stderr.log

+ deepspeed --master_port 51152 --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-480k-1T --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-1T/tinyllama-1T-s3-Q1-10000 --log_type wandb --log_run_name imdb-tinyllama-1T-s3-Q1-10000 --log_project Inverse_Alignment_IMDb --zero_stage 3 --offload none --bf16 True --tf32 True --save_16bit
[rank5]:[W529 17:25:51.014365012 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]:[W529 17:25:51.021848873 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.
[rank6]:[W529 17:25:51.119147718 ProcessGroupNCCL.cpp:4561] [PG ID 0 PG GUID 0 Rank 6]  using GPU 6 to perform barrier as devices used by this process are currently unknown. This can potentially cause a hang if this rank to GPU mapping is incorrect. Specify device_ids in barrier() to force use of a particular device, or call init_process_group() with a device_id.
[rank3]:[W529 17:25:52.805304718 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.
[rank0]:[W529 17:25:53.276718923 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.
[rank1]:[W529 17:25:53.276893358 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.
[rank4]:[W529 17:25:53.276897994 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.
[rank2]:[W529 17:25:53.282328237 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-480k-1T/config.json
loading configuration file /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-480k-1T/config.json
loading configuration file /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-480k-1T/config.json
loading configuration file /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-480k-1T/config.json
loading configuration file /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-480k-1T/config.json
loading configuration file /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-480k-1T/config.json
loading configuration file /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-480k-1T/config.json
loading configuration file /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-480k-1T/config.json
Model config LlamaConfig {
  "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-480k-1T/model.safetensors
loading weights file /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-480k-1T/model.safetensors
loading weights file /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-480k-1T/model.safetensors
loading weights file /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-480k-1T/model.safetensors
loading weights file /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-480k-1T/model.safetensors
loading weights file /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-480k-1T/model.safetensors
loading weights file /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-480k-1T/model.safetensors
loading weights file /aifs4su/hansirui_1st/models/TinyLlama-1.1B-intermediate-step-480k-1T/model.safetensors
Will use torch_dtype=torch.float32 as defined in model's config object
Instantiating LlamaForCausalLM model under default dtype torch.float32.
Will use torch_dtype=torch.float32 as defined in model's config object
Instantiating LlamaForCausalLM model under default dtype torch.float32.
Detected DeepSpeed ZeRO-3: activating zero.init() for this model
Will use torch_dtype=torch.float32 as defined in model's config object
Will use torch_dtype=torch.float32 as defined in model's config object
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.
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.
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
Detected DeepSpeed ZeRO-3: activating zero.init() for this model
Detected DeepSpeed ZeRO-3: activating zero.init() for this model
Detected DeepSpeed ZeRO-3: activating zero.init() for this model
Will use torch_dtype=torch.float32 as defined in model's config object
Instantiating LlamaForCausalLM model under default dtype torch.float32.
Detected DeepSpeed ZeRO-3: activating zero.init() for this model
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 model checkpoint weights were used when initializing LlamaForCausalLM.

All model checkpoint weights were used when initializing LlamaForCausalLM.

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

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

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

All model checkpoint weights were used when initializing LlamaForCausalLM.

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

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

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

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

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

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

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

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

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

loading file tokenizer.model
loading file tokenizer.json
loading file added_tokens.json
loading file special_tokens_map.json
loading file tokenizer_config.json
loading file chat_template.jinja
You are resizing the embedding layer without providing a `pad_to_multiple_of` parameter. This means that the new embedding dimension will be 32001. This might induce some performance reduction as *Tensor Cores* will not be available. For more details about this, or help on choosing the correct value for resizing, refer to this guide: https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html#requirements-tc
The new embeddings will be initialized from a multivariate normal distribution that has old embeddings' mean and covariance. As described in this article: https://nlp.stanford.edu/~johnhew/vocab-expansion.html. To disable this, use `mean_resizing=False`
The new embeddings will be initialized from a multivariate normal distribution that has old embeddings' mean and covariance. As described in this article: https://nlp.stanford.edu/~johnhew/vocab-expansion.html. To disable this, use `mean_resizing=False`
The new embeddings will be initialized from a multivariate normal distribution that has old embeddings' mean and covariance. As described in this article: https://nlp.stanford.edu/~johnhew/vocab-expansion.html. To disable this, use `mean_resizing=False`
The new embeddings will be initialized from a multivariate normal distribution that has old embeddings' mean and covariance. As described in this article: https://nlp.stanford.edu/~johnhew/vocab-expansion.html. To disable this, use `mean_resizing=False`
The new embeddings will be initialized from a multivariate normal distribution that has old embeddings' mean and covariance. As described in this article: https://nlp.stanford.edu/~johnhew/vocab-expansion.html. To disable this, use `mean_resizing=False`
The new embeddings will be initialized from a multivariate normal distribution that has old embeddings' mean and covariance. As described in this article: https://nlp.stanford.edu/~johnhew/vocab-expansion.html. To disable this, use `mean_resizing=False`
The new embeddings will be initialized from a multivariate normal distribution that has old embeddings' mean and covariance. As described in this article: https://nlp.stanford.edu/~johnhew/vocab-expansion.html. To disable this, use `mean_resizing=False`
The new embeddings will be initialized from a multivariate normal distribution that has old embeddings' mean and covariance. As described in this article: https://nlp.stanford.edu/~johnhew/vocab-expansion.html. To disable this, use `mean_resizing=False`
The new lm_head weights will be initialized from a multivariate normal distribution that has old embeddings' mean and covariance. As described in this article: https://nlp.stanford.edu/~johnhew/vocab-expansion.html. To disable this, use `mean_resizing=False`
The new lm_head weights will be initialized from a multivariate normal distribution that has old embeddings' mean and covariance. As described in this article: https://nlp.stanford.edu/~johnhew/vocab-expansion.html. To disable this, use `mean_resizing=False`
The new lm_head weights will be initialized from a multivariate normal distribution that has old embeddings' mean and covariance. As described in this article: https://nlp.stanford.edu/~johnhew/vocab-expansion.html. To disable this, use `mean_resizing=False`
The new lm_head weights will be initialized from a multivariate normal distribution that has old embeddings' mean and covariance. As described in this article: https://nlp.stanford.edu/~johnhew/vocab-expansion.html. To disable this, use `mean_resizing=False`
The new lm_head weights will be initialized from a multivariate normal distribution that has old embeddings' mean and covariance. As described in this article: https://nlp.stanford.edu/~johnhew/vocab-expansion.html. To disable this, use `mean_resizing=False`
The new lm_head weights will be initialized from a multivariate normal distribution that has old embeddings' mean and covariance. As described in this article: https://nlp.stanford.edu/~johnhew/vocab-expansion.html. To disable this, use `mean_resizing=False`
The new lm_head weights will be initialized from a multivariate normal distribution that has old embeddings' mean and covariance. As described in this article: https://nlp.stanford.edu/~johnhew/vocab-expansion.html. To disable this, use `mean_resizing=False`
The new lm_head weights will be initialized from a multivariate normal distribution that has old embeddings' mean and covariance. As described in this article: https://nlp.stanford.edu/~johnhew/vocab-expansion.html. To disable this, use `mean_resizing=False`
Using /home/hansirui_1st/.cache/torch_extensions/py311_cu124 as PyTorch extensions root...
Using /home/hansirui_1st/.cache/torch_extensions/py311_cu124 as PyTorch extensions root...
Using /home/hansirui_1st/.cache/torch_extensions/py311_cu124 as PyTorch extensions root...
Using /home/hansirui_1st/.cache/torch_extensions/py311_cu124 as PyTorch extensions root...
Using /home/hansirui_1st/.cache/torch_extensions/py311_cu124 as PyTorch extensions root...
Using /home/hansirui_1st/.cache/torch_extensions/py311_cu124 as PyTorch extensions root...
Using /home/hansirui_1st/.cache/torch_extensions/py311_cu124 as PyTorch extensions root...
Using /home/hansirui_1st/.cache/torch_extensions/py311_cu124 as PyTorch extensions root...
Detected CUDA files, patching ldflags
Emitting ninja build file /home/hansirui_1st/.cache/torch_extensions/py311_cu124/fused_adam/build.ninja...
/aifs4su/hansirui_1st/miniconda3/envs/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-1T/tinyllama-1T-s3-Q1-10000/wandb/run-20250529_172629-0t1vq5hu
wandb: Run `wandb offline` to turn off syncing.
wandb: Syncing run imdb-tinyllama-1T-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/0t1vq5hu

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 2.9431):   0%|          | 0/1250 [00:05<?, ?it/s]
Training 1/1 epoch (loss 2.9431):   0%|          | 1/1250 [00:05<1:53:28,  5.45s/it]
Training 1/1 epoch (loss 2.9469):   0%|          | 1/1250 [00:07<1:53:28,  5.45s/it]
Training 1/1 epoch (loss 2.9469):   0%|          | 2/1250 [00:07<1:06:30,  3.20s/it]
Training 1/1 epoch (loss 2.8404):   0%|          | 2/1250 [00:07<1:06:30,  3.20s/it]
Training 1/1 epoch (loss 2.8404):   0%|          | 3/1250 [00:07<39:16,  1.89s/it]  
Training 1/1 epoch (loss 3.2492):   0%|          | 3/1250 [00:07<39:16,  1.89s/it]
Training 1/1 epoch (loss 3.2492):   0%|          | 4/1250 [00:07<26:19,  1.27s/it]
Training 1/1 epoch (loss 2.9856):   0%|          | 4/1250 [00:08<26:19,  1.27s/it]
Training 1/1 epoch (loss 2.9856):   0%|          | 5/1250 [00:08<19:52,  1.04it/s]
Training 1/1 epoch (loss 3.2084):   0%|          | 5/1250 [00:08<19:52,  1.04it/s]
Training 1/1 epoch (loss 3.2084):   0%|          | 6/1250 [00:08<15:21,  1.35it/s]
Training 1/1 epoch (loss 2.9686):   0%|          | 6/1250 [00:08<15:21,  1.35it/s]
Training 1/1 epoch (loss 2.9686):   1%|          | 7/1250 [00:08<12:48,  1.62it/s]
Training 1/1 epoch (loss 2.8229):   1%|          | 7/1250 [00:09<12:48,  1.62it/s]
Training 1/1 epoch (loss 2.8229):   1%|          | 8/1250 [00:09<11:25,  1.81it/s]
Training 1/1 epoch (loss 2.9485):   1%|          | 8/1250 [00:09<11:25,  1.81it/s]
Training 1/1 epoch (loss 2.9485):   1%|          | 9/1250 [00:09<10:04,  2.05it/s]
Training 1/1 epoch (loss 2.7161):   1%|          | 9/1250 [00:09<10:04,  2.05it/s]
Training 1/1 epoch (loss 2.7161):   1%|          | 10/1250 [00:09<08:55,  2.32it/s]
Training 1/1 epoch (loss 3.0050):   1%|          | 10/1250 [00:10<08:55,  2.32it/s]
Training 1/1 epoch (loss 3.0050):   1%|          | 11/1250 [00:10<08:40,  2.38it/s]
Training 1/1 epoch (loss 2.9368):   1%|          | 11/1250 [00:10<08:40,  2.38it/s]
Training 1/1 epoch (loss 2.9368):   1%|          | 12/1250 [00:10<08:01,  2.57it/s]
Training 1/1 epoch (loss 2.8264):   1%|          | 12/1250 [00:10<08:01,  2.57it/s]
Training 1/1 epoch (loss 2.8264):   1%|          | 13/1250 [00:10<07:33,  2.73it/s]
Training 1/1 epoch (loss 2.6714):   1%|          | 13/1250 [00:11<07:33,  2.73it/s]
Training 1/1 epoch (loss 2.6714):   1%|          | 14/1250 [00:11<07:07,  2.89it/s]
Training 1/1 epoch (loss 3.0056):   1%|          | 14/1250 [00:11<07:07,  2.89it/s]
Training 1/1 epoch (loss 3.0056):   1%|          | 15/1250 [00:11<07:06,  2.89it/s]
Training 1/1 epoch (loss 2.8702):   1%|          | 15/1250 [00:11<07:06,  2.89it/s]
Training 1/1 epoch (loss 2.8702):   1%|▏         | 16/1250 [00:11<06:55,  2.97it/s]
Training 1/1 epoch (loss 2.9951):   1%|▏         | 16/1250 [00:12<06:55,  2.97it/s]
Training 1/1 epoch (loss 2.9951):   1%|▏         | 17/1250 [00:12<07:17,  2.82it/s]
Training 1/1 epoch (loss 3.0666):   1%|▏         | 17/1250 [00:12<07:17,  2.82it/s]
Training 1/1 epoch (loss 3.0666):   1%|▏         | 18/1250 [00:12<07:08,  2.87it/s]
Training 1/1 epoch (loss 2.9809):   1%|▏         | 18/1250 [00:12<07:08,  2.87it/s]
Training 1/1 epoch (loss 2.9809):   2%|▏         | 19/1250 [00:12<06:53,  2.98it/s]
Training 1/1 epoch (loss 2.9604):   2%|▏         | 19/1250 [00:13<06:53,  2.98it/s]
Training 1/1 epoch (loss 2.9604):   2%|▏         | 20/1250 [00:13<06:46,  3.02it/s]
Training 1/1 epoch (loss 2.8485):   2%|▏         | 20/1250 [00:13<06:46,  3.02it/s]
Training 1/1 epoch (loss 2.8485):   2%|▏         | 21/1250 [00:13<06:35,  3.11it/s]
Training 1/1 epoch (loss 3.1385):   2%|▏         | 21/1250 [00:13<06:35,  3.11it/s]
Training 1/1 epoch (loss 3.1385):   2%|▏         | 22/1250 [00:13<07:05,  2.89it/s]
Training 1/1 epoch (loss 3.0077):   2%|▏         | 22/1250 [00:14<07:05,  2.89it/s]
Training 1/1 epoch (loss 3.0077):   2%|▏         | 23/1250 [00:14<07:10,  2.85it/s]
Training 1/1 epoch (loss 2.5717):   2%|▏         | 23/1250 [00:14<07:10,  2.85it/s]
Training 1/1 epoch (loss 2.5717):   2%|▏         | 24/1250 [00:14<07:13,  2.82it/s]
Training 1/1 epoch (loss 2.8567):   2%|▏         | 24/1250 [00:14<07:13,  2.82it/s]
Training 1/1 epoch (loss 2.8567):   2%|▏         | 25/1250 [00:14<07:12,  2.83it/s]
Training 1/1 epoch (loss 2.7675):   2%|▏         | 25/1250 [00:15<07:12,  2.83it/s]
Training 1/1 epoch (loss 2.7675):   2%|▏         | 26/1250 [00:15<06:55,  2.94it/s]
Training 1/1 epoch (loss 3.0234):   2%|▏         | 26/1250 [00:15<06:55,  2.94it/s]
Training 1/1 epoch (loss 3.0234):   2%|▏         | 27/1250 [00:15<07:09,  2.85it/s]
Training 1/1 epoch (loss 3.0146):   2%|▏         | 27/1250 [00:15<07:09,  2.85it/s]
Training 1/1 epoch (loss 3.0146):   2%|▏         | 28/1250 [00:15<06:57,  2.92it/s]
Training 1/1 epoch (loss 2.9705):   2%|▏         | 28/1250 [00:16<06:57,  2.92it/s]
Training 1/1 epoch (loss 2.9705):   2%|▏         | 29/1250 [00:16<06:59,  2.91it/s]
Training 1/1 epoch (loss 2.9443):   2%|▏         | 29/1250 [00:16<06:59,  2.91it/s]
Training 1/1 epoch (loss 2.9443):   2%|▏         | 30/1250 [00:16<07:07,  2.85it/s]
Training 1/1 epoch (loss 3.1438):   2%|▏         | 30/1250 [00:17<07:07,  2.85it/s]
Training 1/1 epoch (loss 3.1438):   2%|▏         | 31/1250 [00:17<07:03,  2.88it/s]
Training 1/1 epoch (loss 2.9828):   2%|▏         | 31/1250 [00:17<07:03,  2.88it/s]
Training 1/1 epoch (loss 2.9828):   3%|▎         | 32/1250 [00:17<06:59,  2.90it/s]
Training 1/1 epoch (loss 3.0442):   3%|▎         | 32/1250 [00:17<06:59,  2.90it/s]
Training 1/1 epoch (loss 3.0442):   3%|▎         | 33/1250 [00:17<07:02,  2.88it/s]
Training 1/1 epoch (loss 2.7946):   3%|▎         | 33/1250 [00:18<07:02,  2.88it/s]
Training 1/1 epoch (loss 2.7946):   3%|▎         | 34/1250 [00:18<07:05,  2.86it/s]
Training 1/1 epoch (loss 2.9816):   3%|▎         | 34/1250 [00:18<07:05,  2.86it/s]
Training 1/1 epoch (loss 2.9816):   3%|▎         | 35/1250 [00:18<07:00,  2.89it/s]
Training 1/1 epoch (loss 2.9471):   3%|▎         | 35/1250 [00:18<07:00,  2.89it/s]
Training 1/1 epoch (loss 2.9471):   3%|▎         | 36/1250 [00:18<06:58,  2.90it/s]
Training 1/1 epoch (loss 2.7825):   3%|▎         | 36/1250 [00:19<06:58,  2.90it/s]
Training 1/1 epoch (loss 2.7825):   3%|▎         | 37/1250 [00:19<06:58,  2.90it/s]
Training 1/1 epoch (loss 2.7514):   3%|▎         | 37/1250 [00:19<06:58,  2.90it/s]
Training 1/1 epoch (loss 2.7514):   3%|▎         | 38/1250 [00:19<06:47,  2.97it/s]
Training 1/1 epoch (loss 3.0962):   3%|▎         | 38/1250 [00:19<06:47,  2.97it/s]
Training 1/1 epoch (loss 3.0962):   3%|▎         | 39/1250 [00:19<06:44,  2.99it/s]
Training 1/1 epoch (loss 2.8145):   3%|▎         | 39/1250 [00:20<06:44,  2.99it/s]
Training 1/1 epoch (loss 2.8145):   3%|▎         | 40/1250 [00:20<07:05,  2.84it/s]
Training 1/1 epoch (loss 2.9322):   3%|▎         | 40/1250 [00:20<07:05,  2.84it/s]
Training 1/1 epoch (loss 2.9322):   3%|▎         | 41/1250 [00:20<06:52,  2.93it/s]
Training 1/1 epoch (loss 2.7641):   3%|▎         | 41/1250 [00:20<06:52,  2.93it/s]
Training 1/1 epoch (loss 2.7641):   3%|▎         | 42/1250 [00:20<07:14,  2.78it/s]
Training 1/1 epoch (loss 2.8599):   3%|▎         | 42/1250 [00:21<07:14,  2.78it/s]
Training 1/1 epoch (loss 2.8599):   3%|▎         | 43/1250 [00:21<06:58,  2.88it/s]
Training 1/1 epoch (loss 2.9119):   3%|▎         | 43/1250 [00:21<06:58,  2.88it/s]
Training 1/1 epoch (loss 2.9119):   4%|▎         | 44/1250 [00:21<06:46,  2.96it/s]
Training 1/1 epoch (loss 2.8669):   4%|▎         | 44/1250 [00:21<06:46,  2.96it/s]
Training 1/1 epoch (loss 2.8669):   4%|▎         | 45/1250 [00:21<06:51,  2.93it/s]
Training 1/1 epoch (loss 2.7548):   4%|▎         | 45/1250 [00:22<06:51,  2.93it/s]
Training 1/1 epoch (loss 2.7548):   4%|▎         | 46/1250 [00:22<06:58,  2.88it/s]
Training 1/1 epoch (loss 2.9779):   4%|▎         | 46/1250 [00:22<06:58,  2.88it/s]
Training 1/1 epoch (loss 2.9779):   4%|▍         | 47/1250 [00:22<06:36,  3.03it/s]
Training 1/1 epoch (loss 2.9614):   4%|▍         | 47/1250 [00:22<06:36,  3.03it/s]
Training 1/1 epoch (loss 2.9614):   4%|▍         | 48/1250 [00:22<06:46,  2.95it/s]
Training 1/1 epoch (loss 2.7782):   4%|▍         | 48/1250 [00:23<06:46,  2.95it/s]
Training 1/1 epoch (loss 2.7782):   4%|▍         | 49/1250 [00:23<08:02,  2.49it/s]
Training 1/1 epoch (loss 2.9420):   4%|▍         | 49/1250 [00:23<08:02,  2.49it/s]
Training 1/1 epoch (loss 2.9420):   4%|▍         | 50/1250 [00:23<07:40,  2.60it/s]
Training 1/1 epoch (loss 2.8061):   4%|▍         | 50/1250 [00:24<07:40,  2.60it/s]
Training 1/1 epoch (loss 2.8061):   4%|▍         | 51/1250 [00:24<07:57,  2.51it/s]
Training 1/1 epoch (loss 2.8840):   4%|▍         | 51/1250 [00:24<07:57,  2.51it/s]
Training 1/1 epoch (loss 2.8840):   4%|▍         | 52/1250 [00:24<07:33,  2.64it/s]
Training 1/1 epoch (loss 2.9800):   4%|▍         | 52/1250 [00:24<07:33,  2.64it/s]
Training 1/1 epoch (loss 2.9800):   4%|▍         | 53/1250 [00:24<07:25,  2.69it/s]
Training 1/1 epoch (loss 2.7454):   4%|▍         | 53/1250 [00:25<07:25,  2.69it/s]
Training 1/1 epoch (loss 2.7454):   4%|▍         | 54/1250 [00:25<07:23,  2.70it/s]
Training 1/1 epoch (loss 2.8337):   4%|▍         | 54/1250 [00:25<07:23,  2.70it/s]
Training 1/1 epoch (loss 2.8337):   4%|▍         | 55/1250 [00:25<07:07,  2.80it/s]
Training 1/1 epoch (loss 2.8162):   4%|▍         | 55/1250 [00:25<07:07,  2.80it/s]
Training 1/1 epoch (loss 2.8162):   4%|▍         | 56/1250 [00:25<07:22,  2.70it/s]
Training 1/1 epoch (loss 2.7496):   4%|▍         | 56/1250 [00:26<07:22,  2.70it/s]
Training 1/1 epoch (loss 2.7496):   5%|▍         | 57/1250 [00:26<07:33,  2.63it/s]
Training 1/1 epoch (loss 2.6391):   5%|▍         | 57/1250 [00:26<07:33,  2.63it/s]
Training 1/1 epoch (loss 2.6391):   5%|▍         | 58/1250 [00:26<07:13,  2.75it/s]
Training 1/1 epoch (loss 2.7713):   5%|▍         | 58/1250 [00:27<07:13,  2.75it/s]
Training 1/1 epoch (loss 2.7713):   5%|▍         | 59/1250 [00:27<06:49,  2.91it/s]
Training 1/1 epoch (loss 2.9023):   5%|▍         | 59/1250 [00:27<06:49,  2.91it/s]
Training 1/1 epoch (loss 2.9023):   5%|▍         | 60/1250 [00:27<06:49,  2.91it/s]
Training 1/1 epoch (loss 2.7720):   5%|▍         | 60/1250 [00:27<06:49,  2.91it/s]
Training 1/1 epoch (loss 2.7720):   5%|▍         | 61/1250 [00:27<06:50,  2.89it/s]
Training 1/1 epoch (loss 2.8423):   5%|▍         | 61/1250 [00:28<06:50,  2.89it/s]
Training 1/1 epoch (loss 2.8423):   5%|▍         | 62/1250 [00:28<07:55,  2.50it/s]
Training 1/1 epoch (loss 2.9824):   5%|▍         | 62/1250 [00:28<07:55,  2.50it/s]
Training 1/1 epoch (loss 2.9824):   5%|▌         | 63/1250 [00:28<08:24,  2.35it/s]
Training 1/1 epoch (loss 3.1130):   5%|▌         | 63/1250 [00:29<08:24,  2.35it/s]
Training 1/1 epoch (loss 3.1130):   5%|▌         | 64/1250 [00:29<07:47,  2.54it/s]
Training 1/1 epoch (loss 2.8913):   5%|▌         | 64/1250 [00:29<07:47,  2.54it/s]
Training 1/1 epoch (loss 2.8913):   5%|▌         | 65/1250 [00:29<07:41,  2.57it/s]
Training 1/1 epoch (loss 2.7743):   5%|▌         | 65/1250 [00:29<07:41,  2.57it/s]
Training 1/1 epoch (loss 2.7743):   5%|▌         | 66/1250 [00:29<07:34,  2.61it/s]
Training 1/1 epoch (loss 2.8412):   5%|▌         | 66/1250 [00:30<07:34,  2.61it/s]
Training 1/1 epoch (loss 2.8412):   5%|▌         | 67/1250 [00:30<07:39,  2.57it/s]
Training 1/1 epoch (loss 2.9112):   5%|▌         | 67/1250 [00:30<07:39,  2.57it/s]
Training 1/1 epoch (loss 2.9112):   5%|▌         | 68/1250 [00:30<07:09,  2.75it/s]
Training 1/1 epoch (loss 2.7371):   5%|▌         | 68/1250 [00:30<07:09,  2.75it/s]
Training 1/1 epoch (loss 2.7371):   6%|▌         | 69/1250 [00:30<07:02,  2.80it/s]
Training 1/1 epoch (loss 2.9480):   6%|▌         | 69/1250 [00:31<07:02,  2.80it/s]
Training 1/1 epoch (loss 2.9480):   6%|▌         | 70/1250 [00:31<07:01,  2.80it/s]
Training 1/1 epoch (loss 2.7706):   6%|▌         | 70/1250 [00:31<07:01,  2.80it/s]
Training 1/1 epoch (loss 2.7706):   6%|▌         | 71/1250 [00:31<06:46,  2.90it/s]
Training 1/1 epoch (loss 2.7700):   6%|▌         | 71/1250 [00:31<06:46,  2.90it/s]
Training 1/1 epoch (loss 2.7700):   6%|▌         | 72/1250 [00:31<06:48,  2.88it/s]
Training 1/1 epoch (loss 2.9774):   6%|▌         | 72/1250 [00:32<06:48,  2.88it/s]
Training 1/1 epoch (loss 2.9774):   6%|▌         | 73/1250 [00:32<06:51,  2.86it/s]
Training 1/1 epoch (loss 2.9490):   6%|▌         | 73/1250 [00:32<06:51,  2.86it/s]
Training 1/1 epoch (loss 2.9490):   6%|▌         | 74/1250 [00:32<06:38,  2.95it/s]
Training 1/1 epoch (loss 2.8017):   6%|▌         | 74/1250 [00:32<06:38,  2.95it/s]
Training 1/1 epoch (loss 2.8017):   6%|▌         | 75/1250 [00:32<06:37,  2.96it/s]
Training 1/1 epoch (loss 2.8868):   6%|▌         | 75/1250 [00:33<06:37,  2.96it/s]
Training 1/1 epoch (loss 2.8868):   6%|▌         | 76/1250 [00:33<06:33,  2.98it/s]
Training 1/1 epoch (loss 2.7817):   6%|▌         | 76/1250 [00:33<06:33,  2.98it/s]
Training 1/1 epoch (loss 2.7817):   6%|▌         | 77/1250 [00:33<06:38,  2.94it/s]
Training 1/1 epoch (loss 2.9865):   6%|▌         | 77/1250 [00:33<06:38,  2.94it/s]
Training 1/1 epoch (loss 2.9865):   6%|▌         | 78/1250 [00:33<06:54,  2.83it/s]
Training 1/1 epoch (loss 2.8642):   6%|▌         | 78/1250 [00:34<06:54,  2.83it/s]
Training 1/1 epoch (loss 2.8642):   6%|▋         | 79/1250 [00:34<07:08,  2.73it/s]
Training 1/1 epoch (loss 2.8344):   6%|▋         | 79/1250 [00:34<07:08,  2.73it/s]
Training 1/1 epoch (loss 2.8344):   6%|▋         | 80/1250 [00:34<06:53,  2.83it/s]
Training 1/1 epoch (loss 2.9445):   6%|▋         | 80/1250 [00:34<06:53,  2.83it/s]
Training 1/1 epoch (loss 2.9445):   6%|▋         | 81/1250 [00:34<06:46,  2.88it/s]
Training 1/1 epoch (loss 2.9105):   6%|▋         | 81/1250 [00:35<06:46,  2.88it/s]
Training 1/1 epoch (loss 2.9105):   7%|▋         | 82/1250 [00:35<06:35,  2.95it/s]
Training 1/1 epoch (loss 2.9879):   7%|▋         | 82/1250 [00:35<06:35,  2.95it/s]
Training 1/1 epoch (loss 2.9879):   7%|▋         | 83/1250 [00:35<06:23,  3.04it/s]
Training 1/1 epoch (loss 2.8390):   7%|▋         | 83/1250 [00:35<06:23,  3.04it/s]
Training 1/1 epoch (loss 2.8390):   7%|▋         | 84/1250 [00:35<06:29,  2.99it/s]
Training 1/1 epoch (loss 2.7115):   7%|▋         | 84/1250 [00:36<06:29,  2.99it/s]
Training 1/1 epoch (loss 2.7115):   7%|▋         | 85/1250 [00:36<06:29,  2.99it/s]
Training 1/1 epoch (loss 2.8002):   7%|▋         | 85/1250 [00:36<06:29,  2.99it/s]
Training 1/1 epoch (loss 2.8002):   7%|▋         | 86/1250 [00:36<06:41,  2.90it/s]
Training 1/1 epoch (loss 2.9690):   7%|▋         | 86/1250 [00:37<06:41,  2.90it/s]
Training 1/1 epoch (loss 2.9690):   7%|▋         | 87/1250 [00:37<06:43,  2.88it/s]
Training 1/1 epoch (loss 2.7454):   7%|▋         | 87/1250 [00:37<06:43,  2.88it/s]
Training 1/1 epoch (loss 2.7454):   7%|▋         | 88/1250 [00:37<06:43,  2.88it/s]
Training 1/1 epoch (loss 2.8628):   7%|▋         | 88/1250 [00:37<06:43,  2.88it/s]
Training 1/1 epoch (loss 2.8628):   7%|▋         | 89/1250 [00:37<06:38,  2.91it/s]
Training 1/1 epoch (loss 3.0633):   7%|▋         | 89/1250 [00:38<06:38,  2.91it/s]
Training 1/1 epoch (loss 3.0633):   7%|▋         | 90/1250 [00:38<06:43,  2.88it/s]
Training 1/1 epoch (loss 2.7011):   7%|▋         | 90/1250 [00:38<06:43,  2.88it/s]
Training 1/1 epoch (loss 2.7011):   7%|▋         | 91/1250 [00:38<06:39,  2.90it/s]
Training 1/1 epoch (loss 2.7780):   7%|▋         | 91/1250 [00:38<06:39,  2.90it/s]
Training 1/1 epoch (loss 2.7780):   7%|▋         | 92/1250 [00:38<06:33,  2.94it/s]
Training 1/1 epoch (loss 2.7543):   7%|▋         | 92/1250 [00:39<06:33,  2.94it/s]
Training 1/1 epoch (loss 2.7543):   7%|▋         | 93/1250 [00:39<06:49,  2.82it/s]
Training 1/1 epoch (loss 2.7619):   7%|▋         | 93/1250 [00:39<06:49,  2.82it/s]
Training 1/1 epoch (loss 2.7619):   8%|▊         | 94/1250 [00:39<07:15,  2.66it/s]
Training 1/1 epoch (loss 2.8318):   8%|▊         | 94/1250 [00:39<07:15,  2.66it/s]
Training 1/1 epoch (loss 2.8318):   8%|▊         | 95/1250 [00:39<07:34,  2.54it/s]
Training 1/1 epoch (loss 2.8768):   8%|▊         | 95/1250 [00:40<07:34,  2.54it/s]
Training 1/1 epoch (loss 2.8768):   8%|▊         | 96/1250 [00:40<08:13,  2.34it/s]
Training 1/1 epoch (loss 2.7662):   8%|▊         | 96/1250 [00:40<08:13,  2.34it/s]
Training 1/1 epoch (loss 2.7662):   8%|▊         | 97/1250 [00:40<07:58,  2.41it/s]
Training 1/1 epoch (loss 2.7607):   8%|▊         | 97/1250 [00:41<07:58,  2.41it/s]
Training 1/1 epoch (loss 2.7607):   8%|▊         | 98/1250 [00:41<07:19,  2.62it/s]
Training 1/1 epoch (loss 2.8731):   8%|▊         | 98/1250 [00:41<07:19,  2.62it/s]
Training 1/1 epoch (loss 2.8731):   8%|▊         | 99/1250 [00:41<06:53,  2.79it/s]
Training 1/1 epoch (loss 3.0974):   8%|▊         | 99/1250 [00:41<06:53,  2.79it/s]
Training 1/1 epoch (loss 3.0974):   8%|▊         | 100/1250 [00:41<07:10,  2.67it/s]
Training 1/1 epoch (loss 2.8144):   8%|▊         | 100/1250 [00:42<07:10,  2.67it/s]
Training 1/1 epoch (loss 2.8144):   8%|▊         | 101/1250 [00:42<06:58,  2.75it/s]
Training 1/1 epoch (loss 2.7572):   8%|▊         | 101/1250 [00:42<06:58,  2.75it/s]
Training 1/1 epoch (loss 2.7572):   8%|▊         | 102/1250 [00:42<06:49,  2.81it/s]
Training 1/1 epoch (loss 2.8391):   8%|▊         | 102/1250 [00:42<06:49,  2.81it/s]
Training 1/1 epoch (loss 2.8391):   8%|▊         | 103/1250 [00:42<06:30,  2.94it/s]
Training 1/1 epoch (loss 2.9753):   8%|▊         | 103/1250 [00:43<06:30,  2.94it/s]
Training 1/1 epoch (loss 2.9753):   8%|▊         | 104/1250 [00:43<06:33,  2.91it/s]
Training 1/1 epoch (loss 2.8194):   8%|▊         | 104/1250 [00:43<06:33,  2.91it/s]
Training 1/1 epoch (loss 2.8194):   8%|▊         | 105/1250 [00:43<06:20,  3.01it/s]
Training 1/1 epoch (loss 2.8027):   8%|▊         | 105/1250 [00:43<06:20,  3.01it/s]
Training 1/1 epoch (loss 2.8027):   8%|▊         | 106/1250 [00:43<06:52,  2.78it/s]
Training 1/1 epoch (loss 2.8189):   8%|▊         | 106/1250 [00:44<06:52,  2.78it/s]
Training 1/1 epoch (loss 2.8189):   9%|▊         | 107/1250 [00:44<06:44,  2.82it/s]
Training 1/1 epoch (loss 2.9953):   9%|▊         | 107/1250 [00:44<06:44,  2.82it/s]
Training 1/1 epoch (loss 2.9953):   9%|▊         | 108/1250 [00:44<06:34,  2.89it/s]
Training 1/1 epoch (loss 2.9417):   9%|▊         | 108/1250 [00:44<06:34,  2.89it/s]
Training 1/1 epoch (loss 2.9417):   9%|▊         | 109/1250 [00:44<06:20,  3.00it/s]
Training 1/1 epoch (loss 2.8546):   9%|▊         | 109/1250 [00:45<06:20,  3.00it/s]
Training 1/1 epoch (loss 2.8546):   9%|▉         | 110/1250 [00:45<06:14,  3.04it/s]
Training 1/1 epoch (loss 2.8867):   9%|▉         | 110/1250 [00:45<06:14,  3.04it/s]
Training 1/1 epoch (loss 2.8867):   9%|▉         | 111/1250 [00:45<06:16,  3.02it/s]
Training 1/1 epoch (loss 2.7350):   9%|▉         | 111/1250 [00:45<06:16,  3.02it/s]
Training 1/1 epoch (loss 2.7350):   9%|▉         | 112/1250 [00:45<06:17,  3.01it/s]
Training 1/1 epoch (loss 2.7250):   9%|▉         | 112/1250 [00:46<06:17,  3.01it/s]
Training 1/1 epoch (loss 2.7250):   9%|▉         | 113/1250 [00:46<06:31,  2.90it/s]
Training 1/1 epoch (loss 2.6639):   9%|▉         | 113/1250 [00:46<06:31,  2.90it/s]
Training 1/1 epoch (loss 2.6639):   9%|▉         | 114/1250 [00:46<06:35,  2.87it/s]
Training 1/1 epoch (loss 2.7430):   9%|▉         | 114/1250 [00:46<06:35,  2.87it/s]
Training 1/1 epoch (loss 2.7430):   9%|▉         | 115/1250 [00:46<06:32,  2.89it/s]
Training 1/1 epoch (loss 2.8149):   9%|▉         | 115/1250 [00:47<06:32,  2.89it/s]
Training 1/1 epoch (loss 2.8149):   9%|▉         | 116/1250 [00:47<06:16,  3.01it/s]
Training 1/1 epoch (loss 2.7659):   9%|▉         | 116/1250 [00:47<06:16,  3.01it/s]
Training 1/1 epoch (loss 2.7659):   9%|▉         | 117/1250 [00:47<06:18,  2.99it/s]
Training 1/1 epoch (loss 2.7451):   9%|▉         | 117/1250 [00:47<06:18,  2.99it/s]
Training 1/1 epoch (loss 2.7451):   9%|▉         | 118/1250 [00:47<06:18,  2.99it/s]
Training 1/1 epoch (loss 2.8699):   9%|▉         | 118/1250 [00:48<06:18,  2.99it/s]
Training 1/1 epoch (loss 2.8699):  10%|▉         | 119/1250 [00:48<06:24,  2.94it/s]
Training 1/1 epoch (loss 2.9826):  10%|▉         | 119/1250 [00:48<06:24,  2.94it/s]
Training 1/1 epoch (loss 2.9826):  10%|▉         | 120/1250 [00:48<06:40,  2.82it/s]
Training 1/1 epoch (loss 2.9322):  10%|▉         | 120/1250 [00:49<06:40,  2.82it/s]
Training 1/1 epoch (loss 2.9322):  10%|▉         | 121/1250 [00:49<06:31,  2.89it/s]
Training 1/1 epoch (loss 2.7240):  10%|▉         | 121/1250 [00:49<06:31,  2.89it/s]
Training 1/1 epoch (loss 2.7240):  10%|▉         | 122/1250 [00:49<06:16,  2.99it/s]
Training 1/1 epoch (loss 2.8411):  10%|▉         | 122/1250 [00:49<06:16,  2.99it/s]
Training 1/1 epoch (loss 2.8411):  10%|▉         | 123/1250 [00:49<06:11,  3.04it/s]
Training 1/1 epoch (loss 2.6664):  10%|▉         | 123/1250 [00:49<06:11,  3.04it/s]
Training 1/1 epoch (loss 2.6664):  10%|▉         | 124/1250 [00:49<05:57,  3.15it/s]
Training 1/1 epoch (loss 2.5935):  10%|▉         | 124/1250 [00:50<05:57,  3.15it/s]
Training 1/1 epoch (loss 2.5935):  10%|█         | 125/1250 [00:50<06:17,  2.98it/s]
Training 1/1 epoch (loss 2.8362):  10%|█         | 125/1250 [00:50<06:17,  2.98it/s]
Training 1/1 epoch (loss 2.8362):  10%|█         | 126/1250 [00:50<06:14,  3.00it/s]
Training 1/1 epoch (loss 2.6994):  10%|█         | 126/1250 [00:50<06:14,  3.00it/s]
Training 1/1 epoch (loss 2.6994):  10%|█         | 127/1250 [00:50<06:10,  3.03it/s]
Training 1/1 epoch (loss 2.8743):  10%|█         | 127/1250 [00:51<06:10,  3.03it/s]
Training 1/1 epoch (loss 2.8743):  10%|█         | 128/1250 [00:51<06:03,  3.09it/s]
Training 1/1 epoch (loss 2.7251):  10%|█         | 128/1250 [00:51<06:03,  3.09it/s]
Training 1/1 epoch (loss 2.7251):  10%|█         | 129/1250 [00:51<05:55,  3.16it/s]
Training 1/1 epoch (loss 2.7631):  10%|█         | 129/1250 [00:51<05:55,  3.16it/s]
Training 1/1 epoch (loss 2.7631):  10%|█         | 130/1250 [00:51<06:10,  3.03it/s]
Training 1/1 epoch (loss 2.9168):  10%|█         | 130/1250 [00:52<06:10,  3.03it/s]
Training 1/1 epoch (loss 2.9168):  10%|█         | 131/1250 [00:52<06:37,  2.81it/s]
Training 1/1 epoch (loss 2.9141):  10%|█         | 131/1250 [00:52<06:37,  2.81it/s]
Training 1/1 epoch (loss 2.9141):  11%|█         | 132/1250 [00:52<06:23,  2.92it/s]
Training 1/1 epoch (loss 2.8750):  11%|█         | 132/1250 [00:52<06:23,  2.92it/s]
Training 1/1 epoch (loss 2.8750):  11%|█         | 133/1250 [00:52<06:16,  2.97it/s]
Training 1/1 epoch (loss 2.9954):  11%|█         | 133/1250 [00:53<06:16,  2.97it/s]
Training 1/1 epoch (loss 2.9954):  11%|█         | 134/1250 [00:53<07:50,  2.37it/s]
Training 1/1 epoch (loss 2.8709):  11%|█         | 134/1250 [00:54<07:50,  2.37it/s]
Training 1/1 epoch (loss 2.8709):  11%|█         | 135/1250 [00:54<07:50,  2.37it/s]
Training 1/1 epoch (loss 2.8426):  11%|█         | 135/1250 [00:54<07:50,  2.37it/s]
Training 1/1 epoch (loss 2.8426):  11%|█         | 136/1250 [00:54<07:35,  2.45it/s]
Training 1/1 epoch (loss 2.7097):  11%|█         | 136/1250 [00:54<07:35,  2.45it/s]
Training 1/1 epoch (loss 2.7097):  11%|█         | 137/1250 [00:54<07:18,  2.54it/s]
Training 1/1 epoch (loss 2.7272):  11%|█         | 137/1250 [00:55<07:18,  2.54it/s]
Training 1/1 epoch (loss 2.7272):  11%|█         | 138/1250 [00:55<06:51,  2.70it/s]
Training 1/1 epoch (loss 2.9721):  11%|█         | 138/1250 [00:55<06:51,  2.70it/s]
Training 1/1 epoch (loss 2.9721):  11%|█         | 139/1250 [00:55<06:36,  2.80it/s]
Training 1/1 epoch (loss 2.8974):  11%|█         | 139/1250 [00:55<06:36,  2.80it/s]
Training 1/1 epoch (loss 2.8974):  11%|█         | 140/1250 [00:55<06:14,  2.97it/s]
Training 1/1 epoch (loss 2.7571):  11%|█         | 140/1250 [00:56<06:14,  2.97it/s]
Training 1/1 epoch (loss 2.7571):  11%|█▏        | 141/1250 [00:56<06:32,  2.83it/s]
Training 1/1 epoch (loss 2.9425):  11%|█▏        | 141/1250 [00:56<06:32,  2.83it/s]
Training 1/1 epoch (loss 2.9425):  11%|█▏        | 142/1250 [00:56<06:29,  2.84it/s]
Training 1/1 epoch (loss 2.7775):  11%|█▏        | 142/1250 [00:56<06:29,  2.84it/s]
Training 1/1 epoch (loss 2.7775):  11%|█▏        | 143/1250 [00:56<06:21,  2.90it/s]
Training 1/1 epoch (loss 2.9933):  11%|█▏        | 143/1250 [00:57<06:21,  2.90it/s]
Training 1/1 epoch (loss 2.9933):  12%|█▏        | 144/1250 [00:57<06:21,  2.90it/s]
Training 1/1 epoch (loss 2.8607):  12%|█▏        | 144/1250 [00:57<06:21,  2.90it/s]
Training 1/1 epoch (loss 2.8607):  12%|█▏        | 145/1250 [00:57<06:27,  2.85it/s]
Training 1/1 epoch (loss 2.9262):  12%|█▏        | 145/1250 [00:57<06:27,  2.85it/s]
Training 1/1 epoch (loss 2.9262):  12%|█▏        | 146/1250 [00:57<06:20,  2.90it/s]
Training 1/1 epoch (loss 2.7681):  12%|█▏        | 146/1250 [00:58<06:20,  2.90it/s]
Training 1/1 epoch (loss 2.7681):  12%|█▏        | 147/1250 [00:58<07:06,  2.58it/s]
Training 1/1 epoch (loss 2.9255):  12%|█▏        | 147/1250 [00:58<07:06,  2.58it/s]
Training 1/1 epoch (loss 2.9255):  12%|█▏        | 148/1250 [00:58<07:47,  2.36it/s]
Training 1/1 epoch (loss 2.7794):  12%|█▏        | 148/1250 [00:59<07:47,  2.36it/s]
Training 1/1 epoch (loss 2.7794):  12%|█▏        | 149/1250 [00:59<07:04,  2.59it/s]
Training 1/1 epoch (loss 3.0724):  12%|█▏        | 149/1250 [00:59<07:04,  2.59it/s]
Training 1/1 epoch (loss 3.0724):  12%|█▏        | 150/1250 [00:59<07:02,  2.61it/s]
Training 1/1 epoch (loss 2.8239):  12%|█▏        | 150/1250 [00:59<07:02,  2.61it/s]
Training 1/1 epoch (loss 2.8239):  12%|█▏        | 151/1250 [00:59<06:41,  2.74it/s]
Training 1/1 epoch (loss 2.8889):  12%|█▏        | 151/1250 [01:00<06:41,  2.74it/s]
Training 1/1 epoch (loss 2.8889):  12%|█▏        | 152/1250 [01:00<07:23,  2.48it/s]
Training 1/1 epoch (loss 2.9986):  12%|█▏        | 152/1250 [01:00<07:23,  2.48it/s]
Training 1/1 epoch (loss 2.9986):  12%|█▏        | 153/1250 [01:00<07:13,  2.53it/s]
Training 1/1 epoch (loss 2.9800):  12%|█▏        | 153/1250 [01:00<07:13,  2.53it/s]
Training 1/1 epoch (loss 2.9800):  12%|█▏        | 154/1250 [01:00<06:37,  2.75it/s]
Training 1/1 epoch (loss 2.8152):  12%|█▏        | 154/1250 [01:01<06:37,  2.75it/s]
Training 1/1 epoch (loss 2.8152):  12%|█▏        | 155/1250 [01:01<06:18,  2.89it/s]
Training 1/1 epoch (loss 3.0026):  12%|█▏        | 155/1250 [01:01<06:18,  2.89it/s]
Training 1/1 epoch (loss 3.0026):  12%|█▏        | 156/1250 [01:01<06:10,  2.96it/s]
Training 1/1 epoch (loss 2.9617):  12%|█▏        | 156/1250 [01:01<06:10,  2.96it/s]
Training 1/1 epoch (loss 2.9617):  13%|█▎        | 157/1250 [01:01<05:53,  3.09it/s]
Training 1/1 epoch (loss 2.9243):  13%|█▎        | 157/1250 [01:02<05:53,  3.09it/s]
Training 1/1 epoch (loss 2.9243):  13%|█▎        | 158/1250 [01:02<05:59,  3.04it/s]
Training 1/1 epoch (loss 3.1867):  13%|█▎        | 158/1250 [01:02<05:59,  3.04it/s]
Training 1/1 epoch (loss 3.1867):  13%|█▎        | 159/1250 [01:02<06:05,  2.99it/s]
Training 1/1 epoch (loss 2.7637):  13%|█▎        | 159/1250 [01:02<06:05,  2.99it/s]
Training 1/1 epoch (loss 2.7637):  13%|█▎        | 160/1250 [01:02<06:18,  2.88it/s]
Training 1/1 epoch (loss 2.8238):  13%|█▎        | 160/1250 [01:03<06:18,  2.88it/s]
Training 1/1 epoch (loss 2.8238):  13%|█▎        | 161/1250 [01:03<06:09,  2.95it/s]
Training 1/1 epoch (loss 2.7362):  13%|█▎        | 161/1250 [01:03<06:09,  2.95it/s]
Training 1/1 epoch (loss 2.7362):  13%|█▎        | 162/1250 [01:03<05:56,  3.05it/s]
Training 1/1 epoch (loss 2.9208):  13%|█▎        | 162/1250 [01:03<05:56,  3.05it/s]
Training 1/1 epoch (loss 2.9208):  13%|█▎        | 163/1250 [01:03<06:06,  2.97it/s]
Training 1/1 epoch (loss 2.7017):  13%|█▎        | 163/1250 [01:04<06:06,  2.97it/s]
Training 1/1 epoch (loss 2.7017):  13%|█▎        | 164/1250 [01:04<06:27,  2.80it/s]
Training 1/1 epoch (loss 2.8445):  13%|█▎        | 164/1250 [01:04<06:27,  2.80it/s]
Training 1/1 epoch (loss 2.8445):  13%|█▎        | 165/1250 [01:04<06:26,  2.81it/s]
Training 1/1 epoch (loss 2.8219):  13%|█▎        | 165/1250 [01:04<06:26,  2.81it/s]
Training 1/1 epoch (loss 2.8219):  13%|█▎        | 166/1250 [01:04<06:10,  2.93it/s]
Training 1/1 epoch (loss 2.7584):  13%|█▎        | 166/1250 [01:05<06:10,  2.93it/s]
Training 1/1 epoch (loss 2.7584):  13%|█▎        | 167/1250 [01:05<05:57,  3.03it/s]
Training 1/1 epoch (loss 2.7869):  13%|█▎        | 167/1250 [01:05<05:57,  3.03it/s]
Training 1/1 epoch (loss 2.7869):  13%|█▎        | 168/1250 [01:05<06:05,  2.96it/s]
Training 1/1 epoch (loss 2.8387):  13%|█▎        | 168/1250 [01:05<06:05,  2.96it/s]
Training 1/1 epoch (loss 2.8387):  14%|█▎        | 169/1250 [01:05<06:08,  2.93it/s]
Training 1/1 epoch (loss 2.9099):  14%|█▎        | 169/1250 [01:06<06:08,  2.93it/s]
Training 1/1 epoch (loss 2.9099):  14%|█▎        | 170/1250 [01:06<05:57,  3.02it/s]
Training 1/1 epoch (loss 2.8050):  14%|█▎        | 170/1250 [01:06<05:57,  3.02it/s]
Training 1/1 epoch (loss 2.8050):  14%|█▎        | 171/1250 [01:06<06:11,  2.90it/s]
Training 1/1 epoch (loss 2.7045):  14%|█▎        | 171/1250 [01:06<06:11,  2.90it/s]
Training 1/1 epoch (loss 2.7045):  14%|█▍        | 172/1250 [01:06<06:01,  2.98it/s]
Training 1/1 epoch (loss 2.6318):  14%|█▍        | 172/1250 [01:07<06:01,  2.98it/s]
Training 1/1 epoch (loss 2.6318):  14%|█▍        | 173/1250 [01:07<05:53,  3.05it/s]
Training 1/1 epoch (loss 2.9167):  14%|█▍        | 173/1250 [01:07<05:53,  3.05it/s]
Training 1/1 epoch (loss 2.9167):  14%|█▍        | 174/1250 [01:07<06:00,  2.99it/s]
Training 1/1 epoch (loss 3.0358):  14%|█▍        | 174/1250 [01:07<06:00,  2.99it/s]
Training 1/1 epoch (loss 3.0358):  14%|█▍        | 175/1250 [01:07<05:59,  2.99it/s]
Training 1/1 epoch (loss 2.7926):  14%|█▍        | 175/1250 [01:08<05:59,  2.99it/s]
Training 1/1 epoch (loss 2.7926):  14%|█▍        | 176/1250 [01:08<06:05,  2.94it/s]
Training 1/1 epoch (loss 3.0718):  14%|█▍        | 176/1250 [01:08<06:05,  2.94it/s]
Training 1/1 epoch (loss 3.0718):  14%|█▍        | 177/1250 [01:08<06:10,  2.89it/s]
Training 1/1 epoch (loss 2.9168):  14%|█▍        | 177/1250 [01:09<06:10,  2.89it/s]
Training 1/1 epoch (loss 2.9168):  14%|█▍        | 178/1250 [01:09<06:25,  2.78it/s]
Training 1/1 epoch (loss 3.0796):  14%|█▍        | 178/1250 [01:09<06:25,  2.78it/s]
Training 1/1 epoch (loss 3.0796):  14%|█▍        | 179/1250 [01:09<06:03,  2.95it/s]
Training 1/1 epoch (loss 2.9889):  14%|█▍        | 179/1250 [01:09<06:03,  2.95it/s]
Training 1/1 epoch (loss 2.9889):  14%|█▍        | 180/1250 [01:09<05:57,  2.99it/s]
Training 1/1 epoch (loss 2.9761):  14%|█▍        | 180/1250 [01:09<05:57,  2.99it/s]
Training 1/1 epoch (loss 2.9761):  14%|█▍        | 181/1250 [01:09<05:46,  3.09it/s]
Training 1/1 epoch (loss 2.8659):  14%|█▍        | 181/1250 [01:10<05:46,  3.09it/s]
Training 1/1 epoch (loss 2.8659):  15%|█▍        | 182/1250 [01:10<05:44,  3.10it/s]
Training 1/1 epoch (loss 2.9024):  15%|█▍        | 182/1250 [01:10<05:44,  3.10it/s]
Training 1/1 epoch (loss 2.9024):  15%|█▍        | 183/1250 [01:10<06:12,  2.86it/s]
Training 1/1 epoch (loss 2.9271):  15%|█▍        | 183/1250 [01:11<06:12,  2.86it/s]
Training 1/1 epoch (loss 2.9271):  15%|█▍        | 184/1250 [01:11<06:02,  2.94it/s]
Training 1/1 epoch (loss 2.8184):  15%|█▍        | 184/1250 [01:11<06:02,  2.94it/s]
Training 1/1 epoch (loss 2.8184):  15%|█▍        | 185/1250 [01:11<05:56,  2.99it/s]
Training 1/1 epoch (loss 2.8956):  15%|█▍        | 185/1250 [01:11<05:56,  2.99it/s]
Training 1/1 epoch (loss 2.8956):  15%|█▍        | 186/1250 [01:11<05:51,  3.03it/s]
Training 1/1 epoch (loss 2.9444):  15%|█▍        | 186/1250 [01:11<05:51,  3.03it/s]
Training 1/1 epoch (loss 2.9444):  15%|█▍        | 187/1250 [01:11<05:43,  3.09it/s]
Training 1/1 epoch (loss 2.6345):  15%|█▍        | 187/1250 [01:12<05:43,  3.09it/s]
Training 1/1 epoch (loss 2.6345):  15%|█▌        | 188/1250 [01:12<05:52,  3.01it/s]
Training 1/1 epoch (loss 2.7368):  15%|█▌        | 188/1250 [01:12<05:52,  3.01it/s]
Training 1/1 epoch (loss 2.7368):  15%|█▌        | 189/1250 [01:12<05:55,  2.99it/s]
Training 1/1 epoch (loss 2.7126):  15%|█▌        | 189/1250 [01:12<05:55,  2.99it/s]
Training 1/1 epoch (loss 2.7126):  15%|█▌        | 190/1250 [01:12<05:44,  3.08it/s]
Training 1/1 epoch (loss 2.9198):  15%|█▌        | 190/1250 [01:13<05:44,  3.08it/s]
Training 1/1 epoch (loss 2.9198):  15%|█▌        | 191/1250 [01:13<06:03,  2.92it/s]
Training 1/1 epoch (loss 3.0116):  15%|█▌        | 191/1250 [01:13<06:03,  2.92it/s]
Training 1/1 epoch (loss 3.0116):  15%|█▌        | 192/1250 [01:13<05:53,  2.99it/s]
Training 1/1 epoch (loss 2.8323):  15%|█▌        | 192/1250 [01:14<05:53,  2.99it/s]
Training 1/1 epoch (loss 2.8323):  15%|█▌        | 193/1250 [01:14<06:04,  2.90it/s]
Training 1/1 epoch (loss 2.9665):  15%|█▌        | 193/1250 [01:14<06:04,  2.90it/s]
Training 1/1 epoch (loss 2.9665):  16%|█▌        | 194/1250 [01:14<06:17,  2.79it/s]
Training 1/1 epoch (loss 2.8471):  16%|█▌        | 194/1250 [01:14<06:17,  2.79it/s]
Training 1/1 epoch (loss 2.8471):  16%|█▌        | 195/1250 [01:14<06:26,  2.73it/s]
Training 1/1 epoch (loss 2.7015):  16%|█▌        | 195/1250 [01:15<06:26,  2.73it/s]
Training 1/1 epoch (loss 2.7015):  16%|█▌        | 196/1250 [01:15<06:20,  2.77it/s]
Training 1/1 epoch (loss 2.8216):  16%|█▌        | 196/1250 [01:15<06:20,  2.77it/s]
Training 1/1 epoch (loss 2.8216):  16%|█▌        | 197/1250 [01:15<06:09,  2.85it/s]
Training 1/1 epoch (loss 2.9587):  16%|█▌        | 197/1250 [01:15<06:09,  2.85it/s]
Training 1/1 epoch (loss 2.9587):  16%|█▌        | 198/1250 [01:15<05:59,  2.93it/s]
Training 1/1 epoch (loss 2.9185):  16%|█▌        | 198/1250 [01:16<05:59,  2.93it/s]
Training 1/1 epoch (loss 2.9185):  16%|█▌        | 199/1250 [01:16<05:46,  3.04it/s]
Training 1/1 epoch (loss 2.8770):  16%|█▌        | 199/1250 [01:16<05:46,  3.04it/s]
Training 1/1 epoch (loss 2.8770):  16%|█▌        | 200/1250 [01:16<06:10,  2.84it/s]
Training 1/1 epoch (loss 2.9282):  16%|█▌        | 200/1250 [01:16<06:10,  2.84it/s]
Training 1/1 epoch (loss 2.9282):  16%|█▌        | 201/1250 [01:16<06:06,  2.87it/s]
Training 1/1 epoch (loss 2.7861):  16%|█▌        | 201/1250 [01:17<06:06,  2.87it/s]
Training 1/1 epoch (loss 2.7861):  16%|█▌        | 202/1250 [01:17<05:57,  2.93it/s]
Training 1/1 epoch (loss 2.7526):  16%|█▌        | 202/1250 [01:17<05:57,  2.93it/s]
Training 1/1 epoch (loss 2.7526):  16%|█▌        | 203/1250 [01:17<05:52,  2.97it/s]
Training 1/1 epoch (loss 2.7059):  16%|█▌        | 203/1250 [01:17<05:52,  2.97it/s]
Training 1/1 epoch (loss 2.7059):  16%|█▋        | 204/1250 [01:17<05:47,  3.01it/s]
Training 1/1 epoch (loss 2.7238):  16%|█▋        | 204/1250 [01:18<05:47,  3.01it/s]
Training 1/1 epoch (loss 2.7238):  16%|█▋        | 205/1250 [01:18<05:42,  3.05it/s]
Training 1/1 epoch (loss 2.9659):  16%|█▋        | 205/1250 [01:18<05:42,  3.05it/s]
Training 1/1 epoch (loss 2.9659):  16%|█▋        | 206/1250 [01:18<06:09,  2.83it/s]
Training 1/1 epoch (loss 2.8513):  16%|█▋        | 206/1250 [01:18<06:09,  2.83it/s]
Training 1/1 epoch (loss 2.8513):  17%|█▋        | 207/1250 [01:18<06:06,  2.84it/s]
Training 1/1 epoch (loss 2.8415):  17%|█▋        | 207/1250 [01:19<06:06,  2.84it/s]
Training 1/1 epoch (loss 2.8415):  17%|█▋        | 208/1250 [01:19<05:56,  2.93it/s]
Training 1/1 epoch (loss 2.8569):  17%|█▋        | 208/1250 [01:19<05:56,  2.93it/s]
Training 1/1 epoch (loss 2.8569):  17%|█▋        | 209/1250 [01:19<06:01,  2.88it/s]
Training 1/1 epoch (loss 2.9371):  17%|█▋        | 209/1250 [01:19<06:01,  2.88it/s]
Training 1/1 epoch (loss 2.9371):  17%|█▋        | 210/1250 [01:19<05:54,  2.94it/s]
Training 1/1 epoch (loss 2.8593):  17%|█▋        | 210/1250 [01:20<05:54,  2.94it/s]
Training 1/1 epoch (loss 2.8593):  17%|█▋        | 211/1250 [01:20<05:43,  3.02it/s]
Training 1/1 epoch (loss 3.0368):  17%|█▋        | 211/1250 [01:20<05:43,  3.02it/s]
Training 1/1 epoch (loss 3.0368):  17%|█▋        | 212/1250 [01:20<05:43,  3.02it/s]
Training 1/1 epoch (loss 2.7631):  17%|█▋        | 212/1250 [01:21<05:43,  3.02it/s]
Training 1/1 epoch (loss 2.7631):  17%|█▋        | 213/1250 [01:21<06:26,  2.68it/s]
Training 1/1 epoch (loss 2.7101):  17%|█▋        | 213/1250 [01:21<06:26,  2.68it/s]
Training 1/1 epoch (loss 2.7101):  17%|█▋        | 214/1250 [01:21<06:06,  2.82it/s]
Training 1/1 epoch (loss 2.6916):  17%|█▋        | 214/1250 [01:21<06:06,  2.82it/s]
Training 1/1 epoch (loss 2.6916):  17%|█▋        | 215/1250 [01:21<05:51,  2.94it/s]
Training 1/1 epoch (loss 2.5994):  17%|█▋        | 215/1250 [01:21<05:51,  2.94it/s]
Training 1/1 epoch (loss 2.5994):  17%|█▋        | 216/1250 [01:21<05:48,  2.96it/s]
Training 1/1 epoch (loss 2.7197):  17%|█▋        | 216/1250 [01:22<05:48,  2.96it/s]
Training 1/1 epoch (loss 2.7197):  17%|█▋        | 217/1250 [01:22<05:52,  2.93it/s]
Training 1/1 epoch (loss 2.9473):  17%|█▋        | 217/1250 [01:22<05:52,  2.93it/s]
Training 1/1 epoch (loss 2.9473):  17%|█▋        | 218/1250 [01:22<05:54,  2.91it/s]
Training 1/1 epoch (loss 2.9564):  17%|█▋        | 218/1250 [01:23<05:54,  2.91it/s]
Training 1/1 epoch (loss 2.9564):  18%|█▊        | 219/1250 [01:23<06:08,  2.80it/s]
Training 1/1 epoch (loss 2.6365):  18%|█▊        | 219/1250 [01:23<06:08,  2.80it/s]
Training 1/1 epoch (loss 2.6365):  18%|█▊        | 220/1250 [01:23<07:19,  2.34it/s]
Training 1/1 epoch (loss 2.7110):  18%|█▊        | 220/1250 [01:24<07:19,  2.34it/s]
Training 1/1 epoch (loss 2.7110):  18%|█▊        | 221/1250 [01:24<06:53,  2.49it/s]
Training 1/1 epoch (loss 2.9319):  18%|█▊        | 221/1250 [01:24<06:53,  2.49it/s]
Training 1/1 epoch (loss 2.9319):  18%|█▊        | 222/1250 [01:24<06:32,  2.62it/s]
Training 1/1 epoch (loss 2.7660):  18%|█▊        | 222/1250 [01:24<06:32,  2.62it/s]
Training 1/1 epoch (loss 2.7660):  18%|█▊        | 223/1250 [01:24<06:32,  2.62it/s]
Training 1/1 epoch (loss 2.7666):  18%|█▊        | 223/1250 [01:25<06:32,  2.62it/s]
Training 1/1 epoch (loss 2.7666):  18%|█▊        | 224/1250 [01:25<06:43,  2.54it/s]
Training 1/1 epoch (loss 2.6435):  18%|█▊        | 224/1250 [01:25<06:43,  2.54it/s]
Training 1/1 epoch (loss 2.6435):  18%|█▊        | 225/1250 [01:25<06:18,  2.71it/s]
Training 1/1 epoch (loss 2.9251):  18%|█▊        | 225/1250 [01:25<06:18,  2.71it/s]
Training 1/1 epoch (loss 2.9251):  18%|█▊        | 226/1250 [01:25<06:00,  2.84it/s]
Training 1/1 epoch (loss 2.9908):  18%|█▊        | 226/1250 [01:26<06:00,  2.84it/s]
Training 1/1 epoch (loss 2.9908):  18%|█▊        | 227/1250 [01:26<06:02,  2.82it/s]
Training 1/1 epoch (loss 2.8930):  18%|█▊        | 227/1250 [01:26<06:02,  2.82it/s]
Training 1/1 epoch (loss 2.8930):  18%|█▊        | 228/1250 [01:26<06:08,  2.78it/s]
Training 1/1 epoch (loss 2.8373):  18%|█▊        | 228/1250 [01:26<06:08,  2.78it/s]
Training 1/1 epoch (loss 2.8373):  18%|█▊        | 229/1250 [01:26<06:03,  2.81it/s]
Training 1/1 epoch (loss 2.7076):  18%|█▊        | 229/1250 [01:27<06:03,  2.81it/s]
Training 1/1 epoch (loss 2.7076):  18%|█▊        | 230/1250 [01:27<06:05,  2.79it/s]
Training 1/1 epoch (loss 2.9365):  18%|█▊        | 230/1250 [01:27<06:05,  2.79it/s]
Training 1/1 epoch (loss 2.9365):  18%|█▊        | 231/1250 [01:27<05:55,  2.87it/s]
Training 1/1 epoch (loss 2.9870):  18%|█▊        | 231/1250 [01:27<05:55,  2.87it/s]
Training 1/1 epoch (loss 2.9870):  19%|█▊        | 232/1250 [01:27<06:09,  2.76it/s]
Training 1/1 epoch (loss 2.8369):  19%|█▊        | 232/1250 [01:28<06:09,  2.76it/s]
Training 1/1 epoch (loss 2.8369):  19%|█▊        | 233/1250 [01:28<06:28,  2.62it/s]
Training 1/1 epoch (loss 2.8622):  19%|█▊        | 233/1250 [01:28<06:28,  2.62it/s]
Training 1/1 epoch (loss 2.8622):  19%|█▊        | 234/1250 [01:28<07:43,  2.19it/s]
Training 1/1 epoch (loss 2.8816):  19%|█▊        | 234/1250 [01:29<07:43,  2.19it/s]
Training 1/1 epoch (loss 2.8816):  19%|█▉        | 235/1250 [01:29<07:24,  2.28it/s]
Training 1/1 epoch (loss 2.9095):  19%|█▉        | 235/1250 [01:29<07:24,  2.28it/s]
Training 1/1 epoch (loss 2.9095):  19%|█▉        | 236/1250 [01:29<07:22,  2.29it/s]
Training 1/1 epoch (loss 2.6702):  19%|█▉        | 236/1250 [01:30<07:22,  2.29it/s]
Training 1/1 epoch (loss 2.6702):  19%|█▉        | 237/1250 [01:30<07:38,  2.21it/s]
Training 1/1 epoch (loss 2.8421):  19%|█▉        | 237/1250 [01:30<07:38,  2.21it/s]
Training 1/1 epoch (loss 2.8421):  19%|█▉        | 238/1250 [01:30<07:39,  2.20it/s]
Training 1/1 epoch (loss 2.7217):  19%|█▉        | 238/1250 [01:31<07:39,  2.20it/s]
Training 1/1 epoch (loss 2.7217):  19%|█▉        | 239/1250 [01:31<07:31,  2.24it/s]
Training 1/1 epoch (loss 2.7442):  19%|█▉        | 239/1250 [01:31<07:31,  2.24it/s]
Training 1/1 epoch (loss 2.7442):  19%|█▉        | 240/1250 [01:31<07:23,  2.28it/s]
Training 1/1 epoch (loss 2.6688):  19%|█▉        | 240/1250 [01:31<07:23,  2.28it/s]
Training 1/1 epoch (loss 2.6688):  19%|█▉        | 241/1250 [01:31<06:47,  2.48it/s]
Training 1/1 epoch (loss 2.7901):  19%|█▉        | 241/1250 [01:32<06:47,  2.48it/s]
Training 1/1 epoch (loss 2.7901):  19%|█▉        | 242/1250 [01:32<06:16,  2.67it/s]
Training 1/1 epoch (loss 2.6722):  19%|█▉        | 242/1250 [01:32<06:16,  2.67it/s]
Training 1/1 epoch (loss 2.6722):  19%|█▉        | 243/1250 [01:32<06:04,  2.76it/s]
Training 1/1 epoch (loss 2.6406):  19%|█▉        | 243/1250 [01:32<06:04,  2.76it/s]
Training 1/1 epoch (loss 2.6406):  20%|█▉        | 244/1250 [01:32<06:02,  2.77it/s]
Training 1/1 epoch (loss 2.7727):  20%|█▉        | 244/1250 [01:33<06:02,  2.77it/s]
Training 1/1 epoch (loss 2.7727):  20%|█▉        | 245/1250 [01:33<06:04,  2.76it/s]
Training 1/1 epoch (loss 2.8293):  20%|█▉        | 245/1250 [01:33<06:04,  2.76it/s]
Training 1/1 epoch (loss 2.8293):  20%|█▉        | 246/1250 [01:33<05:44,  2.91it/s]
Training 1/1 epoch (loss 2.7062):  20%|█▉        | 246/1250 [01:33<05:44,  2.91it/s]
Training 1/1 epoch (loss 2.7062):  20%|█▉        | 247/1250 [01:33<05:52,  2.85it/s]
Training 1/1 epoch (loss 2.7384):  20%|█▉        | 247/1250 [01:34<05:52,  2.85it/s]
Training 1/1 epoch (loss 2.7384):  20%|█▉        | 248/1250 [01:34<05:54,  2.82it/s]
Training 1/1 epoch (loss 2.9392):  20%|█▉        | 248/1250 [01:34<05:54,  2.82it/s]
Training 1/1 epoch (loss 2.9392):  20%|█▉        | 249/1250 [01:34<06:01,  2.77it/s]
Training 1/1 epoch (loss 2.8576):  20%|█▉        | 249/1250 [01:35<06:01,  2.77it/s]
Training 1/1 epoch (loss 2.8576):  20%|██        | 250/1250 [01:35<05:48,  2.87it/s]
Training 1/1 epoch (loss 2.7553):  20%|██        | 250/1250 [01:35<05:48,  2.87it/s]
Training 1/1 epoch (loss 2.7553):  20%|██        | 251/1250 [01:35<05:39,  2.94it/s]
Training 1/1 epoch (loss 2.8370):  20%|██        | 251/1250 [01:35<05:39,  2.94it/s]
Training 1/1 epoch (loss 2.8370):  20%|██        | 252/1250 [01:35<05:29,  3.03it/s]
Training 1/1 epoch (loss 2.7298):  20%|██        | 252/1250 [01:35<05:29,  3.03it/s]
Training 1/1 epoch (loss 2.7298):  20%|██        | 253/1250 [01:35<05:29,  3.02it/s]
Training 1/1 epoch (loss 2.8798):  20%|██        | 253/1250 [01:36<05:29,  3.02it/s]
Training 1/1 epoch (loss 2.8798):  20%|██        | 254/1250 [01:36<05:39,  2.93it/s]
Training 1/1 epoch (loss 2.7551):  20%|██        | 254/1250 [01:36<05:39,  2.93it/s]
Training 1/1 epoch (loss 2.7551):  20%|██        | 255/1250 [01:36<05:45,  2.88it/s]
Training 1/1 epoch (loss 2.8803):  20%|██        | 255/1250 [01:37<05:45,  2.88it/s]
Training 1/1 epoch (loss 2.8803):  20%|██        | 256/1250 [01:37<05:54,  2.80it/s]
Training 1/1 epoch (loss 2.8360):  20%|██        | 256/1250 [01:37<05:54,  2.80it/s]
Training 1/1 epoch (loss 2.8360):  21%|██        | 257/1250 [01:37<05:55,  2.79it/s]
Training 1/1 epoch (loss 2.8185):  21%|██        | 257/1250 [01:37<05:55,  2.79it/s]
Training 1/1 epoch (loss 2.8185):  21%|██        | 258/1250 [01:37<05:44,  2.88it/s]
Training 1/1 epoch (loss 2.7580):  21%|██        | 258/1250 [01:38<05:44,  2.88it/s]
Training 1/1 epoch (loss 2.7580):  21%|██        | 259/1250 [01:38<05:36,  2.95it/s]
Training 1/1 epoch (loss 2.8601):  21%|██        | 259/1250 [01:38<05:36,  2.95it/s]
Training 1/1 epoch (loss 2.8601):  21%|██        | 260/1250 [01:38<05:45,  2.86it/s]
Training 1/1 epoch (loss 2.7503):  21%|██        | 260/1250 [01:38<05:45,  2.86it/s]
Training 1/1 epoch (loss 2.7503):  21%|██        | 261/1250 [01:38<05:52,  2.81it/s]
Training 1/1 epoch (loss 2.7581):  21%|██        | 261/1250 [01:39<05:52,  2.81it/s]
Training 1/1 epoch (loss 2.7581):  21%|██        | 262/1250 [01:39<05:57,  2.76it/s]
Training 1/1 epoch (loss 2.7755):  21%|██        | 262/1250 [01:39<05:57,  2.76it/s]
Training 1/1 epoch (loss 2.7755):  21%|██        | 263/1250 [01:39<05:53,  2.79it/s]
Training 1/1 epoch (loss 2.5074):  21%|██        | 263/1250 [01:39<05:53,  2.79it/s]
Training 1/1 epoch (loss 2.5074):  21%|██        | 264/1250 [01:39<05:48,  2.83it/s]
Training 1/1 epoch (loss 2.8189):  21%|██        | 264/1250 [01:40<05:48,  2.83it/s]
Training 1/1 epoch (loss 2.8189):  21%|██        | 265/1250 [01:40<05:41,  2.88it/s]
Training 1/1 epoch (loss 2.8258):  21%|██        | 265/1250 [01:40<05:41,  2.88it/s]
Training 1/1 epoch (loss 2.8258):  21%|██▏       | 266/1250 [01:40<05:34,  2.94it/s]
Training 1/1 epoch (loss 2.9070):  21%|██▏       | 266/1250 [01:40<05:34,  2.94it/s]
Training 1/1 epoch (loss 2.9070):  21%|██▏       | 267/1250 [01:40<05:32,  2.96it/s]
Training 1/1 epoch (loss 2.8604):  21%|██▏       | 267/1250 [01:41<05:32,  2.96it/s]
Training 1/1 epoch (loss 2.8604):  21%|██▏       | 268/1250 [01:41<05:32,  2.95it/s]
Training 1/1 epoch (loss 2.8039):  21%|██▏       | 268/1250 [01:41<05:32,  2.95it/s]
Training 1/1 epoch (loss 2.8039):  22%|██▏       | 269/1250 [01:41<05:44,  2.85it/s]
Training 1/1 epoch (loss 2.7712):  22%|██▏       | 269/1250 [01:41<05:44,  2.85it/s]
Training 1/1 epoch (loss 2.7712):  22%|██▏       | 270/1250 [01:41<05:31,  2.96it/s]
Training 1/1 epoch (loss 2.6228):  22%|██▏       | 270/1250 [01:42<05:31,  2.96it/s]
Training 1/1 epoch (loss 2.6228):  22%|██▏       | 271/1250 [01:42<05:20,  3.05it/s]
Training 1/1 epoch (loss 2.5480):  22%|██▏       | 271/1250 [01:42<05:20,  3.05it/s]
Training 1/1 epoch (loss 2.5480):  22%|██▏       | 272/1250 [01:42<05:26,  2.99it/s]
Training 1/1 epoch (loss 2.7337):  22%|██▏       | 272/1250 [01:42<05:26,  2.99it/s]
Training 1/1 epoch (loss 2.7337):  22%|██▏       | 273/1250 [01:42<05:42,  2.85it/s]
Training 1/1 epoch (loss 2.8524):  22%|██▏       | 273/1250 [01:43<05:42,  2.85it/s]
Training 1/1 epoch (loss 2.8524):  22%|██▏       | 274/1250 [01:43<05:35,  2.91it/s]
Training 1/1 epoch (loss 2.9081):  22%|██▏       | 274/1250 [01:43<05:35,  2.91it/s]
Training 1/1 epoch (loss 2.9081):  22%|██▏       | 275/1250 [01:43<05:29,  2.96it/s]
Training 1/1 epoch (loss 2.8290):  22%|██▏       | 275/1250 [01:43<05:29,  2.96it/s]
Training 1/1 epoch (loss 2.8290):  22%|██▏       | 276/1250 [01:43<05:40,  2.86it/s]
Training 1/1 epoch (loss 2.7824):  22%|██▏       | 276/1250 [01:44<05:40,  2.86it/s]
Training 1/1 epoch (loss 2.7824):  22%|██▏       | 277/1250 [01:44<05:52,  2.76it/s]
Training 1/1 epoch (loss 2.9044):  22%|██▏       | 277/1250 [01:44<05:52,  2.76it/s]
Training 1/1 epoch (loss 2.9044):  22%|██▏       | 278/1250 [01:44<05:56,  2.73it/s]
Training 1/1 epoch (loss 2.9523):  22%|██▏       | 278/1250 [01:45<05:56,  2.73it/s]
Training 1/1 epoch (loss 2.9523):  22%|██▏       | 279/1250 [01:45<05:59,  2.70it/s]
Training 1/1 epoch (loss 2.7367):  22%|██▏       | 279/1250 [01:45<05:59,  2.70it/s]
Training 1/1 epoch (loss 2.7367):  22%|██▏       | 280/1250 [01:45<05:48,  2.78it/s]
Training 1/1 epoch (loss 2.9114):  22%|██▏       | 280/1250 [01:45<05:48,  2.78it/s]
Training 1/1 epoch (loss 2.9114):  22%|██▏       | 281/1250 [01:45<05:44,  2.81it/s]
Training 1/1 epoch (loss 2.7701):  22%|██▏       | 281/1250 [01:46<05:44,  2.81it/s]
Training 1/1 epoch (loss 2.7701):  23%|██▎       | 282/1250 [01:46<05:31,  2.92it/s]
Training 1/1 epoch (loss 2.8238):  23%|██▎       | 282/1250 [01:46<05:31,  2.92it/s]
Training 1/1 epoch (loss 2.8238):  23%|██▎       | 283/1250 [01:46<05:32,  2.91it/s]
Training 1/1 epoch (loss 2.9327):  23%|██▎       | 283/1250 [01:46<05:32,  2.91it/s]
Training 1/1 epoch (loss 2.9327):  23%|██▎       | 284/1250 [01:46<05:31,  2.92it/s]
Training 1/1 epoch (loss 2.7839):  23%|██▎       | 284/1250 [01:47<05:31,  2.92it/s]
Training 1/1 epoch (loss 2.7839):  23%|██▎       | 285/1250 [01:47<05:22,  2.99it/s]
Training 1/1 epoch (loss 2.6116):  23%|██▎       | 285/1250 [01:47<05:22,  2.99it/s]
Training 1/1 epoch (loss 2.6116):  23%|██▎       | 286/1250 [01:47<05:19,  3.02it/s]
Training 1/1 epoch (loss 2.7865):  23%|██▎       | 286/1250 [01:47<05:19,  3.02it/s]
Training 1/1 epoch (loss 2.7865):  23%|██▎       | 287/1250 [01:47<05:16,  3.04it/s]
Training 1/1 epoch (loss 2.7880):  23%|██▎       | 287/1250 [01:48<05:16,  3.04it/s]
Training 1/1 epoch (loss 2.7880):  23%|██▎       | 288/1250 [01:48<05:13,  3.07it/s]
Training 1/1 epoch (loss 2.6956):  23%|██▎       | 288/1250 [01:48<05:13,  3.07it/s]
Training 1/1 epoch (loss 2.6956):  23%|██▎       | 289/1250 [01:48<05:19,  3.01it/s]
Training 1/1 epoch (loss 2.6824):  23%|██▎       | 289/1250 [01:48<05:19,  3.01it/s]
Training 1/1 epoch (loss 2.6824):  23%|██▎       | 290/1250 [01:48<05:34,  2.87it/s]
Training 1/1 epoch (loss 2.7482):  23%|██▎       | 290/1250 [01:49<05:34,  2.87it/s]
Training 1/1 epoch (loss 2.7482):  23%|██▎       | 291/1250 [01:49<05:36,  2.85it/s]
Training 1/1 epoch (loss 2.9872):  23%|██▎       | 291/1250 [01:49<05:36,  2.85it/s]
Training 1/1 epoch (loss 2.9872):  23%|██▎       | 292/1250 [01:49<05:33,  2.87it/s]
Training 1/1 epoch (loss 2.9354):  23%|██▎       | 292/1250 [01:49<05:33,  2.87it/s]
Training 1/1 epoch (loss 2.9354):  23%|██▎       | 293/1250 [01:49<05:44,  2.77it/s]
Training 1/1 epoch (loss 2.7712):  23%|██▎       | 293/1250 [01:50<05:44,  2.77it/s]
Training 1/1 epoch (loss 2.7712):  24%|██▎       | 294/1250 [01:50<05:29,  2.90it/s]
Training 1/1 epoch (loss 2.7200):  24%|██▎       | 294/1250 [01:50<05:29,  2.90it/s]
Training 1/1 epoch (loss 2.7200):  24%|██▎       | 295/1250 [01:50<05:24,  2.95it/s]
Training 1/1 epoch (loss 2.8250):  24%|██▎       | 295/1250 [01:51<05:24,  2.95it/s]
Training 1/1 epoch (loss 2.8250):  24%|██▎       | 296/1250 [01:51<05:54,  2.69it/s]
Training 1/1 epoch (loss 2.7569):  24%|██▎       | 296/1250 [01:51<05:54,  2.69it/s]
Training 1/1 epoch (loss 2.7569):  24%|██▍       | 297/1250 [01:51<05:47,  2.74it/s]
Training 1/1 epoch (loss 2.8134):  24%|██▍       | 297/1250 [01:51<05:47,  2.74it/s]
Training 1/1 epoch (loss 2.8134):  24%|██▍       | 298/1250 [01:51<05:46,  2.75it/s]
Training 1/1 epoch (loss 2.6956):  24%|██▍       | 298/1250 [01:52<05:46,  2.75it/s]
Training 1/1 epoch (loss 2.6956):  24%|██▍       | 299/1250 [01:52<05:31,  2.87it/s]
Training 1/1 epoch (loss 2.8514):  24%|██▍       | 299/1250 [01:52<05:31,  2.87it/s]
Training 1/1 epoch (loss 2.8514):  24%|██▍       | 300/1250 [01:52<05:23,  2.94it/s]
Training 1/1 epoch (loss 2.7176):  24%|██▍       | 300/1250 [01:52<05:23,  2.94it/s]
Training 1/1 epoch (loss 2.7176):  24%|██▍       | 301/1250 [01:52<05:16,  3.00it/s]
Training 1/1 epoch (loss 2.6137):  24%|██▍       | 301/1250 [01:53<05:16,  3.00it/s]
Training 1/1 epoch (loss 2.6137):  24%|██▍       | 302/1250 [01:53<05:39,  2.79it/s]
Training 1/1 epoch (loss 2.4917):  24%|██▍       | 302/1250 [01:53<05:39,  2.79it/s]
Training 1/1 epoch (loss 2.4917):  24%|██▍       | 303/1250 [01:53<06:32,  2.41it/s]
Training 1/1 epoch (loss 2.9178):  24%|██▍       | 303/1250 [01:54<06:32,  2.41it/s]
Training 1/1 epoch (loss 2.9178):  24%|██▍       | 304/1250 [01:54<06:23,  2.47it/s]
Training 1/1 epoch (loss 3.0055):  24%|██▍       | 304/1250 [01:54<06:23,  2.47it/s]
Training 1/1 epoch (loss 3.0055):  24%|██▍       | 305/1250 [01:54<06:11,  2.54it/s]
Training 1/1 epoch (loss 2.9180):  24%|██▍       | 305/1250 [01:54<06:11,  2.54it/s]
Training 1/1 epoch (loss 2.9180):  24%|██▍       | 306/1250 [01:54<05:56,  2.65it/s]
Training 1/1 epoch (loss 2.8254):  24%|██▍       | 306/1250 [01:55<05:56,  2.65it/s]
Training 1/1 epoch (loss 2.8254):  25%|██▍       | 307/1250 [01:55<05:46,  2.72it/s]
Training 1/1 epoch (loss 2.7462):  25%|██▍       | 307/1250 [01:55<05:46,  2.72it/s]
Training 1/1 epoch (loss 2.7462):  25%|██▍       | 308/1250 [01:55<05:27,  2.88it/s]
Training 1/1 epoch (loss 2.6662):  25%|██▍       | 308/1250 [01:55<05:27,  2.88it/s]
Training 1/1 epoch (loss 2.6662):  25%|██▍       | 309/1250 [01:55<05:15,  2.98it/s]
Training 1/1 epoch (loss 2.6979):  25%|██▍       | 309/1250 [01:55<05:15,  2.98it/s]
Training 1/1 epoch (loss 2.6979):  25%|██▍       | 310/1250 [01:55<05:12,  3.01it/s]
Training 1/1 epoch (loss 2.8578):  25%|██▍       | 310/1250 [01:56<05:12,  3.01it/s]
Training 1/1 epoch (loss 2.8578):  25%|██▍       | 311/1250 [01:56<05:15,  2.98it/s]
Training 1/1 epoch (loss 2.7132):  25%|██▍       | 311/1250 [01:56<05:15,  2.98it/s]
Training 1/1 epoch (loss 2.7132):  25%|██▍       | 312/1250 [01:56<05:26,  2.88it/s]
Training 1/1 epoch (loss 2.5502):  25%|██▍       | 312/1250 [01:57<05:26,  2.88it/s]
Training 1/1 epoch (loss 2.5502):  25%|██▌       | 313/1250 [01:57<05:39,  2.76it/s]
Training 1/1 epoch (loss 2.6810):  25%|██▌       | 313/1250 [01:57<05:39,  2.76it/s]
Training 1/1 epoch (loss 2.6810):  25%|██▌       | 314/1250 [01:57<05:31,  2.82it/s]
Training 1/1 epoch (loss 2.8947):  25%|██▌       | 314/1250 [01:57<05:31,  2.82it/s]
Training 1/1 epoch (loss 2.8947):  25%|██▌       | 315/1250 [01:57<05:23,  2.89it/s]
Training 1/1 epoch (loss 2.7441):  25%|██▌       | 315/1250 [01:58<05:23,  2.89it/s]
Training 1/1 epoch (loss 2.7441):  25%|██▌       | 316/1250 [01:58<05:49,  2.67it/s]
Training 1/1 epoch (loss 2.8273):  25%|██▌       | 316/1250 [01:58<05:49,  2.67it/s]
Training 1/1 epoch (loss 2.8273):  25%|██▌       | 317/1250 [01:58<06:10,  2.52it/s]
Training 1/1 epoch (loss 2.9711):  25%|██▌       | 317/1250 [01:59<06:10,  2.52it/s]
Training 1/1 epoch (loss 2.9711):  25%|██▌       | 318/1250 [01:59<05:57,  2.60it/s]
Training 1/1 epoch (loss 2.7190):  25%|██▌       | 318/1250 [01:59<05:57,  2.60it/s]
Training 1/1 epoch (loss 2.7190):  26%|██▌       | 319/1250 [01:59<05:32,  2.80it/s]
Training 1/1 epoch (loss 2.8411):  26%|██▌       | 319/1250 [01:59<05:32,  2.80it/s]
Training 1/1 epoch (loss 2.8411):  26%|██▌       | 320/1250 [01:59<05:31,  2.80it/s]
Training 1/1 epoch (loss 2.7386):  26%|██▌       | 320/1250 [02:00<05:31,  2.80it/s]
Training 1/1 epoch (loss 2.7386):  26%|██▌       | 321/1250 [02:00<05:38,  2.74it/s]
Training 1/1 epoch (loss 2.8214):  26%|██▌       | 321/1250 [02:00<05:38,  2.74it/s]
Training 1/1 epoch (loss 2.8214):  26%|██▌       | 322/1250 [02:00<05:39,  2.73it/s]
Training 1/1 epoch (loss 2.6663):  26%|██▌       | 322/1250 [02:00<05:39,  2.73it/s]
Training 1/1 epoch (loss 2.6663):  26%|██▌       | 323/1250 [02:00<05:31,  2.80it/s]
Training 1/1 epoch (loss 2.9963):  26%|██▌       | 323/1250 [02:01<05:31,  2.80it/s]
Training 1/1 epoch (loss 2.9963):  26%|██▌       | 324/1250 [02:01<05:16,  2.92it/s]
Training 1/1 epoch (loss 2.5491):  26%|██▌       | 324/1250 [02:01<05:16,  2.92it/s]
Training 1/1 epoch (loss 2.5491):  26%|██▌       | 325/1250 [02:01<05:09,  2.99it/s]
Training 1/1 epoch (loss 2.8459):  26%|██▌       | 325/1250 [02:01<05:09,  2.99it/s]
Training 1/1 epoch (loss 2.8459):  26%|██▌       | 326/1250 [02:01<05:08,  2.99it/s]
Training 1/1 epoch (loss 2.6885):  26%|██▌       | 326/1250 [02:02<05:08,  2.99it/s]
Training 1/1 epoch (loss 2.6885):  26%|██▌       | 327/1250 [02:02<05:13,  2.94it/s]
Training 1/1 epoch (loss 2.4939):  26%|██▌       | 327/1250 [02:02<05:13,  2.94it/s]
Training 1/1 epoch (loss 2.4939):  26%|██▌       | 328/1250 [02:02<05:06,  3.01it/s]
Training 1/1 epoch (loss 3.0906):  26%|██▌       | 328/1250 [02:02<05:06,  3.01it/s]
Training 1/1 epoch (loss 3.0906):  26%|██▋       | 329/1250 [02:02<05:08,  2.98it/s]
Training 1/1 epoch (loss 2.6919):  26%|██▋       | 329/1250 [02:03<05:08,  2.98it/s]
Training 1/1 epoch (loss 2.6919):  26%|██▋       | 330/1250 [02:03<05:10,  2.96it/s]
Training 1/1 epoch (loss 2.7513):  26%|██▋       | 330/1250 [02:03<05:10,  2.96it/s]
Training 1/1 epoch (loss 2.7513):  26%|██▋       | 331/1250 [02:03<05:08,  2.98it/s]
Training 1/1 epoch (loss 2.9258):  26%|██▋       | 331/1250 [02:03<05:08,  2.98it/s]
Training 1/1 epoch (loss 2.9258):  27%|██▋       | 332/1250 [02:03<05:06,  3.00it/s]
Training 1/1 epoch (loss 2.6962):  27%|██▋       | 332/1250 [02:04<05:06,  3.00it/s]
Training 1/1 epoch (loss 2.6962):  27%|██▋       | 333/1250 [02:04<05:04,  3.01it/s]
Training 1/1 epoch (loss 2.8803):  27%|██▋       | 333/1250 [02:04<05:04,  3.01it/s]
Training 1/1 epoch (loss 2.8803):  27%|██▋       | 334/1250 [02:04<05:04,  3.01it/s]
Training 1/1 epoch (loss 2.7907):  27%|██▋       | 334/1250 [02:04<05:04,  3.01it/s]
Training 1/1 epoch (loss 2.7907):  27%|██▋       | 335/1250 [02:04<05:00,  3.04it/s]
Training 1/1 epoch (loss 2.8659):  27%|██▋       | 335/1250 [02:05<05:00,  3.04it/s]
Training 1/1 epoch (loss 2.8659):  27%|██▋       | 336/1250 [02:05<05:14,  2.91it/s]
Training 1/1 epoch (loss 3.0631):  27%|██▋       | 336/1250 [02:05<05:14,  2.91it/s]
Training 1/1 epoch (loss 3.0631):  27%|██▋       | 337/1250 [02:05<05:12,  2.92it/s]
Training 1/1 epoch (loss 2.8838):  27%|██▋       | 337/1250 [02:05<05:12,  2.92it/s]
Training 1/1 epoch (loss 2.8838):  27%|██▋       | 338/1250 [02:05<05:23,  2.82it/s]
Training 1/1 epoch (loss 2.8658):  27%|██▋       | 338/1250 [02:06<05:23,  2.82it/s]
Training 1/1 epoch (loss 2.8658):  27%|██▋       | 339/1250 [02:06<05:25,  2.80it/s]
Training 1/1 epoch (loss 2.8144):  27%|██▋       | 339/1250 [02:06<05:25,  2.80it/s]
Training 1/1 epoch (loss 2.8144):  27%|██▋       | 340/1250 [02:06<05:21,  2.83it/s]
Training 1/1 epoch (loss 2.6536):  27%|██▋       | 340/1250 [02:06<05:21,  2.83it/s]
Training 1/1 epoch (loss 2.6536):  27%|██▋       | 341/1250 [02:06<05:15,  2.88it/s]
Training 1/1 epoch (loss 2.7537):  27%|██▋       | 341/1250 [02:07<05:15,  2.88it/s]
Training 1/1 epoch (loss 2.7537):  27%|██▋       | 342/1250 [02:07<05:16,  2.87it/s]
Training 1/1 epoch (loss 2.6642):  27%|██▋       | 342/1250 [02:07<05:16,  2.87it/s]
Training 1/1 epoch (loss 2.6642):  27%|██▋       | 343/1250 [02:07<05:03,  2.99it/s]
Training 1/1 epoch (loss 2.8087):  27%|██▋       | 343/1250 [02:07<05:03,  2.99it/s]
Training 1/1 epoch (loss 2.8087):  28%|██▊       | 344/1250 [02:07<05:07,  2.94it/s]
Training 1/1 epoch (loss 2.7556):  28%|██▊       | 344/1250 [02:08<05:07,  2.94it/s]
Training 1/1 epoch (loss 2.7556):  28%|██▊       | 345/1250 [02:08<05:10,  2.92it/s]
Training 1/1 epoch (loss 2.7583):  28%|██▊       | 345/1250 [02:08<05:10,  2.92it/s]
Training 1/1 epoch (loss 2.7583):  28%|██▊       | 346/1250 [02:08<05:06,  2.95it/s]
Training 1/1 epoch (loss 2.8910):  28%|██▊       | 346/1250 [02:08<05:06,  2.95it/s]
Training 1/1 epoch (loss 2.8910):  28%|██▊       | 347/1250 [02:08<05:03,  2.97it/s]
Training 1/1 epoch (loss 2.9117):  28%|██▊       | 347/1250 [02:09<05:03,  2.97it/s]
Training 1/1 epoch (loss 2.9117):  28%|██▊       | 348/1250 [02:09<05:04,  2.96it/s]
Training 1/1 epoch (loss 2.7459):  28%|██▊       | 348/1250 [02:09<05:04,  2.96it/s]
Training 1/1 epoch (loss 2.7459):  28%|██▊       | 349/1250 [02:09<04:57,  3.03it/s]
Training 1/1 epoch (loss 2.8986):  28%|██▊       | 349/1250 [02:09<04:57,  3.03it/s]
Training 1/1 epoch (loss 2.8986):  28%|██▊       | 350/1250 [02:09<04:50,  3.10it/s]
Training 1/1 epoch (loss 2.7822):  28%|██▊       | 350/1250 [02:10<04:50,  3.10it/s]
Training 1/1 epoch (loss 2.7822):  28%|██▊       | 351/1250 [02:10<04:46,  3.13it/s]
Training 1/1 epoch (loss 2.9602):  28%|██▊       | 351/1250 [02:10<04:46,  3.13it/s]
Training 1/1 epoch (loss 2.9602):  28%|██▊       | 352/1250 [02:10<05:07,  2.92it/s]
Training 1/1 epoch (loss 2.9708):  28%|██▊       | 352/1250 [02:10<05:07,  2.92it/s]
Training 1/1 epoch (loss 2.9708):  28%|██▊       | 353/1250 [02:10<05:13,  2.86it/s]
Training 1/1 epoch (loss 2.7881):  28%|██▊       | 353/1250 [02:11<05:13,  2.86it/s]
Training 1/1 epoch (loss 2.7881):  28%|██▊       | 354/1250 [02:11<05:11,  2.88it/s]
Training 1/1 epoch (loss 2.6643):  28%|██▊       | 354/1250 [02:11<05:11,  2.88it/s]
Training 1/1 epoch (loss 2.6643):  28%|██▊       | 355/1250 [02:11<05:05,  2.93it/s]
Training 1/1 epoch (loss 2.7512):  28%|██▊       | 355/1250 [02:11<05:05,  2.93it/s]
Training 1/1 epoch (loss 2.7512):  28%|██▊       | 356/1250 [02:11<05:02,  2.95it/s]
Training 1/1 epoch (loss 2.9928):  28%|██▊       | 356/1250 [02:12<05:02,  2.95it/s]
Training 1/1 epoch (loss 2.9928):  29%|██▊       | 357/1250 [02:12<05:14,  2.84it/s]
Training 1/1 epoch (loss 2.9059):  29%|██▊       | 357/1250 [02:12<05:14,  2.84it/s]
Training 1/1 epoch (loss 2.9059):  29%|██▊       | 358/1250 [02:12<05:16,  2.81it/s]
Training 1/1 epoch (loss 2.7712):  29%|██▊       | 358/1250 [02:12<05:16,  2.81it/s]
Training 1/1 epoch (loss 2.7712):  29%|██▊       | 359/1250 [02:12<05:05,  2.92it/s]
Training 1/1 epoch (loss 2.6026):  29%|██▊       | 359/1250 [02:13<05:05,  2.92it/s]
Training 1/1 epoch (loss 2.6026):  29%|██▉       | 360/1250 [02:13<05:10,  2.87it/s]
Training 1/1 epoch (loss 2.6747):  29%|██▉       | 360/1250 [02:13<05:10,  2.87it/s]
Training 1/1 epoch (loss 2.6747):  29%|██▉       | 361/1250 [02:13<05:08,  2.88it/s]
Training 1/1 epoch (loss 2.7518):  29%|██▉       | 361/1250 [02:14<05:08,  2.88it/s]
Training 1/1 epoch (loss 2.7518):  29%|██▉       | 362/1250 [02:14<05:09,  2.87it/s]
Training 1/1 epoch (loss 2.8559):  29%|██▉       | 362/1250 [02:14<05:09,  2.87it/s]
Training 1/1 epoch (loss 2.8559):  29%|██▉       | 363/1250 [02:14<04:57,  2.98it/s]
Training 1/1 epoch (loss 2.9245):  29%|██▉       | 363/1250 [02:14<04:57,  2.98it/s]
Training 1/1 epoch (loss 2.9245):  29%|██▉       | 364/1250 [02:14<04:57,  2.98it/s]
Training 1/1 epoch (loss 2.6623):  29%|██▉       | 364/1250 [02:15<04:57,  2.98it/s]
Training 1/1 epoch (loss 2.6623):  29%|██▉       | 365/1250 [02:15<05:18,  2.78it/s]
Training 1/1 epoch (loss 2.5515):  29%|██▉       | 365/1250 [02:15<05:18,  2.78it/s]
Training 1/1 epoch (loss 2.5515):  29%|██▉       | 366/1250 [02:15<05:12,  2.83it/s]
Training 1/1 epoch (loss 2.6564):  29%|██▉       | 366/1250 [02:15<05:12,  2.83it/s]
Training 1/1 epoch (loss 2.6564):  29%|██▉       | 367/1250 [02:15<05:03,  2.91it/s]
Training 1/1 epoch (loss 2.7153):  29%|██▉       | 367/1250 [02:16<05:03,  2.91it/s]
Training 1/1 epoch (loss 2.7153):  29%|██▉       | 368/1250 [02:16<05:03,  2.91it/s]
Training 1/1 epoch (loss 2.8273):  29%|██▉       | 368/1250 [02:16<05:03,  2.91it/s]
Training 1/1 epoch (loss 2.8273):  30%|██▉       | 369/1250 [02:16<05:03,  2.91it/s]
Training 1/1 epoch (loss 2.8851):  30%|██▉       | 369/1250 [02:16<05:03,  2.91it/s]
Training 1/1 epoch (loss 2.8851):  30%|██▉       | 370/1250 [02:16<05:02,  2.91it/s]
Training 1/1 epoch (loss 2.6380):  30%|██▉       | 370/1250 [02:17<05:02,  2.91it/s]
Training 1/1 epoch (loss 2.6380):  30%|██▉       | 371/1250 [02:17<04:59,  2.94it/s]
Training 1/1 epoch (loss 2.7528):  30%|██▉       | 371/1250 [02:17<04:59,  2.94it/s]
Training 1/1 epoch (loss 2.7528):  30%|██▉       | 372/1250 [02:17<04:56,  2.96it/s]
Training 1/1 epoch (loss 2.6994):  30%|██▉       | 372/1250 [02:17<04:56,  2.96it/s]
Training 1/1 epoch (loss 2.6994):  30%|██▉       | 373/1250 [02:17<04:48,  3.04it/s]
Training 1/1 epoch (loss 2.5205):  30%|██▉       | 373/1250 [02:18<04:48,  3.04it/s]
Training 1/1 epoch (loss 2.5205):  30%|██▉       | 374/1250 [02:18<04:40,  3.12it/s]
Training 1/1 epoch (loss 2.7465):  30%|██▉       | 374/1250 [02:18<04:40,  3.12it/s]
Training 1/1 epoch (loss 2.7465):  30%|███       | 375/1250 [02:18<04:40,  3.12it/s]
Training 1/1 epoch (loss 2.9521):  30%|███       | 375/1250 [02:18<04:40,  3.12it/s]
Training 1/1 epoch (loss 2.9521):  30%|███       | 376/1250 [02:18<04:54,  2.97it/s]
Training 1/1 epoch (loss 2.9065):  30%|███       | 376/1250 [02:19<04:54,  2.97it/s]
Training 1/1 epoch (loss 2.9065):  30%|███       | 377/1250 [02:19<05:09,  2.82it/s]
Training 1/1 epoch (loss 2.7587):  30%|███       | 377/1250 [02:19<05:09,  2.82it/s]
Training 1/1 epoch (loss 2.7587):  30%|███       | 378/1250 [02:19<05:01,  2.89it/s]
Training 1/1 epoch (loss 2.6394):  30%|███       | 378/1250 [02:19<05:01,  2.89it/s]
Training 1/1 epoch (loss 2.6394):  30%|███       | 379/1250 [02:19<04:50,  3.00it/s]
Training 1/1 epoch (loss 2.8081):  30%|███       | 379/1250 [02:20<04:50,  3.00it/s]
Training 1/1 epoch (loss 2.8081):  30%|███       | 380/1250 [02:20<04:44,  3.06it/s]
Training 1/1 epoch (loss 2.8622):  30%|███       | 380/1250 [02:20<04:44,  3.06it/s]
Training 1/1 epoch (loss 2.8622):  30%|███       | 381/1250 [02:20<04:43,  3.06it/s]
Training 1/1 epoch (loss 2.9108):  30%|███       | 381/1250 [02:20<04:43,  3.06it/s]
Training 1/1 epoch (loss 2.9108):  31%|███       | 382/1250 [02:20<04:50,  2.99it/s]
Training 1/1 epoch (loss 2.7704):  31%|███       | 382/1250 [02:21<04:50,  2.99it/s]
Training 1/1 epoch (loss 2.7704):  31%|███       | 383/1250 [02:21<04:47,  3.02it/s]
Training 1/1 epoch (loss 2.6240):  31%|███       | 383/1250 [02:21<04:47,  3.02it/s]
Training 1/1 epoch (loss 2.6240):  31%|███       | 384/1250 [02:21<05:05,  2.83it/s]
Training 1/1 epoch (loss 2.7724):  31%|███       | 384/1250 [02:21<05:05,  2.83it/s]
Training 1/1 epoch (loss 2.7724):  31%|███       | 385/1250 [02:21<05:03,  2.85it/s]
Training 1/1 epoch (loss 2.5598):  31%|███       | 385/1250 [02:22<05:03,  2.85it/s]
Training 1/1 epoch (loss 2.5598):  31%|███       | 386/1250 [02:22<04:47,  3.01it/s]
Training 1/1 epoch (loss 2.6407):  31%|███       | 386/1250 [02:22<04:47,  3.01it/s]
Training 1/1 epoch (loss 2.6407):  31%|███       | 387/1250 [02:22<05:09,  2.79it/s]
Training 1/1 epoch (loss 2.7247):  31%|███       | 387/1250 [02:22<05:09,  2.79it/s]
Training 1/1 epoch (loss 2.7247):  31%|███       | 388/1250 [02:22<05:02,  2.85it/s]
Training 1/1 epoch (loss 2.7953):  31%|███       | 388/1250 [02:23<05:02,  2.85it/s]
Training 1/1 epoch (loss 2.7953):  31%|███       | 389/1250 [02:23<06:21,  2.26it/s]
Training 1/1 epoch (loss 2.7305):  31%|███       | 389/1250 [02:23<06:21,  2.26it/s]
Training 1/1 epoch (loss 2.7305):  31%|███       | 390/1250 [02:23<05:47,  2.48it/s]
Training 1/1 epoch (loss 2.9599):  31%|███       | 390/1250 [02:24<05:47,  2.48it/s]
Training 1/1 epoch (loss 2.9599):  31%|███▏      | 391/1250 [02:24<05:37,  2.55it/s]
Training 1/1 epoch (loss 2.7857):  31%|███▏      | 391/1250 [02:24<05:37,  2.55it/s]
Training 1/1 epoch (loss 2.7857):  31%|███▏      | 392/1250 [02:24<05:29,  2.61it/s]
Training 1/1 epoch (loss 2.8636):  31%|███▏      | 392/1250 [02:24<05:29,  2.61it/s]
Training 1/1 epoch (loss 2.8636):  31%|███▏      | 393/1250 [02:24<05:32,  2.58it/s]
Training 1/1 epoch (loss 2.6808):  31%|███▏      | 393/1250 [02:25<05:32,  2.58it/s]
Training 1/1 epoch (loss 2.6808):  32%|███▏      | 394/1250 [02:25<05:25,  2.63it/s]
Training 1/1 epoch (loss 2.4952):  32%|███▏      | 394/1250 [02:25<05:25,  2.63it/s]
Training 1/1 epoch (loss 2.4952):  32%|███▏      | 395/1250 [02:25<05:27,  2.61it/s]
Training 1/1 epoch (loss 2.7016):  32%|███▏      | 395/1250 [02:26<05:27,  2.61it/s]
Training 1/1 epoch (loss 2.7016):  32%|███▏      | 396/1250 [02:26<05:12,  2.74it/s]
Training 1/1 epoch (loss 2.5014):  32%|███▏      | 396/1250 [02:26<05:12,  2.74it/s]
Training 1/1 epoch (loss 2.5014):  32%|███▏      | 397/1250 [02:26<05:01,  2.83it/s]
Training 1/1 epoch (loss 2.6134):  32%|███▏      | 397/1250 [02:26<05:01,  2.83it/s]
Training 1/1 epoch (loss 2.6134):  32%|███▏      | 398/1250 [02:26<05:19,  2.67it/s]
Training 1/1 epoch (loss 2.8076):  32%|███▏      | 398/1250 [02:27<05:19,  2.67it/s]
Training 1/1 epoch (loss 2.8076):  32%|███▏      | 399/1250 [02:27<05:11,  2.73it/s]
Training 1/1 epoch (loss 2.8822):  32%|███▏      | 399/1250 [02:27<05:11,  2.73it/s]
Training 1/1 epoch (loss 2.8822):  32%|███▏      | 400/1250 [02:27<05:13,  2.71it/s]
Training 1/1 epoch (loss 2.6062):  32%|███▏      | 400/1250 [02:27<05:13,  2.71it/s]
Training 1/1 epoch (loss 2.6062):  32%|███▏      | 401/1250 [02:27<05:22,  2.63it/s]
Training 1/1 epoch (loss 2.9317):  32%|███▏      | 401/1250 [02:28<05:22,  2.63it/s]
Training 1/1 epoch (loss 2.9317):  32%|███▏      | 402/1250 [02:28<05:21,  2.64it/s]
Training 1/1 epoch (loss 2.8921):  32%|███▏      | 402/1250 [02:28<05:21,  2.64it/s]
Training 1/1 epoch (loss 2.8921):  32%|███▏      | 403/1250 [02:28<05:47,  2.43it/s]
Training 1/1 epoch (loss 2.6160):  32%|███▏      | 403/1250 [02:29<05:47,  2.43it/s]
Training 1/1 epoch (loss 2.6160):  32%|███▏      | 404/1250 [02:29<05:39,  2.49it/s]
Training 1/1 epoch (loss 2.7883):  32%|███▏      | 404/1250 [02:29<05:39,  2.49it/s]
Training 1/1 epoch (loss 2.7883):  32%|███▏      | 405/1250 [02:29<05:09,  2.73it/s]
Training 1/1 epoch (loss 2.7512):  32%|███▏      | 405/1250 [02:29<05:09,  2.73it/s]
Training 1/1 epoch (loss 2.7512):  32%|███▏      | 406/1250 [02:29<04:55,  2.85it/s]
Training 1/1 epoch (loss 2.6987):  32%|███▏      | 406/1250 [02:30<04:55,  2.85it/s]
Training 1/1 epoch (loss 2.6987):  33%|███▎      | 407/1250 [02:30<04:50,  2.90it/s]
Training 1/1 epoch (loss 2.7689):  33%|███▎      | 407/1250 [02:30<04:50,  2.90it/s]
Training 1/1 epoch (loss 2.7689):  33%|███▎      | 408/1250 [02:30<04:47,  2.93it/s]
Training 1/1 epoch (loss 2.9144):  33%|███▎      | 408/1250 [02:30<04:47,  2.93it/s]
Training 1/1 epoch (loss 2.9144):  33%|███▎      | 409/1250 [02:30<04:50,  2.89it/s]
Training 1/1 epoch (loss 2.9180):  33%|███▎      | 409/1250 [02:31<04:50,  2.89it/s]
Training 1/1 epoch (loss 2.9180):  33%|███▎      | 410/1250 [02:31<04:59,  2.81it/s]
Training 1/1 epoch (loss 2.6599):  33%|███▎      | 410/1250 [02:31<04:59,  2.81it/s]
Training 1/1 epoch (loss 2.6599):  33%|███▎      | 411/1250 [02:31<04:45,  2.94it/s]
Training 1/1 epoch (loss 2.5595):  33%|███▎      | 411/1250 [02:31<04:45,  2.94it/s]
Training 1/1 epoch (loss 2.5595):  33%|███▎      | 412/1250 [02:31<04:35,  3.04it/s]
Training 1/1 epoch (loss 2.6950):  33%|███▎      | 412/1250 [02:32<04:35,  3.04it/s]
Training 1/1 epoch (loss 2.6950):  33%|███▎      | 413/1250 [02:32<04:36,  3.03it/s]
Training 1/1 epoch (loss 2.8636):  33%|███▎      | 413/1250 [02:32<04:36,  3.03it/s]
Training 1/1 epoch (loss 2.8636):  33%|███▎      | 414/1250 [02:32<04:32,  3.06it/s]
Training 1/1 epoch (loss 2.7607):  33%|███▎      | 414/1250 [02:32<04:32,  3.06it/s]
Training 1/1 epoch (loss 2.7607):  33%|███▎      | 415/1250 [02:32<04:29,  3.09it/s]
Training 1/1 epoch (loss 2.8561):  33%|███▎      | 415/1250 [02:33<04:29,  3.09it/s]
Training 1/1 epoch (loss 2.8561):  33%|███▎      | 416/1250 [02:33<04:43,  2.94it/s]
Training 1/1 epoch (loss 2.8872):  33%|███▎      | 416/1250 [02:33<04:43,  2.94it/s]
Training 1/1 epoch (loss 2.8872):  33%|███▎      | 417/1250 [02:33<04:45,  2.92it/s]
Training 1/1 epoch (loss 2.7830):  33%|███▎      | 417/1250 [02:33<04:45,  2.92it/s]
Training 1/1 epoch (loss 2.7830):  33%|███▎      | 418/1250 [02:33<04:47,  2.89it/s]
Training 1/1 epoch (loss 2.8993):  33%|███▎      | 418/1250 [02:34<04:47,  2.89it/s]
Training 1/1 epoch (loss 2.8993):  34%|███▎      | 419/1250 [02:34<04:59,  2.78it/s]
Training 1/1 epoch (loss 2.7858):  34%|███▎      | 419/1250 [02:34<04:59,  2.78it/s]
Training 1/1 epoch (loss 2.7858):  34%|███▎      | 420/1250 [02:34<04:56,  2.80it/s]
Training 1/1 epoch (loss 2.7142):  34%|███▎      | 420/1250 [02:34<04:56,  2.80it/s]
Training 1/1 epoch (loss 2.7142):  34%|███▎      | 421/1250 [02:34<04:57,  2.79it/s]
Training 1/1 epoch (loss 2.7387):  34%|███▎      | 421/1250 [02:35<04:57,  2.79it/s]
Training 1/1 epoch (loss 2.7387):  34%|███▍      | 422/1250 [02:35<05:13,  2.64it/s]
Training 1/1 epoch (loss 2.8256):  34%|███▍      | 422/1250 [02:35<05:13,  2.64it/s]
Training 1/1 epoch (loss 2.8256):  34%|███▍      | 423/1250 [02:35<05:04,  2.71it/s]
Training 1/1 epoch (loss 2.7409):  34%|███▍      | 423/1250 [02:36<05:04,  2.71it/s]
Training 1/1 epoch (loss 2.7409):  34%|███▍      | 424/1250 [02:36<05:04,  2.71it/s]
Training 1/1 epoch (loss 2.8812):  34%|███▍      | 424/1250 [02:36<05:04,  2.71it/s]
Training 1/1 epoch (loss 2.8812):  34%|███▍      | 425/1250 [02:36<05:06,  2.69it/s]
Training 1/1 epoch (loss 3.0137):  34%|███▍      | 425/1250 [02:36<05:06,  2.69it/s]
Training 1/1 epoch (loss 3.0137):  34%|███▍      | 426/1250 [02:36<04:59,  2.75it/s]
Training 1/1 epoch (loss 2.7769):  34%|███▍      | 426/1250 [02:37<04:59,  2.75it/s]
Training 1/1 epoch (loss 2.7769):  34%|███▍      | 427/1250 [02:37<04:50,  2.83it/s]
Training 1/1 epoch (loss 2.6991):  34%|███▍      | 427/1250 [02:37<04:50,  2.83it/s]
Training 1/1 epoch (loss 2.6991):  34%|███▍      | 428/1250 [02:37<04:59,  2.74it/s]
Training 1/1 epoch (loss 2.7067):  34%|███▍      | 428/1250 [02:37<04:59,  2.74it/s]
Training 1/1 epoch (loss 2.7067):  34%|███▍      | 429/1250 [02:37<04:45,  2.88it/s]
Training 1/1 epoch (loss 2.5678):  34%|███▍      | 429/1250 [02:38<04:45,  2.88it/s]
Training 1/1 epoch (loss 2.5678):  34%|███▍      | 430/1250 [02:38<04:35,  2.98it/s]
Training 1/1 epoch (loss 2.7060):  34%|███▍      | 430/1250 [02:38<04:35,  2.98it/s]
Training 1/1 epoch (loss 2.7060):  34%|███▍      | 431/1250 [02:38<04:31,  3.02it/s]
Training 1/1 epoch (loss 2.8099):  34%|███▍      | 431/1250 [02:38<04:31,  3.02it/s]
Training 1/1 epoch (loss 2.8099):  35%|███▍      | 432/1250 [02:38<04:28,  3.05it/s]
Training 1/1 epoch (loss 2.6792):  35%|███▍      | 432/1250 [02:39<04:28,  3.05it/s]
Training 1/1 epoch (loss 2.6792):  35%|███▍      | 433/1250 [02:39<04:38,  2.93it/s]
Training 1/1 epoch (loss 2.8604):  35%|███▍      | 433/1250 [02:39<04:38,  2.93it/s]
Training 1/1 epoch (loss 2.8604):  35%|███▍      | 434/1250 [02:39<04:31,  3.00it/s]
Training 1/1 epoch (loss 2.8567):  35%|███▍      | 434/1250 [02:39<04:31,  3.00it/s]
Training 1/1 epoch (loss 2.8567):  35%|███▍      | 435/1250 [02:39<04:27,  3.04it/s]
Training 1/1 epoch (loss 2.8899):  35%|███▍      | 435/1250 [02:40<04:27,  3.04it/s]
Training 1/1 epoch (loss 2.8899):  35%|███▍      | 436/1250 [02:40<04:18,  3.14it/s]
Training 1/1 epoch (loss 2.7012):  35%|███▍      | 436/1250 [02:40<04:18,  3.14it/s]
Training 1/1 epoch (loss 2.7012):  35%|███▍      | 437/1250 [02:40<04:17,  3.16it/s]
Training 1/1 epoch (loss 2.6956):  35%|███▍      | 437/1250 [02:40<04:17,  3.16it/s]
Training 1/1 epoch (loss 2.6956):  35%|███▌      | 438/1250 [02:40<04:19,  3.13it/s]
Training 1/1 epoch (loss 2.8203):  35%|███▌      | 438/1250 [02:41<04:19,  3.13it/s]
Training 1/1 epoch (loss 2.8203):  35%|███▌      | 439/1250 [02:41<04:23,  3.07it/s]
Training 1/1 epoch (loss 3.1007):  35%|███▌      | 439/1250 [02:41<04:23,  3.07it/s]
Training 1/1 epoch (loss 3.1007):  35%|███▌      | 440/1250 [02:41<04:37,  2.92it/s]
Training 1/1 epoch (loss 2.6527):  35%|███▌      | 440/1250 [02:41<04:37,  2.92it/s]
Training 1/1 epoch (loss 2.6527):  35%|███▌      | 441/1250 [02:41<04:37,  2.92it/s]
Training 1/1 epoch (loss 2.7218):  35%|███▌      | 441/1250 [02:42<04:37,  2.92it/s]
Training 1/1 epoch (loss 2.7218):  35%|███▌      | 442/1250 [02:42<04:24,  3.06it/s]
Training 1/1 epoch (loss 2.7354):  35%|███▌      | 442/1250 [02:42<04:24,  3.06it/s]
Training 1/1 epoch (loss 2.7354):  35%|███▌      | 443/1250 [02:42<04:19,  3.11it/s]
Training 1/1 epoch (loss 2.9662):  35%|███▌      | 443/1250 [02:42<04:19,  3.11it/s]
Training 1/1 epoch (loss 2.9662):  36%|███▌      | 444/1250 [02:42<04:38,  2.90it/s]
Training 1/1 epoch (loss 2.6802):  36%|███▌      | 444/1250 [02:43<04:38,  2.90it/s]
Training 1/1 epoch (loss 2.6802):  36%|███▌      | 445/1250 [02:43<04:32,  2.95it/s]
Training 1/1 epoch (loss 2.6602):  36%|███▌      | 445/1250 [02:43<04:32,  2.95it/s]
Training 1/1 epoch (loss 2.6602):  36%|███▌      | 446/1250 [02:43<04:34,  2.93it/s]
Training 1/1 epoch (loss 2.7585):  36%|███▌      | 446/1250 [02:43<04:34,  2.93it/s]
Training 1/1 epoch (loss 2.7585):  36%|███▌      | 447/1250 [02:43<04:28,  2.99it/s]
Training 1/1 epoch (loss 2.5878):  36%|███▌      | 447/1250 [02:44<04:28,  2.99it/s]
Training 1/1 epoch (loss 2.5878):  36%|███▌      | 448/1250 [02:44<04:36,  2.91it/s]
Training 1/1 epoch (loss 2.8178):  36%|███▌      | 448/1250 [02:44<04:36,  2.91it/s]
Training 1/1 epoch (loss 2.8178):  36%|███▌      | 449/1250 [02:44<04:31,  2.95it/s]
Training 1/1 epoch (loss 2.7410):  36%|███▌      | 449/1250 [02:44<04:31,  2.95it/s]
Training 1/1 epoch (loss 2.7410):  36%|███▌      | 450/1250 [02:44<04:29,  2.97it/s]
Training 1/1 epoch (loss 2.6744):  36%|███▌      | 450/1250 [02:45<04:29,  2.97it/s]
Training 1/1 epoch (loss 2.6744):  36%|███▌      | 451/1250 [02:45<04:42,  2.83it/s]
Training 1/1 epoch (loss 2.6418):  36%|███▌      | 451/1250 [02:45<04:42,  2.83it/s]
Training 1/1 epoch (loss 2.6418):  36%|███▌      | 452/1250 [02:45<04:32,  2.93it/s]
Training 1/1 epoch (loss 2.8310):  36%|███▌      | 452/1250 [02:45<04:32,  2.93it/s]
Training 1/1 epoch (loss 2.8310):  36%|███▌      | 453/1250 [02:45<04:30,  2.95it/s]
Training 1/1 epoch (loss 2.7421):  36%|███▌      | 453/1250 [02:46<04:30,  2.95it/s]
Training 1/1 epoch (loss 2.7421):  36%|███▋      | 454/1250 [02:46<04:25,  3.00it/s]
Training 1/1 epoch (loss 2.7024):  36%|███▋      | 454/1250 [02:46<04:25,  3.00it/s]
Training 1/1 epoch (loss 2.7024):  36%|███▋      | 455/1250 [02:46<04:31,  2.93it/s]
Training 1/1 epoch (loss 2.8726):  36%|███▋      | 455/1250 [02:46<04:31,  2.93it/s]
Training 1/1 epoch (loss 2.8726):  36%|███▋      | 456/1250 [02:46<04:47,  2.76it/s]
Training 1/1 epoch (loss 2.9177):  36%|███▋      | 456/1250 [02:47<04:47,  2.76it/s]
Training 1/1 epoch (loss 2.9177):  37%|███▋      | 457/1250 [02:47<04:48,  2.75it/s]
Training 1/1 epoch (loss 2.7573):  37%|███▋      | 457/1250 [02:47<04:48,  2.75it/s]
Training 1/1 epoch (loss 2.7573):  37%|███▋      | 458/1250 [02:47<04:36,  2.86it/s]
Training 1/1 epoch (loss 2.9776):  37%|███▋      | 458/1250 [02:47<04:36,  2.86it/s]
Training 1/1 epoch (loss 2.9776):  37%|███▋      | 459/1250 [02:47<04:38,  2.84it/s]
Training 1/1 epoch (loss 2.8129):  37%|███▋      | 459/1250 [02:48<04:38,  2.84it/s]
Training 1/1 epoch (loss 2.8129):  37%|███▋      | 460/1250 [02:48<04:31,  2.91it/s]
Training 1/1 epoch (loss 2.6111):  37%|███▋      | 460/1250 [02:48<04:31,  2.91it/s]
Training 1/1 epoch (loss 2.6111):  37%|███▋      | 461/1250 [02:48<04:19,  3.04it/s]
Training 1/1 epoch (loss 2.6947):  37%|███▋      | 461/1250 [02:48<04:19,  3.04it/s]
Training 1/1 epoch (loss 2.6947):  37%|███▋      | 462/1250 [02:48<04:19,  3.04it/s]
Training 1/1 epoch (loss 2.7731):  37%|███▋      | 462/1250 [02:49<04:19,  3.04it/s]
Training 1/1 epoch (loss 2.7731):  37%|███▋      | 463/1250 [02:49<04:24,  2.97it/s]
Training 1/1 epoch (loss 2.6580):  37%|███▋      | 463/1250 [02:49<04:24,  2.97it/s]
Training 1/1 epoch (loss 2.6580):  37%|███▋      | 464/1250 [02:49<04:29,  2.92it/s]
Training 1/1 epoch (loss 2.4423):  37%|███▋      | 464/1250 [02:49<04:29,  2.92it/s]
Training 1/1 epoch (loss 2.4423):  37%|███▋      | 465/1250 [02:49<04:25,  2.95it/s]
Training 1/1 epoch (loss 2.5912):  37%|███▋      | 465/1250 [02:50<04:25,  2.95it/s]
Training 1/1 epoch (loss 2.5912):  37%|███▋      | 466/1250 [02:50<04:15,  3.07it/s]
Training 1/1 epoch (loss 2.6140):  37%|███▋      | 466/1250 [02:50<04:15,  3.07it/s]
Training 1/1 epoch (loss 2.6140):  37%|███▋      | 467/1250 [02:50<04:13,  3.09it/s]
Training 1/1 epoch (loss 2.7745):  37%|███▋      | 467/1250 [02:50<04:13,  3.09it/s]
Training 1/1 epoch (loss 2.7745):  37%|███▋      | 468/1250 [02:50<04:20,  3.00it/s]
Training 1/1 epoch (loss 2.8650):  37%|███▋      | 468/1250 [02:51<04:20,  3.00it/s]
Training 1/1 epoch (loss 2.8650):  38%|███▊      | 469/1250 [02:51<04:21,  2.98it/s]
Training 1/1 epoch (loss 2.8666):  38%|███▊      | 469/1250 [02:51<04:21,  2.98it/s]
Training 1/1 epoch (loss 2.8666):  38%|███▊      | 470/1250 [02:51<04:18,  3.01it/s]
Training 1/1 epoch (loss 2.8657):  38%|███▊      | 470/1250 [02:51<04:18,  3.01it/s]
Training 1/1 epoch (loss 2.8657):  38%|███▊      | 471/1250 [02:51<04:21,  2.98it/s]
Training 1/1 epoch (loss 2.6816):  38%|███▊      | 471/1250 [02:52<04:21,  2.98it/s]
Training 1/1 epoch (loss 2.6816):  38%|███▊      | 472/1250 [02:52<04:28,  2.90it/s]
Training 1/1 epoch (loss 2.6764):  38%|███▊      | 472/1250 [02:52<04:28,  2.90it/s]
Training 1/1 epoch (loss 2.6764):  38%|███▊      | 473/1250 [02:52<04:24,  2.94it/s]
Training 1/1 epoch (loss 2.6320):  38%|███▊      | 473/1250 [02:52<04:24,  2.94it/s]
Training 1/1 epoch (loss 2.6320):  38%|███▊      | 474/1250 [02:52<04:32,  2.84it/s]
Training 1/1 epoch (loss 2.7111):  38%|███▊      | 474/1250 [02:53<04:32,  2.84it/s]
Training 1/1 epoch (loss 2.7111):  38%|███▊      | 475/1250 [02:53<06:06,  2.11it/s]
Training 1/1 epoch (loss 2.8139):  38%|███▊      | 475/1250 [02:54<06:06,  2.11it/s]
Training 1/1 epoch (loss 2.8139):  38%|███▊      | 476/1250 [02:54<05:56,  2.17it/s]
Training 1/1 epoch (loss 2.7732):  38%|███▊      | 476/1250 [02:54<05:56,  2.17it/s]
Training 1/1 epoch (loss 2.7732):  38%|███▊      | 477/1250 [02:54<05:48,  2.22it/s]
Training 1/1 epoch (loss 2.9237):  38%|███▊      | 477/1250 [02:54<05:48,  2.22it/s]
Training 1/1 epoch (loss 2.9237):  38%|███▊      | 478/1250 [02:54<05:34,  2.31it/s]
Training 1/1 epoch (loss 2.6960):  38%|███▊      | 478/1250 [02:55<05:34,  2.31it/s]
Training 1/1 epoch (loss 2.6960):  38%|███▊      | 479/1250 [02:55<05:26,  2.36it/s]
Training 1/1 epoch (loss 2.7336):  38%|███▊      | 479/1250 [02:56<05:26,  2.36it/s]
Training 1/1 epoch (loss 2.7336):  38%|███▊      | 480/1250 [02:56<06:11,  2.07it/s]
Training 1/1 epoch (loss 2.6960):  38%|███▊      | 480/1250 [02:56<06:11,  2.07it/s]
Training 1/1 epoch (loss 2.6960):  38%|███▊      | 481/1250 [02:56<06:17,  2.04it/s]
Training 1/1 epoch (loss 2.9209):  38%|███▊      | 481/1250 [02:57<06:17,  2.04it/s]
Training 1/1 epoch (loss 2.9209):  39%|███▊      | 482/1250 [02:57<06:52,  1.86it/s]
Training 1/1 epoch (loss 2.6867):  39%|███▊      | 482/1250 [02:57<06:52,  1.86it/s]
Training 1/1 epoch (loss 2.6867):  39%|███▊      | 483/1250 [02:57<07:35,  1.68it/s]
Training 1/1 epoch (loss 2.6091):  39%|███▊      | 483/1250 [02:58<07:35,  1.68it/s]
Training 1/1 epoch (loss 2.6091):  39%|███▊      | 484/1250 [02:58<08:41,  1.47it/s]
Training 1/1 epoch (loss 2.6082):  39%|███▊      | 484/1250 [02:59<08:41,  1.47it/s]
Training 1/1 epoch (loss 2.6082):  39%|███▉      | 485/1250 [02:59<08:49,  1.44it/s]
Training 1/1 epoch (loss 2.7619):  39%|███▉      | 485/1250 [03:00<08:49,  1.44it/s]
Training 1/1 epoch (loss 2.7619):  39%|███▉      | 486/1250 [03:00<08:28,  1.50it/s]
Training 1/1 epoch (loss 2.7679):  39%|███▉      | 486/1250 [03:00<08:28,  1.50it/s]
Training 1/1 epoch (loss 2.7679):  39%|███▉      | 487/1250 [03:00<07:06,  1.79it/s]
Training 1/1 epoch (loss 2.6222):  39%|███▉      | 487/1250 [03:00<07:06,  1.79it/s]
Training 1/1 epoch (loss 2.6222):  39%|███▉      | 488/1250 [03:00<06:15,  2.03it/s]
Training 1/1 epoch (loss 2.7442):  39%|███▉      | 488/1250 [03:01<06:15,  2.03it/s]
Training 1/1 epoch (loss 2.7442):  39%|███▉      | 489/1250 [03:01<05:52,  2.16it/s]
Training 1/1 epoch (loss 2.9563):  39%|███▉      | 489/1250 [03:01<05:52,  2.16it/s]
Training 1/1 epoch (loss 2.9563):  39%|███▉      | 490/1250 [03:01<05:30,  2.30it/s]
Training 1/1 epoch (loss 2.7571):  39%|███▉      | 490/1250 [03:01<05:30,  2.30it/s]
Training 1/1 epoch (loss 2.7571):  39%|███▉      | 491/1250 [03:01<05:01,  2.52it/s]
Training 1/1 epoch (loss 2.6694):  39%|███▉      | 491/1250 [03:02<05:01,  2.52it/s]
Training 1/1 epoch (loss 2.6694):  39%|███▉      | 492/1250 [03:02<04:54,  2.57it/s]
Training 1/1 epoch (loss 2.7813):  39%|███▉      | 492/1250 [03:02<04:54,  2.57it/s]
Training 1/1 epoch (loss 2.7813):  39%|███▉      | 493/1250 [03:02<04:34,  2.76it/s]
Training 1/1 epoch (loss 2.5468):  39%|███▉      | 493/1250 [03:02<04:34,  2.76it/s]
Training 1/1 epoch (loss 2.5468):  40%|███▉      | 494/1250 [03:02<04:30,  2.80it/s]
Training 1/1 epoch (loss 2.8784):  40%|███▉      | 494/1250 [03:03<04:30,  2.80it/s]
Training 1/1 epoch (loss 2.8784):  40%|███▉      | 495/1250 [03:03<04:32,  2.77it/s]
Training 1/1 epoch (loss 2.8191):  40%|███▉      | 495/1250 [03:03<04:32,  2.77it/s]
Training 1/1 epoch (loss 2.8191):  40%|███▉      | 496/1250 [03:03<04:41,  2.68it/s]
Training 1/1 epoch (loss 2.6459):  40%|███▉      | 496/1250 [03:03<04:41,  2.68it/s]
Training 1/1 epoch (loss 2.6459):  40%|███▉      | 497/1250 [03:03<04:44,  2.65it/s]
Training 1/1 epoch (loss 2.8724):  40%|███▉      | 497/1250 [03:04<04:44,  2.65it/s]
Training 1/1 epoch (loss 2.8724):  40%|███▉      | 498/1250 [03:04<04:51,  2.58it/s]
Training 1/1 epoch (loss 2.4903):  40%|███▉      | 498/1250 [03:04<04:51,  2.58it/s]
Training 1/1 epoch (loss 2.4903):  40%|███▉      | 499/1250 [03:04<04:50,  2.58it/s]
Training 1/1 epoch (loss 2.8719):  40%|███▉      | 499/1250 [03:05<04:50,  2.58it/s]
Training 1/1 epoch (loss 2.8719):  40%|████      | 500/1250 [03:05<04:35,  2.72it/s]
Training 1/1 epoch (loss 2.7786):  40%|████      | 500/1250 [03:05<04:35,  2.72it/s]
Training 1/1 epoch (loss 2.7786):  40%|████      | 501/1250 [03:05<04:32,  2.75it/s]
Training 1/1 epoch (loss 2.9849):  40%|████      | 501/1250 [03:05<04:32,  2.75it/s]
Training 1/1 epoch (loss 2.9849):  40%|████      | 502/1250 [03:05<04:32,  2.74it/s]
Training 1/1 epoch (loss 3.0052):  40%|████      | 502/1250 [03:06<04:32,  2.74it/s]
Training 1/1 epoch (loss 3.0052):  40%|████      | 503/1250 [03:06<04:31,  2.76it/s]
Training 1/1 epoch (loss 2.5883):  40%|████      | 503/1250 [03:06<04:31,  2.76it/s]
Training 1/1 epoch (loss 2.5883):  40%|████      | 504/1250 [03:06<04:30,  2.76it/s]
Training 1/1 epoch (loss 2.9588):  40%|████      | 504/1250 [03:06<04:30,  2.76it/s]
Training 1/1 epoch (loss 2.9588):  40%|████      | 505/1250 [03:06<04:28,  2.78it/s]
Training 1/1 epoch (loss 2.9290):  40%|████      | 505/1250 [03:07<04:28,  2.78it/s]
Training 1/1 epoch (loss 2.9290):  40%|████      | 506/1250 [03:07<04:28,  2.77it/s]
Training 1/1 epoch (loss 2.7336):  40%|████      | 506/1250 [03:07<04:28,  2.77it/s]
Training 1/1 epoch (loss 2.7336):  41%|████      | 507/1250 [03:07<04:40,  2.65it/s]
Training 1/1 epoch (loss 2.7791):  41%|████      | 507/1250 [03:08<04:40,  2.65it/s]
Training 1/1 epoch (loss 2.7791):  41%|████      | 508/1250 [03:08<04:44,  2.60it/s]
Training 1/1 epoch (loss 2.8120):  41%|████      | 508/1250 [03:08<04:44,  2.60it/s]
Training 1/1 epoch (loss 2.8120):  41%|████      | 509/1250 [03:08<04:41,  2.63it/s]
Training 1/1 epoch (loss 2.6461):  41%|████      | 509/1250 [03:08<04:41,  2.63it/s]
Training 1/1 epoch (loss 2.6461):  41%|████      | 510/1250 [03:08<04:38,  2.66it/s]
Training 1/1 epoch (loss 2.7195):  41%|████      | 510/1250 [03:09<04:38,  2.66it/s]
Training 1/1 epoch (loss 2.7195):  41%|████      | 511/1250 [03:09<04:30,  2.74it/s]
Training 1/1 epoch (loss 2.7153):  41%|████      | 511/1250 [03:09<04:30,  2.74it/s]
Training 1/1 epoch (loss 2.7153):  41%|████      | 512/1250 [03:09<04:42,  2.61it/s]
Training 1/1 epoch (loss 2.7367):  41%|████      | 512/1250 [03:10<04:42,  2.61it/s]
Training 1/1 epoch (loss 2.7367):  41%|████      | 513/1250 [03:10<04:53,  2.51it/s]
Training 1/1 epoch (loss 2.6231):  41%|████      | 513/1250 [03:10<04:53,  2.51it/s]
Training 1/1 epoch (loss 2.6231):  41%|████      | 514/1250 [03:10<04:40,  2.62it/s]
Training 1/1 epoch (loss 2.6504):  41%|████      | 514/1250 [03:10<04:40,  2.62it/s]
Training 1/1 epoch (loss 2.6504):  41%|████      | 515/1250 [03:10<04:28,  2.74it/s]
Training 1/1 epoch (loss 2.7719):  41%|████      | 515/1250 [03:11<04:28,  2.74it/s]
Training 1/1 epoch (loss 2.7719):  41%|████▏     | 516/1250 [03:11<04:17,  2.86it/s]
Training 1/1 epoch (loss 2.8487):  41%|████▏     | 516/1250 [03:11<04:17,  2.86it/s]
Training 1/1 epoch (loss 2.8487):  41%|████▏     | 517/1250 [03:11<04:06,  2.97it/s]
Training 1/1 epoch (loss 2.7260):  41%|████▏     | 517/1250 [03:11<04:06,  2.97it/s]
Training 1/1 epoch (loss 2.7260):  41%|████▏     | 518/1250 [03:11<04:09,  2.93it/s]
Training 1/1 epoch (loss 2.6551):  41%|████▏     | 518/1250 [03:12<04:09,  2.93it/s]
Training 1/1 epoch (loss 2.6551):  42%|████▏     | 519/1250 [03:12<04:12,  2.90it/s]
Training 1/1 epoch (loss 2.5670):  42%|████▏     | 519/1250 [03:12<04:12,  2.90it/s]
Training 1/1 epoch (loss 2.5670):  42%|████▏     | 520/1250 [03:12<04:06,  2.96it/s]
Training 1/1 epoch (loss 2.8664):  42%|████▏     | 520/1250 [03:12<04:06,  2.96it/s]
Training 1/1 epoch (loss 2.8664):  42%|████▏     | 521/1250 [03:12<04:04,  2.98it/s]
Training 1/1 epoch (loss 2.8194):  42%|████▏     | 521/1250 [03:13<04:04,  2.98it/s]
Training 1/1 epoch (loss 2.8194):  42%|████▏     | 522/1250 [03:13<04:03,  2.99it/s]
Training 1/1 epoch (loss 2.9336):  42%|████▏     | 522/1250 [03:13<04:03,  2.99it/s]
Training 1/1 epoch (loss 2.9336):  42%|████▏     | 523/1250 [03:13<04:02,  3.00it/s]
Training 1/1 epoch (loss 2.8083):  42%|████▏     | 523/1250 [03:13<04:02,  3.00it/s]
Training 1/1 epoch (loss 2.8083):  42%|████▏     | 524/1250 [03:13<04:00,  3.01it/s]
Training 1/1 epoch (loss 2.7809):  42%|████▏     | 524/1250 [03:14<04:00,  3.01it/s]
Training 1/1 epoch (loss 2.7809):  42%|████▏     | 525/1250 [03:14<04:17,  2.81it/s]
Training 1/1 epoch (loss 2.6987):  42%|████▏     | 525/1250 [03:14<04:17,  2.81it/s]
Training 1/1 epoch (loss 2.6987):  42%|████▏     | 526/1250 [03:14<04:17,  2.82it/s]
Training 1/1 epoch (loss 2.6630):  42%|████▏     | 526/1250 [03:14<04:17,  2.82it/s]
Training 1/1 epoch (loss 2.6630):  42%|████▏     | 527/1250 [03:14<04:18,  2.80it/s]
Training 1/1 epoch (loss 2.7548):  42%|████▏     | 527/1250 [03:15<04:18,  2.80it/s]
Training 1/1 epoch (loss 2.7548):  42%|████▏     | 528/1250 [03:15<04:51,  2.48it/s]
Training 1/1 epoch (loss 2.6078):  42%|████▏     | 528/1250 [03:15<04:51,  2.48it/s]
Training 1/1 epoch (loss 2.6078):  42%|████▏     | 529/1250 [03:15<04:43,  2.54it/s]
Training 1/1 epoch (loss 2.7915):  42%|████▏     | 529/1250 [03:15<04:43,  2.54it/s]
Training 1/1 epoch (loss 2.7915):  42%|████▏     | 530/1250 [03:15<04:24,  2.72it/s]
Training 1/1 epoch (loss 2.5355):  42%|████▏     | 530/1250 [03:16<04:24,  2.72it/s]
Training 1/1 epoch (loss 2.5355):  42%|████▏     | 531/1250 [03:16<04:20,  2.76it/s]
Training 1/1 epoch (loss 2.7242):  42%|████▏     | 531/1250 [03:16<04:20,  2.76it/s]
Training 1/1 epoch (loss 2.7242):  43%|████▎     | 532/1250 [03:16<04:13,  2.83it/s]
Training 1/1 epoch (loss 2.8145):  43%|████▎     | 532/1250 [03:16<04:13,  2.83it/s]
Training 1/1 epoch (loss 2.8145):  43%|████▎     | 533/1250 [03:16<04:01,  2.97it/s]
Training 1/1 epoch (loss 2.8687):  43%|████▎     | 533/1250 [03:17<04:01,  2.97it/s]
Training 1/1 epoch (loss 2.8687):  43%|████▎     | 534/1250 [03:17<04:06,  2.91it/s]
Training 1/1 epoch (loss 2.9662):  43%|████▎     | 534/1250 [03:17<04:06,  2.91it/s]
Training 1/1 epoch (loss 2.9662):  43%|████▎     | 535/1250 [03:17<04:03,  2.93it/s]
Training 1/1 epoch (loss 2.8878):  43%|████▎     | 535/1250 [03:17<04:03,  2.93it/s]
Training 1/1 epoch (loss 2.8878):  43%|████▎     | 536/1250 [03:17<03:59,  2.98it/s]
Training 1/1 epoch (loss 2.9633):  43%|████▎     | 536/1250 [03:18<03:59,  2.98it/s]
Training 1/1 epoch (loss 2.9633):  43%|████▎     | 537/1250 [03:18<04:08,  2.87it/s]
Training 1/1 epoch (loss 2.6094):  43%|████▎     | 537/1250 [03:18<04:08,  2.87it/s]
Training 1/1 epoch (loss 2.6094):  43%|████▎     | 538/1250 [03:18<03:58,  2.99it/s]
Training 1/1 epoch (loss 2.8166):  43%|████▎     | 538/1250 [03:18<03:58,  2.99it/s]
Training 1/1 epoch (loss 2.8166):  43%|████▎     | 539/1250 [03:18<03:55,  3.02it/s]
Training 1/1 epoch (loss 2.8963):  43%|████▎     | 539/1250 [03:19<03:55,  3.02it/s]
Training 1/1 epoch (loss 2.8963):  43%|████▎     | 540/1250 [03:19<03:52,  3.05it/s]
Training 1/1 epoch (loss 2.7442):  43%|████▎     | 540/1250 [03:19<03:52,  3.05it/s]
Training 1/1 epoch (loss 2.7442):  43%|████▎     | 541/1250 [03:19<03:54,  3.02it/s]
Training 1/1 epoch (loss 2.7688):  43%|████▎     | 541/1250 [03:19<03:54,  3.02it/s]
Training 1/1 epoch (loss 2.7688):  43%|████▎     | 542/1250 [03:19<03:47,  3.11it/s]
Training 1/1 epoch (loss 2.7116):  43%|████▎     | 542/1250 [03:20<03:47,  3.11it/s]
Training 1/1 epoch (loss 2.7116):  43%|████▎     | 543/1250 [03:20<03:54,  3.01it/s]
Training 1/1 epoch (loss 2.6899):  43%|████▎     | 543/1250 [03:20<03:54,  3.01it/s]
Training 1/1 epoch (loss 2.6899):  44%|████▎     | 544/1250 [03:20<04:03,  2.90it/s]
Training 1/1 epoch (loss 2.7599):  44%|████▎     | 544/1250 [03:20<04:03,  2.90it/s]
Training 1/1 epoch (loss 2.7599):  44%|████▎     | 545/1250 [03:20<03:59,  2.95it/s]
Training 1/1 epoch (loss 2.8811):  44%|████▎     | 545/1250 [03:21<03:59,  2.95it/s]
Training 1/1 epoch (loss 2.8811):  44%|████▎     | 546/1250 [03:21<03:54,  3.01it/s]
Training 1/1 epoch (loss 2.7996):  44%|████▎     | 546/1250 [03:21<03:54,  3.01it/s]
Training 1/1 epoch (loss 2.7996):  44%|████▍     | 547/1250 [03:21<04:05,  2.86it/s]
Training 1/1 epoch (loss 2.9047):  44%|████▍     | 547/1250 [03:22<04:05,  2.86it/s]
Training 1/1 epoch (loss 2.9047):  44%|████▍     | 548/1250 [03:22<03:59,  2.93it/s]
Training 1/1 epoch (loss 2.9886):  44%|████▍     | 548/1250 [03:22<03:59,  2.93it/s]
Training 1/1 epoch (loss 2.9886):  44%|████▍     | 549/1250 [03:22<04:04,  2.87it/s]
Training 1/1 epoch (loss 2.8122):  44%|████▍     | 549/1250 [03:22<04:04,  2.87it/s]
Training 1/1 epoch (loss 2.8122):  44%|████▍     | 550/1250 [03:22<04:00,  2.91it/s]
Training 1/1 epoch (loss 2.6779):  44%|████▍     | 550/1250 [03:23<04:00,  2.91it/s]
Training 1/1 epoch (loss 2.6779):  44%|████▍     | 551/1250 [03:23<03:48,  3.05it/s]
Training 1/1 epoch (loss 2.5751):  44%|████▍     | 551/1250 [03:23<03:48,  3.05it/s]
Training 1/1 epoch (loss 2.5751):  44%|████▍     | 552/1250 [03:23<04:49,  2.41it/s]
Training 1/1 epoch (loss 2.8549):  44%|████▍     | 552/1250 [03:23<04:49,  2.41it/s]
Training 1/1 epoch (loss 2.8549):  44%|████▍     | 553/1250 [03:23<04:37,  2.51it/s]
Training 1/1 epoch (loss 2.7576):  44%|████▍     | 553/1250 [03:24<04:37,  2.51it/s]
Training 1/1 epoch (loss 2.7576):  44%|████▍     | 554/1250 [03:24<04:51,  2.39it/s]
Training 1/1 epoch (loss 2.5462):  44%|████▍     | 554/1250 [03:24<04:51,  2.39it/s]
Training 1/1 epoch (loss 2.5462):  44%|████▍     | 555/1250 [03:24<04:31,  2.56it/s]
Training 1/1 epoch (loss 2.7674):  44%|████▍     | 555/1250 [03:25<04:31,  2.56it/s]
Training 1/1 epoch (loss 2.7674):  44%|████▍     | 556/1250 [03:25<04:11,  2.76it/s]
Training 1/1 epoch (loss 2.9608):  44%|████▍     | 556/1250 [03:25<04:11,  2.76it/s]
Training 1/1 epoch (loss 2.9608):  45%|████▍     | 557/1250 [03:25<04:06,  2.81it/s]
Training 1/1 epoch (loss 2.7740):  45%|████▍     | 557/1250 [03:25<04:06,  2.81it/s]
Training 1/1 epoch (loss 2.7740):  45%|████▍     | 558/1250 [03:25<04:20,  2.66it/s]
Training 1/1 epoch (loss 2.8548):  45%|████▍     | 558/1250 [03:26<04:20,  2.66it/s]
Training 1/1 epoch (loss 2.8548):  45%|████▍     | 559/1250 [03:26<04:07,  2.79it/s]
Training 1/1 epoch (loss 2.8711):  45%|████▍     | 559/1250 [03:26<04:07,  2.79it/s]
Training 1/1 epoch (loss 2.8711):  45%|████▍     | 560/1250 [03:26<04:03,  2.83it/s]
Training 1/1 epoch (loss 2.6154):  45%|████▍     | 560/1250 [03:26<04:03,  2.83it/s]
Training 1/1 epoch (loss 2.6154):  45%|████▍     | 561/1250 [03:26<04:04,  2.82it/s]
Training 1/1 epoch (loss 2.7962):  45%|████▍     | 561/1250 [03:27<04:04,  2.82it/s]
Training 1/1 epoch (loss 2.7962):  45%|████▍     | 562/1250 [03:27<04:00,  2.87it/s]
Training 1/1 epoch (loss 2.8797):  45%|████▍     | 562/1250 [03:27<04:00,  2.87it/s]
Training 1/1 epoch (loss 2.8797):  45%|████▌     | 563/1250 [03:27<03:49,  2.99it/s]
Training 1/1 epoch (loss 2.8930):  45%|████▌     | 563/1250 [03:27<03:49,  2.99it/s]
Training 1/1 epoch (loss 2.8930):  45%|████▌     | 564/1250 [03:27<03:56,  2.90it/s]
Training 1/1 epoch (loss 2.8607):  45%|████▌     | 564/1250 [03:28<03:56,  2.90it/s]
Training 1/1 epoch (loss 2.8607):  45%|████▌     | 565/1250 [03:28<04:16,  2.67it/s]
Training 1/1 epoch (loss 2.8291):  45%|████▌     | 565/1250 [03:28<04:16,  2.67it/s]
Training 1/1 epoch (loss 2.8291):  45%|████▌     | 566/1250 [03:28<04:03,  2.81it/s]
Training 1/1 epoch (loss 2.7973):  45%|████▌     | 566/1250 [03:29<04:03,  2.81it/s]
Training 1/1 epoch (loss 2.7973):  45%|████▌     | 567/1250 [03:29<04:17,  2.65it/s]
Training 1/1 epoch (loss 2.7298):  45%|████▌     | 567/1250 [03:29<04:17,  2.65it/s]
Training 1/1 epoch (loss 2.7298):  45%|████▌     | 568/1250 [03:29<04:24,  2.58it/s]
Training 1/1 epoch (loss 2.8594):  45%|████▌     | 568/1250 [03:29<04:24,  2.58it/s]
Training 1/1 epoch (loss 2.8594):  46%|████▌     | 569/1250 [03:29<04:44,  2.39it/s]
Training 1/1 epoch (loss 2.7135):  46%|████▌     | 569/1250 [03:30<04:44,  2.39it/s]
Training 1/1 epoch (loss 2.7135):  46%|████▌     | 570/1250 [03:30<04:43,  2.40it/s]
Training 1/1 epoch (loss 2.7890):  46%|████▌     | 570/1250 [03:30<04:43,  2.40it/s]
Training 1/1 epoch (loss 2.7890):  46%|████▌     | 571/1250 [03:30<04:20,  2.61it/s]
Training 1/1 epoch (loss 2.8807):  46%|████▌     | 571/1250 [03:30<04:20,  2.61it/s]
Training 1/1 epoch (loss 2.8807):  46%|████▌     | 572/1250 [03:30<04:07,  2.73it/s]
Training 1/1 epoch (loss 2.7958):  46%|████▌     | 572/1250 [03:31<04:07,  2.73it/s]
Training 1/1 epoch (loss 2.7958):  46%|████▌     | 573/1250 [03:31<04:18,  2.62it/s]
Training 1/1 epoch (loss 2.8241):  46%|████▌     | 573/1250 [03:31<04:18,  2.62it/s]
Training 1/1 epoch (loss 2.8241):  46%|████▌     | 574/1250 [03:31<04:22,  2.58it/s]
Training 1/1 epoch (loss 2.8871):  46%|████▌     | 574/1250 [03:32<04:22,  2.58it/s]
Training 1/1 epoch (loss 2.8871):  46%|████▌     | 575/1250 [03:32<04:16,  2.63it/s]
Training 1/1 epoch (loss 2.6851):  46%|████▌     | 575/1250 [03:32<04:16,  2.63it/s]
Training 1/1 epoch (loss 2.6851):  46%|████▌     | 576/1250 [03:32<04:09,  2.71it/s]
Training 1/1 epoch (loss 2.6616):  46%|████▌     | 576/1250 [03:32<04:09,  2.71it/s]
Training 1/1 epoch (loss 2.6616):  46%|████▌     | 577/1250 [03:32<04:00,  2.80it/s]
Training 1/1 epoch (loss 2.8728):  46%|████▌     | 577/1250 [03:33<04:00,  2.80it/s]
Training 1/1 epoch (loss 2.8728):  46%|████▌     | 578/1250 [03:33<04:00,  2.80it/s]
Training 1/1 epoch (loss 2.9902):  46%|████▌     | 578/1250 [03:33<04:00,  2.80it/s]
Training 1/1 epoch (loss 2.9902):  46%|████▋     | 579/1250 [03:33<03:51,  2.90it/s]
Training 1/1 epoch (loss 2.9352):  46%|████▋     | 579/1250 [03:33<03:51,  2.90it/s]
Training 1/1 epoch (loss 2.9352):  46%|████▋     | 580/1250 [03:33<03:57,  2.82it/s]
Training 1/1 epoch (loss 2.7541):  46%|████▋     | 580/1250 [03:34<03:57,  2.82it/s]
Training 1/1 epoch (loss 2.7541):  46%|████▋     | 581/1250 [03:34<04:01,  2.77it/s]
Training 1/1 epoch (loss 2.6526):  46%|████▋     | 581/1250 [03:34<04:01,  2.77it/s]
Training 1/1 epoch (loss 2.6526):  47%|████▋     | 582/1250 [03:34<04:03,  2.75it/s]
Training 1/1 epoch (loss 2.6189):  47%|████▋     | 582/1250 [03:34<04:03,  2.75it/s]
Training 1/1 epoch (loss 2.6189):  47%|████▋     | 583/1250 [03:34<03:54,  2.85it/s]
Training 1/1 epoch (loss 2.6658):  47%|████▋     | 583/1250 [03:35<03:54,  2.85it/s]
Training 1/1 epoch (loss 2.6658):  47%|████▋     | 584/1250 [03:35<04:00,  2.76it/s]
Training 1/1 epoch (loss 2.8424):  47%|████▋     | 584/1250 [03:35<04:00,  2.76it/s]
Training 1/1 epoch (loss 2.8424):  47%|████▋     | 585/1250 [03:35<04:02,  2.74it/s]
Training 1/1 epoch (loss 2.6215):  47%|████▋     | 585/1250 [03:36<04:02,  2.74it/s]
Training 1/1 epoch (loss 2.6215):  47%|████▋     | 586/1250 [03:36<03:53,  2.84it/s]
Training 1/1 epoch (loss 2.7304):  47%|████▋     | 586/1250 [03:36<03:53,  2.84it/s]
Training 1/1 epoch (loss 2.7304):  47%|████▋     | 587/1250 [03:36<04:00,  2.76it/s]
Training 1/1 epoch (loss 2.5255):  47%|████▋     | 587/1250 [03:36<04:00,  2.76it/s]
Training 1/1 epoch (loss 2.5255):  47%|████▋     | 588/1250 [03:36<03:52,  2.85it/s]
Training 1/1 epoch (loss 2.6795):  47%|████▋     | 588/1250 [03:37<03:52,  2.85it/s]
Training 1/1 epoch (loss 2.6795):  47%|████▋     | 589/1250 [03:37<03:46,  2.91it/s]
Training 1/1 epoch (loss 2.7579):  47%|████▋     | 589/1250 [03:37<03:46,  2.91it/s]
Training 1/1 epoch (loss 2.7579):  47%|████▋     | 590/1250 [03:37<03:46,  2.91it/s]
Training 1/1 epoch (loss 2.6447):  47%|████▋     | 590/1250 [03:37<03:46,  2.91it/s]
Training 1/1 epoch (loss 2.6447):  47%|████▋     | 591/1250 [03:37<03:50,  2.86it/s]
Training 1/1 epoch (loss 2.7672):  47%|████▋     | 591/1250 [03:38<03:50,  2.86it/s]
Training 1/1 epoch (loss 2.7672):  47%|████▋     | 592/1250 [03:38<03:48,  2.88it/s]
Training 1/1 epoch (loss 2.8807):  47%|████▋     | 592/1250 [03:38<03:48,  2.88it/s]
Training 1/1 epoch (loss 2.8807):  47%|████▋     | 593/1250 [03:38<03:49,  2.86it/s]
Training 1/1 epoch (loss 2.6761):  47%|████▋     | 593/1250 [03:38<03:49,  2.86it/s]
Training 1/1 epoch (loss 2.6761):  48%|████▊     | 594/1250 [03:38<03:49,  2.86it/s]
Training 1/1 epoch (loss 2.6565):  48%|████▊     | 594/1250 [03:39<03:49,  2.86it/s]
Training 1/1 epoch (loss 2.6565):  48%|████▊     | 595/1250 [03:39<03:46,  2.89it/s]
Training 1/1 epoch (loss 2.7000):  48%|████▊     | 595/1250 [03:39<03:46,  2.89it/s]
Training 1/1 epoch (loss 2.7000):  48%|████▊     | 596/1250 [03:39<03:35,  3.03it/s]
Training 1/1 epoch (loss 2.7839):  48%|████▊     | 596/1250 [03:39<03:35,  3.03it/s]
Training 1/1 epoch (loss 2.7839):  48%|████▊     | 597/1250 [03:39<03:47,  2.87it/s]
Training 1/1 epoch (loss 2.7255):  48%|████▊     | 597/1250 [03:40<03:47,  2.87it/s]
Training 1/1 epoch (loss 2.7255):  48%|████▊     | 598/1250 [03:40<03:41,  2.94it/s]
Training 1/1 epoch (loss 2.7522):  48%|████▊     | 598/1250 [03:40<03:41,  2.94it/s]
Training 1/1 epoch (loss 2.7522):  48%|████▊     | 599/1250 [03:40<03:43,  2.92it/s]
Training 1/1 epoch (loss 2.7732):  48%|████▊     | 599/1250 [03:40<03:43,  2.92it/s]
Training 1/1 epoch (loss 2.7732):  48%|████▊     | 600/1250 [03:40<03:49,  2.83it/s]
Training 1/1 epoch (loss 2.9322):  48%|████▊     | 600/1250 [03:41<03:49,  2.83it/s]
Training 1/1 epoch (loss 2.9322):  48%|████▊     | 601/1250 [03:41<03:50,  2.82it/s]
Training 1/1 epoch (loss 2.6647):  48%|████▊     | 601/1250 [03:41<03:50,  2.82it/s]
Training 1/1 epoch (loss 2.6647):  48%|████▊     | 602/1250 [03:41<03:44,  2.89it/s]
Training 1/1 epoch (loss 2.6633):  48%|████▊     | 602/1250 [03:41<03:44,  2.89it/s]
Training 1/1 epoch (loss 2.6633):  48%|████▊     | 603/1250 [03:41<03:51,  2.80it/s]
Training 1/1 epoch (loss 2.8071):  48%|████▊     | 603/1250 [03:42<03:51,  2.80it/s]
Training 1/1 epoch (loss 2.8071):  48%|████▊     | 604/1250 [03:42<03:39,  2.95it/s]
Training 1/1 epoch (loss 2.7215):  48%|████▊     | 604/1250 [03:42<03:39,  2.95it/s]
Training 1/1 epoch (loss 2.7215):  48%|████▊     | 605/1250 [03:42<03:34,  3.01it/s]
Training 1/1 epoch (loss 2.8361):  48%|████▊     | 605/1250 [03:42<03:34,  3.01it/s]
Training 1/1 epoch (loss 2.8361):  48%|████▊     | 606/1250 [03:42<03:37,  2.96it/s]
Training 1/1 epoch (loss 2.5946):  48%|████▊     | 606/1250 [03:43<03:37,  2.96it/s]
Training 1/1 epoch (loss 2.5946):  49%|████▊     | 607/1250 [03:43<03:32,  3.02it/s]
Training 1/1 epoch (loss 2.9467):  49%|████▊     | 607/1250 [03:43<03:32,  3.02it/s]
Training 1/1 epoch (loss 2.9467):  49%|████▊     | 608/1250 [03:43<03:36,  2.96it/s]
Training 1/1 epoch (loss 2.6877):  49%|████▊     | 608/1250 [03:43<03:36,  2.96it/s]
Training 1/1 epoch (loss 2.6877):  49%|████▊     | 609/1250 [03:43<03:44,  2.86it/s]
Training 1/1 epoch (loss 2.8047):  49%|████▊     | 609/1250 [03:44<03:44,  2.86it/s]
Training 1/1 epoch (loss 2.8047):  49%|████▉     | 610/1250 [03:44<03:49,  2.79it/s]
Training 1/1 epoch (loss 2.8422):  49%|████▉     | 610/1250 [03:44<03:49,  2.79it/s]
Training 1/1 epoch (loss 2.8422):  49%|████▉     | 611/1250 [03:44<03:43,  2.85it/s]
Training 1/1 epoch (loss 2.6157):  49%|████▉     | 611/1250 [03:45<03:43,  2.85it/s]
Training 1/1 epoch (loss 2.6157):  49%|████▉     | 612/1250 [03:45<03:49,  2.78it/s]
Training 1/1 epoch (loss 2.8673):  49%|████▉     | 612/1250 [03:45<03:49,  2.78it/s]
Training 1/1 epoch (loss 2.8673):  49%|████▉     | 613/1250 [03:45<03:44,  2.84it/s]
Training 1/1 epoch (loss 2.9131):  49%|████▉     | 613/1250 [03:45<03:44,  2.84it/s]
Training 1/1 epoch (loss 2.9131):  49%|████▉     | 614/1250 [03:45<03:39,  2.89it/s]
Training 1/1 epoch (loss 2.7717):  49%|████▉     | 614/1250 [03:46<03:39,  2.89it/s]
Training 1/1 epoch (loss 2.7717):  49%|████▉     | 615/1250 [03:46<03:36,  2.93it/s]
Training 1/1 epoch (loss 2.8407):  49%|████▉     | 615/1250 [03:46<03:36,  2.93it/s]
Training 1/1 epoch (loss 2.8407):  49%|████▉     | 616/1250 [03:46<03:43,  2.84it/s]
Training 1/1 epoch (loss 2.3852):  49%|████▉     | 616/1250 [03:46<03:43,  2.84it/s]
Training 1/1 epoch (loss 2.3852):  49%|████▉     | 617/1250 [03:46<03:50,  2.74it/s]
Training 1/1 epoch (loss 2.7459):  49%|████▉     | 617/1250 [03:47<03:50,  2.74it/s]
Training 1/1 epoch (loss 2.7459):  49%|████▉     | 618/1250 [03:47<03:46,  2.79it/s]
Training 1/1 epoch (loss 2.6517):  49%|████▉     | 618/1250 [03:47<03:46,  2.79it/s]
Training 1/1 epoch (loss 2.6517):  50%|████▉     | 619/1250 [03:47<03:44,  2.80it/s]
Training 1/1 epoch (loss 2.6508):  50%|████▉     | 619/1250 [03:47<03:44,  2.80it/s]
Training 1/1 epoch (loss 2.6508):  50%|████▉     | 620/1250 [03:47<03:39,  2.86it/s]
Training 1/1 epoch (loss 2.5915):  50%|████▉     | 620/1250 [03:48<03:39,  2.86it/s]
Training 1/1 epoch (loss 2.5915):  50%|████▉     | 621/1250 [03:48<03:32,  2.96it/s]
Training 1/1 epoch (loss 2.9703):  50%|████▉     | 621/1250 [03:48<03:32,  2.96it/s]
Training 1/1 epoch (loss 2.9703):  50%|████▉     | 622/1250 [03:48<03:32,  2.95it/s]
Training 1/1 epoch (loss 2.7742):  50%|████▉     | 622/1250 [03:48<03:32,  2.95it/s]
Training 1/1 epoch (loss 2.7742):  50%|████▉     | 623/1250 [03:48<03:29,  3.00it/s]
Training 1/1 epoch (loss 2.7100):  50%|████▉     | 623/1250 [03:49<03:29,  3.00it/s]
Training 1/1 epoch (loss 2.7100):  50%|████▉     | 624/1250 [03:49<03:28,  3.01it/s]
Training 1/1 epoch (loss 2.7804):  50%|████▉     | 624/1250 [03:49<03:28,  3.01it/s]
Training 1/1 epoch (loss 2.7804):  50%|█████     | 625/1250 [03:49<03:42,  2.81it/s]
Training 1/1 epoch (loss 2.8126):  50%|█████     | 625/1250 [03:49<03:42,  2.81it/s]
Training 1/1 epoch (loss 2.8126):  50%|█████     | 626/1250 [03:49<03:44,  2.78it/s]
Training 1/1 epoch (loss 2.5222):  50%|█████     | 626/1250 [03:50<03:44,  2.78it/s]
Training 1/1 epoch (loss 2.5222):  50%|█████     | 627/1250 [03:50<03:35,  2.88it/s]
Training 1/1 epoch (loss 2.7319):  50%|█████     | 627/1250 [03:50<03:35,  2.88it/s]
Training 1/1 epoch (loss 2.7319):  50%|█████     | 628/1250 [03:50<03:30,  2.96it/s]
Training 1/1 epoch (loss 2.8925):  50%|█████     | 628/1250 [03:50<03:30,  2.96it/s]
Training 1/1 epoch (loss 2.8925):  50%|█████     | 629/1250 [03:50<03:26,  3.01it/s]
Training 1/1 epoch (loss 2.4747):  50%|█████     | 629/1250 [03:51<03:26,  3.01it/s]
Training 1/1 epoch (loss 2.4747):  50%|█████     | 630/1250 [03:51<03:26,  3.00it/s]
Training 1/1 epoch (loss 2.7060):  50%|█████     | 630/1250 [03:51<03:26,  3.00it/s]
Training 1/1 epoch (loss 2.7060):  50%|█████     | 631/1250 [03:51<03:21,  3.07it/s]
Training 1/1 epoch (loss 2.8996):  50%|█████     | 631/1250 [03:51<03:21,  3.07it/s]
Training 1/1 epoch (loss 2.8996):  51%|█████     | 632/1250 [03:51<03:38,  2.83it/s]
Training 1/1 epoch (loss 2.7837):  51%|█████     | 632/1250 [03:52<03:38,  2.83it/s]
Training 1/1 epoch (loss 2.7837):  51%|█████     | 633/1250 [03:52<03:38,  2.83it/s]
Training 1/1 epoch (loss 2.7224):  51%|█████     | 633/1250 [03:52<03:38,  2.83it/s]
Training 1/1 epoch (loss 2.7224):  51%|█████     | 634/1250 [03:52<03:30,  2.93it/s]
Training 1/1 epoch (loss 2.6303):  51%|█████     | 634/1250 [03:52<03:30,  2.93it/s]
Training 1/1 epoch (loss 2.6303):  51%|█████     | 635/1250 [03:52<03:31,  2.91it/s]
Training 1/1 epoch (loss 2.5313):  51%|█████     | 635/1250 [03:53<03:31,  2.91it/s]
Training 1/1 epoch (loss 2.5313):  51%|█████     | 636/1250 [03:53<04:03,  2.52it/s]
Training 1/1 epoch (loss 2.6430):  51%|█████     | 636/1250 [03:53<04:03,  2.52it/s]
Training 1/1 epoch (loss 2.6430):  51%|█████     | 637/1250 [03:53<03:53,  2.62it/s]
Training 1/1 epoch (loss 2.5807):  51%|█████     | 637/1250 [03:54<03:53,  2.62it/s]
Training 1/1 epoch (loss 2.5807):  51%|█████     | 638/1250 [03:54<03:48,  2.67it/s]
Training 1/1 epoch (loss 2.9059):  51%|█████     | 638/1250 [03:54<03:48,  2.67it/s]
Training 1/1 epoch (loss 2.9059):  51%|█████     | 639/1250 [03:54<03:44,  2.73it/s]
Training 1/1 epoch (loss 2.7133):  51%|█████     | 639/1250 [03:54<03:44,  2.73it/s]
Training 1/1 epoch (loss 2.7133):  51%|█████     | 640/1250 [03:54<03:44,  2.71it/s]
Training 1/1 epoch (loss 2.6685):  51%|█████     | 640/1250 [03:55<03:44,  2.71it/s]
Training 1/1 epoch (loss 2.6685):  51%|█████▏    | 641/1250 [03:55<03:43,  2.72it/s]
Training 1/1 epoch (loss 2.6587):  51%|█████▏    | 641/1250 [03:55<03:43,  2.72it/s]
Training 1/1 epoch (loss 2.6587):  51%|█████▏    | 642/1250 [03:55<03:32,  2.86it/s]
Training 1/1 epoch (loss 2.7331):  51%|█████▏    | 642/1250 [03:56<03:32,  2.86it/s]
Training 1/1 epoch (loss 2.7331):  51%|█████▏    | 643/1250 [03:56<03:45,  2.69it/s]
Training 1/1 epoch (loss 2.7027):  51%|█████▏    | 643/1250 [03:56<03:45,  2.69it/s]
Training 1/1 epoch (loss 2.7027):  52%|█████▏    | 644/1250 [03:56<03:40,  2.75it/s]
Training 1/1 epoch (loss 2.6384):  52%|█████▏    | 644/1250 [03:56<03:40,  2.75it/s]
Training 1/1 epoch (loss 2.6384):  52%|█████▏    | 645/1250 [03:56<03:33,  2.83it/s]
Training 1/1 epoch (loss 2.3503):  52%|█████▏    | 645/1250 [03:57<03:33,  2.83it/s]
Training 1/1 epoch (loss 2.3503):  52%|█████▏    | 646/1250 [03:57<03:38,  2.76it/s]
Training 1/1 epoch (loss 2.6597):  52%|█████▏    | 646/1250 [03:57<03:38,  2.76it/s]
Training 1/1 epoch (loss 2.6597):  52%|█████▏    | 647/1250 [03:57<03:38,  2.76it/s]
Training 1/1 epoch (loss 2.9339):  52%|█████▏    | 647/1250 [03:57<03:38,  2.76it/s]
Training 1/1 epoch (loss 2.9339):  52%|█████▏    | 648/1250 [03:57<03:42,  2.71it/s]
Training 1/1 epoch (loss 2.5646):  52%|█████▏    | 648/1250 [03:58<03:42,  2.71it/s]
Training 1/1 epoch (loss 2.5646):  52%|█████▏    | 649/1250 [03:58<04:15,  2.35it/s]
Training 1/1 epoch (loss 2.8481):  52%|█████▏    | 649/1250 [03:58<04:15,  2.35it/s]
Training 1/1 epoch (loss 2.8481):  52%|█████▏    | 650/1250 [03:58<04:09,  2.41it/s]
Training 1/1 epoch (loss 2.7800):  52%|█████▏    | 650/1250 [03:59<04:09,  2.41it/s]
Training 1/1 epoch (loss 2.7800):  52%|█████▏    | 651/1250 [03:59<03:57,  2.53it/s]
Training 1/1 epoch (loss 2.6242):  52%|█████▏    | 651/1250 [03:59<03:57,  2.53it/s]
Training 1/1 epoch (loss 2.6242):  52%|█████▏    | 652/1250 [03:59<03:42,  2.69it/s]
Training 1/1 epoch (loss 2.6171):  52%|█████▏    | 652/1250 [03:59<03:42,  2.69it/s]
Training 1/1 epoch (loss 2.6171):  52%|█████▏    | 653/1250 [03:59<03:44,  2.66it/s]
Training 1/1 epoch (loss 2.5592):  52%|█████▏    | 653/1250 [04:00<03:44,  2.66it/s]
Training 1/1 epoch (loss 2.5592):  52%|█████▏    | 654/1250 [04:00<03:39,  2.72it/s]
Training 1/1 epoch (loss 2.7348):  52%|█████▏    | 654/1250 [04:00<03:39,  2.72it/s]
Training 1/1 epoch (loss 2.7348):  52%|█████▏    | 655/1250 [04:00<03:32,  2.80it/s]
Training 1/1 epoch (loss 2.9552):  52%|█████▏    | 655/1250 [04:00<03:32,  2.80it/s]
Training 1/1 epoch (loss 2.9552):  52%|█████▏    | 656/1250 [04:00<03:26,  2.87it/s]
Training 1/1 epoch (loss 2.8662):  52%|█████▏    | 656/1250 [04:01<03:26,  2.87it/s]
Training 1/1 epoch (loss 2.8662):  53%|█████▎    | 657/1250 [04:01<03:26,  2.87it/s]
Training 1/1 epoch (loss 2.8978):  53%|█████▎    | 657/1250 [04:01<03:26,  2.87it/s]
Training 1/1 epoch (loss 2.8978):  53%|█████▎    | 658/1250 [04:01<03:20,  2.96it/s]
Training 1/1 epoch (loss 2.6213):  53%|█████▎    | 658/1250 [04:01<03:20,  2.96it/s]
Training 1/1 epoch (loss 2.6213):  53%|█████▎    | 659/1250 [04:01<03:21,  2.93it/s]
Training 1/1 epoch (loss 2.4187):  53%|█████▎    | 659/1250 [04:02<03:21,  2.93it/s]
Training 1/1 epoch (loss 2.4187):  53%|█████▎    | 660/1250 [04:02<03:23,  2.90it/s]
Training 1/1 epoch (loss 2.5700):  53%|█████▎    | 660/1250 [04:02<03:23,  2.90it/s]
Training 1/1 epoch (loss 2.5700):  53%|█████▎    | 661/1250 [04:02<03:28,  2.83it/s]
Training 1/1 epoch (loss 2.6825):  53%|█████▎    | 661/1250 [04:02<03:28,  2.83it/s]
Training 1/1 epoch (loss 2.6825):  53%|█████▎    | 662/1250 [04:02<03:24,  2.88it/s]
Training 1/1 epoch (loss 2.7438):  53%|█████▎    | 662/1250 [04:03<03:24,  2.88it/s]
Training 1/1 epoch (loss 2.7438):  53%|█████▎    | 663/1250 [04:03<03:18,  2.96it/s]
Training 1/1 epoch (loss 2.7994):  53%|█████▎    | 663/1250 [04:03<03:18,  2.96it/s]
Training 1/1 epoch (loss 2.7994):  53%|█████▎    | 664/1250 [04:03<03:20,  2.93it/s]
Training 1/1 epoch (loss 2.7399):  53%|█████▎    | 664/1250 [04:03<03:20,  2.93it/s]
Training 1/1 epoch (loss 2.7399):  53%|█████▎    | 665/1250 [04:03<03:24,  2.86it/s]
Training 1/1 epoch (loss 2.7107):  53%|█████▎    | 665/1250 [04:04<03:24,  2.86it/s]
Training 1/1 epoch (loss 2.7107):  53%|█████▎    | 666/1250 [04:04<03:29,  2.78it/s]
Training 1/1 epoch (loss 2.9298):  53%|█████▎    | 666/1250 [04:04<03:29,  2.78it/s]
Training 1/1 epoch (loss 2.9298):  53%|█████▎    | 667/1250 [04:04<03:28,  2.80it/s]
Training 1/1 epoch (loss 2.7903):  53%|█████▎    | 667/1250 [04:05<03:28,  2.80it/s]
Training 1/1 epoch (loss 2.7903):  53%|█████▎    | 668/1250 [04:05<03:27,  2.81it/s]
Training 1/1 epoch (loss 2.7540):  53%|█████▎    | 668/1250 [04:05<03:27,  2.81it/s]
Training 1/1 epoch (loss 2.7540):  54%|█████▎    | 669/1250 [04:05<03:22,  2.86it/s]
Training 1/1 epoch (loss 3.0198):  54%|█████▎    | 669/1250 [04:05<03:22,  2.86it/s]
Training 1/1 epoch (loss 3.0198):  54%|█████▎    | 670/1250 [04:05<03:15,  2.97it/s]
Training 1/1 epoch (loss 3.0074):  54%|█████▎    | 670/1250 [04:06<03:15,  2.97it/s]
Training 1/1 epoch (loss 3.0074):  54%|█████▎    | 671/1250 [04:06<03:18,  2.92it/s]
Training 1/1 epoch (loss 2.9435):  54%|█████▎    | 671/1250 [04:06<03:18,  2.92it/s]
Training 1/1 epoch (loss 2.9435):  54%|█████▍    | 672/1250 [04:06<03:15,  2.96it/s]
Training 1/1 epoch (loss 2.6271):  54%|█████▍    | 672/1250 [04:06<03:15,  2.96it/s]
Training 1/1 epoch (loss 2.6271):  54%|█████▍    | 673/1250 [04:06<03:17,  2.92it/s]
Training 1/1 epoch (loss 2.8534):  54%|█████▍    | 673/1250 [04:07<03:17,  2.92it/s]
Training 1/1 epoch (loss 2.8534):  54%|█████▍    | 674/1250 [04:07<03:09,  3.04it/s]
Training 1/1 epoch (loss 2.5239):  54%|█████▍    | 674/1250 [04:07<03:09,  3.04it/s]
Training 1/1 epoch (loss 2.5239):  54%|█████▍    | 675/1250 [04:07<03:11,  3.00it/s]
Training 1/1 epoch (loss 2.7671):  54%|█████▍    | 675/1250 [04:07<03:11,  3.00it/s]
Training 1/1 epoch (loss 2.7671):  54%|█████▍    | 676/1250 [04:07<03:15,  2.94it/s]
Training 1/1 epoch (loss 2.5753):  54%|█████▍    | 676/1250 [04:08<03:15,  2.94it/s]
Training 1/1 epoch (loss 2.5753):  54%|█████▍    | 677/1250 [04:08<03:15,  2.93it/s]
Training 1/1 epoch (loss 2.8298):  54%|█████▍    | 677/1250 [04:08<03:15,  2.93it/s]
Training 1/1 epoch (loss 2.8298):  54%|█████▍    | 678/1250 [04:08<03:09,  3.01it/s]
Training 1/1 epoch (loss 2.8314):  54%|█████▍    | 678/1250 [04:08<03:09,  3.01it/s]
Training 1/1 epoch (loss 2.8314):  54%|█████▍    | 679/1250 [04:08<03:08,  3.03it/s]
Training 1/1 epoch (loss 2.7359):  54%|█████▍    | 679/1250 [04:09<03:08,  3.03it/s]
Training 1/1 epoch (loss 2.7359):  54%|█████▍    | 680/1250 [04:09<03:11,  2.98it/s]
Training 1/1 epoch (loss 2.6415):  54%|█████▍    | 680/1250 [04:09<03:11,  2.98it/s]
Training 1/1 epoch (loss 2.6415):  54%|█████▍    | 681/1250 [04:09<03:11,  2.97it/s]
Training 1/1 epoch (loss 2.8631):  54%|█████▍    | 681/1250 [04:09<03:11,  2.97it/s]
Training 1/1 epoch (loss 2.8631):  55%|█████▍    | 682/1250 [04:09<03:09,  3.00it/s]
Training 1/1 epoch (loss 2.8550):  55%|█████▍    | 682/1250 [04:10<03:09,  3.00it/s]
Training 1/1 epoch (loss 2.8550):  55%|█████▍    | 683/1250 [04:10<03:11,  2.96it/s]
Training 1/1 epoch (loss 2.8308):  55%|█████▍    | 683/1250 [04:10<03:11,  2.96it/s]
Training 1/1 epoch (loss 2.8308):  55%|█████▍    | 684/1250 [04:10<03:07,  3.02it/s]
Training 1/1 epoch (loss 2.5500):  55%|█████▍    | 684/1250 [04:10<03:07,  3.02it/s]
Training 1/1 epoch (loss 2.5500):  55%|█████▍    | 685/1250 [04:10<03:06,  3.03it/s]
Training 1/1 epoch (loss 2.8118):  55%|█████▍    | 685/1250 [04:11<03:06,  3.03it/s]
Training 1/1 epoch (loss 2.8118):  55%|█████▍    | 686/1250 [04:11<03:08,  3.00it/s]
Training 1/1 epoch (loss 2.6204):  55%|█████▍    | 686/1250 [04:11<03:08,  3.00it/s]
Training 1/1 epoch (loss 2.6204):  55%|█████▍    | 687/1250 [04:11<02:59,  3.13it/s]
Training 1/1 epoch (loss 2.7879):  55%|█████▍    | 687/1250 [04:11<02:59,  3.13it/s]
Training 1/1 epoch (loss 2.7879):  55%|█████▌    | 688/1250 [04:11<03:08,  2.99it/s]
Training 1/1 epoch (loss 2.8381):  55%|█████▌    | 688/1250 [04:12<03:08,  2.99it/s]
Training 1/1 epoch (loss 2.8381):  55%|█████▌    | 689/1250 [04:12<03:06,  3.00it/s]
Training 1/1 epoch (loss 2.8529):  55%|█████▌    | 689/1250 [04:12<03:06,  3.00it/s]
Training 1/1 epoch (loss 2.8529):  55%|█████▌    | 690/1250 [04:12<03:04,  3.03it/s]
Training 1/1 epoch (loss 2.6622):  55%|█████▌    | 690/1250 [04:12<03:04,  3.03it/s]
Training 1/1 epoch (loss 2.6622):  55%|█████▌    | 691/1250 [04:12<03:01,  3.08it/s]
Training 1/1 epoch (loss 2.7844):  55%|█████▌    | 691/1250 [04:13<03:01,  3.08it/s]
Training 1/1 epoch (loss 2.7844):  55%|█████▌    | 692/1250 [04:13<03:08,  2.96it/s]
Training 1/1 epoch (loss 2.7658):  55%|█████▌    | 692/1250 [04:13<03:08,  2.96it/s]
Training 1/1 epoch (loss 2.7658):  55%|█████▌    | 693/1250 [04:13<03:04,  3.02it/s]
Training 1/1 epoch (loss 2.9522):  55%|█████▌    | 693/1250 [04:13<03:04,  3.02it/s]
Training 1/1 epoch (loss 2.9522):  56%|█████▌    | 694/1250 [04:13<02:59,  3.10it/s]
Training 1/1 epoch (loss 2.7292):  56%|█████▌    | 694/1250 [04:14<02:59,  3.10it/s]
Training 1/1 epoch (loss 2.7292):  56%|█████▌    | 695/1250 [04:14<03:13,  2.87it/s]
Training 1/1 epoch (loss 2.9572):  56%|█████▌    | 695/1250 [04:14<03:13,  2.87it/s]
Training 1/1 epoch (loss 2.9572):  56%|█████▌    | 696/1250 [04:14<03:20,  2.76it/s]
Training 1/1 epoch (loss 2.7399):  56%|█████▌    | 696/1250 [04:14<03:20,  2.76it/s]
Training 1/1 epoch (loss 2.7399):  56%|█████▌    | 697/1250 [04:14<03:25,  2.69it/s]
Training 1/1 epoch (loss 2.6775):  56%|█████▌    | 697/1250 [04:15<03:25,  2.69it/s]
Training 1/1 epoch (loss 2.6775):  56%|█████▌    | 698/1250 [04:15<03:24,  2.70it/s]
Training 1/1 epoch (loss 2.8843):  56%|█████▌    | 698/1250 [04:15<03:24,  2.70it/s]
Training 1/1 epoch (loss 2.8843):  56%|█████▌    | 699/1250 [04:15<03:22,  2.72it/s]
Training 1/1 epoch (loss 3.0212):  56%|█████▌    | 699/1250 [04:15<03:22,  2.72it/s]
Training 1/1 epoch (loss 3.0212):  56%|█████▌    | 700/1250 [04:15<03:14,  2.83it/s]
Training 1/1 epoch (loss 2.9040):  56%|█████▌    | 700/1250 [04:16<03:14,  2.83it/s]
Training 1/1 epoch (loss 2.9040):  56%|█████▌    | 701/1250 [04:16<03:14,  2.83it/s]
Training 1/1 epoch (loss 2.7188):  56%|█████▌    | 701/1250 [04:16<03:14,  2.83it/s]
Training 1/1 epoch (loss 2.7188):  56%|█████▌    | 702/1250 [04:16<03:07,  2.93it/s]
Training 1/1 epoch (loss 2.7964):  56%|█████▌    | 702/1250 [04:16<03:07,  2.93it/s]
Training 1/1 epoch (loss 2.7964):  56%|█████▌    | 703/1250 [04:16<03:05,  2.95it/s]
Training 1/1 epoch (loss 2.5746):  56%|█████▌    | 703/1250 [04:17<03:05,  2.95it/s]
Training 1/1 epoch (loss 2.5746):  56%|█████▋    | 704/1250 [04:17<03:10,  2.86it/s]
Training 1/1 epoch (loss 2.7986):  56%|█████▋    | 704/1250 [04:17<03:10,  2.86it/s]
Training 1/1 epoch (loss 2.7986):  56%|█████▋    | 705/1250 [04:17<03:06,  2.93it/s]
Training 1/1 epoch (loss 2.8114):  56%|█████▋    | 705/1250 [04:17<03:06,  2.93it/s]
Training 1/1 epoch (loss 2.8114):  56%|█████▋    | 706/1250 [04:17<03:07,  2.90it/s]
Training 1/1 epoch (loss 2.7998):  56%|█████▋    | 706/1250 [04:18<03:07,  2.90it/s]
Training 1/1 epoch (loss 2.7998):  57%|█████▋    | 707/1250 [04:18<03:19,  2.72it/s]
Training 1/1 epoch (loss 2.8607):  57%|█████▋    | 707/1250 [04:18<03:19,  2.72it/s]
Training 1/1 epoch (loss 2.8607):  57%|█████▋    | 708/1250 [04:18<03:12,  2.81it/s]
Training 1/1 epoch (loss 2.8848):  57%|█████▋    | 708/1250 [04:18<03:12,  2.81it/s]
Training 1/1 epoch (loss 2.8848):  57%|█████▋    | 709/1250 [04:18<03:02,  2.97it/s]
Training 1/1 epoch (loss 2.7264):  57%|█████▋    | 709/1250 [04:19<03:02,  2.97it/s]
Training 1/1 epoch (loss 2.7264):  57%|█████▋    | 710/1250 [04:19<03:00,  2.99it/s]
Training 1/1 epoch (loss 2.8575):  57%|█████▋    | 710/1250 [04:19<03:00,  2.99it/s]
Training 1/1 epoch (loss 2.8575):  57%|█████▋    | 711/1250 [04:19<02:57,  3.04it/s]
Training 1/1 epoch (loss 2.8407):  57%|█████▋    | 711/1250 [04:19<02:57,  3.04it/s]
Training 1/1 epoch (loss 2.8407):  57%|█████▋    | 712/1250 [04:19<02:59,  3.00it/s]
Training 1/1 epoch (loss 2.6309):  57%|█████▋    | 712/1250 [04:20<02:59,  3.00it/s]
Training 1/1 epoch (loss 2.6309):  57%|█████▋    | 713/1250 [04:20<03:01,  2.95it/s]
Training 1/1 epoch (loss 2.9797):  57%|█████▋    | 713/1250 [04:20<03:01,  2.95it/s]
Training 1/1 epoch (loss 2.9797):  57%|█████▋    | 714/1250 [04:20<03:01,  2.95it/s]
Training 1/1 epoch (loss 2.8169):  57%|█████▋    | 714/1250 [04:20<03:01,  2.95it/s]
Training 1/1 epoch (loss 2.8169):  57%|█████▋    | 715/1250 [04:20<02:57,  3.02it/s]
Training 1/1 epoch (loss 2.4872):  57%|█████▋    | 715/1250 [04:21<02:57,  3.02it/s]
Training 1/1 epoch (loss 2.4872):  57%|█████▋    | 716/1250 [04:21<03:02,  2.92it/s]
Training 1/1 epoch (loss 2.8422):  57%|█████▋    | 716/1250 [04:21<03:02,  2.92it/s]
Training 1/1 epoch (loss 2.8422):  57%|█████▋    | 717/1250 [04:21<02:57,  3.00it/s]
Training 1/1 epoch (loss 2.8244):  57%|█████▋    | 717/1250 [04:21<02:57,  3.00it/s]
Training 1/1 epoch (loss 2.8244):  57%|█████▋    | 718/1250 [04:21<02:56,  3.02it/s]
Training 1/1 epoch (loss 2.8057):  57%|█████▋    | 718/1250 [04:22<02:56,  3.02it/s]
Training 1/1 epoch (loss 2.8057):  58%|█████▊    | 719/1250 [04:22<02:59,  2.96it/s]
Training 1/1 epoch (loss 2.9178):  58%|█████▊    | 719/1250 [04:22<02:59,  2.96it/s]
Training 1/1 epoch (loss 2.9178):  58%|█████▊    | 720/1250 [04:22<03:02,  2.90it/s]
Training 1/1 epoch (loss 2.6634):  58%|█████▊    | 720/1250 [04:23<03:02,  2.90it/s]
Training 1/1 epoch (loss 2.6634):  58%|█████▊    | 721/1250 [04:23<03:03,  2.88it/s]
Training 1/1 epoch (loss 2.6638):  58%|█████▊    | 721/1250 [04:23<03:03,  2.88it/s]
Training 1/1 epoch (loss 2.6638):  58%|█████▊    | 722/1250 [04:23<03:52,  2.27it/s]
Training 1/1 epoch (loss 2.5081):  58%|█████▊    | 722/1250 [04:24<03:52,  2.27it/s]
Training 1/1 epoch (loss 2.5081):  58%|█████▊    | 723/1250 [04:24<03:41,  2.38it/s]
Training 1/1 epoch (loss 2.6696):  58%|█████▊    | 723/1250 [04:24<03:41,  2.38it/s]
Training 1/1 epoch (loss 2.6696):  58%|█████▊    | 724/1250 [04:24<03:27,  2.53it/s]
Training 1/1 epoch (loss 3.0889):  58%|█████▊    | 724/1250 [04:24<03:27,  2.53it/s]
Training 1/1 epoch (loss 3.0889):  58%|█████▊    | 725/1250 [04:24<03:22,  2.60it/s]
Training 1/1 epoch (loss 2.6679):  58%|█████▊    | 725/1250 [04:25<03:22,  2.60it/s]
Training 1/1 epoch (loss 2.6679):  58%|█████▊    | 726/1250 [04:25<03:14,  2.70it/s]
Training 1/1 epoch (loss 2.6324):  58%|█████▊    | 726/1250 [04:25<03:14,  2.70it/s]
Training 1/1 epoch (loss 2.6324):  58%|█████▊    | 727/1250 [04:25<03:06,  2.80it/s]
Training 1/1 epoch (loss 2.6400):  58%|█████▊    | 727/1250 [04:25<03:06,  2.80it/s]
Training 1/1 epoch (loss 2.6400):  58%|█████▊    | 728/1250 [04:25<03:14,  2.69it/s]
Training 1/1 epoch (loss 2.8310):  58%|█████▊    | 728/1250 [04:26<03:14,  2.69it/s]
Training 1/1 epoch (loss 2.8310):  58%|█████▊    | 729/1250 [04:26<03:12,  2.70it/s]
Training 1/1 epoch (loss 2.8372):  58%|█████▊    | 729/1250 [04:26<03:12,  2.70it/s]
Training 1/1 epoch (loss 2.8372):  58%|█████▊    | 730/1250 [04:26<03:07,  2.77it/s]
Training 1/1 epoch (loss 2.7676):  58%|█████▊    | 730/1250 [04:26<03:07,  2.77it/s]
Training 1/1 epoch (loss 2.7676):  58%|█████▊    | 731/1250 [04:26<03:06,  2.78it/s]
Training 1/1 epoch (loss 2.4912):  58%|█████▊    | 731/1250 [04:27<03:06,  2.78it/s]
Training 1/1 epoch (loss 2.4912):  59%|█████▊    | 732/1250 [04:27<02:56,  2.93it/s]
Training 1/1 epoch (loss 2.6205):  59%|█████▊    | 732/1250 [04:27<02:56,  2.93it/s]
Training 1/1 epoch (loss 2.6205):  59%|█████▊    | 733/1250 [04:27<02:55,  2.94it/s]
Training 1/1 epoch (loss 2.7251):  59%|█████▊    | 733/1250 [04:27<02:55,  2.94it/s]
Training 1/1 epoch (loss 2.7251):  59%|█████▊    | 734/1250 [04:27<02:55,  2.94it/s]
Training 1/1 epoch (loss 2.6939):  59%|█████▊    | 734/1250 [04:28<02:55,  2.94it/s]
Training 1/1 epoch (loss 2.6939):  59%|█████▉    | 735/1250 [04:28<03:11,  2.69it/s]
Training 1/1 epoch (loss 2.9324):  59%|█████▉    | 735/1250 [04:28<03:11,  2.69it/s]
Training 1/1 epoch (loss 2.9324):  59%|█████▉    | 736/1250 [04:28<03:26,  2.49it/s]
Training 1/1 epoch (loss 2.5819):  59%|█████▉    | 736/1250 [04:29<03:26,  2.49it/s]
Training 1/1 epoch (loss 2.5819):  59%|█████▉    | 737/1250 [04:29<03:30,  2.44it/s]
Training 1/1 epoch (loss 2.7011):  59%|█████▉    | 737/1250 [04:29<03:30,  2.44it/s]
Training 1/1 epoch (loss 2.7011):  59%|█████▉    | 738/1250 [04:29<03:21,  2.55it/s]
Training 1/1 epoch (loss 2.7576):  59%|█████▉    | 738/1250 [04:29<03:21,  2.55it/s]
Training 1/1 epoch (loss 2.7576):  59%|█████▉    | 739/1250 [04:29<03:12,  2.66it/s]
Training 1/1 epoch (loss 2.6903):  59%|█████▉    | 739/1250 [04:30<03:12,  2.66it/s]
Training 1/1 epoch (loss 2.6903):  59%|█████▉    | 740/1250 [04:30<03:05,  2.75it/s]
Training 1/1 epoch (loss 2.6679):  59%|█████▉    | 740/1250 [04:30<03:05,  2.75it/s]
Training 1/1 epoch (loss 2.6679):  59%|█████▉    | 741/1250 [04:30<02:59,  2.83it/s]
Training 1/1 epoch (loss 2.8213):  59%|█████▉    | 741/1250 [04:30<02:59,  2.83it/s]
Training 1/1 epoch (loss 2.8213):  59%|█████▉    | 742/1250 [04:30<02:54,  2.91it/s]
Training 1/1 epoch (loss 2.7489):  59%|█████▉    | 742/1250 [04:31<02:54,  2.91it/s]
Training 1/1 epoch (loss 2.7489):  59%|█████▉    | 743/1250 [04:31<02:54,  2.90it/s]
Training 1/1 epoch (loss 2.8107):  59%|█████▉    | 743/1250 [04:31<02:54,  2.90it/s]
Training 1/1 epoch (loss 2.8107):  60%|█████▉    | 744/1250 [04:31<02:56,  2.87it/s]
Training 1/1 epoch (loss 2.7591):  60%|█████▉    | 744/1250 [04:31<02:56,  2.87it/s]
Training 1/1 epoch (loss 2.7591):  60%|█████▉    | 745/1250 [04:31<02:59,  2.81it/s]
Training 1/1 epoch (loss 2.8344):  60%|█████▉    | 745/1250 [04:32<02:59,  2.81it/s]
Training 1/1 epoch (loss 2.8344):  60%|█████▉    | 746/1250 [04:32<03:01,  2.78it/s]
Training 1/1 epoch (loss 2.5994):  60%|█████▉    | 746/1250 [04:32<03:01,  2.78it/s]
Training 1/1 epoch (loss 2.5994):  60%|█████▉    | 747/1250 [04:32<02:59,  2.80it/s]
Training 1/1 epoch (loss 2.7995):  60%|█████▉    | 747/1250 [04:33<02:59,  2.80it/s]
Training 1/1 epoch (loss 2.7995):  60%|█████▉    | 748/1250 [04:33<02:57,  2.83it/s]
Training 1/1 epoch (loss 2.5950):  60%|█████▉    | 748/1250 [04:33<02:57,  2.83it/s]
Training 1/1 epoch (loss 2.5950):  60%|█████▉    | 749/1250 [04:33<02:52,  2.91it/s]
Training 1/1 epoch (loss 2.7940):  60%|█████▉    | 749/1250 [04:33<02:52,  2.91it/s]
Training 1/1 epoch (loss 2.7940):  60%|██████    | 750/1250 [04:33<02:49,  2.95it/s]
Training 1/1 epoch (loss 2.5636):  60%|██████    | 750/1250 [04:34<02:49,  2.95it/s]
Training 1/1 epoch (loss 2.5636):  60%|██████    | 751/1250 [04:34<02:48,  2.96it/s]
Training 1/1 epoch (loss 2.8083):  60%|██████    | 751/1250 [04:34<02:48,  2.96it/s]
Training 1/1 epoch (loss 2.8083):  60%|██████    | 752/1250 [04:34<03:07,  2.65it/s]
Training 1/1 epoch (loss 2.9822):  60%|██████    | 752/1250 [04:34<03:07,  2.65it/s]
Training 1/1 epoch (loss 2.9822):  60%|██████    | 753/1250 [04:34<03:04,  2.69it/s]
Training 1/1 epoch (loss 2.9166):  60%|██████    | 753/1250 [04:35<03:04,  2.69it/s]
Training 1/1 epoch (loss 2.9166):  60%|██████    | 754/1250 [04:35<02:58,  2.79it/s]
Training 1/1 epoch (loss 2.7191):  60%|██████    | 754/1250 [04:35<02:58,  2.79it/s]
Training 1/1 epoch (loss 2.7191):  60%|██████    | 755/1250 [04:35<02:53,  2.85it/s]
Training 1/1 epoch (loss 2.9729):  60%|██████    | 755/1250 [04:35<02:53,  2.85it/s]
Training 1/1 epoch (loss 2.9729):  60%|██████    | 756/1250 [04:35<02:50,  2.89it/s]
Training 1/1 epoch (loss 2.7689):  60%|██████    | 756/1250 [04:36<02:50,  2.89it/s]
Training 1/1 epoch (loss 2.7689):  61%|██████    | 757/1250 [04:36<02:51,  2.87it/s]
Training 1/1 epoch (loss 2.6778):  61%|██████    | 757/1250 [04:36<02:51,  2.87it/s]
Training 1/1 epoch (loss 2.6778):  61%|██████    | 758/1250 [04:36<02:48,  2.91it/s]
Training 1/1 epoch (loss 2.7340):  61%|██████    | 758/1250 [04:36<02:48,  2.91it/s]
Training 1/1 epoch (loss 2.7340):  61%|██████    | 759/1250 [04:36<02:48,  2.92it/s]
Training 1/1 epoch (loss 2.7932):  61%|██████    | 759/1250 [04:37<02:48,  2.92it/s]
Training 1/1 epoch (loss 2.7932):  61%|██████    | 760/1250 [04:37<02:46,  2.95it/s]
Training 1/1 epoch (loss 2.8299):  61%|██████    | 760/1250 [04:37<02:46,  2.95it/s]
Training 1/1 epoch (loss 2.8299):  61%|██████    | 761/1250 [04:37<02:45,  2.95it/s]
Training 1/1 epoch (loss 2.6074):  61%|██████    | 761/1250 [04:37<02:45,  2.95it/s]
Training 1/1 epoch (loss 2.6074):  61%|██████    | 762/1250 [04:37<02:46,  2.93it/s]
Training 1/1 epoch (loss 2.6011):  61%|██████    | 762/1250 [04:38<02:46,  2.93it/s]
Training 1/1 epoch (loss 2.6011):  61%|██████    | 763/1250 [04:38<02:45,  2.94it/s]
Training 1/1 epoch (loss 2.7645):  61%|██████    | 763/1250 [04:38<02:45,  2.94it/s]
Training 1/1 epoch (loss 2.7645):  61%|██████    | 764/1250 [04:38<02:39,  3.05it/s]
Training 1/1 epoch (loss 2.7985):  61%|██████    | 764/1250 [04:38<02:39,  3.05it/s]
Training 1/1 epoch (loss 2.7985):  61%|██████    | 765/1250 [04:38<02:44,  2.94it/s]
Training 1/1 epoch (loss 2.5274):  61%|██████    | 765/1250 [04:39<02:44,  2.94it/s]
Training 1/1 epoch (loss 2.5274):  61%|██████▏   | 766/1250 [04:39<02:43,  2.97it/s]
Training 1/1 epoch (loss 2.5422):  61%|██████▏   | 766/1250 [04:39<02:43,  2.97it/s]
Training 1/1 epoch (loss 2.5422):  61%|██████▏   | 767/1250 [04:39<02:44,  2.93it/s]
Training 1/1 epoch (loss 2.7259):  61%|██████▏   | 767/1250 [04:39<02:44,  2.93it/s]
Training 1/1 epoch (loss 2.7259):  61%|██████▏   | 768/1250 [04:39<02:49,  2.84it/s]
Training 1/1 epoch (loss 2.9017):  61%|██████▏   | 768/1250 [04:40<02:49,  2.84it/s]
Training 1/1 epoch (loss 2.9017):  62%|██████▏   | 769/1250 [04:40<02:46,  2.89it/s]
Training 1/1 epoch (loss 2.7449):  62%|██████▏   | 769/1250 [04:40<02:46,  2.89it/s]
Training 1/1 epoch (loss 2.7449):  62%|██████▏   | 770/1250 [04:40<02:48,  2.85it/s]
Training 1/1 epoch (loss 2.8049):  62%|██████▏   | 770/1250 [04:41<02:48,  2.85it/s]
Training 1/1 epoch (loss 2.8049):  62%|██████▏   | 771/1250 [04:41<02:48,  2.85it/s]
Training 1/1 epoch (loss 2.8361):  62%|██████▏   | 771/1250 [04:41<02:48,  2.85it/s]
Training 1/1 epoch (loss 2.8361):  62%|██████▏   | 772/1250 [04:41<02:42,  2.94it/s]
Training 1/1 epoch (loss 2.6996):  62%|██████▏   | 772/1250 [04:41<02:42,  2.94it/s]
Training 1/1 epoch (loss 2.6996):  62%|██████▏   | 773/1250 [04:41<02:39,  2.99it/s]
Training 1/1 epoch (loss 2.6951):  62%|██████▏   | 773/1250 [04:41<02:39,  2.99it/s]
Training 1/1 epoch (loss 2.6951):  62%|██████▏   | 774/1250 [04:41<02:38,  3.01it/s]
Training 1/1 epoch (loss 2.7918):  62%|██████▏   | 774/1250 [04:42<02:38,  3.01it/s]
Training 1/1 epoch (loss 2.7918):  62%|██████▏   | 775/1250 [04:42<02:38,  3.00it/s]
Training 1/1 epoch (loss 2.6249):  62%|██████▏   | 775/1250 [04:42<02:38,  3.00it/s]
Training 1/1 epoch (loss 2.6249):  62%|██████▏   | 776/1250 [04:42<02:40,  2.95it/s]
Training 1/1 epoch (loss 2.7974):  62%|██████▏   | 776/1250 [04:43<02:40,  2.95it/s]
Training 1/1 epoch (loss 2.7974):  62%|██████▏   | 777/1250 [04:43<02:44,  2.88it/s]
Training 1/1 epoch (loss 2.8290):  62%|██████▏   | 777/1250 [04:43<02:44,  2.88it/s]
Training 1/1 epoch (loss 2.8290):  62%|██████▏   | 778/1250 [04:43<02:37,  3.00it/s]
Training 1/1 epoch (loss 2.6965):  62%|██████▏   | 778/1250 [04:43<02:37,  3.00it/s]
Training 1/1 epoch (loss 2.6965):  62%|██████▏   | 779/1250 [04:43<02:36,  3.01it/s]
Training 1/1 epoch (loss 2.9995):  62%|██████▏   | 779/1250 [04:43<02:36,  3.01it/s]
Training 1/1 epoch (loss 2.9995):  62%|██████▏   | 780/1250 [04:43<02:33,  3.06it/s]
Training 1/1 epoch (loss 2.5981):  62%|██████▏   | 780/1250 [04:44<02:33,  3.06it/s]
Training 1/1 epoch (loss 2.5981):  62%|██████▏   | 781/1250 [04:44<02:40,  2.93it/s]
Training 1/1 epoch (loss 2.8203):  62%|██████▏   | 781/1250 [04:44<02:40,  2.93it/s]
Training 1/1 epoch (loss 2.8203):  63%|██████▎   | 782/1250 [04:44<02:49,  2.76it/s]
Training 1/1 epoch (loss 2.7977):  63%|██████▎   | 782/1250 [04:45<02:49,  2.76it/s]
Training 1/1 epoch (loss 2.7977):  63%|██████▎   | 783/1250 [04:45<02:52,  2.71it/s]
Training 1/1 epoch (loss 2.5840):  63%|██████▎   | 783/1250 [04:45<02:52,  2.71it/s]
Training 1/1 epoch (loss 2.5840):  63%|██████▎   | 784/1250 [04:45<02:46,  2.80it/s]
Training 1/1 epoch (loss 2.9107):  63%|██████▎   | 784/1250 [04:45<02:46,  2.80it/s]
Training 1/1 epoch (loss 2.9107):  63%|██████▎   | 785/1250 [04:45<02:43,  2.84it/s]
Training 1/1 epoch (loss 2.8426):  63%|██████▎   | 785/1250 [04:46<02:43,  2.84it/s]
Training 1/1 epoch (loss 2.8426):  63%|██████▎   | 786/1250 [04:46<02:44,  2.82it/s]
Training 1/1 epoch (loss 2.8196):  63%|██████▎   | 786/1250 [04:46<02:44,  2.82it/s]
Training 1/1 epoch (loss 2.8196):  63%|██████▎   | 787/1250 [04:46<03:43,  2.07it/s]
Training 1/1 epoch (loss 2.5697):  63%|██████▎   | 787/1250 [04:47<03:43,  2.07it/s]
Training 1/1 epoch (loss 2.5697):  63%|██████▎   | 788/1250 [04:47<03:25,  2.24it/s]
Training 1/1 epoch (loss 2.5427):  63%|██████▎   | 788/1250 [04:47<03:25,  2.24it/s]
Training 1/1 epoch (loss 2.5427):  63%|██████▎   | 789/1250 [04:47<03:04,  2.49it/s]
Training 1/1 epoch (loss 2.6282):  63%|██████▎   | 789/1250 [04:47<03:04,  2.49it/s]
Training 1/1 epoch (loss 2.6282):  63%|██████▎   | 790/1250 [04:47<02:56,  2.60it/s]
Training 1/1 epoch (loss 2.7595):  63%|██████▎   | 790/1250 [04:48<02:56,  2.60it/s]
Training 1/1 epoch (loss 2.7595):  63%|██████▎   | 791/1250 [04:48<02:51,  2.68it/s]
Training 1/1 epoch (loss 2.7224):  63%|██████▎   | 791/1250 [04:48<02:51,  2.68it/s]
Training 1/1 epoch (loss 2.7224):  63%|██████▎   | 792/1250 [04:48<02:45,  2.77it/s]
Training 1/1 epoch (loss 2.5571):  63%|██████▎   | 792/1250 [04:48<02:45,  2.77it/s]
Training 1/1 epoch (loss 2.5571):  63%|██████▎   | 793/1250 [04:48<02:44,  2.78it/s]
Training 1/1 epoch (loss 2.7249):  63%|██████▎   | 793/1250 [04:49<02:44,  2.78it/s]
Training 1/1 epoch (loss 2.7249):  64%|██████▎   | 794/1250 [04:49<02:44,  2.78it/s]
Training 1/1 epoch (loss 2.8927):  64%|██████▎   | 794/1250 [04:49<02:44,  2.78it/s]
Training 1/1 epoch (loss 2.8927):  64%|██████▎   | 795/1250 [04:49<02:36,  2.91it/s]
Training 1/1 epoch (loss 2.6904):  64%|██████▎   | 795/1250 [04:49<02:36,  2.91it/s]
Training 1/1 epoch (loss 2.6904):  64%|██████▎   | 796/1250 [04:49<02:30,  3.01it/s]
Training 1/1 epoch (loss 2.6662):  64%|██████▎   | 796/1250 [04:50<02:30,  3.01it/s]
Training 1/1 epoch (loss 2.6662):  64%|██████▍   | 797/1250 [04:50<02:33,  2.95it/s]
Training 1/1 epoch (loss 2.8839):  64%|██████▍   | 797/1250 [04:50<02:33,  2.95it/s]
Training 1/1 epoch (loss 2.8839):  64%|██████▍   | 798/1250 [04:50<03:00,  2.51it/s]
Training 1/1 epoch (loss 2.8420):  64%|██████▍   | 798/1250 [04:51<03:00,  2.51it/s]
Training 1/1 epoch (loss 2.8420):  64%|██████▍   | 799/1250 [04:51<02:51,  2.63it/s]
Training 1/1 epoch (loss 2.7810):  64%|██████▍   | 799/1250 [04:51<02:51,  2.63it/s]
Training 1/1 epoch (loss 2.7810):  64%|██████▍   | 800/1250 [04:51<02:48,  2.67it/s]
Training 1/1 epoch (loss 2.7131):  64%|██████▍   | 800/1250 [04:51<02:48,  2.67it/s]
Training 1/1 epoch (loss 2.7131):  64%|██████▍   | 801/1250 [04:51<02:42,  2.76it/s]
Training 1/1 epoch (loss 2.8420):  64%|██████▍   | 801/1250 [04:52<02:42,  2.76it/s]
Training 1/1 epoch (loss 2.8420):  64%|██████▍   | 802/1250 [04:52<02:39,  2.81it/s]
Training 1/1 epoch (loss 2.7272):  64%|██████▍   | 802/1250 [04:52<02:39,  2.81it/s]
Training 1/1 epoch (loss 2.7272):  64%|██████▍   | 803/1250 [04:52<02:34,  2.90it/s]
Training 1/1 epoch (loss 2.6088):  64%|██████▍   | 803/1250 [04:52<02:34,  2.90it/s]
Training 1/1 epoch (loss 2.6088):  64%|██████▍   | 804/1250 [04:52<02:31,  2.95it/s]
Training 1/1 epoch (loss 2.7235):  64%|██████▍   | 804/1250 [04:53<02:31,  2.95it/s]
Training 1/1 epoch (loss 2.7235):  64%|██████▍   | 805/1250 [04:53<02:30,  2.95it/s]
Training 1/1 epoch (loss 2.7137):  64%|██████▍   | 805/1250 [04:53<02:30,  2.95it/s]
Training 1/1 epoch (loss 2.7137):  64%|██████▍   | 806/1250 [04:53<03:05,  2.40it/s]
Training 1/1 epoch (loss 2.7162):  64%|██████▍   | 806/1250 [04:54<03:05,  2.40it/s]
Training 1/1 epoch (loss 2.7162):  65%|██████▍   | 807/1250 [04:54<02:57,  2.49it/s]
Training 1/1 epoch (loss 2.6596):  65%|██████▍   | 807/1250 [04:54<02:57,  2.49it/s]
Training 1/1 epoch (loss 2.6596):  65%|██████▍   | 808/1250 [04:54<02:54,  2.53it/s]
Training 1/1 epoch (loss 2.6618):  65%|██████▍   | 808/1250 [04:54<02:54,  2.53it/s]
Training 1/1 epoch (loss 2.6618):  65%|██████▍   | 809/1250 [04:54<02:56,  2.49it/s]
Training 1/1 epoch (loss 2.8156):  65%|██████▍   | 809/1250 [04:55<02:56,  2.49it/s]
Training 1/1 epoch (loss 2.8156):  65%|██████▍   | 810/1250 [04:55<02:49,  2.59it/s]
Training 1/1 epoch (loss 2.7768):  65%|██████▍   | 810/1250 [04:55<02:49,  2.59it/s]
Training 1/1 epoch (loss 2.7768):  65%|██████▍   | 811/1250 [04:55<02:42,  2.71it/s]
Training 1/1 epoch (loss 2.7296):  65%|██████▍   | 811/1250 [04:55<02:42,  2.71it/s]
Training 1/1 epoch (loss 2.7296):  65%|██████▍   | 812/1250 [04:55<02:38,  2.76it/s]
Training 1/1 epoch (loss 2.6777):  65%|██████▍   | 812/1250 [04:56<02:38,  2.76it/s]
Training 1/1 epoch (loss 2.6777):  65%|██████▌   | 813/1250 [04:56<02:32,  2.87it/s]
Training 1/1 epoch (loss 2.7758):  65%|██████▌   | 813/1250 [04:56<02:32,  2.87it/s]
Training 1/1 epoch (loss 2.7758):  65%|██████▌   | 814/1250 [04:56<02:43,  2.66it/s]
Training 1/1 epoch (loss 2.8336):  65%|██████▌   | 814/1250 [04:57<02:43,  2.66it/s]
Training 1/1 epoch (loss 2.8336):  65%|██████▌   | 815/1250 [04:57<02:40,  2.71it/s]
Training 1/1 epoch (loss 2.8850):  65%|██████▌   | 815/1250 [04:57<02:40,  2.71it/s]
Training 1/1 epoch (loss 2.8850):  65%|██████▌   | 816/1250 [04:57<02:34,  2.80it/s]
Training 1/1 epoch (loss 2.8073):  65%|██████▌   | 816/1250 [04:57<02:34,  2.80it/s]
Training 1/1 epoch (loss 2.8073):  65%|██████▌   | 817/1250 [04:57<02:31,  2.86it/s]
Training 1/1 epoch (loss 2.6364):  65%|██████▌   | 817/1250 [04:58<02:31,  2.86it/s]
Training 1/1 epoch (loss 2.6364):  65%|██████▌   | 818/1250 [04:58<02:52,  2.50it/s]
Training 1/1 epoch (loss 2.9309):  65%|██████▌   | 818/1250 [04:58<02:52,  2.50it/s]
Training 1/1 epoch (loss 2.9309):  66%|██████▌   | 819/1250 [04:58<02:54,  2.47it/s]
Training 1/1 epoch (loss 2.6973):  66%|██████▌   | 819/1250 [04:59<02:54,  2.47it/s]
Training 1/1 epoch (loss 2.6973):  66%|██████▌   | 820/1250 [04:59<03:02,  2.36it/s]
Training 1/1 epoch (loss 2.6018):  66%|██████▌   | 820/1250 [04:59<03:02,  2.36it/s]
Training 1/1 epoch (loss 2.6018):  66%|██████▌   | 821/1250 [04:59<02:56,  2.43it/s]
Training 1/1 epoch (loss 2.5811):  66%|██████▌   | 821/1250 [04:59<02:56,  2.43it/s]
Training 1/1 epoch (loss 2.5811):  66%|██████▌   | 822/1250 [04:59<02:48,  2.54it/s]
Training 1/1 epoch (loss 2.6145):  66%|██████▌   | 822/1250 [05:00<02:48,  2.54it/s]
Training 1/1 epoch (loss 2.6145):  66%|██████▌   | 823/1250 [05:00<02:44,  2.59it/s]
Training 1/1 epoch (loss 2.6305):  66%|██████▌   | 823/1250 [05:00<02:44,  2.59it/s]
Training 1/1 epoch (loss 2.6305):  66%|██████▌   | 824/1250 [05:00<02:44,  2.58it/s]
Training 1/1 epoch (loss 2.7132):  66%|██████▌   | 824/1250 [05:01<02:44,  2.58it/s]
Training 1/1 epoch (loss 2.7132):  66%|██████▌   | 825/1250 [05:01<02:38,  2.68it/s]
Training 1/1 epoch (loss 2.8757):  66%|██████▌   | 825/1250 [05:01<02:38,  2.68it/s]
Training 1/1 epoch (loss 2.8757):  66%|██████▌   | 826/1250 [05:01<02:31,  2.80it/s]
Training 1/1 epoch (loss 2.7950):  66%|██████▌   | 826/1250 [05:01<02:31,  2.80it/s]
Training 1/1 epoch (loss 2.7950):  66%|██████▌   | 827/1250 [05:01<02:32,  2.78it/s]
Training 1/1 epoch (loss 2.6937):  66%|██████▌   | 827/1250 [05:02<02:32,  2.78it/s]
Training 1/1 epoch (loss 2.6937):  66%|██████▌   | 828/1250 [05:02<02:27,  2.87it/s]
Training 1/1 epoch (loss 2.7467):  66%|██████▌   | 828/1250 [05:02<02:27,  2.87it/s]
Training 1/1 epoch (loss 2.7467):  66%|██████▋   | 829/1250 [05:02<02:26,  2.87it/s]
Training 1/1 epoch (loss 2.6299):  66%|██████▋   | 829/1250 [05:02<02:26,  2.87it/s]
Training 1/1 epoch (loss 2.6299):  66%|██████▋   | 830/1250 [05:02<02:29,  2.80it/s]
Training 1/1 epoch (loss 2.7127):  66%|██████▋   | 830/1250 [05:03<02:29,  2.80it/s]
Training 1/1 epoch (loss 2.7127):  66%|██████▋   | 831/1250 [05:03<02:24,  2.90it/s]
Training 1/1 epoch (loss 2.8268):  66%|██████▋   | 831/1250 [05:03<02:24,  2.90it/s]
Training 1/1 epoch (loss 2.8268):  67%|██████▋   | 832/1250 [05:03<02:30,  2.77it/s]
Training 1/1 epoch (loss 2.6800):  67%|██████▋   | 832/1250 [05:03<02:30,  2.77it/s]
Training 1/1 epoch (loss 2.6800):  67%|██████▋   | 833/1250 [05:03<02:25,  2.86it/s]
Training 1/1 epoch (loss 2.8238):  67%|██████▋   | 833/1250 [05:04<02:25,  2.86it/s]
Training 1/1 epoch (loss 2.8238):  67%|██████▋   | 834/1250 [05:04<02:27,  2.82it/s]
Training 1/1 epoch (loss 2.9829):  67%|██████▋   | 834/1250 [05:04<02:27,  2.82it/s]
Training 1/1 epoch (loss 2.9829):  67%|██████▋   | 835/1250 [05:04<02:33,  2.71it/s]
Training 1/1 epoch (loss 2.7706):  67%|██████▋   | 835/1250 [05:04<02:33,  2.71it/s]
Training 1/1 epoch (loss 2.7706):  67%|██████▋   | 836/1250 [05:04<02:27,  2.81it/s]
Training 1/1 epoch (loss 2.7210):  67%|██████▋   | 836/1250 [05:05<02:27,  2.81it/s]
Training 1/1 epoch (loss 2.7210):  67%|██████▋   | 837/1250 [05:05<02:21,  2.93it/s]
Training 1/1 epoch (loss 2.8198):  67%|██████▋   | 837/1250 [05:05<02:21,  2.93it/s]
Training 1/1 epoch (loss 2.8198):  67%|██████▋   | 838/1250 [05:05<02:19,  2.95it/s]
Training 1/1 epoch (loss 2.8230):  67%|██████▋   | 838/1250 [05:05<02:19,  2.95it/s]
Training 1/1 epoch (loss 2.8230):  67%|██████▋   | 839/1250 [05:05<02:25,  2.83it/s]
Training 1/1 epoch (loss 2.5288):  67%|██████▋   | 839/1250 [05:06<02:25,  2.83it/s]
Training 1/1 epoch (loss 2.5288):  67%|██████▋   | 840/1250 [05:06<02:21,  2.90it/s]
Training 1/1 epoch (loss 2.7285):  67%|██████▋   | 840/1250 [05:06<02:21,  2.90it/s]
Training 1/1 epoch (loss 2.7285):  67%|██████▋   | 841/1250 [05:06<02:26,  2.79it/s]
Training 1/1 epoch (loss 2.8483):  67%|██████▋   | 841/1250 [05:06<02:26,  2.79it/s]
Training 1/1 epoch (loss 2.8483):  67%|██████▋   | 842/1250 [05:06<02:28,  2.75it/s]
Training 1/1 epoch (loss 2.6609):  67%|██████▋   | 842/1250 [05:07<02:28,  2.75it/s]
Training 1/1 epoch (loss 2.6609):  67%|██████▋   | 843/1250 [05:07<02:20,  2.89it/s]
Training 1/1 epoch (loss 2.8179):  67%|██████▋   | 843/1250 [05:07<02:20,  2.89it/s]
Training 1/1 epoch (loss 2.8179):  68%|██████▊   | 844/1250 [05:07<02:23,  2.83it/s]
Training 1/1 epoch (loss 2.7405):  68%|██████▊   | 844/1250 [05:08<02:23,  2.83it/s]
Training 1/1 epoch (loss 2.7405):  68%|██████▊   | 845/1250 [05:08<02:21,  2.86it/s]
Training 1/1 epoch (loss 2.8293):  68%|██████▊   | 845/1250 [05:08<02:21,  2.86it/s]
Training 1/1 epoch (loss 2.8293):  68%|██████▊   | 846/1250 [05:08<02:16,  2.96it/s]
Training 1/1 epoch (loss 2.6338):  68%|██████▊   | 846/1250 [05:08<02:16,  2.96it/s]
Training 1/1 epoch (loss 2.6338):  68%|██████▊   | 847/1250 [05:08<02:13,  3.02it/s]
Training 1/1 epoch (loss 2.7195):  68%|██████▊   | 847/1250 [05:08<02:13,  3.02it/s]
Training 1/1 epoch (loss 2.7195):  68%|██████▊   | 848/1250 [05:08<02:13,  3.01it/s]
Training 1/1 epoch (loss 2.7580):  68%|██████▊   | 848/1250 [05:09<02:13,  3.01it/s]
Training 1/1 epoch (loss 2.7580):  68%|██████▊   | 849/1250 [05:09<02:16,  2.93it/s]
Training 1/1 epoch (loss 2.8976):  68%|██████▊   | 849/1250 [05:09<02:16,  2.93it/s]
Training 1/1 epoch (loss 2.8976):  68%|██████▊   | 850/1250 [05:09<02:15,  2.95it/s]
Training 1/1 epoch (loss 2.6515):  68%|██████▊   | 850/1250 [05:09<02:15,  2.95it/s]
Training 1/1 epoch (loss 2.6515):  68%|██████▊   | 851/1250 [05:09<02:14,  2.96it/s]
Training 1/1 epoch (loss 2.5806):  68%|██████▊   | 851/1250 [05:10<02:14,  2.96it/s]
Training 1/1 epoch (loss 2.5806):  68%|██████▊   | 852/1250 [05:10<02:11,  3.02it/s]
Training 1/1 epoch (loss 2.9495):  68%|██████▊   | 852/1250 [05:10<02:11,  3.02it/s]
Training 1/1 epoch (loss 2.9495):  68%|██████▊   | 853/1250 [05:10<02:09,  3.07it/s]
Training 1/1 epoch (loss 2.6416):  68%|██████▊   | 853/1250 [05:10<02:09,  3.07it/s]
Training 1/1 epoch (loss 2.6416):  68%|██████▊   | 854/1250 [05:10<02:14,  2.94it/s]
Training 1/1 epoch (loss 2.8636):  68%|██████▊   | 854/1250 [05:11<02:14,  2.94it/s]
Training 1/1 epoch (loss 2.8636):  68%|██████▊   | 855/1250 [05:11<02:10,  3.03it/s]
Training 1/1 epoch (loss 2.4451):  68%|██████▊   | 855/1250 [05:11<02:10,  3.03it/s]
Training 1/1 epoch (loss 2.4451):  68%|██████▊   | 856/1250 [05:11<02:13,  2.95it/s]
Training 1/1 epoch (loss 2.7285):  68%|██████▊   | 856/1250 [05:12<02:13,  2.95it/s]
Training 1/1 epoch (loss 2.7285):  69%|██████▊   | 857/1250 [05:12<02:18,  2.83it/s]
Training 1/1 epoch (loss 2.6827):  69%|██████▊   | 857/1250 [05:12<02:18,  2.83it/s]
Training 1/1 epoch (loss 2.6827):  69%|██████▊   | 858/1250 [05:12<02:13,  2.95it/s]
Training 1/1 epoch (loss 2.6798):  69%|██████▊   | 858/1250 [05:12<02:13,  2.95it/s]
Training 1/1 epoch (loss 2.6798):  69%|██████▊   | 859/1250 [05:12<02:14,  2.90it/s]
Training 1/1 epoch (loss 2.7341):  69%|██████▊   | 859/1250 [05:13<02:14,  2.90it/s]
Training 1/1 epoch (loss 2.7341):  69%|██████▉   | 860/1250 [05:13<02:12,  2.93it/s]
Training 1/1 epoch (loss 2.8041):  69%|██████▉   | 860/1250 [05:13<02:12,  2.93it/s]
Training 1/1 epoch (loss 2.8041):  69%|██████▉   | 861/1250 [05:13<02:10,  2.97it/s]
Training 1/1 epoch (loss 2.7210):  69%|██████▉   | 861/1250 [05:13<02:10,  2.97it/s]
Training 1/1 epoch (loss 2.7210):  69%|██████▉   | 862/1250 [05:13<02:10,  2.96it/s]
Training 1/1 epoch (loss 2.7602):  69%|██████▉   | 862/1250 [05:14<02:10,  2.96it/s]
Training 1/1 epoch (loss 2.7602):  69%|██████▉   | 863/1250 [05:14<02:12,  2.92it/s]
Training 1/1 epoch (loss 2.7064):  69%|██████▉   | 863/1250 [05:14<02:12,  2.92it/s]
Training 1/1 epoch (loss 2.7064):  69%|██████▉   | 864/1250 [05:14<02:14,  2.87it/s]
Training 1/1 epoch (loss 2.6887):  69%|██████▉   | 864/1250 [05:14<02:14,  2.87it/s]
Training 1/1 epoch (loss 2.6887):  69%|██████▉   | 865/1250 [05:14<02:18,  2.78it/s]
Training 1/1 epoch (loss 2.6178):  69%|██████▉   | 865/1250 [05:15<02:18,  2.78it/s]
Training 1/1 epoch (loss 2.6178):  69%|██████▉   | 866/1250 [05:15<02:20,  2.74it/s]
Training 1/1 epoch (loss 2.7494):  69%|██████▉   | 866/1250 [05:15<02:20,  2.74it/s]
Training 1/1 epoch (loss 2.7494):  69%|██████▉   | 867/1250 [05:15<02:14,  2.85it/s]
Training 1/1 epoch (loss 2.9886):  69%|██████▉   | 867/1250 [05:15<02:14,  2.85it/s]
Training 1/1 epoch (loss 2.9886):  69%|██████▉   | 868/1250 [05:15<02:08,  2.98it/s]
Training 1/1 epoch (loss 2.5916):  69%|██████▉   | 868/1250 [05:16<02:08,  2.98it/s]
Training 1/1 epoch (loss 2.5916):  70%|██████▉   | 869/1250 [05:16<02:11,  2.89it/s]
Training 1/1 epoch (loss 2.5591):  70%|██████▉   | 869/1250 [05:16<02:11,  2.89it/s]
Training 1/1 epoch (loss 2.5591):  70%|██████▉   | 870/1250 [05:16<02:08,  2.95it/s]
Training 1/1 epoch (loss 2.6214):  70%|██████▉   | 870/1250 [05:16<02:08,  2.95it/s]
Training 1/1 epoch (loss 2.6214):  70%|██████▉   | 871/1250 [05:16<02:04,  3.05it/s]
Training 1/1 epoch (loss 2.7169):  70%|██████▉   | 871/1250 [05:17<02:04,  3.05it/s]
Training 1/1 epoch (loss 2.7169):  70%|██████▉   | 872/1250 [05:17<02:13,  2.83it/s]
Training 1/1 epoch (loss 2.9122):  70%|██████▉   | 872/1250 [05:17<02:13,  2.83it/s]
Training 1/1 epoch (loss 2.9122):  70%|██████▉   | 873/1250 [05:17<02:15,  2.79it/s]
Training 1/1 epoch (loss 2.6920):  70%|██████▉   | 873/1250 [05:17<02:15,  2.79it/s]
Training 1/1 epoch (loss 2.6920):  70%|██████▉   | 874/1250 [05:17<02:11,  2.85it/s]
Training 1/1 epoch (loss 2.7603):  70%|██████▉   | 874/1250 [05:18<02:11,  2.85it/s]
Training 1/1 epoch (loss 2.7603):  70%|███████   | 875/1250 [05:18<02:21,  2.66it/s]
Training 1/1 epoch (loss 2.8047):  70%|███████   | 875/1250 [05:18<02:21,  2.66it/s]
Training 1/1 epoch (loss 2.8047):  70%|███████   | 876/1250 [05:18<02:16,  2.73it/s]
Training 1/1 epoch (loss 2.8655):  70%|███████   | 876/1250 [05:19<02:16,  2.73it/s]
Training 1/1 epoch (loss 2.8655):  70%|███████   | 877/1250 [05:19<02:16,  2.74it/s]
Training 1/1 epoch (loss 2.9794):  70%|███████   | 877/1250 [05:19<02:16,  2.74it/s]
Training 1/1 epoch (loss 2.9794):  70%|███████   | 878/1250 [05:19<02:08,  2.90it/s]
Training 1/1 epoch (loss 2.7757):  70%|███████   | 878/1250 [05:19<02:08,  2.90it/s]
Training 1/1 epoch (loss 2.7757):  70%|███████   | 879/1250 [05:19<02:10,  2.84it/s]
Training 1/1 epoch (loss 2.8580):  70%|███████   | 879/1250 [05:20<02:10,  2.84it/s]
Training 1/1 epoch (loss 2.8580):  70%|███████   | 880/1250 [05:20<02:13,  2.78it/s]
Training 1/1 epoch (loss 2.6340):  70%|███████   | 880/1250 [05:20<02:13,  2.78it/s]
Training 1/1 epoch (loss 2.6340):  70%|███████   | 881/1250 [05:20<02:17,  2.68it/s]
Training 1/1 epoch (loss 2.7345):  70%|███████   | 881/1250 [05:20<02:17,  2.68it/s]
Training 1/1 epoch (loss 2.7345):  71%|███████   | 882/1250 [05:20<02:14,  2.73it/s]
Training 1/1 epoch (loss 2.8713):  71%|███████   | 882/1250 [05:21<02:14,  2.73it/s]
Training 1/1 epoch (loss 2.8713):  71%|███████   | 883/1250 [05:21<02:12,  2.78it/s]
Training 1/1 epoch (loss 2.8173):  71%|███████   | 883/1250 [05:21<02:12,  2.78it/s]
Training 1/1 epoch (loss 2.8173):  71%|███████   | 884/1250 [05:21<02:08,  2.86it/s]
Training 1/1 epoch (loss 2.6738):  71%|███████   | 884/1250 [05:21<02:08,  2.86it/s]
Training 1/1 epoch (loss 2.6738):  71%|███████   | 885/1250 [05:21<02:04,  2.92it/s]
Training 1/1 epoch (loss 2.7872):  71%|███████   | 885/1250 [05:22<02:04,  2.92it/s]
Training 1/1 epoch (loss 2.7872):  71%|███████   | 886/1250 [05:22<02:02,  2.96it/s]
Training 1/1 epoch (loss 2.7190):  71%|███████   | 886/1250 [05:22<02:02,  2.96it/s]
Training 1/1 epoch (loss 2.7190):  71%|███████   | 887/1250 [05:22<02:00,  3.01it/s]
Training 1/1 epoch (loss 2.6603):  71%|███████   | 887/1250 [05:22<02:00,  3.01it/s]
Training 1/1 epoch (loss 2.6603):  71%|███████   | 888/1250 [05:22<02:03,  2.92it/s]
Training 1/1 epoch (loss 2.7479):  71%|███████   | 888/1250 [05:23<02:03,  2.92it/s]
Training 1/1 epoch (loss 2.7479):  71%|███████   | 889/1250 [05:23<02:02,  2.94it/s]
Training 1/1 epoch (loss 2.7355):  71%|███████   | 889/1250 [05:23<02:02,  2.94it/s]
Training 1/1 epoch (loss 2.7355):  71%|███████   | 890/1250 [05:23<02:11,  2.73it/s]
Training 1/1 epoch (loss 2.8962):  71%|███████   | 890/1250 [05:23<02:11,  2.73it/s]
Training 1/1 epoch (loss 2.8962):  71%|███████▏  | 891/1250 [05:23<02:09,  2.76it/s]
Training 1/1 epoch (loss 2.7229):  71%|███████▏  | 891/1250 [05:24<02:09,  2.76it/s]
Training 1/1 epoch (loss 2.7229):  71%|███████▏  | 892/1250 [05:24<02:13,  2.68it/s]
Training 1/1 epoch (loss 2.5737):  71%|███████▏  | 892/1250 [05:24<02:13,  2.68it/s]
Training 1/1 epoch (loss 2.5737):  71%|███████▏  | 893/1250 [05:24<02:14,  2.66it/s]
Training 1/1 epoch (loss 2.5473):  71%|███████▏  | 893/1250 [05:25<02:14,  2.66it/s]
Training 1/1 epoch (loss 2.5473):  72%|███████▏  | 894/1250 [05:25<02:13,  2.66it/s]
Training 1/1 epoch (loss 3.0634):  72%|███████▏  | 894/1250 [05:25<02:13,  2.66it/s]
Training 1/1 epoch (loss 3.0634):  72%|███████▏  | 895/1250 [05:25<02:08,  2.76it/s]
Training 1/1 epoch (loss 2.4401):  72%|███████▏  | 895/1250 [05:25<02:08,  2.76it/s]
Training 1/1 epoch (loss 2.4401):  72%|███████▏  | 896/1250 [05:25<02:03,  2.87it/s]
Training 1/1 epoch (loss 2.6763):  72%|███████▏  | 896/1250 [05:26<02:03,  2.87it/s]
Training 1/1 epoch (loss 2.6763):  72%|███████▏  | 897/1250 [05:26<02:04,  2.84it/s]
Training 1/1 epoch (loss 2.8189):  72%|███████▏  | 897/1250 [05:26<02:04,  2.84it/s]
Training 1/1 epoch (loss 2.8189):  72%|███████▏  | 898/1250 [05:26<02:05,  2.82it/s]
Training 1/1 epoch (loss 2.7895):  72%|███████▏  | 898/1250 [05:26<02:05,  2.82it/s]
Training 1/1 epoch (loss 2.7895):  72%|███████▏  | 899/1250 [05:26<02:07,  2.74it/s]
Training 1/1 epoch (loss 2.9235):  72%|███████▏  | 899/1250 [05:27<02:07,  2.74it/s]
Training 1/1 epoch (loss 2.9235):  72%|███████▏  | 900/1250 [05:27<02:10,  2.67it/s]
Training 1/1 epoch (loss 2.8328):  72%|███████▏  | 900/1250 [05:27<02:10,  2.67it/s]
Training 1/1 epoch (loss 2.8328):  72%|███████▏  | 901/1250 [05:27<02:05,  2.77it/s]
Training 1/1 epoch (loss 2.7728):  72%|███████▏  | 901/1250 [05:27<02:05,  2.77it/s]
Training 1/1 epoch (loss 2.7728):  72%|███████▏  | 902/1250 [05:27<01:58,  2.93it/s]
Training 1/1 epoch (loss 2.7290):  72%|███████▏  | 902/1250 [05:28<01:58,  2.93it/s]
Training 1/1 epoch (loss 2.7290):  72%|███████▏  | 903/1250 [05:28<02:13,  2.60it/s]
Training 1/1 epoch (loss 2.7892):  72%|███████▏  | 903/1250 [05:28<02:13,  2.60it/s]
Training 1/1 epoch (loss 2.7892):  72%|███████▏  | 904/1250 [05:28<02:28,  2.33it/s]
Training 1/1 epoch (loss 2.6401):  72%|███████▏  | 904/1250 [05:29<02:28,  2.33it/s]
Training 1/1 epoch (loss 2.6401):  72%|███████▏  | 905/1250 [05:29<02:19,  2.48it/s]
Training 1/1 epoch (loss 2.6162):  72%|███████▏  | 905/1250 [05:29<02:19,  2.48it/s]
Training 1/1 epoch (loss 2.6162):  72%|███████▏  | 906/1250 [05:29<02:11,  2.62it/s]
Training 1/1 epoch (loss 2.5979):  72%|███████▏  | 906/1250 [05:29<02:11,  2.62it/s]
Training 1/1 epoch (loss 2.5979):  73%|███████▎  | 907/1250 [05:29<02:09,  2.64it/s]
Training 1/1 epoch (loss 2.5807):  73%|███████▎  | 907/1250 [05:30<02:09,  2.64it/s]
Training 1/1 epoch (loss 2.5807):  73%|███████▎  | 908/1250 [05:30<02:06,  2.69it/s]
Training 1/1 epoch (loss 2.8714):  73%|███████▎  | 908/1250 [05:30<02:06,  2.69it/s]
Training 1/1 epoch (loss 2.8714):  73%|███████▎  | 909/1250 [05:30<02:03,  2.76it/s]
Training 1/1 epoch (loss 2.6463):  73%|███████▎  | 909/1250 [05:30<02:03,  2.76it/s]
Training 1/1 epoch (loss 2.6463):  73%|███████▎  | 910/1250 [05:30<01:58,  2.87it/s]
Training 1/1 epoch (loss 2.5270):  73%|███████▎  | 910/1250 [05:31<01:58,  2.87it/s]
Training 1/1 epoch (loss 2.5270):  73%|███████▎  | 911/1250 [05:31<01:58,  2.85it/s]
Training 1/1 epoch (loss 2.7916):  73%|███████▎  | 911/1250 [05:31<01:58,  2.85it/s]
Training 1/1 epoch (loss 2.7916):  73%|███████▎  | 912/1250 [05:31<01:58,  2.86it/s]
Training 1/1 epoch (loss 2.5609):  73%|███████▎  | 912/1250 [05:32<01:58,  2.86it/s]
Training 1/1 epoch (loss 2.5609):  73%|███████▎  | 913/1250 [05:32<02:04,  2.70it/s]
Training 1/1 epoch (loss 2.6735):  73%|███████▎  | 913/1250 [05:32<02:04,  2.70it/s]
Training 1/1 epoch (loss 2.6735):  73%|███████▎  | 914/1250 [05:32<02:01,  2.77it/s]
Training 1/1 epoch (loss 2.8230):  73%|███████▎  | 914/1250 [05:32<02:01,  2.77it/s]
Training 1/1 epoch (loss 2.8230):  73%|███████▎  | 915/1250 [05:32<02:03,  2.71it/s]
Training 1/1 epoch (loss 2.7885):  73%|███████▎  | 915/1250 [05:33<02:03,  2.71it/s]
Training 1/1 epoch (loss 2.7885):  73%|███████▎  | 916/1250 [05:33<02:05,  2.66it/s]
Training 1/1 epoch (loss 2.5354):  73%|███████▎  | 916/1250 [05:33<02:05,  2.66it/s]
Training 1/1 epoch (loss 2.5354):  73%|███████▎  | 917/1250 [05:33<02:02,  2.71it/s]
Training 1/1 epoch (loss 2.9062):  73%|███████▎  | 917/1250 [05:33<02:02,  2.71it/s]
Training 1/1 epoch (loss 2.9062):  73%|███████▎  | 918/1250 [05:33<01:56,  2.85it/s]
Training 1/1 epoch (loss 2.6448):  73%|███████▎  | 918/1250 [05:34<01:56,  2.85it/s]
Training 1/1 epoch (loss 2.6448):  74%|███████▎  | 919/1250 [05:34<01:58,  2.79it/s]
Training 1/1 epoch (loss 2.8303):  74%|███████▎  | 919/1250 [05:34<01:58,  2.79it/s]
Training 1/1 epoch (loss 2.8303):  74%|███████▎  | 920/1250 [05:34<02:04,  2.65it/s]
Training 1/1 epoch (loss 2.7136):  74%|███████▎  | 920/1250 [05:35<02:04,  2.65it/s]
Training 1/1 epoch (loss 2.7136):  74%|███████▎  | 921/1250 [05:35<02:05,  2.62it/s]
Training 1/1 epoch (loss 2.6686):  74%|███████▎  | 921/1250 [05:35<02:05,  2.62it/s]
Training 1/1 epoch (loss 2.6686):  74%|███████▍  | 922/1250 [05:35<01:59,  2.75it/s]
Training 1/1 epoch (loss 2.6389):  74%|███████▍  | 922/1250 [05:35<01:59,  2.75it/s]
Training 1/1 epoch (loss 2.6389):  74%|███████▍  | 923/1250 [05:35<01:58,  2.76it/s]
Training 1/1 epoch (loss 2.9130):  74%|███████▍  | 923/1250 [05:36<01:58,  2.76it/s]
Training 1/1 epoch (loss 2.9130):  74%|███████▍  | 924/1250 [05:36<01:53,  2.88it/s]
Training 1/1 epoch (loss 2.7648):  74%|███████▍  | 924/1250 [05:36<01:53,  2.88it/s]
Training 1/1 epoch (loss 2.7648):  74%|███████▍  | 925/1250 [05:36<01:50,  2.93it/s]
Training 1/1 epoch (loss 2.7511):  74%|███████▍  | 925/1250 [05:36<01:50,  2.93it/s]
Training 1/1 epoch (loss 2.7511):  74%|███████▍  | 926/1250 [05:36<01:52,  2.87it/s]
Training 1/1 epoch (loss 2.6432):  74%|███████▍  | 926/1250 [05:37<01:52,  2.87it/s]
Training 1/1 epoch (loss 2.6432):  74%|███████▍  | 927/1250 [05:37<01:51,  2.90it/s]
Training 1/1 epoch (loss 2.9608):  74%|███████▍  | 927/1250 [05:37<01:51,  2.90it/s]
Training 1/1 epoch (loss 2.9608):  74%|███████▍  | 928/1250 [05:37<01:59,  2.69it/s]
Training 1/1 epoch (loss 2.8336):  74%|███████▍  | 928/1250 [05:37<01:59,  2.69it/s]
Training 1/1 epoch (loss 2.8336):  74%|███████▍  | 929/1250 [05:37<02:01,  2.65it/s]
Training 1/1 epoch (loss 2.9421):  74%|███████▍  | 929/1250 [05:38<02:01,  2.65it/s]
Training 1/1 epoch (loss 2.9421):  74%|███████▍  | 930/1250 [05:38<01:55,  2.76it/s]
Training 1/1 epoch (loss 2.8252):  74%|███████▍  | 930/1250 [05:38<01:55,  2.76it/s]
Training 1/1 epoch (loss 2.8252):  74%|███████▍  | 931/1250 [05:38<01:52,  2.83it/s]
Training 1/1 epoch (loss 2.8008):  74%|███████▍  | 931/1250 [05:38<01:52,  2.83it/s]
Training 1/1 epoch (loss 2.8008):  75%|███████▍  | 932/1250 [05:38<01:51,  2.86it/s]
Training 1/1 epoch (loss 2.7679):  75%|███████▍  | 932/1250 [05:39<01:51,  2.86it/s]
Training 1/1 epoch (loss 2.7679):  75%|███████▍  | 933/1250 [05:39<01:51,  2.84it/s]
Training 1/1 epoch (loss 2.6153):  75%|███████▍  | 933/1250 [05:39<01:51,  2.84it/s]
Training 1/1 epoch (loss 2.6153):  75%|███████▍  | 934/1250 [05:39<01:49,  2.89it/s]
Training 1/1 epoch (loss 2.6405):  75%|███████▍  | 934/1250 [05:39<01:49,  2.89it/s]
Training 1/1 epoch (loss 2.6405):  75%|███████▍  | 935/1250 [05:39<01:49,  2.88it/s]
Training 1/1 epoch (loss 2.7853):  75%|███████▍  | 935/1250 [05:40<01:49,  2.88it/s]
Training 1/1 epoch (loss 2.7853):  75%|███████▍  | 936/1250 [05:40<01:50,  2.84it/s]
Training 1/1 epoch (loss 2.5449):  75%|███████▍  | 936/1250 [05:40<01:50,  2.84it/s]
Training 1/1 epoch (loss 2.5449):  75%|███████▍  | 937/1250 [05:40<01:49,  2.86it/s]
Training 1/1 epoch (loss 2.6389):  75%|███████▍  | 937/1250 [05:41<01:49,  2.86it/s]
Training 1/1 epoch (loss 2.6389):  75%|███████▌  | 938/1250 [05:41<01:52,  2.77it/s]
Training 1/1 epoch (loss 2.7939):  75%|███████▌  | 938/1250 [05:41<01:52,  2.77it/s]
Training 1/1 epoch (loss 2.7939):  75%|███████▌  | 939/1250 [05:41<01:46,  2.91it/s]
Training 1/1 epoch (loss 2.7351):  75%|███████▌  | 939/1250 [05:41<01:46,  2.91it/s]
Training 1/1 epoch (loss 2.7351):  75%|███████▌  | 940/1250 [05:41<01:45,  2.93it/s]
Training 1/1 epoch (loss 2.7076):  75%|███████▌  | 940/1250 [05:42<01:45,  2.93it/s]
Training 1/1 epoch (loss 2.7076):  75%|███████▌  | 941/1250 [05:42<01:47,  2.89it/s]
Training 1/1 epoch (loss 2.7065):  75%|███████▌  | 941/1250 [05:42<01:47,  2.89it/s]
Training 1/1 epoch (loss 2.7065):  75%|███████▌  | 942/1250 [05:42<01:48,  2.85it/s]
Training 1/1 epoch (loss 2.5334):  75%|███████▌  | 942/1250 [05:42<01:48,  2.85it/s]
Training 1/1 epoch (loss 2.5334):  75%|███████▌  | 943/1250 [05:42<01:51,  2.75it/s]
Training 1/1 epoch (loss 2.4604):  75%|███████▌  | 943/1250 [05:43<01:51,  2.75it/s]
Training 1/1 epoch (loss 2.4604):  76%|███████▌  | 944/1250 [05:43<01:50,  2.77it/s]
Training 1/1 epoch (loss 2.7037):  76%|███████▌  | 944/1250 [05:43<01:50,  2.77it/s]
Training 1/1 epoch (loss 2.7037):  76%|███████▌  | 945/1250 [05:43<01:49,  2.79it/s]
Training 1/1 epoch (loss 2.7576):  76%|███████▌  | 945/1250 [05:43<01:49,  2.79it/s]
Training 1/1 epoch (loss 2.7576):  76%|███████▌  | 946/1250 [05:43<01:49,  2.78it/s]
Training 1/1 epoch (loss 2.6594):  76%|███████▌  | 946/1250 [05:44<01:49,  2.78it/s]
Training 1/1 epoch (loss 2.6594):  76%|███████▌  | 947/1250 [05:44<01:51,  2.73it/s]
Training 1/1 epoch (loss 2.6088):  76%|███████▌  | 947/1250 [05:44<01:51,  2.73it/s]
Training 1/1 epoch (loss 2.6088):  76%|███████▌  | 948/1250 [05:44<01:48,  2.79it/s]
Training 1/1 epoch (loss 2.7690):  76%|███████▌  | 948/1250 [05:45<01:48,  2.79it/s]
Training 1/1 epoch (loss 2.7690):  76%|███████▌  | 949/1250 [05:45<01:53,  2.65it/s]
Training 1/1 epoch (loss 2.5939):  76%|███████▌  | 949/1250 [05:45<01:53,  2.65it/s]
Training 1/1 epoch (loss 2.5939):  76%|███████▌  | 950/1250 [05:45<01:52,  2.66it/s]
Training 1/1 epoch (loss 2.5322):  76%|███████▌  | 950/1250 [05:45<01:52,  2.66it/s]
Training 1/1 epoch (loss 2.5322):  76%|███████▌  | 951/1250 [05:45<01:47,  2.78it/s]
Training 1/1 epoch (loss 2.8348):  76%|███████▌  | 951/1250 [05:46<01:47,  2.78it/s]
Training 1/1 epoch (loss 2.8348):  76%|███████▌  | 952/1250 [05:46<01:46,  2.79it/s]
Training 1/1 epoch (loss 2.5795):  76%|███████▌  | 952/1250 [05:46<01:46,  2.79it/s]
Training 1/1 epoch (loss 2.5795):  76%|███████▌  | 953/1250 [05:46<01:46,  2.78it/s]
Training 1/1 epoch (loss 2.6889):  76%|███████▌  | 953/1250 [05:46<01:46,  2.78it/s]
Training 1/1 epoch (loss 2.6889):  76%|███████▋  | 954/1250 [05:46<01:47,  2.76it/s]
Training 1/1 epoch (loss 2.6685):  76%|███████▋  | 954/1250 [05:47<01:47,  2.76it/s]
Training 1/1 epoch (loss 2.6685):  76%|███████▋  | 955/1250 [05:47<01:46,  2.76it/s]
Training 1/1 epoch (loss 2.7345):  76%|███████▋  | 955/1250 [05:47<01:46,  2.76it/s]
Training 1/1 epoch (loss 2.7345):  76%|███████▋  | 956/1250 [05:47<01:41,  2.91it/s]
Training 1/1 epoch (loss 2.9136):  76%|███████▋  | 956/1250 [05:47<01:41,  2.91it/s]
Training 1/1 epoch (loss 2.9136):  77%|███████▋  | 957/1250 [05:47<01:47,  2.73it/s]
Training 1/1 epoch (loss 2.6790):  77%|███████▋  | 957/1250 [05:48<01:47,  2.73it/s]
Training 1/1 epoch (loss 2.6790):  77%|███████▋  | 958/1250 [05:48<01:47,  2.72it/s]
Training 1/1 epoch (loss 2.9678):  77%|███████▋  | 958/1250 [05:48<01:47,  2.72it/s]
Training 1/1 epoch (loss 2.9678):  77%|███████▋  | 959/1250 [05:48<01:44,  2.78it/s]
Training 1/1 epoch (loss 2.4710):  77%|███████▋  | 959/1250 [05:48<01:44,  2.78it/s]
Training 1/1 epoch (loss 2.4710):  77%|███████▋  | 960/1250 [05:48<01:44,  2.79it/s]
Training 1/1 epoch (loss 2.4875):  77%|███████▋  | 960/1250 [05:49<01:44,  2.79it/s]
Training 1/1 epoch (loss 2.4875):  77%|███████▋  | 961/1250 [05:49<01:43,  2.80it/s]
Training 1/1 epoch (loss 2.4818):  77%|███████▋  | 961/1250 [05:49<01:43,  2.80it/s]
Training 1/1 epoch (loss 2.4818):  77%|███████▋  | 962/1250 [05:49<01:41,  2.85it/s]
Training 1/1 epoch (loss 2.8613):  77%|███████▋  | 962/1250 [05:49<01:41,  2.85it/s]
Training 1/1 epoch (loss 2.8613):  77%|███████▋  | 963/1250 [05:49<01:39,  2.90it/s]
Training 1/1 epoch (loss 2.8231):  77%|███████▋  | 963/1250 [05:50<01:39,  2.90it/s]
Training 1/1 epoch (loss 2.8231):  77%|███████▋  | 964/1250 [05:50<01:38,  2.90it/s]
Training 1/1 epoch (loss 2.4747):  77%|███████▋  | 964/1250 [05:50<01:38,  2.90it/s]
Training 1/1 epoch (loss 2.4747):  77%|███████▋  | 965/1250 [05:50<01:36,  2.95it/s]
Training 1/1 epoch (loss 2.6964):  77%|███████▋  | 965/1250 [05:50<01:36,  2.95it/s]
Training 1/1 epoch (loss 2.6964):  77%|███████▋  | 966/1250 [05:51<01:36,  2.93it/s]
Training 1/1 epoch (loss 2.6514):  77%|███████▋  | 966/1250 [05:51<01:36,  2.93it/s]
Training 1/1 epoch (loss 2.6514):  77%|███████▋  | 967/1250 [05:51<01:33,  3.02it/s]
Training 1/1 epoch (loss 2.7059):  77%|███████▋  | 967/1250 [05:51<01:33,  3.02it/s]
Training 1/1 epoch (loss 2.7059):  77%|███████▋  | 968/1250 [05:51<01:35,  2.95it/s]
Training 1/1 epoch (loss 3.0112):  77%|███████▋  | 968/1250 [05:52<01:35,  2.95it/s]
Training 1/1 epoch (loss 3.0112):  78%|███████▊  | 969/1250 [05:52<01:37,  2.87it/s]
Training 1/1 epoch (loss 2.6039):  78%|███████▊  | 969/1250 [05:52<01:37,  2.87it/s]
Training 1/1 epoch (loss 2.6039):  78%|███████▊  | 970/1250 [05:52<01:35,  2.94it/s]
Training 1/1 epoch (loss 3.0167):  78%|███████▊  | 970/1250 [05:52<01:35,  2.94it/s]
Training 1/1 epoch (loss 3.0167):  78%|███████▊  | 971/1250 [05:52<01:35,  2.91it/s]
Training 1/1 epoch (loss 2.7090):  78%|███████▊  | 971/1250 [05:53<01:35,  2.91it/s]
Training 1/1 epoch (loss 2.7090):  78%|███████▊  | 972/1250 [05:53<01:39,  2.79it/s]
Training 1/1 epoch (loss 2.7744):  78%|███████▊  | 972/1250 [05:53<01:39,  2.79it/s]
Training 1/1 epoch (loss 2.7744):  78%|███████▊  | 973/1250 [05:53<01:55,  2.39it/s]
Training 1/1 epoch (loss 2.5755):  78%|███████▊  | 973/1250 [05:54<01:55,  2.39it/s]
Training 1/1 epoch (loss 2.5755):  78%|███████▊  | 974/1250 [05:54<01:51,  2.47it/s]
Training 1/1 epoch (loss 2.6999):  78%|███████▊  | 974/1250 [05:54<01:51,  2.47it/s]
Training 1/1 epoch (loss 2.6999):  78%|███████▊  | 975/1250 [05:54<01:48,  2.52it/s]
Training 1/1 epoch (loss 2.5906):  78%|███████▊  | 975/1250 [05:54<01:48,  2.52it/s]
Training 1/1 epoch (loss 2.5906):  78%|███████▊  | 976/1250 [05:54<01:50,  2.48it/s]
Training 1/1 epoch (loss 2.7943):  78%|███████▊  | 976/1250 [05:55<01:50,  2.48it/s]
Training 1/1 epoch (loss 2.7943):  78%|███████▊  | 977/1250 [05:55<01:47,  2.54it/s]
Training 1/1 epoch (loss 2.7930):  78%|███████▊  | 977/1250 [05:55<01:47,  2.54it/s]
Training 1/1 epoch (loss 2.7930):  78%|███████▊  | 978/1250 [05:55<01:43,  2.63it/s]
Training 1/1 epoch (loss 2.9794):  78%|███████▊  | 978/1250 [05:55<01:43,  2.63it/s]
Training 1/1 epoch (loss 2.9794):  78%|███████▊  | 979/1250 [05:55<01:40,  2.71it/s]
Training 1/1 epoch (loss 2.7873):  78%|███████▊  | 979/1250 [05:56<01:40,  2.71it/s]
Training 1/1 epoch (loss 2.7873):  78%|███████▊  | 980/1250 [05:56<01:39,  2.73it/s]
Training 1/1 epoch (loss 2.7252):  78%|███████▊  | 980/1250 [05:56<01:39,  2.73it/s]
Training 1/1 epoch (loss 2.7252):  78%|███████▊  | 981/1250 [05:56<01:34,  2.83it/s]
Training 1/1 epoch (loss 2.7612):  78%|███████▊  | 981/1250 [05:56<01:34,  2.83it/s]
Training 1/1 epoch (loss 2.7612):  79%|███████▊  | 982/1250 [05:56<01:35,  2.82it/s]
Training 1/1 epoch (loss 2.7707):  79%|███████▊  | 982/1250 [05:57<01:35,  2.82it/s]
Training 1/1 epoch (loss 2.7707):  79%|███████▊  | 983/1250 [05:57<01:34,  2.81it/s]
Training 1/1 epoch (loss 2.7729):  79%|███████▊  | 983/1250 [05:57<01:34,  2.81it/s]
Training 1/1 epoch (loss 2.7729):  79%|███████▊  | 984/1250 [05:57<01:31,  2.89it/s]
Training 1/1 epoch (loss 2.8742):  79%|███████▊  | 984/1250 [05:57<01:31,  2.89it/s]
Training 1/1 epoch (loss 2.8742):  79%|███████▉  | 985/1250 [05:57<01:34,  2.81it/s]
Training 1/1 epoch (loss 2.5919):  79%|███████▉  | 985/1250 [05:58<01:34,  2.81it/s]
Training 1/1 epoch (loss 2.5919):  79%|███████▉  | 986/1250 [05:58<01:53,  2.32it/s]
Training 1/1 epoch (loss 2.7192):  79%|███████▉  | 986/1250 [05:59<01:53,  2.32it/s]
Training 1/1 epoch (loss 2.7192):  79%|███████▉  | 987/1250 [05:59<01:51,  2.35it/s]
Training 1/1 epoch (loss 2.6991):  79%|███████▉  | 987/1250 [05:59<01:51,  2.35it/s]
Training 1/1 epoch (loss 2.6991):  79%|███████▉  | 988/1250 [05:59<01:44,  2.51it/s]
Training 1/1 epoch (loss 2.9396):  79%|███████▉  | 988/1250 [05:59<01:44,  2.51it/s]
Training 1/1 epoch (loss 2.9396):  79%|███████▉  | 989/1250 [05:59<01:35,  2.72it/s]
Training 1/1 epoch (loss 2.6126):  79%|███████▉  | 989/1250 [06:00<01:35,  2.72it/s]
Training 1/1 epoch (loss 2.6126):  79%|███████▉  | 990/1250 [06:00<01:35,  2.72it/s]
Training 1/1 epoch (loss 2.6447):  79%|███████▉  | 990/1250 [06:00<01:35,  2.72it/s]
Training 1/1 epoch (loss 2.6447):  79%|███████▉  | 991/1250 [06:00<01:32,  2.79it/s]
Training 1/1 epoch (loss 2.3736):  79%|███████▉  | 991/1250 [06:00<01:32,  2.79it/s]
Training 1/1 epoch (loss 2.3736):  79%|███████▉  | 992/1250 [06:00<01:31,  2.82it/s]
Training 1/1 epoch (loss 2.6367):  79%|███████▉  | 992/1250 [06:01<01:31,  2.82it/s]
Training 1/1 epoch (loss 2.6367):  79%|███████▉  | 993/1250 [06:01<01:29,  2.88it/s]
Training 1/1 epoch (loss 2.5600):  79%|███████▉  | 993/1250 [06:01<01:29,  2.88it/s]
Training 1/1 epoch (loss 2.5600):  80%|███████▉  | 994/1250 [06:01<01:27,  2.94it/s]
Training 1/1 epoch (loss 2.4748):  80%|███████▉  | 994/1250 [06:01<01:27,  2.94it/s]
Training 1/1 epoch (loss 2.4748):  80%|███████▉  | 995/1250 [06:01<01:26,  2.94it/s]
Training 1/1 epoch (loss 2.6628):  80%|███████▉  | 995/1250 [06:02<01:26,  2.94it/s]
Training 1/1 epoch (loss 2.6628):  80%|███████▉  | 996/1250 [06:02<01:25,  2.98it/s]
Training 1/1 epoch (loss 2.8017):  80%|███████▉  | 996/1250 [06:02<01:25,  2.98it/s]
Training 1/1 epoch (loss 2.8017):  80%|███████▉  | 997/1250 [06:02<01:24,  2.99it/s]
Training 1/1 epoch (loss 2.7231):  80%|███████▉  | 997/1250 [06:02<01:24,  2.99it/s]
Training 1/1 epoch (loss 2.7231):  80%|███████▉  | 998/1250 [06:02<01:25,  2.95it/s]
Training 1/1 epoch (loss 2.6633):  80%|███████▉  | 998/1250 [06:03<01:25,  2.95it/s]
Training 1/1 epoch (loss 2.6633):  80%|███████▉  | 999/1250 [06:03<01:26,  2.90it/s]
Training 1/1 epoch (loss 2.6786):  80%|███████▉  | 999/1250 [06:03<01:26,  2.90it/s]
Training 1/1 epoch (loss 2.6786):  80%|████████  | 1000/1250 [06:03<01:26,  2.88it/s]
Training 1/1 epoch (loss 2.7935):  80%|████████  | 1000/1250 [06:03<01:26,  2.88it/s]
Training 1/1 epoch (loss 2.7935):  80%|████████  | 1001/1250 [06:03<01:34,  2.63it/s]
Training 1/1 epoch (loss 2.5360):  80%|████████  | 1001/1250 [06:04<01:34,  2.63it/s]
Training 1/1 epoch (loss 2.5360):  80%|████████  | 1002/1250 [06:04<01:30,  2.76it/s]
Training 1/1 epoch (loss 2.6398):  80%|████████  | 1002/1250 [06:04<01:30,  2.76it/s]
Training 1/1 epoch (loss 2.6398):  80%|████████  | 1003/1250 [06:04<01:29,  2.77it/s]
Training 1/1 epoch (loss 2.5722):  80%|████████  | 1003/1250 [06:04<01:29,  2.77it/s]
Training 1/1 epoch (loss 2.5722):  80%|████████  | 1004/1250 [06:04<01:30,  2.73it/s]
Training 1/1 epoch (loss 2.8345):  80%|████████  | 1004/1250 [06:05<01:30,  2.73it/s]
Training 1/1 epoch (loss 2.8345):  80%|████████  | 1005/1250 [06:05<01:27,  2.79it/s]
Training 1/1 epoch (loss 2.7330):  80%|████████  | 1005/1250 [06:05<01:27,  2.79it/s]
Training 1/1 epoch (loss 2.7330):  80%|████████  | 1006/1250 [06:05<01:26,  2.83it/s]
Training 1/1 epoch (loss 2.7918):  80%|████████  | 1006/1250 [06:05<01:26,  2.83it/s]
Training 1/1 epoch (loss 2.7918):  81%|████████  | 1007/1250 [06:05<01:24,  2.87it/s]
Training 1/1 epoch (loss 2.7334):  81%|████████  | 1007/1250 [06:06<01:24,  2.87it/s]
Training 1/1 epoch (loss 2.7334):  81%|████████  | 1008/1250 [06:06<01:22,  2.92it/s]
Training 1/1 epoch (loss 2.8525):  81%|████████  | 1008/1250 [06:06<01:22,  2.92it/s]
Training 1/1 epoch (loss 2.8525):  81%|████████  | 1009/1250 [06:06<01:21,  2.94it/s]
Training 1/1 epoch (loss 2.7950):  81%|████████  | 1009/1250 [06:06<01:21,  2.94it/s]
Training 1/1 epoch (loss 2.7950):  81%|████████  | 1010/1250 [06:06<01:21,  2.94it/s]
Training 1/1 epoch (loss 2.8791):  81%|████████  | 1010/1250 [06:07<01:21,  2.94it/s]
Training 1/1 epoch (loss 2.8791):  81%|████████  | 1011/1250 [06:07<01:22,  2.90it/s]
Training 1/1 epoch (loss 2.7453):  81%|████████  | 1011/1250 [06:07<01:22,  2.90it/s]
Training 1/1 epoch (loss 2.7453):  81%|████████  | 1012/1250 [06:07<01:21,  2.91it/s]
Training 1/1 epoch (loss 2.5717):  81%|████████  | 1012/1250 [06:07<01:21,  2.91it/s]
Training 1/1 epoch (loss 2.5717):  81%|████████  | 1013/1250 [06:07<01:21,  2.90it/s]
Training 1/1 epoch (loss 2.5567):  81%|████████  | 1013/1250 [06:08<01:21,  2.90it/s]
Training 1/1 epoch (loss 2.5567):  81%|████████  | 1014/1250 [06:08<01:23,  2.82it/s]
Training 1/1 epoch (loss 2.6503):  81%|████████  | 1014/1250 [06:08<01:23,  2.82it/s]
Training 1/1 epoch (loss 2.6503):  81%|████████  | 1015/1250 [06:08<01:22,  2.85it/s]
Training 1/1 epoch (loss 2.7187):  81%|████████  | 1015/1250 [06:09<01:22,  2.85it/s]
Training 1/1 epoch (loss 2.7187):  81%|████████▏ | 1016/1250 [06:09<01:27,  2.67it/s]
Training 1/1 epoch (loss 2.7622):  81%|████████▏ | 1016/1250 [06:09<01:27,  2.67it/s]
Training 1/1 epoch (loss 2.7622):  81%|████████▏ | 1017/1250 [06:09<01:24,  2.75it/s]
Training 1/1 epoch (loss 2.7984):  81%|████████▏ | 1017/1250 [06:09<01:24,  2.75it/s]
Training 1/1 epoch (loss 2.7984):  81%|████████▏ | 1018/1250 [06:09<01:20,  2.88it/s]
Training 1/1 epoch (loss 2.7525):  81%|████████▏ | 1018/1250 [06:10<01:20,  2.88it/s]
Training 1/1 epoch (loss 2.7525):  82%|████████▏ | 1019/1250 [06:10<01:21,  2.84it/s]
Training 1/1 epoch (loss 2.9155):  82%|████████▏ | 1019/1250 [06:10<01:21,  2.84it/s]
Training 1/1 epoch (loss 2.9155):  82%|████████▏ | 1020/1250 [06:10<01:22,  2.78it/s]
Training 1/1 epoch (loss 2.6640):  82%|████████▏ | 1020/1250 [06:10<01:22,  2.78it/s]
Training 1/1 epoch (loss 2.6640):  82%|████████▏ | 1021/1250 [06:10<01:21,  2.81it/s]
Training 1/1 epoch (loss 2.9314):  82%|████████▏ | 1021/1250 [06:11<01:21,  2.81it/s]
Training 1/1 epoch (loss 2.9314):  82%|████████▏ | 1022/1250 [06:11<01:24,  2.69it/s]
Training 1/1 epoch (loss 2.6192):  82%|████████▏ | 1022/1250 [06:11<01:24,  2.69it/s]
Training 1/1 epoch (loss 2.6192):  82%|████████▏ | 1023/1250 [06:11<01:22,  2.74it/s]
Training 1/1 epoch (loss 2.6696):  82%|████████▏ | 1023/1250 [06:12<01:22,  2.74it/s]
Training 1/1 epoch (loss 2.6696):  82%|████████▏ | 1024/1250 [06:12<01:23,  2.71it/s]
Training 1/1 epoch (loss 2.5941):  82%|████████▏ | 1024/1250 [06:12<01:23,  2.71it/s]
Training 1/1 epoch (loss 2.5941):  82%|████████▏ | 1025/1250 [06:12<01:24,  2.67it/s]
Training 1/1 epoch (loss 2.7293):  82%|████████▏ | 1025/1250 [06:12<01:24,  2.67it/s]
Training 1/1 epoch (loss 2.7293):  82%|████████▏ | 1026/1250 [06:12<01:24,  2.66it/s]
Training 1/1 epoch (loss 2.6182):  82%|████████▏ | 1026/1250 [06:13<01:24,  2.66it/s]
Training 1/1 epoch (loss 2.6182):  82%|████████▏ | 1027/1250 [06:13<01:23,  2.67it/s]
Training 1/1 epoch (loss 2.6089):  82%|████████▏ | 1027/1250 [06:13<01:23,  2.67it/s]
Training 1/1 epoch (loss 2.6089):  82%|████████▏ | 1028/1250 [06:13<01:23,  2.66it/s]
Training 1/1 epoch (loss 2.7368):  82%|████████▏ | 1028/1250 [06:13<01:23,  2.66it/s]
Training 1/1 epoch (loss 2.7368):  82%|████████▏ | 1029/1250 [06:13<01:25,  2.60it/s]
Training 1/1 epoch (loss 2.7922):  82%|████████▏ | 1029/1250 [06:14<01:25,  2.60it/s]
Training 1/1 epoch (loss 2.7922):  82%|████████▏ | 1030/1250 [06:14<01:27,  2.51it/s]
Training 1/1 epoch (loss 2.7183):  82%|████████▏ | 1030/1250 [06:14<01:27,  2.51it/s]
Training 1/1 epoch (loss 2.7183):  82%|████████▏ | 1031/1250 [06:14<01:25,  2.55it/s]
Training 1/1 epoch (loss 2.7416):  82%|████████▏ | 1031/1250 [06:15<01:25,  2.55it/s]
Training 1/1 epoch (loss 2.7416):  83%|████████▎ | 1032/1250 [06:15<01:29,  2.44it/s]
Training 1/1 epoch (loss 2.5828):  83%|████████▎ | 1032/1250 [06:15<01:29,  2.44it/s]
Training 1/1 epoch (loss 2.5828):  83%|████████▎ | 1033/1250 [06:15<01:28,  2.44it/s]
Training 1/1 epoch (loss 2.5607):  83%|████████▎ | 1033/1250 [06:15<01:28,  2.44it/s]
Training 1/1 epoch (loss 2.5607):  83%|████████▎ | 1034/1250 [06:15<01:25,  2.54it/s]
Training 1/1 epoch (loss 2.5121):  83%|████████▎ | 1034/1250 [06:16<01:25,  2.54it/s]
Training 1/1 epoch (loss 2.5121):  83%|████████▎ | 1035/1250 [06:16<01:20,  2.68it/s]
Training 1/1 epoch (loss 2.6123):  83%|████████▎ | 1035/1250 [06:16<01:20,  2.68it/s]
Training 1/1 epoch (loss 2.6123):  83%|████████▎ | 1036/1250 [06:16<01:16,  2.81it/s]
Training 1/1 epoch (loss 2.8178):  83%|████████▎ | 1036/1250 [06:16<01:16,  2.81it/s]
Training 1/1 epoch (loss 2.8178):  83%|████████▎ | 1037/1250 [06:16<01:12,  2.95it/s]
Training 1/1 epoch (loss 2.5709):  83%|████████▎ | 1037/1250 [06:17<01:12,  2.95it/s]
Training 1/1 epoch (loss 2.5709):  83%|████████▎ | 1038/1250 [06:17<01:14,  2.86it/s]
Training 1/1 epoch (loss 2.4821):  83%|████████▎ | 1038/1250 [06:17<01:14,  2.86it/s]
Training 1/1 epoch (loss 2.4821):  83%|████████▎ | 1039/1250 [06:17<01:13,  2.87it/s]
Training 1/1 epoch (loss 2.5646):  83%|████████▎ | 1039/1250 [06:18<01:13,  2.87it/s]
Training 1/1 epoch (loss 2.5646):  83%|████████▎ | 1040/1250 [06:18<01:15,  2.77it/s]
Training 1/1 epoch (loss 2.4441):  83%|████████▎ | 1040/1250 [06:18<01:15,  2.77it/s]
Training 1/1 epoch (loss 2.4441):  83%|████████▎ | 1041/1250 [06:18<01:17,  2.69it/s]
Training 1/1 epoch (loss 2.8763):  83%|████████▎ | 1041/1250 [06:18<01:17,  2.69it/s]
Training 1/1 epoch (loss 2.8763):  83%|████████▎ | 1042/1250 [06:18<01:12,  2.85it/s]
Training 1/1 epoch (loss 2.7807):  83%|████████▎ | 1042/1250 [06:19<01:12,  2.85it/s]
Training 1/1 epoch (loss 2.7807):  83%|████████▎ | 1043/1250 [06:19<01:14,  2.76it/s]
Training 1/1 epoch (loss 2.7071):  83%|████████▎ | 1043/1250 [06:19<01:14,  2.76it/s]
Training 1/1 epoch (loss 2.7071):  84%|████████▎ | 1044/1250 [06:19<01:16,  2.71it/s]
Training 1/1 epoch (loss 2.8064):  84%|████████▎ | 1044/1250 [06:19<01:16,  2.71it/s]
Training 1/1 epoch (loss 2.8064):  84%|████████▎ | 1045/1250 [06:19<01:14,  2.74it/s]
Training 1/1 epoch (loss 2.7755):  84%|████████▎ | 1045/1250 [06:20<01:14,  2.74it/s]
Training 1/1 epoch (loss 2.7755):  84%|████████▎ | 1046/1250 [06:20<01:09,  2.93it/s]
Training 1/1 epoch (loss 2.7773):  84%|████████▎ | 1046/1250 [06:20<01:09,  2.93it/s]
Training 1/1 epoch (loss 2.7773):  84%|████████▍ | 1047/1250 [06:20<01:09,  2.91it/s]
Training 1/1 epoch (loss 2.7112):  84%|████████▍ | 1047/1250 [06:20<01:09,  2.91it/s]
Training 1/1 epoch (loss 2.7112):  84%|████████▍ | 1048/1250 [06:20<01:10,  2.85it/s]
Training 1/1 epoch (loss 2.6231):  84%|████████▍ | 1048/1250 [06:21<01:10,  2.85it/s]
Training 1/1 epoch (loss 2.6231):  84%|████████▍ | 1049/1250 [06:21<01:12,  2.78it/s]
Training 1/1 epoch (loss 2.8800):  84%|████████▍ | 1049/1250 [06:21<01:12,  2.78it/s]
Training 1/1 epoch (loss 2.8800):  84%|████████▍ | 1050/1250 [06:21<01:09,  2.87it/s]
Training 1/1 epoch (loss 2.7105):  84%|████████▍ | 1050/1250 [06:21<01:09,  2.87it/s]
Training 1/1 epoch (loss 2.7105):  84%|████████▍ | 1051/1250 [06:21<01:10,  2.80it/s]
Training 1/1 epoch (loss 2.7094):  84%|████████▍ | 1051/1250 [06:22<01:10,  2.80it/s]
Training 1/1 epoch (loss 2.7094):  84%|████████▍ | 1052/1250 [06:22<01:09,  2.86it/s]
Training 1/1 epoch (loss 2.5874):  84%|████████▍ | 1052/1250 [06:22<01:09,  2.86it/s]
Training 1/1 epoch (loss 2.5874):  84%|████████▍ | 1053/1250 [06:22<01:06,  2.98it/s]
Training 1/1 epoch (loss 2.5746):  84%|████████▍ | 1053/1250 [06:22<01:06,  2.98it/s]
Training 1/1 epoch (loss 2.5746):  84%|████████▍ | 1054/1250 [06:22<01:05,  3.02it/s]
Training 1/1 epoch (loss 2.5310):  84%|████████▍ | 1054/1250 [06:23<01:05,  3.02it/s]
Training 1/1 epoch (loss 2.5310):  84%|████████▍ | 1055/1250 [06:23<01:13,  2.66it/s]
Training 1/1 epoch (loss 2.6827):  84%|████████▍ | 1055/1250 [06:23<01:13,  2.66it/s]
Training 1/1 epoch (loss 2.6827):  84%|████████▍ | 1056/1250 [06:23<01:23,  2.33it/s]
Training 1/1 epoch (loss 2.7653):  84%|████████▍ | 1056/1250 [06:24<01:23,  2.33it/s]
Training 1/1 epoch (loss 2.7653):  85%|████████▍ | 1057/1250 [06:24<01:17,  2.48it/s]
Training 1/1 epoch (loss 2.7596):  85%|████████▍ | 1057/1250 [06:24<01:17,  2.48it/s]
Training 1/1 epoch (loss 2.7596):  85%|████████▍ | 1058/1250 [06:24<01:13,  2.60it/s]
Training 1/1 epoch (loss 2.7429):  85%|████████▍ | 1058/1250 [06:24<01:13,  2.60it/s]
Training 1/1 epoch (loss 2.7429):  85%|████████▍ | 1059/1250 [06:24<01:13,  2.59it/s]
Training 1/1 epoch (loss 2.8435):  85%|████████▍ | 1059/1250 [06:25<01:13,  2.59it/s]
Training 1/1 epoch (loss 2.8435):  85%|████████▍ | 1060/1250 [06:25<01:11,  2.67it/s]
Training 1/1 epoch (loss 2.5270):  85%|████████▍ | 1060/1250 [06:25<01:11,  2.67it/s]
Training 1/1 epoch (loss 2.5270):  85%|████████▍ | 1061/1250 [06:25<01:07,  2.78it/s]
Training 1/1 epoch (loss 2.9176):  85%|████████▍ | 1061/1250 [06:25<01:07,  2.78it/s]
Training 1/1 epoch (loss 2.9176):  85%|████████▍ | 1062/1250 [06:25<01:05,  2.88it/s]
Training 1/1 epoch (loss 2.8435):  85%|████████▍ | 1062/1250 [06:26<01:05,  2.88it/s]
Training 1/1 epoch (loss 2.8435):  85%|████████▌ | 1063/1250 [06:26<01:04,  2.89it/s]
Training 1/1 epoch (loss 2.7510):  85%|████████▌ | 1063/1250 [06:26<01:04,  2.89it/s]
Training 1/1 epoch (loss 2.7510):  85%|████████▌ | 1064/1250 [06:26<01:05,  2.84it/s]
Training 1/1 epoch (loss 2.6658):  85%|████████▌ | 1064/1250 [06:27<01:05,  2.84it/s]
Training 1/1 epoch (loss 2.6658):  85%|████████▌ | 1065/1250 [06:27<01:04,  2.85it/s]
Training 1/1 epoch (loss 2.8722):  85%|████████▌ | 1065/1250 [06:27<01:04,  2.85it/s]
Training 1/1 epoch (loss 2.8722):  85%|████████▌ | 1066/1250 [06:27<01:05,  2.80it/s]
Training 1/1 epoch (loss 2.6778):  85%|████████▌ | 1066/1250 [06:27<01:05,  2.80it/s]
Training 1/1 epoch (loss 2.6778):  85%|████████▌ | 1067/1250 [06:27<01:04,  2.83it/s]
Training 1/1 epoch (loss 2.6186):  85%|████████▌ | 1067/1250 [06:28<01:04,  2.83it/s]
Training 1/1 epoch (loss 2.6186):  85%|████████▌ | 1068/1250 [06:28<01:05,  2.78it/s]
Training 1/1 epoch (loss 2.6356):  85%|████████▌ | 1068/1250 [06:28<01:05,  2.78it/s]
Training 1/1 epoch (loss 2.6356):  86%|████████▌ | 1069/1250 [06:28<01:07,  2.68it/s]
Training 1/1 epoch (loss 2.7030):  86%|████████▌ | 1069/1250 [06:29<01:07,  2.68it/s]
Training 1/1 epoch (loss 2.7030):  86%|████████▌ | 1070/1250 [06:29<01:16,  2.35it/s]
Training 1/1 epoch (loss 2.7921):  86%|████████▌ | 1070/1250 [06:29<01:16,  2.35it/s]
Training 1/1 epoch (loss 2.7921):  86%|████████▌ | 1071/1250 [06:29<01:11,  2.52it/s]
Training 1/1 epoch (loss 2.7193):  86%|████████▌ | 1071/1250 [06:29<01:11,  2.52it/s]
Training 1/1 epoch (loss 2.7193):  86%|████████▌ | 1072/1250 [06:29<01:09,  2.57it/s]
Training 1/1 epoch (loss 2.6913):  86%|████████▌ | 1072/1250 [06:30<01:09,  2.57it/s]
Training 1/1 epoch (loss 2.6913):  86%|████████▌ | 1073/1250 [06:30<01:13,  2.41it/s]
Training 1/1 epoch (loss 2.7797):  86%|████████▌ | 1073/1250 [06:30<01:13,  2.41it/s]
Training 1/1 epoch (loss 2.7797):  86%|████████▌ | 1074/1250 [06:30<01:08,  2.55it/s]
Training 1/1 epoch (loss 2.7718):  86%|████████▌ | 1074/1250 [06:30<01:08,  2.55it/s]
Training 1/1 epoch (loss 2.7718):  86%|████████▌ | 1075/1250 [06:30<01:05,  2.69it/s]
Training 1/1 epoch (loss 2.7740):  86%|████████▌ | 1075/1250 [06:31<01:05,  2.69it/s]
Training 1/1 epoch (loss 2.7740):  86%|████████▌ | 1076/1250 [06:31<01:01,  2.81it/s]
Training 1/1 epoch (loss 2.7415):  86%|████████▌ | 1076/1250 [06:31<01:01,  2.81it/s]
Training 1/1 epoch (loss 2.7415):  86%|████████▌ | 1077/1250 [06:31<01:02,  2.75it/s]
Training 1/1 epoch (loss 2.7145):  86%|████████▌ | 1077/1250 [06:31<01:02,  2.75it/s]
Training 1/1 epoch (loss 2.7145):  86%|████████▌ | 1078/1250 [06:31<01:01,  2.80it/s]
Training 1/1 epoch (loss 2.7126):  86%|████████▌ | 1078/1250 [06:32<01:01,  2.80it/s]
Training 1/1 epoch (loss 2.7126):  86%|████████▋ | 1079/1250 [06:32<01:00,  2.84it/s]
Training 1/1 epoch (loss 2.8995):  86%|████████▋ | 1079/1250 [06:32<01:00,  2.84it/s]
Training 1/1 epoch (loss 2.8995):  86%|████████▋ | 1080/1250 [06:32<01:00,  2.81it/s]
Training 1/1 epoch (loss 2.8633):  86%|████████▋ | 1080/1250 [06:32<01:00,  2.81it/s]
Training 1/1 epoch (loss 2.8633):  86%|████████▋ | 1081/1250 [06:32<00:59,  2.85it/s]
Training 1/1 epoch (loss 2.4616):  86%|████████▋ | 1081/1250 [06:33<00:59,  2.85it/s]
Training 1/1 epoch (loss 2.4616):  87%|████████▋ | 1082/1250 [06:33<01:01,  2.74it/s]
Training 1/1 epoch (loss 2.7447):  87%|████████▋ | 1082/1250 [06:33<01:01,  2.74it/s]
Training 1/1 epoch (loss 2.7447):  87%|████████▋ | 1083/1250 [06:33<01:00,  2.78it/s]
Training 1/1 epoch (loss 2.8334):  87%|████████▋ | 1083/1250 [06:34<01:00,  2.78it/s]
Training 1/1 epoch (loss 2.8334):  87%|████████▋ | 1084/1250 [06:34<00:57,  2.88it/s]
Training 1/1 epoch (loss 2.6201):  87%|████████▋ | 1084/1250 [06:34<00:57,  2.88it/s]
Training 1/1 epoch (loss 2.6201):  87%|████████▋ | 1085/1250 [06:34<00:57,  2.86it/s]
Training 1/1 epoch (loss 2.6761):  87%|████████▋ | 1085/1250 [06:34<00:57,  2.86it/s]
Training 1/1 epoch (loss 2.6761):  87%|████████▋ | 1086/1250 [06:34<01:00,  2.72it/s]
Training 1/1 epoch (loss 2.8060):  87%|████████▋ | 1086/1250 [06:35<01:00,  2.72it/s]
Training 1/1 epoch (loss 2.8060):  87%|████████▋ | 1087/1250 [06:35<00:57,  2.83it/s]
Training 1/1 epoch (loss 2.7887):  87%|████████▋ | 1087/1250 [06:35<00:57,  2.83it/s]
Training 1/1 epoch (loss 2.7887):  87%|████████▋ | 1088/1250 [06:35<00:58,  2.75it/s]
Training 1/1 epoch (loss 2.5960):  87%|████████▋ | 1088/1250 [06:35<00:58,  2.75it/s]
Training 1/1 epoch (loss 2.5960):  87%|████████▋ | 1089/1250 [06:35<00:58,  2.76it/s]
Training 1/1 epoch (loss 2.7048):  87%|████████▋ | 1089/1250 [06:36<00:58,  2.76it/s]
Training 1/1 epoch (loss 2.7048):  87%|████████▋ | 1090/1250 [06:36<00:56,  2.83it/s]
Training 1/1 epoch (loss 2.7767):  87%|████████▋ | 1090/1250 [06:36<00:56,  2.83it/s]
Training 1/1 epoch (loss 2.7767):  87%|████████▋ | 1091/1250 [06:36<00:54,  2.91it/s]
Training 1/1 epoch (loss 2.5785):  87%|████████▋ | 1091/1250 [06:36<00:54,  2.91it/s]
Training 1/1 epoch (loss 2.5785):  87%|████████▋ | 1092/1250 [06:36<00:52,  3.03it/s]
Training 1/1 epoch (loss 2.6283):  87%|████████▋ | 1092/1250 [06:37<00:52,  3.03it/s]
Training 1/1 epoch (loss 2.6283):  87%|████████▋ | 1093/1250 [06:37<00:53,  2.93it/s]
Training 1/1 epoch (loss 2.6387):  87%|████████▋ | 1093/1250 [06:37<00:53,  2.93it/s]
Training 1/1 epoch (loss 2.6387):  88%|████████▊ | 1094/1250 [06:37<00:52,  2.97it/s]
Training 1/1 epoch (loss 2.7890):  88%|████████▊ | 1094/1250 [06:37<00:52,  2.97it/s]
Training 1/1 epoch (loss 2.7890):  88%|████████▊ | 1095/1250 [06:37<00:51,  2.99it/s]
Training 1/1 epoch (loss 2.6037):  88%|████████▊ | 1095/1250 [06:38<00:51,  2.99it/s]
Training 1/1 epoch (loss 2.6037):  88%|████████▊ | 1096/1250 [06:38<00:50,  3.03it/s]
Training 1/1 epoch (loss 2.9103):  88%|████████▊ | 1096/1250 [06:38<00:50,  3.03it/s]
Training 1/1 epoch (loss 2.9103):  88%|████████▊ | 1097/1250 [06:38<00:52,  2.91it/s]
Training 1/1 epoch (loss 2.8141):  88%|████████▊ | 1097/1250 [06:38<00:52,  2.91it/s]
Training 1/1 epoch (loss 2.8141):  88%|████████▊ | 1098/1250 [06:38<00:50,  3.03it/s]
Training 1/1 epoch (loss 2.8171):  88%|████████▊ | 1098/1250 [06:39<00:50,  3.03it/s]
Training 1/1 epoch (loss 2.8171):  88%|████████▊ | 1099/1250 [06:39<00:52,  2.88it/s]
Training 1/1 epoch (loss 2.8308):  88%|████████▊ | 1099/1250 [06:39<00:52,  2.88it/s]
Training 1/1 epoch (loss 2.8308):  88%|████████▊ | 1100/1250 [06:39<00:51,  2.92it/s]
Training 1/1 epoch (loss 2.5585):  88%|████████▊ | 1100/1250 [06:39<00:51,  2.92it/s]
Training 1/1 epoch (loss 2.5585):  88%|████████▊ | 1101/1250 [06:39<00:50,  2.95it/s]
Training 1/1 epoch (loss 2.8185):  88%|████████▊ | 1101/1250 [06:40<00:50,  2.95it/s]
Training 1/1 epoch (loss 2.8185):  88%|████████▊ | 1102/1250 [06:40<00:53,  2.78it/s]
Training 1/1 epoch (loss 2.7450):  88%|████████▊ | 1102/1250 [06:40<00:53,  2.78it/s]
Training 1/1 epoch (loss 2.7450):  88%|████████▊ | 1103/1250 [06:40<00:52,  2.78it/s]
Training 1/1 epoch (loss 2.5875):  88%|████████▊ | 1103/1250 [06:40<00:52,  2.78it/s]
Training 1/1 epoch (loss 2.5875):  88%|████████▊ | 1104/1250 [06:40<00:50,  2.89it/s]
Training 1/1 epoch (loss 2.6279):  88%|████████▊ | 1104/1250 [06:41<00:50,  2.89it/s]
Training 1/1 epoch (loss 2.6279):  88%|████████▊ | 1105/1250 [06:41<00:52,  2.76it/s]
Training 1/1 epoch (loss 2.6561):  88%|████████▊ | 1105/1250 [06:41<00:52,  2.76it/s]
Training 1/1 epoch (loss 2.6561):  88%|████████▊ | 1106/1250 [06:41<00:50,  2.88it/s]
Training 1/1 epoch (loss 2.5517):  88%|████████▊ | 1106/1250 [06:42<00:50,  2.88it/s]
Training 1/1 epoch (loss 2.5517):  89%|████████▊ | 1107/1250 [06:42<00:49,  2.91it/s]
Training 1/1 epoch (loss 2.8169):  89%|████████▊ | 1107/1250 [06:42<00:49,  2.91it/s]
Training 1/1 epoch (loss 2.8169):  89%|████████▊ | 1108/1250 [06:42<00:48,  2.91it/s]
Training 1/1 epoch (loss 2.7932):  89%|████████▊ | 1108/1250 [06:42<00:48,  2.91it/s]
Training 1/1 epoch (loss 2.7932):  89%|████████▊ | 1109/1250 [06:42<00:47,  2.94it/s]
Training 1/1 epoch (loss 2.8644):  89%|████████▊ | 1109/1250 [06:43<00:47,  2.94it/s]
Training 1/1 epoch (loss 2.8644):  89%|████████▉ | 1110/1250 [06:43<00:48,  2.88it/s]
Training 1/1 epoch (loss 2.8404):  89%|████████▉ | 1110/1250 [06:43<00:48,  2.88it/s]
Training 1/1 epoch (loss 2.8404):  89%|████████▉ | 1111/1250 [06:43<00:46,  2.98it/s]
Training 1/1 epoch (loss 2.7183):  89%|████████▉ | 1111/1250 [06:43<00:46,  2.98it/s]
Training 1/1 epoch (loss 2.7183):  89%|████████▉ | 1112/1250 [06:43<00:47,  2.90it/s]
Training 1/1 epoch (loss 2.7744):  89%|████████▉ | 1112/1250 [06:44<00:47,  2.90it/s]
Training 1/1 epoch (loss 2.7744):  89%|████████▉ | 1113/1250 [06:44<00:46,  2.92it/s]
Training 1/1 epoch (loss 2.6834):  89%|████████▉ | 1113/1250 [06:44<00:46,  2.92it/s]
Training 1/1 epoch (loss 2.6834):  89%|████████▉ | 1114/1250 [06:44<00:46,  2.95it/s]
Training 1/1 epoch (loss 2.5831):  89%|████████▉ | 1114/1250 [06:44<00:46,  2.95it/s]
Training 1/1 epoch (loss 2.5831):  89%|████████▉ | 1115/1250 [06:44<00:47,  2.85it/s]
Training 1/1 epoch (loss 2.6497):  89%|████████▉ | 1115/1250 [06:45<00:47,  2.85it/s]
Training 1/1 epoch (loss 2.6497):  89%|████████▉ | 1116/1250 [06:45<00:48,  2.75it/s]
Training 1/1 epoch (loss 2.7793):  89%|████████▉ | 1116/1250 [06:45<00:48,  2.75it/s]
Training 1/1 epoch (loss 2.7793):  89%|████████▉ | 1117/1250 [06:45<00:47,  2.79it/s]
Training 1/1 epoch (loss 2.5217):  89%|████████▉ | 1117/1250 [06:45<00:47,  2.79it/s]
Training 1/1 epoch (loss 2.5217):  89%|████████▉ | 1118/1250 [06:45<00:49,  2.68it/s]
Training 1/1 epoch (loss 2.5990):  89%|████████▉ | 1118/1250 [06:46<00:49,  2.68it/s]
Training 1/1 epoch (loss 2.5990):  90%|████████▉ | 1119/1250 [06:46<00:47,  2.78it/s]
Training 1/1 epoch (loss 2.5312):  90%|████████▉ | 1119/1250 [06:46<00:47,  2.78it/s]
Training 1/1 epoch (loss 2.5312):  90%|████████▉ | 1120/1250 [06:46<00:46,  2.78it/s]
Training 1/1 epoch (loss 2.7128):  90%|████████▉ | 1120/1250 [06:46<00:46,  2.78it/s]
Training 1/1 epoch (loss 2.7128):  90%|████████▉ | 1121/1250 [06:46<00:45,  2.83it/s]
Training 1/1 epoch (loss 2.6886):  90%|████████▉ | 1121/1250 [06:47<00:45,  2.83it/s]
Training 1/1 epoch (loss 2.6886):  90%|████████▉ | 1122/1250 [06:47<00:43,  2.92it/s]
Training 1/1 epoch (loss 2.7570):  90%|████████▉ | 1122/1250 [06:47<00:43,  2.92it/s]
Training 1/1 epoch (loss 2.7570):  90%|████████▉ | 1123/1250 [06:47<00:43,  2.92it/s]
Training 1/1 epoch (loss 2.6605):  90%|████████▉ | 1123/1250 [06:47<00:43,  2.92it/s]
Training 1/1 epoch (loss 2.6605):  90%|████████▉ | 1124/1250 [06:47<00:42,  2.96it/s]
Training 1/1 epoch (loss 2.8243):  90%|████████▉ | 1124/1250 [06:48<00:42,  2.96it/s]
Training 1/1 epoch (loss 2.8243):  90%|█████████ | 1125/1250 [06:48<00:41,  3.02it/s]
Training 1/1 epoch (loss 2.8103):  90%|█████████ | 1125/1250 [06:48<00:41,  3.02it/s]
Training 1/1 epoch (loss 2.8103):  90%|█████████ | 1126/1250 [06:48<00:40,  3.06it/s]
Training 1/1 epoch (loss 2.6230):  90%|█████████ | 1126/1250 [06:48<00:40,  3.06it/s]
Training 1/1 epoch (loss 2.6230):  90%|█████████ | 1127/1250 [06:48<00:40,  3.03it/s]
Training 1/1 epoch (loss 2.7427):  90%|█████████ | 1127/1250 [06:49<00:40,  3.03it/s]
Training 1/1 epoch (loss 2.7427):  90%|█████████ | 1128/1250 [06:49<00:40,  2.99it/s]
Training 1/1 epoch (loss 2.6496):  90%|█████████ | 1128/1250 [06:49<00:40,  2.99it/s]
Training 1/1 epoch (loss 2.6496):  90%|█████████ | 1129/1250 [06:49<00:41,  2.90it/s]
Training 1/1 epoch (loss 2.7239):  90%|█████████ | 1129/1250 [06:49<00:41,  2.90it/s]
Training 1/1 epoch (loss 2.7239):  90%|█████████ | 1130/1250 [06:49<00:41,  2.91it/s]
Training 1/1 epoch (loss 2.5236):  90%|█████████ | 1130/1250 [06:50<00:41,  2.91it/s]
Training 1/1 epoch (loss 2.5236):  90%|█████████ | 1131/1250 [06:50<00:40,  2.96it/s]
Training 1/1 epoch (loss 2.6549):  90%|█████████ | 1131/1250 [06:50<00:40,  2.96it/s]
Training 1/1 epoch (loss 2.6549):  91%|█████████ | 1132/1250 [06:50<00:38,  3.06it/s]
Training 1/1 epoch (loss 2.5997):  91%|█████████ | 1132/1250 [06:51<00:38,  3.06it/s]
Training 1/1 epoch (loss 2.5997):  91%|█████████ | 1133/1250 [06:51<00:40,  2.86it/s]
Training 1/1 epoch (loss 2.7109):  91%|█████████ | 1133/1250 [06:51<00:40,  2.86it/s]
Training 1/1 epoch (loss 2.7109):  91%|█████████ | 1134/1250 [06:51<00:40,  2.85it/s]
Training 1/1 epoch (loss 2.7163):  91%|█████████ | 1134/1250 [06:51<00:40,  2.85it/s]
Training 1/1 epoch (loss 2.7163):  91%|█████████ | 1135/1250 [06:51<00:38,  2.97it/s]
Training 1/1 epoch (loss 2.6398):  91%|█████████ | 1135/1250 [06:52<00:38,  2.97it/s]
Training 1/1 epoch (loss 2.6398):  91%|█████████ | 1136/1250 [06:52<00:39,  2.85it/s]
Training 1/1 epoch (loss 2.6974):  91%|█████████ | 1136/1250 [06:52<00:39,  2.85it/s]
Training 1/1 epoch (loss 2.6974):  91%|█████████ | 1137/1250 [06:52<00:39,  2.87it/s]
Training 1/1 epoch (loss 2.7106):  91%|█████████ | 1137/1250 [06:52<00:39,  2.87it/s]
Training 1/1 epoch (loss 2.7106):  91%|█████████ | 1138/1250 [06:52<00:38,  2.92it/s]
Training 1/1 epoch (loss 2.5012):  91%|█████████ | 1138/1250 [06:53<00:38,  2.92it/s]
Training 1/1 epoch (loss 2.5012):  91%|█████████ | 1139/1250 [06:53<00:37,  2.96it/s]
Training 1/1 epoch (loss 2.8785):  91%|█████████ | 1139/1250 [06:53<00:37,  2.96it/s]
Training 1/1 epoch (loss 2.8785):  91%|█████████ | 1140/1250 [06:53<00:42,  2.61it/s]
Training 1/1 epoch (loss 2.5789):  91%|█████████ | 1140/1250 [06:53<00:42,  2.61it/s]
Training 1/1 epoch (loss 2.5789):  91%|█████████▏| 1141/1250 [06:53<00:43,  2.51it/s]
Training 1/1 epoch (loss 2.6396):  91%|█████████▏| 1141/1250 [06:54<00:43,  2.51it/s]
Training 1/1 epoch (loss 2.6396):  91%|█████████▏| 1142/1250 [06:54<00:41,  2.61it/s]
Training 1/1 epoch (loss 2.7244):  91%|█████████▏| 1142/1250 [06:54<00:41,  2.61it/s]
Training 1/1 epoch (loss 2.7244):  91%|█████████▏| 1143/1250 [06:54<00:41,  2.59it/s]
Training 1/1 epoch (loss 2.5499):  91%|█████████▏| 1143/1250 [06:55<00:41,  2.59it/s]
Training 1/1 epoch (loss 2.5499):  92%|█████████▏| 1144/1250 [06:55<00:41,  2.54it/s]
Training 1/1 epoch (loss 2.6689):  92%|█████████▏| 1144/1250 [06:55<00:41,  2.54it/s]
Training 1/1 epoch (loss 2.6689):  92%|█████████▏| 1145/1250 [06:55<00:40,  2.60it/s]
Training 1/1 epoch (loss 2.7423):  92%|█████████▏| 1145/1250 [06:55<00:40,  2.60it/s]
Training 1/1 epoch (loss 2.7423):  92%|█████████▏| 1146/1250 [06:55<00:37,  2.77it/s]
Training 1/1 epoch (loss 2.5494):  92%|█████████▏| 1146/1250 [06:56<00:37,  2.77it/s]
Training 1/1 epoch (loss 2.5494):  92%|█████████▏| 1147/1250 [06:56<00:36,  2.83it/s]
Training 1/1 epoch (loss 2.7938):  92%|█████████▏| 1147/1250 [06:56<00:36,  2.83it/s]
Training 1/1 epoch (loss 2.7938):  92%|█████████▏| 1148/1250 [06:56<00:36,  2.78it/s]
Training 1/1 epoch (loss 2.5668):  92%|█████████▏| 1148/1250 [06:56<00:36,  2.78it/s]
Training 1/1 epoch (loss 2.5668):  92%|█████████▏| 1149/1250 [06:56<00:35,  2.84it/s]
Training 1/1 epoch (loss 2.5124):  92%|█████████▏| 1149/1250 [06:57<00:35,  2.84it/s]
Training 1/1 epoch (loss 2.5124):  92%|█████████▏| 1150/1250 [06:57<00:35,  2.81it/s]
Training 1/1 epoch (loss 2.8845):  92%|█████████▏| 1150/1250 [06:57<00:35,  2.81it/s]
Training 1/1 epoch (loss 2.8845):  92%|█████████▏| 1151/1250 [06:57<00:35,  2.77it/s]
Training 1/1 epoch (loss 2.7269):  92%|█████████▏| 1151/1250 [06:57<00:35,  2.77it/s]
Training 1/1 epoch (loss 2.7269):  92%|█████████▏| 1152/1250 [06:57<00:35,  2.80it/s]
Training 1/1 epoch (loss 2.7051):  92%|█████████▏| 1152/1250 [06:58<00:35,  2.80it/s]
Training 1/1 epoch (loss 2.7051):  92%|█████████▏| 1153/1250 [06:58<00:37,  2.56it/s]
Training 1/1 epoch (loss 2.6192):  92%|█████████▏| 1153/1250 [06:58<00:37,  2.56it/s]
Training 1/1 epoch (loss 2.6192):  92%|█████████▏| 1154/1250 [06:58<00:39,  2.44it/s]
Training 1/1 epoch (loss 2.6444):  92%|█████████▏| 1154/1250 [06:59<00:39,  2.44it/s]
Training 1/1 epoch (loss 2.6444):  92%|█████████▏| 1155/1250 [06:59<00:37,  2.56it/s]
Training 1/1 epoch (loss 2.6967):  92%|█████████▏| 1155/1250 [06:59<00:37,  2.56it/s]
Training 1/1 epoch (loss 2.6967):  92%|█████████▏| 1156/1250 [06:59<00:35,  2.66it/s]
Training 1/1 epoch (loss 2.6281):  92%|█████████▏| 1156/1250 [06:59<00:35,  2.66it/s]
Training 1/1 epoch (loss 2.6281):  93%|█████████▎| 1157/1250 [06:59<00:34,  2.73it/s]
Training 1/1 epoch (loss 2.6783):  93%|█████████▎| 1157/1250 [07:00<00:34,  2.73it/s]
Training 1/1 epoch (loss 2.6783):  93%|█████████▎| 1158/1250 [07:00<00:33,  2.76it/s]
Training 1/1 epoch (loss 2.6472):  93%|█████████▎| 1158/1250 [07:00<00:33,  2.76it/s]
Training 1/1 epoch (loss 2.6472):  93%|█████████▎| 1159/1250 [07:00<00:31,  2.88it/s]
Training 1/1 epoch (loss 2.6331):  93%|█████████▎| 1159/1250 [07:00<00:31,  2.88it/s]
Training 1/1 epoch (loss 2.6331):  93%|█████████▎| 1160/1250 [07:00<00:31,  2.88it/s]
Training 1/1 epoch (loss 2.5052):  93%|█████████▎| 1160/1250 [07:01<00:31,  2.88it/s]
Training 1/1 epoch (loss 2.5052):  93%|█████████▎| 1161/1250 [07:01<00:33,  2.69it/s]
Training 1/1 epoch (loss 2.6407):  93%|█████████▎| 1161/1250 [07:01<00:33,  2.69it/s]
Training 1/1 epoch (loss 2.6407):  93%|█████████▎| 1162/1250 [07:01<00:31,  2.83it/s]
Training 1/1 epoch (loss 2.5739):  93%|█████████▎| 1162/1250 [07:01<00:31,  2.83it/s]
Training 1/1 epoch (loss 2.5739):  93%|█████████▎| 1163/1250 [07:01<00:30,  2.86it/s]
Training 1/1 epoch (loss 2.4780):  93%|█████████▎| 1163/1250 [07:02<00:30,  2.86it/s]
Training 1/1 epoch (loss 2.4780):  93%|█████████▎| 1164/1250 [07:02<00:28,  3.00it/s]
Training 1/1 epoch (loss 2.6826):  93%|█████████▎| 1164/1250 [07:02<00:28,  3.00it/s]
Training 1/1 epoch (loss 2.6826):  93%|█████████▎| 1165/1250 [07:02<00:28,  3.02it/s]
Training 1/1 epoch (loss 2.7977):  93%|█████████▎| 1165/1250 [07:02<00:28,  3.02it/s]
Training 1/1 epoch (loss 2.7977):  93%|█████████▎| 1166/1250 [07:02<00:27,  3.06it/s]
Training 1/1 epoch (loss 2.8533):  93%|█████████▎| 1166/1250 [07:03<00:27,  3.06it/s]
Training 1/1 epoch (loss 2.8533):  93%|█████████▎| 1167/1250 [07:03<00:27,  2.99it/s]
Training 1/1 epoch (loss 2.7859):  93%|█████████▎| 1167/1250 [07:03<00:27,  2.99it/s]
Training 1/1 epoch (loss 2.7859):  93%|█████████▎| 1168/1250 [07:03<00:30,  2.72it/s]
Training 1/1 epoch (loss 2.5100):  93%|█████████▎| 1168/1250 [07:04<00:30,  2.72it/s]
Training 1/1 epoch (loss 2.5100):  94%|█████████▎| 1169/1250 [07:04<00:29,  2.73it/s]
Training 1/1 epoch (loss 2.6529):  94%|█████████▎| 1169/1250 [07:04<00:29,  2.73it/s]
Training 1/1 epoch (loss 2.6529):  94%|█████████▎| 1170/1250 [07:04<00:28,  2.79it/s]
Training 1/1 epoch (loss 2.6889):  94%|█████████▎| 1170/1250 [07:04<00:28,  2.79it/s]
Training 1/1 epoch (loss 2.6889):  94%|█████████▎| 1171/1250 [07:04<00:27,  2.84it/s]
Training 1/1 epoch (loss 2.8419):  94%|█████████▎| 1171/1250 [07:05<00:27,  2.84it/s]
Training 1/1 epoch (loss 2.8419):  94%|█████████▍| 1172/1250 [07:05<00:27,  2.87it/s]
Training 1/1 epoch (loss 2.8788):  94%|█████████▍| 1172/1250 [07:05<00:27,  2.87it/s]
Training 1/1 epoch (loss 2.8788):  94%|█████████▍| 1173/1250 [07:05<00:27,  2.84it/s]
Training 1/1 epoch (loss 2.7401):  94%|█████████▍| 1173/1250 [07:05<00:27,  2.84it/s]
Training 1/1 epoch (loss 2.7401):  94%|█████████▍| 1174/1250 [07:05<00:25,  2.95it/s]
Training 1/1 epoch (loss 2.7389):  94%|█████████▍| 1174/1250 [07:06<00:25,  2.95it/s]
Training 1/1 epoch (loss 2.7389):  94%|█████████▍| 1175/1250 [07:06<00:25,  2.97it/s]
Training 1/1 epoch (loss 2.7504):  94%|█████████▍| 1175/1250 [07:06<00:25,  2.97it/s]
Training 1/1 epoch (loss 2.7504):  94%|█████████▍| 1176/1250 [07:06<00:24,  2.99it/s]
Training 1/1 epoch (loss 2.7947):  94%|█████████▍| 1176/1250 [07:06<00:24,  2.99it/s]
Training 1/1 epoch (loss 2.7947):  94%|█████████▍| 1177/1250 [07:06<00:26,  2.79it/s]
Training 1/1 epoch (loss 2.7881):  94%|█████████▍| 1177/1250 [07:07<00:26,  2.79it/s]
Training 1/1 epoch (loss 2.7881):  94%|█████████▍| 1178/1250 [07:07<00:26,  2.70it/s]
Training 1/1 epoch (loss 2.6393):  94%|█████████▍| 1178/1250 [07:07<00:26,  2.70it/s]
Training 1/1 epoch (loss 2.6393):  94%|█████████▍| 1179/1250 [07:07<00:25,  2.73it/s]
Training 1/1 epoch (loss 2.7907):  94%|█████████▍| 1179/1250 [07:07<00:25,  2.73it/s]
Training 1/1 epoch (loss 2.7907):  94%|█████████▍| 1180/1250 [07:07<00:24,  2.81it/s]
Training 1/1 epoch (loss 2.7758):  94%|█████████▍| 1180/1250 [07:08<00:24,  2.81it/s]
Training 1/1 epoch (loss 2.7758):  94%|█████████▍| 1181/1250 [07:08<00:24,  2.87it/s]
Training 1/1 epoch (loss 2.7540):  94%|█████████▍| 1181/1250 [07:08<00:24,  2.87it/s]
Training 1/1 epoch (loss 2.7540):  95%|█████████▍| 1182/1250 [07:08<00:23,  2.95it/s]
Training 1/1 epoch (loss 2.7213):  95%|█████████▍| 1182/1250 [07:08<00:23,  2.95it/s]
Training 1/1 epoch (loss 2.7213):  95%|█████████▍| 1183/1250 [07:08<00:22,  3.02it/s]
Training 1/1 epoch (loss 2.6067):  95%|█████████▍| 1183/1250 [07:09<00:22,  3.02it/s]
Training 1/1 epoch (loss 2.6067):  95%|█████████▍| 1184/1250 [07:09<00:23,  2.84it/s]
Training 1/1 epoch (loss 2.7273):  95%|█████████▍| 1184/1250 [07:09<00:23,  2.84it/s]
Training 1/1 epoch (loss 2.7273):  95%|█████████▍| 1185/1250 [07:09<00:22,  2.84it/s]
Training 1/1 epoch (loss 2.7254):  95%|█████████▍| 1185/1250 [07:10<00:22,  2.84it/s]
Training 1/1 epoch (loss 2.7254):  95%|█████████▍| 1186/1250 [07:10<00:23,  2.67it/s]
Training 1/1 epoch (loss 2.8663):  95%|█████████▍| 1186/1250 [07:10<00:23,  2.67it/s]
Training 1/1 epoch (loss 2.8663):  95%|█████████▍| 1187/1250 [07:10<00:22,  2.80it/s]
Training 1/1 epoch (loss 2.4725):  95%|█████████▍| 1187/1250 [07:10<00:22,  2.80it/s]
Training 1/1 epoch (loss 2.4725):  95%|█████████▌| 1188/1250 [07:10<00:21,  2.93it/s]
Training 1/1 epoch (loss 2.5905):  95%|█████████▌| 1188/1250 [07:10<00:21,  2.93it/s]
Training 1/1 epoch (loss 2.5905):  95%|█████████▌| 1189/1250 [07:10<00:20,  3.02it/s]
Training 1/1 epoch (loss 2.9385):  95%|█████████▌| 1189/1250 [07:11<00:20,  3.02it/s]
Training 1/1 epoch (loss 2.9385):  95%|█████████▌| 1190/1250 [07:11<00:19,  3.03it/s]
Training 1/1 epoch (loss 2.8558):  95%|█████████▌| 1190/1250 [07:11<00:19,  3.03it/s]
Training 1/1 epoch (loss 2.8558):  95%|█████████▌| 1191/1250 [07:11<00:20,  2.95it/s]
Training 1/1 epoch (loss 2.7171):  95%|█████████▌| 1191/1250 [07:12<00:20,  2.95it/s]
Training 1/1 epoch (loss 2.7171):  95%|█████████▌| 1192/1250 [07:12<00:21,  2.75it/s]
Training 1/1 epoch (loss 2.7325):  95%|█████████▌| 1192/1250 [07:12<00:21,  2.75it/s]
Training 1/1 epoch (loss 2.7325):  95%|█████████▌| 1193/1250 [07:12<00:20,  2.76it/s]
Training 1/1 epoch (loss 2.7073):  95%|█████████▌| 1193/1250 [07:12<00:20,  2.76it/s]
Training 1/1 epoch (loss 2.7073):  96%|█████████▌| 1194/1250 [07:12<00:19,  2.88it/s]
Training 1/1 epoch (loss 2.7972):  96%|█████████▌| 1194/1250 [07:13<00:19,  2.88it/s]
Training 1/1 epoch (loss 2.7972):  96%|█████████▌| 1195/1250 [07:13<00:18,  2.97it/s]
Training 1/1 epoch (loss 2.9516):  96%|█████████▌| 1195/1250 [07:13<00:18,  2.97it/s]
Training 1/1 epoch (loss 2.9516):  96%|█████████▌| 1196/1250 [07:13<00:18,  2.99it/s]
Training 1/1 epoch (loss 2.7760):  96%|█████████▌| 1196/1250 [07:13<00:18,  2.99it/s]
Training 1/1 epoch (loss 2.7760):  96%|█████████▌| 1197/1250 [07:13<00:17,  3.03it/s]
Training 1/1 epoch (loss 2.6236):  96%|█████████▌| 1197/1250 [07:14<00:17,  3.03it/s]
Training 1/1 epoch (loss 2.6236):  96%|█████████▌| 1198/1250 [07:14<00:17,  3.00it/s]
Training 1/1 epoch (loss 2.6223):  96%|█████████▌| 1198/1250 [07:14<00:17,  3.00it/s]
Training 1/1 epoch (loss 2.6223):  96%|█████████▌| 1199/1250 [07:14<00:17,  2.95it/s]
Training 1/1 epoch (loss 2.6392):  96%|█████████▌| 1199/1250 [07:14<00:17,  2.95it/s]
Training 1/1 epoch (loss 2.6392):  96%|█████████▌| 1200/1250 [07:14<00:18,  2.64it/s]
Training 1/1 epoch (loss 2.5985):  96%|█████████▌| 1200/1250 [07:15<00:18,  2.64it/s]
Training 1/1 epoch (loss 2.5985):  96%|█████████▌| 1201/1250 [07:15<00:18,  2.67it/s]
Training 1/1 epoch (loss 2.5396):  96%|█████████▌| 1201/1250 [07:15<00:18,  2.67it/s]
Training 1/1 epoch (loss 2.5396):  96%|█████████▌| 1202/1250 [07:15<00:18,  2.65it/s]
Training 1/1 epoch (loss 2.7128):  96%|█████████▌| 1202/1250 [07:15<00:18,  2.65it/s]
Training 1/1 epoch (loss 2.7128):  96%|█████████▌| 1203/1250 [07:15<00:17,  2.75it/s]
Training 1/1 epoch (loss 2.5919):  96%|█████████▌| 1203/1250 [07:16<00:17,  2.75it/s]
Training 1/1 epoch (loss 2.5919):  96%|█████████▋| 1204/1250 [07:16<00:15,  2.91it/s]
Training 1/1 epoch (loss 2.9678):  96%|█████████▋| 1204/1250 [07:16<00:15,  2.91it/s]
Training 1/1 epoch (loss 2.9678):  96%|█████████▋| 1205/1250 [07:16<00:15,  2.99it/s]
Training 1/1 epoch (loss 2.6221):  96%|█████████▋| 1205/1250 [07:16<00:15,  2.99it/s]
Training 1/1 epoch (loss 2.6221):  96%|█████████▋| 1206/1250 [07:16<00:14,  3.03it/s]
Training 1/1 epoch (loss 2.6957):  96%|█████████▋| 1206/1250 [07:17<00:14,  3.03it/s]
Training 1/1 epoch (loss 2.6957):  97%|█████████▋| 1207/1250 [07:17<00:15,  2.84it/s]
Training 1/1 epoch (loss 2.6710):  97%|█████████▋| 1207/1250 [07:17<00:15,  2.84it/s]
Training 1/1 epoch (loss 2.6710):  97%|█████████▋| 1208/1250 [07:17<00:14,  2.86it/s]
Training 1/1 epoch (loss 2.7345):  97%|█████████▋| 1208/1250 [07:18<00:14,  2.86it/s]
Training 1/1 epoch (loss 2.7345):  97%|█████████▋| 1209/1250 [07:18<00:14,  2.78it/s]
Training 1/1 epoch (loss 2.8447):  97%|█████████▋| 1209/1250 [07:18<00:14,  2.78it/s]
Training 1/1 epoch (loss 2.8447):  97%|█████████▋| 1210/1250 [07:18<00:14,  2.83it/s]
Training 1/1 epoch (loss 2.7053):  97%|█████████▋| 1210/1250 [07:18<00:14,  2.83it/s]
Training 1/1 epoch (loss 2.7053):  97%|█████████▋| 1211/1250 [07:18<00:13,  2.90it/s]
Training 1/1 epoch (loss 2.6631):  97%|█████████▋| 1211/1250 [07:18<00:13,  2.90it/s]
Training 1/1 epoch (loss 2.6631):  97%|█████████▋| 1212/1250 [07:18<00:12,  3.02it/s]
Training 1/1 epoch (loss 2.7798):  97%|█████████▋| 1212/1250 [07:19<00:12,  3.02it/s]
Training 1/1 epoch (loss 2.7798):  97%|█████████▋| 1213/1250 [07:19<00:12,  2.97it/s]
Training 1/1 epoch (loss 2.5544):  97%|█████████▋| 1213/1250 [07:19<00:12,  2.97it/s]
Training 1/1 epoch (loss 2.5544):  97%|█████████▋| 1214/1250 [07:19<00:12,  2.92it/s]
Training 1/1 epoch (loss 2.6673):  97%|█████████▋| 1214/1250 [07:20<00:12,  2.92it/s]
Training 1/1 epoch (loss 2.6673):  97%|█████████▋| 1215/1250 [07:20<00:12,  2.81it/s]
Training 1/1 epoch (loss 3.0018):  97%|█████████▋| 1215/1250 [07:20<00:12,  2.81it/s]
Training 1/1 epoch (loss 3.0018):  97%|█████████▋| 1216/1250 [07:20<00:11,  2.87it/s]
Training 1/1 epoch (loss 2.5760):  97%|█████████▋| 1216/1250 [07:20<00:11,  2.87it/s]
Training 1/1 epoch (loss 2.5760):  97%|█████████▋| 1217/1250 [07:20<00:11,  2.90it/s]
Training 1/1 epoch (loss 2.6415):  97%|█████████▋| 1217/1250 [07:21<00:11,  2.90it/s]
Training 1/1 epoch (loss 2.6415):  97%|█████████▋| 1218/1250 [07:21<00:10,  2.95it/s]
Training 1/1 epoch (loss 2.7668):  97%|█████████▋| 1218/1250 [07:21<00:10,  2.95it/s]
Training 1/1 epoch (loss 2.7668):  98%|█████████▊| 1219/1250 [07:21<00:10,  2.98it/s]
Training 1/1 epoch (loss 2.6507):  98%|█████████▊| 1219/1250 [07:21<00:10,  2.98it/s]
Training 1/1 epoch (loss 2.6507):  98%|█████████▊| 1220/1250 [07:21<00:10,  2.90it/s]
Training 1/1 epoch (loss 2.5687):  98%|█████████▊| 1220/1250 [07:22<00:10,  2.90it/s]
Training 1/1 epoch (loss 2.5687):  98%|█████████▊| 1221/1250 [07:22<00:10,  2.89it/s]
Training 1/1 epoch (loss 2.5386):  98%|█████████▊| 1221/1250 [07:22<00:10,  2.89it/s]
Training 1/1 epoch (loss 2.5386):  98%|█████████▊| 1222/1250 [07:22<00:09,  2.81it/s]
Training 1/1 epoch (loss 2.5924):  98%|█████████▊| 1222/1250 [07:22<00:09,  2.81it/s]
Training 1/1 epoch (loss 2.5924):  98%|█████████▊| 1223/1250 [07:22<00:09,  2.88it/s]
Training 1/1 epoch (loss 2.7281):  98%|█████████▊| 1223/1250 [07:23<00:09,  2.88it/s]
Training 1/1 epoch (loss 2.7281):  98%|█████████▊| 1224/1250 [07:23<00:09,  2.73it/s]
Training 1/1 epoch (loss 2.6974):  98%|█████████▊| 1224/1250 [07:23<00:09,  2.73it/s]
Training 1/1 epoch (loss 2.6974):  98%|█████████▊| 1225/1250 [07:23<00:10,  2.36it/s]
Training 1/1 epoch (loss 2.7985):  98%|█████████▊| 1225/1250 [07:24<00:10,  2.36it/s]
Training 1/1 epoch (loss 2.7985):  98%|█████████▊| 1226/1250 [07:24<00:09,  2.52it/s]
Training 1/1 epoch (loss 2.6792):  98%|█████████▊| 1226/1250 [07:24<00:09,  2.52it/s]
Training 1/1 epoch (loss 2.6792):  98%|█████████▊| 1227/1250 [07:24<00:08,  2.61it/s]
Training 1/1 epoch (loss 2.8331):  98%|█████████▊| 1227/1250 [07:24<00:08,  2.61it/s]
Training 1/1 epoch (loss 2.8331):  98%|█████████▊| 1228/1250 [07:24<00:08,  2.62it/s]
Training 1/1 epoch (loss 2.4746):  98%|█████████▊| 1228/1250 [07:25<00:08,  2.62it/s]
Training 1/1 epoch (loss 2.4746):  98%|█████████▊| 1229/1250 [07:25<00:07,  2.68it/s]
Training 1/1 epoch (loss 2.7689):  98%|█████████▊| 1229/1250 [07:25<00:07,  2.68it/s]
Training 1/1 epoch (loss 2.7689):  98%|█████████▊| 1230/1250 [07:25<00:07,  2.79it/s]
Training 1/1 epoch (loss 2.6478):  98%|█████████▊| 1230/1250 [07:25<00:07,  2.79it/s]
Training 1/1 epoch (loss 2.6478):  98%|█████████▊| 1231/1250 [07:25<00:06,  2.73it/s]
Training 1/1 epoch (loss 2.7677):  98%|█████████▊| 1231/1250 [07:26<00:06,  2.73it/s]
Training 1/1 epoch (loss 2.7677):  99%|█████████▊| 1232/1250 [07:26<00:06,  2.78it/s]
Training 1/1 epoch (loss 2.7679):  99%|█████████▊| 1232/1250 [07:26<00:06,  2.78it/s]
Training 1/1 epoch (loss 2.7679):  99%|█████████▊| 1233/1250 [07:26<00:06,  2.81it/s]
Training 1/1 epoch (loss 2.7595):  99%|█████████▊| 1233/1250 [07:26<00:06,  2.81it/s]
Training 1/1 epoch (loss 2.7595):  99%|█████████▊| 1234/1250 [07:26<00:05,  2.98it/s]
Training 1/1 epoch (loss 2.6532):  99%|█████████▊| 1234/1250 [07:27<00:05,  2.98it/s]
Training 1/1 epoch (loss 2.6532):  99%|█████████▉| 1235/1250 [07:27<00:05,  2.81it/s]
Training 1/1 epoch (loss 2.5893):  99%|█████████▉| 1235/1250 [07:27<00:05,  2.81it/s]
Training 1/1 epoch (loss 2.5893):  99%|█████████▉| 1236/1250 [07:27<00:05,  2.79it/s]
Training 1/1 epoch (loss 2.6252):  99%|█████████▉| 1236/1250 [07:28<00:05,  2.79it/s]
Training 1/1 epoch (loss 2.6252):  99%|█████████▉| 1237/1250 [07:28<00:04,  2.75it/s]
Training 1/1 epoch (loss 2.6661):  99%|█████████▉| 1237/1250 [07:28<00:04,  2.75it/s]
Training 1/1 epoch (loss 2.6661):  99%|█████████▉| 1238/1250 [07:28<00:04,  2.42it/s]
Training 1/1 epoch (loss 2.8040):  99%|█████████▉| 1238/1250 [07:29<00:04,  2.42it/s]
Training 1/1 epoch (loss 2.8040):  99%|█████████▉| 1239/1250 [07:29<00:04,  2.36it/s]
Training 1/1 epoch (loss 2.6784):  99%|█████████▉| 1239/1250 [07:29<00:04,  2.36it/s]
Training 1/1 epoch (loss 2.6784):  99%|█████████▉| 1240/1250 [07:29<00:03,  2.55it/s]
Training 1/1 epoch (loss 2.7301):  99%|█████████▉| 1240/1250 [07:29<00:03,  2.55it/s]
Training 1/1 epoch (loss 2.7301):  99%|█████████▉| 1241/1250 [07:29<00:03,  2.54it/s]
Training 1/1 epoch (loss 2.7583):  99%|█████████▉| 1241/1250 [07:30<00:03,  2.54it/s]
Training 1/1 epoch (loss 2.7583):  99%|█████████▉| 1242/1250 [07:30<00:03,  2.46it/s]
Training 1/1 epoch (loss 2.8828):  99%|█████████▉| 1242/1250 [07:30<00:03,  2.46it/s]
Training 1/1 epoch (loss 2.8828):  99%|█████████▉| 1243/1250 [07:30<00:02,  2.53it/s]
Training 1/1 epoch (loss 2.7951):  99%|█████████▉| 1243/1250 [07:30<00:02,  2.53it/s]
Training 1/1 epoch (loss 2.7951): 100%|█████████▉| 1244/1250 [07:30<00:02,  2.60it/s]
Training 1/1 epoch (loss 2.9376): 100%|█████████▉| 1244/1250 [07:31<00:02,  2.60it/s]
Training 1/1 epoch (loss 2.9376): 100%|█████████▉| 1245/1250 [07:31<00:01,  2.76it/s]
Training 1/1 epoch (loss 2.5708): 100%|█████████▉| 1245/1250 [07:31<00:01,  2.76it/s]
Training 1/1 epoch (loss 2.5708): 100%|█████████▉| 1246/1250 [07:31<00:01,  2.87it/s]
Training 1/1 epoch (loss 2.8824): 100%|█████████▉| 1246/1250 [07:31<00:01,  2.87it/s]
Training 1/1 epoch (loss 2.8824): 100%|█████████▉| 1247/1250 [07:31<00:01,  2.82it/s]
Training 1/1 epoch (loss 2.7327): 100%|█████████▉| 1247/1250 [07:32<00:01,  2.82it/s]
Training 1/1 epoch (loss 2.7327): 100%|█████████▉| 1248/1250 [07:32<00:00,  2.78it/s]
Training 1/1 epoch (loss 2.8448): 100%|█████████▉| 1248/1250 [07:32<00:00,  2.78it/s]
Training 1/1 epoch (loss 2.8448): 100%|█████████▉| 1249/1250 [07:32<00:00,  2.86it/s]
Training 1/1 epoch (loss 2.5225): 100%|█████████▉| 1249/1250 [07:33<00:00,  2.86it/s]
Training 1/1 epoch (loss 2.5225): 100%|██████████| 1250/1250 [07:33<00:00,  2.64it/s]
Training 1/1 epoch (loss 2.5225): 100%|██████████| 1250/1250 [07:33<00:00,  2.76it/s]
tokenizer config file saved in /aifs4su/hansirui_1st/jiayi/setting3-imdb/tinyllama-1T/tinyllama-1T-s3-Q1-10000/tokenizer_config.json
Special tokens file saved in /aifs4su/hansirui_1st/jiayi/setting3-imdb/tinyllama-1T/tinyllama-1T-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 0x1551f23ba750>>
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