To do: Experiment

1. rt-wmp tran/recv test between two laptop

2. uvc_camera installation on two laptop

3. Experiment:

       Distance vs. RSSI vs. Channel

     1/3/5/10                            1-14(check available channel)

1) Distance measurement in both the good network environment (idle traffic) or poor network environment (busy traffic) 

2) To be measured data:  RSSI, FPS (frame per second)--- rostopic hz

3) Record bags: name format: RSSI-Distance-Channel-Floor-NetworkStatus-time.bag

[INFO|<string>:438] 2025-03-04 19:33:39,759 >> Training completed. Do not forget to share your model on huggingface.co/models =) swanlab: Step 210 on key train/epoch already exists, ignored. swanlab: Step 210 on key train/num_input_tokens_seen already exists, ignored. {'train_runtime': 222.6408, 'train_samples_per_second': 7.546, 'train_steps_per_second': 0.943, 'train_loss': 3.434720888591948, 'epoch': 30.0, 'num_input_tokens_seen': 665264} 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 210/210 [03:39<00:00, 1.04s/it] [INFO|trainer.py:3942] 2025-03-04 19:33:39,764 >> Saving model checkpoint to saves/DeepSeek-R1-1.5B-Distill/lora/train_2025-03-04-19-22-19 [INFO|configuration_utils.py:697] 2025-03-04 19:33:39,782 >> loading configuration file /root/autodl-tmp/ai/models/DeepSeek-R1-Distill-Qwen-1.5B/config.json [INFO|configuration_utils.py:771] 2025-03-04 19:33:39,783 >> Model config Qwen2Config { "architectures": [ "Qwen2ForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151643, "hidden_act": "silu", "hidden_size": 1536, "initializer_range": 0.02, "intermediate_size": 8960, "max_position_embeddings": 131072, "max_window_layers": 21, "model_type": "qwen2", "num_attention_heads": 12, "num_hidden_layers": 28, "num_key_value_heads": 2, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 10000, "sliding_window": 4096, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.49.0", "use_cache": true, "use_mrope": false, "use_sliding_window": false, "vocab_size": 151936 } ***** train metrics ***** epoch = 30.0 num_input_tokens_seen = 665264 total_flos = 5773005GF train_loss = 3.4347 train_runtime = 0:03:42.64 train_samples_per_second = 7.546 train_steps_per_second = 0.943 Figure saved at: saves/DeepSeek-R1-1.5B-Distill/lora/train_2025-03-04-19-22-19/training_loss.png [WARNING|2025-03-04 19:33:40] llamafactory.extras.ploting:162 >> No metric eval_loss to plot. [WARNING|2025-03-04 19:33:40] llamafactory.extras.ploting:162 >> No metric eval_accuracy to plot. [INFO|modelcard.py:449] 2025-03-04 19:33:40,019 >> Dropping the following result as it does not have all the necessary fields: {'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}} swanlab: Experiment dragon-6 has completed swanlab: 🌟 Run `swanlab watch /root/autodl-tmp/ai/LLaMA-Factory/swanlog` to view SwanLab Experiment Dashboard locally swanlab: 🏠 View project at https://swanlab.cn/@chrisfang/llamafactory-test swanlab: 🚀 View run at https://swanlab.cn/@chrisfang/llamafactory-test/runs/l0n927vfjxvq6iclvs3a8 优化空间
最新发布
03-08
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值