developer_uid: chai_backend_admin
submission_id: chaiml-ca18-v2-dpo-lr15-b025_v1
model_name: training123
model_group: ChaiML/ca18-v2-dpo_lr15-
status: torndown
timestamp: 2025-11-19T20:41:32+00:00
num_battles: 5481
num_wins: 2911
celo_rating: 1307.93
family_friendly_score: 0.5058
family_friendly_standard_error: 0.007070592054418074
submission_type: basic
model_repo: ChaiML/ca18-v2-dpo_lr15-b025
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 2048
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.6833094964147159, 'latency_mean': 1.4633399033546448, 'latency_p50': 1.4642126560211182, 'latency_p90': 1.615598440170288}, {'batch_size': 3, 'throughput': 1.27146854038323, 'latency_mean': 2.3516019940376283, 'latency_p50': 2.3424932956695557, 'latency_p90': 2.602141261100769}, {'batch_size': 5, 'throughput': 1.558217936615334, 'latency_mean': 3.199846315383911, 'latency_p50': 3.190608859062195, 'latency_p90': 3.636689376831055}, {'batch_size': 6, 'throughput': 1.6443513314026739, 'latency_mean': 3.6260667765140533, 'latency_p50': 3.628116011619568, 'latency_p90': 4.074522185325622}, {'batch_size': 8, 'throughput': 1.7559874570625933, 'latency_mean': 4.5283633387088775, 'latency_p50': 4.54190468788147, 'latency_p90': 5.118712115287781}, {'batch_size': 10, 'throughput': 1.8321124761968497, 'latency_mean': 5.418526685237884, 'latency_p50': 5.466740846633911, 'latency_p90': 6.231857633590698}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: training123
is_internal_developer: True
language_model: ChaiML/ca18-v2-dpo_lr15-b025
model_size: 13B
ranking_group: single
throughput_3p7s: 1.67
us_pacific_date: 2025-11-16
win_ratio: 0.5311074621419449
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', 'User:', 'You:'], 'max_input_tokens': 2048, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': True}
Resubmit model
Connection pool is full, discarding connection: %s. Connection pool size: %s
Shutdown handler not registered because Python interpreter is not running in the main thread
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer
Waiting for job on chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer to finish
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: ║ ║
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: ║ ║
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: ║ Version: 0.30.2 ║
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: ║ ║
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: ║ belonging to: ║
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: ║ ║
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: ║ ║
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Stopping job with name chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer
Waiting for job on chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer to finish
Failed to get response for submission chaiml-7b07-69d4-linear-w01_v16: ('http://chaiml-7b07-69d4-linear-w01-v16-predictor.tenant-chaiml-guanaco.kchai-coreweave-us-east-04a.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:58250->127.0.0.1:8080: read: connection reset by peer\n')
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: Downloaded to shared memory in 26.005s
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: Checking if ChaiML/ca18-v2-dpo_lr15-b025 already exists in ChaiML
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpyq4y7_zk, device:0
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: ║ ║
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: ║ ║
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: ║ Version: 0.30.2 ║
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: ║ ║
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: ║ belonging to: ║
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: ║ ║
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: ║ ║
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: Downloaded to shared memory in 20.550s
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: Checking if ChaiML/ca18-v2-dpo_lr15-b025 already exists in ChaiML
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpmx8tqtk2, device:0
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: quantized model in 26.084s
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: Processed model ChaiML/ca18-v2-dpo_lr15-b025 in 46.634s
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ca18-v2-dpo-lr15-b025-v1/nvidia
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ca18-v2-dpo-lr15-b025-v1/nvidia/config.json
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ca18-v2-dpo-lr15-b025-v1/nvidia/special_tokens_map.json
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ca18-v2-dpo-lr15-b025-v1/nvidia/tokenizer_config.json
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ca18-v2-dpo-lr15-b025-v1/nvidia/tokenizer.json
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ca18-v2-dpo-lr15-b025-v1/nvidia/flywheel_model.0.safetensors
chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:10, 34.60it/s] Loading 0: 4%|▍ | 14/363 [00:00<00:07, 49.19it/s] Loading 0: 6%|▋ | 23/363 [00:00<00:06, 53.78it/s] Loading 0: 9%|▉ | 32/363 [00:00<00:05, 55.94it/s] Loading 0: 11%|█▏ | 41/363 [00:00<00:05, 57.45it/s] Loading 0: 14%|█▍ | 50/363 [00:00<00:05, 57.64it/s] Loading 0: 17%|█▋ | 60/363 [00:01<00:04, 63.18it/s] Loading 0: 18%|█▊ | 67/363 [00:01<00:06, 46.82it/s] Loading 0: 20%|██ | 73/363 [00:01<00:06, 45.14it/s] Loading 0: 22%|██▏ | 80/363 [00:01<00:06, 43.91it/s] Loading 0: 23%|██▎ | 85/363 [00:01<00:06, 44.43it/s] Loading 0: 25%|██▌ | 91/363 [00:01<00:06, 43.33it/s] Loading 0: 28%|██▊ | 100/363 [00:02<00:05, 47.46it/s] Loading 0: 30%|███ | 110/363 [00:02<00:04, 54.43it/s] Loading 0: 32%|███▏ | 116/363 [00:02<00:04, 55.13it/s] Loading 0: 34%|███▍ | 123/363 [00:02<00:04, 53.03it/s] Loading 0: 36%|███▌ | 129/363 [00:02<00:04, 53.73it/s] Loading 0: 37%|███▋ | 136/363 [00:02<00:04, 49.50it/s] Loading 0: 39%|███▉ | 142/363 [00:02<00:05, 43.03it/s] Loading 0: 40%|████ | 147/363 [00:03<00:05, 42.46it/s] Loading 0: 42%|████▏ | 154/363 [00:03<00:04, 44.21it/s] Loading 0: 44%|████▍ | 159/363 [00:03<00:04, 45.24it/s] Loading 0: 46%|████▌ | 166/363 [00:03<00:03, 50.93it/s] Loading 0: 47%|████▋ | 172/363 [00:03<00:03, 49.61it/s] Loading 0: 49%|████▉ | 178/363 [00:03<00:03, 51.49it/s] Loading 0: 51%|█████ | 185/363 [00:03<00:03, 48.54it/s] Loading 0: 53%|█████▎ | 193/363 [00:03<00:03, 55.70it/s] Loading 0: 55%|█████▍ | 199/363 [00:03<00:03, 53.59it/s] Loading 0: 56%|█████▋ | 205/363 [00:04<00:03, 43.60it/s] Loading 0: 58%|█████▊ | 212/363 [00:04<00:03, 43.67it/s] Loading 0: 61%|██████ | 222/363 [00:04<00:02, 51.18it/s] Loading 0: 63%|██████▎ | 228/363 [00:04<00:03, 39.73it/s] Loading 0: 64%|██████▍ | 234/363 [00:04<00:02, 43.54it/s] Loading 0: 66%|██████▌ | 239/363 [00:04<00:03, 40.90it/s] Loading 0: 68%|██████▊ | 247/363 [00:05<00:02, 49.45it/s] Loading 0: 70%|██████▉ | 253/363 [00:05<00:02, 49.15it/s] Loading 0: 71%|███████▏ | 259/363 [00:05<00:02, 50.75it/s] Loading 0: 73%|███████▎ | 266/363 [00:05<00:02, 48.31it/s] Loading 0: 75%|███████▌ | 274/363 [00:05<00:01, 55.41it/s] Loading 0: 77%|███████▋ | 280/363 [00:05<00:01, 53.15it/s] Loading 0: 79%|███████▉ | 286/363 [00:05<00:01, 53.59it/s] Loading 0: 81%|████████ | 293/363 [00:05<00:01, 49.55it/s] Loading 0: 83%|████████▎ | 303/363 [00:06<00:01, 55.23it/s] Loading 0: 85%|████████▌ | 309/363 [00:06<00:01, 33.20it/s] Loading 0: 87%|████████▋ | 314/363 [00:06<00:01, 34.82it/s] Loading 0: 88%|████████▊ | 321/363 [00:06<00:01, 37.79it/s] Loading 0: 91%|█████████ | 330/363 [00:07<00:00, 38.74it/s] Loading 0: 93%|█████████▎| 339/363 [00:07<00:00, 43.61it/s] Loading 0: 96%|█████████▌| 348/363 [00:07<00:00, 47.20it/s] Loading 0: 98%|█████████▊| 357/363 [00:07<00:00, 49.90it/s]
Job chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer completed after 104.31s with status: succeeded
Stopping job with name chaiml-ca18-v2-dpo-lr15-b025-v1-mkmlizer
Pipeline stage MKMLizer completed in 229.02s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-ca18-v2-dpo-lr15-b025-v1
Waiting for inference service chaiml-ca18-v2-dpo-lr15-b025-v1 to be ready
Inference service chaiml-ca18-v2-dpo-lr15-b025-v1 ready after 171.1108922958374s
Pipeline stage MKMLDeployer completed in 171.65s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.7556171417236328s
Received healthy response to inference request in 1.4724371433258057s
Received healthy response to inference request in 1.8395698070526123s
Received healthy response to inference request in 1.3886640071868896s
Received healthy response to inference request in 1.4131648540496826s
5 requests
0 failed requests
5th percentile: 1.3935641765594482
10th percentile: 1.3984643459320067
20th percentile: 1.408264684677124
30th percentile: 1.4250193119049073
40th percentile: 1.4487282276153564
50th percentile: 1.4724371433258057
60th percentile: 1.5857091426849366
70th percentile: 1.6989811420440672
80th percentile: 1.7724076747894286
90th percentile: 1.8059887409210205
95th percentile: 1.8227792739868165
99th percentile: 1.8362117004394531
mean time: 1.5738905906677245
Pipeline stage StressChecker completed in 9.23s
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 0.65s
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 0.67s
Shutdown handler de-registered
chaiml-ca18-v2-dpo-lr15-b025_v1 status is now deployed due to DeploymentManager action
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 0.12s
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-ca18-v2-dpo-lr15-b025-v1-profiler
Waiting for inference service chaiml-ca18-v2-dpo-lr15-b025-v1-profiler to be ready
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 2604.06s
Shutdown handler de-registered
chaiml-ca18-v2-dpo-lr15-b025_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-ca18-v2-dpo-lr15-b025_v1 status is now torndown due to DeploymentManager action