developer_uid: chai_backend_admin
submission_id: chaiml-ir-v0-sft-cosine_57448_v1
model_name: chaiml-ir-v0-sft-cosine_57448_v1
model_group: ChaiML/ir-v0-sft_cosine-
status: inactive
timestamp: 2025-10-26T04:07:34+00:00
num_battles: 5992
num_wins: 3160
celo_rating: 1289.33
family_friendly_score: 0.478
family_friendly_standard_error: 0.007064219702132713
submission_type: basic
model_repo: ChaiML/ir-v0-sft_cosine-lr1e5g32
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 8
max_input_tokens: 2048
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.3840280079215793, 'latency_mean': 2.6038740146160126, 'latency_p50': 2.610337972640991, 'latency_p90': 2.8603359937667845}, {'batch_size': 2, 'throughput': 0.5759785763583802, 'latency_mean': 3.467159802913666, 'latency_p50': 3.505472779273987, 'latency_p90': 3.7254443407058715}, {'batch_size': 3, 'throughput': 0.7174234698078022, 'latency_mean': 4.15581316113472, 'latency_p50': 4.1464338302612305, 'latency_p90': 4.582592725753784}, {'batch_size': 4, 'throughput': 0.8225855677969474, 'latency_mean': 4.851585673093796, 'latency_p50': 4.836740732192993, 'latency_p90': 5.430031180381775}, {'batch_size': 5, 'throughput': 0.87932893875717, 'latency_mean': 5.658617179393769, 'latency_p50': 5.663761854171753, 'latency_p90': 6.57194414138794}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: chaiml-ir-v0-sft-cosine_57448_v1
is_internal_developer: True
language_model: ChaiML/ir-v0-sft_cosine-lr1e5g32
model_size: 24B
ranking_group: single
throughput_3p7s: 0.63
us_pacific_date: 2025-10-25
win_ratio: 0.527369826435247
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>', 'You:', 'User:'], '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': '####\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-ir-v0-sft-cosine-57448-v1-mkmlizer
Waiting for job on chaiml-ir-v0-sft-cosine-57448-v1-mkmlizer to finish
chaiml-ir-v0-sft-cosine-57448-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ir-v0-sft-cosine-57448-v1-mkmlizer: ║ ║
chaiml-ir-v0-sft-cosine-57448-v1-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-ir-v0-sft-cosine-57448-v1-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-ir-v0-sft-cosine-57448-v1-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-ir-v0-sft-cosine-57448-v1-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-ir-v0-sft-cosine-57448-v1-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-ir-v0-sft-cosine-57448-v1-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-ir-v0-sft-cosine-57448-v1-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-ir-v0-sft-cosine-57448-v1-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-ir-v0-sft-cosine-57448-v1-mkmlizer: ║ ║
chaiml-ir-v0-sft-cosine-57448-v1-mkmlizer: ║ Version: 0.30.2 ║
chaiml-ir-v0-sft-cosine-57448-v1-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-ir-v0-sft-cosine-57448-v1-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-ir-v0-sft-cosine-57448-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-ir-v0-sft-cosine-57448-v1-mkmlizer: ║ ║
chaiml-ir-v0-sft-cosine-57448-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-ir-v0-sft-cosine-57448-v1-mkmlizer: ║ belonging to: ║
chaiml-ir-v0-sft-cosine-57448-v1-mkmlizer: ║ ║
chaiml-ir-v0-sft-cosine-57448-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-ir-v0-sft-cosine-57448-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-ir-v0-sft-cosine-57448-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-ir-v0-sft-cosine-57448-v1-mkmlizer: ║ ║
chaiml-ir-v0-sft-cosine-57448-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ir-v0-sft-cosine-57448-v1-mkmlizer: Downloaded to shared memory in 61.193s
chaiml-ir-v0-sft-cosine-57448-v1-mkmlizer: Checking if ChaiML/ir-v0-sft_cosine-lr1e5g32 already exists in ChaiML
chaiml-ir-v0-sft-cosine-57448-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpcdbs7vws, device:0
chaiml-ir-v0-sft-cosine-57448-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ir-v0-sft-cosine-57448-v1-mkmlizer: quantized model in 42.269s
chaiml-ir-v0-sft-cosine-57448-v1-mkmlizer: Processed model ChaiML/ir-v0-sft_cosine-lr1e5g32 in 103.462s
chaiml-ir-v0-sft-cosine-57448-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ir-v0-sft-cosine-57448-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ir-v0-sft-cosine-57448-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ir-v0-sft-cosine-57448-v1/nvidia
chaiml-ir-v0-sft-cosine-57448-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ir-v0-sft-cosine-57448-v1/nvidia/config.json
chaiml-ir-v0-sft-cosine-57448-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ir-v0-sft-cosine-57448-v1/nvidia/special_tokens_map.json
chaiml-ir-v0-sft-cosine-57448-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ir-v0-sft-cosine-57448-v1/nvidia/tokenizer_config.json
chaiml-ir-v0-sft-cosine-57448-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ir-v0-sft-cosine-57448-v1/nvidia/tokenizer.json
chaiml-ir-v0-sft-cosine-57448-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ir-v0-sft-cosine-57448-v1/nvidia/flywheel_model.0.safetensors
chaiml-ir-v0-sft-cosine-57448-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-ir-v0-sft-cosine-57448-v1/nvidia/flywheel_model.1.safetensors
chaiml-ir-v0-sft-cosine-57448-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:16, 21.85it/s] Loading 0: 3%|▎ | 12/363 [00:00<00:08, 40.11it/s] Loading 0: 5%|▍ | 17/363 [00:00<00:09, 36.72it/s] Loading 0: 6%|▌ | 22/363 [00:00<00:09, 36.49it/s] Loading 0: 7%|▋ | 26/363 [00:00<00:09, 36.71it/s] Loading 0: 9%|▉ | 32/363 [00:00<00:07, 42.03it/s] Loading 0: 10%|█ | 37/363 [00:01<00:12, 25.88it/s] Loading 0: 11%|█▏ | 41/363 [00:01<00:13, 23.99it/s] Loading 0: 13%|█▎ | 48/363 [00:01<00:09, 31.69it/s] Loading 0: 14%|█▍ | 52/363 [00:01<00:10, 30.47it/s] Loading 0: 16%|█▌ | 57/363 [00:01<00:09, 33.98it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:09, 31.72it/s] Loading 0: 18%|█▊ | 65/363 [00:02<00:09, 32.95it/s] Loading 0: 19%|█▉ | 70/363 [00:02<00:10, 28.90it/s] Loading 0: 20%|██ | 74/363 [00:02<00:11, 26.01it/s] Loading 0: 22%|██▏ | 79/363 [00:02<00:09, 30.10it/s] Loading 0: 23%|██▎ | 83/363 [00:02<00:08, 31.27it/s] Loading 0: 24%|██▍ | 87/363 [00:02<00:10, 27.37it/s] Loading 0: 25%|██▌ | 92/363 [00:03<00:10, 26.74it/s] Loading 0: 27%|██▋ | 99/363 [00:03<00:07, 33.65it/s] Loading 0: 28%|██▊ | 103/363 [00:03<00:08, 31.75it/s] Loading 0: 29%|██▉ | 107/363 [00:03<00:09, 26.77it/s] Loading 0: 31%|███ | 112/363 [00:03<00:08, 29.38it/s] Loading 0: 32%|███▏ | 116/363 [00:03<00:08, 30.31it/s] Loading 0: 33%|███▎ | 120/363 [00:03<00:07, 32.23it/s] Loading 0: 34%|███▍ | 124/363 [00:04<00:07, 30.39it/s] Loading 0: 36%|███▌ | 129/363 [00:04<00:06, 33.97it/s] Loading 0: 37%|███▋ | 133/363 [00:04<00:07, 31.77it/s] Loading 0: 38%|███▊ | 138/363 [00:04<00:06, 34.99it/s] Loading 0: 39%|███▉ | 142/363 [00:04<00:06, 32.14it/s] Loading 0: 41%|████ | 149/363 [00:04<00:05, 38.66it/s] Loading 0: 42%|████▏ | 153/363 [00:05<00:08, 24.61it/s] Loading 0: 44%|████▎ | 158/363 [00:05<00:08, 24.81it/s] Loading 0: 45%|████▌ | 165/363 [00:05<00:06, 31.51it/s] Loading 0: 47%|████▋ | 169/363 [00:05<00:06, 29.84it/s] Loading 0: 48%|████▊ | 174/363 [00:05<00:05, 33.16it/s] Loading 0: 49%|████▉ | 178/363 [00:05<00:05, 31.71it/s] Loading 0: 50%|█████ | 182/363 [00:05<00:05, 32.79it/s] Loading 0: 52%|█████▏ | 187/363 [00:06<00:06, 28.85it/s] Loading 0: 53%|█████▎ | 191/363 [00:06<00:06, 28.36it/s] Loading 0: 54%|█████▎ | 195/363 [00:06<00:06, 25.70it/s] Loading 0: 55%|█████▌ | 201/363 [00:19<02:15, 1.20it/s] Loading 0: 56%|█████▌ | 203/363 [00:19<01:56, 1.38it/s] Loading 0: 57%|█████▋ | 208/363 [00:19<01:14, 2.09it/s] Loading 0: 58%|█████▊ | 211/363 [00:19<00:57, 2.64it/s] Loading 0: 59%|█████▉ | 214/363 [00:20<00:43, 3.40it/s] Loading 0: 60%|██████ | 218/363 [00:20<00:30, 4.79it/s] Loading 0: 61%|██████ | 221/363 [00:20<00:23, 6.08it/s] Loading 0: 62%|██████▏ | 224/363 [00:20<00:19, 7.28it/s] Loading 0: 63%|██████▎ | 229/363 [00:20<00:12, 10.61it/s] Loading 0: 64%|██████▍ | 232/363 [00:20<00:10, 12.53it/s] Loading 0: 65%|██████▌ | 237/363 [00:20<00:07, 17.16it/s] Loading 0: 66%|██████▋ | 241/363 [00:20<00:06, 18.98it/s] Loading 0: 68%|██████▊ | 246/363 [00:21<00:04, 23.79it/s] Loading 0: 69%|██████▉ | 250/363 [00:21<00:04, 24.64it/s] Loading 0: 70%|███████ | 255/363 [00:21<00:03, 29.13it/s] Loading 0: 71%|███████▏ | 259/363 [00:21<00:03, 28.79it/s] Loading 0: 73%|███████▎ | 266/363 [00:21<00:02, 35.88it/s] Loading 0: 75%|███████▍ | 271/363 [00:21<00:03, 25.60it/s] Loading 0: 76%|███████▌ | 275/363 [00:22<00:03, 24.08it/s] Loading 0: 78%|███████▊ | 282/363 [00:22<00:02, 30.96it/s] Loading 0: 79%|███████▉ | 286/363 [00:22<00:02, 29.87it/s] Loading 0: 80%|████████ | 291/363 [00:22<00:02, 33.12it/s] Loading 0: 81%|████████▏ | 295/363 [00:22<00:02, 31.49it/s] Loading 0: 82%|████████▏ | 299/363 [00:22<00:01, 32.47it/s] Loading 0: 84%|████████▎ | 304/363 [00:22<00:02, 29.43it/s] Loading 0: 85%|████████▍ | 308/363 [00:23<00:01, 28.82it/s] Loading 0: 86%|████████▌ | 312/363 [00:23<00:01, 25.53it/s] Loading 0: 88%|████████▊ | 318/363 [00:23<00:01, 31.08it/s] Loading 0: 89%|████████▊ | 322/363 [00:23<00:01, 30.04it/s] Loading 0: 90%|█████████ | 327/363 [00:23<00:01, 33.59it/s] Loading 0: 91%|█████████ | 331/363 [00:23<00:01, 31.45it/s] Loading 0: 92%|█████████▏| 335/363 [00:23<00:00, 32.53it/s] Loading 0: 93%|█████████▎| 339/363 [00:24<00:00, 32.92it/s] Loading 0: 94%|█████████▍| 343/363 [00:24<00:00, 20.06it/s] Loading 0: 96%|█████████▌| 347/363 [00:24<00:00, 23.32it/s] Loading 0: 97%|█████████▋| 351/363 [00:24<00:00, 23.80it/s] Loading 0: 98%|█████████▊| 355/363 [00:24<00:00, 24.93it/s] Loading 0: 99%|█████████▊| 358/363 [00:25<00:00, 21.56it/s]
Job chaiml-ir-v0-sft-cosine-57448-v1-mkmlizer completed after 175.23s with status: succeeded
Stopping job with name chaiml-ir-v0-sft-cosine-57448-v1-mkmlizer
Pipeline stage MKMLizer completed in 175.77s
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-ir-v0-sft-cosine-57448-v1
Waiting for inference service chaiml-ir-v0-sft-cosine-57448-v1 to be ready
Inference service chaiml-ir-v0-sft-cosine-57448-v1 ready after 91.0383985042572s
Pipeline stage MKMLDeployer completed in 91.50s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 2.8349428176879883s
Received healthy response to inference request in 2.4422290325164795s
Received healthy response to inference request in 2.2260241508483887s
Received healthy response to inference request in 2.2690482139587402s
5 requests
1 failed requests
5th percentile: 2.234628963470459
10th percentile: 2.2432337760925294
20th percentile: 2.26044340133667
30th percentile: 2.303684377670288
40th percentile: 2.372956705093384
50th percentile: 2.4422290325164795
60th percentile: 2.599314546585083
70th percentile: 2.7564000606536863
80th percentile: 6.296825742721561
90th percentile: 13.220591592788697
95th percentile: 16.682474517822264
99th percentile: 19.451980857849122
mean time: 5.983320331573486
%s, retrying in %s seconds...
Received healthy response to inference request in 3.5846264362335205s
Received healthy response to inference request in 2.2032787799835205s
Received healthy response to inference request in 3.04298734664917s
Received healthy response to inference request in 2.5274996757507324s
Received healthy response to inference request in 2.440040111541748s
5 requests
0 failed requests
5th percentile: 2.250631046295166
10th percentile: 2.2979833126068114
20th percentile: 2.3926878452301024
30th percentile: 2.457532024383545
40th percentile: 2.4925158500671385
50th percentile: 2.5274996757507324
60th percentile: 2.7336947441101076
70th percentile: 2.9398898124694823
80th percentile: 3.15131516456604
90th percentile: 3.3679708003997804
95th percentile: 3.47629861831665
99th percentile: 3.5629608726501463
mean time: 2.7596864700317383
Pipeline stage StressChecker completed in 46.79s
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 0.71s
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 0.69s
Shutdown handler de-registered
chaiml-ir-v0-sft-cosine_57448_v1 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
Pipeline stage OfflineFamilyFriendlyScorer completed in 3159.27s
Shutdown handler de-registered
chaiml-ir-v0-sft-cosine_57448_v1 status is now inactive due to auto deactivation removed underperforming models