developer_uid: zonemercy
submission_id: chaiml-cai-v1-2-dpo-bas_22910_v4
model_name: test
model_group: ChaiML/cai-v1-2-dpo_base
status: torndown
timestamp: 2025-11-05T01:01:40+00:00
num_battles: 5776
num_wins: 3213
celo_rating: 1337.37
family_friendly_score: 0.4658
family_friendly_standard_error: 0.007054507211705152
submission_type: basic
model_repo: ChaiML/cai-v1-2-dpo_basev0-lr5e6b01
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 1
max_input_tokens: 2048
max_output_tokens: 128
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.2810677279901187, 'latency_mean': 3.557755922079086, 'latency_p50': 3.5540329217910767, 'latency_p90': 3.747069478034973}, {'batch_size': 2, 'throughput': 0.46044407495954986, 'latency_mean': 4.34223712682724, 'latency_p50': 4.365335583686829, 'latency_p90': 4.546096849441528}, {'batch_size': 3, 'throughput': 0.6067313453651175, 'latency_mean': 4.926750878095627, 'latency_p50': 4.9175015687942505, 'latency_p90': 5.383564305305481}, {'batch_size': 4, 'throughput': 0.7185554206300279, 'latency_mean': 5.547577011585235, 'latency_p50': 5.556762337684631, 'latency_p90': 6.170244121551514}, {'batch_size': 5, 'throughput': 0.8094960100558134, 'latency_mean': 6.13551295876503, 'latency_p50': 6.1446332931518555, 'latency_p90': 6.6753501176834105}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: test
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: ChaiML/cai-v1-2-dpo_basev0-lr5e6b01
model_size: 24B
ranking_group: single
throughput_3p7s: 0.32
us_pacific_date: 2025-11-01
win_ratio: 0.5562673130193906
generation_params: {'temperature': 0.3, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['You:', '</s>', 'User:'], 'max_input_tokens': 2048, 'best_of': 1, 'max_output_tokens': 128}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '####\n{bot_name}:', 'truncate_by_message': True}
Resubmit model
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer
Waiting for job on chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer to finish
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: ║ ║
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: ║ ║
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: ║ Version: 0.30.2 ║
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: ║ https://mk1.ai ║
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: ║ ║
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: ║ belonging to: ║
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: ║ ║
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: ║ Chai Research Corp. ║
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: ║ ║
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: Downloaded to shared memory in 46.076s
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: Checking if ChaiML/cai-v1-2-dpo_basev0-lr5e6b01 already exists in ChaiML
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmpu0dpsq2m, device:0
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Job chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer completed after 82.64s with status: failed
Stopping job with name chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer
%s, retrying in %s seconds...
Starting job with name chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer
Waiting for job on chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer to finish
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: ║ ║
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: ║ ║
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: ║ Version: 0.30.2 ║
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: ║ https://mk1.ai ║
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: ║ ║
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: ║ belonging to: ║
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: ║ ║
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: ║ Chai Research Corp. ║
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: ║ ║
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: Downloaded to shared memory in 51.996s
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: Checking if ChaiML/cai-v1-2-dpo_basev0-lr5e6b01 already exists in ChaiML
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmphj2vfvm9, device:0
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission mistralai-mistral-nem_93303_v569: ('http://mistralai-mistral-nem-93303-v569-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Failed to get response for submission mistralai-mistral-nem_93303_v569: ('http://mistralai-mistral-nem-93303-v569-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: quantized model in 290.790s
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: Processed model ChaiML/cai-v1-2-dpo_basev0-lr5e6b01 in 342.786s
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: creating bucket guanaco-mkml-models
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-cai-v1-2-dpo-bas-22910-v4/nvidia
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-cai-v1-2-dpo-bas-22910-v4/nvidia/config.json
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-cai-v1-2-dpo-bas-22910-v4/nvidia/special_tokens_map.json
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-cai-v1-2-dpo-bas-22910-v4/nvidia/tokenizer_config.json
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-cai-v1-2-dpo-bas-22910-v4/nvidia/tokenizer.json
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-cai-v1-2-dpo-bas-22910-v4/nvidia/flywheel_model.1.safetensors
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-cai-v1-2-dpo-bas-22910-v4/nvidia/flywheel_model.0.safetensors
chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 3/363 [00:02<04:37, 1.30it/s] Loading 0: 1%| | 4/363 [00:04<06:54, 1.16s/it] Loading 0: 1%|▏ | 5/363 [00:06<08:43, 1.46s/it] Loading 0: 2%|▏ | 8/363 [00:06<04:06, 1.44it/s] Loading 0: 2%|▏ | 9/363 [00:07<03:38, 1.62it/s] Loading 0: 3%|▎ | 10/363 [00:07<03:03, 1.92it/s] Loading 0: 3%|▎ | 12/363 [00:09<04:10, 1.40it/s] Loading 0: 4%|▎ | 13/363 [00:11<05:47, 1.01it/s] Loading 0: 4%|▍ | 14/363 [00:13<07:13, 1.24s/it] Loading 0: 5%|▍ | 17/363 [00:13<03:48, 1.51it/s] Loading 0: 5%|▍ | 18/363 [00:13<03:20, 1.72it/s] Loading 0: 5%|▌ | 19/363 [00:13<02:45, 2.08it/s] Loading 0: 6%|▌ | 21/363 [00:15<03:50, 1.48it/s] Loading 0: 6%|▌ | 22/363 [00:17<05:24, 1.05it/s] Loading 0: 6%|▋ | 23/363 [00:19<06:49, 1.21s/it] Loading 0: 7%|▋ | 26/363 [00:20<03:39, 1.53it/s] Loading 0: 7%|▋ | 27/363 [00:20<03:12, 1.74it/s] Loading 0: 8%|▊ | 28/363 [00:20<02:39, 2.10it/s] Loading 0: 8%|▊ | 30/363 [00:20<01:57, 2.84it/s] Loading 0: 9%|▊ | 31/363 [00:21<01:49, 3.03it/s] Loading 0: 9%|▉ | 32/363 [00:21<01:32, 3.58it/s] Loading 0: 9%|▉ | 33/363 [00:21<01:19, 4.17it/s] Loading 0: 9%|▉ | 34/363 [00:23<03:47, 1.45it/s] Loading 0: 10%|▉ | 35/363 [00:25<05:40, 1.04s/it] Loading 0: 10%|▉ | 36/363 [00:27<07:14, 1.33s/it] Loading 0: 11%|█ | 39/363 [00:29<05:17, 1.02it/s] Loading 0: 11%|█ | 40/363 [00:31<06:27, 1.20s/it] Loading 0: 11%|█▏ | 41/363 [00:33<07:30, 1.40s/it] Loading 0: 12%|█▏ | 44/363 [00:33<04:02, 1.32it/s] Loading 0: 12%|█▏ | 45/363 [00:34<03:31, 1.50it/s] Loading 0: 13%|█▎ | 46/363 [00:34<02:53, 1.83it/s] Loading 0: 13%|█▎ | 48/363 [00:36<03:47, 1.39it/s] Loading 0: 13%|█▎ | 49/363 [00:38<05:12, 1.01it/s] Loading 0: 14%|█▍ | 50/363 [00:40<06:30, 1.25s/it] Loading 0: 15%|█▍ | 53/363 [00:40<03:29, 1.48it/s] Loading 0: 15%|█▍ | 54/363 [00:40<03:03, 1.69it/s] Loading 0: 15%|█▌ | 55/363 [00:41<02:31, 2.04it/s] Loading 0: 16%|█▌ | 57/363 [00:43<03:29, 1.46it/s] Loading 0: 16%|█▌ | 58/363 [00:45<04:54, 1.04it/s] Loading 0: 16%|█▋ | 59/363 [00:47<06:12, 1.23s/it] Loading 0: 17%|█▋ | 62/363 [00:47<03:19, 1.51it/s] Loading 0: 17%|█▋ | 63/363 [00:47<02:55, 1.71it/s] Loading 0: 18%|█▊ | 64/363 [00:47<02:25, 2.05it/s] Loading 0: 18%|█▊ | 65/363 [00:49<04:11, 1.19it/s] Loading 0: 18%|█▊ | 67/363 [00:50<02:47, 1.76it/s] Loading 0: 19%|█▊ | 68/363 [00:50<02:26, 2.01it/s] Loading 0: 19%|█▉ | 69/363 [00:50<02:05, 2.35it/s] Loading 0: 19%|█▉ | 70/363 [00:50<01:41, 2.89it/s] Loading 0: 20%|█▉ | 71/363 [00:52<03:50, 1.27it/s] Loading 0: 20%|█▉ | 72/363 [00:54<05:26, 1.12s/it] Loading 0: 20%|██ | 73/363 [00:56<06:43, 1.39s/it] Loading 0: 21%|██ | 76/363 [00:57<03:16, 1.46it/s] Loading 0: 21%|██ | 77/363 [00:57<02:50, 1.68it/s] Loading 0: 21%|██▏ | 78/363 [00:57<02:18, 2.06it/s] Loading 0: 22%|██▏ | 79/363 [00:59<04:03, 1.17it/s] Loading 0: 22%|██▏ | 80/363 [01:01<05:31, 1.17s/it] Loading 0: 23%|██▎ | 82/363 [01:01<03:27, 1.35it/s] Loading 0: 23%|██▎ | 83/363 [01:02<02:54, 1.60it/s] Loading 0: 23%|██▎ | 84/363 [01:02<02:18, 2.01it/s] Loading 0: 24%|██▎ | 86/363 [01:04<03:15, 1.41it/s] Loading 0: 24%|██▍ | 87/363 [01:06<04:40, 1.02s/it] Loading 0: 25%|██▍ | 90/363 [01:08<03:50, 1.19it/s] Loading 0: 25%|██▌ | 91/363 [01:10<04:48, 1.06s/it] Loading 0: 25%|██▌ | 92/363 [01:12<05:45, 1.27s/it] Loading 0: 26%|██▌ | 95/363 [01:12<03:11, 1.40it/s] Loading 0: 26%|██▋ | 96/363 [01:12<02:47, 1.59it/s] Loading 0: 27%|██▋ | 97/363 [01:12<02:18, 1.92it/s] Loading 0: 27%|██▋ | 99/363 [01:14<03:04, 1.43it/s] Loading 0: 28%|██▊ | 100/363 [01:16<04:15, 1.03it/s] Loading 0: 28%|██▊ | 101/363 [01:19<05:21, 1.23s/it] Loading 0: 29%|██▊ | 104/363 [01:19<02:52, 1.50it/s] Loading 0: 29%|██▉ | 105/363 [01:19<02:31, 1.70it/s] Loading 0: 29%|██▉ | 106/363 [01:19<02:05, 2.05it/s] Loading 0: 29%|██▉ | 107/363 [01:19<01:43, 2.47it/s] Loading 0: 30%|██▉ | 108/363 [01:21<03:25, 1.24it/s] Loading 0: 31%|███ | 111/363 [01:23<03:04, 1.37it/s] Loading 0: 31%|███ | 112/363 [01:25<04:05, 1.02it/s] Loading 0: 31%|███ | 113/363 [01:27<05:05, 1.22s/it] Loading 0: 32%|███▏ | 116/363 [01:28<02:46, 1.48it/s] Loading 0: 32%|███▏ | 117/363 [01:28<02:26, 1.68it/s] Loading 0: 33%|███▎ | 118/363 [01:28<02:00, 2.03it/s] Loading 0: 33%|███▎ | 120/363 [01:30<02:46, 1.46it/s] Loading 0: 33%|███▎ | 121/363 [01:32<03:52, 1.04it/s] Loading 0: 34%|███▎ | 122/363 [01:34<04:53, 1.22s/it] Loading 0: 34%|███▍ | 125/363 [01:34<02:37, 1.51it/s] Loading 0: 35%|███▍ | 126/363 [01:35<02:18, 1.72it/s] Loading 0: 35%|███▍ | 127/363 [01:35<01:54, 2.07it/s] Loading 0: 36%|███▌ | 129/363 [01:37<02:39, 1.47it/s] Loading 0: 36%|███▌ | 130/363 [01:39<03:43, 1.04it/s] Loading 0: 36%|███▌ | 131/363 [01:41<04:42, 1.22s/it] Loading 0: 37%|███▋ | 134/363 [01:41<02:30, 1.52it/s] Loading 0: 37%|███▋ | 135/363 [01:41<02:12, 1.72it/s] Loading 0: 37%|███▋ | 136/363 [01:42<01:49, 2.07it/s] Loading 0: 38%|███▊ | 138/363 [01:44<02:33, 1.47it/s] Loading 0: 38%|███▊ | 139/363 [01:46<03:35, 1.04it/s] Loading 0: 39%|███▊ | 140/363 [01:48<04:32, 1.22s/it] Loading 0: 39%|███▉ | 143/363 [01:48<02:25, 1.51it/s] Loading 0: 40%|███▉ | 144/363 [01:48<02:07, 1.72it/s] Loading 0: 40%|███▉ | 145/363 [01:48<01:45, 2.07it/s] Loading 0: 40%|████ | 147/363 [01:49<01:17, 2.79it/s] Loading 0: 41%|████ | 148/363 [01:49<01:12, 2.98it/s] Loading 0: 41%|████ | 149/363 [01:49<01:00, 3.51it/s] Loading 0: 41%|████▏ | 150/363 [01:49<00:52, 4.06it/s] Loading 0: 42%|████▏ | 151/363 [01:51<02:30, 1.41it/s] Loading 0: 42%|████▏ | 152/363 [01:53<03:43, 1.06s/it] Loading 0: 42%|████▏ | 153/363 [01:55<04:42, 1.35s/it] Loading 0: 43%|████▎ | 156/363 [01:57<03:21, 1.03it/s] Loading 0: 43%|████▎ | 157/363 [01:59<04:03, 1.18s/it] Loading 0: 44%|████▎ | 158/363 [02:01<04:45, 1.39s/it] Loading 0: 44%|████▍ | 161/363 [02:02<02:32, 1.32it/s] Loading 0: 45%|████▍ | 162/363 [02:02<02:12, 1.51it/s] Loading 0: 45%|████▍ | 163/363 [02:02<01:49, 1.83it/s] Loading 0: 45%|████▌ | 165/363 [02:04<02:22, 1.39it/s] Loading 0: 46%|████▌ | 166/363 [02:06<03:15, 1.01it/s] Loading 0: 46%|████▌ | 167/363 [02:08<04:04, 1.25s/it] Loading 0: 47%|████▋ | 170/363 [02:08<02:10, 1.48it/s] Loading 0: 47%|████▋ | 171/363 [02:09<01:54, 1.68it/s] Loading 0: 47%|████▋ | 172/363 [02:09<01:34, 2.03it/s] Loading 0: 48%|████▊ | 174/363 [02:11<02:10, 1.45it/s] Loading 0: 48%|████▊ | 175/363 [02:13<03:02, 1.03it/s] Loading 0: 48%|████▊ | 176/363 [02:15<03:49, 1.23s/it] Loading 0: 49%|████▉ | 179/363 [02:15<02:02, 1.50it/s] Loading 0: 50%|████▉ | 180/363 [02:15<01:47, 1.71it/s] Loading 0: 50%|████▉ | 181/363 [02:15<01:28, 2.06it/s] Loading 0: 50%|█████ | 182/363 [02:18<02:32, 1.18it/s] Loading 0: 51%|█████ | 184/363 [02:18<01:41, 1.76it/s] Loading 0: 51%|█████ | 185/363 [02:18<01:28, 2.01it/s] Loading 0: 51%|█████ | 186/363 [02:18<01:12, 2.45it/s] Loading 0: 52%|█████▏ | 187/363 [02:18<00:59, 2.97it/s] Loading 0: 52%|█████▏ | 188/363 [02:20<02:17, 1.28it/s] Loading 0: 52%|█████▏ | 189/363 [02:22<03:18, 1.14s/it] Loading 0: 53%|█████▎ | 192/363 [02:24<02:31, 1.13it/s] Loading 0: 53%|█████▎ | 193/363 [02:26<03:09, 1.12s/it] Loading 0: 53%|█████▎ | 194/363 [02:28<03:45, 1.33s/it] Loading 0: 54%|█████▍ | 197/363 [02:29<02:00, 1.37it/s] Loading 0: 55%|█████▍ | 198/363 [02:29<01:45, 1.57it/s] Loading 0: 55%|█████▍ | 199/363 [02:29<01:27, 1.88it/s] Loading 0: 55%|█████▌ | 201/363 [02:31<01:55, 1.41it/s] Loading 0: 56%|█████▌ | 202/363 [02:33<02:38, 1.01it/s] Loading 0: 56%|█████▌ | 203/363 [02:35<03:18, 1.24s/it] Loading 0: 57%|█████▋ | 206/363 [02:36<01:45, 1.49it/s] Loading 0: 57%|█████▋ | 207/363 [02:36<01:32, 1.69it/s] Loading 0: 57%|█████▋ | 208/363 [02:36<01:15, 2.05it/s] Loading 0: 58%|█████▊ | 210/363 [02:38<01:44, 1.46it/s] Loading 0: 58%|█████▊ | 211/363 [02:40<02:26, 1.03it/s] Loading 0: 58%|█████▊ | 212/363 [02:42<03:05, 1.23s/it] Loading 0: 59%|█████▉ | 215/363 [02:42<01:38, 1.50it/s] Loading 0: 60%|█████▉ | 216/363 [02:43<01:26, 1.71it/s] Loading 0: 60%|█████▉ | 217/363 [02:43<01:10, 2.06it/s] Loading 0: 60%|██████ | 218/363 [02:45<02:05, 1.16it/s] Loading 0: 60%|██████ | 219/363 [02:47<02:47, 1.16s/it] Loading 0: 61%|██████ | 221/363 [02:47<01:45, 1.35it/s] Loading 0: 61%|██████ | 222/363 [02:47<01:28, 1.59it/s] Loading 0: 61%|██████▏ | 223/363 [02:48<01:10, 1.99it/s] Loading 0: 62%|██████▏ | 224/363 [02:48<00:56, 2.46it/s] Loading 0: 62%|██████▏ | 225/363 [02:50<01:56, 1.19it/s] Loading 0: 63%|██████▎ | 228/363 [02:52<01:40, 1.34it/s] Loading 0: 63%|██████▎ | 229/363 [02:54<02:14, 1.00s/it] Loading 0: 63%|██████▎ | 230/363 [02:56<02:45, 1.25s/it] Loading 0: 64%|██████▍ | 233/363 [02:56<01:29, 1.46it/s] Loading 0: 64%|██████▍ | 234/363 [02:56<01:17, 1.66it/s] Loading 0: 65%|██████▍ | 235/363 [02:56<01:04, 2.00it/s] Loading 0: 65%|██████▌ | 237/363 [02:58<01:26, 1.45it/s] Loading 0: 66%|██████▌ | 238/363 [03:00<02:00, 1.03it/s] Loading 0: 66%|██████▌ | 239/363 [03:03<02:31, 1.22s/it] Loading 0: 67%|██████▋ | 242/363 [03:03<01:20, 1.51it/s] Loading 0: 67%|██████▋ | 243/363 [03:03<01:10, 1.71it/s] Loading 0: 67%|██████▋ | 244/363 [03:03<00:57, 2.06it/s] Loading 0: 68%|██████▊ | 246/363 [03:05<01:19, 1.46it/s] Loading 0: 68%|██████▊ | 247/363 [03:07<01:51, 1.04it/s] Loading 0: 68%|██████▊ | 248/363 [03:09<02:20, 1.23s/it] Loading 0: 69%|██████▉ | 251/363 [03:10<01:14, 1.51it/s] Loading 0: 69%|██████▉ | 252/363 [03:10<01:04, 1.71it/s] Loading 0: 70%|██████▉ | 253/363 [03:10<00:53, 2.06it/s] Loading 0: 70%|███████ | 255/363 [03:12<01:13, 1.46it/s] Loading 0: 71%|███████ | 256/363 [03:14<01:43, 1.04it/s] Loading 0: 71%|███████ | 257/363 [03:16<02:09, 1.22s/it] Loading 0: 72%|███████▏ | 260/363 [03:16<01:08, 1.51it/s] Loading 0: 72%|███████▏ | 261/363 [03:17<00:59, 1.72it/s] Loading 0: 72%|███████▏ | 262/363 [03:17<00:48, 2.07it/s] Loading 0: 73%|███████▎ | 264/363 [03:17<00:35, 2.80it/s] Loading 0: 73%|███████▎ | 265/363 [03:17<00:32, 2.99it/s] Loading 0: 73%|███████▎ | 266/363 [03:17<00:27, 3.53it/s] Loading 0: 74%|███████▎ | 267/363 [03:18<00:23, 4.06it/s] Loading 0: 74%|███████▍ | 268/363 [03:20<01:07, 1.41it/s] Loading 0: 74%|███████▍ | 269/363 [03:22<01:39, 1.06s/it] Loading 0: 74%|███████▍ | 270/363 [03:24<02:05, 1.35s/it] Loading 0: 75%|███████▌ | 273/363 [03:39<05:06, 3.41s/it] Loading 0: 75%|███████▌ | 274/363 [03:41<04:37, 3.12s/it] Loading 0: 76%|███████▌ | 275/363 [03:43<04:14, 2.89s/it] Loading 0: 77%|███████▋ | 278/363 [03:43<02:08, 1.51s/it] Loading 0: 77%|███████▋ | 279/363 [03:44<01:46, 1.27s/it] Loading 0: 77%|███████▋ | 280/363 [03:44<01:24, 1.02s/it] Loading 0: 78%|███████▊ | 282/363 [03:46<01:22, 1.01s/it] Loading 0: 78%|███████▊ | 283/363 [03:48<01:37, 1.22s/it] Loading 0: 78%|███████▊ | 284/363 [03:50<01:52, 1.42s/it] Loading 0: 79%|███████▉ | 287/363 [03:50<00:57, 1.32it/s] Loading 0: 79%|███████▉ | 288/363 [03:50<00:48, 1.53it/s] Loading 0: 80%|███████▉ | 289/363 [03:50<00:39, 1.86it/s] Loading 0: 80%|████████ | 291/363 [03:52<00:51, 1.40it/s] Loading 0: 80%|████████ | 292/363 [03:54<01:10, 1.01it/s] Loading 0: 81%|████████ | 293/363 [03:57<01:26, 1.24s/it] Loading 0: 82%|████████▏ | 296/363 [03:57<00:44, 1.50it/s] Loading 0: 82%|████████▏ | 297/363 [03:57<00:38, 1.72it/s] Loading 0: 82%|████████▏ | 298/363 [03:57<00:31, 2.08it/s] Loading 0: 82%|████████▏ | 299/363 [03:59<00:53, 1.20it/s] Loading 0: 83%|████████▎ | 301/363 [03:59<00:34, 1.80it/s] Loading 0: 83%|████████▎ | 302/363 [04:00<00:29, 2.08it/s] Loading 0: 83%|████████▎ | 303/363 [04:00<00:23, 2.55it/s] Loading 0: 84%|████████▎ | 304/363 [04:00<00:19, 3.08it/s] Loading 0: 84%|████████▍ | 305/363 [04:02<00:44, 1.30it/s] Loading 0: 84%|████████▍ | 306/363 [04:04<01:04, 1.13s/it] Loading 0: 85%|████████▌ | 309/363 [04:06<00:47, 1.14it/s] Loading 0: 85%|████████▌ | 310/363 [04:08<00:58, 1.11s/it] Loading 0: 86%|████████▌ | 311/363 [04:10<01:08, 1.33s/it] Loading 0: 87%|████████▋ | 314/363 [04:10<00:35, 1.39it/s] Loading 0: 87%|████████▋ | 315/363 [04:10<00:29, 1.61it/s] Loading 0: 87%|████████▋ | 316/363 [04:11<00:24, 1.94it/s] Loading 0: 88%|████████▊ | 318/363 [04:13<00:31, 1.43it/s] Loading 0: 88%|████████▊ | 319/363 [04:15<00:42, 1.03it/s] Loading 0: 88%|████████▊ | 320/363 [04:17<00:52, 1.23s/it] Loading 0: 89%|████████▉ | 323/363 [04:17<00:26, 1.51it/s] Loading 0: 89%|████████▉ | 324/363 [04:17<00:22, 1.73it/s] Loading 0: 90%|████████▉ | 325/363 [04:17<00:18, 2.09it/s] Loading 0: 90%|█████████ | 327/363 [04:19<00:24, 1.48it/s] Loading 0: 90%|█████████ | 328/363 [04:21<00:33, 1.04it/s] Loading 0: 91%|█████████ | 329/363 [04:23<00:41, 1.21s/it] Loading 0: 91%|█████████▏| 332/363 [04:24<00:20, 1.53it/s] Loading 0: 92%|█████████▏| 333/363 [04:24<00:17, 1.75it/s] Loading 0: 92%|█████████▏| 334/363 [04:24<00:13, 2.11it/s] Loading 0: 92%|█████████▏| 335/363 [04:26<00:23, 1.20it/s] Loading 0: 93%|█████████▎| 336/363 [04:28<00:30, 1.14s/it] Loading 0: 93%|█████████▎| 338/363 [04:28<00:18, 1.38it/s] Loading 0: 93%|█████████▎| 339/363 [04:29<00:14, 1.64it/s] Loading 0: 94%|█████████▎| 340/363 [04:29<00:11, 2.06it/s] Loading 0: 94%|█████████▍| 341/363 [04:29<00:09, 2.30it/s] Loading 0: 94%|█████████▍| 343/363 [04:31<00:13, 1.48it/s] Loading 0: 95%|█████████▌| 346/363 [04:33<00:11, 1.49it/s] Loading 0: 96%|█████████▌| 347/363 [04:35<00:14, 1.09it/s] Loading 0: 96%|█████████▌| 348/363 [04:37<00:17, 1.15s/it] Loading 0: 97%|█████████▋| 351/363 [04:37<00:07, 1.53it/s] Loading 0: 97%|█████████▋| 352/363 [04:37<00:06, 1.74it/s] Loading 0: 97%|█████████▋| 353/363 [04:38<00:04, 2.09it/s] Loading 0: 98%|█████████▊| 355/363 [04:40<00:05, 1.47it/s] Loading 0: 98%|█████████▊| 356/363 [04:42<00:06, 1.05it/s] Loading 0: 98%|█████████▊| 357/363 [04:44<00:07, 1.21s/it] Loading 0: 99%|█████████▉| 360/363 [04:44<00:01, 1.53it/s] Loading 0: 99%|█████████▉| 361/363 [04:44<00:01, 1.75it/s] Loading 0: 100%|█████████▉| 362/363 [04:44<00:00, 2.11it/s]
Job chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer completed after 428.56s with status: succeeded
Stopping job with name chaiml-cai-v1-2-dpo-bas-22910-v4-mkmlizer
Pipeline stage MKMLizer completed in 512.14s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-cai-v1-2-dpo-bas-22910-v4
Waiting for inference service chaiml-cai-v1-2-dpo-bas-22910-v4 to be ready
Unable to record family friendly update due to error: Invalid JSON input: Expecting value: line 1 column 1 (char 0)
Failed to get response for submission mistralai-mistral-nem_93303_v569: ('http://mistralai-mistral-nem-93303-v569-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Inference service chaiml-cai-v1-2-dpo-bas-22910-v4 ready after 251.65155577659607s
Pipeline stage MKMLDeployer completed in 252.26s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.3196604251861572s
Received healthy response to inference request in 2.9793858528137207s
Received healthy response to inference request in 2.9794580936431885s
Received healthy response to inference request in 2.984546422958374s
Received healthy response to inference request in 3.085561513900757s
5 requests
0 failed requests
5th percentile: 2.979400300979614
10th percentile: 2.9794147491455076
20th percentile: 2.979443645477295
30th percentile: 2.9804757595062257
40th percentile: 2.9825110912322996
50th percentile: 2.984546422958374
60th percentile: 3.024952459335327
70th percentile: 3.0653584957122804
80th percentile: 3.132381296157837
90th percentile: 3.226020860671997
95th percentile: 3.272840642929077
99th percentile: 3.3102964687347414
mean time: 3.0697224617004393
Pipeline stage StressChecker completed in 17.00s
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 0.73s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 1.29s
Shutdown handler de-registered
chaiml-cai-v1-2-dpo-bas_22910_v4 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-cai-v1-2-dpo-bas-22910-v4-profiler
Waiting for inference service chaiml-cai-v1-2-dpo-bas-22910-v4-profiler to be ready
Tearing down inference service chaiml-cai-v1-2-dpo-bas-22910-v4-profiler
%s, retrying in %s seconds...
Creating inference service chaiml-cai-v1-2-dpo-bas-22910-v4-profiler
Waiting for inference service chaiml-cai-v1-2-dpo-bas-22910-v4-profiler to be ready
Tearing down inference service chaiml-cai-v1-2-dpo-bas-22910-v4-profiler
%s, retrying in %s seconds...
Creating inference service chaiml-cai-v1-2-dpo-bas-22910-v4-profiler
Waiting for inference service chaiml-cai-v1-2-dpo-bas-22910-v4-profiler to be ready
Inference service chaiml-cai-v1-2-dpo-bas-22910-v4-profiler ready after 131.13148427009583s
Pipeline stage MKMLProfilerDeployer completed in 1060.75s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-cai-v1-2-dpo-753adff218ed097c9570cdb42c9eaa1e-deplok8ksz:/code/chaiverse_profiler_1762041420 --namespace tenant-chaiml-guanaco
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml exec -it chaiml-cai-v1-2-dpo-753adff218ed097c9570cdb42c9eaa1e-deplok8ksz --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1762041420 && python profiles.py profile --best_of_n 1 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 2048 --output_tokens 128 --summary /code/chaiverse_profiler_1762041420/summary.json'
%s, retrying in %s seconds...
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-cai-v1-2-dpo-753adff218ed097c9570cdb42c9eaa1e-deplo2srz7:/code/chaiverse_profiler_1762041588 --namespace tenant-chaiml-guanaco
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml exec -it chaiml-cai-v1-2-dpo-753adff218ed097c9570cdb42c9eaa1e-deplo2srz7 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1762041588 && python profiles.py profile --best_of_n 1 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 2048 --output_tokens 128 --summary /code/chaiverse_profiler_1762041588/summary.json'
%s, retrying in %s seconds...
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-cai-v1-2-dpo-753adff218ed097c9570cdb42c9eaa1e-deplo2srz7:/code/chaiverse_profiler_1762041641 --namespace tenant-chaiml-guanaco
clean up pipeline due to error=ISVCScriptError('Command failed with error: error: cannot exec into a container in a completed pod; current phase is Failed\n, output: ')
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-cai-v1-2-dpo-bas-22910-v4-profiler is running
Tearing down inference service chaiml-cai-v1-2-dpo-bas-22910-v4-profiler
Service chaiml-cai-v1-2-dpo-bas-22910-v4-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 0.81s
Shutdown handler de-registered
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-cai-v1-2-dpo-bas-22910-v4-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 0.88s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-cai-v1-2-dpo-bas-22910-v4-profiler
Waiting for inference service chaiml-cai-v1-2-dpo-bas-22910-v4-profiler to be ready
Tearing down inference service chaiml-cai-v1-2-dpo-bas-22910-v4-profiler
%s, retrying in %s seconds...
Creating inference service chaiml-cai-v1-2-dpo-bas-22910-v4-profiler
Waiting for inference service chaiml-cai-v1-2-dpo-bas-22910-v4-profiler to be ready
Inference service chaiml-cai-v1-2-dpo-bas-22910-v4-profiler ready after 90.73172378540039s
Pipeline stage MKMLProfilerDeployer completed in 696.31s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-cai-v1-2-dpo-753adff218ed097c9570cdb42c9eaa1e-deplovv44k:/code/chaiverse_profiler_1762042429 --namespace tenant-chaiml-guanaco
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml exec -it chaiml-cai-v1-2-dpo-753adff218ed097c9570cdb42c9eaa1e-deplovv44k --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1762042429 && python profiles.py profile --best_of_n 1 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 2048 --output_tokens 128 --summary /code/chaiverse_profiler_1762042429/summary.json'
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml exec -it chaiml-cai-v1-2-dpo-753adff218ed097c9570cdb42c9eaa1e-deplovv44k --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1762042429/summary.json'
Pipeline stage MKMLProfilerRunner completed in 2009.04s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-cai-v1-2-dpo-bas-22910-v4-profiler is running
Tearing down inference service chaiml-cai-v1-2-dpo-bas-22910-v4-profiler
Service chaiml-cai-v1-2-dpo-bas-22910-v4-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 0.73s
Shutdown handler de-registered
chaiml-cai-v1-2-dpo-bas_22910_v4 status is now inactive due to auto deactivation removed underperforming models
chaiml-cai-v1-2-dpo-bas_22910_v4 status is now torndown due to DeploymentManager action