Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage VLLMUploader
Starting job with name chaiml-q235b-opus-judge-50366-v1-uploader
Waiting for job on chaiml-q235b-opus-judge-50366-v1-uploader to finish
chaiml-q235b-opus-judge-50366-v1-uploader: Using quantization_mode: w4a16
chaiml-q235b-opus-judge-50366-v1-uploader: Checking if ChaiML/q235b_opus_judge_dpo_with_repetition_fixed-step420-merged-W4A16 already exists in ChaiML
chaiml-q235b-opus-judge-50366-v1-uploader: Downloading snapshot of ChaiML/q235b_opus_judge_dpo_with_repetition_fixed-step420-merged...
2026-04-02T07:22:45.767905+00:00 monitor updated for chaiml-q235b-opus-judge_50366_v1
2026-04-02T07:23:45.857086+00:00 monitor updated for chaiml-q235b-opus-judge_50366_v1
2026-04-02T07:24:45.947228+00:00 monitor updated for chaiml-q235b-opus-judge_50366_v1
chaiml-q235b-opus-judge-50366-v1-uploader: Downloaded in 180.371s
chaiml-q235b-opus-judge-50366-v1-uploader: Applying quantization...
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:25:28 INFO __init__.py L202: Patched transformers.models.qwen3_moe.modeling_qwen3_moe.Qwen3MoeSparseMoeBlock -> auto_round.modeling.unfused_moe.qwen3_moe.LinearQwen3MoeSparseMoeBlock[0m
2026-04-02T07:25:46.034454+00:00 monitor updated for chaiml-q235b-opus-judge_50366_v1
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:26:25 INFO base.py L448: `enable_opt_rtn` is turned on, set `--disable_opt_rtn` for higher speed at the cost of accuracy.[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:26:25 INFO base.py L486: using torch.bfloat16 for quantization tuning[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:26:25 INFO base.py L1573: Using predefined ignore_layers: ['mlp.gate'][0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:26:27 INFO base.py L1081: start to compute imatrix[0m
chaiml-q235b-opus-judge-50366-v1-uploader: Warning: You are sending unauthenticated requests to the HF Hub. Please set a HF_TOKEN to enable higher rate limits and faster downloads.
2026-04-02T07:26:46.129950+00:00 monitor updated for chaiml-q235b-opus-judge_50366_v1
chaiml-q235b-opus-judge-50366-v1-uploader: [33;1m2026-04-02 07:26:55 WARNING base.py L1201: MoE layer detected: optimized RTN is disabled for efficiency. Use `--enable_opt_rtn` to force-enable it for MoE layers.[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:26:57 INFO device.py L1468: 'peak_ram': 18.99GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:27:03 INFO device.py L1468: 'peak_ram': 20.29GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:27:10 INFO device.py L1468: 'peak_ram': 21.62GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:27:21 INFO device.py L1468: 'peak_ram': 27.02GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:27:27 INFO device.py L1468: 'peak_ram': 27.02GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:27:34 INFO device.py L1468: 'peak_ram': 27.02GB, 'peak_vram': 11.38GB[0m
2026-04-02T07:27:46.214065+00:00 monitor updated for chaiml-q235b-opus-judge_50366_v1
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:27:40 INFO device.py L1468: 'peak_ram': 27.02GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:27:50 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:27:57 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:28:03 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:28:10 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:28:19 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:28:26 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:28:32 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:28:39 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
2026-04-02T07:28:46.299255+00:00 monitor updated for chaiml-q235b-opus-judge_50366_v1
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:28:48 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:28:55 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:29:01 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:29:08 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:29:17 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:29:24 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:29:30 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:29:37 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
2026-04-02T07:29:46.386173+00:00 monitor updated for chaiml-q235b-opus-judge_50366_v1
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:29:46 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:29:53 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:29:59 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:30:06 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:30:15 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:30:22 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:30:28 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:30:35 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
2026-04-02T07:30:46.475602+00:00 monitor updated for chaiml-q235b-opus-judge_50366_v1
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:30:44 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:30:51 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:30:57 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:31:13 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:31:19 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
Retrying (%r) after connection broken by '%r': %s
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:31:26 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:31:32 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:31:42 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
2026-04-02T07:31:46.555860+00:00 monitor updated for chaiml-q235b-opus-judge_50366_v1
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:31:48 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:31:55 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:32:05 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:32:11 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:32:17 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:32:24 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:32:34 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:32:40 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
2026-04-02T07:32:46.643104+00:00 monitor updated for chaiml-q235b-opus-judge_50366_v1
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:32:47 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:32:53 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:33:03 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:33:09 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:33:16 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:33:22 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:33:31 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:33:38 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:33:44 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
2026-04-02T07:33:47.055905+00:00 monitor updated for chaiml-q235b-opus-judge_50366_v1
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:33:51 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:34:00 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:34:07 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:34:13 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:34:19 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:34:29 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:34:36 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
2026-04-02T07:34:47.265423+00:00 monitor updated for chaiml-q235b-opus-judge_50366_v1
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:34:42 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:34:48 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:35:04 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:35:11 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:35:17 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:35:33 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:35:40 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
2026-04-02T07:35:47.395967+00:00 monitor updated for chaiml-q235b-opus-judge_50366_v1
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:35:46 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:35:56 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:36:02 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:36:08 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:36:15 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:36:24 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:36:31 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:36:37 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
2026-04-02T07:36:47.486013+00:00 monitor updated for chaiml-q235b-opus-judge_50366_v1
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:36:47 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:36:53 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:36:59 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:37:06 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:37:15 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:37:21 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:37:28 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:37:34 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
2026-04-02T07:37:47.607161+00:00 monitor updated for chaiml-q235b-opus-judge_50366_v1
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:37:44 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:37:50 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:37:56 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:38:03 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:38:12 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:38:16 INFO shard_writer.py L208: model has been saved to /dev/shm/model_output/[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [33;1m2026-04-02 07:38:16 WARNING export.py L336: /dev/shm/model_output already exists, this may cause model conflict[0m
chaiml-q235b-opus-judge-50366-v1-uploader: [38;20m2026-04-02 07:38:16 INFO device.py L1468: 'peak_ram': 27.86GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-judge-50366-v1-uploader: Checking if ChaiML/q235b_opus_judge_dpo_with_repetition_fixed-step420-merged-W4A16 already exists in ChaiML
chaiml-q235b-opus-judge-50366-v1-uploader: Creating repo ChaiML/q235b_opus_judge_dpo_with_repetition_fixed-step420-merged-W4A16 and uploading /dev/shm/model_output to it
chaiml-q235b-opus-judge-50366-v1-uploader: ---------- 2026-04-02 07:38:17 (0:00:00) ----------
chaiml-q235b-opus-judge-50366-v1-uploader: Files: hashed 7/32 (21.5M/131.9G) | pre-uploaded: 0/0 (0.0/131.9G) (+30 unsure) | committed: 0/32 (0.0/131.9G) | ignored: 0
chaiml-q235b-opus-judge-50366-v1-uploader: Workers: hashing: 25 | get upload mode: 3 | pre-uploading: 0 | committing: 0 | waiting: 36
chaiml-q235b-opus-judge-50366-v1-uploader: ---------------------------------------------------
2026-04-02T07:38:47.706394+00:00 monitor updated for chaiml-q235b-opus-judge_50366_v1
chaiml-q235b-opus-judge-50366-v1-uploader:
[K[F
[K[F
[K[F
[K[F
[K[F
[K[F
[K[F
chaiml-q235b-opus-judge-50366-v1-uploader: ---------- 2026-04-02 07:39:17 (0:01:00) ----------
chaiml-q235b-opus-judge-50366-v1-uploader: Files: hashed 32/32 (131.9G/131.9G) | pre-uploaded: 10/26 (46.0G/131.9G) | committed: 0/32 (0.0/131.9G) | ignored: 0
chaiml-q235b-opus-judge-50366-v1-uploader: Workers: hashing: 0 | get upload mode: 0 | pre-uploading: 16 | committing: 0 | waiting: 48
chaiml-q235b-opus-judge-50366-v1-uploader: ---------------------------------------------------
2026-04-02T07:39:47.843327+00:00 monitor updated for chaiml-q235b-opus-judge_50366_v1
chaiml-q235b-opus-judge-50366-v1-uploader: Processed model ChaiML/q235b_opus_judge_dpo_with_repetition_fixed-step420-merged in 1079.636s
chaiml-q235b-opus-judge-50366-v1-uploader: creating bucket guanaco-vllm-models
chaiml-q235b-opus-judge-50366-v1-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:56: SyntaxWarning: invalid escape sequence '\.'
chaiml-q235b-opus-judge-50366-v1-uploader: RE_S3_DATESTRING = re.compile('\.[0-9]*(?:[Z\\-\\+]*?)')
chaiml-q235b-opus-judge-50366-v1-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:57: SyntaxWarning: invalid escape sequence '\s'
chaiml-q235b-opus-judge-50366-v1-uploader: RE_XML_NAMESPACE = re.compile(b'^(<?[^>]+?>\s*|\s*)(<\w+) xmlns=[\'"](https?://[^\'"]+)[\'"]', re.MULTILINE)
chaiml-q235b-opus-judge-50366-v1-uploader: cp /dev/shm/model_output/model-00025-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-50366-v1/default/model-00025-of-00025.safetensors
2026-04-02T07:40:47.982328+00:00 monitor updated for chaiml-q235b-opus-judge_50366_v1
chaiml-q235b-opus-judge-50366-v1-uploader: cp /dev/shm/model_output/model-00015-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-50366-v1/default/model-00015-of-00025.safetensors
chaiml-q235b-opus-judge-50366-v1-uploader: cp /dev/shm/model_output/model-00018-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-50366-v1/default/model-00018-of-00025.safetensors
chaiml-q235b-opus-judge-50366-v1-uploader: cp /dev/shm/model_output/model-00008-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-50366-v1/default/model-00008-of-00025.safetensors
chaiml-q235b-opus-judge-50366-v1-uploader: cp /dev/shm/model_output/model-00011-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-50366-v1/default/model-00011-of-00025.safetensors
chaiml-q235b-opus-judge-50366-v1-uploader: cp /dev/shm/model_output/model-00014-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-50366-v1/default/model-00014-of-00025.safetensors
chaiml-q235b-opus-judge-50366-v1-uploader: cp /dev/shm/model_output/model-00003-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-50366-v1/default/model-00003-of-00025.safetensors
chaiml-q235b-opus-judge-50366-v1-uploader: cp /dev/shm/model_output/model-00004-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-50366-v1/default/model-00004-of-00025.safetensors
chaiml-q235b-opus-judge-50366-v1-uploader: cp /dev/shm/model_output/model-00022-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-50366-v1/default/model-00022-of-00025.safetensors
chaiml-q235b-opus-judge-50366-v1-uploader: cp /dev/shm/model_output/model-00019-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-50366-v1/default/model-00019-of-00025.safetensors
chaiml-q235b-opus-judge-50366-v1-uploader: cp /dev/shm/model_output/model-00020-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-50366-v1/default/model-00020-of-00025.safetensors
chaiml-q235b-opus-judge-50366-v1-uploader: cp /dev/shm/model_output/model-00005-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-50366-v1/default/model-00005-of-00025.safetensors
chaiml-q235b-opus-judge-50366-v1-uploader: cp /dev/shm/model_output/model-00009-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-50366-v1/default/model-00009-of-00025.safetensors
chaiml-q235b-opus-judge-50366-v1-uploader: cp /dev/shm/model_output/model-00006-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-50366-v1/default/model-00006-of-00025.safetensors
chaiml-q235b-opus-judge-50366-v1-uploader: cp /dev/shm/model_output/model-00017-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-50366-v1/default/model-00017-of-00025.safetensors
chaiml-q235b-opus-judge-50366-v1-uploader: cp /dev/shm/model_output/model-00023-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-50366-v1/default/model-00023-of-00025.safetensors
chaiml-q235b-opus-judge-50366-v1-uploader: cp /dev/shm/model_output/model-00007-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-50366-v1/default/model-00007-of-00025.safetensors
chaiml-q235b-opus-judge-50366-v1-uploader: cp /dev/shm/model_output/model-00002-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-50366-v1/default/model-00002-of-00025.safetensors
chaiml-q235b-opus-judge-50366-v1-uploader: cp /dev/shm/model_output/model-00001-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-50366-v1/default/model-00001-of-00025.safetensors
chaiml-q235b-opus-judge-50366-v1-uploader: cp /dev/shm/model_output/model-00021-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-50366-v1/default/model-00021-of-00025.safetensors
chaiml-q235b-opus-judge-50366-v1-uploader: cp /dev/shm/model_output/model-00010-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-50366-v1/default/model-00010-of-00025.safetensors
chaiml-q235b-opus-judge-50366-v1-uploader: cp /dev/shm/model_output/model-00016-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-50366-v1/default/model-00016-of-00025.safetensors
chaiml-q235b-opus-judge-50366-v1-uploader: cp /dev/shm/model_output/model-00013-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-50366-v1/default/model-00013-of-00025.safetensors
chaiml-q235b-opus-judge-50366-v1-uploader: cp /dev/shm/model_output/model-00024-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-50366-v1/default/model-00024-of-00025.safetensors
chaiml-q235b-opus-judge-50366-v1-uploader: cp /dev/shm/model_output/model-00012-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-50366-v1/default/model-00012-of-00025.safetensors
Job chaiml-q235b-opus-judge-50366-v1-uploader completed after 1162.98s with status: succeeded
Stopping job with name chaiml-q235b-opus-judge-50366-v1-uploader
Pipeline stage VLLMUploader completed in 1164.03s
run pipeline stage %s
Running pipeline stage VLLMUploaderAMD
Pipeline stage vllm_upload_amd skipped, reason=not amd cluster
Pipeline stage VLLMUploaderAMD completed in 0.19s
run pipeline stage %s
Running pipeline stage VLLMTemplater
Pipeline stage VLLMTemplater completed in 2.11s
run pipeline stage %s
Running pipeline stage VLLMDeployer
Creating inference service chaiml-q235b-opus-judge-50366-v1
Waiting for inference service chaiml-q235b-opus-judge-50366-v1 to be ready
2026-04-02T07:41:48.078775+00:00 monitor updated for chaiml-q235b-opus-judge_50366_v1
2026-04-02T07:42:48.364275+00:00 monitor updated for chaiml-q235b-opus-judge_50366_v1
2026-04-02T07:43:48.526568+00:00 monitor updated for chaiml-q235b-opus-judge_50366_v1
2026-04-02T07:44:48.629133+00:00 monitor updated for chaiml-q235b-opus-judge_50366_v1
Inference service chaiml-q235b-opus-judge-50366-v1 ready after 230.83203268051147s
Pipeline stage VLLMDeployer completed in 231.82s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.6707677841186523s
Received healthy response to inference request in 1.8201699256896973s
Received healthy response to inference request in 1.5161776542663574s
Received healthy response to inference request in 1.4427647590637207s
Received healthy response to inference request in 1.4664185047149658s
Received healthy response to inference request in 1.5829689502716064s
Received healthy response to inference request in 1.750877857208252s
Received healthy response to inference request in 1.5470936298370361s
Received healthy response to inference request in 1.59639573097229s
Received healthy response to inference request in 1.604485273361206s
Received healthy response to inference request in 1.5379889011383057s
Received healthy response to inference request in 1.6695160865783691s
Received healthy response to inference request in 1.5183241367340088s
Received healthy response to inference request in 1.5118775367736816s
Received healthy response to inference request in 1.5759174823760986s
Received healthy response to inference request in 1.4666073322296143s
Received healthy response to inference request in 1.470097303390503s
Received healthy response to inference request in 1.4728991985321045s
Received healthy response to inference request in 1.6130139827728271s
Received healthy response to inference request in 1.506216049194336s
Received healthy response to inference request in 1.5931823253631592s
Received healthy response to inference request in 1.5820963382720947s
Received healthy response to inference request in 1.4637324810028076s
Received healthy response to inference request in 1.5661849975585938s
Received healthy response to inference request in 1.527902364730835s
2026-04-02T07:45:48.817452+00:00 monitor updated for chaiml-q235b-opus-judge_50366_v1
Received healthy response to inference request in 1.470848798751831s
Received healthy response to inference request in 1.4794816970825195s
Received healthy response to inference request in 1.5844664573669434s
Received healthy response to inference request in 1.491117000579834s
Received healthy response to inference request in 2.1019790172576904s
30 requests
0 failed requests
5th percentile: 1.4649411916732789
10th percentile: 1.4665884494781494
20th percentile: 1.4724891185760498
30th percentile: 1.5016863346099854
40th percentile: 1.5174655437469482
50th percentile: 1.542541265487671
60th percentile: 1.5783890247344972
70th percentile: 1.587081217765808
80th percentile: 1.6061910152435304
90th percentile: 1.7578070640563965
95th percentile: 1.9751649260520927
99th percentile: 3.2158190417289747
mean time: 1.640052318572998
Pipeline stage StressChecker completed in 53.20s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 1.71s
Shutdown handler de-registered
chaiml-q235b-opus-judge_50366_v1 status is now deployed due to DeploymentManager action
chaiml-q235b-opus-judge_50366_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-q235b-opus-judge_50366_v1 status is now torndown due to DeploymentManager action