developer_uid: rica40325
submission_id: rica40325-960-sft_v2
model_name: rica40325-960-sft_v2
model_group: rica40325/960-sft
status: inactive
timestamp: 2025-04-03T08:22:38+00:00
num_battles: 8387
num_wins: 3934
celo_rating: 1263.31
family_friendly_score: 0.5396000000000001
family_friendly_standard_error: 0.007048855793673183
submission_type: basic
model_repo: rica40325/960-sft
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6066850595210734, 'latency_mean': 1.648204472064972, 'latency_p50': 1.6499701738357544, 'latency_p90': 1.8057353019714355}, {'batch_size': 3, 'throughput': 1.1023676934197126, 'latency_mean': 2.711665771007538, 'latency_p50': 2.7462449073791504, 'latency_p90': 2.95674147605896}, {'batch_size': 5, 'throughput': 1.3348604358089047, 'latency_mean': 3.7379108333587645, 'latency_p50': 3.775225043296814, 'latency_p90': 4.168617486953735}, {'batch_size': 6, 'throughput': 1.4160929022232016, 'latency_mean': 4.213706496953964, 'latency_p50': 4.258833289146423, 'latency_p90': 4.724549722671509}, {'batch_size': 8, 'throughput': 1.4793528976659254, 'latency_mean': 5.378135648965835, 'latency_p50': 5.422442078590393, 'latency_p90': 6.079607319831848}, {'batch_size': 10, 'throughput': 1.5030536959839407, 'latency_mean': 6.601508510112763, 'latency_p50': 6.615401864051819, 'latency_p90': 7.370748567581177}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: rica40325-960-sft_v2
is_internal_developer: False
language_model: rica40325/960-sft
model_size: 13B
ranking_group: single
throughput_3p7s: 1.33
us_pacific_date: 2025-04-03
win_ratio: 0.46905925837605816
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 1024, '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': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{bot_name}:', 'truncate_by_message': False}
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 rica40325-960-sft-v2-mkmlizer
Waiting for job on rica40325-960-sft-v2-mkmlizer to finish
rica40325-960-sft-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rica40325-960-sft-v2-mkmlizer: ║ _____ __ __ ║
rica40325-960-sft-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rica40325-960-sft-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rica40325-960-sft-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rica40325-960-sft-v2-mkmlizer: ║ /___/ ║
rica40325-960-sft-v2-mkmlizer: ║ ║
rica40325-960-sft-v2-mkmlizer: ║ Version: 0.12.8 ║
rica40325-960-sft-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rica40325-960-sft-v2-mkmlizer: ║ https://mk1.ai ║
rica40325-960-sft-v2-mkmlizer: ║ ║
rica40325-960-sft-v2-mkmlizer: ║ The license key for the current software has been verified as ║
rica40325-960-sft-v2-mkmlizer: ║ belonging to: ║
rica40325-960-sft-v2-mkmlizer: ║ ║
rica40325-960-sft-v2-mkmlizer: ║ Chai Research Corp. ║
rica40325-960-sft-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rica40325-960-sft-v2-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
rica40325-960-sft-v2-mkmlizer: ║ ║
rica40325-960-sft-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission chaiml-slerpv1-ft-sft-e_58952_v1: HTTPConnectionPool(host='chaiml-slerpv1-ft-sft-e-58952-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
rica40325-960-sft-v2-mkmlizer: Downloaded to shared memory in 35.443s
rica40325-960-sft-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmplwdh5eg8, device:0
rica40325-960-sft-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission chaiml-sft-gemma2-28b-v_83370_v3: HTTPConnectionPool(host='chaiml-sft-gemma2-28b-v-83370-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
rica40325-960-sft-v2-mkmlizer: quantized model in 35.631s
rica40325-960-sft-v2-mkmlizer: Processed model rica40325/960-sft in 71.075s
rica40325-960-sft-v2-mkmlizer: creating bucket guanaco-mkml-models
rica40325-960-sft-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rica40325-960-sft-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rica40325-960-sft-v2
rica40325-960-sft-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rica40325-960-sft-v2/config.json
rica40325-960-sft-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rica40325-960-sft-v2/special_tokens_map.json
rica40325-960-sft-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rica40325-960-sft-v2/tokenizer_config.json
rica40325-960-sft-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rica40325-960-sft-v2/tokenizer.json
rica40325-960-sft-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rica40325-960-sft-v2/flywheel_model.0.safetensors
rica40325-960-sft-v2-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:11, 30.98it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:07, 49.20it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:08, 40.30it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:08, 39.94it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:07, 46.91it/s] Loading 0: 10%|█ | 37/363 [00:00<00:07, 44.87it/s] Loading 0: 12%|█▏ | 42/363 [00:00<00:07, 43.65it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:06, 48.87it/s] Loading 0: 15%|█▌ | 55/363 [00:01<00:06, 46.17it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:08, 34.45it/s] Loading 0: 18%|█▊ | 65/363 [00:01<00:08, 33.27it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:07, 39.99it/s] Loading 0: 21%|██▏ | 78/363 [00:01<00:07, 40.04it/s] Loading 0: 23%|██▎ | 83/363 [00:02<00:07, 39.61it/s] Loading 0: 25%|██▍ | 90/363 [00:02<00:06, 44.89it/s] Loading 0: 26%|██▋ | 96/363 [00:02<00:06, 44.13it/s] Loading 0: 28%|██▊ | 101/363 [00:02<00:06, 43.63it/s] Loading 0: 29%|██▉ | 107/363 [00:02<00:05, 47.51it/s] Loading 0: 31%|███ | 113/363 [00:02<00:05, 42.19it/s] Loading 0: 33%|███▎ | 118/363 [00:02<00:06, 40.46it/s] Loading 0: 35%|███▍ | 126/363 [00:02<00:04, 47.75it/s] Loading 0: 36%|███▌ | 131/363 [00:03<00:04, 48.10it/s] Loading 0: 37%|███▋ | 136/363 [00:03<00:05, 38.72it/s] Loading 0: 39%|███▉ | 142/363 [00:03<00:06, 32.04it/s] Loading 0: 40%|████ | 146/363 [00:03<00:06, 32.60it/s] Loading 0: 41%|████▏ | 150/363 [00:03<00:06, 32.28it/s] Loading 0: 43%|████▎ | 156/363 [00:03<00:05, 38.22it/s] Loading 0: 44%|████▍ | 161/363 [00:03<00:05, 40.21it/s] Loading 0: 46%|████▌ | 166/363 [00:04<00:04, 41.81it/s] Loading 0: 47%|████▋ | 172/363 [00:04<00:04, 42.08it/s] Loading 0: 49%|████▉ | 177/363 [00:04<00:04, 42.18it/s] Loading 0: 51%|█████ | 184/363 [00:04<00:03, 47.51it/s] Loading 0: 52%|█████▏ | 190/363 [00:04<00:03, 45.51it/s] Loading 0: 54%|█████▎ | 195/363 [00:04<00:03, 44.78it/s] Loading 0: 56%|█████▌ | 202/363 [00:04<00:03, 49.12it/s] Loading 0: 57%|█████▋ | 208/363 [00:04<00:03, 46.94it/s] Loading 0: 59%|█████▊ | 213/363 [00:05<00:03, 45.01it/s] Loading 0: 61%|██████ | 220/363 [00:05<00:02, 50.94it/s] Loading 0: 62%|██████▏ | 226/363 [00:05<00:04, 32.26it/s] Loading 0: 64%|██████▎ | 231/363 [00:05<00:03, 34.26it/s] Loading 0: 66%|██████▌ | 238/363 [00:05<00:03, 39.84it/s] Loading 0: 67%|██████▋ | 244/363 [00:05<00:03, 39.41it/s] Loading 0: 69%|██████▊ | 249/363 [00:06<00:02, 39.87it/s] Loading 0: 71%|███████ | 256/363 [00:06<00:02, 44.91it/s] Loading 0: 72%|███████▏ | 262/363 [00:06<00:02, 42.95it/s] Loading 0: 74%|███████▎ | 267/363 [00:06<00:02, 41.93it/s] Loading 0: 75%|███████▌ | 273/363 [00:06<00:01, 45.86it/s] Loading 0: 77%|███████▋ | 278/363 [00:06<00:01, 44.89it/s] Loading 0: 78%|███████▊ | 283/363 [00:06<00:01, 44.91it/s] Loading 0: 79%|███████▉ | 288/363 [00:06<00:01, 45.49it/s] Loading 0: 81%|████████ | 293/363 [00:07<00:01, 37.90it/s] Loading 0: 83%|████████▎ | 301/363 [00:07<00:01, 47.39it/s] Loading 0: 85%|████████▍ | 307/363 [00:14<00:19, 2.80it/s] Loading 0: 86%|████████▌ | 312/363 [00:14<00:13, 3.71it/s] Loading 0: 88%|████████▊ | 320/363 [00:14<00:07, 5.76it/s] Loading 0: 90%|████████▉ | 326/363 [00:14<00:04, 7.63it/s] Loading 0: 91%|█████████ | 331/363 [00:14<00:03, 9.65it/s] Loading 0: 93%|█████████▎| 338/363 [00:14<00:01, 13.55it/s] Loading 0: 95%|█████████▍| 344/363 [00:14<00:01, 17.01it/s] Loading 0: 96%|█████████▌| 349/363 [00:14<00:00, 20.25it/s] Loading 0: 98%|█████████▊| 356/363 [00:15<00:00, 26.46it/s] Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 30.22it/s]
Job rica40325-960-sft-v2-mkmlizer completed after 94.0s with status: succeeded
Stopping job with name rica40325-960-sft-v2-mkmlizer
Pipeline stage MKMLizer completed in 94.54s
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 rica40325-960-sft-v2
Waiting for inference service rica40325-960-sft-v2 to be ready
Failed to get response for submission chaiml-sft-gemma2-28b-v_83370_v4: HTTPConnectionPool(host='chaiml-sft-gemma2-28b-v-83370-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission chaiml-slerpv1-ft-sft-e_58952_v1: HTTPConnectionPool(host='chaiml-slerpv1-ft-sft-e-58952-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission chaiml-sft-gemma2-28b-v_83370_v3: HTTPConnectionPool(host='chaiml-sft-gemma2-28b-v-83370-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service rica40325-960-sft-v2 ready after 110.46996831893921s
Pipeline stage MKMLDeployer completed in 111.00s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2765557765960693s
Received healthy response to inference request in 1.641197919845581s
Received healthy response to inference request in 1.723637342453003s
Received healthy response to inference request in 1.5241100788116455s
Received healthy response to inference request in 1.6040465831756592s
5 requests
0 failed requests
5th percentile: 1.5400973796844482
10th percentile: 1.556084680557251
20th percentile: 1.5880592823028565
30th percentile: 1.6114768505096435
40th percentile: 1.6263373851776124
50th percentile: 1.641197919845581
60th percentile: 1.67417368888855
70th percentile: 1.7071494579315185
80th percentile: 1.8342210292816163
90th percentile: 2.055388402938843
95th percentile: 2.165972089767456
99th percentile: 2.2544390392303466
mean time: 1.7539095401763916
Pipeline stage StressChecker completed in 10.13s
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 0.66s
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 0.63s
Shutdown handler de-registered
rica40325-960-sft_v2 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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4329.30s
Shutdown handler de-registered
rica40325-960-sft_v2 status is now inactive due to auto deactivation removed underperforming models
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1