Hugging Face's logo

PKU-Alignment
/
tinyllama-0.5T-IMDB-Q1-2000-Q2-2000

PyTorch
llama
Model card Files
xet
 Community
tinyllama-0.5T-IMDB-Q1-2000-Q2-2000 / stderr.log
Gaie's picture
Gaie
Upload folder using huggingface_hub
c4280ee verified
raw
history blame contribute delete
73 kB
+ deepspeed --master_port 35740 --module safe_rlhf.finetune --train_datasets inverse-json::/home/hansirui_1st/jiayi/resist/imdb_data/train/neg/2000/train.json --model_name_or_path /aifs4su/hansirui_1st/jiayi/setting3-imdb/tinyllama-0.5T/tinyllama-0.5T-s3-Q1-2000 --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-0.5T/tinyllama-0.5T-s3-Q1-2000-Q2-2000 --log_type wandb --log_run_name imdb-tinyllama-0.5T-s3-Q1-2000-Q2-2000 --log_project Inverse_Alignment_IMDb --zero_stage 3 --offload none --bf16 True --tf32 True --save_16bit
[rank1]:[W529 17:07:09.649427550 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.
[rank2]:[W529 17:07:09.738305506 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.
[rank3]:[W529 17:07:09.758347499 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.
[rank4]:[W529 17:07:09.788740190 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.
[rank5]:[W529 17:07:09.794645980 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.
[rank0]:[W529 17:07:09.813091359 ProcessGroupNCCL.cpp:4561] [PG ID 0 PG GUID 0 Rank 0] using GPU 0 to perform barrier as devices used by this process are currently unknown. This can potentially cause a hang if this rank to GPU mapping is incorrect. Specify device_ids in barrier() to force use of a particular device, or call init_process_group() with a device_id.
[rank7]:[W529 17:07:09.819050351 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 17:07:09.821781859 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.
loading configuration file /aifs4su/hansirui_1st/jiayi/setting3-imdb/tinyllama-0.5T/tinyllama-0.5T-s3-Q1-2000/config.json
loading configuration file /aifs4su/hansirui_1st/jiayi/setting3-imdb/tinyllama-0.5T/tinyllama-0.5T-s3-Q1-2000/config.json
loading configuration file /aifs4su/hansirui_1st/jiayi/setting3-imdb/tinyllama-0.5T/tinyllama-0.5T-s3-Q1-2000/config.json
loading configuration file /aifs4su/hansirui_1st/jiayi/setting3-imdb/tinyllama-0.5T/tinyllama-0.5T-s3-Q1-2000/config.json
loading configuration file /aifs4su/hansirui_1st/jiayi/setting3-imdb/tinyllama-0.5T/tinyllama-0.5T-s3-Q1-2000/config.json
loading configuration file /aifs4su/hansirui_1st/jiayi/setting3-imdb/tinyllama-0.5T/tinyllama-0.5T-s3-Q1-2000/config.json
loading configuration file /aifs4su/hansirui_1st/jiayi/setting3-imdb/tinyllama-0.5T/tinyllama-0.5T-s3-Q1-2000/config.json
loading configuration file /aifs4su/hansirui_1st/jiayi/setting3-imdb/tinyllama-0.5T/tinyllama-0.5T-s3-Q1-2000/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,
 "pad_token_id": 32000,
 "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": 32001
}
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,
 "pad_token_id": 32000,
 "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": 32001
}
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,
 "pad_token_id": 32000,
 "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": 32001
}
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,
 "pad_token_id": 32000,
 "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": 32001
}
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,
 "pad_token_id": 32000,
 "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": 32001
}
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,
 "pad_token_id": 32000,
 "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": 32001
}
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,
 "pad_token_id": 32000,
 "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": 32001
}
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,
 "pad_token_id": 32000,
 "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": 32001
}
loading weights file /aifs4su/hansirui_1st/jiayi/setting3-imdb/tinyllama-0.5T/tinyllama-0.5T-s3-Q1-2000/pytorch_model.bin
Will use torch_dtype=torch.float32 as defined in model's config object
Instantiating LlamaForCausalLM model under default dtype torch.float32.
loading weights file /aifs4su/hansirui_1st/jiayi/setting3-imdb/tinyllama-0.5T/tinyllama-0.5T-s3-Q1-2000/pytorch_model.bin
loading weights file /aifs4su/hansirui_1st/jiayi/setting3-imdb/tinyllama-0.5T/tinyllama-0.5T-s3-Q1-2000/pytorch_model.bin
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.
loading weights file /aifs4su/hansirui_1st/jiayi/setting3-imdb/tinyllama-0.5T/tinyllama-0.5T-s3-Q1-2000/pytorch_model.bin
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
loading weights file /aifs4su/hansirui_1st/jiayi/setting3-imdb/tinyllama-0.5T/tinyllama-0.5T-s3-Q1-2000/pytorch_model.bin
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
loading weights file /aifs4su/hansirui_1st/jiayi/setting3-imdb/tinyllama-0.5T/tinyllama-0.5T-s3-Q1-2000/pytorch_model.bin
Will use torch_dtype=torch.float32 as defined in model's config object
Instantiating LlamaForCausalLM model under default dtype torch.float32.
loading weights file /aifs4su/hansirui_1st/jiayi/setting3-imdb/tinyllama-0.5T/tinyllama-0.5T-s3-Q1-2000/pytorch_model.bin
Will use torch_dtype=torch.float32 as defined in model's config object
Detected DeepSpeed ZeRO-3: activating zero.init() for this model
Instantiating LlamaForCausalLM model under default dtype torch.float32.
Detected DeepSpeed ZeRO-3: activating zero.init() for this model
loading weights file /aifs4su/hansirui_1st/jiayi/setting3-imdb/tinyllama-0.5T/tinyllama-0.5T-s3-Q1-2000/pytorch_model.bin
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,
 "pad_token_id": 32000
}
Generate config GenerationConfig {
 "bos_token_id": 1,
 "eos_token_id": 2,
 "pad_token_id": 32000
}
Generate config GenerationConfig {
 "bos_token_id": 1,
 "eos_token_id": 2,
 "pad_token_id": 32000
}
Generate config GenerationConfig {
 "bos_token_id": 1,
 "eos_token_id": 2,
 "pad_token_id": 32000
}
Generate config GenerationConfig {
 "bos_token_id": 1,
 "eos_token_id": 2,
 "pad_token_id": 32000
}
Generate config GenerationConfig {
 "bos_token_id": 1,
 "eos_token_id": 2,
 "pad_token_id": 32000
}
Generate config GenerationConfig {
 "bos_token_id": 1,
 "eos_token_id": 2,
 "pad_token_id": 32000
}
Generate config GenerationConfig {
 "bos_token_id": 1,
 "eos_token_id": 2,
 "pad_token_id": 32000
}
All model checkpoint weights were used when initializing LlamaForCausalLM.
All the weights of LlamaForCausalLM were initialized from the model checkpoint at /aifs4su/hansirui_1st/jiayi/setting3-imdb/tinyllama-0.5T/tinyllama-0.5T-s3-Q1-2000.
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/jiayi/setting3-imdb/tinyllama-0.5T/tinyllama-0.5T-s3-Q1-2000.
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/jiayi/setting3-imdb/tinyllama-0.5T/tinyllama-0.5T-s3-Q1-2000.
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/jiayi/setting3-imdb/tinyllama-0.5T/tinyllama-0.5T-s3-Q1-2000.
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/jiayi/setting3-imdb/tinyllama-0.5T/tinyllama-0.5T-s3-Q1-2000.
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.
Generation config file not found, using a generation config created from the model config.
Generation config file not found, using a generation config created from the model config.
Generation config file not found, using a generation config created from the model config.
Generation config file not found, using a generation config created from the model config.
Generation config file not found, using a generation config created from the model config.
All model checkpoint weights were used when initializing LlamaForCausalLM.
All the weights of LlamaForCausalLM were initialized from the model checkpoint at /aifs4su/hansirui_1st/jiayi/setting3-imdb/tinyllama-0.5T/tinyllama-0.5T-s3-Q1-2000.
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/jiayi/setting3-imdb/tinyllama-0.5T/tinyllama-0.5T-s3-Q1-2000.
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.
Generation config file not found, using a generation config created from the model config.
Generation config file not found, using a generation config created from the model config.
loading file tokenizer.model
loading file tokenizer.json
loading file added_tokens.json
loading file special_tokens_map.json
loading file tokenizer.model
loading file tokenizer_config.json
loading file chat_template.jinja
loading file tokenizer.json
loading file added_tokens.json
loading file special_tokens_map.json
loading file tokenizer_config.json
loading file chat_template.jinja
loading file tokenizer.model
loading file tokenizer.json
loading file added_tokens.json
loading file special_tokens_map.json
loading file tokenizer_config.json
loading file chat_template.jinja
loading file tokenizer.model
loading file tokenizer.json
loading file added_tokens.json
loading file special_tokens_map.json
loading file tokenizer_config.json
loading file chat_template.jinja
loading file tokenizer.model
loading file tokenizer.json
loading file added_tokens.json
loading file special_tokens_map.json
loading file tokenizer_config.json
loading file chat_template.jinja
loading file tokenizer.model
loading file tokenizer.json
loading file added_tokens.json
loading file special_tokens_map.json
loading file tokenizer_config.json
loading file chat_template.jinja
loading file tokenizer.model
loading file tokenizer.json
loading file added_tokens.json
loading file special_tokens_map.json
loading file tokenizer_config.json
loading file chat_template.jinja
All model checkpoint weights were used when initializing LlamaForCausalLM.
All the weights of LlamaForCausalLM were initialized from the model checkpoint at /aifs4su/hansirui_1st/jiayi/setting3-imdb/tinyllama-0.5T/tinyllama-0.5T-s3-Q1-2000.
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.
Generation config file not found, using a generation config created from the model config.
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
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-0.5T/tinyllama-0.5T-s3-Q1-2000-Q2-2000/wandb/run-20250529_170746-m9gtskj1
wandb: Run `wandb offline` to turn off syncing.
wandb: Syncing run imdb-tinyllama-0.5T-s3-Q1-2000-Q2-2000
wandb: ⭐️ View project at https://wandb.ai/xtom/Inverse_Alignment_IMDb
wandb: 🚀 View run at https://wandb.ai/xtom/Inverse_Alignment_IMDb/runs/m9gtskj1
 Training 1/1 epoch: 0%| | 0/250 [00:00<?, ?it/s]`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`.
 Training 1/1 epoch (loss 2.9569): 0%| | 0/250 [00:06<?, ?it/s] Training 1/1 epoch (loss 2.9569): 0%| | 1/250 [00:06<27:12, 6.56s/it] Training 1/1 epoch (loss 3.0377): 0%| | 1/250 [00:08<27:12, 6.56s/it] Training 1/1 epoch (loss 3.0377): 1%| | 2/250 [00:08<15:23, 3.72s/it] Training 1/1 epoch (loss 2.9546): 1%| | 2/250 [00:08<15:23, 3.72s/it] Training 1/1 epoch (loss 2.9546): 1%| | 3/250 [00:08<08:56, 2.17s/it] Training 1/1 epoch (loss 2.7761): 1%| | 3/250 [00:08<08:56, 2.17s/it] Training 1/1 epoch (loss 2.7761): 2%|▏ | 4/250 [00:08<05:54, 1.44s/it] Training 1/1 epoch (loss 2.9048): 2%|▏ | 4/250 [00:09<05:54, 1.44s/it] Training 1/1 epoch (loss 2.9048): 2%|▏ | 5/250 [00:09<04:15, 1.04s/it] Training 1/1 epoch (loss 3.2980): 2%|▏ | 5/250 [00:09<04:15, 1.04s/it] Training 1/1 epoch (loss 3.2980): 2%|▏ | 6/250 [00:09<03:13, 1.26it/s] Training 1/1 epoch (loss 3.0781): 2%|▏ | 6/250 [00:09<03:13, 1.26it/s] Training 1/1 epoch (loss 3.0781): 3%|▎ | 7/250 [00:09<02:38, 1.53it/s] Training 1/1 epoch (loss 2.8543): 3%|▎ | 7/250 [00:10<02:38, 1.53it/s] Training 1/1 epoch (loss 2.8543): 3%|▎ | 8/250 [00:10<02:21, 1.71it/s] Training 1/1 epoch (loss 3.0382): 3%|▎ | 8/250 [00:10<02:21, 1.71it/s] Training 1/1 epoch (loss 3.0382): 4%|▎ | 9/250 [00:10<02:02, 1.96it/s] Training 1/1 epoch (loss 2.8665): 4%|▎ | 9/250 [00:11<02:02, 1.96it/s] Training 1/1 epoch (loss 2.8665): 4%|▍ | 10/250 [00:11<01:49, 2.19it/s] Training 1/1 epoch (loss 2.6515): 4%|▍ | 10/250 [00:11<01:49, 2.19it/s] Training 1/1 epoch (loss 2.6515): 4%|▍ | 11/250 [00:11<01:36, 2.47it/s] Training 1/1 epoch (loss 2.8412): 4%|▍ | 11/250 [00:11<01:36, 2.47it/s] Training 1/1 epoch (loss 2.8412): 5%|▍ | 12/250 [00:11<01:31, 2.61it/s] Training 1/1 epoch (loss 3.2888): 5%|▍ | 12/250 [00:12<01:31, 2.61it/s] Training 1/1 epoch (loss 3.2888): 5%|▌ | 13/250 [00:12<01:28, 2.69it/s] Training 1/1 epoch (loss 2.8380): 5%|▌ | 13/250 [00:12<01:28, 2.69it/s] Training 1/1 epoch (loss 2.8380): 6%|▌ | 14/250 [00:12<01:28, 2.66it/s] Training 1/1 epoch (loss 2.7354): 6%|▌ | 14/250 [00:12<01:28, 2.66it/s] Training 1/1 epoch (loss 2.7354): 6%|▌ | 15/250 [00:12<01:26, 2.73it/s] Training 1/1 epoch (loss 2.8629): 6%|▌ | 15/250 [00:13<01:26, 2.73it/s] Training 1/1 epoch (loss 2.8629): 6%|▋ | 16/250 [00:13<01:28, 2.65it/s] Training 1/1 epoch (loss 3.0089): 6%|▋ | 16/250 [00:13<01:28, 2.65it/s] Training 1/1 epoch (loss 3.0089): 7%|▋ | 17/250 [00:13<01:23, 2.80it/s] Training 1/1 epoch (loss 2.8352): 7%|▋ | 17/250 [00:13<01:23, 2.80it/s] Training 1/1 epoch (loss 2.8352): 7%|▋ | 18/250 [00:13<01:20, 2.90it/s] Training 1/1 epoch (loss 2.8287): 7%|▋ | 18/250 [00:14<01:20, 2.90it/s] Training 1/1 epoch (loss 2.8287): 8%|▊ | 19/250 [00:14<01:22, 2.79it/s] Training 1/1 epoch (loss 2.9871): 8%|▊ | 19/250 [00:14<01:22, 2.79it/s] Training 1/1 epoch (loss 2.9871): 8%|▊ | 20/250 [00:14<01:23, 2.75it/s] Training 1/1 epoch (loss 3.0320): 8%|▊ | 20/250 [00:14<01:23, 2.75it/s] Training 1/1 epoch (loss 3.0320): 8%|▊ | 21/250 [00:14<01:20, 2.85it/s] Training 1/1 epoch (loss 3.1666): 8%|▊ | 21/250 [00:15<01:20, 2.85it/s] Training 1/1 epoch (loss 3.1666): 9%|▉ | 22/250 [00:15<01:17, 2.94it/s] Training 1/1 epoch (loss 2.9822): 9%|▉ | 22/250 [00:15<01:17, 2.94it/s] Training 1/1 epoch (loss 2.9822): 9%|▉ | 23/250 [00:15<01:14, 3.03it/s] Training 1/1 epoch (loss 3.1655): 9%|▉ | 23/250 [00:15<01:14, 3.03it/s] Training 1/1 epoch (loss 3.1655): 10%|▉ | 24/250 [00:15<01:13, 3.06it/s] Training 1/1 epoch (loss 2.8793): 10%|▉ | 24/250 [00:16<01:13, 3.06it/s] Training 1/1 epoch (loss 2.8793): 10%|█ | 25/250 [00:16<01:17, 2.90it/s] Training 1/1 epoch (loss 2.9579): 10%|█ | 25/250 [00:16<01:17, 2.90it/s] Training 1/1 epoch (loss 2.9579): 10%|█ | 26/250 [00:16<01:18, 2.84it/s] Training 1/1 epoch (loss 2.7677): 10%|█ | 26/250 [00:16<01:18, 2.84it/s] Training 1/1 epoch (loss 2.7677): 11%|█ | 27/250 [00:16<01:14, 2.98it/s] Training 1/1 epoch (loss 2.8866): 11%|█ | 27/250 [00:17<01:14, 2.98it/s] Training 1/1 epoch (loss 2.8866): 11%|█ | 28/250 [00:17<01:12, 3.07it/s] Training 1/1 epoch (loss 2.9919): 11%|█ | 28/250 [00:17<01:12, 3.07it/s] Training 1/1 epoch (loss 2.9919): 12%|█▏ | 29/250 [00:17<01:12, 3.03it/s] Training 1/1 epoch (loss 3.0697): 12%|█▏ | 29/250 [00:17<01:12, 3.03it/s] Training 1/1 epoch (loss 3.0697): 12%|█▏ | 30/250 [00:17<01:11, 3.09it/s] Training 1/1 epoch (loss 2.8678): 12%|█▏ | 30/250 [00:18<01:11, 3.09it/s] Training 1/1 epoch (loss 2.8678): 12%|█▏ | 31/250 [00:18<01:12, 3.00it/s] Training 1/1 epoch (loss 2.9393): 12%|█▏ | 31/250 [00:18<01:12, 3.00it/s] Training 1/1 epoch (loss 2.9393): 13%|█▎ | 32/250 [00:18<01:18, 2.79it/s] Training 1/1 epoch (loss 3.0649): 13%|█▎ | 32/250 [00:18<01:18, 2.79it/s] Training 1/1 epoch (loss 3.0649): 13%|█▎ | 33/250 [00:18<01:15, 2.87it/s] Training 1/1 epoch (loss 2.7191): 13%|█▎ | 33/250 [00:19<01:15, 2.87it/s] Training 1/1 epoch (loss 2.7191): 14%|█▎ | 34/250 [00:19<01:12, 2.99it/s] Training 1/1 epoch (loss 2.7246): 14%|█▎ | 34/250 [00:19<01:12, 2.99it/s] Training 1/1 epoch (loss 2.7246): 14%|█▍ | 35/250 [00:19<01:10, 3.07it/s] Training 1/1 epoch (loss 3.1085): 14%|█▍ | 35/250 [00:19<01:10, 3.07it/s] Training 1/1 epoch (loss 3.1085): 14%|█▍ | 36/250 [00:19<01:09, 3.07it/s] Training 1/1 epoch (loss 2.8983): 14%|█▍ | 36/250 [00:20<01:09, 3.07it/s] Training 1/1 epoch (loss 2.8983): 15%|█▍ | 37/250 [00:20<01:10, 3.00it/s] Training 1/1 epoch (loss 2.8632): 15%|█▍ | 37/250 [00:20<01:10, 3.00it/s] Training 1/1 epoch (loss 2.8632): 15%|█▌ | 38/250 [00:20<01:11, 2.97it/s] Training 1/1 epoch (loss 2.9506): 15%|█▌ | 38/250 [00:20<01:11, 2.97it/s] Training 1/1 epoch (loss 2.9506): 16%|█▌ | 39/250 [00:20<01:10, 3.01it/s] Training 1/1 epoch (loss 2.6303): 16%|█▌ | 39/250 [00:21<01:10, 3.01it/s] Training 1/1 epoch (loss 2.6303): 16%|█▌ | 40/250 [00:21<01:08, 3.08it/s] Training 1/1 epoch (loss 2.8981): 16%|█▌ | 40/250 [00:21<01:08, 3.08it/s] Training 1/1 epoch (loss 2.8981): 16%|█▋ | 41/250 [00:21<01:07, 3.08it/s] Training 1/1 epoch (loss 2.9121): 16%|█▋ | 41/250 [00:21<01:07, 3.08it/s] Training 1/1 epoch (loss 2.9121): 17%|█▋ | 42/250 [00:21<01:08, 3.04it/s] Training 1/1 epoch (loss 2.7552): 17%|█▋ | 42/250 [00:22<01:08, 3.04it/s] Training 1/1 epoch (loss 2.7552): 17%|█▋ | 43/250 [00:22<01:07, 3.07it/s] Training 1/1 epoch (loss 2.8394): 17%|█▋ | 43/250 [00:22<01:07, 3.07it/s] Training 1/1 epoch (loss 2.8394): 18%|█▊ | 44/250 [00:22<01:12, 2.85it/s] Training 1/1 epoch (loss 2.9630): 18%|█▊ | 44/250 [00:22<01:12, 2.85it/s] Training 1/1 epoch (loss 2.9630): 18%|█▊ | 45/250 [00:22<01:12, 2.83it/s] Training 1/1 epoch (loss 3.0351): 18%|█▊ | 45/250 [00:23<01:12, 2.83it/s] Training 1/1 epoch (loss 3.0351): 18%|█▊ | 46/250 [00:23<01:09, 2.94it/s] Training 1/1 epoch (loss 3.0776): 18%|█▊ | 46/250 [00:23<01:09, 2.94it/s] Training 1/1 epoch (loss 3.0776): 19%|█▉ | 47/250 [00:23<01:07, 3.02it/s] Training 1/1 epoch (loss 3.0304): 19%|█▉ | 47/250 [00:23<01:07, 3.02it/s] Training 1/1 epoch (loss 3.0304): 19%|█▉ | 48/250 [00:23<01:12, 2.79it/s] Training 1/1 epoch (loss 2.8088): 19%|█▉ | 48/250 [00:24<01:12, 2.79it/s] Training 1/1 epoch (loss 2.8088): 20%|█▉ | 49/250 [00:24<01:10, 2.84it/s] Training 1/1 epoch (loss 2.8677): 20%|█▉ | 49/250 [00:24<01:10, 2.84it/s] Training 1/1 epoch (loss 2.8677): 20%|██ | 50/250 [00:24<01:12, 2.75it/s] Training 1/1 epoch (loss 2.9854): 20%|██ | 50/250 [00:25<01:12, 2.75it/s] Training 1/1 epoch (loss 2.9854): 20%|██ | 51/250 [00:25<01:13, 2.71it/s] Training 1/1 epoch (loss 2.9369): 20%|██ | 51/250 [00:25<01:13, 2.71it/s] Training 1/1 epoch (loss 2.9369): 21%|██ | 52/250 [00:25<01:10, 2.82it/s] Training 1/1 epoch (loss 2.8369): 21%|██ | 52/250 [00:25<01:10, 2.82it/s] Training 1/1 epoch (loss 2.8369): 21%|██ | 53/250 [00:25<01:06, 2.94it/s] Training 1/1 epoch (loss 2.9919): 21%|██ | 53/250 [00:26<01:06, 2.94it/s] Training 1/1 epoch (loss 2.9919): 22%|██▏ | 54/250 [00:26<01:05, 2.97it/s] Training 1/1 epoch (loss 2.7437): 22%|██▏ | 54/250 [00:26<01:05, 2.97it/s] Training 1/1 epoch (loss 2.7437): 22%|██▏ | 55/250 [00:26<01:04, 3.01it/s] Training 1/1 epoch (loss 2.7115): 22%|██▏ | 55/250 [00:26<01:04, 3.01it/s] Training 1/1 epoch (loss 2.7115): 22%|██▏ | 56/250 [00:26<01:09, 2.81it/s] Training 1/1 epoch (loss 2.8008): 22%|██▏ | 56/250 [00:27<01:09, 2.81it/s] Training 1/1 epoch (loss 2.8008): 23%|██▎ | 57/250 [00:27<01:08, 2.84it/s] Training 1/1 epoch (loss 3.0737): 23%|██▎ | 57/250 [00:27<01:08, 2.84it/s] Training 1/1 epoch (loss 3.0737): 23%|██▎ | 58/250 [00:27<01:04, 2.97it/s] Training 1/1 epoch (loss 3.1533): 23%|██▎ | 58/250 [00:27<01:04, 2.97it/s] Training 1/1 epoch (loss 3.1533): 24%|██▎ | 59/250 [00:27<01:05, 2.94it/s] Training 1/1 epoch (loss 2.9432): 24%|██▎ | 59/250 [00:28<01:05, 2.94it/s] Training 1/1 epoch (loss 2.9432): 24%|██▍ | 60/250 [00:28<01:03, 2.98it/s] Training 1/1 epoch (loss 2.7887): 24%|██▍ | 60/250 [00:28<01:03, 2.98it/s] Training 1/1 epoch (loss 2.7887): 24%|██▍ | 61/250 [00:28<01:04, 2.92it/s] Training 1/1 epoch (loss 2.9347): 24%|██▍ | 61/250 [00:28<01:04, 2.92it/s] Training 1/1 epoch (loss 2.9347): 25%|██▍ | 62/250 [00:28<01:08, 2.76it/s] Training 1/1 epoch (loss 2.9433): 25%|██▍ | 62/250 [00:29<01:08, 2.76it/s] Training 1/1 epoch (loss 2.9433): 25%|██▌ | 63/250 [00:29<01:03, 2.95it/s] Training 1/1 epoch (loss 2.7820): 25%|██▌ | 63/250 [00:29<01:03, 2.95it/s] Training 1/1 epoch (loss 2.7820): 26%|██▌ | 64/250 [00:29<01:02, 2.96it/s] Training 1/1 epoch (loss 2.8712): 26%|██▌ | 64/250 [00:29<01:02, 2.96it/s] Training 1/1 epoch (loss 2.8712): 26%|██▌ | 65/250 [00:29<01:00, 3.05it/s] Training 1/1 epoch (loss 2.8959): 26%|██▌ | 65/250 [00:30<01:00, 3.05it/s] Training 1/1 epoch (loss 2.8959): 26%|██▋ | 66/250 [00:30<01:04, 2.84it/s] Training 1/1 epoch (loss 2.8169): 26%|██▋ | 66/250 [00:30<01:04, 2.84it/s] Training 1/1 epoch (loss 2.8169): 27%|██▋ | 67/250 [00:30<01:02, 2.94it/s] Training 1/1 epoch (loss 2.7407): 27%|██▋ | 67/250 [00:30<01:02, 2.94it/s] Training 1/1 epoch (loss 2.7407): 27%|██▋ | 68/250 [00:30<01:05, 2.79it/s] Training 1/1 epoch (loss 2.7547): 27%|██▋ | 68/250 [00:31<01:05, 2.79it/s] Training 1/1 epoch (loss 2.7547): 28%|██▊ | 69/250 [00:31<01:02, 2.89it/s] Training 1/1 epoch (loss 3.0405): 28%|██▊ | 69/250 [00:31<01:02, 2.89it/s] Training 1/1 epoch (loss 3.0405): 28%|██▊ | 70/250 [00:31<00:59, 3.01it/s] Training 1/1 epoch (loss 2.7963): 28%|██▊ | 70/250 [00:31<00:59, 3.01it/s] Training 1/1 epoch (loss 2.7963): 28%|██▊ | 71/250 [00:31<00:57, 3.10it/s] Training 1/1 epoch (loss 2.9995): 28%|██▊ | 71/250 [00:32<00:57, 3.10it/s] Training 1/1 epoch (loss 2.9995): 29%|██▉ | 72/250 [00:32<00:58, 3.04it/s] Training 1/1 epoch (loss 2.6801): 29%|██▉ | 72/250 [00:32<00:58, 3.04it/s] Training 1/1 epoch (loss 2.6801): 29%|██▉ | 73/250 [00:32<00:59, 2.98it/s] Training 1/1 epoch (loss 2.7230): 29%|██▉ | 73/250 [00:32<00:59, 2.98it/s] Training 1/1 epoch (loss 2.7230): 30%|██▉ | 74/250 [00:32<01:03, 2.77it/s] Training 1/1 epoch (loss 3.0787): 30%|██▉ | 74/250 [00:33<01:03, 2.77it/s] Training 1/1 epoch (loss 3.0787): 30%|███ | 75/250 [00:33<00:58, 2.98it/s] Training 1/1 epoch (loss 2.7310): 30%|███ | 75/250 [00:33<00:58, 2.98it/s] Training 1/1 epoch (loss 2.7310): 30%|███ | 76/250 [00:33<00:59, 2.94it/s] Training 1/1 epoch (loss 2.6970): 30%|███ | 76/250 [00:33<00:59, 2.94it/s] Training 1/1 epoch (loss 2.6970): 31%|███ | 77/250 [00:33<00:57, 3.01it/s] Training 1/1 epoch (loss 2.7959): 31%|███ | 77/250 [00:34<00:57, 3.01it/s] Training 1/1 epoch (loss 2.7959): 31%|███ | 78/250 [00:34<00:57, 3.02it/s] Training 1/1 epoch (loss 2.8402): 31%|███ | 78/250 [00:34<00:57, 3.02it/s] Training 1/1 epoch (loss 2.8402): 32%|███▏ | 79/250 [00:34<01:14, 2.29it/s] Training 1/1 epoch (loss 2.8734): 32%|███▏ | 79/250 [00:35<01:14, 2.29it/s] Training 1/1 epoch (loss 2.8734): 32%|███▏ | 80/250 [00:35<01:09, 2.46it/s] Training 1/1 epoch (loss 3.0184): 32%|███▏ | 80/250 [00:35<01:09, 2.46it/s] Training 1/1 epoch (loss 3.0184): 32%|███▏ | 81/250 [00:35<01:14, 2.28it/s] Training 1/1 epoch (loss 3.0716): 32%|███▏ | 81/250 [00:36<01:14, 2.28it/s] Training 1/1 epoch (loss 3.0716): 33%|███▎ | 82/250 [00:36<01:07, 2.49it/s] Training 1/1 epoch (loss 2.9271): 33%|███▎ | 82/250 [00:36<01:07, 2.49it/s] Training 1/1 epoch (loss 2.9271): 33%|███▎ | 83/250 [00:36<01:04, 2.57it/s] Training 1/1 epoch (loss 2.7876): 33%|███▎ | 83/250 [00:36<01:04, 2.57it/s] Training 1/1 epoch (loss 2.7876): 34%|███▎ | 84/250 [00:36<00:59, 2.79it/s] Training 1/1 epoch (loss 3.0099): 34%|███▎ | 84/250 [00:37<00:59, 2.79it/s] Training 1/1 epoch (loss 3.0099): 34%|███▍ | 85/250 [00:37<01:02, 2.65it/s] Training 1/1 epoch (loss 2.8661): 34%|███▍ | 85/250 [00:37<01:02, 2.65it/s] Training 1/1 epoch (loss 2.8661): 34%|███▍ | 86/250 [00:37<00:58, 2.80it/s] Training 1/1 epoch (loss 2.8720): 34%|███▍ | 86/250 [00:37<00:58, 2.80it/s] Training 1/1 epoch (loss 2.8720): 35%|███▍ | 87/250 [00:37<00:57, 2.84it/s] Training 1/1 epoch (loss 2.8479): 35%|███▍ | 87/250 [00:38<00:57, 2.84it/s] Training 1/1 epoch (loss 2.8479): 35%|███▌ | 88/250 [00:38<00:56, 2.87it/s] Training 1/1 epoch (loss 2.9156): 35%|███▌ | 88/250 [00:38<00:56, 2.87it/s] Training 1/1 epoch (loss 2.9156): 36%|███▌ | 89/250 [00:38<00:57, 2.82it/s] Training 1/1 epoch (loss 2.9804): 36%|███▌ | 89/250 [00:38<00:57, 2.82it/s] Training 1/1 epoch (loss 2.9804): 36%|███▌ | 90/250 [00:38<00:54, 2.95it/s] Training 1/1 epoch (loss 2.9829): 36%|███▌ | 90/250 [00:39<00:54, 2.95it/s] Training 1/1 epoch (loss 2.9829): 36%|███▋ | 91/250 [00:39<00:57, 2.78it/s] Training 1/1 epoch (loss 2.7605): 36%|███▋ | 91/250 [00:39<00:57, 2.78it/s] Training 1/1 epoch (loss 2.7605): 37%|███▋ | 92/250 [00:39<00:54, 2.91it/s] Training 1/1 epoch (loss 2.5390): 37%|███▋ | 92/250 [00:39<00:54, 2.91it/s] Training 1/1 epoch (loss 2.5390): 37%|███▋ | 93/250 [00:39<00:52, 3.01it/s] Training 1/1 epoch (loss 2.9113): 37%|███▋ | 93/250 [00:40<00:52, 3.01it/s] Training 1/1 epoch (loss 2.9113): 38%|███▊ | 94/250 [00:40<00:53, 2.91it/s] Training 1/1 epoch (loss 2.9765): 38%|███▊ | 94/250 [00:40<00:53, 2.91it/s] Training 1/1 epoch (loss 2.9765): 38%|███▊ | 95/250 [00:40<00:51, 3.00it/s] Training 1/1 epoch (loss 2.7962): 38%|███▊ | 95/250 [00:40<00:51, 3.00it/s] Training 1/1 epoch (loss 2.7962): 38%|███▊ | 96/250 [00:40<00:52, 2.94it/s] Training 1/1 epoch (loss 2.8831): 38%|███▊ | 96/250 [00:41<00:52, 2.94it/s] Training 1/1 epoch (loss 2.8831): 39%|███▉ | 97/250 [00:41<00:55, 2.77it/s] Training 1/1 epoch (loss 2.8831): 39%|███▉ | 97/250 [00:41<00:55, 2.77it/s] Training 1/1 epoch (loss 2.8831): 39%|███▉ | 98/250 [00:41<00:51, 2.96it/s] Training 1/1 epoch (loss 2.9433): 39%|███▉ | 98/250 [00:41<00:51, 2.96it/s] Training 1/1 epoch (loss 2.9433): 40%|███▉ | 99/250 [00:41<00:50, 3.01it/s] Training 1/1 epoch (loss 2.9080): 40%|███▉ | 99/250 [00:42<00:50, 3.01it/s] Training 1/1 epoch (loss 2.9080): 40%|████ | 100/250 [00:42<00:50, 3.00it/s] Training 1/1 epoch (loss 2.8043): 40%|████ | 100/250 [00:42<00:50, 3.00it/s] Training 1/1 epoch (loss 2.8043): 40%|████ | 101/250 [00:42<00:47, 3.12it/s] Training 1/1 epoch (loss 2.9029): 40%|████ | 101/250 [00:42<00:47, 3.12it/s] Training 1/1 epoch (loss 2.9029): 41%|████ | 102/250 [00:42<00:47, 3.10it/s] Training 1/1 epoch (loss 2.9736): 41%|████ | 102/250 [00:43<00:47, 3.10it/s] Training 1/1 epoch (loss 2.9736): 41%|████ | 103/250 [00:43<00:49, 2.96it/s] Training 1/1 epoch (loss 2.8638): 41%|████ | 103/250 [00:43<00:49, 2.96it/s] Training 1/1 epoch (loss 2.8638): 42%|████▏ | 104/250 [00:43<00:48, 3.03it/s] Training 1/1 epoch (loss 2.8801): 42%|████▏ | 104/250 [00:43<00:48, 3.03it/s] Training 1/1 epoch (loss 2.8801): 42%|████▏ | 105/250 [00:43<00:47, 3.05it/s] Training 1/1 epoch (loss 2.6284): 42%|████▏ | 105/250 [00:44<00:47, 3.05it/s] Training 1/1 epoch (loss 2.6284): 42%|████▏ | 106/250 [00:44<00:45, 3.15it/s] Training 1/1 epoch (loss 2.9856): 42%|████▏ | 106/250 [00:44<00:45, 3.15it/s] Training 1/1 epoch (loss 2.9856): 43%|████▎ | 107/250 [00:44<00:46, 3.06it/s] Training 1/1 epoch (loss 3.0391): 43%|████▎ | 107/250 [00:44<00:46, 3.06it/s] Training 1/1 epoch (loss 3.0391): 43%|████▎ | 108/250 [00:44<00:46, 3.07it/s] Training 1/1 epoch (loss 2.7468): 43%|████▎ | 108/250 [00:45<00:46, 3.07it/s] Training 1/1 epoch (loss 2.7468): 44%|████▎ | 109/250 [00:45<00:48, 2.90it/s] Training 1/1 epoch (loss 2.9060): 44%|████▎ | 109/250 [00:45<00:48, 2.90it/s] Training 1/1 epoch (loss 2.9060): 44%|████▍ | 110/250 [00:45<00:47, 2.93it/s] Training 1/1 epoch (loss 2.8874): 44%|████▍ | 110/250 [00:45<00:47, 2.93it/s] Training 1/1 epoch (loss 2.8874): 44%|████▍ | 111/250 [00:45<00:46, 3.01it/s] Training 1/1 epoch (loss 2.9917): 44%|████▍ | 111/250 [00:46<00:46, 3.01it/s] Training 1/1 epoch (loss 2.9917): 45%|████▍ | 112/250 [00:46<00:49, 2.81it/s] Training 1/1 epoch (loss 2.9446): 45%|████▍ | 112/250 [00:46<00:49, 2.81it/s] Training 1/1 epoch (loss 2.9446): 45%|████▌ | 113/250 [00:46<00:47, 2.88it/s] Training 1/1 epoch (loss 2.9152): 45%|████▌ | 113/250 [00:46<00:47, 2.88it/s] Training 1/1 epoch (loss 2.9152): 46%|████▌ | 114/250 [00:46<00:46, 2.91it/s] Training 1/1 epoch (loss 2.7549): 46%|████▌ | 114/250 [00:47<00:46, 2.91it/s] Training 1/1 epoch (loss 2.7549): 46%|████▌ | 115/250 [00:47<00:46, 2.89it/s] Training 1/1 epoch (loss 2.8923): 46%|████▌ | 115/250 [00:47<00:46, 2.89it/s] Training 1/1 epoch (loss 2.8923): 46%|████▋ | 116/250 [00:47<00:44, 2.99it/s] Training 1/1 epoch (loss 2.9197): 46%|████▋ | 116/250 [00:47<00:44, 2.99it/s] Training 1/1 epoch (loss 2.9197): 47%|████▋ | 117/250 [00:47<00:45, 2.96it/s] Training 1/1 epoch (loss 2.8291): 47%|████▋ | 117/250 [00:48<00:45, 2.96it/s] Training 1/1 epoch (loss 2.8291): 47%|████▋ | 118/250 [00:48<00:43, 3.01it/s] Training 1/1 epoch (loss 2.8796): 47%|████▋ | 118/250 [00:48<00:43, 3.01it/s] Training 1/1 epoch (loss 2.8796): 48%|████▊ | 119/250 [00:48<00:43, 3.04it/s] Training 1/1 epoch (loss 2.8862): 48%|████▊ | 119/250 [00:48<00:43, 3.04it/s] Training 1/1 epoch (loss 2.8862): 48%|████▊ | 120/250 [00:48<00:44, 2.95it/s] Training 1/1 epoch (loss 2.9230): 48%|████▊ | 120/250 [00:49<00:44, 2.95it/s] Training 1/1 epoch (loss 2.9230): 48%|████▊ | 121/250 [00:49<00:43, 2.99it/s] Training 1/1 epoch (loss 2.7878): 48%|████▊ | 121/250 [00:49<00:43, 2.99it/s] Training 1/1 epoch (loss 2.7878): 49%|████▉ | 122/250 [00:49<00:42, 3.01it/s] Training 1/1 epoch (loss 2.8874): 49%|████▉ | 122/250 [00:49<00:42, 3.01it/s] Training 1/1 epoch (loss 2.8874): 49%|████▉ | 123/250 [00:49<00:40, 3.12it/s] Training 1/1 epoch (loss 3.0631): 49%|████▉ | 123/250 [00:50<00:40, 3.12it/s] Training 1/1 epoch (loss 3.0631): 50%|████▉ | 124/250 [00:50<00:40, 3.09it/s] Training 1/1 epoch (loss 2.8415): 50%|████▉ | 124/250 [00:50<00:40, 3.09it/s] Training 1/1 epoch (loss 2.8415): 50%|█████ | 125/250 [00:50<00:42, 2.96it/s] Training 1/1 epoch (loss 3.0931): 50%|█████ | 125/250 [00:50<00:42, 2.96it/s] Training 1/1 epoch (loss 3.0931): 50%|█████ | 126/250 [00:50<00:40, 3.08it/s] Training 1/1 epoch (loss 2.9303): 50%|█████ | 126/250 [00:51<00:40, 3.08it/s] Training 1/1 epoch (loss 2.9303): 51%|█████ | 127/250 [00:51<00:41, 2.94it/s] Training 1/1 epoch (loss 3.0772): 51%|█████ | 127/250 [00:51<00:41, 2.94it/s] Training 1/1 epoch (loss 3.0772): 51%|█████ | 128/250 [00:51<00:41, 2.91it/s] Training 1/1 epoch (loss 2.7777): 51%|█████ | 128/250 [00:51<00:41, 2.91it/s] Training 1/1 epoch (loss 2.7777): 52%|█████▏ | 129/250 [00:51<00:41, 2.93it/s] Training 1/1 epoch (loss 2.7818): 52%|█████▏ | 129/250 [00:52<00:41, 2.93it/s] Training 1/1 epoch (loss 2.7818): 52%|█████▏ | 130/250 [00:52<00:40, 2.99it/s] Training 1/1 epoch (loss 2.8807): 52%|█████▏ | 130/250 [00:52<00:40, 2.99it/s] Training 1/1 epoch (loss 2.8807): 52%|█████▏ | 131/250 [00:52<00:39, 3.04it/s] Training 1/1 epoch (loss 2.7691): 52%|█████▏ | 131/250 [00:52<00:39, 3.04it/s] Training 1/1 epoch (loss 2.7691): 53%|█████▎ | 132/250 [00:52<00:39, 2.96it/s] Training 1/1 epoch (loss 2.8665): 53%|█████▎ | 132/250 [00:53<00:39, 2.96it/s] Training 1/1 epoch (loss 2.8665): 53%|█████▎ | 133/250 [00:53<00:42, 2.78it/s] Training 1/1 epoch (loss 3.0312): 53%|█████▎ | 133/250 [00:53<00:42, 2.78it/s] Training 1/1 epoch (loss 3.0312): 54%|█████▎ | 134/250 [00:53<00:40, 2.83it/s] Training 1/1 epoch (loss 2.9349): 54%|█████▎ | 134/250 [00:53<00:40, 2.83it/s] Training 1/1 epoch (loss 2.9349): 54%|█████▍ | 135/250 [00:53<00:39, 2.91it/s] Training 1/1 epoch (loss 3.1792): 54%|█████▍ | 135/250 [00:54<00:39, 2.91it/s] Training 1/1 epoch (loss 3.1792): 54%|█████▍ | 136/250 [00:54<00:40, 2.84it/s] Training 1/1 epoch (loss 2.9692): 54%|█████▍ | 136/250 [00:54<00:40, 2.84it/s] Training 1/1 epoch (loss 2.9692): 55%|█████▍ | 137/250 [00:54<00:39, 2.89it/s] Training 1/1 epoch (loss 2.8729): 55%|█████▍ | 137/250 [00:55<00:39, 2.89it/s] Training 1/1 epoch (loss 2.8729): 55%|█████▌ | 138/250 [00:55<00:38, 2.91it/s] Training 1/1 epoch (loss 2.7611): 55%|█████▌ | 138/250 [00:55<00:38, 2.91it/s] Training 1/1 epoch (loss 2.7611): 56%|█████▌ | 139/250 [00:55<00:37, 2.98it/s] Training 1/1 epoch (loss 3.1251): 56%|█████▌ | 139/250 [00:55<00:37, 2.98it/s] Training 1/1 epoch (loss 3.1251): 56%|█████▌ | 140/250 [00:55<00:36, 3.01it/s] Training 1/1 epoch (loss 2.6513): 56%|█████▌ | 140/250 [00:55<00:36, 3.01it/s] Training 1/1 epoch (loss 2.6513): 56%|█████▋ | 141/250 [00:55<00:36, 3.00it/s] Training 1/1 epoch (loss 2.9585): 56%|█████▋ | 141/250 [00:56<00:36, 3.00it/s] Training 1/1 epoch (loss 2.9585): 57%|█████▋ | 142/250 [00:56<00:36, 2.97it/s] Training 1/1 epoch (loss 2.9004): 57%|█████▋ | 142/250 [00:56<00:36, 2.97it/s] Training 1/1 epoch (loss 2.9004): 57%|█████▋ | 143/250 [00:56<00:36, 2.96it/s] Training 1/1 epoch (loss 2.8449): 57%|█████▋ | 143/250 [00:57<00:36, 2.96it/s] Training 1/1 epoch (loss 2.8449): 58%|█████▊ | 144/250 [00:57<00:36, 2.94it/s] Training 1/1 epoch (loss 2.7722): 58%|█████▊ | 144/250 [00:57<00:36, 2.94it/s] Training 1/1 epoch (loss 2.7722): 58%|█████▊ | 145/250 [00:57<00:35, 2.99it/s] Training 1/1 epoch (loss 2.8626): 58%|█████▊ | 145/250 [00:57<00:35, 2.99it/s] Training 1/1 epoch (loss 2.8626): 58%|█████▊ | 146/250 [00:57<00:34, 2.97it/s] Training 1/1 epoch (loss 2.8917): 58%|█████▊ | 146/250 [00:57<00:34, 2.97it/s] Training 1/1 epoch (loss 2.8917): 59%|█████▉ | 147/250 [00:57<00:34, 3.03it/s] Training 1/1 epoch (loss 3.0023): 59%|█████▉ | 147/250 [00:58<00:34, 3.03it/s] Training 1/1 epoch (loss 3.0023): 59%|█████▉ | 148/250 [00:58<00:34, 2.92it/s] Training 1/1 epoch (loss 2.9360): 59%|█████▉ | 148/250 [00:58<00:34, 2.92it/s] Training 1/1 epoch (loss 2.9360): 60%|█████▉ | 149/250 [00:58<00:32, 3.06it/s] Training 1/1 epoch (loss 2.9851): 60%|█████▉ | 149/250 [00:58<00:32, 3.06it/s] Training 1/1 epoch (loss 2.9851): 60%|██████ | 150/250 [00:58<00:32, 3.08it/s] Training 1/1 epoch (loss 2.6597): 60%|██████ | 150/250 [00:59<00:32, 3.08it/s] Training 1/1 epoch (loss 2.6597): 60%|██████ | 151/250 [00:59<00:33, 2.97it/s] Training 1/1 epoch (loss 3.0012): 60%|██████ | 151/250 [00:59<00:33, 2.97it/s] Training 1/1 epoch (loss 3.0012): 61%|██████ | 152/250 [00:59<00:33, 2.94it/s] Training 1/1 epoch (loss 2.7538): 61%|██████ | 152/250 [01:00<00:33, 2.94it/s] Training 1/1 epoch (loss 2.7538): 61%|██████ | 153/250 [01:00<00:33, 2.92it/s] Training 1/1 epoch (loss 2.8736): 61%|██████ | 153/250 [01:00<00:33, 2.92it/s] Training 1/1 epoch (loss 2.8736): 62%|██████▏ | 154/250 [01:00<00:33, 2.91it/s] Training 1/1 epoch (loss 2.9623): 62%|██████▏ | 154/250 [01:00<00:33, 2.91it/s] Training 1/1 epoch (loss 2.9623): 62%|██████▏ | 155/250 [01:00<00:31, 3.02it/s] Training 1/1 epoch (loss 3.0655): 62%|██████▏ | 155/250 [01:00<00:31, 3.02it/s] Training 1/1 epoch (loss 3.0655): 62%|██████▏ | 156/250 [01:00<00:29, 3.15it/s] Training 1/1 epoch (loss 2.8502): 62%|██████▏ | 156/250 [01:01<00:29, 3.15it/s] Training 1/1 epoch (loss 2.8502): 63%|██████▎ | 157/250 [01:01<00:31, 2.96it/s] Training 1/1 epoch (loss 2.7783): 63%|██████▎ | 157/250 [01:01<00:31, 2.96it/s] Training 1/1 epoch (loss 2.7783): 63%|██████▎ | 158/250 [01:01<00:29, 3.09it/s] Training 1/1 epoch (loss 2.7863): 63%|██████▎ | 158/250 [01:01<00:29, 3.09it/s] Training 1/1 epoch (loss 2.7863): 64%|██████▎ | 159/250 [01:01<00:29, 3.11it/s] Training 1/1 epoch (loss 2.7115): 64%|██████▎ | 159/250 [01:02<00:29, 3.11it/s] Training 1/1 epoch (loss 2.7115): 64%|██████▍ | 160/250 [01:02<00:29, 3.03it/s] Training 1/1 epoch (loss 2.8615): 64%|██████▍ | 160/250 [01:02<00:29, 3.03it/s] Training 1/1 epoch (loss 2.8615): 64%|██████▍ | 161/250 [01:02<00:29, 2.99it/s] Training 1/1 epoch (loss 2.7495): 64%|██████▍ | 161/250 [01:02<00:29, 2.99it/s] Training 1/1 epoch (loss 2.7495): 65%|██████▍ | 162/250 [01:02<00:28, 3.08it/s] Training 1/1 epoch (loss 2.7999): 65%|██████▍ | 162/250 [01:03<00:28, 3.08it/s] Training 1/1 epoch (loss 2.7999): 65%|██████▌ | 163/250 [01:03<00:29, 2.99it/s] Training 1/1 epoch (loss 2.8108): 65%|██████▌ | 163/250 [01:03<00:29, 2.99it/s] Training 1/1 epoch (loss 2.8108): 66%|██████▌ | 164/250 [01:03<00:27, 3.08it/s] Training 1/1 epoch (loss 2.6783): 66%|██████▌ | 164/250 [01:03<00:27, 3.08it/s] Training 1/1 epoch (loss 2.6783): 66%|██████▌ | 165/250 [01:03<00:28, 3.00it/s] Training 1/1 epoch (loss 2.5218): 66%|██████▌ | 165/250 [01:04<00:28, 3.00it/s] Training 1/1 epoch (loss 2.5218): 66%|██████▋ | 166/250 [01:04<00:31, 2.65it/s] Training 1/1 epoch (loss 2.9099): 66%|██████▋ | 166/250 [01:04<00:31, 2.65it/s] Training 1/1 epoch (loss 2.9099): 67%|██████▋ | 167/250 [01:04<00:35, 2.33it/s] Training 1/1 epoch (loss 3.0178): 67%|██████▋ | 167/250 [01:05<00:35, 2.33it/s] Training 1/1 epoch (loss 3.0178): 67%|██████▋ | 168/250 [01:05<00:33, 2.48it/s] Training 1/1 epoch (loss 2.8553): 67%|██████▋ | 168/250 [01:05<00:33, 2.48it/s] Training 1/1 epoch (loss 2.8553): 68%|██████▊ | 169/250 [01:05<00:33, 2.45it/s] Training 1/1 epoch (loss 2.9165): 68%|██████▊ | 169/250 [01:06<00:33, 2.45it/s] Training 1/1 epoch (loss 2.9165): 68%|██████▊ | 170/250 [01:06<00:31, 2.54it/s] Training 1/1 epoch (loss 2.9279): 68%|██████▊ | 170/250 [01:06<00:31, 2.54it/s] Training 1/1 epoch (loss 2.9279): 68%|██████▊ | 171/250 [01:06<00:29, 2.69it/s] Training 1/1 epoch (loss 2.7077): 68%|██████▊ | 171/250 [01:06<00:29, 2.69it/s] Training 1/1 epoch (loss 2.7077): 69%|██████▉ | 172/250 [01:06<00:27, 2.85it/s] Training 1/1 epoch (loss 2.8073): 69%|██████▉ | 172/250 [01:07<00:27, 2.85it/s] Training 1/1 epoch (loss 2.8073): 69%|██████▉ | 173/250 [01:07<00:29, 2.62it/s] Training 1/1 epoch (loss 2.9363): 69%|██████▉ | 173/250 [01:07<00:29, 2.62it/s] Training 1/1 epoch (loss 2.9363): 70%|██████▉ | 174/250 [01:07<00:26, 2.83it/s] Training 1/1 epoch (loss 2.9026): 70%|██████▉ | 174/250 [01:07<00:26, 2.83it/s] Training 1/1 epoch (loss 2.9026): 70%|███████ | 175/250 [01:07<00:28, 2.67it/s] Training 1/1 epoch (loss 2.9216): 70%|███████ | 175/250 [01:08<00:28, 2.67it/s] Training 1/1 epoch (loss 2.9216): 70%|███████ | 176/250 [01:08<00:27, 2.71it/s] Training 1/1 epoch (loss 2.9627): 70%|███████ | 176/250 [01:08<00:27, 2.71it/s] Training 1/1 epoch (loss 2.9627): 71%|███████ | 177/250 [01:08<00:26, 2.77it/s] Training 1/1 epoch (loss 3.0689): 71%|███████ | 177/250 [01:08<00:26, 2.77it/s] Training 1/1 epoch (loss 3.0689): 71%|███████ | 178/250 [01:08<00:25, 2.84it/s] Training 1/1 epoch (loss 3.0053): 71%|███████ | 178/250 [01:09<00:25, 2.84it/s] Training 1/1 epoch (loss 3.0053): 72%|███████▏ | 179/250 [01:09<00:25, 2.83it/s] Training 1/1 epoch (loss 2.7126): 72%|███████▏ | 179/250 [01:09<00:25, 2.83it/s] Training 1/1 epoch (loss 2.7126): 72%|███████▏ | 180/250 [01:09<00:23, 2.98it/s] Training 1/1 epoch (loss 2.8001): 72%|███████▏ | 180/250 [01:09<00:23, 2.98it/s] Training 1/1 epoch (loss 2.8001): 72%|███████▏ | 181/250 [01:09<00:23, 2.93it/s] Training 1/1 epoch (loss 2.8183): 72%|███████▏ | 181/250 [01:10<00:23, 2.93it/s] Training 1/1 epoch (loss 2.8183): 73%|███████▎ | 182/250 [01:10<00:22, 3.06it/s] Training 1/1 epoch (loss 2.6359): 73%|███████▎ | 182/250 [01:10<00:22, 3.06it/s] Training 1/1 epoch (loss 2.6359): 73%|███████▎ | 183/250 [01:10<00:21, 3.09it/s] Training 1/1 epoch (loss 2.7996): 73%|███████▎ | 183/250 [01:10<00:21, 3.09it/s] Training 1/1 epoch (loss 2.7996): 74%|███████▎ | 184/250 [01:10<00:21, 3.05it/s] Training 1/1 epoch (loss 2.9427): 74%|███████▎ | 184/250 [01:11<00:21, 3.05it/s] Training 1/1 epoch (loss 2.9427): 74%|███████▍ | 185/250 [01:11<00:22, 2.86it/s] Training 1/1 epoch (loss 2.9168): 74%|███████▍ | 185/250 [01:11<00:22, 2.86it/s] Training 1/1 epoch (loss 2.9168): 74%|███████▍ | 186/250 [01:11<00:21, 3.02it/s] Training 1/1 epoch (loss 2.8834): 74%|███████▍ | 186/250 [01:11<00:21, 3.02it/s] Training 1/1 epoch (loss 2.8834): 75%|███████▍ | 187/250 [01:11<00:20, 3.12it/s] Training 1/1 epoch (loss 3.0043): 75%|███████▍ | 187/250 [01:12<00:20, 3.12it/s] Training 1/1 epoch (loss 3.0043): 75%|███████▌ | 188/250 [01:12<00:20, 3.02it/s] Training 1/1 epoch (loss 2.7308): 75%|███████▌ | 188/250 [01:12<00:20, 3.02it/s] Training 1/1 epoch (loss 2.7308): 76%|███████▌ | 189/250 [01:12<00:20, 3.03it/s] Training 1/1 epoch (loss 2.8509): 76%|███████▌ | 189/250 [01:12<00:20, 3.03it/s] Training 1/1 epoch (loss 2.8509): 76%|███████▌ | 190/250 [01:12<00:19, 3.03it/s] Training 1/1 epoch (loss 2.9738): 76%|███████▌ | 190/250 [01:13<00:19, 3.03it/s] Training 1/1 epoch (loss 2.9738): 76%|███████▋ | 191/250 [01:13<00:19, 2.98it/s] Training 1/1 epoch (loss 2.8560): 76%|███████▋ | 191/250 [01:13<00:19, 2.98it/s] Training 1/1 epoch (loss 2.8560): 77%|███████▋ | 192/250 [01:13<00:19, 3.05it/s] Training 1/1 epoch (loss 2.6815): 77%|███████▋ | 192/250 [01:13<00:19, 3.05it/s] Training 1/1 epoch (loss 2.6815): 77%|███████▋ | 193/250 [01:13<00:18, 3.13it/s] Training 1/1 epoch (loss 2.8268): 77%|███████▋ | 193/250 [01:14<00:18, 3.13it/s] Training 1/1 epoch (loss 2.8268): 78%|███████▊ | 194/250 [01:14<00:18, 2.95it/s] Training 1/1 epoch (loss 2.8547): 78%|███████▊ | 194/250 [01:14<00:18, 2.95it/s] Training 1/1 epoch (loss 2.8547): 78%|███████▊ | 195/250 [01:14<00:18, 2.98it/s] Training 1/1 epoch (loss 2.7310): 78%|███████▊ | 195/250 [01:14<00:18, 2.98it/s] Training 1/1 epoch (loss 2.7310): 78%|███████▊ | 196/250 [01:14<00:17, 3.10it/s] Training 1/1 epoch (loss 2.7577): 78%|███████▊ | 196/250 [01:15<00:17, 3.10it/s] Training 1/1 epoch (loss 2.7577): 79%|███████▉ | 197/250 [01:15<00:17, 3.00it/s] Training 1/1 epoch (loss 2.8548): 79%|███████▉ | 197/250 [01:15<00:17, 3.00it/s] Training 1/1 epoch (loss 2.8548): 79%|███████▉ | 198/250 [01:15<00:16, 3.09it/s] Training 1/1 epoch (loss 2.8305): 79%|███████▉ | 198/250 [01:15<00:16, 3.09it/s] Training 1/1 epoch (loss 2.8305): 80%|███████▉ | 199/250 [01:15<00:16, 3.08it/s] Training 1/1 epoch (loss 2.9257): 80%|███████▉ | 199/250 [01:16<00:16, 3.08it/s] Training 1/1 epoch (loss 2.9257): 80%|████████ | 200/250 [01:16<00:16, 2.95it/s] Training 1/1 epoch (loss 2.7121): 80%|████████ | 200/250 [01:16<00:16, 2.95it/s] Training 1/1 epoch (loss 2.7121): 80%|████████ | 201/250 [01:16<00:16, 2.90it/s] Training 1/1 epoch (loss 2.8820): 80%|████████ | 201/250 [01:16<00:16, 2.90it/s] Training 1/1 epoch (loss 2.8820): 81%|████████ | 202/250 [01:16<00:16, 2.97it/s] Training 1/1 epoch (loss 2.8471): 81%|████████ | 202/250 [01:17<00:16, 2.97it/s] Training 1/1 epoch (loss 2.8471): 81%|████████ | 203/250 [01:17<00:15, 3.09it/s] Training 1/1 epoch (loss 2.9012): 81%|████████ | 203/250 [01:17<00:15, 3.09it/s] Training 1/1 epoch (loss 2.9012): 82%|████████▏ | 204/250 [01:17<00:16, 2.85it/s] Training 1/1 epoch (loss 2.8010): 82%|████████▏ | 204/250 [01:17<00:16, 2.85it/s] Training 1/1 epoch (loss 2.8010): 82%|████████▏ | 205/250 [01:17<00:16, 2.81it/s] Training 1/1 epoch (loss 3.0511): 82%|████████▏ | 205/250 [01:18<00:16, 2.81it/s] Training 1/1 epoch (loss 3.0511): 82%|████████▏ | 206/250 [01:18<00:15, 2.85it/s] Training 1/1 epoch (loss 2.9218): 82%|████████▏ | 206/250 [01:18<00:15, 2.85it/s] Training 1/1 epoch (loss 2.9218): 83%|████████▎ | 207/250 [01:18<00:15, 2.80it/s] Training 1/1 epoch (loss 2.7514): 83%|████████▎ | 207/250 [01:18<00:15, 2.80it/s] Training 1/1 epoch (loss 2.7514): 83%|████████▎ | 208/250 [01:18<00:14, 2.88it/s] Training 1/1 epoch (loss 2.8525): 83%|████████▎ | 208/250 [01:19<00:14, 2.88it/s] Training 1/1 epoch (loss 2.8525): 84%|████████▎ | 209/250 [01:19<00:13, 2.93it/s] Training 1/1 epoch (loss 2.7220): 84%|████████▎ | 209/250 [01:19<00:13, 2.93it/s] Training 1/1 epoch (loss 2.7220): 84%|████████▍ | 210/250 [01:19<00:13, 2.90it/s] Training 1/1 epoch (loss 2.8610): 84%|████████▍ | 210/250 [01:20<00:13, 2.90it/s] Training 1/1 epoch (loss 2.8610): 84%|████████▍ | 211/250 [01:20<00:13, 2.89it/s] Training 1/1 epoch (loss 2.8913): 84%|████████▍ | 211/250 [01:20<00:13, 2.89it/s] Training 1/1 epoch (loss 2.8913): 85%|████████▍ | 212/250 [01:20<00:13, 2.82it/s] Training 1/1 epoch (loss 2.7884): 85%|████████▍ | 212/250 [01:20<00:13, 2.82it/s] Training 1/1 epoch (loss 2.7884): 85%|████████▌ | 213/250 [01:20<00:12, 2.88it/s] Training 1/1 epoch (loss 2.9705): 85%|████████▌ | 213/250 [01:21<00:12, 2.88it/s] Training 1/1 epoch (loss 2.9705): 86%|████████▌ | 214/250 [01:21<00:12, 2.99it/s] Training 1/1 epoch (loss 2.9836): 86%|████████▌ | 214/250 [01:21<00:12, 2.99it/s] Training 1/1 epoch (loss 2.9836): 86%|████████▌ | 215/250 [01:21<00:11, 2.98it/s] Training 1/1 epoch (loss 2.8263): 86%|████████▌ | 215/250 [01:21<00:11, 2.98it/s] Training 1/1 epoch (loss 2.8263): 86%|████████▋ | 216/250 [01:21<00:11, 3.04it/s] Training 1/1 epoch (loss 3.0411): 86%|████████▋ | 216/250 [01:22<00:11, 3.04it/s] Training 1/1 epoch (loss 3.0411): 87%|████████▋ | 217/250 [01:22<00:11, 2.98it/s] Training 1/1 epoch (loss 2.8783): 87%|████████▋ | 217/250 [01:22<00:11, 2.98it/s] Training 1/1 epoch (loss 2.8783): 87%|████████▋ | 218/250 [01:22<00:10, 3.00it/s] Training 1/1 epoch (loss 3.0012): 87%|████████▋ | 218/250 [01:22<00:10, 3.00it/s] Training 1/1 epoch (loss 3.0012): 88%|████████▊ | 219/250 [01:22<00:10, 2.95it/s] Training 1/1 epoch (loss 2.9963): 88%|████████▊ | 219/250 [01:23<00:10, 2.95it/s] Training 1/1 epoch (loss 2.9963): 88%|████████▊ | 220/250 [01:23<00:10, 2.93it/s] Training 1/1 epoch (loss 2.8562): 88%|████████▊ | 220/250 [01:23<00:10, 2.93it/s] Training 1/1 epoch (loss 2.8562): 88%|████████▊ | 221/250 [01:23<00:10, 2.87it/s] Training 1/1 epoch (loss 2.8069): 88%|████████▊ | 221/250 [01:23<00:10, 2.87it/s] Training 1/1 epoch (loss 2.8069): 89%|████████▉ | 222/250 [01:23<00:09, 3.00it/s] Training 1/1 epoch (loss 2.7189): 89%|████████▉ | 222/250 [01:24<00:09, 3.00it/s] Training 1/1 epoch (loss 2.7189): 89%|████████▉ | 223/250 [01:24<00:08, 3.02it/s] Training 1/1 epoch (loss 2.8743): 89%|████████▉ | 223/250 [01:24<00:08, 3.02it/s] Training 1/1 epoch (loss 2.8743): 90%|████████▉ | 224/250 [01:24<00:09, 2.83it/s] Training 1/1 epoch (loss 2.8232): 90%|████████▉ | 224/250 [01:24<00:09, 2.83it/s] Training 1/1 epoch (loss 2.8232): 90%|█████████ | 225/250 [01:24<00:08, 2.86it/s] Training 1/1 epoch (loss 2.7487): 90%|█████████ | 225/250 [01:25<00:08, 2.86it/s] Training 1/1 epoch (loss 2.7487): 90%|█████████ | 226/250 [01:25<00:08, 2.73it/s] Training 1/1 epoch (loss 2.4603): 90%|█████████ | 226/250 [01:25<00:08, 2.73it/s] Training 1/1 epoch (loss 2.4603): 91%|█████████ | 227/250 [01:25<00:07, 2.90it/s] Training 1/1 epoch (loss 2.9602): 91%|█████████ | 227/250 [01:25<00:07, 2.90it/s] Training 1/1 epoch (loss 2.9602): 91%|█████████ | 228/250 [01:25<00:07, 2.99it/s] Training 1/1 epoch (loss 2.6884): 91%|█████████ | 228/250 [01:26<00:07, 2.99it/s] Training 1/1 epoch (loss 2.6884): 92%|█████████▏| 229/250 [01:26<00:07, 2.88it/s] Training 1/1 epoch (loss 2.9989): 92%|█████████▏| 229/250 [01:26<00:07, 2.88it/s] Training 1/1 epoch (loss 2.9989): 92%|█████████▏| 230/250 [01:26<00:06, 3.03it/s] Training 1/1 epoch (loss 2.9632): 92%|█████████▏| 230/250 [01:26<00:06, 3.03it/s] Training 1/1 epoch (loss 2.9632): 92%|█████████▏| 231/250 [01:26<00:06, 3.03it/s] Training 1/1 epoch (loss 2.7529): 92%|█████████▏| 231/250 [01:27<00:06, 3.03it/s] Training 1/1 epoch (loss 2.7529): 93%|█████████▎| 232/250 [01:27<00:06, 2.98it/s] Training 1/1 epoch (loss 2.7683): 93%|█████████▎| 232/250 [01:27<00:06, 2.98it/s] Training 1/1 epoch (loss 2.7683): 93%|█████████▎| 233/250 [01:27<00:05, 3.01it/s] Training 1/1 epoch (loss 2.8857): 93%|█████████▎| 233/250 [01:27<00:05, 3.01it/s] Training 1/1 epoch (loss 2.8857): 94%|█████████▎| 234/250 [01:27<00:05, 3.03it/s] Training 1/1 epoch (loss 2.6388): 94%|█████████▎| 234/250 [01:28<00:05, 3.03it/s] Training 1/1 epoch (loss 2.6388): 94%|█████████▍| 235/250 [01:28<00:05, 2.91it/s] Training 1/1 epoch (loss 2.6983): 94%|█████████▍| 235/250 [01:28<00:05, 2.91it/s] Training 1/1 epoch (loss 2.6983): 94%|█████████▍| 236/250 [01:28<00:04, 2.81it/s] Training 1/1 epoch (loss 2.7366): 94%|█████████▍| 236/250 [01:28<00:04, 2.81it/s] Training 1/1 epoch (loss 2.7366): 95%|█████████▍| 237/250 [01:28<00:04, 2.90it/s] Training 1/1 epoch (loss 2.6978): 95%|█████████▍| 237/250 [01:29<00:04, 2.90it/s] Training 1/1 epoch (loss 2.6978): 95%|█████████▌| 238/250 [01:29<00:03, 3.00it/s] Training 1/1 epoch (loss 2.7799): 95%|█████████▌| 238/250 [01:29<00:03, 3.00it/s] Training 1/1 epoch (loss 2.7799): 96%|█████████▌| 239/250 [01:29<00:03, 3.09it/s] Training 1/1 epoch (loss 2.6227): 96%|█████████▌| 239/250 [01:29<00:03, 3.09it/s] Training 1/1 epoch (loss 2.6227): 96%|█████████▌| 240/250 [01:29<00:03, 3.02it/s] Training 1/1 epoch (loss 2.8183): 96%|█████████▌| 240/250 [01:30<00:03, 3.02it/s] Training 1/1 epoch (loss 2.8183): 96%|█████████▋| 241/250 [01:30<00:03, 2.90it/s] Training 1/1 epoch (loss 2.7131): 96%|█████████▋| 241/250 [01:30<00:03, 2.90it/s] Training 1/1 epoch (loss 2.7131): 97%|█████████▋| 242/250 [01:30<00:02, 2.82it/s] Training 1/1 epoch (loss 2.8713): 97%|█████████▋| 242/250 [01:30<00:02, 2.82it/s] Training 1/1 epoch (loss 2.8713): 97%|█████████▋| 243/250 [01:30<00:02, 2.89it/s] Training 1/1 epoch (loss 2.8103): 97%|█████████▋| 243/250 [01:31<00:02, 2.89it/s] Training 1/1 epoch (loss 2.8103): 98%|█████████▊| 244/250 [01:31<00:02, 2.94it/s] Training 1/1 epoch (loss 2.8500): 98%|█████████▊| 244/250 [01:31<00:02, 2.94it/s] Training 1/1 epoch (loss 2.8500): 98%|█████████▊| 245/250 [01:31<00:01, 3.04it/s] Training 1/1 epoch (loss 2.8870): 98%|█████████▊| 245/250 [01:31<00:01, 3.04it/s] Training 1/1 epoch (loss 2.8870): 98%|█████████▊| 246/250 [01:31<00:01, 3.06it/s] Training 1/1 epoch (loss 2.7972): 98%|█████████▊| 246/250 [01:32<00:01, 3.06it/s] Training 1/1 epoch (loss 2.7972): 99%|█████████▉| 247/250 [01:32<00:00, 3.12it/s] Training 1/1 epoch (loss 2.9410): 99%|█████████▉| 247/250 [01:32<00:00, 3.12it/s] Training 1/1 epoch (loss 2.9410): 99%|█████████▉| 248/250 [01:32<00:00, 3.11it/s] Training 1/1 epoch (loss 2.7465): 99%|█████████▉| 248/250 [01:32<00:00, 3.11it/s] Training 1/1 epoch (loss 2.7465): 100%|█████████▉| 249/250 [01:32<00:00, 3.00it/s] Training 1/1 epoch (loss 2.8509): 100%|█████████▉| 249/250 [01:33<00:00, 3.00it/s] Training 1/1 epoch (loss 2.8509): 100%|██████████| 250/250 [01:33<00:00, 3.02it/s] Training 1/1 epoch (loss 2.8509): 100%|██████████| 250/250 [01:33<00:00, 2.68it/s]
tokenizer config file saved in /aifs4su/hansirui_1st/jiayi/setting3-imdb/tinyllama-0.5T/tinyllama-0.5T-s3-Q1-2000-Q2-2000/tokenizer_config.json
Special tokens file saved in /aifs4su/hansirui_1st/jiayi/setting3-imdb/tinyllama-0.5T/tinyllama-0.5T-s3-Q1-2000-Q2-2000/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 0x1550cc80e950>>
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