57s/it]
Training 1/1 epoch (loss 2.6189):  33%|███▎      | 418/1250 [10:16<22:36,  1.63s/it]
Training 1/1 epoch (loss 2.7220):  33%|███▎      | 418/1250 [10:17<22:36,  1.63s/it]
Training 1/1 epoch (loss 2.7220):  34%|███▎      | 419/1250 [10:17<19:33,  1.41s/it]
Training 1/1 epoch (loss 2.6373):  34%|███▎      | 419/1250 [10:18<19:33,  1.41s/it]
Training 1/1 epoch (loss 2.6373):  34%|███▎      | 420/1250 [10:18<20:26,  1.48s/it]
Training 1/1 epoch (loss 2.5842):  34%|███▎      | 420/1250 [10:20<20:26,  1.48s/it]
Training 1/1 epoch (loss 2.5842):  34%|███▎      | 421/1250 [10:20<22:33,  1.63s/it]
Training 1/1 epoch (loss 2.5287):  34%|███▎      | 421/1250 [10:21<22:33,  1.63s/it]
Training 1/1 epoch (loss 2.5287):  34%|███▍      | 422/1250 [10:21<18:09,  1.32s/it]
Training 1/1 epoch (loss 2.5558):  34%|███▍      | 422/1250 [10:23<18:09,  1.32s/it]
Training 1/1 epoch (loss 2.5558):  34%|███▍      | 423/1250 [10:23<22:31,  1.63s/it]
Training 1/1 epoch (loss 2.5308):  34%|███▍      | 423/1250 [10:26<22:31,  1.63s/it]
Training 1/1 epoch (loss 2.5308):  34%|███▍      | 424/1250 [10:26<25:34,  1.86s/it]
Training 1/1 epoch (loss 2.7111):  34%|███▍      | 424/1250 [10:26<25:34,  1.86s/it]
Training 1/1 epoch (loss 2.7111):  34%|███▍      | 425/1250 [10:26<21:23,  1.56s/it]
Training 1/1 epoch (loss 2.7780):  34%|███▍      | 425/1250 [10:28<21:23,  1.56s/it]
Training 1/1 epoch (loss 2.7780):  34%|███▍      | 426/1250 [10:28<22:20,  1.63s/it]
Training 1/1 epoch (loss 2.5859):  34%|███▍      | 426/1250 [10:30<22:20,  1.63s/it]
Training 1/1 epoch (loss 2.5859):  34%|███▍      | 427/1250 [10:30<21:48,  1.59s/it]
Training 1/1 epoch (loss 2.5363):  34%|███▍      | 427/1250 [10:30<21:48,  1.59s/it]
Training 1/1 epoch (loss 2.5363):  34%|███▍      | 428/1250 [10:30<18:31,  1.35s/it]
Training 1/1 epoch (loss 2.5184):  34%|███▍      | 428/1250 [10:32<18:31,  1.35s/it]
Training 1/1 epoch (loss 2.5184):  34%|███▍      | 429/1250 [10:32<20:54,  1.53s/it]
Training 1/1 epoch (loss 2.4157):  34%|███▍      | 429/1250 [10:34<20:54,  1.53s/it]
Training 1/1 epoch (loss 2.4157):  34%|███▍      | 430/1250 [10:34<20:18,  1.49s/it]
Training 1/1 epoch (loss 2.5697):  34%|███▍      | 430/1250 [10:35<20:18,  1.49s/it]
Training 1/1 epoch (loss 2.5697):  34%|███▍      | 431/1250 [10:35<19:41,  1.44s/it]
Training 1/1 epoch (loss 2.6282):  34%|███▍      | 431/1250 [10:37<19:41,  1.44s/it]
Training 1/1 epoch (loss 2.6282):  35%|███▍      | 432/1250 [10:37<22:55,  1.68s/it]
Training 1/1 epoch (loss 2.5365):  35%|███▍      | 432/1250 [10:38<22:55,  1.68s/it]
Training 1/1 epoch (loss 2.5365):  35%|███▍      | 433/1250 [10:38<18:47,  1.38s/it]
Training 1/1 epoch (loss 2.6741):  35%|███▍      | 433/1250 [10:40<18:47,  1.38s/it]
Training 1/1 epoch (loss 2.6741):  35%|███▍      | 434/1250 [10:40<20:43,  1.52s/it]
Training 1/1 epoch (loss 2.6643):  35%|███▍      | 434/1250 [10:41<20:43,  1.52s/it]
Training 1/1 epoch (loss 2.6643):  35%|███▍      | 435/1250 [10:41<18:45,  1.38s/it]
Training 1/1 epoch (loss 2.7269):  35%|███▍      | 435/1250 [10:41<18:45,  1.38s/it]
Training 1/1 epoch (loss 2.7269):  35%|███▍      | 436/1250 [10:41<15:07,  1.11s/it]
Training 1/1 epoch (loss 2.5342):  35%|███▍      | 436/1250 [10:43<15:07,  1.11s/it]
Training 1/1 epoch (loss 2.5342):  35%|███▍      | 437/1250 [10:43<18:50,  1.39s/it]
Training 1/1 epoch (loss 2.5106):  35%|███▍      | 437/1250 [10:45<18:50,  1.39s/it]
Training 1/1 epoch (loss 2.5106):  35%|███▌      | 438/1250 [10:45<19:04,  1.41s/it]
Training 1/1 epoch (loss 2.6423):  35%|███▌      | 438/1250 [10:46<19:04,  1.41s/it]
Training 1/1 epoch (loss 2.6423):  35%|███▌      | 439/1250 [10:46<16:15,  1.20s/it]
Training 1/1 epoch (loss 2.9034):  35%|███▌      | 439/1250 [10:48<16:15,  1.20s/it]
Training 1/1 epoch (loss 2.9034):  35%|███▌      | 440/1250 [10:48<19:55,  1.48s/it]
Training 1/1 epoch (loss 2.4833):  35%|███▌      | 440/1250 [10:49<19:55,  1.48s/it]
Training 1/1 epoch (loss 2.4833):  35%|███▌      | 441/1250 [10:49<19:51,  1.47s/it]
Training 1/1 epoch (loss 2.5617):  35%|███▌      | 441/1250 [10:51<19:51,  1.47s/it]
Training 1/1 epoch (loss 2.5617):  35%|███▌      | 442/1250 [10:51<21:24,  1.59s/it]
Training 1/1 epoch (loss 2.5330):  35%|███▌      | 442/1250 [10:53<21:24,  1.59s/it]
Training 1/1 epoch (loss 2.5330):  35%|███▌      | 443/1250 [10:53<22:00,  1.64s/it]
Training 1/1 epoch (loss 2.7666):  35%|███▌      | 443/1250 [10:53<22:00,  1.64s/it]
Training 1/1 epoch (loss 2.7666):  36%|███▌      | 444/1250 [10:53<17:09,  1.28s/it]
Training 1/1 epoch (loss 2.5395):  36%|███▌      | 444/1250 [10:56<17:09,  1.28s/it]
Training 1/1 epoch (loss 2.5395):  36%|███▌      | 445/1250 [10:56<21:28,  1.60s/it]
Training 1/1 epoch (loss 2.4934):  36%|███▌      | 445/1250 [10:57<21:28,  1.60s/it]
Training 1/1 epoch (loss 2.4934):  36%|███▌      | 446/1250 [10:57<21:58,  1.64s/it]
Training 1/1 epoch (loss 2.5582):  36%|███▌      | 446/1250 [10:58<21:58,  1.64s/it]
Training 1/1 epoch (loss 2.5582):  36%|███▌      | 447/1250 [10:58<18:07,  1.35s/it]
Training 1/1 epoch (loss 2.4085):  36%|███▌      | 447/1250 [11:00<18:07,  1.35s/it]
Training 1/1 epoch (loss 2.4085):  36%|███▌      | 448/1250 [11:00<20:40,  1.55s/it]
Training 1/1 epoch (loss 2.6301):  36%|███▌      | 448/1250 [11:01<20:40,  1.55s/it]
Training 1/1 epoch (loss 2.6301):  36%|███▌      | 449/1250 [11:01<18:55,  1.42s/it]
Training 1/1 epoch (loss 2.5570):  36%|███▌      | 449/1250 [11:03<18:55,  1.42s/it]
Training 1/1 epoch (loss 2.5570):  36%|███▌      | 450/1250 [11:03<20:16,  1.52s/it]
Training 1/1 epoch (loss 2.5005):  36%|███▌      | 450/1250 [11:05<20:16,  1.52s/it]
Training 1/1 epoch (loss 2.5005):  36%|███▌      | 451/1250 [11:05<24:09,  1.81s/it]
Training 1/1 epoch (loss 2.5036):  36%|███▌      | 451/1250 [11:06<24:09,  1.81s/it]
Training 1/1 epoch (loss 2.5036):  36%|███▌      | 452/1250 [11:06<20:30,  1.54s/it]
Training 1/1 epoch (loss 2.6251):  36%|███▌      | 452/1250 [11:08<20:30,  1.54s/it]
Training 1/1 epoch (loss 2.6251):  36%|███▌      | 453/1250 [11:08<22:32,  1.70s/it]
Training 1/1 epoch (loss 2.6079):  36%|███▌      | 453/1250 [11:11<22:32,  1.70s/it]
Training 1/1 epoch (loss 2.6079):  36%|███▋      | 454/1250 [11:11<25:38,  1.93s/it]
Training 1/1 epoch (loss 2.5340):  36%|███▋      | 454/1250 [11:12<25:38,  1.93s/it]
Training 1/1 epoch (loss 2.5340):  36%|███▋      | 455/1250 [11:12<20:20,  1.54s/it]
Training 1/1 epoch (loss 2.7243):  36%|███▋      | 455/1250 [11:13<20:20,  1.54s/it]
Training 1/1 epoch (loss 2.7243):  36%|███▋      | 456/1250 [11:13<22:01,  1.66s/it]
Training 1/1 epoch (loss 2.7251):  36%|███▋      | 456/1250 [11:15<22:01,  1.66s/it]
Training 1/1 epoch (loss 2.7251):  37%|███▋      | 457/1250 [11:15<22:47,  1.72s/it]
Training 1/1 epoch (loss 2.5736):  37%|███▋      | 457/1250 [11:17<22:47,  1.72s/it]
Training 1/1 epoch (loss 2.5736):  37%|███▋      | 458/1250 [11:17<21:59,  1.67s/it]
Training 1/1 epoch (loss 2.8168):  37%|███▋      | 458/1250 [11:18<21:59,  1.67s/it]
Training 1/1 epoch (loss 2.8168):  37%|███▋      | 459/1250 [11:18<19:01,  1.44s/it]
Training 1/1 epoch (loss 2.6727):  37%|███▋      | 459/1250 [11:19<19:01,  1.44s/it]
Training 1/1 epoch (loss 2.6727):  37%|███▋      | 460/1250 [11:19<17:49,  1.35s/it]
Training 1/1 epoch (loss 2.4602):  37%|███▋      | 460/1250 [11:20<17:49,  1.35s/it]
Training 1/1 epoch (loss 2.4602):  37%|███▋      | 461/1250 [11:20<17:24,  1.32s/it]
Training 1/1 epoch (loss 2.5269):  37%|███▋      | 461/1250 [11:21<17:24,  1.32s/it]
Training 1/1 epoch (loss 2.5269):  37%|███▋      | 462/1250 [11:21<16:17,  1.24s/it]
Training 1/1 epoch (loss 2.6007):  37%|███▋      | 462/1250 [11:23<16:17,  1.24s/it]
Training 1/1 epoch (loss 2.6007):  37%|███▋      | 463/1250 [11:23<16:50,  1.28s/it]
Training 1/1 epoch (loss 2.4682):  37%|███▋      | 463/1250 [11:24<16:50,  1.28s/it]
Training 1/1 epoch (loss 2.4682):  37%|███▋      | 464/1250 [11:24<16:47,  1.28s/it]
Training 1/1 epoch (loss 2.3068):  37%|███▋      | 464/1250 [11:26<16:47,  1.28s/it]
Training 1/1 epoch (loss 2.3068):  37%|███▋      | 465/1250 [11:26<20:47,  1.59s/it]
Training 1/1 epoch (loss 2.3991):  37%|███▋      | 465/1250 [11:27<20:47,  1.59s/it]
Training 1/1 epoch (loss 2.3991):  37%|███▋      | 466/1250 [11:27<17:23,  1.33s/it]
Training 1/1 epoch (loss 2.4429):  37%|███▋      | 466/1250 [11:29<17:23,  1.33s/it]
Training 1/1 epoch (loss 2.4429):  37%|███▋      | 467/1250 [11:29<19:38,  1.51s/it]
Training 1/1 epoch (loss 2.5941):  37%|███▋      | 467/1250 [11:31<19:38,  1.51s/it]
Training 1/1 epoch (loss 2.5941):  37%|███▋      | 468/1250 [11:31<20:27,  1.57s/it]
Training 1/1 epoch (loss 2.6405):  37%|███▋      | 468/1250 [11:31<20:27,  1.57s/it]
Training 1/1 epoch (loss 2.6405):  38%|███▊      | 469/1250 [11:31<16:24,  1.26s/it]
Training 1/1 epoch (loss 2.6718):  38%|███▊      | 469/1250 [11:32<16:24,  1.26s/it]
Training 1/1 epoch (loss 2.6718):  38%|███▊      | 470/1250 [11:32<16:37,  1.28s/it]
Training 1/1 epoch (loss 2.7111):  38%|███▊      | 470/1250 [11:34<16:37,  1.28s/it]
Training 1/1 epoch (loss 2.7111):  38%|███▊      | 471/1250 [11:34<18:31,  1.43s/it]
Training 1/1 epoch (loss 2.4984):  38%|███▊      | 471/1250 [11:35<18:31,  1.43s/it]
Training 1/1 epoch (loss 2.4984):  38%|███▊      | 472/1250 [11:35<17:03,  1.32s/it]
Training 1/1 epoch (loss 2.5212):  38%|███▊      | 472/1250 [11:37<17:03,  1.32s/it]
Training 1/1 epoch (loss 2.5212):  38%|███▊      | 473/1250 [11:37<18:44,  1.45s/it]
Training 1/1 epoch (loss 2.4705):  38%|███▊      | 473/1250 [11:38<18:44,  1.45s/it]
Training 1/1 epoch (loss 2.4705):  38%|███▊      | 474/1250 [11:38<17:27,  1.35s/it]
Training 1/1 epoch (loss 2.5481):  38%|███▊      | 474/1250 [11:39<17:27,  1.35s/it]
Training 1/1 epoch (loss 2.5481):  38%|███▊      | 475/1250 [11:39<14:45,  1.14s/it]
Training 1/1 epoch (loss 2.6578):  38%|███▊      | 475/1250 [11:40<14:45,  1.14s/it]
Training 1/1 epoch (loss 2.6578):  38%|███▊      | 476/1250 [11:40<16:50,  1.31s/it]
Training 1/1 epoch (loss 2.6011):  38%|███▊      | 476/1250 [11:42<16:50,  1.31s/it]
Training 1/1 epoch (loss 2.6011):  38%|███▊      | 477/1250 [11:42<18:12,  1.41s/it]
Training 1/1 epoch (loss 2.7581):  38%|███▊      | 477/1250 [11:44<18:12,  1.41s/it]
Training 1/1 epoch (loss 2.7581):  38%|███▊      | 478/1250 [11:44<18:19,  1.42s/it]
Training 1/1 epoch (loss 2.5347):  38%|███▊      | 478/1250 [11:45<18:19,  1.42s/it]
Training 1/1 epoch (loss 2.5347):  38%|███▊      | 479/1250 [11:45<19:52,  1.55s/it]
Training 1/1 epoch (loss 2.5335):  38%|███▊      | 479/1250 [11:47<19:52,  1.55s/it]
Training 1/1 epoch (loss 2.5335):  38%|███▊      | 480/1250 [11:47<18:30,  1.44s/it]
Training 1/1 epoch (loss 2.5061):  38%|███▊      | 480/1250 [11:49<18:30,  1.44s/it]
Training 1/1 epoch (loss 2.5061):  38%|███▊      | 481/1250 [11:49<21:55,  1.71s/it]
Training 1/1 epoch (loss 2.7551):  38%|███▊      | 481/1250 [11:50<21:55,  1.71s/it]
Training 1/1 epoch (loss 2.7551):  39%|███▊      | 482/1250 [11:50<20:13,  1.58s/it]
Training 1/1 epoch (loss 2.5300):  39%|███▊      | 482/1250 [11:51<20:13,  1.58s/it]
Training 1/1 epoch (loss 2.5300):  39%|███▊      | 483/1250 [11:51<16:05,  1.26s/it]
Training 1/1 epoch (loss 2.4110):  39%|███▊      | 483/1250 [11:52<16:05,  1.26s/it]
Training 1/1 epoch (loss 2.4110):  39%|███▊      | 484/1250 [11:52<16:22,  1.28s/it]
Training 1/1 epoch (loss 2.4364):  39%|███▊      | 484/1250 [11:54<16:22,  1.28s/it]
Training 1/1 epoch (loss 2.4364):  39%|███▉      | 485/1250 [11:54<17:19,  1.36s/it]
Training 1/1 epoch (loss 2.6351):  39%|███▉      | 485/1250 [11:54<17:19,  1.36s/it]
Training 1/1 epoch (loss 2.6351):  39%|███▉      | 486/1250 [11:54<14:00,  1.10s/it]
Training 1/1 epoch (loss 2.5930):  39%|███▉      | 486/1250 [11:57<14:00,  1.10s/it]
Training 1/1 epoch (loss 2.5930):  39%|███▉      | 487/1250 [11:57<19:08,  1.51s/it]
Training 1/1 epoch (loss 2.4453):  39%|███▉      | 487/1250 [11:59<19:08,  1.51s/it]
Training 1/1 epoch (loss 2.4453):  39%|███▉      | 488/1250 [11:59<21:03,  1.66s/it]
Training 1/1 epoch (loss 2.5649):  39%|███▉      | 488/1250 [11:59<21:03,  1.66s/it]
Training 1/1 epoch (loss 2.5649):  39%|███▉      | 489/1250 [11:59<17:31,  1.38s/it]
Training 1/1 epoch (loss 2.7979):  39%|███▉      | 489/1250 [12:01<17:31,  1.38s/it]
Training 1/1 epoch (loss 2.7979):  39%|███▉      | 490/1250 [12:01<17:21,  1.37s/it]
Training 1/1 epoch (loss 2.5990):  39%|███▉      | 490/1250 [12:02<17:21,  1.37s/it]
Training 1/1 epoch (loss 2.5990):  39%|███▉      | 491/1250 [12:02<17:20,  1.37s/it]
Training 1/1 epoch (loss 2.5440):  39%|███▉      | 491/1250 [12:03<17:20,  1.37s/it]
Training 1/1 epoch (loss 2.5440):  39%|███▉      | 492/1250 [12:03<16:58,  1.34s/it]
Training 1/1 epoch (loss 2.6045):  39%|███▉      | 492/1250 [12:05<16:58,  1.34s/it]
Training 1/1 epoch (loss 2.6045):  39%|███▉      | 493/1250 [12:05<19:01,  1.51s/it]
Training 1/1 epoch (loss 2.4121):  39%|███▉      | 493/1250 [12:06<19:01,  1.51s/it]
Training 1/1 epoch (loss 2.4121):  40%|███▉      | 494/1250 [12:06<15:22,  1.22s/it]
Training 1/1 epoch (loss 2.6961):  40%|███▉      | 494/1250 [12:07<15:22,  1.22s/it]
Training 1/1 epoch (loss 2.6961):  40%|███▉      | 495/1250 [12:07<15:47,  1.25s/it]
Training 1/1 epoch (loss 2.6368):  40%|███▉      | 495/1250 [12:09<15:47,  1.25s/it]
Training 1/1 epoch (loss 2.6368):  40%|███▉      | 496/1250 [12:09<16:37,  1.32s/it]
Training 1/1 epoch (loss 2.4938):  40%|███▉      | 496/1250 [12:09<16:37,  1.32s/it]
Training 1/1 epoch (loss 2.4938):  40%|███▉      | 497/1250 [12:09<14:33,  1.16s/it]
Training 1/1 epoch (loss 2.7109):  40%|███▉      | 497/1250 [12:12<14:33,  1.16s/it]
Training 1/1 epoch (loss 2.7109):  40%|███▉      | 498/1250 [12:12<19:18,  1.54s/it]
Training 1/1 epoch (loss 2.3223):  40%|███▉      | 498/1250 [12:14<19:18,  1.54s/it]
Training 1/1 epoch (loss 2.3223):  40%|███▉      | 499/1250 [12:14<22:01,  1.76s/it]
Training 1/1 epoch (loss 2.6849):  40%|███▉      | 499/1250 [12:15<22:01,  1.76s/it]
Training 1/1 epoch (loss 2.6849):  40%|████      | 500/1250 [12:15<17:11,  1.38s/it]
Training 1/1 epoch (loss 2.6097):  40%|████      | 500/1250 [12:16<17:11,  1.38s/it]
Training 1/1 epoch (loss 2.6097):  40%|████      | 501/1250 [12:16<17:37,  1.41s/it]
Training 1/1 epoch (loss 2.7321):  40%|████      | 501/1250 [12:18<17:37,  1.41s/it]
Training 1/1 epoch (loss 2.7321):  40%|████      | 502/1250 [12:18<20:05,  1.61s/it]
Training 1/1 epoch (loss 2.8476):  40%|████      | 502/1250 [12:19<20:05,  1.61s/it]
Training 1/1 epoch (loss 2.8476):  40%|████      | 503/1250 [12:19<15:57,  1.28s/it]
Training 1/1 epoch (loss 2.4316):  40%|████      | 503/1250 [12:20<15:57,  1.28s/it]
Training 1/1 epoch (loss 2.4316):  40%|████      | 504/1250 [12:20<17:52,  1.44s/it]
Training 1/1 epoch (loss 2.8073):  40%|████      | 504/1250 [12:23<17:52,  1.44s/it]
Training 1/1 epoch (loss 2.8073):  40%|████      | 505/1250 [12:23<21:30,  1.73s/it]
Training 1/1 epoch (loss 2.7498):  40%|████      | 505/1250 [12:23<21:30,  1.73s/it]
Training 1/1 epoch (loss 2.7498):  40%|████      | 506/1250 [12:23<16:25,  1.32s/it]
Training 1/1 epoch (loss 2.5748):  40%|████      | 506/1250 [12:26<16:25,  1.32s/it]
Training 1/1 epoch (loss 2.5748):  41%|████      | 507/1250 [12:26<20:02,  1.62s/it]
Training 1/1 epoch (loss 2.5914):  41%|████      | 507/1250 [12:27<20:02,  1.62s/it]
Training 1/1 epoch (loss 2.5914):  41%|████      | 508/1250 [12:27<20:13,  1.63s/it]
Training 1/1 epoch (loss 2.6236):  41%|████      | 508/1250 [12:28<20:13,  1.63s/it]
Training 1/1 epoch (loss 2.6236):  41%|████      | 509/1250 [12:28<16:52,  1.37s/it]
Training 1/1 epoch (loss 2.4864):  41%|████      | 509/1250 [12:30<16:52,  1.37s/it]
Training 1/1 epoch (loss 2.4864):  41%|████      | 510/1250 [12:30<19:41,  1.60s/it]
Training 1/1 epoch (loss 2.4993):  41%|████      | 510/1250 [12:32<19:41,  1.60s/it]
Training 1/1 epoch (loss 2.4993):  41%|████      | 511/1250 [12:32<19:10,  1.56s/it]
Training 1/1 epoch (loss 2.5413):  41%|████      | 511/1250 [12:33<19:10,  1.56s/it]
Training 1/1 epoch (loss 2.5413):  41%|████      | 512/1250 [12:33<18:40,  1.52s/it]
Training 1/1 epoch (loss 2.5662):  41%|████      | 512/1250 [12:34<18:40,  1.52s/it]
Training 1/1 epoch (loss 2.5662):  41%|████      | 513/1250 [12:34<17:06,  1.39s/it]
Training 1/1 epoch (loss 2.4906):  41%|████      | 513/1250 [12:36<17:06,  1.39s/it]
Training 1/1 epoch (loss 2.4906):  41%|████      | 514/1250 [12:36<17:35,  1.43s/it]
Training 1/1 epoch (loss 2.4394):  41%|████      | 514/1250 [12:37<17:35,  1.43s/it]
Training 1/1 epoch (loss 2.4394):  41%|████      | 515/1250 [12:37<15:49,  1.29s/it]
Training 1/1 epoch (loss 2.5632):  41%|████      | 515/1250 [12:39<15:49,  1.29s/it]
Training 1/1 epoch (loss 2.5632):  41%|████▏     | 516/1250 [12:39<18:21,  1.50s/it]
Training 1/1 epoch (loss 2.7066):  41%|████▏     | 516/1250 [12:39<18:21,  1.50s/it]
Training 1/1 epoch (loss 2.7066):  41%|████▏     | 517/1250 [12:39<16:15,  1.33s/it]
Training 1/1 epoch (loss 2.5641):  41%|████▏     | 517/1250 [12:41<16:15,  1.33s/it]
Training 1/1 epoch (loss 2.5641):  41%|████▏     | 518/1250 [12:41<18:01,  1.48s/it]
Training 1/1 epoch (loss 2.5284):  41%|████▏     | 518/1250 [12:43<18:01,  1.48s/it]
Training 1/1 epoch (loss 2.5284):  42%|████▏     | 519/1250 [12:43<19:10,  1.57s/it]
Training 1/1 epoch (loss 2.4196):  42%|████▏     | 519/1250 [12:44<19:10,  1.57s/it]
Training 1/1 epoch (loss 2.4196):  42%|████▏     | 520/1250 [12:44<17:22,  1.43s/it]
Training 1/1 epoch (loss 2.7214):  42%|████▏     | 520/1250 [12:47<17:22,  1.43s/it]
Training 1/1 epoch (loss 2.7214):  42%|████▏     | 521/1250 [12:47<20:45,  1.71s/it]
Training 1/1 epoch (loss 2.6504):  42%|████▏     | 521/1250 [12:49<20:45,  1.71s/it]
Training 1/1 epoch (loss 2.6504):  42%|████▏     | 522/1250 [12:49<22:06,  1.82s/it]
Training 1/1 epoch (loss 2.7730):  42%|████▏     | 522/1250 [12:49<22:06,  1.82s/it]
Training 1/1 epoch (loss 2.7730):  42%|████▏     | 523/1250 [12:49<17:37,  1.45s/it]
Training 1/1 epoch (loss 2.6191):  42%|████▏     | 523/1250 [12:50<17:37,  1.45s/it]
Training 1/1 epoch (loss 2.6191):  42%|████▏     | 524/1250 [12:50<15:57,  1.32s/it]
Training 1/1 epoch (loss 2.6424):  42%|████▏     | 524/1250 [12:52<15:57,  1.32s/it]
Training 1/1 epoch (loss 2.6424):  42%|████▏     | 525/1250 [12:52<17:39,  1.46s/it]
Training 1/1 epoch (loss 2.5818):  42%|████▏     | 525/1250 [12:53<17:39,  1.46s/it]
Training 1/1 epoch (loss 2.5818):  42%|████▏     | 526/1250 [12:53<14:52,  1.23s/it]
Training 1/1 epoch (loss 2.4771):  42%|████▏     | 526/1250 [12:54<14:52,  1.23s/it]
Training 1/1 epoch (loss 2.4771):  42%|████▏     | 527/1250 [12:54<16:11,  1.34s/it]
Training 1/1 epoch (loss 2.6574):  42%|████▏     | 527/1250 [12:56<16:11,  1.34s/it]
Training 1/1 epoch (loss 2.6574):  42%|████▏     | 528/1250 [12:56<19:10,  1.59s/it]
Training 1/1 epoch (loss 2.4600):  42%|████▏     | 528/1250 [12:57<19:10,  1.59s/it]
Training 1/1 epoch (loss 2.4600):  42%|████▏     | 529/1250 [12:57<16:15,  1.35s/it]
Training 1/1 epoch (loss 2.6247):  42%|████▏     | 529/1250 [12:59<16:15,  1.35s/it]
Training 1/1 epoch (loss 2.6247):  42%|████▏     | 530/1250 [12:59<15:55,  1.33s/it]
Training 1/1 epoch (loss 2.3705):  42%|████▏     | 530/1250 [13:00<15:55,  1.33s/it]
Training 1/1 epoch (loss 2.3705):  42%|████▏     | 531/1250 [13:00<16:37,  1.39s/it]
Training 1/1 epoch (loss 2.5586):  42%|████▏     | 531/1250 [13:01<16:37,  1.39s/it]
Training 1/1 epoch (loss 2.5586):  43%|████▎     | 532/1250 [13:01<16:03,  1.34s/it]
Training 1/1 epoch (loss 2.6245):  43%|████▎     | 532/1250 [13:04<16:03,  1.34s/it]
Training 1/1 epoch (loss 2.6245):  43%|████▎     | 533/1250 [13:04<19:27,  1.63s/it]
Training 1/1 epoch (loss 2.7376):  43%|████▎     | 533/1250 [13:04<19:27,  1.63s/it]
Training 1/1 epoch (loss 2.7376):  43%|████▎     | 534/1250 [13:04<16:09,  1.35s/it]
Training 1/1 epoch (loss 2.8108):  43%|████▎     | 534/1250 [13:06<16:09,  1.35s/it]
Training 1/1 epoch (loss 2.8108):  43%|████▎     | 535/1250 [13:06<15:55,  1.34s/it]
Training 1/1 epoch (loss 2.7653):  43%|████▎     | 535/1250 [13:07<15:55,  1.34s/it]
Training 1/1 epoch (loss 2.7653):  43%|████▎     | 536/1250 [13:07<16:28,  1.38s/it]
Training 1/1 epoch (loss 2.8272):  43%|████▎     | 536/1250 [13:08<16:28,  1.38s/it]
Training 1/1 epoch (loss 2.8272):  43%|████▎     | 537/1250 [13:08<13:24,  1.13s/it]
Training 1/1 epoch (loss 2.4811):  43%|████▎     | 537/1250 [13:09<13:24,  1.13s/it]
Training 1/1 epoch (loss 2.4811):  43%|████▎     | 538/1250 [13:09<14:18,  1.21s/it]
Training 1/1 epoch (loss 2.6670):  43%|████▎     | 538/1250 [13:10<14:18,  1.21s/it]
Training 1/1 epoch (loss 2.6670):  43%|████▎     | 539/1250 [13:10<15:04,  1.27s/it]
Training 1/1 epoch (loss 2.7530):  43%|████▎     | 539/1250 [13:11<15:04,  1.27s/it]
Training 1/1 epoch (loss 2.7530):  43%|████▎     | 540/1250 [13:11<12:05,  1.02s/it]
Training 1/1 epoch (loss 2.6119):  43%|████▎     | 540/1250 [13:13<12:05,  1.02s/it]
Training 1/1 epoch (loss 2.6119):  43%|████▎     | 541/1250 [13:13<15:18,  1.29s/it]
Training 1/1 epoch (loss 2.6061):  43%|████▎     | 541/1250 [13:14<15:18,  1.29s/it]
Training 1/1 epoch (loss 2.6061):  43%|████▎     | 542/1250 [13:14<15:52,  1.35s/it]
Training 1/1 epoch (loss 2.4441):  43%|████▎     | 542/1250 [13:16<15:52,  1.35s/it]
Training 1/1 epoch (loss 2.4441):  43%|████▎     | 543/1250 [13:16<15:26,  1.31s/it]
Training 1/1 epoch (loss 2.5208):  43%|████▎     | 543/1250 [13:17<15:26,  1.31s/it]
Training 1/1 epoch (loss 2.5208):  44%|████▎     | 544/1250 [13:17<16:22,  1.39s/it]
Training 1/1 epoch (loss 2.5969):  44%|████▎     | 544/1250 [13:19<16:22,  1.39s/it]
Training 1/1 epoch (loss 2.5969):  44%|████▎     | 545/1250 [13:19<18:43,  1.59s/it]
Training 1/1 epoch (loss 2.6844):  44%|████▎     | 545/1250 [13:20<18:43,  1.59s/it]
Training 1/1 epoch (loss 2.6844):  44%|████▎     | 546/1250 [13:20<15:22,  1.31s/it]
Training 1/1 epoch (loss 2.6625):  44%|████▎     | 546/1250 [13:22<15:22,  1.31s/it]
Training 1/1 epoch (loss 2.6625):  44%|████▍     | 547/1250 [13:22<17:22,  1.48s/it]
Training 1/1 epoch (loss 2.7248):  44%|████▍     | 547/1250 [13:24<17:22,  1.48s/it]
Training 1/1 epoch (loss 2.7248):  44%|████▍     | 548/1250 [13:24<20:34,  1.76s/it]
Training 1/1 epoch (loss 2.8320):  44%|████▍     | 548/1250 [13:25<20:34,  1.76s/it]
Training 1/1 epoch (loss 2.8320):  44%|████▍     | 549/1250 [13:25<15:59,  1.37s/it]
Training 1/1 epoch (loss 2.6510):  44%|████▍     | 549/1250 [13:26<15:59,  1.37s/it]
Training 1/1 epoch (loss 2.6510):  44%|████▍     | 550/1250 [13:26<16:59,  1.46s/it]
Training 1/1 epoch (loss 2.5457):  44%|████▍     | 550/1250 [13:28<16:59,  1.46s/it]
Training 1/1 epoch (loss 2.5457):  44%|████▍     | 551/1250 [13:28<18:41,  1.60s/it]
Training 1/1 epoch (loss 2.4311):  44%|████▍     | 551/1250 [13:29<18:41,  1.60s/it]
Training 1/1 epoch (loss 2.4311):  44%|████▍     | 552/1250 [13:29<15:59,  1.37s/it]
Training 1/1 epoch (loss 2.7267):  44%|████▍     | 552/1250 [13:31<15:59,  1.37s/it]
Training 1/1 epoch (loss 2.7267):  44%|████▍     | 553/1250 [13:31<16:25,  1.41s/it]
Training 1/1 epoch (loss 2.5724):  44%|████▍     | 553/1250 [13:33<16:25,  1.41s/it]
Training 1/1 epoch (loss 2.5724):  44%|████▍     | 554/1250 [13:33<18:25,  1.59s/it]
Training 1/1 epoch (loss 2.3507):  44%|████▍     | 554/1250 [13:33<18:25,  1.59s/it]
Training 1/1 epoch (loss 2.3507):  44%|████▍     | 555/1250 [13:33<14:58,  1.29s/it]
Training 1/1 epoch (loss 2.5844):  44%|████▍     | 555/1250 [13:35<14:58,  1.29s/it]
Training 1/1 epoch (loss 2.5844):  44%|████▍     | 556/1250 [13:35<15:27,  1.34s/it]
Training 1/1 epoch (loss 2.7556):  44%|████▍     | 556/1250 [13:36<15:27,  1.34s/it]
Training 1/1 epoch (loss 2.7556):  45%|████▍     | 557/1250 [13:36<16:16,  1.41s/it]
Training 1/1 epoch (loss 2.6244):  45%|████▍     | 557/1250 [13:37<16:16,  1.41s/it]
Training 1/1 epoch (loss 2.6244):  45%|████▍     | 558/1250 [13:37<13:49,  1.20s/it]
Training 1/1 epoch (loss 2.6870):  45%|████▍     | 558/1250 [13:39<13:49,  1.20s/it]
Training 1/1 epoch (loss 2.6870):  45%|████▍     | 559/1250 [13:39<18:08,  1.58s/it]
Training 1/1 epoch (loss 2.7056):  45%|████▍     | 559/1250 [13:41<18:08,  1.58s/it]
Training 1/1 epoch (loss 2.7056):  45%|████▍     | 560/1250 [13:41<18:39,  1.62s/it]
Training 1/1 epoch (loss 2.4816):  45%|████▍     | 560/1250 [13:42<18:39,  1.62s/it]
Training 1/1 epoch (loss 2.4816):  45%|████▍     | 561/1250 [13:42<16:01,  1.40s/it]
Training 1/1 epoch (loss 2.6817):  45%|████▍     | 561/1250 [13:44<16:01,  1.40s/it]
Training 1/1 epoch (loss 2.6817):  45%|████▍     | 562/1250 [13:44<17:11,  1.50s/it]
Training 1/1 epoch (loss 2.7023):  45%|████▍     | 562/1250 [13:44<17:11,  1.50s/it]
Training 1/1 epoch (loss 2.7023):  45%|████▌     | 563/1250 [13:44<14:20,  1.25s/it]
Training 1/1 epoch (loss 2.7654):  45%|████▌     | 563/1250 [13:46<14:20,  1.25s/it]
Training 1/1 epoch (loss 2.7654):  45%|████▌     | 564/1250 [13:46<14:07,  1.24s/it]
Training 1/1 epoch (loss 2.6745):  45%|████▌     | 564/1250 [13:48<14:07,  1.24s/it]
Training 1/1 epoch (loss 2.6745):  45%|████▌     | 565/1250 [13:48<16:58,  1.49s/it]
Training 1/1 epoch (loss 2.6957):  45%|████▌     | 565/1250 [13:49<16:58,  1.49s/it]
Training 1/1 epoch (loss 2.6957):  45%|████▌     | 566/1250 [13:49<16:38,  1.46s/it]
Training 1/1 epoch (loss 2.6633):  45%|████▌     | 566/1250 [13:50<16:38,  1.46s/it]
Training 1/1 epoch (loss 2.6633):  45%|████▌     | 567/1250 [13:50<14:31,  1.28s/it]
Training 1/1 epoch (loss 2.5755):  45%|████▌     | 567/1250 [13:52<14:31,  1.28s/it]
Training 1/1 epoch (loss 2.5755):  45%|████▌     | 568/1250 [13:52<18:58,  1.67s/it]
Training 1/1 epoch (loss 2.7143):  45%|████▌     | 568/1250 [13:53<18:58,  1.67s/it]
Training 1/1 epoch (loss 2.7143):  46%|████▌     | 569/1250 [13:53<16:23,  1.44s/it]
Training 1/1 epoch (loss 2.5625):  46%|████▌     | 569/1250 [13:55<16:23,  1.44s/it]
Training 1/1 epoch (loss 2.5625):  46%|████▌     | 570/1250 [13:55<16:04,  1.42s/it]
Training 1/1 epoch (loss 2.6036):  46%|████▌     | 570/1250 [13:57<16:04,  1.42s/it]
Training 1/1 epoch (loss 2.6036):  46%|████▌     | 571/1250 [13:57<17:39,  1.56s/it]
Training 1/1 epoch (loss 2.7195):  46%|████▌     | 571/1250 [13:57<17:39,  1.56s/it]
Training 1/1 epoch (loss 2.7195):  46%|████▌     | 572/1250 [13:57<13:49,  1.22s/it]
Training 1/1 epoch (loss 2.6236):  46%|████▌     | 572/1250 [13:58<13:49,  1.22s/it]
Training 1/1 epoch (loss 2.6236):  46%|████▌     | 573/1250 [13:58<14:08,  1.25s/it]
Training 1/1 epoch (loss 2.6549):  46%|████▌     | 573/1250 [14:00<14:08,  1.25s/it]
Training 1/1 epoch (loss 2.6549):  46%|████▌     | 574/1250 [14:00<15:06,  1.34s/it]
Training 1/1 epoch (loss 2.7592):  46%|████▌     | 574/1250 [14:01<15:06,  1.34s/it]
Training 1/1 epoch (loss 2.7592):  46%|████▌     | 575/1250 [14:01<12:47,  1.14s/it]
Training 1/1 epoch (loss 2.5464):  46%|████▌     | 575/1250 [14:02<12:47,  1.14s/it]
Training 1/1 epoch (loss 2.5464):  46%|████▌     | 576/1250 [14:02<14:13,  1.27s/it]
Training 1/1 epoch (loss 2.5353):  46%|████▌     | 576/1250 [14:04<14:13,  1.27s/it]
Training 1/1 epoch (loss 2.5353):  46%|████▌     | 577/1250 [14:04<15:34,  1.39s/it]
Training 1/1 epoch (loss 2.7078):  46%|████▌     | 577/1250 [14:05<15:34,  1.39s/it]
Training 1/1 epoch (loss 2.7078):  46%|████▌     | 578/1250 [14:05<13:34,  1.21s/it]
Training 1/1 epoch (loss 2.8384):  46%|████▌     | 578/1250 [14:06<13:34,  1.21s/it]
Training 1/1 epoch (loss 2.8384):  46%|████▋     | 579/1250 [14:06<15:37,  1.40s/it]
Training 1/1 epoch (loss 2.7911):  46%|████▋     | 579/1250 [14:07<15:37,  1.40s/it]
Training 1/1 epoch (loss 2.7911):  46%|████▋     | 580/1250 [14:07<13:31,  1.21s/it]
Training 1/1 epoch (loss 2.5906):  46%|████▋     | 580/1250 [14:09<13:31,  1.21s/it]
Training 1/1 epoch (loss 2.5906):  46%|████▋     | 581/1250 [14:09<15:29,  1.39s/it]
Training 1/1 epoch (loss 2.5244):  46%|████▋     | 581/1250 [14:11<15:29,  1.39s/it]
Training 1/1 epoch (loss 2.5244):  47%|████▋     | 582/1250 [14:11<16:55,  1.52s/it]
Training 1/1 epoch (loss 2.4629):  47%|████▋     | 582/1250 [14:12<16:55,  1.52s/it]
Training 1/1 epoch (loss 2.4629):  47%|████▋     | 583/1250 [14:12<14:32,  1.31s/it]
Training 1/1 epoch (loss 2.5469):  47%|████▋     | 583/1250 [14:14<14:32,  1.31s/it]
Training 1/1 epoch (loss 2.5469):  47%|████▋     | 584/1250 [14:14<16:38,  1.50s/it]
Training 1/1 epoch (loss 2.6817):  47%|████▋     | 584/1250 [14:16<16:38,  1.50s/it]
Training 1/1 epoch (loss 2.6817):  47%|████▋     | 585/1250 [14:16<18:01,  1.63s/it]
Training 1/1 epoch (loss 2.5131):  47%|████▋     | 585/1250 [14:16<18:01,  1.63s/it]
Training 1/1 epoch (loss 2.5131):  47%|████▋     | 586/1250 [14:16<14:19,  1.29s/it]
Training 1/1 epoch (loss 2.5664):  47%|████▋     | 586/1250 [14:17<14:19,  1.29s/it]
Training 1/1 epoch (loss 2.5664):  47%|████▋     | 587/1250 [14:17<14:46,  1.34s/it]
Training 1/1 epoch (loss 2.3229):  47%|████▋     | 587/1250 [14:20<14:46,  1.34s/it]
Training 1/1 epoch (loss 2.3229):  47%|████▋     | 588/1250 [14:20<18:31,  1.68s/it]
Training 1/1 epoch (loss 2.4710):  47%|████▋     | 588/1250 [14:21<18:31,  1.68s/it]
Training 1/1 epoch (loss 2.4710):  47%|████▋     | 589/1250 [14:21<15:26,  1.40s/it]
Training 1/1 epoch (loss 2.6074):  47%|████▋     | 589/1250 [14:23<15:26,  1.40s/it]
Training 1/1 epoch (loss 2.6074):  47%|████▋     | 590/1250 [14:23<17:25,  1.58s/it]
Training 1/1 epoch (loss 2.4835):  47%|████▋     | 590/1250 [14:24<17:25,  1.58s/it]
Training 1/1 epoch (loss 2.4835):  47%|████▋     | 591/1250 [14:24<15:38,  1.42s/it]
Training 1/1 epoch (loss 2.6145):  47%|████▋     | 591/1250 [14:26<15:38,  1.42s/it]
Training 1/1 epoch (loss 2.6145):  47%|████▋     | 592/1250 [14:26<16:44,  1.53s/it]
Training 1/1 epoch (loss 2.7174):  47%|████▋     | 592/1250 [14:27<16:44,  1.53s/it]
Training 1/1 epoch (loss 2.7174):  47%|████▋     | 593/1250 [14:27<16:50,  1.54s/it]
Training 1/1 epoch (loss 2.5328):  47%|████▋     | 593/1250 [14:28<16:50,  1.54s/it]
Training 1/1 epoch (loss 2.5328):  48%|████▊     | 594/1250 [14:28<13:46,  1.26s/it]
Training 1/1 epoch (loss 2.4997):  48%|████▊     | 594/1250 [14:30<13:46,  1.26s/it]
Training 1/1 epoch (loss 2.4997):  48%|████▊     | 595/1250 [14:30<16:36,  1.52s/it]
Training 1/1 epoch (loss 2.5500):  48%|████▊     | 595/1250 [14:32<16:36,  1.52s/it]
Training 1/1 epoch (loss 2.5500):  48%|████▊     | 596/1250 [14:32<18:08,  1.66s/it]
Training 1/1 epoch (loss 2.6454):  48%|████▊     | 596/1250 [14:33<18:08,  1.66s/it]
Training 1/1 epoch (loss 2.6454):  48%|████▊     | 597/1250 [14:33<15:00,  1.38s/it]
Training 1/1 epoch (loss 2.5811):  48%|████▊     | 597/1250 [14:33<15:00,  1.38s/it]
Training 1/1 epoch (loss 2.5811):  48%|████▊     | 598/1250 [14:33<13:22,  1.23s/it]
Training 1/1 epoch (loss 2.6443):  48%|████▊     | 598/1250 [14:36<13:22,  1.23s/it]
Training 1/1 epoch (loss 2.6443):  48%|████▊     | 599/1250 [14:36<16:19,  1.50s/it]
Training 1/1 epoch (loss 2.6103):  48%|████▊     | 599/1250 [14:36<16:19,  1.50s/it]
Training 1/1 epoch (loss 2.6103):  48%|████▊     | 600/1250 [14:36<13:29,  1.24s/it]
Training 1/1 epoch (loss 2.7919):  48%|████▊     | 600/1250 [14:38<13:29,  1.24s/it]
Training 1/1 epoch (loss 2.7919):  48%|████▊     | 601/1250 [14:38<15:58,  1.48s/it]
Training 1/1 epoch (loss 2.5110):  48%|████▊     | 601/1250 [14:40<15:58,  1.48s/it]
Training 1/1 epoch (loss 2.5110):  48%|████▊     | 602/1250 [14:40<16:02,  1.49s/it]
Training 1/1 epoch (loss 2.4821):  48%|████▊     | 602/1250 [14:41<16:02,  1.49s/it]
Training 1/1 epoch (loss 2.4821):  48%|████▊     | 603/1250 [14:41<16:05,  1.49s/it]
Training 1/1 epoch (loss 2.6708):  48%|████▊     | 603/1250 [14:43<16:05,  1.49s/it]
Training 1/1 epoch (loss 2.6708):  48%|████▊     | 604/1250 [14:43<16:16,  1.51s/it]
Training 1/1 epoch (loss 2.5681):  48%|████▊     | 604/1250 [14:44<16:16,  1.51s/it]
Training 1/1 epoch (loss 2.5681):  48%|████▊     | 605/1250 [14:44<15:26,  1.44s/it]
Training 1/1 epoch (loss 2.7022):  48%|████▊     | 605/1250 [14:45<15:26,  1.44s/it]
Training 1/1 epoch (loss 2.7022):  48%|████▊     | 606/1250 [14:45<15:13,  1.42s/it]
Training 1/1 epoch (loss 2.4906):  48%|████▊     | 606/1250 [14:47<15:13,  1.42s/it]
Training 1/1 epoch (loss 2.4906):  49%|████▊     | 607/1250 [14:47<16:46,  1.57s/it]
Training 1/1 epoch (loss 2.8043):  49%|████▊     | 607/1250 [14:49<16:46,  1.57s/it]
Training 1/1 epoch (loss 2.8043):  49%|████▊     | 608/1250 [14:49<15:40,  1.47s/it]
Training 1/1 epoch (loss 2.5385):  49%|████▊     | 608/1250 [14:50<15:40,  1.47s/it]
Training 1/1 epoch (loss 2.5385):  49%|████▊     | 609/1250 [14:50<16:53,  1.58s/it]
Training 1/1 epoch (loss 2.6402):  49%|████▊     | 609/1250 [14:52<16:53,  1.58s/it]
Training 1/1 epoch (loss 2.6402):  49%|████▉     | 610/1250 [14:52<16:44,  1.57s/it]
Training 1/1 epoch (loss 2.6810):  49%|████▉     | 610/1250 [14:53<16:44,  1.57s/it]
Training 1/1 epoch (loss 2.6810):  49%|████▉     | 611/1250 [14:53<13:49,  1.30s/it]
Training 1/1 epoch (loss 2.4853):  49%|████▉     | 611/1250 [14:54<13:49,  1.30s/it]
Training 1/1 epoch (loss 2.4853):  49%|████▉     | 612/1250 [14:54<14:57,  1.41s/it]
Training 1/1 epoch (loss 2.7313):  49%|████▉     | 612/1250 [14:56<14:57,  1.41s/it]
Training 1/1 epoch (loss 2.7313):  49%|████▉     | 613/1250 [14:56<14:29,  1.36s/it]
Training 1/1 epoch (loss 2.7618):  49%|████▉     | 613/1250 [14:56<14:29,  1.36s/it]
Training 1/1 epoch (loss 2.7618):  49%|████▉     | 614/1250 [14:56<11:50,  1.12s/it]
Training 1/1 epoch (loss 2.5682):  49%|████▉     | 614/1250 [14:58<11:50,  1.12s/it]
Training 1/1 epoch (loss 2.5682):  49%|████▉     | 615/1250 [14:58<13:59,  1.32s/it]
Training 1/1 epoch (loss 2.6902):  49%|████▉     | 615/1250 [15:00<13:59,  1.32s/it]
Training 1/1 epoch (loss 2.6902):  49%|████▉     | 616/1250 [15:00<16:49,  1.59s/it]
Training 1/1 epoch (loss 2.2787):  49%|████▉     | 616/1250 [15:01<16:49,  1.59s/it]
Training 1/1 epoch (loss 2.2787):  49%|████▉     | 617/1250 [15:01<14:08,  1.34s/it]
Training 1/1 epoch (loss 2.5914):  49%|████▉     | 617/1250 [15:03<14:08,  1.34s/it]
Training 1/1 epoch (loss 2.5914):  49%|████▉     | 618/1250 [15:03<15:03,  1.43s/it]
Training 1/1 epoch (loss 2.4870):  49%|████▉     | 618/1250 [15:04<15:03,  1.43s/it]
Training 1/1 epoch (loss 2.4870):  50%|████▉     | 619/1250 [15:04<14:01,  1.33s/it]
Training 1/1 epoch (loss 2.5183):  50%|████▉     | 619/1250 [15:05<14:01,  1.33s/it]
Training 1/1 epoch (loss 2.5183):  50%|████▉     | 620/1250 [15:05<14:42,  1.40s/it]
Training 1/1 epoch (loss 2.4669):  50%|████▉     | 620/1250 [15:08<14:42,  1.40s/it]
Training 1/1 epoch (loss 2.4669):  50%|████▉     | 621/1250 [15:08<17:54,  1.71s/it]
Training 1/1 epoch (loss 2.7508):  50%|████▉     | 621/1250 [15:09<17:54,  1.71s/it]
Training 1/1 epoch (loss 2.7508):  50%|████▉     | 622/1250 [15:09<15:27,  1.48s/it]
Training 1/1 epoch (loss 2.6511):  50%|████▉     | 622/1250 [15:11<15:27,  1.48s/it]
Training 1/1 epoch (loss 2.6511):  50%|████▉     | 623/1250 [15:11<18:34,  1.78s/it]
Training 1/1 epoch (loss 2.5640):  50%|████▉     | 623/1250 [15:14<18:34,  1.78s/it]
Training 1/1 epoch (loss 2.5640):  50%|████▉     | 624/1250 [15:14<21:14,  2.04s/it]
Training 1/1 epoch (loss 2.6227):  50%|████▉     | 624/1250 [15:15<21:14,  2.04s/it]
Training 1/1 epoch (loss 2.6227):  50%|█████     | 625/1250 [15:15<18:11,  1.75s/it]
Training 1/1 epoch (loss 2.6607):  50%|█████     | 625/1250 [15:16<18:11,  1.75s/it]
Training 1/1 epoch (loss 2.6607):  50%|█████     | 626/1250 [15:16<17:53,  1.72s/it]
Training 1/1 epoch (loss 2.3666):  50%|█████     | 626/1250 [15:18<17:53,  1.72s/it]
Training 1/1 epoch (loss 2.3666):  50%|█████     | 627/1250 [15:18<17:08,  1.65s/it]
Training 1/1 epoch (loss 2.5780):  50%|█████     | 627/1250 [15:20<17:08,  1.65s/it]
Training 1/1 epoch (loss 2.5780):  50%|█████     | 628/1250 [15:20<17:41,  1.71s/it]
Training 1/1 epoch (loss 2.7759):  50%|█████     | 628/1250 [15:21<17:41,  1.71s/it]
Training 1/1 epoch (loss 2.7759):  50%|█████     | 629/1250 [15:21<16:50,  1.63s/it]
Training 1/1 epoch (loss 2.3194):  50%|█████     | 629/1250 [15:22<16:50,  1.63s/it]
Training 1/1 epoch (loss 2.3194):  50%|█████     | 630/1250 [15:22<13:33,  1.31s/it]
Training 1/1 epoch (loss 2.6304):  50%|█████     | 630/1250 [15:23<13:33,  1.31s/it]
Training 1/1 epoch (loss 2.6304):  50%|█████     | 631/1250 [15:23<13:50,  1.34s/it]
Training 1/1 epoch (loss 2.7322):  50%|█████     | 631/1250 [15:25<13:50,  1.34s/it]
Training 1/1 epoch (loss 2.7322):  51%|█████     | 632/1250 [15:25<15:19,  1.49s/it]
Training 1/1 epoch (loss 2.6277):  51%|█████     | 632/1250 [15:26<15:19,  1.49s/it]
Training 1/1 epoch (loss 2.6277):  51%|█████     | 633/1250 [15:26<13:24,  1.30s/it]
Training 1/1 epoch (loss 2.5903):  51%|█████     | 633/1250 [15:27<13:24,  1.30s/it]
Training 1/1 epoch (loss 2.5903):  51%|█████     | 634/1250 [15:27<13:54,  1.35s/it]
Training 1/1 epoch (loss 2.4531):  51%|█████     | 634/1250 [15:30<13:54,  1.35s/it]
Training 1/1 epoch (loss 2.4531):  51%|█████     | 635/1250 [15:30<17:13,  1.68s/it]
Training 1/1 epoch (loss 2.4080):  51%|█████     | 635/1250 [15:30<17:13,  1.68s/it]
Training 1/1 epoch (loss 2.4080):  51%|█████     | 636/1250 [15:30<14:05,  1.38s/it]
Training 1/1 epoch (loss 2.4797):  51%|█████     | 636/1250 [15:33<14:05,  1.38s/it]
Training 1/1 epoch (loss 2.4797):  51%|█████     | 637/1250 [15:33<17:07,  1.68s/it]
Training 1/1 epoch (loss 2.4366):  51%|█████     | 637/1250 [15:35<17:07,  1.68s/it]
Training 1/1 epoch (loss 2.4366):  51%|█████     | 638/1250 [15:35<17:49,  1.75s/it]
Training 1/1 epoch (loss 2.7567):  51%|█████     | 638/1250 [15:36<17:49,  1.75s/it]
Training 1/1 epoch (loss 2.7567):  51%|█████     | 639/1250 [15:36<15:37,  1.53s/it]
Training 1/1 epoch (loss 2.5729):  51%|█████     | 639/1250 [15:39<15:37,  1.53s/it]
Training 1/1 epoch (loss 2.5729):  51%|█████     | 640/1250 [15:39<19:22,  1.91s/it]
Training 1/1 epoch (loss 2.5568):  51%|█████     | 640/1250 [15:40<19:22,  1.91s/it]
Training 1/1 epoch (loss 2.5568):  51%|█████▏    | 641/1250 [15:40<18:00,  1.77s/it]
Training 1/1 epoch (loss 2.5435):  51%|█████▏    | 641/1250 [15:42<18:00,  1.77s/it]
Training 1/1 epoch (loss 2.5435):  51%|█████▏    | 642/1250 [15:42<18:59,  1.87s/it]
Training 1/1 epoch (loss 2.6269):  51%|█████▏    | 642/1250 [15:44<18:59,  1.87s/it]
Training 1/1 epoch (loss 2.6269):  51%|█████▏    | 643/1250 [15:44<18:21,  1.81s/it]
Training 1/1 epoch (loss 2.5830):  51%|█████▏    | 643/1250 [15:45<18:21,  1.81s/it]
Training 1/1 epoch (loss 2.5830):  52%|█████▏    | 644/1250 [15:45<15:06,  1.50s/it]
Training 1/1 epoch (loss 2.4615):  52%|█████▏    | 644/1250 [15:46<15:06,  1.50s/it]
Training 1/1 epoch (loss 2.4615):  52%|█████▏    | 645/1250 [15:46<15:23,  1.53s/it]
Training 1/1 epoch (loss 2.1903):  52%|█████▏    | 645/1250 [15:47<15:23,  1.53s/it]
Training 1/1 epoch (loss 2.1903):  52%|█████▏    | 646/1250 [15:47<13:50,  1.37s/it]
Training 1/1 epoch (loss 2.5423):  52%|█████▏    | 646/1250 [15:48<13:50,  1.37s/it]
Training 1/1 epoch (loss 2.5423):  52%|█████▏    | 647/1250 [15:48<11:24,  1.14s/it]
Training 1/1 epoch (loss 2.7382):  52%|█████▏    | 647/1250 [15:50<11:24,  1.14s/it]
Training 1/1 epoch (loss 2.7382):  52%|█████▏    | 648/1250 [15:50<15:37,  1.56s/it]
Training 1/1 epoch (loss 2.4365):  52%|█████▏    | 648/1250 [15:52<15:37,  1.56s/it]
Training 1/1 epoch (loss 2.4365):  52%|█████▏    | 649/1250 [15:52<16:08,  1.61s/it]
Training 1/1 epoch (loss 2.7005):  52%|█████▏    | 649/1250 [15:53<16:08,  1.61s/it]
Training 1/1 epoch (loss 2.7005):  52%|█████▏    | 650/1250 [15:53<15:31,  1.55s/it]
Training 1/1 epoch (loss 2.6318):  52%|█████▏    | 650/1250 [15:54<15:31,  1.55s/it]
Training 1/1 epoch (loss 2.6318):  52%|█████▏    | 651/1250 [15:54<14:01,  1.40s/it]
Training 1/1 epoch (loss 2.4586):  52%|█████▏    | 651/1250 [15:56<14:01,  1.40s/it]
Training 1/1 epoch (loss 2.4586):  52%|█████▏    | 652/1250 [15:56<14:33,  1.46s/it]
Training 1/1 epoch (loss 2.4828):  52%|█████▏    | 652/1250 [15:58<14:33,  1.46s/it]
Training 1/1 epoch (loss 2.4828):  52%|█████▏    | 653/1250 [15:58<14:35,  1.47s/it]
Training 1/1 epoch (loss 2.4164):  52%|█████▏    | 653/1250 [15:59<14:35,  1.47s/it]
Training 1/1 epoch (loss 2.4164):  52%|█████▏    | 654/1250 [15:59<14:56,  1.50s/it]
Training 1/1 epoch (loss 2.5949):  52%|█████▏    | 654/1250 [16:01<14:56,  1.50s/it]
Training 1/1 epoch (loss 2.5949):  52%|█████▏    | 655/1250 [16:01<14:37,  1.47s/it]
Training 1/1 epoch (loss 2.7660):  52%|█████▏    | 655/1250 [16:02<14:37,  1.47s/it]
Training 1/1 epoch (loss 2.7660):  52%|█████▏    | 656/1250 [16:02<13:02,  1.32s/it]
Training 1/1 epoch (loss 2.7274):  52%|█████▏    | 656/1250 [16:03<13:02,  1.32s/it]
Training 1/1 epoch (loss 2.7274):  53%|█████▎    | 657/1250 [16:03<13:57,  1.41s/it]
Training 1/1 epoch (loss 2.7435):  53%|█████▎    | 657/1250 [16:04<13:57,  1.41s/it]
Training 1/1 epoch (loss 2.7435):  53%|█████▎    | 658/1250 [16:04<11:36,  1.18s/it]
Training 1/1 epoch (loss 2.4963):  53%|█████▎    | 658/1250 [16:06<11:36,  1.18s/it]
Training 1/1 epoch (loss 2.4963):  53%|█████▎    | 659/1250 [16:06<15:39,  1.59s/it]
Training 1/1 epoch (loss 2.2754):  53%|█████▎    | 659/1250 [16:09<15:39,  1.59s/it]
Training 1/1 epoch (loss 2.2754):  53%|█████▎    | 660/1250 [16:09<18:05,  1.84s/it]
Training 1/1 epoch (loss 2.4492):  53%|█████▎    | 660/1250 [16:09<18:05,  1.84s/it]
Training 1/1 epoch (loss 2.4492):  53%|█████▎    | 661/1250 [16:09<14:02,  1.43s/it]
Training 1/1 epoch (loss 2.5118):  53%|█████▎    | 661/1250 [16:12<14:02,  1.43s/it]
Training 1/1 epoch (loss 2.5118):  53%|█████▎    | 662/1250 [16:12<16:55,  1.73s/it]
Training 1/1 epoch (loss 2.6008):  53%|█████▎    | 662/1250 [16:13<16:55,  1.73s/it]
Training 1/1 epoch (loss 2.6008):  53%|█████▎    | 663/1250 [16:13<16:42,  1.71s/it]
Training 1/1 epoch (loss 2.6699):  53%|█████▎    | 663/1250 [16:14<16:42,  1.71s/it]
Training 1/1 epoch (loss 2.6699):  53%|█████▎    | 664/1250 [16:14<13:32,  1.39s/it]
Training 1/1 epoch (loss 2.6048):  53%|█████▎    | 664/1250 [16:16<13:32,  1.39s/it]
Training 1/1 epoch (loss 2.6048):  53%|█████▎    | 665/1250 [16:16<14:22,  1.47s/it]
Training 1/1 epoch (loss 2.5760):  53%|█████▎    | 665/1250 [16:18<14:22,  1.47s/it]
Training 1/1 epoch (loss 2.5760):  53%|█████▎    | 666/1250 [16:18<15:55,  1.64s/it]
Training 1/1 epoch (loss 2.7904):  53%|█████▎    | 666/1250 [16:18<15:55,  1.64s/it]
Training 1/1 epoch (loss 2.7904):  53%|█████▎    | 667/1250 [16:18<12:42,  1.31s/it]
Training 1/1 epoch (loss 2.6637):  53%|█████▎    | 667/1250 [16:21<12:42,  1.31s/it]
Training 1/1 epoch (loss 2.6637):  53%|█████▎    | 668/1250 [16:21<16:14,  1.67s/it]
Training 1/1 epoch (loss 2.6271):  53%|█████▎    | 668/1250 [16:22<16:14,  1.67s/it]
Training 1/1 epoch (loss 2.6271):  54%|█████▎    | 669/1250 [16:22<15:02,  1.55s/it]
Training 1/1 epoch (loss 2.8648):  54%|█████▎    | 669/1250 [16:23<15:02,  1.55s/it]
Training 1/1 epoch (loss 2.8648):  54%|█████▎    | 670/1250 [16:23<12:32,  1.30s/it]
Training 1/1 epoch (loss 2.8592):  54%|█████▎    | 670/1250 [16:24<12:32,  1.30s/it]
Training 1/1 epoch (loss 2.8592):  54%|█████▎    | 671/1250 [16:24<13:05,  1.36s/it]
Training 1/1 epoch (loss 2.7948):  54%|█████▎    | 671/1250 [16:26<13:05,  1.36s/it]
Training 1/1 epoch (loss 2.7948):  54%|█████▍    | 672/1250 [16:26<14:14,  1.48s/it]
Training 1/1 epoch (loss 2.4465):  54%|█████▍    | 672/1250 [16:27<14:14,  1.48s/it]
Training 1/1 epoch (loss 2.4465):  54%|█████▍    | 673/1250 [16:27<14:21,  1.49s/it]
Training 1/1 epoch (loss 2.7113):  54%|█████▍    | 673/1250 [16:30<14:21,  1.49s/it]
Training 1/1 epoch (loss 2.7113):  54%|█████▍    | 674/1250 [16:30<16:44,  1.74s/it]
Training 1/1 epoch (loss 2.3839):  54%|█████▍    | 674/1250 [16:31<16:44,  1.74s/it]
Training 1/1 epoch (loss 2.3839):  54%|█████▍    | 675/1250 [16:31<14:16,  1.49s/it]
Training 1/1 epoch (loss 2.6224):  54%|█████▍    | 675/1250 [16:33<14:16,  1.49s/it]
Training 1/1 epoch (loss 2.6224):  54%|█████▍    | 676/1250 [16:33<15:13,  1.59s/it]
Training 1/1 epoch (loss 2.4234):  54%|█████▍    | 676/1250 [16:35<15:13,  1.59s/it]
Training 1/1 epoch (loss 2.4234):  54%|█████▍    | 677/1250 [16:35<17:44,  1.86s/it]
Training 1/1 epoch (loss 2.6902):  54%|█████▍    | 677/1250 [16:36<17:44,  1.86s/it]
Training 1/1 epoch (loss 2.6902):  54%|█████▍    | 678/1250 [16:36<14:40,  1.54s/it]
Training 1/1 epoch (loss 2.6778):  54%|█████▍    | 678/1250 [16:38<14:40,  1.54s/it]
Training 1/1 epoch (loss 2.6778):  54%|█████▍    | 679/1250 [16:38<15:59,  1.68s/it]
Training 1/1 epoch (loss 2.6037):  54%|█████▍    | 679/1250 [16:39<15:59,  1.68s/it]
Training 1/1 epoch (loss 2.6037):  54%|█████▍    | 680/1250 [16:39<15:40,  1.65s/it]
Training 1/1 epoch (loss 2.4749):  54%|█████▍    | 680/1250 [16:40<15:40,  1.65s/it]
Training 1/1 epoch (loss 2.4749):  54%|█████▍    | 681/1250 [16:40<13:07,  1.38s/it]
Training 1/1 epoch (loss 2.6862):  54%|█████▍    | 681/1250 [16:42<13:07,  1.38s/it]
Training 1/1 epoch (loss 2.6862):  55%|█████▍    | 682/1250 [16:42<15:20,  1.62s/it]
Training 1/1 epoch (loss 2.7036):  55%|█████▍    | 682/1250 [16:44<15:20,  1.62s/it]
Training 1/1 epoch (loss 2.7036):  55%|█████▍    | 683/1250 [16:44<15:06,  1.60s/it]
Training 1/1 epoch (loss 2.6619):  55%|█████▍    | 683/1250 [16:45<15:06,  1.60s/it]
Training 1/1 epoch (loss 2.6619):  55%|█████▍    | 684/1250 [16:45<14:20,  1.52s/it]
Training 1/1 epoch (loss 2.3929):  55%|█████▍    | 684/1250 [16:47<14:20,  1.52s/it]
Training 1/1 epoch (loss 2.3929):  55%|█████▍    | 685/1250 [16:47<13:55,  1.48s/it]
Training 1/1 epoch (loss 2.6683):  55%|█████▍    | 685/1250 [16:48<13:55,  1.48s/it]
Training 1/1 epoch (loss 2.6683):  55%|█████▍    | 686/1250 [16:48<14:00,  1.49s/it]
Training 1/1 epoch (loss 2.4910):  55%|█████▍    | 686/1250 [16:49<14:00,  1.49s/it]
Training 1/1 epoch (loss 2.4910):  55%|█████▍    | 687/1250 [16:49<12:48,  1.37s/it]
Training 1/1 epoch (loss 2.6414):  55%|█████▍    | 687/1250 [16:51<12:48,  1.37s/it]
Training 1/1 epoch (loss 2.6414):  55%|█████▌    | 688/1250 [16:51<14:38,  1.56s/it]
Training 1/1 epoch (loss 2.6943):  55%|█████▌    | 688/1250 [16:52<14:38,  1.56s/it]
Training 1/1 epoch (loss 2.6943):  55%|█████▌    | 689/1250 [16:52<11:56,  1.28s/it]
Training 1/1 epoch (loss 2.7189):  55%|█████▌    | 689/1250 [16:54<11:56,  1.28s/it]
Training 1/1 epoch (loss 2.7189):  55%|█████▌    | 690/1250 [16:54<15:23,  1.65s/it]
Training 1/1 epoch (loss 2.5563):  55%|█████▌    | 690/1250 [16:56<15:23,  1.65s/it]
Training 1/1 epoch (loss 2.5563):  55%|█████▌    | 691/1250 [16:56<15:52,  1.70s/it]
Training 1/1 epoch (loss 2.6491):  55%|█████▌    | 691/1250 [16:57<15:52,  1.70s/it]
Training 1/1 epoch (loss 2.6491):  55%|█████▌    | 692/1250 [16:57<13:19,  1.43s/it]
Training 1/1 epoch (loss 2.6049):  55%|█████▌    | 692/1250 [16:58<13:19,  1.43s/it]
Training 1/1 epoch (loss 2.6049):  55%|█████▌    | 693/1250 [16:58<13:16,  1.43s/it]
Training 1/1 epoch (loss 2.7655):  55%|█████▌    | 693/1250 [16:59<13:16,  1.43s/it]
Training 1/1 epoch (loss 2.7655):  56%|█████▌    | 694/1250 [16:59<12:01,  1.30s/it]
Training 1/1 epoch (loss 2.5687):  56%|█████▌    | 694/1250 [17:01<12:01,  1.30s/it]
Training 1/1 epoch (loss 2.5687):  56%|█████▌    | 695/1250 [17:01<12:31,  1.35s/it]
Training 1/1 epoch (loss 2.8039):  56%|█████▌    | 695/1250 [17:03<12:31,  1.35s/it]
Training 1/1 epoch (loss 2.8039):  56%|█████▌    | 696/1250 [17:03<13:34,  1.47s/it]
Training 1/1 epoch (loss 2.6238):  56%|█████▌    | 696/1250 [17:03<13:34,  1.47s/it]
Training 1/1 epoch (loss 2.6238):  56%|█████▌    | 697/1250 [17:03<11:38,  1.26s/it]
Training 1/1 epoch (loss 2.4462):  56%|█████▌    | 697/1250 [17:04<11:38,  1.26s/it]
Training 1/1 epoch (loss 2.4462):  56%|█████▌    | 698/1250 [17:04<10:52,  1.18s/it]
Training 1/1 epoch (loss 2.7596):  56%|█████▌    | 698/1250 [17:07<10:52,  1.18s/it]
Training 1/1 epoch (loss 2.7596):  56%|█████▌    | 699/1250 [17:07<14:12,  1.55s/it]
Training 1/1 epoch (loss 2.8827):  56%|█████▌    | 699/1250 [17:07<14:12,  1.55s/it]
Training 1/1 epoch (loss 2.8827):  56%|█████▌    | 700/1250 [17:07<11:15,  1.23s/it]
Training 1/1 epoch (loss 2.7614):  56%|█████▌    | 700/1250 [17:09<11:15,  1.23s/it]
Training 1/1 epoch (loss 2.7614):  56%|█████▌    | 701/1250 [17:09<11:34,  1.27s/it]
Training 1/1 epoch (loss 2.5256):  56%|█████▌    | 701/1250 [17:10<11:34,  1.27s/it]
Training 1/1 epoch (loss 2.5256):  56%|█████▌    | 702/1250 [17:10<12:43,  1.39s/it]
Training 1/1 epoch (loss 2.6495):  56%|█████▌    | 702/1250 [17:12<12:43,  1.39s/it]
Training 1/1 epoch (loss 2.6495):  56%|█████▌    | 703/1250 [17:12<12:35,  1.38s/it]
Training 1/1 epoch (loss 2.4158):  56%|█████▌    | 703/1250 [17:14<12:35,  1.38s/it]
Training 1/1 epoch (loss 2.4158):  56%|█████▋    | 704/1250 [17:14<16:11,  1.78s/it]
Training 1/1 epoch (loss 2.6337):  56%|█████▋    | 704/1250 [17:15<16:11,  1.78s/it]
Training 1/1 epoch (loss 2.6337):  56%|█████▋    | 705/1250 [17:15<14:06,  1.55s/it]
Training 1/1 epoch (loss 2.7225):  56%|█████▋    | 705/1250 [17:18<14:06,  1.55s/it]
Training 1/1 epoch (loss 2.7225):  56%|█████▋    | 706/1250 [17:18<15:49,  1.75s/it]
Training 1/1 epoch (loss 2.6764):  56%|█████▋    | 706/1250 [17:20<15:49,  1.75s/it]
Training 1/1 epoch (loss 2.6764):  57%|█████▋    | 707/1250 [17:20<17:44,  1.96s/it]
Training 1/1 epoch (loss 2.7126):  57%|█████▋    | 707/1250 [17:21<17:44,  1.96s/it]
Training 1/1 epoch (loss 2.7126):  57%|█████▋    | 708/1250 [17:21<13:42,  1.52s/it]
Training 1/1 epoch (loss 2.7566):  57%|█████▋    | 708/1250 [17:22<13:42,  1.52s/it]
Training 1/1 epoch (loss 2.7566):  57%|█████▋    | 709/1250 [17:22<14:54,  1.65s/it]
Training 1/1 epoch (loss 2.5558):  57%|█████▋    | 709/1250 [17:25<14:54,  1.65s/it]
Training 1/1 epoch (loss 2.5558):  57%|█████▋    | 710/1250 [17:25<16:35,  1.84s/it]
Training 1/1 epoch (loss 2.6972):  57%|█████▋    | 710/1250 [17:25<16:35,  1.84s/it]
Training 1/1 epoch (loss 2.6972):  57%|█████▋    | 711/1250 [17:25<13:15,  1.48s/it]
Training 1/1 epoch (loss 2.7081):  57%|█████▋    | 711/1250 [17:28<13:15,  1.48s/it]
Training 1/1 epoch (loss 2.7081):  57%|█████▋    | 712/1250 [17:28<15:37,  1.74s/it]
Training 1/1 epoch (loss 2.4670):  57%|█████▋    | 712/1250 [17:29<15:37,  1.74s/it]
Training 1/1 epoch (loss 2.4670):  57%|█████▋    | 713/1250 [17:29<15:11,  1.70s/it]
Training 1/1 epoch (loss 2.8242):  57%|█████▋    | 713/1250 [17:31<15:11,  1.70s/it]
Training 1/1 epoch (loss 2.8242):  57%|█████▋    | 714/1250 [17:31<15:19,  1.72s/it]
Training 1/1 epoch (loss 2.7099):  57%|█████▋    | 714/1250 [17:33<15:19,  1.72s/it]
Training 1/1 epoch (loss 2.7099):  57%|█████▋    | 715/1250 [17:33<16:54,  1.90s/it]
Training 1/1 epoch (loss 2.3441):  57%|█████▋    | 715/1250 [17:34<16:54,  1.90s/it]
Training 1/1 epoch (loss 2.3441):  57%|█████▋    | 716/1250 [17:34<13:04,  1.47s/it]
Training 1/1 epoch (loss 2.6468):  57%|█████▋    | 716/1250 [17:36<13:04,  1.47s/it]
Training 1/1 epoch (loss 2.6468):  57%|█████▋    | 717/1250 [17:36<13:50,  1.56s/it]
Training 1/1 epoch (loss 2.6536):  57%|█████▋    | 717/1250 [17:38<13:50,  1.56s/it]
Training 1/1 epoch (loss 2.6536):  57%|█████▋    | 718/1250 [17:38<14:44,  1.66s/it]
Training 1/1 epoch (loss 2.6858):  57%|█████▋    | 718/1250 [17:38<14:44,  1.66s/it]
Training 1/1 epoch (loss 2.6858):  58%|█████▊    | 719/1250 [17:38<11:32,  1.30s/it]
Training 1/1 epoch (loss 2.7392):  58%|█████▊    | 719/1250 [17:41<11:32,  1.30s/it]
Training 1/1 epoch (loss 2.7392):  58%|█████▊    | 720/1250 [17:41<14:36,  1.65s/it]
Training 1/1 epoch (loss 2.5389):  58%|█████▊    | 720/1250 [17:42<14:36,  1.65s/it]
Training 1/1 epoch (loss 2.5389):  58%|█████▊    | 721/1250 [17:42<14:54,  1.69s/it]
Training 1/1 epoch (loss 2.5279):  58%|█████▊    | 721/1250 [17:43<14:54,  1.69s/it]
Training 1/1 epoch (loss 2.5279):  58%|█████▊    | 722/1250 [17:43<12:49,  1.46s/it]
Training 1/1 epoch (loss 2.4048):  58%|█████▊    | 722/1250 [17:45<12:49,  1.46s/it]
Training 1/1 epoch (loss 2.4048):  58%|█████▊    | 723/1250 [17:45<13:15,  1.51s/it]
Training 1/1 epoch (loss 2.5238):  58%|█████▊    | 723/1250 [17:46<13:15,  1.51s/it]
Training 1/1 epoch (loss 2.5238):  58%|█████▊    | 724/1250 [17:46<13:29,  1.54s/it]
Training 1/1 epoch (loss 2.8951):  58%|█████▊    | 724/1250 [17:47<13:29,  1.54s/it]
Training 1/1 epoch (loss 2.8951):  58%|█████▊    | 725/1250 [17:47<11:00,  1.26s/it]
Training 1/1 epoch (loss 2.5546):  58%|█████▊    | 725/1250 [17:49<11:00,  1.26s/it]
Training 1/1 epoch (loss 2.5546):  58%|█████▊    | 726/1250 [17:49<14:08,  1.62s/it]
Training 1/1 epoch (loss 2.4951):  58%|█████▊    | 726/1250 [17:52<14:08,  1.62s/it]
Training 1/1 epoch (loss 2.4951):  58%|█████▊    | 727/1250 [17:52<15:14,  1.75s/it]
Training 1/1 epoch (loss 2.4851):  58%|█████▊    | 727/1250 [17:52<15:14,  1.75s/it]
Training 1/1 epoch (loss 2.4851):  58%|█████▊    | 728/1250 [17:52<12:42,  1.46s/it]
Training 1/1 epoch (loss 2.6863):  58%|█████▊    | 728/1250 [17:55<12:42,  1.46s/it]
Training 1/1 epoch (loss 2.6863):  58%|█████▊    | 729/1250 [17:55<14:51,  1.71s/it]
Training 1/1 epoch (loss 2.6912):  58%|█████▊    | 729/1250 [17:56<14:51,  1.71s/it]
Training 1/1 epoch (loss 2.6912):  58%|█████▊    | 730/1250 [17:56<12:56,  1.49s/it]
Training 1/1 epoch (loss 2.6046):  58%|█████▊    | 730/1250 [17:57<12:56,  1.49s/it]
Training 1/1 epoch (loss 2.6046):  58%|█████▊    | 731/1250 [17:57<12:48,  1.48s/it]
Training 1/1 epoch (loss 2.3552):  58%|█████▊    | 731/1250 [17:59<12:48,  1.48s/it]
Training 1/1 epoch (loss 2.3552):  59%|█████▊    | 732/1250 [17:59<13:59,  1.62s/it]
Training 1/1 epoch (loss 2.4945):  59%|█████▊    | 732/1250 [18:00<13:59,  1.62s/it]
Training 1/1 epoch (loss 2.4945):  59%|█████▊    | 733/1250 [18:00<12:40,  1.47s/it]
Training 1/1 epoch (loss 2.6101):  59%|█████▊    | 733/1250 [18:02<12:40,  1.47s/it]
Training 1/1 epoch (loss 2.6101):  59%|█████▊    | 734/1250 [18:02<13:46,  1.60s/it]
Training 1/1 epoch (loss 2.5340):  59%|█████▊    | 734/1250 [18:04<13:46,  1.60s/it]
Training 1/1 epoch (loss 2.5340):  59%|█████▉    | 735/1250 [18:04<13:25,  1.56s/it]
Training 1/1 epoch (loss 2.7817):  59%|█████▉    | 735/1250 [18:04<13:25,  1.56s/it]
Training 1/1 epoch (loss 2.7817):  59%|█████▉    | 736/1250 [18:04<10:54,  1.27s/it]
Training 1/1 epoch (loss 2.4524):  59%|█████▉    | 736/1250 [18:07<10:54,  1.27s/it]
Training 1/1 epoch (loss 2.4524):  59%|█████▉    | 737/1250 [18:07<13:50,  1.62s/it]
Training 1/1 epoch (loss 2.5512):  59%|█████▉    | 737/1250 [18:08<13:50,  1.62s/it]
Training 1/1 epoch (loss 2.5512):  59%|█████▉    | 738/1250 [18:08<14:37,  1.71s/it]
Training 1/1 epoch (loss 2.6145):  59%|█████▉    | 738/1250 [18:09<14:37,  1.71s/it]
Training 1/1 epoch (loss 2.6145):  59%|█████▉    | 739/1250 [18:09<11:13,  1.32s/it]
Training 1/1 epoch (loss 2.5717):  59%|█████▉    | 739/1250 [18:11<11:13,  1.32s/it]
Training 1/1 epoch (loss 2.5717):  59%|█████▉    | 740/1250 [18:11<12:27,  1.47s/it]
Training 1/1 epoch (loss 2.5406):  59%|█████▉    | 740/1250 [18:12<12:27,  1.47s/it]
Training 1/1 epoch (loss 2.5406):  59%|█████▉    | 741/1250 [18:12<11:46,  1.39s/it]
Training 1/1 epoch (loss 2.6900):  59%|█████▉    | 741/1250 [18:13<11:46,  1.39s/it]
Training 1/1 epoch (loss 2.6900):  59%|█████▉    | 742/1250 [18:13<09:50,  1.16s/it]
Training 1/1 epoch (loss 2.6204):  59%|█████▉    | 742/1250 [18:14<09:50,  1.16s/it]
Training 1/1 epoch (loss 2.6204):  59%|█████▉    | 743/1250 [18:14<10:36,  1.25s/it]
Training 1/1 epoch (loss 2.6929):  59%|█████▉    | 743/1250 [18:17<10:36,  1.25s/it]
Training 1/1 epoch (loss 2.6929):  60%|█████▉    | 744/1250 [18:17<14:11,  1.68s/it]
Training 1/1 epoch (loss 2.5914):  60%|█████▉    | 744/1250 [18:18<14:11,  1.68s/it]
Training 1/1 epoch (loss 2.5914):  60%|█████▉    | 745/1250 [18:18<12:21,  1.47s/it]
Training 1/1 epoch (loss 2.6766):  60%|█████▉    | 745/1250 [18:20<12:21,  1.47s/it]
Training 1/1 epoch (loss 2.6766):  60%|█████▉    | 746/1250 [18:20<14:46,  1.76s/it]
Training 1/1 epoch (loss 2.4528):  60%|█████▉    | 746/1250 [18:21<14:46,  1.76s/it]
Training 1/1 epoch (loss 2.4528):  60%|█████▉    | 747/1250 [18:21<13:32,  1.61s/it]
Training 1/1 epoch (loss 2.6642):  60%|█████▉    | 747/1250 [18:22<13:32,  1.61s/it]
Training 1/1 epoch (loss 2.6642):  60%|█████▉    | 748/1250 [18:22<11:49,  1.41s/it]
Training 1/1 epoch (loss 2.4567):  60%|█████▉    | 748/1250 [18:24<11:49,  1.41s/it]
Training 1/1 epoch (loss 2.4567):  60%|█████▉    | 749/1250 [18:24<13:05,  1.57s/it]
Training 1/1 epoch (loss 2.6649):  60%|█████▉    | 749/1250 [18:26<13:05,  1.57s/it]
Training 1/1 epoch (loss 2.6649):  60%|██████    | 750/1250 [18:26<12:57,  1.56s/it]
Training 1/1 epoch (loss 2.4400):  60%|██████    | 750/1250 [18:27<12:57,  1.56s/it]
Training 1/1 epoch (loss 2.4400):  60%|██████    | 751/1250 [18:27<12:09,  1.46s/it]
Training 1/1 epoch (loss 2.6450):  60%|██████    | 751/1250 [18:29<12:09,  1.46s/it]
Training 1/1 epoch (loss 2.6450):  60%|██████    | 752/1250 [18:29<12:20,  1.49s/it]
Training 1/1 epoch (loss 2.7684):  60%|██████    | 752/1250 [18:29<12:20,  1.49s/it]
Training 1/1 epoch (loss 2.7684):  60%|██████    | 753/1250 [18:29<10:53,  1.31s/it]
Training 1/1 epoch (loss 2.7738):  60%|██████    | 753/1250 [18:31<10:53,  1.31s/it]
Training 1/1 epoch (loss 2.7738):  60%|██████    | 754/1250 [18:31<12:02,  1.46s/it]
Training 1/1 epoch (loss 2.5576):  60%|██████    | 754/1250 [18:33<12:02,  1.46s/it]
Training 1/1 epoch (loss 2.5576):  60%|██████    | 755/1250 [18:33<12:49,  1.56s/it]
Training 1/1 epoch (loss 2.7882):  60%|██████    | 755/1250 [18:34<12:49,  1.56s/it]
Training 1/1 epoch (loss 2.7882):  60%|██████    | 756/1250 [18:34<10:26,  1.27s/it]
Training 1/1 epoch (loss 2.5757):  60%|██████    | 756/1250 [18:35<10:26,  1.27s/it]
Training 1/1 epoch (loss 2.5757):  61%|██████    | 757/1250 [18:35<10:40,  1.30s/it]
Training 1/1 epoch (loss 2.5358):  61%|██████    | 757/1250 [18:37<10:40,  1.30s/it]
Training 1/1 epoch (loss 2.5358):  61%|██████    | 758/1250 [18:37<12:08,  1.48s/it]
Training 1/1 epoch (loss 2.6014):  61%|██████    | 758/1250 [18:38<12:08,  1.48s/it]
Training 1/1 epoch (loss 2.6014):  61%|██████    | 759/1250 [18:38<10:28,  1.28s/it]
Training 1/1 epoch (loss 2.6589):  61%|██████    | 759/1250 [18:40<10:28,  1.28s/it]
Training 1/1 epoch (loss 2.6589):  61%|██████    | 760/1250 [18:40<12:29,  1.53s/it]
Training 1/1 epoch (loss 2.6697):  61%|██████    | 760/1250 [18:42<12:29,  1.53s/it]
Training 1/1 epoch (loss 2.6697):  61%|██████    | 761/1250 [18:42<14:42,  1.80s/it]
Training 1/1 epoch (loss 2.4782):  61%|██████    | 761/1250 [18:43<14:42,  1.80s/it]
Training 1/1 epoch (loss 2.4782):  61%|██████    | 762/1250 [18:43<12:20,  1.52s/it]
Training 1/1 epoch (loss 2.4893):  61%|██████    | 762/1250 [18:45<12:20,  1.52s/it]
Training 1/1 epoch (loss 2.4893):  61%|██████    | 763/1250 [18:45<12:53,  1.59s/it]
Training 1/1 epoch (loss 2.6189):  61%|██████    | 763/1250 [18:46<12:53,  1.59s/it]
Training 1/1 epoch (loss 2.6189):  61%|██████    | 764/1250 [18:46<12:11,  1.50s/it]
Training 1/1 epoch (loss 2.6710):  61%|██████    | 764/1250 [18:47<12:11,  1.50s/it]
Training 1/1 epoch (loss 2.6710):  61%|██████    | 765/1250 [18:47<10:40,  1.32s/it]
Training 1/1 epoch (loss 2.3150):  61%|██████    | 765/1250 [18:48<10:40,  1.32s/it]
Training 1/1 epoch (loss 2.3150):  61%|██████▏   | 766/1250 [18:48<10:46,  1.33s/it]
Training 1/1 epoch (loss 2.4091):  61%|██████▏   | 766/1250 [18:50<10:46,  1.33s/it]
Training 1/1 epoch (loss 2.4091):  61%|██████▏   | 767/1250 [18:50<11:00,  1.37s/it]
Training 1/1 epoch (loss 2.6093):  61%|██████▏   | 767/1250 [18:51<11:00,  1.37s/it]
Training 1/1 epoch (loss 2.6093):  61%|██████▏   | 768/1250 [18:51<09:30,  1.18s/it]
Training 1/1 epoch (loss 2.7798):  61%|██████▏   | 768/1250 [18:53<09:30,  1.18s/it]
Training 1/1 epoch (loss 2.7798):  62%|██████▏   | 769/1250 [18:53<11:20,  1.41s/it]
Training 1/1 epoch (loss 2.6157):  62%|██████▏   | 769/1250 [18:53<11:20,  1.41s/it]
Training 1/1 epoch (loss 2.6157):  62%|██████▏   | 770/1250 [18:53<09:37,  1.20s/it]
Training 1/1 epoch (loss 2.6638):  62%|██████▏   | 770/1250 [18:55<09:37,  1.20s/it]
Training 1/1 epoch (loss 2.6638):  62%|██████▏   | 771/1250 [18:55<11:39,  1.46s/it]
Training 1/1 epoch (loss 2.7043):  62%|██████▏   | 771/1250 [18:58<11:39,  1.46s/it]
Training 1/1 epoch (loss 2.7043):  62%|██████▏   | 772/1250 [18:58<13:40,  1.72s/it]
Training 1/1 epoch (loss 2.5573):  62%|██████▏   | 772/1250 [18:58<13:40,  1.72s/it]
Training 1/1 epoch (loss 2.5573):  62%|██████▏   | 773/1250 [18:58<10:49,  1.36s/it]
Training 1/1 epoch (loss 2.5263):  62%|██████▏   | 773/1250 [19:00<10:49,  1.36s/it]
Training 1/1 epoch (loss 2.5263):  62%|██████▏   | 774/1250 [19:00<11:56,  1.51s/it]
Training 1/1 epoch (loss 2.6907):  62%|██████▏   | 774/1250 [19:02<11:56,  1.51s/it]
Training 1/1 epoch (loss 2.6907):  62%|██████▏   | 775/1250 [19:02<12:18,  1.55s/it]
Training 1/1 epoch (loss 2.5233):  62%|██████▏   | 775/1250 [19:03<12:18,  1.55s/it]
Training 1/1 epoch (loss 2.5233):  62%|██████▏   | 776/1250 [19:03<11:03,  1.40s/it]
Training 1/1 epoch (loss 2.6244):  62%|██████▏   | 776/1250 [19:04<11:03,  1.40s/it]
Training 1/1 epoch (loss 2.6244):  62%|██████▏   | 777/1250 [19:04<11:21,  1.44s/it]
Training 1/1 epoch (loss 2.7002):  62%|██████▏   | 777/1250 [19:05<11:21,  1.44s/it]
Training 1/1 epoch (loss 2.7002):  62%|██████▏   | 778/1250 [19:05<09:26,  1.20s/it]
Training 1/1 epoch (loss 2.5338):  62%|██████▏   | 778/1250 [19:07<09:26,  1.20s/it]
Training 1/1 epoch (loss 2.5338):  62%|██████▏   | 779/1250 [19:07<11:39,  1.49s/it]
Training 1/1 epoch (loss 2.8167):  62%|██████▏   | 779/1250 [19:09<11:39,  1.49s/it]
Training 1/1 epoch (loss 2.8167):  62%|██████▏   | 780/1250 [19:09<13:10,  1.68s/it]
Training 1/1 epoch (loss 2.4582):  62%|██████▏   | 780/1250 [19:10<13:10,  1.68s/it]
Training 1/1 epoch (loss 2.4582):  62%|██████▏   | 781/1250 [19:10<10:33,  1.35s/it]
Training 1/1 epoch (loss 2.6639):  62%|██████▏   | 781/1250 [19:12<10:33,  1.35s/it]
Training 1/1 epoch (loss 2.6639):  63%|██████▎   | 782/1250 [19:12<11:38,  1.49s/it]
Training 1/1 epoch (loss 2.6254):  63%|██████▎   | 782/1250 [19:13<11:38,  1.49s/it]
Training 1/1 epoch (loss 2.6254):  63%|██████▎   | 783/1250 [19:13<10:42,  1.38s/it]
Training 1/1 epoch (loss 2.4882):  63%|██████▎   | 783/1250 [19:14<10:42,  1.38s/it]
Training 1/1 epoch (loss 2.4882):  63%|██████▎   | 784/1250 [19:14<09:42,  1.25s/it]
Training 1/1 epoch (loss 2.7216):  63%|██████▎   | 784/1250 [19:16<09:42,  1.25s/it]
Training 1/1 epoch (loss 2.7216):  63%|██████▎   | 785/1250 [19:16<12:32,  1.62s/it]
Training 1/1 epoch (loss 2.6348):  63%|██████▎   | 785/1250 [19:17<12:32,  1.62s/it]
Training 1/1 epoch (loss 2.6348):  63%|██████▎   | 786/1250 [19:17<11:33,  1.49s/it]
Training 1/1 epoch (loss 2.6470):  63%|██████▎   | 786/1250 [19:19<11:33,  1.49s/it]
Training 1/1 epoch (loss 2.6470):  63%|██████▎   | 787/1250 [19:19<12:20,  1.60s/it]
Training 1/1 epoch (loss 2.4259):  63%|██████▎   | 787/1250 [19:20<12:20,  1.60s/it]
Training 1/1 epoch (loss 2.4259):  63%|██████▎   | 788/1250 [19:20<11:26,  1.48s/it]
Training 1/1 epoch (loss 2.4005):  63%|██████▎   | 788/1250 [19:22<11:26,  1.48s/it]
Training 1/1 epoch (loss 2.4005):  63%|██████▎   | 789/1250 [19:22<11:10,  1.46s/it]
Training 1/1 epoch (loss 2.5451):  63%|██████▎   | 789/1250 [19:24<11:10,  1.46s/it]
Training 1/1 epoch (loss 2.5451):  63%|██████▎   | 790/1250 [19:24<11:51,  1.55s/it]
Training 1/1 epoch (loss 2.5916):  63%|██████▎   | 790/1250 [19:24<11:51,  1.55s/it]
Training 1/1 epoch (loss 2.5916):  63%|██████▎   | 791/1250 [19:24<10:11,  1.33s/it]
Training 1/1 epoch (loss 2.6291):  63%|██████▎   | 791/1250 [19:26<10:11,  1.33s/it]
Training 1/1 epoch (loss 2.6291):  63%|██████▎   | 792/1250 [19:26<10:11,  1.34s/it]
Training 1/1 epoch (loss 2.4113):  63%|██████▎   | 792/1250 [19:28<10:11,  1.34s/it]
Training 1/1 epoch (loss 2.4113):  63%|██████▎   | 793/1250 [19:28<11:26,  1.50s/it]
Training 1/1 epoch (loss 2.5931):  63%|██████▎   | 793/1250 [19:28<11:26,  1.50s/it]
Training 1/1 epoch (loss 2.5931):  64%|██████▎   | 794/1250 [19:28<09:03,  1.19s/it]
Training 1/1 epoch (loss 2.7272):  64%|██████▎   | 794/1250 [19:30<09:03,  1.19s/it]
Training 1/1 epoch (loss 2.7272):  64%|██████▎   | 795/1250 [19:30<09:34,  1.26s/it]
Training 1/1 epoch (loss 2.5390):  64%|██████▎   | 795/1250 [19:31<09:34,  1.26s/it]
Training 1/1 epoch (loss 2.5390):  64%|██████▎   | 796/1250 [19:31<10:40,  1.41s/it]
Training 1/1 epoch (loss 2.4921):  64%|██████▎   | 796/1250 [19:32<10:40,  1.41s/it]
Training 1/1 epoch (loss 2.4921):  64%|██████▍   | 797/1250 [19:32<08:49,  1.17s/it]
Training 1/1 epoch (loss 2.7276):  64%|██████▍   | 797/1250 [19:34<08:49,  1.17s/it]
Training 1/1 epoch (loss 2.7276):  64%|██████▍   | 798/1250 [19:34<11:12,  1.49s/it]
Training 1/1 epoch (loss 2.6862):  64%|██████▍   | 798/1250 [19:36<11:12,  1.49s/it]
Training 1/1 epoch (loss 2.6862):  64%|██████▍   | 799/1250 [19:36<11:16,  1.50s/it]
Training 1/1 epoch (loss 2.6211):  64%|██████▍   | 799/1250 [19:37<11:16,  1.50s/it]
Training 1/1 epoch (loss 2.6211):  64%|██████▍   | 800/1250 [19:37<09:52,  1.32s/it]
Training 1/1 epoch (loss 2.5910):  64%|██████▍   | 800/1250 [19:38<09:52,  1.32s/it]
Training 1/1 epoch (loss 2.5910):  64%|██████▍   | 801/1250 [19:38<10:34,  1.41s/it]
Training 1/1 epoch (loss 2.7081):  64%|██████▍   | 801/1250 [19:39<10:34,  1.41s/it]
Training 1/1 epoch (loss 2.7081):  64%|██████▍   | 802/1250 [19:39<09:14,  1.24s/it]
Training 1/1 epoch (loss 2.6299):  64%|██████▍   | 802/1250 [19:41<09:14,  1.24s/it]
Training 1/1 epoch (loss 2.6299):  64%|██████▍   | 803/1250 [19:41<10:17,  1.38s/it]
Training 1/1 epoch (loss 2.5030):  64%|██████▍   | 803/1250 [19:43<10:17,  1.38s/it]
Training 1/1 epoch (loss 2.5030):  64%|██████▍   | 804/1250 [19:43<12:14,  1.65s/it]
Training 1/1 epoch (loss 2.6330):  64%|██████▍   | 804/1250 [19:44<12:14,  1.65s/it]
Training 1/1 epoch (loss 2.6330):  64%|██████▍   | 805/1250 [19:44<09:54,  1.34s/it]
Training 1/1 epoch (loss 2.5741):  64%|██████▍   | 805/1250 [19:46<09:54,  1.34s/it]
Training 1/1 epoch (loss 2.5741):  64%|██████▍   | 806/1250 [19:46<11:29,  1.55s/it]
Training 1/1 epoch (loss 2.6079):  64%|██████▍   | 806/1250 [19:47<11:29,  1.55s/it]
Training 1/1 epoch (loss 2.6079):  65%|██████▍   | 807/1250 [19:47<11:45,  1.59s/it]
Training 1/1 epoch (loss 2.5071):  65%|██████▍   | 807/1250 [19:48<11:45,  1.59s/it]
Training 1/1 epoch (loss 2.5071):  65%|██████▍   | 808/1250 [19:48<09:37,  1.31s/it]
Training 1/1 epoch (loss 2.5349):  65%|██████▍   | 808/1250 [19:49<09:37,  1.31s/it]
Training 1/1 epoch (loss 2.5349):  65%|██████▍   | 809/1250 [19:49<09:26,  1.28s/it]
Training 1/1 epoch (loss 2.6618):  65%|██████▍   | 809/1250 [19:51<09:26,  1.28s/it]
Training 1/1 epoch (loss 2.6618):  65%|██████▍   | 810/1250 [19:51<10:55,  1.49s/it]
Training 1/1 epoch (loss 2.5876):  65%|██████▍   | 810/1250 [19:52<10:55,  1.49s/it]
Training 1/1 epoch (loss 2.5876):  65%|██████▍   | 811/1250 [19:52<09:05,  1.24s/it]
Training 1/1 epoch (loss 2.6055):  65%|██████▍   | 811/1250 [19:54<09:05,  1.24s/it]
Training 1/1 epoch (loss 2.6055):  65%|██████▍   | 812/1250 [19:54<11:11,  1.53s/it]
Training 1/1 epoch (loss 2.5211):  65%|██████▍   | 812/1250 [19:56<11:11,  1.53s/it]
Training 1/1 epoch (loss 2.5211):  65%|██████▌   | 813/1250 [19:56<11:18,  1.55s/it]
Training 1/1 epoch (loss 2.6334):  65%|██████▌   | 813/1250 [19:56<11:18,  1.55s/it]
Training 1/1 epoch (loss 2.6334):  65%|██████▌   | 814/1250 [19:56<09:02,  1.25s/it]
Training 1/1 epoch (loss 2.6441):  65%|██████▌   | 814/1250 [19:58<09:02,  1.25s/it]
Training 1/1 epoch (loss 2.6441):  65%|██████▌   | 815/1250 [19:58<09:32,  1.31s/it]
Training 1/1 epoch (loss 2.7660):  65%|██████▌   | 815/1250 [19:59<09:32,  1.31s/it]
Training 1/1 epoch (loss 2.7660):  65%|██████▌   | 816/1250 [19:59<09:30,  1.31s/it]
Training 1/1 epoch (loss 2.6304):  65%|██████▌   | 816/1250 [20:00<09:30,  1.31s/it]
Training 1/1 epoch (loss 2.6304):  65%|██████▌   | 817/1250 [20:00<08:03,  1.12s/it]
Training 1/1 epoch (loss 2.4917):  65%|██████▌   | 817/1250 [20:01<08:03,  1.12s/it]
Training 1/1 epoch (loss 2.4917):  65%|██████▌   | 818/1250 [20:01<08:18,  1.15s/it]
Training 1/1 epoch (loss 2.7647):  65%|██████▌   | 818/1250 [20:02<08:18,  1.15s/it]
Training 1/1 epoch (loss 2.7647):  66%|██████▌   | 819/1250 [20:02<08:23,  1.17s/it]
Training 1/1 epoch (loss 2.5597):  66%|██████▌   | 819/1250 [20:04<08:23,  1.17s/it]
Training 1/1 epoch (loss 2.5597):  66%|██████▌   | 820/1250 [20:04<08:54,  1.24s/it]
Training 1/1 epoch (loss 2.4858):  66%|██████▌   | 820/1250 [20:06<08:54,  1.24s/it]
Training 1/1 epoch (loss 2.4858):  66%|██████▌   | 821/1250 [20:06<11:11,  1.57s/it]
Training 1/1 epoch (loss 2.4307):  66%|██████▌   | 821/1250 [20:07<11:11,  1.57s/it]
Training 1/1 epoch (loss 2.4307):  66%|██████▌   | 822/1250 [20:07<09:33,  1.34s/it]
Training 1/1 epoch (loss 2.4565):  66%|██████▌   | 822/1250 [20:08<09:33,  1.34s/it]
Training 1/1 epoch (loss 2.4565):  66%|██████▌   | 823/1250 [20:08<09:28,  1.33s/it]
Training 1/1 epoch (loss 2.4885):  66%|██████▌   | 823/1250 [20:10<09:28,  1.33s/it]
Training 1/1 epoch (loss 2.4885):  66%|██████▌   | 824/1250 [20:10<11:45,  1.66s/it]
Training 1/1 epoch (loss 2.5281):  66%|██████▌   | 824/1250 [20:11<11:45,  1.66s/it]
Training 1/1 epoch (loss 2.5281):  66%|██████▌   | 825/1250 [20:11<09:52,  1.39s/it]
Training 1/1 epoch (loss 2.7554):  66%|██████▌   | 825/1250 [20:13<09:52,  1.39s/it]
Training 1/1 epoch (loss 2.7554):  66%|██████▌   | 826/1250 [20:13<11:11,  1.58s/it]
Training 1/1 epoch (loss 2.6348):  66%|██████▌   | 826/1250 [20:14<11:11,  1.58s/it]
Training 1/1 epoch (loss 2.6348):  66%|██████▌   | 827/1250 [20:14<10:19,  1.46s/it]
Training 1/1 epoch (loss 2.5573):  66%|██████▌   | 827/1250 [20:16<10:19,  1.46s/it]
Training 1/1 epoch (loss 2.5573):  66%|██████▌   | 828/1250 [20:16<10:12,  1.45s/it]
Training 1/1 epoch (loss 2.5925):  66%|██████▌   | 828/1250 [20:18<10:12,  1.45s/it]
Training 1/1 epoch (loss 2.5925):  66%|██████▋   | 829/1250 [20:18<10:52,  1.55s/it]
Training 1/1 epoch (loss 2.5363):  66%|██████▋   | 829/1250 [20:18<10:52,  1.55s/it]
Training 1/1 epoch (loss 2.5363):  66%|██████▋   | 830/1250 [20:18<09:21,  1.34s/it]
Training 1/1 epoch (loss 2.5350):  66%|██████▋   | 830/1250 [20:19<09:21,  1.34s/it]
Training 1/1 epoch (loss 2.5350):  66%|██████▋   | 831/1250 [20:19<08:37,  1.24s/it]
Training 1/1 epoch (loss 2.7175):  66%|██████▋   | 831/1250 [20:22<08:37,  1.24s/it]
Training 1/1 epoch (loss 2.7175):  67%|██████▋   | 832/1250 [20:22<10:30,  1.51s/it]
Training 1/1 epoch (loss 2.5325):  67%|██████▋   | 832/1250 [20:22<10:30,  1.51s/it]
Training 1/1 epoch (loss 2.5325):  67%|██████▋   | 833/1250 [20:22<09:15,  1.33s/it]
Training 1/1 epoch (loss 2.6689):  67%|██████▋   | 833/1250 [20:24<09:15,  1.33s/it]
Training 1/1 epoch (loss 2.6689):  67%|██████▋   | 834/1250 [20:24<08:51,  1.28s/it]
Training 1/1 epoch (loss 2.7942):  67%|██████▋   | 834/1250 [20:26<08:51,  1.28s/it]
Training 1/1 epoch (loss 2.7942):  67%|██████▋   | 835/1250 [20:26<10:15,  1.48s/it]
Training 1/1 epoch (loss 2.5888):  67%|██████▋   | 835/1250 [20:26<10:15,  1.48s/it]
Training 1/1 epoch (loss 2.5888):  67%|██████▋   | 836/1250 [20:26<08:36,  1.25s/it]
Training 1/1 epoch (loss 2.5762):  67%|██████▋   | 836/1250 [20:28<08:36,  1.25s/it]
Training 1/1 epoch (loss 2.5762):  67%|██████▋   | 837/1250 [20:28<08:51,  1.29s/it]
Training 1/1 epoch (loss 2.6959):  67%|██████▋   | 837/1250 [20:29<08:51,  1.29s/it]
Training 1/1 epoch (loss 2.6959):  67%|██████▋   | 838/1250 [20:29<08:55,  1.30s/it]
Training 1/1 epoch (loss 2.6638):  67%|██████▋   | 838/1250 [20:29<08:55,  1.30s/it]
Training 1/1 epoch (loss 2.6638):  67%|██████▋   | 839/1250 [20:29<07:07,  1.04s/it]
Training 1/1 epoch (loss 2.3857):  67%|██████▋   | 839/1250 [20:31<07:07,  1.04s/it]
Training 1/1 epoch (loss 2.3857):  67%|██████▋   | 840/1250 [20:31<08:48,  1.29s/it]
Training 1/1 epoch (loss 2.5791):  67%|██████▋   | 840/1250 [20:33<08:48,  1.29s/it]
Training 1/1 epoch (loss 2.5791):  67%|██████▋   | 841/1250 [20:33<10:00,  1.47s/it]
Training 1/1 epoch (loss 2.7169):  67%|██████▋   | 841/1250 [20:34<10:00,  1.47s/it]
Training 1/1 epoch (loss 2.7169):  67%|██████▋   | 842/1250 [20:34<08:10,  1.20s/it]
Training 1/1 epoch (loss 2.5354):  67%|██████▋   | 842/1250 [20:35<08:10,  1.20s/it]
Training 1/1 epoch (loss 2.5354):  67%|██████▋   | 843/1250 [20:35<07:51,  1.16s/it]
Training 1/1 epoch (loss 2.7006):  67%|██████▋   | 843/1250 [20:37<07:51,  1.16s/it]
Training 1/1 epoch (loss 2.7006):  68%|██████▊   | 844/1250 [20:37<10:12,  1.51s/it]
Training 1/1 epoch (loss 2.5832):  68%|██████▊   | 844/1250 [20:38<10:12,  1.51s/it]
Training 1/1 epoch (loss 2.5832):  68%|██████▊   | 845/1250 [20:38<09:48,  1.45s/it]
Training 1/1 epoch (loss 2.6906):  68%|██████▊   | 845/1250 [20:40<09:48,  1.45s/it]
Training 1/1 epoch (loss 2.6906):  68%|██████▊   | 846/1250 [20:40<10:41,  1.59s/it]
Training 1/1 epoch (loss 2.5068):  68%|██████▊   | 846/1250 [20:42<10:41,  1.59s/it]
Training 1/1 epoch (loss 2.5068):  68%|██████▊   | 847/1250 [20:42<10:35,  1.58s/it]
Training 1/1 epoch (loss 2.6124):  68%|██████▊   | 847/1250 [20:44<10:35,  1.58s/it]
Training 1/1 epoch (loss 2.6124):  68%|██████▊   | 848/1250 [20:44<10:52,  1.62s/it]
Training 1/1 epoch (loss 2.6230):  68%|██████▊   | 848/1250 [20:45<10:52,  1.62s/it]
Training 1/1 epoch (loss 2.6230):  68%|██████▊   | 849/1250 [20:45<10:35,  1.59s/it]
Training 1/1 epoch (loss 2.7716):  68%|██████▊   | 849/1250 [20:46<10:35,  1.59s/it]
Training 1/1 epoch (loss 2.7716):  68%|██████▊   | 850/1250 [20:46<08:25,  1.26s/it]
Training 1/1 epoch (loss 2.5207):  68%|██████▊   | 850/1250 [20:47<08:25,  1.26s/it]
Training 1/1 epoch (loss 2.5207):  68%|██████▊   | 851/1250 [20:47<09:20,  1.40s/it]
Training 1/1 epoch (loss 2.4372):  68%|██████▊   | 851/1250 [20:49<09:20,  1.40s/it]
Training 1/1 epoch (loss 2.4372):  68%|██████▊   | 852/1250 [20:49<09:14,  1.39s/it]
Training 1/1 epoch (loss 2.7808):  68%|██████▊   | 852/1250 [20:49<09:14,  1.39s/it]
Training 1/1 epoch (loss 2.7808):  68%|██████▊   | 853/1250 [20:49<07:18,  1.10s/it]
Training 1/1 epoch (loss 2.5053):  68%|██████▊   | 853/1250 [20:50<07:18,  1.10s/it]
Training 1/1 epoch (loss 2.5053):  68%|██████▊   | 854/1250 [20:50<07:40,  1.16s/it]
Training 1/1 epoch (loss 2.7193):  68%|██████▊   | 854/1250 [20:53<07:40,  1.16s/it]
Training 1/1 epoch (loss 2.7193):  68%|██████▊   | 855/1250 [20:53<09:58,  1.51s/it]
Training 1/1 epoch (loss 2.3415):  68%|██████▊   | 855/1250 [20:53<09:58,  1.51s/it]
Training 1/1 epoch (loss 2.3415):  68%|██████▊   | 856/1250 [20:53<08:09,  1.24s/it]
Training 1/1 epoch (loss 2.6195):  68%|██████▊   | 856/1250 [20:55<08:09,  1.24s/it]
Training 1/1 epoch (loss 2.6195):  69%|██████▊   | 857/1250 [20:55<08:46,  1.34s/it]
Training 1/1 epoch (loss 2.5837):  69%|██████▊   | 857/1250 [20:56<08:46,  1.34s/it]
Training 1/1 epoch (loss 2.5837):  69%|██████▊   | 858/1250 [20:56<08:41,  1.33s/it]
Training 1/1 epoch (loss 2.5090):  69%|██████▊   | 858/1250 [20:57<08:41,  1.33s/it]
Training 1/1 epoch (loss 2.5090):  69%|██████▊   | 859/1250 [20:57<07:28,  1.15s/it]
Training 1/1 epoch (loss 2.5764):  69%|██████▊   | 859/1250 [20:59<07:28,  1.15s/it]
Training 1/1 epoch (loss 2.5764):  69%|██████▉   | 860/1250 [20:59<08:19,  1.28s/it]
Training 1/1 epoch (loss 2.6460):  69%|██████▉   | 860/1250 [21:00<08:19,  1.28s/it]
Training 1/1 epoch (loss 2.6460):  69%|██████▉   | 861/1250 [21:00<07:58,  1.23s/it]
Training 1/1 epoch (loss 2.5679):  69%|██████▉   | 861/1250 [21:01<07:58,  1.23s/it]
Training 1/1 epoch (loss 2.5679):  69%|██████▉   | 862/1250 [21:01<07:49,  1.21s/it]
Training 1/1 epoch (loss 2.6031):  69%|██████▉   | 862/1250 [21:02<07:49,  1.21s/it]
Training 1/1 epoch (loss 2.6031):  69%|██████▉   | 863/1250 [21:02<08:01,  1.24s/it]
Training 1/1 epoch (loss 2.5348):  69%|██████▉   | 863/1250 [21:03<08:01,  1.24s/it]
Training 1/1 epoch (loss 2.5348):  69%|██████▉   | 864/1250 [21:03<07:21,  1.14s/it]
Training 1/1 epoch (loss 2.5406):  69%|██████▉   | 864/1250 [21:05<07:21,  1.14s/it]
Training 1/1 epoch (loss 2.5406):  69%|██████▉   | 865/1250 [21:05<08:58,  1.40s/it]
Training 1/1 epoch (loss 2.4610):  69%|██████▉   | 865/1250 [21:07<08:58,  1.40s/it]
Training 1/1 epoch (loss 2.4610):  69%|██████▉   | 866/1250 [21:07<09:48,  1.53s/it]
Training 1/1 epoch (loss 2.6391):  69%|██████▉   | 866/1250 [21:08<09:48,  1.53s/it]
Training 1/1 epoch (loss 2.6391):  69%|██████▉   | 867/1250 [21:08<07:57,  1.25s/it]
Training 1/1 epoch (loss 2.8108):  69%|██████▉   | 867/1250 [21:09<07:57,  1.25s/it]
Training 1/1 epoch (loss 2.8108):  69%|██████▉   | 868/1250 [21:09<09:09,  1.44s/it]
Training 1/1 epoch (loss 2.4407):  69%|██████▉   | 868/1250 [21:12<09:09,  1.44s/it]
Training 1/1 epoch (loss 2.4407):  70%|██████▉   | 869/1250 [21:12<11:08,  1.76s/it]
Training 1/1 epoch (loss 2.4503):  70%|██████▉   | 869/1250 [21:12<11:08,  1.76s/it]
Training 1/1 epoch (loss 2.4503):  70%|██████▉   | 870/1250 [21:12<08:38,  1.36s/it]
Training 1/1 epoch (loss 2.5171):  70%|██████▉   | 870/1250 [21:15<08:38,  1.36s/it]
Training 1/1 epoch (loss 2.5171):  70%|██████▉   | 871/1250 [21:15<10:37,  1.68s/it]
Training 1/1 epoch (loss 2.5934):  70%|██████▉   | 871/1250 [21:16<10:37,  1.68s/it]
Training 1/1 epoch (loss 2.5934):  70%|██████▉   | 872/1250 [21:16<10:01,  1.59s/it]
Training 1/1 epoch (loss 2.7718):  70%|██████▉   | 872/1250 [21:17<10:01,  1.59s/it]
Training 1/1 epoch (loss 2.7718):  70%|██████▉   | 873/1250 [21:17<08:28,  1.35s/it]
Training 1/1 epoch (loss 2.5617):  70%|██████▉   | 873/1250 [21:19<08:28,  1.35s/it]
Training 1/1 epoch (loss 2.5617):  70%|██████▉   | 874/1250 [21:19<10:34,  1.69s/it]
Training 1/1 epoch (loss 2.6053):  70%|██████▉   | 874/1250 [21:21<10:34,  1.69s/it]
Training 1/1 epoch (loss 2.6053):  70%|███████   | 875/1250 [21:21<10:18,  1.65s/it]
Training 1/1 epoch (loss 2.6612):  70%|███████   | 875/1250 [21:22<10:18,  1.65s/it]
Training 1/1 epoch (loss 2.6612):  70%|███████   | 876/1250 [21:22<08:55,  1.43s/it]
Training 1/1 epoch (loss 2.7251):  70%|███████   | 876/1250 [21:23<08:55,  1.43s/it]
Training 1/1 epoch (loss 2.7251):  70%|███████   | 877/1250 [21:23<08:39,  1.39s/it]
Training 1/1 epoch (loss 2.8156):  70%|███████   | 877/1250 [21:24<08:39,  1.39s/it]
Training 1/1 epoch (loss 2.8156):  70%|███████   | 878/1250 [21:24<08:22,  1.35s/it]
Training 1/1 epoch (loss 2.6279):  70%|███████   | 878/1250 [21:25<08:22,  1.35s/it]
Training 1/1 epoch (loss 2.6279):  70%|███████   | 879/1250 [21:25<07:33,  1.22s/it]
Training 1/1 epoch (loss 2.7227):  70%|███████   | 879/1250 [21:27<07:33,  1.22s/it]
Training 1/1 epoch (loss 2.7227):  70%|███████   | 880/1250 [21:27<08:10,  1.33s/it]
Training 1/1 epoch (loss 2.4996):  70%|███████   | 880/1250 [21:28<08:10,  1.33s/it]
Training 1/1 epoch (loss 2.4996):  70%|███████   | 881/1250 [21:28<07:23,  1.20s/it]
Training 1/1 epoch (loss 2.6115):  70%|███████   | 881/1250 [21:29<07:23,  1.20s/it]
Training 1/1 epoch (loss 2.6115):  71%|███████   | 882/1250 [21:29<06:33,  1.07s/it]
Training 1/1 epoch (loss 2.7681):  71%|███████   | 882/1250 [21:31<06:33,  1.07s/it]
Training 1/1 epoch (loss 2.7681):  71%|███████   | 883/1250 [21:31<08:10,  1.34s/it]
Training 1/1 epoch (loss 2.6786):  71%|███████   | 883/1250 [21:32<08:10,  1.34s/it]
Training 1/1 epoch (loss 2.6786):  71%|███████   | 884/1250 [21:32<08:06,  1.33s/it]
Training 1/1 epoch (loss 2.5621):  71%|███████   | 884/1250 [21:33<08:06,  1.33s/it]
Training 1/1 epoch (loss 2.5621):  71%|███████   | 885/1250 [21:33<07:56,  1.30s/it]
Training 1/1 epoch (loss 2.6602):  71%|███████   | 885/1250 [21:35<07:56,  1.30s/it]
Training 1/1 epoch (loss 2.6602):  71%|███████   | 886/1250 [21:35<08:55,  1.47s/it]
Training 1/1 epoch (loss 2.5998):  71%|███████   | 886/1250 [21:36<08:55,  1.47s/it]
Training 1/1 epoch (loss 2.5998):  71%|███████   | 887/1250 [21:36<08:02,  1.33s/it]
Training 1/1 epoch (loss 2.5609):  71%|███████   | 887/1250 [21:38<08:02,  1.33s/it]
Training 1/1 epoch (loss 2.5609):  71%|███████   | 888/1250 [21:38<08:52,  1.47s/it]
Training 1/1 epoch (loss 2.6031):  71%|███████   | 888/1250 [21:40<08:52,  1.47s/it]
Training 1/1 epoch (loss 2.6031):  71%|███████   | 889/1250 [21:40<09:23,  1.56s/it]
Training 1/1 epoch (loss 2.6048):  71%|███████   | 889/1250 [21:40<09:23,  1.56s/it]
Training 1/1 epoch (loss 2.6048):  71%|███████   | 890/1250 [21:40<07:25,  1.24s/it]
Training 1/1 epoch (loss 2.7464):  71%|███████   | 890/1250 [21:42<07:25,  1.24s/it]
Training 1/1 epoch (loss 2.7464):  71%|███████▏  | 891/1250 [21:42<09:29,  1.59s/it]
Training 1/1 epoch (loss 2.5917):  71%|███████▏  | 891/1250 [21:45<09:29,  1.59s/it]
Training 1/1 epoch (loss 2.5917):  71%|███████▏  | 892/1250 [21:45<10:59,  1.84s/it]
Training 1/1 epoch (loss 2.4278):  71%|███████▏  | 892/1250 [21:45<10:59,  1.84s/it]
Training 1/1 epoch (loss 2.4278):  71%|███████▏  | 893/1250 [21:45<08:28,  1.42s/it]
Training 1/1 epoch (loss 2.4345):  71%|███████▏  | 893/1250 [21:47<08:28,  1.42s/it]
Training 1/1 epoch (loss 2.4345):  72%|███████▏  | 894/1250 [21:47<09:16,  1.56s/it]
Training 1/1 epoch (loss 2.9056):  72%|███████▏  | 894/1250 [21:49<09:16,  1.56s/it]
Training 1/1 epoch (loss 2.9056):  72%|███████▏  | 895/1250 [21:49<09:30,  1.61s/it]
Training 1/1 epoch (loss 2.2784):  72%|███████▏  | 895/1250 [21:50<09:30,  1.61s/it]
Training 1/1 epoch (loss 2.2784):  72%|███████▏  | 896/1250 [21:50<08:15,  1.40s/it]
Training 1/1 epoch (loss 2.5317):  72%|███████▏  | 896/1250 [21:52<08:15,  1.40s/it]
Training 1/1 epoch (loss 2.5317):  72%|███████▏  | 897/1250 [21:52<09:09,  1.56s/it]
Training 1/1 epoch (loss 2.6922):  72%|███████▏  | 897/1250 [21:53<09:09,  1.56s/it]
Training 1/1 epoch (loss 2.6922):  72%|███████▏  | 898/1250 [21:53<07:58,  1.36s/it]
Training 1/1 epoch (loss 2.5874):  72%|███████▏  | 898/1250 [21:55<07:58,  1.36s/it]
Training 1/1 epoch (loss 2.5874):  72%|███████▏  | 899/1250 [21:55<09:00,  1.54s/it]
Training 1/1 epoch (loss 2.7648):  72%|███████▏  | 899/1250 [21:56<09:00,  1.54s/it]
Training 1/1 epoch (loss 2.7648):  72%|███████▏  | 900/1250 [21:56<08:58,  1.54s/it]
Training 1/1 epoch (loss 2.6152):  72%|███████▏  | 900/1250 [21:57<08:58,  1.54s/it]
Training 1/1 epoch (loss 2.6152):  72%|███████▏  | 901/1250 [21:57<07:53,  1.36s/it]
Training 1/1 epoch (loss 2.6407):  72%|███████▏  | 901/1250 [21:59<07:53,  1.36s/it]
Training 1/1 epoch (loss 2.6407):  72%|███████▏  | 902/1250 [21:59<09:17,  1.60s/it]
Training 1/1 epoch (loss 2.5982):  72%|███████▏  | 902/1250 [22:02<09:17,  1.60s/it]
Training 1/1 epoch (loss 2.5982):  72%|███████▏  | 903/1250 [22:02<10:26,  1.80s/it]
Training 1/1 epoch (loss 2.6316):  72%|███████▏  | 903/1250 [22:03<10:26,  1.80s/it]
Training 1/1 epoch (loss 2.6316):  72%|███████▏  | 904/1250 [22:03<09:40,  1.68s/it]
Training 1/1 epoch (loss 2.5046):  72%|███████▏  | 904/1250 [22:05<09:40,  1.68s/it]
Training 1/1 epoch (loss 2.5046):  72%|███████▏  | 905/1250 [22:05<10:04,  1.75s/it]
Training 1/1 epoch (loss 2.4795):  72%|███████▏  | 905/1250 [22:06<10:04,  1.75s/it]
Training 1/1 epoch (loss 2.4795):  72%|███████▏  | 906/1250 [22:06<08:55,  1.56s/it]
Training 1/1 epoch (loss 2.4291):  72%|███████▏  | 906/1250 [22:07<08:55,  1.56s/it]
Training 1/1 epoch (loss 2.4291):  73%|███████▎  | 907/1250 [22:07<07:39,  1.34s/it]
Training 1/1 epoch (loss 2.4618):  73%|███████▎  | 907/1250 [22:08<07:39,  1.34s/it]
Training 1/1 epoch (loss 2.4618):  73%|███████▎  | 908/1250 [22:08<08:00,  1.41s/it]
Training 1/1 epoch (loss 2.7279):  73%|███████▎  | 908/1250 [22:09<08:00,  1.41s/it]
Training 1/1 epoch (loss 2.7279):  73%|███████▎  | 909/1250 [22:09<07:28,  1.32s/it]
Training 1/1 epoch (loss 2.5039):  73%|███████▎  | 909/1250 [22:11<07:28,  1.32s/it]
Training 1/1 epoch (loss 2.5039):  73%|███████▎  | 910/1250 [22:11<07:51,  1.39s/it]
Training 1/1 epoch (loss 2.3722):  73%|███████▎  | 910/1250 [22:13<07:51,  1.39s/it]
Training 1/1 epoch (loss 2.3722):  73%|███████▎  | 911/1250 [22:13<08:08,  1.44s/it]
Training 1/1 epoch (loss 2.6333):  73%|███████▎  | 911/1250 [22:13<08:08,  1.44s/it]
Training 1/1 epoch (loss 2.6333):  73%|███████▎  | 912/1250 [22:13<06:51,  1.22s/it]
Training 1/1 epoch (loss 2.4461):  73%|███████▎  | 912/1250 [22:15<06:51,  1.22s/it]
Training 1/1 epoch (loss 2.4461):  73%|███████▎  | 913/1250 [22:15<07:27,  1.33s/it]
Training 1/1 epoch (loss 2.5899):  73%|███████▎  | 913/1250 [22:16<07:27,  1.33s/it]
Training 1/1 epoch (loss 2.5899):  73%|███████▎  | 914/1250 [22:16<07:43,  1.38s/it]
Training 1/1 epoch (loss 2.6921):  73%|███████▎  | 914/1250 [22:18<07:43,  1.38s/it]
Training 1/1 epoch (loss 2.6921):  73%|███████▎  | 915/1250 [22:18<07:33,  1.35s/it]
Training 1/1 epoch (loss 2.6312):  73%|███████▎  | 915/1250 [22:19<07:33,  1.35s/it]
Training 1/1 epoch (loss 2.6312):  73%|███████▎  | 916/1250 [22:19<07:33,  1.36s/it]
Training 1/1 epoch (loss 2.3663):  73%|███████▎  | 916/1250 [22:20<07:33,  1.36s/it]
Training 1/1 epoch (loss 2.3663):  73%|███████▎  | 917/1250 [22:20<06:39,  1.20s/it]
Training 1/1 epoch (loss 2.7745):  73%|███████▎  | 917/1250 [22:21<06:39,  1.20s/it]
Training 1/1 epoch (loss 2.7745):  73%|███████▎  | 918/1250 [22:21<06:20,  1.15s/it]
Training 1/1 epoch (loss 2.5045):  73%|███████▎  | 918/1250 [22:22<06:20,  1.15s/it]
Training 1/1 epoch (loss 2.5045):  74%|███████▎  | 919/1250 [22:22<06:51,  1.24s/it]
Training 1/1 epoch (loss 2.6749):  74%|███████▎  | 919/1250 [22:23<06:51,  1.24s/it]
Training 1/1 epoch (loss 2.6749):  74%|███████▎  | 920/1250 [22:23<05:49,  1.06s/it]
Training 1/1 epoch (loss 2.5836):  74%|███████▎  | 920/1250 [22:25<05:49,  1.06s/it]
Training 1/1 epoch (loss 2.5836):  74%|███████▎  | 921/1250 [22:25<08:04,  1.47s/it]
Training 1/1 epoch (loss 2.5361):  74%|███████▎  | 921/1250 [22:27<08:04,  1.47s/it]
Training 1/1 epoch (loss 2.5361):  74%|███████▍  | 922/1250 [22:27<08:20,  1.53s/it]
Training 1/1 epoch (loss 2.4722):  74%|███████▍  | 922/1250 [22:28<08:20,  1.53s/it]
Training 1/1 epoch (loss 2.4722):  74%|███████▍  | 923/1250 [22:28<06:45,  1.24s/it]
Training 1/1 epoch (loss 2.7755):  74%|███████▍  | 923/1250 [22:29<06:45,  1.24s/it]
Training 1/1 epoch (loss 2.7755):  74%|███████▍  | 924/1250 [22:29<07:26,  1.37s/it]
Training 1/1 epoch (loss 2.6048):  74%|███████▍  | 924/1250 [22:31<07:26,  1.37s/it]
Training 1/1 epoch (loss 2.6048):  74%|███████▍  | 925/1250 [22:31<07:55,  1.46s/it]
Training 1/1 epoch (loss 2.6251):  74%|███████▍  | 925/1250 [22:32<07:55,  1.46s/it]
Training 1/1 epoch (loss 2.6251):  74%|███████▍  | 926/1250 [22:32<07:13,  1.34s/it]
Training 1/1 epoch (loss 2.5272):  74%|███████▍  | 926/1250 [22:34<07:13,  1.34s/it]
Training 1/1 epoch (loss 2.5272):  74%|███████▍  | 927/1250 [22:34<08:15,  1.54s/it]
Training 1/1 epoch (loss 2.8139):  74%|███████▍  | 927/1250 [22:36<08:15,  1.54s/it]
Training 1/1 epoch (loss 2.8139):  74%|███████▍  | 928/1250 [22:36<08:21,  1.56s/it]
Training 1/1 epoch (loss 2.6710):  74%|███████▍  | 928/1250 [22:37<08:21,  1.56s/it]
Training 1/1 epoch (loss 2.6710):  74%|███████▍  | 929/1250 [22:37<07:21,  1.37s/it]
Training 1/1 epoch (loss 2.7887):  74%|███████▍  | 929/1250 [22:39<07:21,  1.37s/it]
Training 1/1 epoch (loss 2.7887):  74%|███████▍  | 930/1250 [22:39<09:05,  1.70s/it]
Training 1/1 epoch (loss 2.6824):  74%|███████▍  | 930/1250 [22:40<09:05,  1.70s/it]
Training 1/1 epoch (loss 2.6824):  74%|███████▍  | 931/1250 [22:40<08:11,  1.54s/it]
Training 1/1 epoch (loss 2.5978):  74%|███████▍  | 931/1250 [22:42<08:11,  1.54s/it]
Training 1/1 epoch (loss 2.5978):  75%|███████▍  | 932/1250 [22:42<08:37,  1.63s/it]
Training 1/1 epoch (loss 2.6021):  75%|███████▍  | 932/1250 [22:44<08:37,  1.63s/it]
Training 1/1 epoch (loss 2.6021):  75%|███████▍  | 933/1250 [22:44<08:54,  1.69s/it]
Training 1/1 epoch (loss 2.4795):  75%|███████▍  | 933/1250 [22:45<08:54,  1.69s/it]
Training 1/1 epoch (loss 2.4795):  75%|███████▍  | 934/1250 [22:45<07:13,  1.37s/it]
Training 1/1 epoch (loss 2.5124):  75%|███████▍  | 934/1250 [22:46<07:13,  1.37s/it]
Training 1/1 epoch (loss 2.5124):  75%|███████▍  | 935/1250 [22:46<07:23,  1.41s/it]
Training 1/1 epoch (loss 2.6426):  75%|███████▍  | 935/1250 [22:48<07:23,  1.41s/it]
Training 1/1 epoch (loss 2.6426):  75%|███████▍  | 936/1250 [22:48<07:39,  1.46s/it]
Training 1/1 epoch (loss 2.3844):  75%|███████▍  | 936/1250 [22:48<07:39,  1.46s/it]
Training 1/1 epoch (loss 2.3844):  75%|███████▍  | 937/1250 [22:48<06:38,  1.27s/it]
Training 1/1 epoch (loss 2.5120):  75%|███████▍  | 937/1250 [22:50<06:38,  1.27s/it]
Training 1/1 epoch (loss 2.5120):  75%|███████▌  | 938/1250 [22:50<07:24,  1.43s/it]
Training 1/1 epoch (loss 2.6529):  75%|███████▌  | 938/1250 [22:51<07:24,  1.43s/it]
Training 1/1 epoch (loss 2.6529):  75%|███████▌  | 939/1250 [22:51<06:58,  1.34s/it]
Training 1/1 epoch (loss 2.6475):  75%|███████▌  | 939/1250 [22:53<06:58,  1.34s/it]
Training 1/1 epoch (loss 2.6475):  75%|███████▌  | 940/1250 [22:53<07:34,  1.46s/it]
Training 1/1 epoch (loss 2.5826):  75%|███████▌  | 940/1250 [22:55<07:34,  1.46s/it]
Training 1/1 epoch (loss 2.5826):  75%|███████▌  | 941/1250 [22:55<07:41,  1.49s/it]
Training 1/1 epoch (loss 2.5538):  75%|███████▌  | 941/1250 [22:55<07:41,  1.49s/it]
Training 1/1 epoch (loss 2.5538):  75%|███████▌  | 942/1250 [22:55<06:20,  1.23s/it]
Training 1/1 epoch (loss 2.4481):  75%|███████▌  | 942/1250 [22:57<06:20,  1.23s/it]
Training 1/1 epoch (loss 2.4481):  75%|███████▌  | 943/1250 [22:57<07:13,  1.41s/it]
Training 1/1 epoch (loss 2.3013):  75%|███████▌  | 943/1250 [22:58<07:13,  1.41s/it]
Training 1/1 epoch (loss 2.3013):  76%|███████▌  | 944/1250 [22:58<07:04,  1.39s/it]
Training 1/1 epoch (loss 2.5500):  76%|███████▌  | 944/1250 [22:59<07:04,  1.39s/it]
Training 1/1 epoch (loss 2.5500):  76%|███████▌  | 945/1250 [22:59<05:56,  1.17s/it]
Training 1/1 epoch (loss 2.6140):  76%|███████▌  | 945/1250 [23:02<05:56,  1.17s/it]
Training 1/1 epoch (loss 2.6140):  76%|███████▌  | 946/1250 [23:02<07:54,  1.56s/it]
Training 1/1 epoch (loss 2.5047):  76%|███████▌  | 946/1250 [23:03<07:54,  1.56s/it]
Training 1/1 epoch (loss 2.5047):  76%|███████▌  | 947/1250 [23:03<07:33,  1.50s/it]
Training 1/1 epoch (loss 2.4620):  76%|███████▌  | 947/1250 [23:04<07:33,  1.50s/it]
Training 1/1 epoch (loss 2.4620):  76%|███████▌  | 948/1250 [23:04<06:09,  1.22s/it]
Training 1/1 epoch (loss 2.6158):  76%|███████▌  | 948/1250 [23:05<06:09,  1.22s/it]
Training 1/1 epoch (loss 2.6158):  76%|███████▌  | 949/1250 [23:05<06:59,  1.39s/it]
Training 1/1 epoch (loss 2.4767):  76%|███████▌  | 949/1250 [23:07<06:59,  1.39s/it]
Training 1/1 epoch (loss 2.4767):  76%|███████▌  | 950/1250 [23:07<07:34,  1.51s/it]
Training 1/1 epoch (loss 2.3984):  76%|███████▌  | 950/1250 [23:08<07:34,  1.51s/it]
Training 1/1 epoch (loss 2.3984):  76%|███████▌  | 951/1250 [23:08<06:09,  1.24s/it]
Training 1/1 epoch (loss 2.7034):  76%|███████▌  | 951/1250 [23:10<06:09,  1.24s/it]
Training 1/1 epoch (loss 2.7034):  76%|███████▌  | 952/1250 [23:10<07:44,  1.56s/it]
Training 1/1 epoch (loss 2.4641):  76%|███████▌  | 952/1250 [23:12<07:44,  1.56s/it]
Training 1/1 epoch (loss 2.4641):  76%|███████▌  | 953/1250 [23:12<07:49,  1.58s/it]
Training 1/1 epoch (loss 2.5437):  76%|███████▌  | 953/1250 [23:12<07:49,  1.58s/it]
Training 1/1 epoch (loss 2.5437):  76%|███████▋  | 954/1250 [23:12<06:08,  1.24s/it]
Training 1/1 epoch (loss 2.5106):  76%|███████▋  | 954/1250 [23:13<06:08,  1.24s/it]
Training 1/1 epoch (loss 2.5106):  76%|███████▋  | 955/1250 [23:13<06:16,  1.28s/it]
Training 1/1 epoch (loss 2.5911):  76%|███████▋  | 955/1250 [23:15<06:16,  1.28s/it]
Training 1/1 epoch (loss 2.5911):  76%|███████▋  | 956/1250 [23:15<06:50,  1.40s/it]
Training 1/1 epoch (loss 2.7537):  76%|███████▋  | 956/1250 [23:16<06:50,  1.40s/it]
Training 1/1 epoch (loss 2.7537):  77%|███████▋  | 957/1250 [23:16<05:30,  1.13s/it]
Training 1/1 epoch (loss 2.5620):  77%|███████▋  | 957/1250 [23:17<05:30,  1.13s/it]
Training 1/1 epoch (loss 2.5620):  77%|███████▋  | 958/1250 [23:17<06:11,  1.27s/it]
Training 1/1 epoch (loss 2.7914):  77%|███████▋  | 958/1250 [23:20<06:11,  1.27s/it]
Training 1/1 epoch (loss 2.7914):  77%|███████▋  | 959/1250 [23:20<07:36,  1.57s/it]
Training 1/1 epoch (loss 2.3507):  77%|███████▋  | 959/1250 [23:20<07:36,  1.57s/it]
Training 1/1 epoch (loss 2.3507):  77%|███████▋  | 960/1250 [23:20<05:54,  1.22s/it]
Training 1/1 epoch (loss 2.3302):  77%|███████▋  | 960/1250 [23:22<05:54,  1.22s/it]
Training 1/1 epoch (loss 2.3302):  77%|███████▋  | 961/1250 [23:22<06:30,  1.35s/it]
Training 1/1 epoch (loss 2.3539):  77%|███████▋  | 961/1250 [23:23<06:30,  1.35s/it]
Training 1/1 epoch (loss 2.3539):  77%|███████▋  | 962/1250 [23:23<06:52,  1.43s/it]
Training 1/1 epoch (loss 2.7459):  77%|███████▋  | 962/1250 [23:25<06:52,  1.43s/it]
Training 1/1 epoch (loss 2.7459):  77%|███████▋  | 963/1250 [23:25<06:46,  1.42s/it]
Training 1/1 epoch (loss 2.6836):  77%|███████▋  | 963/1250 [23:26<06:46,  1.42s/it]
Training 1/1 epoch (loss 2.6836):  77%|███████▋  | 964/1250 [23:26<06:48,  1.43s/it]
Training 1/1 epoch (loss 2.3475):  77%|███████▋  | 964/1250 [23:27<06:48,  1.43s/it]
Training 1/1 epoch (loss 2.3475):  77%|███████▋  | 965/1250 [23:27<05:54,  1.24s/it]
Training 1/1 epoch (loss 2.5563):  77%|███████▋  | 965/1250 [23:29<05:54,  1.24s/it]
Training 1/1 epoch (loss 2.5563):  77%|███████▋  | 966/1250 [23:29<06:29,  1.37s/it]
Training 1/1 epoch (loss 2.5153):  77%|███████▋  | 966/1250 [23:31<06:29,  1.37s/it]
Training 1/1 epoch (loss 2.5153):  77%|███████▋  | 967/1250 [23:31<07:27,  1.58s/it]
Training 1/1 epoch (loss 2.5604):  77%|███████▋  | 967/1250 [23:31<07:27,  1.58s/it]
Training 1/1 epoch (loss 2.5604):  77%|███████▋  | 968/1250 [23:31<06:22,  1.36s/it]
Training 1/1 epoch (loss 2.8741):  77%|███████▋  | 968/1250 [23:33<06:22,  1.36s/it]
Training 1/1 epoch (loss 2.8741):  78%|███████▊  | 969/1250 [23:33<07:10,  1.53s/it]
Training 1/1 epoch (loss 2.4924):  78%|███████▊  | 969/1250 [23:35<07:10,  1.53s/it]
Training 1/1 epoch (loss 2.4924):  78%|███████▊  | 970/1250 [23:35<07:07,  1.53s/it]
Training 1/1 epoch (loss 2.8911):  78%|███████▊  | 970/1250 [23:36<07:07,  1.53s/it]
Training 1/1 epoch (loss 2.8911):  78%|███████▊  | 971/1250 [23:36<05:53,  1.27s/it]
Training 1/1 epoch (loss 2.5558):  78%|███████▊  | 971/1250 [23:37<05:53,  1.27s/it]
Training 1/1 epoch (loss 2.5558):  78%|███████▊  | 972/1250 [23:37<05:54,  1.28s/it]
Training 1/1 epoch (loss 2.5788):  78%|███████▊  | 972/1250 [23:39<05:54,  1.28s/it]
Training 1/1 epoch (loss 2.5788):  78%|███████▊  | 973/1250 [23:39<06:59,  1.52s/it]
Training 1/1 epoch (loss 2.4504):  78%|███████▊  | 973/1250 [23:40<06:59,  1.52s/it]
Training 1/1 epoch (loss 2.4504):  78%|███████▊  | 974/1250 [23:40<05:50,  1.27s/it]
Training 1/1 epoch (loss 2.5891):  78%|███████▊  | 974/1250 [23:42<05:50,  1.27s/it]
Training 1/1 epoch (loss 2.5891):  78%|███████▊  | 975/1250 [23:42<06:49,  1.49s/it]
Training 1/1 epoch (loss 2.4772):  78%|███████▊  | 975/1250 [23:43<06:49,  1.49s/it]
Training 1/1 epoch (loss 2.4772):  78%|███████▊  | 976/1250 [23:43<06:19,  1.39s/it]
Training 1/1 epoch (loss 2.6558):  78%|███████▊  | 976/1250 [23:44<06:19,  1.39s/it]
Training 1/1 epoch (loss 2.6558):  78%|███████▊  | 977/1250 [23:44<06:02,  1.33s/it]
Training 1/1 epoch (loss 2.6577):  78%|███████▊  | 977/1250 [23:46<06:02,  1.33s/it]
Training 1/1 epoch (loss 2.6577):  78%|███████▊  | 978/1250 [23:46<06:40,  1.47s/it]
Training 1/1 epoch (loss 2.8601):  78%|███████▊  | 978/1250 [23:47<06:40,  1.47s/it]
Training 1/1 epoch (loss 2.8601):  78%|███████▊  | 979/1250 [23:47<06:15,  1.39s/it]
Training 1/1 epoch (loss 2.6597):  78%|███████▊  | 979/1250 [23:48<06:15,  1.39s/it]
Training 1/1 epoch (loss 2.6597):  78%|███████▊  | 980/1250 [23:48<05:58,  1.33s/it]
Training 1/1 epoch (loss 2.6060):  78%|███████▊  | 980/1250 [23:50<05:58,  1.33s/it]
Training 1/1 epoch (loss 2.6060):  78%|███████▊  | 981/1250 [23:50<06:37,  1.48s/it]
Training 1/1 epoch (loss 2.5961):  78%|███████▊  | 981/1250 [23:51<06:37,  1.48s/it]
Training 1/1 epoch (loss 2.5961):  79%|███████▊  | 982/1250 [23:51<05:42,  1.28s/it]
Training 1/1 epoch (loss 2.6592):  79%|███████▊  | 982/1250 [23:52<05:42,  1.28s/it]
Training 1/1 epoch (loss 2.6592):  79%|███████▊  | 983/1250 [23:52<05:39,  1.27s/it]
Training 1/1 epoch (loss 2.6301):  79%|███████▊  | 983/1250 [23:54<05:39,  1.27s/it]
Training 1/1 epoch (loss 2.6301):  79%|███████▊  | 984/1250 [23:54<06:47,  1.53s/it]
Training 1/1 epoch (loss 2.7192):  79%|███████▊  | 984/1250 [23:55<06:47,  1.53s/it]
Training 1/1 epoch (loss 2.7192):  79%|███████▉  | 985/1250 [23:55<05:24,  1.22s/it]
Training 1/1 epoch (loss 2.4560):  79%|███████▉  | 985/1250 [23:57<05:24,  1.22s/it]
Training 1/1 epoch (loss 2.4560):  79%|███████▉  | 986/1250 [23:57<06:35,  1.50s/it]
Training 1/1 epoch (loss 2.5943):  79%|███████▉  | 986/1250 [23:59<06:35,  1.50s/it]
Training 1/1 epoch (loss 2.5943):  79%|███████▉  | 987/1250 [23:59<07:15,  1.65s/it]
Training 1/1 epoch (loss 2.5223):  79%|███████▉  | 987/1250 [24:00<07:15,  1.65s/it]
Training 1/1 epoch (loss 2.5223):  79%|███████▉  | 988/1250 [24:00<06:20,  1.45s/it]
Training 1/1 epoch (loss 2.8114):  79%|███████▉  | 988/1250 [24:01<06:20,  1.45s/it]
Training 1/1 epoch (loss 2.8114):  79%|███████▉  | 989/1250 [24:01<06:23,  1.47s/it]
Training 1/1 epoch (loss 2.4353):  79%|███████▉  | 989/1250 [24:03<06:23,  1.47s/it]
Training 1/1 epoch (loss 2.4353):  79%|███████▉  | 990/1250 [24:03<06:32,  1.51s/it]
Training 1/1 epoch (loss 2.5145):  79%|███████▉  | 990/1250 [24:04<06:32,  1.51s/it]
Training 1/1 epoch (loss 2.5145):  79%|███████▉  | 991/1250 [24:04<05:32,  1.28s/it]
Training 1/1 epoch (loss 2.2521):  79%|███████▉  | 991/1250 [24:06<05:32,  1.28s/it]
Training 1/1 epoch (loss 2.2521):  79%|███████▉  | 992/1250 [24:06<06:25,  1.50s/it]
Training 1/1 epoch (loss 2.5101):  79%|███████▉  | 992/1250 [24:07<06:25,  1.50s/it]
Training 1/1 epoch (loss 2.5101):  79%|███████▉  | 993/1250 [24:07<06:10,  1.44s/it]
Training 1/1 epoch (loss 2.4350):  79%|███████▉  | 993/1250 [24:08<06:10,  1.44s/it]
Training 1/1 epoch (loss 2.4350):  80%|███████▉  | 994/1250 [24:08<06:01,  1.41s/it]
Training 1/1 epoch (loss 2.2831):  80%|███████▉  | 994/1250 [24:10<06:01,  1.41s/it]
Training 1/1 epoch (loss 2.2831):  80%|███████▉  | 995/1250 [24:10<05:58,  1.40s/it]
Training 1/1 epoch (loss 2.5321):  80%|███████▉  | 995/1250 [24:11<05:58,  1.40s/it]
Training 1/1 epoch (loss 2.5321):  80%|███████▉  | 996/1250 [24:11<05:35,  1.32s/it]
Training 1/1 epoch (loss 2.6333):  80%|███████▉  | 996/1250 [24:12<05:35,  1.32s/it]
Training 1/1 epoch (loss 2.6333):  80%|███████▉  | 997/1250 [24:12<04:57,  1.18s/it]
Training 1/1 epoch (loss 2.5478):  80%|███████▉  | 997/1250 [24:14<04:57,  1.18s/it]
Training 1/1 epoch (loss 2.5478):  80%|███████▉  | 998/1250 [24:14<06:31,  1.55s/it]
Training 1/1 epoch (loss 2.5820):  80%|███████▉  | 998/1250 [24:15<06:31,  1.55s/it]
Training 1/1 epoch (loss 2.5820):  80%|███████▉  | 999/1250 [24:15<05:43,  1.37s/it]
Training 1/1 epoch (loss 2.5452):  80%|███████▉  | 999/1250 [24:17<05:43,  1.37s/it]
Training 1/1 epoch (loss 2.5452):  80%|████████  | 1000/1250 [24:17<06:05,  1.46s/it]
Training 1/1 epoch (loss 2.6420):  80%|████████  | 1000/1250 [24:19<06:05,  1.46s/it]
Training 1/1 epoch (loss 2.6420):  80%|████████  | 1001/1250 [24:19<06:45,  1.63s/it]
Training 1/1 epoch (loss 2.3777):  80%|████████  | 1001/1250 [24:19<06:45,  1.63s/it]
Training 1/1 epoch (loss 2.3777):  80%|████████  | 1002/1250 [24:19<05:16,  1.28s/it]
Training 1/1 epoch (loss 2.4638):  80%|████████  | 1002/1250 [24:21<05:16,  1.28s/it]
Training 1/1 epoch (loss 2.4638):  80%|████████  | 1003/1250 [24:21<05:31,  1.34s/it]
Training 1/1 epoch (loss 2.4468):  80%|████████  | 1003/1250 [24:23<05:31,  1.34s/it]
Training 1/1 epoch (loss 2.4468):  80%|████████  | 1004/1250 [24:23<06:23,  1.56s/it]
Training 1/1 epoch (loss 2.6731):  80%|████████  | 1004/1250 [24:23<06:23,  1.56s/it]
Training 1/1 epoch (loss 2.6731):  80%|████████  | 1005/1250 [24:23<05:19,  1.30s/it]
Training 1/1 epoch (loss 2.5950):  80%|████████  | 1005/1250 [24:25<05:19,  1.30s/it]
Training 1/1 epoch (loss 2.5950):  80%|████████  | 1006/1250 [24:25<05:11,  1.28s/it]
Training 1/1 epoch (loss 2.6667):  80%|████████  | 1006/1250 [24:27<05:11,  1.28s/it]
Training 1/1 epoch (loss 2.6667):  81%|████████  | 1007/1250 [24:27<06:02,  1.49s/it]
Training 1/1 epoch (loss 2.6168):  81%|████████  | 1007/1250 [24:28<06:02,  1.49s/it]
Training 1/1 epoch (loss 2.6168):  81%|████████  | 1008/1250 [24:28<05:55,  1.47s/it]
Training 1/1 epoch (loss 2.7035):  81%|████████  | 1008/1250 [24:30<05:55,  1.47s/it]
Training 1/1 epoch (loss 2.7035):  81%|████████  | 1009/1250 [24:30<06:26,  1.61s/it]
Training 1/1 epoch (loss 2.6358):  81%|████████  | 1009/1250 [24:31<06:26,  1.61s/it]
Training 1/1 epoch (loss 2.6358):  81%|████████  | 1010/1250 [24:31<05:58,  1.49s/it]
Training 1/1 epoch (loss 2.7557):  81%|████████  | 1010/1250 [24:34<05:58,  1.49s/it]
Training 1/1 epoch (loss 2.7557):  81%|████████  | 1011/1250 [24:34<07:05,  1.78s/it]
Training 1/1 epoch (loss 2.6186):  81%|████████  | 1011/1250 [24:36<07:05,  1.78s/it]
Training 1/1 epoch (loss 2.6186):  81%|████████  | 1012/1250 [24:36<07:50,  1.98s/it]
Training 1/1 epoch (loss 2.4513):  81%|████████  | 1012/1250 [24:37<07:50,  1.98s/it]
Training 1/1 epoch (loss 2.4513):  81%|████████  | 1013/1250 [24:37<06:45,  1.71s/it]
Training 1/1 epoch (loss 2.3893):  81%|████████  | 1013/1250 [24:39<06:45,  1.71s/it]
Training 1/1 epoch (loss 2.3893):  81%|████████  | 1014/1250 [24:39<07:13,  1.84s/it]
Training 1/1 epoch (loss 2.5520):  81%|████████  | 1014/1250 [24:42<07:13,  1.84s/it]
Training 1/1 epoch (loss 2.5520):  81%|████████  | 1015/1250 [24:42<07:57,  2.03s/it]
Training 1/1 epoch (loss 2.5779):  81%|████████  | 1015/1250 [24:43<07:57,  2.03s/it]
Training 1/1 epoch (loss 2.5779):  81%|████████▏ | 1016/1250 [24:43<06:45,  1.73s/it]
Training 1/1 epoch (loss 2.5612):  81%|████████▏ | 1016/1250 [24:44<06:45,  1.73s/it]
Training 1/1 epoch (loss 2.5612):  81%|████████▏ | 1017/1250 [24:44<05:43,  1.48s/it]
Training 1/1 epoch (loss 2.6684):  81%|████████▏ | 1017/1250 [24:45<05:43,  1.48s/it]
Training 1/1 epoch (loss 2.6684):  81%|████████▏ | 1018/1250 [24:45<05:04,  1.31s/it]
Training 1/1 epoch (loss 2.5985):  81%|████████▏ | 1018/1250 [24:47<05:04,  1.31s/it]
Training 1/1 epoch (loss 2.5985):  82%|████████▏ | 1019/1250 [24:47<05:42,  1.48s/it]
Training 1/1 epoch (loss 2.7760):  82%|████████▏ | 1019/1250 [24:48<05:42,  1.48s/it]
Training 1/1 epoch (loss 2.7760):  82%|████████▏ | 1020/1250 [24:48<05:55,  1.55s/it]
Training 1/1 epoch (loss 2.5240):  82%|████████▏ | 1020/1250 [24:49<05:55,  1.55s/it]
Training 1/1 epoch (loss 2.5240):  82%|████████▏ | 1021/1250 [24:49<04:53,  1.28s/it]
Training 1/1 epoch (loss 2.8070):  82%|████████▏ | 1021/1250 [24:51<04:53,  1.28s/it]
Training 1/1 epoch (loss 2.8070):  82%|████████▏ | 1022/1250 [24:51<05:18,  1.40s/it]
Training 1/1 epoch (loss 2.4870):  82%|████████▏ | 1022/1250 [24:52<05:18,  1.40s/it]
Training 1/1 epoch (loss 2.4870):  82%|████████▏ | 1023/1250 [24:52<05:26,  1.44s/it]
Training 1/1 epoch (loss 2.5521):  82%|████████▏ | 1023/1250 [24:53<05:26,  1.44s/it]
Training 1/1 epoch (loss 2.5521):  82%|████████▏ | 1024/1250 [24:53<04:54,  1.30s/it]
Training 1/1 epoch (loss 2.4295):  82%|████████▏ | 1024/1250 [24:56<04:54,  1.30s/it]
Training 1/1 epoch (loss 2.4295):  82%|████████▏ | 1025/1250 [24:56<06:09,  1.64s/it]
Training 1/1 epoch (loss 2.6075):  82%|████████▏ | 1025/1250 [24:57<06:09,  1.64s/it]
Training 1/1 epoch (loss 2.6075):  82%|████████▏ | 1026/1250 [24:57<05:53,  1.58s/it]
Training 1/1 epoch (loss 2.4976):  82%|████████▏ | 1026/1250 [24:57<05:53,  1.58s/it]
Training 1/1 epoch (loss 2.4976):  82%|████████▏ | 1027/1250 [24:57<04:38,  1.25s/it]
Training 1/1 epoch (loss 2.4923):  82%|████████▏ | 1027/1250 [24:59<04:38,  1.25s/it]
Training 1/1 epoch (loss 2.4923):  82%|████████▏ | 1028/1250 [24:59<05:19,  1.44s/it]
Training 1/1 epoch (loss 2.6077):  82%|████████▏ | 1028/1250 [25:01<05:19,  1.44s/it]
Training 1/1 epoch (loss 2.6077):  82%|████████▏ | 1029/1250 [25:01<05:50,  1.59s/it]
Training 1/1 epoch (loss 2.6690):  82%|████████▏ | 1029/1250 [25:02<05:50,  1.59s/it]
Training 1/1 epoch (loss 2.6690):  82%|████████▏ | 1030/1250 [25:02<04:41,  1.28s/it]
Training 1/1 epoch (loss 2.6047):  82%|████████▏ | 1030/1250 [25:03<04:41,  1.28s/it]
Training 1/1 epoch (loss 2.6047):  82%|████████▏ | 1031/1250 [25:03<04:37,  1.27s/it]
Training 1/1 epoch (loss 2.5900):  82%|████████▏ | 1031/1250 [25:05<04:37,  1.27s/it]
Training 1/1 epoch (loss 2.5900):  83%|████████▎ | 1032/1250 [25:05<05:26,  1.50s/it]
Training 1/1 epoch (loss 2.4710):  83%|████████▎ | 1032/1250 [25:06<05:26,  1.50s/it]
Training 1/1 epoch (loss 2.4710):  83%|████████▎ | 1033/1250 [25:06<05:00,  1.38s/it]
Training 1/1 epoch (loss 2.4462):  83%|████████▎ | 1033/1250 [25:08<05:00,  1.38s/it]
Training 1/1 epoch (loss 2.4462):  83%|████████▎ | 1034/1250 [25:08<05:34,  1.55s/it]
Training 1/1 epoch (loss 2.3863):  83%|████████▎ | 1034/1250 [25:10<05:34,  1.55s/it]
Training 1/1 epoch (loss 2.3863):  83%|████████▎ | 1035/1250 [25:10<05:54,  1.65s/it]
Training 1/1 epoch (loss 2.5109):  83%|████████▎ | 1035/1250 [25:11<05:54,  1.65s/it]
Training 1/1 epoch (loss 2.5109):  83%|████████▎ | 1036/1250 [25:11<05:08,  1.44s/it]
Training 1/1 epoch (loss 2.6931):  83%|████████▎ | 1036/1250 [25:13<05:08,  1.44s/it]
Training 1/1 epoch (loss 2.6931):  83%|████████▎ | 1037/1250 [25:13<06:09,  1.73s/it]
Training 1/1 epoch (loss 2.4604):  83%|████████▎ | 1037/1250 [25:15<06:09,  1.73s/it]
Training 1/1 epoch (loss 2.4604):  83%|████████▎ | 1038/1250 [25:15<06:05,  1.72s/it]
Training 1/1 epoch (loss 2.3465):  83%|████████▎ | 1038/1250 [25:17<06:05,  1.72s/it]
Training 1/1 epoch (loss 2.3465):  83%|████████▎ | 1039/1250 [25:17<05:44,  1.63s/it]
Training 1/1 epoch (loss 2.4537):  83%|████████▎ | 1039/1250 [25:19<05:44,  1.63s/it]
Training 1/1 epoch (loss 2.4537):  83%|████████▎ | 1040/1250 [25:19<06:18,  1.80s/it]
Training 1/1 epoch (loss 2.3101):  83%|████████▎ | 1040/1250 [25:20<06:18,  1.80s/it]
Training 1/1 epoch (loss 2.3101):  83%|████████▎ | 1041/1250 [25:20<05:11,  1.49s/it]
Training 1/1 epoch (loss 2.7219):  83%|████████▎ | 1041/1250 [25:22<05:11,  1.49s/it]
Training 1/1 epoch (loss 2.7219):  83%|████████▎ | 1042/1250 [25:22<05:48,  1.67s/it]
Training 1/1 epoch (loss 2.6239):  83%|████████▎ | 1042/1250 [25:23<05:48,  1.67s/it]
Training 1/1 epoch (loss 2.6239):  83%|████████▎ | 1043/1250 [25:23<05:30,  1.60s/it]
Training 1/1 epoch (loss 2.6034):  83%|████████▎ | 1043/1250 [25:24<05:30,  1.60s/it]
Training 1/1 epoch (loss 2.6034):  84%|████████▎ | 1044/1250 [25:24<04:19,  1.26s/it]
Training 1/1 epoch (loss 2.6666):  84%|████████▎ | 1044/1250 [25:25<04:19,  1.26s/it]
Training 1/1 epoch (loss 2.6666):  84%|████████▎ | 1045/1250 [25:25<04:32,  1.33s/it]
Training 1/1 epoch (loss 2.6361):  84%|████████▎ | 1045/1250 [25:27<04:32,  1.33s/it]
Training 1/1 epoch (loss 2.6361):  84%|████████▎ | 1046/1250 [25:27<05:36,  1.65s/it]
Training 1/1 epoch (loss 2.6398):  84%|████████▎ | 1046/1250 [25:28<05:36,  1.65s/it]
Training 1/1 epoch (loss 2.6398):  84%|████████▍ | 1047/1250 [25:28<04:26,  1.31s/it]
Training 1/1 epoch (loss 2.6086):  84%|████████▍ | 1047/1250 [25:30<04:26,  1.31s/it]
Training 1/1 epoch (loss 2.6086):  84%|████████▍ | 1048/1250 [25:30<05:22,  1.60s/it]
Training 1/1 epoch (loss 2.4828):  84%|████████▍ | 1048/1250 [25:32<05:22,  1.60s/it]
Training 1/1 epoch (loss 2.4828):  84%|████████▍ | 1049/1250 [25:32<05:35,  1.67s/it]
Training 1/1 epoch (loss 2.7476):  84%|████████▍ | 1049/1250 [25:33<05:35,  1.67s/it]
Training 1/1 epoch (loss 2.7476):  84%|████████▍ | 1050/1250 [25:33<04:40,  1.40s/it]
Training 1/1 epoch (loss 2.6126):  84%|████████▍ | 1050/1250 [25:35<04:40,  1.40s/it]
Training 1/1 epoch (loss 2.6126):  84%|████████▍ | 1051/1250 [25:35<05:07,  1.55s/it]
Training 1/1 epoch (loss 2.5927):  84%|████████▍ | 1051/1250 [25:36<05:07,  1.55s/it]
Training 1/1 epoch (loss 2.5927):  84%|████████▍ | 1052/1250 [25:36<04:28,  1.36s/it]
Training 1/1 epoch (loss 2.4628):  84%|████████▍ | 1052/1250 [25:37<04:28,  1.36s/it]
Training 1/1 epoch (loss 2.4628):  84%|████████▍ | 1053/1250 [25:37<04:40,  1.42s/it]
Training 1/1 epoch (loss 2.4557):  84%|████████▍ | 1053/1250 [25:38<04:40,  1.42s/it]
Training 1/1 epoch (loss 2.4557):  84%|████████▍ | 1054/1250 [25:38<04:18,  1.32s/it]
Training 1/1 epoch (loss 2.3544):  84%|████████▍ | 1054/1250 [25:40<04:18,  1.32s/it]
Training 1/1 epoch (loss 2.3544):  84%|████████▍ | 1055/1250 [25:40<04:24,  1.35s/it]
Training 1/1 epoch (loss 2.4873):  84%|████████▍ | 1055/1250 [25:42<04:24,  1.35s/it]
Training 1/1 epoch (loss 2.4873):  84%|████████▍ | 1056/1250 [25:42<04:59,  1.54s/it]
Training 1/1 epoch (loss 2.6093):  84%|████████▍ | 1056/1250 [25:44<04:59,  1.54s/it]
Training 1/1 epoch (loss 2.6093):  85%|████████▍ | 1057/1250 [25:44<05:49,  1.81s/it]
Training 1/1 epoch (loss 2.6188):  85%|████████▍ | 1057/1250 [25:45<05:49,  1.81s/it]
Training 1/1 epoch (loss 2.6188):  85%|████████▍ | 1058/1250 [25:45<04:37,  1.45s/it]
Training 1/1 epoch (loss 2.5976):  85%|████████▍ | 1058/1250 [25:46<04:37,  1.45s/it]
Training 1/1 epoch (loss 2.5976):  85%|████████▍ | 1059/1250 [25:46<04:49,  1.51s/it]
Training 1/1 epoch (loss 2.6862):  85%|████████▍ | 1059/1250 [25:48<04:49,  1.51s/it]
Training 1/1 epoch (loss 2.6862):  85%|████████▍ | 1060/1250 [25:48<05:11,  1.64s/it]
Training 1/1 epoch (loss 2.4173):  85%|████████▍ | 1060/1250 [25:49<05:11,  1.64s/it]
Training 1/1 epoch (loss 2.4173):  85%|████████▍ | 1061/1250 [25:49<04:08,  1.32s/it]
Training 1/1 epoch (loss 2.8002):  85%|████████▍ | 1061/1250 [25:51<04:08,  1.32s/it]
Training 1/1 epoch (loss 2.8002):  85%|████████▍ | 1062/1250 [25:51<04:37,  1.48s/it]
Training 1/1 epoch (loss 2.7227):  85%|████████▍ | 1062/1250 [25:52<04:37,  1.48s/it]
Training 1/1 epoch (loss 2.7227):  85%|████████▌ | 1063/1250 [25:52<04:31,  1.45s/it]
Training 1/1 epoch (loss 2.6381):  85%|████████▌ | 1063/1250 [25:53<04:31,  1.45s/it]
Training 1/1 epoch (loss 2.6381):  85%|████████▌ | 1064/1250 [25:53<04:15,  1.37s/it]
Training 1/1 epoch (loss 2.5342):  85%|████████▌ | 1064/1250 [25:55<04:15,  1.37s/it]
Training 1/1 epoch (loss 2.5342):  85%|████████▌ | 1065/1250 [25:55<04:35,  1.49s/it]
Training 1/1 epoch (loss 2.7228):  85%|████████▌ | 1065/1250 [25:56<04:35,  1.49s/it]
Training 1/1 epoch (loss 2.7228):  85%|████████▌ | 1066/1250 [25:56<04:14,  1.38s/it]
Training 1/1 epoch (loss 2.5571):  85%|████████▌ | 1066/1250 [25:58<04:14,  1.38s/it]
Training 1/1 epoch (loss 2.5571):  85%|████████▌ | 1067/1250 [25:58<04:31,  1.49s/it]
Training 1/1 epoch (loss 2.5155):  85%|████████▌ | 1067/1250 [26:00<04:31,  1.49s/it]
Training 1/1 epoch (loss 2.5155):  85%|████████▌ | 1068/1250 [26:00<04:38,  1.53s/it]
Training 1/1 epoch (loss 2.4969):  85%|████████▌ | 1068/1250 [26:00<04:38,  1.53s/it]
Training 1/1 epoch (loss 2.4969):  86%|████████▌ | 1069/1250 [26:00<03:42,  1.23s/it]
Training 1/1 epoch (loss 2.5663):  86%|████████▌ | 1069/1250 [26:02<03:42,  1.23s/it]
Training 1/1 epoch (loss 2.5663):  86%|████████▌ | 1070/1250 [26:02<04:36,  1.53s/it]
Training 1/1 epoch (loss 2.6728):  86%|████████▌ | 1070/1250 [26:04<04:36,  1.53s/it]
Training 1/1 epoch (loss 2.6728):  86%|████████▌ | 1071/1250 [26:04<04:52,  1.63s/it]
Training 1/1 epoch (loss 2.5853):  86%|████████▌ | 1071/1250 [26:05<04:52,  1.63s/it]
Training 1/1 epoch (loss 2.5853):  86%|████████▌ | 1072/1250 [26:05<03:58,  1.34s/it]
Training 1/1 epoch (loss 2.5546):  86%|████████▌ | 1072/1250 [26:07<03:58,  1.34s/it]
Training 1/1 epoch (loss 2.5546):  86%|████████▌ | 1073/1250 [26:07<05:01,  1.70s/it]
Training 1/1 epoch (loss 2.6339):  86%|████████▌ | 1073/1250 [26:09<05:01,  1.70s/it]
Training 1/1 epoch (loss 2.6339):  86%|████████▌ | 1074/1250 [26:09<04:56,  1.69s/it]
Training 1/1 epoch (loss 2.6324):  86%|████████▌ | 1074/1250 [26:10<04:56,  1.69s/it]
Training 1/1 epoch (loss 2.6324):  86%|████████▌ | 1075/1250 [26:10<04:39,  1.60s/it]
Training 1/1 epoch (loss 2.6647):  86%|████████▌ | 1075/1250 [26:13<04:39,  1.60s/it]
Training 1/1 epoch (loss 2.6647):  86%|████████▌ | 1076/1250 [26:13<05:12,  1.80s/it]
Training 1/1 epoch (loss 2.5929):  86%|████████▌ | 1076/1250 [26:14<05:12,  1.80s/it]
Training 1/1 epoch (loss 2.5929):  86%|████████▌ | 1077/1250 [26:14<04:22,  1.52s/it]
Training 1/1 epoch (loss 2.5930):  86%|████████▌ | 1077/1250 [26:16<04:22,  1.52s/it]
Training 1/1 epoch (loss 2.5930):  86%|████████▌ | 1078/1250 [26:16<05:03,  1.77s/it]
Training 1/1 epoch (loss 2.5875):  86%|████████▌ | 1078/1250 [26:18<05:03,  1.77s/it]
Training 1/1 epoch (loss 2.5875):  86%|████████▋ | 1079/1250 [26:18<05:12,  1.83s/it]
Training 1/1 epoch (loss 2.7598):  86%|████████▋ | 1079/1250 [26:19<05:12,  1.83s/it]
Training 1/1 epoch (loss 2.7598):  86%|████████▋ | 1080/1250 [26:19<04:47,  1.69s/it]
Training 1/1 epoch (loss 2.7287):  86%|████████▋ | 1080/1250 [26:21<04:47,  1.69s/it]
Training 1/1 epoch (loss 2.7287):  86%|████████▋ | 1081/1250 [26:21<04:59,  1.77s/it]
Training 1/1 epoch (loss 2.3162):  86%|████████▋ | 1081/1250 [26:22<04:59,  1.77s/it]
Training 1/1 epoch (loss 2.3162):  87%|████████▋ | 1082/1250 [26:22<04:26,  1.59s/it]
Training 1/1 epoch (loss 2.6266):  87%|████████▋ | 1082/1250 [26:23<04:26,  1.59s/it]
Training 1/1 epoch (loss 2.6266):  87%|████████▋ | 1083/1250 [26:23<03:45,  1.35s/it]
Training 1/1 epoch (loss 2.7282):  87%|████████▋ | 1083/1250 [26:25<03:45,  1.35s/it]
Training 1/1 epoch (loss 2.7282):  87%|████████▋ | 1084/1250 [26:25<04:24,  1.59s/it]
Training 1/1 epoch (loss 2.4837):  87%|████████▋ | 1084/1250 [26:27<04:24,  1.59s/it]
Training 1/1 epoch (loss 2.4837):  87%|████████▋ | 1085/1250 [26:27<04:06,  1.50s/it]
Training 1/1 epoch (loss 2.5547):  87%|████████▋ | 1085/1250 [26:28<04:06,  1.50s/it]
Training 1/1 epoch (loss 2.5547):  87%|████████▋ | 1086/1250 [26:28<03:57,  1.45s/it]
Training 1/1 epoch (loss 2.6983):  87%|████████▋ | 1086/1250 [26:30<03:57,  1.45s/it]
Training 1/1 epoch (loss 2.6983):  87%|████████▋ | 1087/1250 [26:30<04:23,  1.62s/it]
Training 1/1 epoch (loss 2.6428):  87%|████████▋ | 1087/1250 [26:31<04:23,  1.62s/it]
Training 1/1 epoch (loss 2.6428):  87%|████████▋ | 1088/1250 [26:31<04:07,  1.53s/it]
Training 1/1 epoch (loss 2.4744):  87%|████████▋ | 1088/1250 [26:33<04:07,  1.53s/it]
Training 1/1 epoch (loss 2.4744):  87%|████████▋ | 1089/1250 [26:33<04:33,  1.70s/it]
Training 1/1 epoch (loss 2.5946):  87%|████████▋ | 1089/1250 [26:35<04:33,  1.70s/it]
Training 1/1 epoch (loss 2.5946):  87%|████████▋ | 1090/1250 [26:35<04:32,  1.70s/it]
Training 1/1 epoch (loss 2.6582):  87%|████████▋ | 1090/1250 [26:36<04:32,  1.70s/it]
Training 1/1 epoch (loss 2.6582):  87%|████████▋ | 1091/1250 [26:36<03:29,  1.32s/it]
Training 1/1 epoch (loss 2.4311):  87%|████████▋ | 1091/1250 [26:37<03:29,  1.32s/it]
Training 1/1 epoch (loss 2.4311):  87%|████████▋ | 1092/1250 [26:37<03:34,  1.36s/it]
Training 1/1 epoch (loss 2.4783):  87%|████████▋ | 1092/1250 [26:39<03:34,  1.36s/it]
Training 1/1 epoch (loss 2.4783):  87%|████████▋ | 1093/1250 [26:39<03:58,  1.52s/it]
Training 1/1 epoch (loss 2.4859):  87%|████████▋ | 1093/1250 [26:39<03:58,  1.52s/it]
Training 1/1 epoch (loss 2.4859):  88%|████████▊ | 1094/1250 [26:39<03:11,  1.23s/it]
Training 1/1 epoch (loss 2.6309):  88%|████████▊ | 1094/1250 [26:41<03:11,  1.23s/it]
Training 1/1 epoch (loss 2.6309):  88%|████████▊ | 1095/1250 [26:41<03:12,  1.24s/it]
Training 1/1 epoch (loss 2.4778):  88%|████████▊ | 1095/1250 [26:43<03:12,  1.24s/it]
Training 1/1 epoch (loss 2.4778):  88%|████████▊ | 1096/1250 [26:43<03:41,  1.44s/it]
Training 1/1 epoch (loss 2.7625):  88%|████████▊ | 1096/1250 [26:43<03:41,  1.44s/it]
Training 1/1 epoch (loss 2.7625):  88%|████████▊ | 1097/1250 [26:43<03:04,  1.21s/it]
Training 1/1 epoch (loss 2.6985):  88%|████████▊ | 1097/1250 [26:45<03:04,  1.21s/it]
Training 1/1 epoch (loss 2.6985):  88%|████████▊ | 1098/1250 [26:45<03:25,  1.35s/it]
Training 1/1 epoch (loss 2.6662):  88%|████████▊ | 1098/1250 [26:47<03:25,  1.35s/it]
Training 1/1 epoch (loss 2.6662):  88%|████████▊ | 1099/1250 [26:47<03:43,  1.48s/it]
Training 1/1 epoch (loss 2.6642):  88%|████████▊ | 1099/1250 [26:48<03:43,  1.48s/it]
Training 1/1 epoch (loss 2.6642):  88%|████████▊ | 1100/1250 [26:48<03:13,  1.29s/it]
Training 1/1 epoch (loss 2.4185):  88%|████████▊ | 1100/1250 [26:49<03:13,  1.29s/it]
Training 1/1 epoch (loss 2.4185):  88%|████████▊ | 1101/1250 [26:49<03:10,  1.28s/it]
Training 1/1 epoch (loss 2.6703):  88%|████████▊ | 1101/1250 [26:50<03:10,  1.28s/it]
Training 1/1 epoch (loss 2.6703):  88%|████████▊ | 1102/1250 [26:50<03:20,  1.36s/it]
Training 1/1 epoch (loss 2.5991):  88%|████████▊ | 1102/1250 [26:51<03:20,  1.36s/it]
Training 1/1 epoch (loss 2.5991):  88%|████████▊ | 1103/1250 [26:51<02:58,  1.21s/it]
Training 1/1 epoch (loss 2.4457):  88%|████████▊ | 1103/1250 [26:52<02:58,  1.21s/it]
Training 1/1 epoch (loss 2.4457):  88%|████████▊ | 1104/1250 [26:52<02:58,  1.22s/it]
Training 1/1 epoch (loss 2.5200):  88%|████████▊ | 1104/1250 [26:54<02:58,  1.22s/it]
Training 1/1 epoch (loss 2.5200):  88%|████████▊ | 1105/1250 [26:54<03:00,  1.24s/it]
Training 1/1 epoch (loss 2.5257):  88%|████████▊ | 1105/1250 [26:56<03:00,  1.24s/it]
Training 1/1 epoch (loss 2.5257):  88%|████████▊ | 1106/1250 [26:56<03:35,  1.50s/it]
Training 1/1 epoch (loss 2.4245):  88%|████████▊ | 1106/1250 [26:58<03:35,  1.50s/it]
Training 1/1 epoch (loss 2.4245):  89%|████████▊ | 1107/1250 [26:58<03:48,  1.59s/it]
Training 1/1 epoch (loss 2.6259):  89%|████████▊ | 1107/1250 [26:59<03:48,  1.59s/it]
Training 1/1 epoch (loss 2.6259):  89%|████████▊ | 1108/1250 [26:59<03:31,  1.49s/it]
Training 1/1 epoch (loss 2.6796):  89%|████████▊ | 1108/1250 [27:01<03:31,  1.49s/it]
Training 1/1 epoch (loss 2.6796):  89%|████████▊ | 1109/1250 [27:01<03:49,  1.63s/it]
Training 1/1 epoch (loss 2.7158):  89%|████████▊ | 1109/1250 [27:02<03:49,  1.63s/it]
Training 1/1 epoch (loss 2.7158):  89%|████████▉ | 1110/1250 [27:02<03:18,  1.42s/it]
Training 1/1 epoch (loss 2.7189):  89%|████████▉ | 1110/1250 [27:02<03:18,  1.42s/it]
Training 1/1 epoch (loss 2.7189):  89%|████████▉ | 1111/1250 [27:02<02:44,  1.19s/it]
Training 1/1 epoch (loss 2.5364):  89%|████████▉ | 1111/1250 [27:04<02:44,  1.19s/it]
Training 1/1 epoch (loss 2.5364):  89%|████████▉ | 1112/1250 [27:04<03:05,  1.34s/it]
Training 1/1 epoch (loss 2.6516):  89%|████████▉ | 1112/1250 [27:05<03:05,  1.34s/it]
Training 1/1 epoch (loss 2.6516):  89%|████████▉ | 1113/1250 [27:05<02:44,  1.20s/it]
Training 1/1 epoch (loss 2.5622):  89%|████████▉ | 1113/1250 [27:07<02:44,  1.20s/it]
Training 1/1 epoch (loss 2.5622):  89%|████████▉ | 1114/1250 [27:07<03:07,  1.38s/it]
Training 1/1 epoch (loss 2.4541):  89%|████████▉ | 1114/1250 [27:09<03:07,  1.38s/it]
Training 1/1 epoch (loss 2.4541):  89%|████████▉ | 1115/1250 [27:09<03:33,  1.58s/it]
Training 1/1 epoch (loss 2.5162):  89%|████████▉ | 1115/1250 [27:09<03:33,  1.58s/it]
Training 1/1 epoch (loss 2.5162):  89%|████████▉ | 1116/1250 [27:09<02:51,  1.28s/it]
Training 1/1 epoch (loss 2.6401):  89%|████████▉ | 1116/1250 [27:12<02:51,  1.28s/it]
Training 1/1 epoch (loss 2.6401):  89%|████████▉ | 1117/1250 [27:12<03:36,  1.63s/it]
Training 1/1 epoch (loss 2.4001):  89%|████████▉ | 1117/1250 [27:14<03:36,  1.63s/it]
Training 1/1 epoch (loss 2.4001):  89%|████████▉ | 1118/1250 [27:14<03:57,  1.80s/it]
Training 1/1 epoch (loss 2.4936):  89%|████████▉ | 1118/1250 [27:15<03:57,  1.80s/it]
Training 1/1 epoch (loss 2.4936):  90%|████████▉ | 1119/1250 [27:15<03:03,  1.40s/it]
Training 1/1 epoch (loss 2.3757):  90%|████████▉ | 1119/1250 [27:16<03:03,  1.40s/it]
Training 1/1 epoch (loss 2.3757):  90%|████████▉ | 1120/1250 [27:16<03:08,  1.45s/it]
Training 1/1 epoch (loss 2.5726):  90%|████████▉ | 1120/1250 [27:18<03:08,  1.45s/it]
Training 1/1 epoch (loss 2.5726):  90%|████████▉ | 1121/1250 [27:18<03:20,  1.56s/it]
Training 1/1 epoch (loss 2.5466):  90%|████████▉ | 1121/1250 [27:18<03:20,  1.56s/it]
Training 1/1 epoch (loss 2.5466):  90%|████████▉ | 1122/1250 [27:18<02:37,  1.23s/it]
Training 1/1 epoch (loss 2.6105):  90%|████████▉ | 1122/1250 [27:20<02:37,  1.23s/it]
Training 1/1 epoch (loss 2.6105):  90%|████████▉ | 1123/1250 [27:20<02:58,  1.40s/it]
Training 1/1 epoch (loss 2.5412):  90%|████████▉ | 1123/1250 [27:23<02:58,  1.40s/it]
Training 1/1 epoch (loss 2.5412):  90%|████████▉ | 1124/1250 [27:23<03:34,  1.71s/it]
Training 1/1 epoch (loss 2.6791):  90%|████████▉ | 1124/1250 [27:23<03:34,  1.71s/it]
Training 1/1 epoch (loss 2.6791):  90%|█████████ | 1125/1250 [27:23<02:51,  1.37s/it]
Training 1/1 epoch (loss 2.6925):  90%|█████████ | 1125/1250 [27:25<02:51,  1.37s/it]
Training 1/1 epoch (loss 2.6925):  90%|█████████ | 1126/1250 [27:25<02:49,  1.37s/it]
Training 1/1 epoch (loss 2.4991):  90%|█████████ | 1126/1250 [27:27<02:49,  1.37s/it]
Training 1/1 epoch (loss 2.4991):  90%|█████████ | 1127/1250 [27:27<03:09,  1.54s/it]
Training 1/1 epoch (loss 2.6352):  90%|█████████ | 1127/1250 [27:28<03:09,  1.54s/it]
Training 1/1 epoch (loss 2.6352):  90%|█████████ | 1128/1250 [27:28<03:06,  1.52s/it]
Training 1/1 epoch (loss 2.5169):  90%|█████████ | 1128/1250 [27:30<03:06,  1.52s/it]
Training 1/1 epoch (loss 2.5169):  90%|█████████ | 1129/1250 [27:30<03:34,  1.78s/it]
Training 1/1 epoch (loss 2.5729):  90%|█████████ | 1129/1250 [27:31<03:34,  1.78s/it]
Training 1/1 epoch (loss 2.5729):  90%|█████████ | 1130/1250 [27:31<03:07,  1.56s/it]
Training 1/1 epoch (loss 2.3904):  90%|█████████ | 1130/1250 [27:33<03:07,  1.56s/it]
Training 1/1 epoch (loss 2.3904):  90%|█████████ | 1131/1250 [27:33<03:19,  1.68s/it]
Training 1/1 epoch (loss 2.5233):  90%|█████████ | 1131/1250 [27:36<03:19,  1.68s/it]
Training 1/1 epoch (loss 2.5233):  91%|█████████ | 1132/1250 [27:36<03:48,  1.93s/it]
Training 1/1 epoch (loss 2.4717):  91%|█████████ | 1132/1250 [27:37<03:48,  1.93s/it]
Training 1/1 epoch (loss 2.4717):  91%|█████████ | 1133/1250 [27:37<03:00,  1.54s/it]
Training 1/1 epoch (loss 2.5917):  91%|█████████ | 1133/1250 [27:39<03:00,  1.54s/it]
Training 1/1 epoch (loss 2.5917):  91%|█████████ | 1134/1250 [27:39<03:15,  1.69s/it]
Training 1/1 epoch (loss 2.5820):  91%|█████████ | 1134/1250 [27:40<03:15,  1.69s/it]
Training 1/1 epoch (loss 2.5820):  91%|█████████ | 1135/1250 [27:40<03:01,  1.57s/it]
Training 1/1 epoch (loss 2.5021):  91%|█████████ | 1135/1250 [27:41<03:01,  1.57s/it]
Training 1/1 epoch (loss 2.5021):  91%|█████████ | 1136/1250 [27:41<02:38,  1.39s/it]
Training 1/1 epoch (loss 2.5755):  91%|█████████ | 1136/1250 [27:42<02:38,  1.39s/it]
Training 1/1 epoch (loss 2.5755):  91%|█████████ | 1137/1250 [27:42<02:40,  1.42s/it]
Training 1/1 epoch (loss 2.5868):  91%|█████████ | 1137/1250 [27:43<02:40,  1.42s/it]
Training 1/1 epoch (loss 2.5868):  91%|█████████ | 1138/1250 [27:43<02:13,  1.19s/it]
Training 1/1 epoch (loss 2.3728):  91%|█████████ | 1138/1250 [27:45<02:13,  1.19s/it]
Training 1/1 epoch (loss 2.3728):  91%|█████████ | 1139/1250 [27:45<02:38,  1.43s/it]
Training 1/1 epoch (loss 2.7479):  91%|█████████ | 1139/1250 [27:46<02:38,  1.43s/it]
Training 1/1 epoch (loss 2.7479):  91%|█████████ | 1140/1250 [27:46<02:38,  1.45s/it]
Training 1/1 epoch (loss 2.4649):  91%|█████████ | 1140/1250 [27:47<02:38,  1.45s/it]
Training 1/1 epoch (loss 2.4649):  91%|█████████▏| 1141/1250 [27:47<02:10,  1.19s/it]
Training 1/1 epoch (loss 2.5440):  91%|█████████▏| 1141/1250 [27:49<02:10,  1.19s/it]
Training 1/1 epoch (loss 2.5440):  91%|█████████▏| 1142/1250 [27:49<02:22,  1.32s/it]
Training 1/1 epoch (loss 2.5934):  91%|█████████▏| 1142/1250 [27:50<02:22,  1.32s/it]
Training 1/1 epoch (loss 2.5934):  91%|█████████▏| 1143/1250 [27:50<02:34,  1.44s/it]
Training 1/1 epoch (loss 2.4030):  91%|█████████▏| 1143/1250 [27:51<02:34,  1.44s/it]
Training 1/1 epoch (loss 2.4030):  92%|█████████▏| 1144/1250 [27:51<02:18,  1.30s/it]
Training 1/1 epoch (loss 2.5512):  92%|█████████▏| 1144/1250 [27:54<02:18,  1.30s/it]
Training 1/1 epoch (loss 2.5512):  92%|█████████▏| 1145/1250 [27:54<02:52,  1.64s/it]
Training 1/1 epoch (loss 2.5944):  92%|█████████▏| 1145/1250 [27:55<02:52,  1.64s/it]
Training 1/1 epoch (loss 2.5944):  92%|█████████▏| 1146/1250 [27:55<02:35,  1.49s/it]
Training 1/1 epoch (loss 2.4347):  92%|█████████▏| 1146/1250 [27:56<02:35,  1.49s/it]
Training 1/1 epoch (loss 2.4347):  92%|█████████▏| 1147/1250 [27:56<02:18,  1.34s/it]
Training 1/1 epoch (loss 2.6403):  92%|█████████▏| 1147/1250 [27:58<02:18,  1.34s/it]
Training 1/1 epoch (loss 2.6403):  92%|█████████▏| 1148/1250 [27:58<02:28,  1.46s/it]
Training 1/1 epoch (loss 2.4058):  92%|█████████▏| 1148/1250 [27:58<02:28,  1.46s/it]
Training 1/1 epoch (loss 2.4058):  92%|█████████▏| 1149/1250 [27:58<02:07,  1.26s/it]
Training 1/1 epoch (loss 2.4109):  92%|█████████▏| 1149/1250 [28:00<02:07,  1.26s/it]
Training 1/1 epoch (loss 2.4109):  92%|█████████▏| 1150/1250 [28:00<02:26,  1.47s/it]
Training 1/1 epoch (loss 2.7828):  92%|█████████▏| 1150/1250 [28:02<02:26,  1.47s/it]
Training 1/1 epoch (loss 2.7828):  92%|█████████▏| 1151/1250 [28:02<02:19,  1.41s/it]
Training 1/1 epoch (loss 2.5855):  92%|█████████▏| 1151/1250 [28:03<02:19,  1.41s/it]
Training 1/1 epoch (loss 2.5855):  92%|█████████▏| 1152/1250 [28:03<02:01,  1.24s/it]
Training 1/1 epoch (loss 2.5834):  92%|█████████▏| 1152/1250 [28:05<02:01,  1.24s/it]
Training 1/1 epoch (loss 2.5834):  92%|█████████▏| 1153/1250 [28:05<02:29,  1.54s/it]
Training 1/1 epoch (loss 2.4872):  92%|█████████▏| 1153/1250 [28:07<02:29,  1.54s/it]
Training 1/1 epoch (loss 2.4872):  92%|█████████▏| 1154/1250 [28:07<02:37,  1.64s/it]
Training 1/1 epoch (loss 2.5188):  92%|█████████▏| 1154/1250 [28:07<02:37,  1.64s/it]
Training 1/1 epoch (loss 2.5188):  92%|█████████▏| 1155/1250 [28:07<02:07,  1.34s/it]
Training 1/1 epoch (loss 2.5595):  92%|█████████▏| 1155/1250 [28:09<02:07,  1.34s/it]
Training 1/1 epoch (loss 2.5595):  92%|█████████▏| 1156/1250 [28:09<02:19,  1.48s/it]
Training 1/1 epoch (loss 2.5277):  92%|█████████▏| 1156/1250 [28:10<02:19,  1.48s/it]
Training 1/1 epoch (loss 2.5277):  93%|█████████▎| 1157/1250 [28:10<02:08,  1.39s/it]
Training 1/1 epoch (loss 2.5257):  93%|█████████▎| 1157/1250 [28:11<02:08,  1.39s/it]
Training 1/1 epoch (loss 2.5257):  93%|█████████▎| 1158/1250 [28:11<01:57,  1.28s/it]
Training 1/1 epoch (loss 2.5206):  93%|█████████▎| 1158/1250 [28:13<01:57,  1.28s/it]
Training 1/1 epoch (loss 2.5206):  93%|█████████▎| 1159/1250 [28:13<02:16,  1.50s/it]
Training 1/1 epoch (loss 2.5084):  93%|█████████▎| 1159/1250 [28:14<02:16,  1.50s/it]
Training 1/1 epoch (loss 2.5084):  93%|█████████▎| 1160/1250 [28:14<02:02,  1.36s/it]
Training 1/1 epoch (loss 2.3911):  93%|█████████▎| 1160/1250 [28:17<02:02,  1.36s/it]
Training 1/1 epoch (loss 2.3911):  93%|█████████▎| 1161/1250 [28:17<02:29,  1.68s/it]
Training 1/1 epoch (loss 2.5214):  93%|█████████▎| 1161/1250 [28:19<02:29,  1.68s/it]
Training 1/1 epoch (loss 2.5214):  93%|█████████▎| 1162/1250 [28:19<02:36,  1.78s/it]
Training 1/1 epoch (loss 2.4351):  93%|█████████▎| 1162/1250 [28:20<02:36,  1.78s/it]
Training 1/1 epoch (loss 2.4351):  93%|█████████▎| 1163/1250 [28:20<02:21,  1.62s/it]
Training 1/1 epoch (loss 2.3491):  93%|█████████▎| 1163/1250 [28:22<02:21,  1.62s/it]
Training 1/1 epoch (loss 2.3491):  93%|█████████▎| 1164/1250 [28:22<02:39,  1.86s/it]
Training 1/1 epoch (loss 2.5583):  93%|█████████▎| 1164/1250 [28:24<02:39,  1.86s/it]
Training 1/1 epoch (loss 2.5583):  93%|█████████▎| 1165/1250 [28:24<02:32,  1.79s/it]
Training 1/1 epoch (loss 2.6846):  93%|█████████▎| 1165/1250 [28:26<02:32,  1.79s/it]
Training 1/1 epoch (loss 2.6846):  93%|█████████▎| 1166/1250 [28:26<02:23,  1.71s/it]
Training 1/1 epoch (loss 2.7476):  93%|█████████▎| 1166/1250 [28:28<02:23,  1.71s/it]
Training 1/1 epoch (loss 2.7476):  93%|█████████▎| 1167/1250 [28:28<02:26,  1.77s/it]
Training 1/1 epoch (loss 2.6697):  93%|█████████▎| 1167/1250 [28:29<02:26,  1.77s/it]
Training 1/1 epoch (loss 2.6697):  93%|█████████▎| 1168/1250 [28:29<02:12,  1.62s/it]
Training 1/1 epoch (loss 2.3768):  93%|█████████▎| 1168/1250 [28:30<02:12,  1.62s/it]
Training 1/1 epoch (loss 2.3768):  94%|█████████▎| 1169/1250 [28:30<02:07,  1.58s/it]
Training 1/1 epoch (loss 2.4952):  94%|█████████▎| 1169/1250 [28:32<02:07,  1.58s/it]
Training 1/1 epoch (loss 2.4952):  94%|█████████▎| 1170/1250 [28:32<02:07,  1.59s/it]
Training 1/1 epoch (loss 2.5288):  94%|█████████▎| 1170/1250 [28:32<02:07,  1.59s/it]
Training 1/1 epoch (loss 2.5288):  94%|█████████▎| 1171/1250 [28:32<01:41,  1.29s/it]
Training 1/1 epoch (loss 2.6879):  94%|█████████▎| 1171/1250 [28:34<01:41,  1.29s/it]
Training 1/1 epoch (loss 2.6879):  94%|█████████▍| 1172/1250 [28:34<01:43,  1.33s/it]
Training 1/1 epoch (loss 2.7168):  94%|█████████▍| 1172/1250 [28:35<01:43,  1.33s/it]
Training 1/1 epoch (loss 2.7168):  94%|█████████▍| 1173/1250 [28:35<01:45,  1.37s/it]
Training 1/1 epoch (loss 2.6382):  94%|█████████▍| 1173/1250 [28:36<01:45,  1.37s/it]
Training 1/1 epoch (loss 2.6382):  94%|█████████▍| 1174/1250 [28:36<01:23,  1.10s/it]
Training 1/1 epoch (loss 2.6200):  94%|█████████▍| 1174/1250 [28:37<01:23,  1.10s/it]
Training 1/1 epoch (loss 2.6200):  94%|█████████▍| 1175/1250 [28:37<01:27,  1.17s/it]
Training 1/1 epoch (loss 2.5829):  94%|█████████▍| 1175/1250 [28:39<01:27,  1.17s/it]
Training 1/1 epoch (loss 2.5829):  94%|█████████▍| 1176/1250 [28:39<01:45,  1.43s/it]
Training 1/1 epoch (loss 2.6541):  94%|█████████▍| 1176/1250 [28:41<01:45,  1.43s/it]
Training 1/1 epoch (loss 2.6541):  94%|█████████▍| 1177/1250 [28:41<01:42,  1.40s/it]
Training 1/1 epoch (loss 2.6480):  94%|█████████▍| 1177/1250 [28:42<01:42,  1.40s/it]
Training 1/1 epoch (loss 2.6480):  94%|█████████▍| 1178/1250 [28:42<01:50,  1.53s/it]
Training 1/1 epoch (loss 2.5011):  94%|█████████▍| 1178/1250 [28:43<01:50,  1.53s/it]
Training 1/1 epoch (loss 2.5011):  94%|█████████▍| 1179/1250 [28:43<01:38,  1.39s/it]
Training 1/1 epoch (loss 2.6760):  94%|█████████▍| 1179/1250 [28:44<01:38,  1.39s/it]
Training 1/1 epoch (loss 2.6760):  94%|█████████▍| 1180/1250 [28:44<01:28,  1.26s/it]
Training 1/1 epoch (loss 2.6525):  94%|█████████▍| 1180/1250 [28:47<01:28,  1.26s/it]
Training 1/1 epoch (loss 2.6525):  94%|█████████▍| 1181/1250 [28:47<01:50,  1.60s/it]
Training 1/1 epoch (loss 2.6090):  94%|█████████▍| 1181/1250 [28:47<01:50,  1.60s/it]
Training 1/1 epoch (loss 2.6090):  95%|█████████▍| 1182/1250 [28:47<01:30,  1.33s/it]
Training 1/1 epoch (loss 2.5906):  95%|█████████▍| 1182/1250 [28:50<01:30,  1.33s/it]
Training 1/1 epoch (loss 2.5906):  95%|█████████▍| 1183/1250 [28:50<01:52,  1.67s/it]
Training 1/1 epoch (loss 2.5045):  95%|█████████▍| 1183/1250 [28:52<01:52,  1.67s/it]
Training 1/1 epoch (loss 2.5045):  95%|█████████▍| 1184/1250 [28:52<01:59,  1.81s/it]
Training 1/1 epoch (loss 2.6087):  95%|█████████▍| 1184/1250 [28:53<01:59,  1.81s/it]
Training 1/1 epoch (loss 2.6087):  95%|█████████▍| 1185/1250 [28:53<01:46,  1.64s/it]
Training 1/1 epoch (loss 2.5958):  95%|█████████▍| 1185/1250 [28:55<01:46,  1.64s/it]
Training 1/1 epoch (loss 2.5958):  95%|█████████▍| 1186/1250 [28:55<01:39,  1.56s/it]
Training 1/1 epoch (loss 2.7413):  95%|█████████▍| 1186/1250 [28:56<01:39,  1.56s/it]
Training 1/1 epoch (loss 2.7413):  95%|█████████▍| 1187/1250 [28:56<01:37,  1.55s/it]
Training 1/1 epoch (loss 2.3428):  95%|█████████▍| 1187/1250 [28:58<01:37,  1.55s/it]
Training 1/1 epoch (loss 2.3428):  95%|█████████▌| 1188/1250 [28:58<01:39,  1.60s/it]
Training 1/1 epoch (loss 2.4637):  95%|█████████▌| 1188/1250 [28:59<01:39,  1.60s/it]
Training 1/1 epoch (loss 2.4637):  95%|█████████▌| 1189/1250 [28:59<01:35,  1.57s/it]
Training 1/1 epoch (loss 2.8186):  95%|█████████▌| 1189/1250 [29:01<01:35,  1.57s/it]
Training 1/1 epoch (loss 2.8186):  95%|█████████▌| 1190/1250 [29:01<01:35,  1.58s/it]
Training 1/1 epoch (loss 2.7044):  95%|█████████▌| 1190/1250 [29:02<01:35,  1.58s/it]
Training 1/1 epoch (loss 2.7044):  95%|█████████▌| 1191/1250 [29:02<01:21,  1.38s/it]
Training 1/1 epoch (loss 2.5824):  95%|█████████▌| 1191/1250 [29:04<01:21,  1.38s/it]
Training 1/1 epoch (loss 2.5824):  95%|█████████▌| 1192/1250 [29:04<01:25,  1.47s/it]
Training 1/1 epoch (loss 2.5608):  95%|█████████▌| 1192/1250 [29:05<01:25,  1.47s/it]
Training 1/1 epoch (loss 2.5608):  95%|█████████▌| 1193/1250 [29:05<01:17,  1.36s/it]
Training 1/1 epoch (loss 2.6238):  95%|█████████▌| 1193/1250 [29:07<01:17,  1.36s/it]
Training 1/1 epoch (loss 2.6238):  96%|█████████▌| 1194/1250 [29:07<01:31,  1.63s/it]
Training 1/1 epoch (loss 2.7050):  96%|█████████▌| 1194/1250 [29:09<01:31,  1.63s/it]
Training 1/1 epoch (loss 2.7050):  96%|█████████▌| 1195/1250 [29:09<01:32,  1.68s/it]
Training 1/1 epoch (loss 2.8214):  96%|█████████▌| 1195/1250 [29:10<01:32,  1.68s/it]
Training 1/1 epoch (loss 2.8214):  96%|█████████▌| 1196/1250 [29:10<01:24,  1.56s/it]
Training 1/1 epoch (loss 2.6563):  96%|█████████▌| 1196/1250 [29:12<01:24,  1.56s/it]
Training 1/1 epoch (loss 2.6563):  96%|█████████▌| 1197/1250 [29:12<01:32,  1.74s/it]
Training 1/1 epoch (loss 2.4924):  96%|█████████▌| 1197/1250 [29:13<01:32,  1.74s/it]
Training 1/1 epoch (loss 2.4924):  96%|█████████▌| 1198/1250 [29:13<01:16,  1.48s/it]
Training 1/1 epoch (loss 2.5062):  96%|█████████▌| 1198/1250 [29:15<01:16,  1.48s/it]
Training 1/1 epoch (loss 2.5062):  96%|█████████▌| 1199/1250 [29:15<01:25,  1.69s/it]
Training 1/1 epoch (loss 2.4934):  96%|█████████▌| 1199/1250 [29:17<01:25,  1.69s/it]
Training 1/1 epoch (loss 2.4934):  96%|█████████▌| 1200/1250 [29:17<01:18,  1.57s/it]
Training 1/1 epoch (loss 2.4510):  96%|█████████▌| 1200/1250 [29:18<01:18,  1.57s/it]
Training 1/1 epoch (loss 2.4510):  96%|█████████▌| 1201/1250 [29:18<01:21,  1.66s/it]
Training 1/1 epoch (loss 2.3981):  96%|█████████▌| 1201/1250 [29:20<01:21,  1.66s/it]
Training 1/1 epoch (loss 2.3981):  96%|█████████▌| 1202/1250 [29:20<01:23,  1.75s/it]
Training 1/1 epoch (loss 2.6060):  96%|█████████▌| 1202/1250 [29:21<01:23,  1.75s/it]
Training 1/1 epoch (loss 2.6060):  96%|█████████▌| 1203/1250 [29:21<01:05,  1.39s/it]
Training 1/1 epoch (loss 2.4702):  96%|█████████▌| 1203/1250 [29:22<01:05,  1.39s/it]
Training 1/1 epoch (loss 2.4702):  96%|█████████▋| 1204/1250 [29:22<01:03,  1.38s/it]
Training 1/1 epoch (loss 2.8554):  96%|█████████▋| 1204/1250 [29:24<01:03,  1.38s/it]
Training 1/1 epoch (loss 2.8554):  96%|█████████▋| 1205/1250 [29:24<01:10,  1.56s/it]
Training 1/1 epoch (loss 2.5014):  96%|█████████▋| 1205/1250 [29:25<01:10,  1.56s/it]
Training 1/1 epoch (loss 2.5014):  96%|█████████▋| 1206/1250 [29:25<00:56,  1.29s/it]
Training 1/1 epoch (loss 2.5519):  96%|█████████▋| 1206/1250 [29:26<00:56,  1.29s/it]
Training 1/1 epoch (loss 2.5519):  97%|█████████▋| 1207/1250 [29:26<00:56,  1.31s/it]
Training 1/1 epoch (loss 2.5414):  97%|█████████▋| 1207/1250 [29:27<00:56,  1.31s/it]
Training 1/1 epoch (loss 2.5414):  97%|█████████▋| 1208/1250 [29:27<00:51,  1.23s/it]
Training 1/1 epoch (loss 2.5866):  97%|█████████▋| 1208/1250 [29:28<00:51,  1.23s/it]
Training 1/1 epoch (loss 2.5866):  97%|█████████▋| 1209/1250 [29:28<00:46,  1.13s/it]
Training 1/1 epoch (loss 2.7022):  97%|█████████▋| 1209/1250 [29:31<00:46,  1.13s/it]
Training 1/1 epoch (loss 2.7022):  97%|█████████▋| 1210/1250 [29:31<01:01,  1.53s/it]
Training 1/1 epoch (loss 2.5918):  97%|█████████▋| 1210/1250 [29:32<01:01,  1.53s/it]
Training 1/1 epoch (loss 2.5918):  97%|█████████▋| 1211/1250 [29:32<00:52,  1.34s/it]
Training 1/1 epoch (loss 2.5189):  97%|█████████▋| 1211/1250 [29:33<00:52,  1.34s/it]
Training 1/1 epoch (loss 2.5189):  97%|█████████▋| 1212/1250 [29:33<00:50,  1.32s/it]
Training 1/1 epoch (loss 2.6406):  97%|█████████▋| 1212/1250 [29:34<00:50,  1.32s/it]
Training 1/1 epoch (loss 2.6406):  97%|█████████▋| 1213/1250 [29:34<00:47,  1.28s/it]
Training 1/1 epoch (loss 2.3997):  97%|█████████▋| 1213/1250 [29:35<00:47,  1.28s/it]
Training 1/1 epoch (loss 2.3997):  97%|█████████▋| 1214/1250 [29:35<00:44,  1.24s/it]
Training 1/1 epoch (loss 2.5515):  97%|█████████▋| 1214/1250 [29:37<00:44,  1.24s/it]
Training 1/1 epoch (loss 2.5515):  97%|█████████▋| 1215/1250 [29:37<00:44,  1.26s/it]
Training 1/1 epoch (loss 2.8467):  97%|█████████▋| 1215/1250 [29:39<00:44,  1.26s/it]
Training 1/1 epoch (loss 2.8467):  97%|█████████▋| 1216/1250 [29:39<00:57,  1.70s/it]
Training 1/1 epoch (loss 2.4436):  97%|█████████▋| 1216/1250 [29:40<00:57,  1.70s/it]
Training 1/1 epoch (loss 2.4436):  97%|█████████▋| 1217/1250 [29:40<00:44,  1.35s/it]
Training 1/1 epoch (loss 2.5091):  97%|█████████▋| 1217/1250 [29:41<00:44,  1.35s/it]
Training 1/1 epoch (loss 2.5091):  97%|█████████▋| 1218/1250 [29:41<00:45,  1.43s/it]
Training 1/1 epoch (loss 2.6322):  97%|█████████▋| 1218/1250 [29:43<00:45,  1.43s/it]
Training 1/1 epoch (loss 2.6322):  98%|█████████▊| 1219/1250 [29:43<00:46,  1.52s/it]
Training 1/1 epoch (loss 2.5312):  98%|█████████▊| 1219/1250 [29:44<00:46,  1.52s/it]
Training 1/1 epoch (loss 2.5312):  98%|█████████▊| 1220/1250 [29:44<00:38,  1.28s/it]
Training 1/1 epoch (loss 2.4408):  98%|█████████▊| 1220/1250 [29:45<00:38,  1.28s/it]
Training 1/1 epoch (loss 2.4408):  98%|█████████▊| 1221/1250 [29:45<00:34,  1.18s/it]
Training 1/1 epoch (loss 2.4282):  98%|█████████▊| 1221/1250 [29:46<00:34,  1.18s/it]
Training 1/1 epoch (loss 2.4282):  98%|█████████▊| 1222/1250 [29:46<00:36,  1.31s/it]
Training 1/1 epoch (loss 2.4532):  98%|█████████▊| 1222/1250 [29:47<00:36,  1.31s/it]
Training 1/1 epoch (loss 2.4532):  98%|█████████▊| 1223/1250 [29:47<00:32,  1.19s/it]
Training 1/1 epoch (loss 2.5952):  98%|█████████▊| 1223/1250 [29:50<00:32,  1.19s/it]
Training 1/1 epoch (loss 2.5952):  98%|█████████▊| 1224/1250 [29:50<00:39,  1.53s/it]
Training 1/1 epoch (loss 2.6099):  98%|█████████▊| 1224/1250 [29:50<00:39,  1.53s/it]
Training 1/1 epoch (loss 2.6099):  98%|█████████▊| 1225/1250 [29:50<00:33,  1.32s/it]
Training 1/1 epoch (loss 2.6889):  98%|█████████▊| 1225/1250 [29:51<00:33,  1.32s/it]
Training 1/1 epoch (loss 2.6889):  98%|█████████▊| 1226/1250 [29:51<00:29,  1.23s/it]
Training 1/1 epoch (loss 2.5131):  98%|█████████▊| 1226/1250 [29:53<00:29,  1.23s/it]
Training 1/1 epoch (loss 2.5131):  98%|█████████▊| 1227/1250 [29:53<00:33,  1.44s/it]
Training 1/1 epoch (loss 2.6867):  98%|█████████▊| 1227/1250 [29:54<00:33,  1.44s/it]
Training 1/1 epoch (loss 2.6867):  98%|█████████▊| 1228/1250 [29:54<00:25,  1.16s/it]
Training 1/1 epoch (loss 2.3714):  98%|█████████▊| 1228/1250 [29:56<00:25,  1.16s/it]
Training 1/1 epoch (loss 2.3714):  98%|█████████▊| 1229/1250 [29:56<00:28,  1.36s/it]
Training 1/1 epoch (loss 2.6576):  98%|█████████▊| 1229/1250 [29:57<00:28,  1.36s/it]
Training 1/1 epoch (loss 2.6576):  98%|█████████▊| 1230/1250 [29:57<00:26,  1.35s/it]
Training 1/1 epoch (loss 2.4986):  98%|█████████▊| 1230/1250 [29:58<00:26,  1.35s/it]
Training 1/1 epoch (loss 2.4986):  98%|█████████▊| 1231/1250 [29:58<00:22,  1.17s/it]
Training 1/1 epoch (loss 2.6246):  98%|█████████▊| 1231/1250 [30:01<00:22,  1.17s/it]
Training 1/1 epoch (loss 2.6246):  99%|█████████▊| 1232/1250 [30:01<00:30,  1.71s/it]
Training 1/1 epoch (loss 2.6569):  99%|█████████▊| 1232/1250 [30:03<00:30,  1.71s/it]
Training 1/1 epoch (loss 2.6569):  99%|█████████▊| 1233/1250 [30:03<00:30,  1.80s/it]
Training 1/1 epoch (loss 2.6504):  99%|█████████▊| 1233/1250 [30:04<00:30,  1.80s/it]
Training 1/1 epoch (loss 2.6504):  99%|█████████▊| 1234/1250 [30:04<00:24,  1.50s/it]
Training 1/1 epoch (loss 2.5479):  99%|█████████▊| 1234/1250 [30:05<00:24,  1.50s/it]
Training 1/1 epoch (loss 2.5479):  99%|█████████▉| 1235/1250 [30:05<00:20,  1.39s/it]
Training 1/1 epoch (loss 2.4806):  99%|█████████▉| 1235/1250 [30:07<00:20,  1.39s/it]
Training 1/1 epoch (loss 2.4806):  99%|█████████▉| 1236/1250 [30:07<00:21,  1.52s/it]
Training 1/1 epoch (loss 2.4953):  99%|█████████▉| 1236/1250 [30:07<00:21,  1.52s/it]
Training 1/1 epoch (loss 2.4953):  99%|█████████▉| 1237/1250 [30:07<00:15,  1.22s/it]
Training 1/1 epoch (loss 2.5670):  99%|█████████▉| 1237/1250 [30:09<00:15,  1.22s/it]
Training 1/1 epoch (loss 2.5670):  99%|█████████▉| 1238/1250 [30:09<00:15,  1.28s/it]
Training 1/1 epoch (loss 2.6437):  99%|█████████▉| 1238/1250 [30:10<00:15,  1.28s/it]
Training 1/1 epoch (loss 2.6437):  99%|█████████▉| 1239/1250 [30:10<00:14,  1.28s/it]
Training 1/1 epoch (loss 2.5759):  99%|█████████▉| 1239/1250 [30:11<00:14,  1.28s/it]
Training 1/1 epoch (loss 2.5759):  99%|█████████▉| 1240/1250 [30:11<00:11,  1.16s/it]
Training 1/1 epoch (loss 2.6161):  99%|█████████▉| 1240/1250 [30:12<00:11,  1.16s/it]
Training 1/1 epoch (loss 2.6161):  99%|█████████▉| 1241/1250 [30:12<00:11,  1.30s/it]
Training 1/1 epoch (loss 2.6190):  99%|█████████▉| 1241/1250 [30:13<00:11,  1.30s/it]
Training 1/1 epoch (loss 2.6190):  99%|█████████▉| 1242/1250 [30:13<00:09,  1.15s/it]
Training 1/1 epoch (loss 2.7743):  99%|█████████▉| 1242/1250 [30:15<00:09,  1.15s/it]
Training 1/1 epoch (loss 2.7743):  99%|█████████▉| 1243/1250 [30:15<00:09,  1.30s/it]
Training 1/1 epoch (loss 2.7077):  99%|█████████▉| 1243/1250 [30:17<00:09,  1.30s/it]
Training 1/1 epoch (loss 2.7077): 100%|█████████▉| 1244/1250 [30:17<00:09,  1.55s/it]
Training 1/1 epoch (loss 2.8131): 100%|█████████▉| 1244/1250 [30:17<00:09,  1.55s/it]
Training 1/1 epoch (loss 2.8131): 100%|█████████▉| 1245/1250 [30:17<00:06,  1.21s/it]
Training 1/1 epoch (loss 2.4559): 100%|█████████▉| 1245/1250 [30:19<00:06,  1.21s/it]
Training 1/1 epoch (loss 2.4559): 100%|█████████▉| 1246/1250 [30:19<00:05,  1.40s/it]
Training 1/1 epoch (loss 2.7500): 100%|█████████▉| 1246/1250 [30:21<00:05,  1.40s/it]
Training 1/1 epoch (loss 2.7500): 100%|█████████▉| 1247/1250 [30:21<00:05,  1.67s/it]
Training 1/1 epoch (loss 2.6166): 100%|█████████▉| 1247/1250 [30:22<00:05,  1.67s/it]
Training 1/1 epoch (loss 2.6166): 100%|█████████▉| 1248/1250 [30:22<00:02,  1.32s/it]
Training 1/1 epoch (loss 2.7382): 100%|█████████▉| 1248/1250 [30:24<00:02,  1.32s/it]
Training 1/1 epoch (loss 2.7382): 100%|█████████▉| 1249/1250 [30:24<00:01,  1.67s/it]
Training 1/1 epoch (loss 2.3804): 100%|█████████▉| 1249/1250 [30:26<00:01,  1.67s/it]
Training 1/1 epoch (loss 2.3804): 100%|██████████| 1250/1250 [30:26<00:00,  1.51s/it]
Training 1/1 epoch (loss 2.3804): 100%|██████████| 1250/1250 [30:26<00:00,  1.46s/it]
tokenizer config file saved in /aifs4su/hansirui_1st/jiayi/setting3-imdb/tinyllama-3T/tinyllama-3T-s3-Q1-10000/tokenizer_config.json
Special tokens file saved in /aifs4su/hansirui_1st/jiayi/setting3-imdb/tinyllama-3T/tinyllama-3T-s3-Q1-10000/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 0x155081f08290>>
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/jy-resist/lib/python3.11/site-packages/wandb/sdk/wandb_run.py", line 406, in wrapper
    return func(self, *args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/aifs4su/hansirui_1st/miniconda3/envs/jy-resist/lib/python3.11/site-packages/wandb/sdk/wandb_run.py", line 503, in wrapper
    return func(self, *args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/aifs4su/hansirui_1st/miniconda3/envs/jy-resist/lib/python3.11/site-packages/wandb/sdk/wandb_run.py", line 451, in wrapper
    return func(self, *args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/aifs4su/hansirui_1st/miniconda3/envs/jy-resist/lib/python3.11/site-packages/wandb/sdk/wandb_run.py", line 2309, in finish
    return self._finish(exit_code)
           ^^^^^^^^^^^^^^^^^^^^^^^
  File "/aifs4su/hansirui_1st/miniconda3/envs/jy-resist/lib/python3.11/site-packages/wandb/sdk/wandb_run.py", line 406, in wrapper
    return func(self, *args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/aifs4su/hansirui_1st/miniconda3/envs/jy-resist/lib/python3.11/site-packages/wandb/sdk/wandb_run.py", line 2337, in _finish
    self._atexit_cleanup(exit_code=exit_code)
  File "/aifs4su/hansirui_1st/miniconda3/envs/jy-resist/lib/python3.11/site-packages/wandb/sdk/wandb_run.py", line 2550, in _atexit_cleanup
    self._on_finish()
  File "/aifs4su/hansirui_1st/miniconda3/envs/jy-resist/lib/python3.11/site-packages/wandb/sdk/wandb_run.py", line 2806, in _on_finish
    wait_with_progress(
  File "/aifs4su/hansirui_1st/miniconda3/envs/jy-resist/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/jy-resist/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/jy-resist/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/jy-resist/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