Finetuning run times out at evaluation step on multiple devices about litgpt HOT 4 OPEN

(base) ubuntu@ip-10-0-0-185:~/sky_workdir$ litgpt generate base --prompt "Recommend a movie for me to watch during the weekend and explain the reason." --checkpoint_dir checkpoints/mistralai/Mistral-7B-Instruct-v0.1
Loading model 'checkpoints/mistralai/Mistral-7B-Instruct-v0.1/lit_model.pth' with {'name': 'Mistral-7B-Instruct-v0.1', 'hf_config': {'name': 'Mistral-7B-Instruct-v0.1', 'org': 'mistralai'}, 'scale_embeddings': False, 'block_size': 4096, 'vocab_size': 32000, 'padding_multiple': 512, 'padded_vocab_size': 32000, 'n_layer': 32, 'n_head': 32, 'head_size': 128, 'n_embd': 4096, 'rotary_percentage': 1.0, 'parallel_residual': False, 'bias': False, 'lm_head_bias': False, 'n_query_groups': 8, 'shared_attention_norm': False, 'norm_class_name': 'RMSNorm', 'norm_eps': 1e-05, 'mlp_class_name': 'LLaMAMLP', 'gelu_approximate': 'none', 'intermediate_size': 14336, 'rope_condense_ratio': 1, 'rope_base': 10000, 'n_expert': 0, 'n_expert_per_token': 0, 'rope_n_elem': 128}
Time to instantiate model: 0.11 seconds.
Time to load the model weights: 6.73 seconds.
Seed set to 1234
<s>[INST] Recommend a movie for me to watch during the weekend and explain the reason. [/INST] One great movie that I recommend you to watch during the weekend is "The Shawshank Redemption" released in 1994, directed by Frank Darabont and starring Tim Robbins and Morgan Freeman.


Time for inference 1: 2.38 sec total, 21.01 tokens/sec
Memory used: 14.54 GB

(task, pid=9078) distributed_backend=nccl
(task, pid=9078) All distributed processes registered. Starting with 4 processes
(task, pid=9078) ----------------------------------------------------------------------------------------------------
(task, pid=9078) 
(task, pid=9078) [rank: 1] Seed set to 1337
(task, pid=9078) [rank: 3] Seed set to 1337
(task, pid=9078) [rank: 2] Seed set to 1337
(task, pid=9078) [rank: 0] Seed set to 1337
(task, pid=9078) Number of trainable parameters: 76,652,544
(task, pid=9078) Number of non-trainable parameters: 7,241,732,096
(task, pid=9078) The longest sequence length in the train data is 535, the model's maximum sequence length is 535 and context length is 4096
(task, pid=9078) Validating ...
(task, pid=9078) Recommend a movie for me to watch during the weekend and explain the reason.
(task, pid=9078) Below is an instruction that describes a task. Write a response that appropriately completes the request.
(task, pid=9078) 
(task, pid=9078) ### Instruction:
(task, pid=9078) Recommend a movie for me to watch during the weekend and explain the reason.
(task, pid=9078) 
(task, pid=9078) ### Response:
(task, pid=9078) I recommend the movie "The Shawshank Redemption". It's a classic that is widely loved by many people. It's an excellent story with great characters, and it's sure to keep you engaged from start to finish. Additionally, it's a timeless film that has themes that are still relevant today. It's perfect to watch during the weekend because it's a long movie that will give you plenty of time to get absorbed in the story.