chaiml-ca18-v1-5-dpo-cosine

developer_uid: chai_backend_admin

submission_id: chaiml-ca18-v1-5-dpo-cosine_v1

model_name: training123

model_group: ChaiML/ca18-v1-5-dpo_cos

status: torndown

timestamp: 2025-11-19T09:01:35+00:00

num_battles: 5320

num_wins: 2767

celo_rating: 1304.83

family_friendly_score: 0.5114000000000001

family_friendly_standard_error: 0.007069229661002675

submission_type: basic

model_repo: ChaiML/ca18-v1-5-dpo_cosine

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': 0.6804584886084908, 'latency_mean': 1.4694982826709748, 'latency_p50': 1.4691731929779053, 'latency_p90': 1.61329128742218}, {'batch_size': 3, 'throughput': 1.242735422765244, 'latency_mean': 2.408340960741043, 'latency_p50': 2.3970998525619507, 'latency_p90': 2.684321665763855}, {'batch_size': 5, 'throughput': 1.4997227385627643, 'latency_mean': 3.320345540046692, 'latency_p50': 3.3357491493225098, 'latency_p90': 3.754947471618652}, {'batch_size': 6, 'throughput': 1.5815879491748337, 'latency_mean': 3.776790727376938, 'latency_p50': 3.8047901391983032, 'latency_p90': 4.168810224533081}, {'batch_size': 8, 'throughput': 1.6755035817624915, 'latency_mean': 4.732960373163223, 'latency_p50': 4.751250624656677, 'latency_p90': 5.390478897094726}, {'batch_size': 10, 'throughput': 1.7529839353070094, 'latency_mean': 5.662350931167603, 'latency_p50': 5.654427766799927, 'latency_p90': 6.468475675582885}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/ca18-v1-5-dpo_cosine

model_size: 13B

ranking_group: single

throughput_3p7s: 1.58

us_pacific_date: 2025-11-16

win_ratio: 0.5201127819548872

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': ['</s>', 'User:', 'You:', '\n'], '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

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-ca18-v1-5-dpo-cosine-v1-mkmlizer
Waiting for job on chaiml-ca18-v1-5-dpo-cosine-v1-mkmlizer to finish
chaiml-ca18-v1-5-dpo-cosine-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ca18-v1-5-dpo-cosine-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-5-dpo-cosine-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ca18-v1-5-dpo-cosine-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ca18-v1-5-dpo-cosine-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ca18-v1-5-dpo-cosine-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ca18-v1-5-dpo-cosine-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ca18-v1-5-dpo-cosine-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ca18-v1-5-dpo-cosine-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ca18-v1-5-dpo-cosine-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ca18-v1-5-dpo-cosine-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-5-dpo-cosine-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ca18-v1-5-dpo-cosine-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ca18-v1-5-dpo-cosine-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ca18-v1-5-dpo-cosine-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ca18-v1-5-dpo-cosine-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-5-dpo-cosine-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ca18-v1-5-dpo-cosine-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ca18-v1-5-dpo-cosine-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-5-dpo-cosine-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ca18-v1-5-dpo-cosine-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ca18-v1-5-dpo-cosine-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ca18-v1-5-dpo-cosine-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-5-dpo-cosine-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ca18-v1-5-dpo-cosine-v1-mkmlizer: Downloaded to shared memory in 43.258s
chaiml-ca18-v1-5-dpo-cosine-v1-mkmlizer: Checking if ChaiML/ca18-v1-5-dpo_cosine already exists in ChaiML
chaiml-ca18-v1-5-dpo-cosine-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpyvzvpus1, device:0
chaiml-ca18-v1-5-dpo-cosine-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ca18-v1-5-dpo-cosine-v1-mkmlizer: quantized model in 26.311s
chaiml-ca18-v1-5-dpo-cosine-v1-mkmlizer: Processed model ChaiML/ca18-v1-5-dpo_cosine in 69.570s
chaiml-ca18-v1-5-dpo-cosine-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ca18-v1-5-dpo-cosine-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ca18-v1-5-dpo-cosine-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ca18-v1-5-dpo-cosine-v1/nvidia
chaiml-ca18-v1-5-dpo-cosine-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ca18-v1-5-dpo-cosine-v1/nvidia/special_tokens_map.json
chaiml-ca18-v1-5-dpo-cosine-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ca18-v1-5-dpo-cosine-v1/nvidia/config.json
chaiml-ca18-v1-5-dpo-cosine-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ca18-v1-5-dpo-cosine-v1/nvidia/tokenizer_config.json
chaiml-ca18-v1-5-dpo-cosine-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ca18-v1-5-dpo-cosine-v1/nvidia/tokenizer.json
chaiml-ca18-v1-5-dpo-cosine-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ca18-v1-5-dpo-cosine-v1/nvidia/flywheel_model.0.safetensors
chaiml-ca18-v1-5-dpo-cosine-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:10, 35.17it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:06, 49.88it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:06, 54.04it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:05, 56.71it/s]
Loading 0:  11%|█▏        | 41/363 [00:00<00:05, 58.15it/s]
Loading 0:  14%|█▍        | 50/363 [00:00<00:05, 59.06it/s]
Loading 0:  17%|█▋        | 60/363 [00:01<00:04, 65.15it/s]
Loading 0:  18%|█▊        | 67/363 [00:01<00:06, 48.59it/s]
Loading 0:  20%|██        | 73/363 [00:01<00:06, 46.45it/s]
Loading 0:  23%|██▎       | 82/363 [00:01<00:05, 49.93it/s]
Loading 0:  25%|██▌       | 91/363 [00:01<00:05, 52.27it/s]
Loading 0:  27%|██▋       | 99/363 [00:01<00:04, 57.51it/s]
Loading 0:  29%|██▉       | 106/363 [00:01<00:04, 55.58it/s]
Loading 0:  31%|███       | 113/363 [00:02<00:04, 53.78it/s]
Loading 0:  33%|███▎      | 119/363 [00:02<00:04, 55.09it/s]
Loading 0:  35%|███▍      | 126/363 [00:02<00:04, 58.53it/s]
Loading 0:  37%|███▋      | 133/363 [00:02<00:03, 57.88it/s]
Loading 0:  38%|███▊      | 139/363 [00:02<00:03, 56.09it/s]
Loading 0:  40%|███▉      | 145/363 [00:02<00:05, 40.45it/s]
Loading 0:  41%|████▏     | 150/363 [00:02<00:05, 42.05it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:04, 47.71it/s]
Loading 0:  45%|████▍     | 163/363 [00:03<00:04, 47.95it/s]
Loading 0:  47%|████▋     | 169/363 [00:03<00:03, 50.45it/s]
Loading 0:  48%|████▊     | 176/363 [00:03<00:03, 48.31it/s]
Loading 0:  51%|█████     | 185/363 [00:03<00:03, 50.84it/s]
Loading 0:  53%|█████▎    | 194/363 [00:03<00:03, 52.66it/s]
Loading 0:  56%|█████▌    | 202/363 [00:03<00:02, 58.57it/s]
Loading 0:  58%|█████▊    | 209/363 [00:03<00:02, 58.03it/s]
Loading 0:  59%|█████▉    | 215/363 [00:04<00:02, 56.80it/s]
Loading 0:  61%|██████    | 222/363 [00:04<00:02, 56.00it/s]
Loading 0:  63%|██████▎   | 228/363 [00:04<00:05, 25.32it/s]
Loading 0:  64%|██████▍   | 233/363 [00:04<00:04, 26.07it/s]
Loading 0:  66%|██████▌   | 239/363 [00:05<00:04, 28.64it/s]
Loading 0:  68%|██████▊   | 247/363 [00:05<00:03, 37.11it/s]
Loading 0:  70%|██████▉   | 253/363 [00:05<00:02, 39.84it/s]
Loading 0:  71%|███████▏  | 259/363 [00:05<00:02, 43.29it/s]
Loading 0:  73%|███████▎  | 266/363 [00:05<00:02, 43.34it/s]
Loading 0:  75%|███████▌  | 274/363 [00:05<00:01, 51.33it/s]
Loading 0:  77%|███████▋  | 280/363 [00:05<00:01, 48.50it/s]
Loading 0:  79%|███████▉  | 286/363 [00:05<00:01, 50.62it/s]
Loading 0:  81%|████████  | 293/363 [00:06<00:01, 48.72it/s]
Loading 0:  83%|████████▎ | 303/363 [00:06<00:01, 55.33it/s]
Loading 0:  85%|████████▌ | 309/363 [00:06<00:01, 33.84it/s]
Loading 0:  87%|████████▋ | 314/363 [00:06<00:01, 35.52it/s]
Loading 0:  88%|████████▊ | 321/363 [00:06<00:01, 38.73it/s]
Loading 0:  91%|█████████ | 330/363 [00:07<00:00, 44.38it/s]
Loading 0:  93%|█████████▎| 339/363 [00:07<00:00, 48.10it/s]
Loading 0:  96%|█████████▌| 348/363 [00:07<00:00, 50.68it/s]
Loading 0:  98%|█████████▊| 356/363 [00:07<00:00, 56.25it/s]
Loading 0: 100%|██████████| 363/363 [00:07<00:00, 56.39it/s]
                                                            
Job chaiml-ca18-v1-5-dpo-cosine-v1-mkmlizer completed after 103.83s with status: succeeded
Stopping job with name chaiml-ca18-v1-5-dpo-cosine-v1-mkmlizer
Pipeline stage MKMLizer completed in 104.39s
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-ca18-v1-5-dpo-cosine-v1
Waiting for inference service chaiml-ca18-v1-5-dpo-cosine-v1 to be ready
Inference service chaiml-ca18-v1-5-dpo-cosine-v1 ready after 170.65163016319275s
Pipeline stage MKMLDeployer completed in 171.08s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.5900990962982178s
Received healthy response to inference request in 2.1794002056121826s
Received healthy response to inference request in 1.3665549755096436s
Received healthy response to inference request in 1.6159558296203613s
Received healthy response to inference request in 1.257382869720459s
5 requests
0 failed requests
5th percentile: 1.279217290878296
10th percentile: 1.301051712036133
20th percentile: 1.3447205543518066
30th percentile: 1.4112637996673585
40th percentile: 1.5006814479827881
50th percentile: 1.5900990962982178
60th percentile: 1.6004417896270753
70th percentile: 1.6107844829559326
80th percentile: 1.7286447048187257
90th percentile: 1.9540224552154541
95th percentile: 2.0667113304138183
99th percentile: 2.15686243057251
mean time: 1.6018785953521728
Pipeline stage StressChecker completed in 9.24s
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 0.61s
Shutdown handler de-registered
chaiml-ca18-v1-5-dpo-cosine_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 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-ca18-v1-5-dpo-cosine-v1-profiler
Waiting for inference service chaiml-ca18-v1-5-dpo-cosine-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 2653.63s
Shutdown handler de-registered
chaiml-ca18-v1-5-dpo-cosine_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-ca18-v1-5-dpo-cosine_v1 status is now torndown due to DeploymentManager action