developer_uid: NischayDnk
submission_id: chaiml-exp118-dpo-ftmeg_78741_v4
model_name: chaiml-exp118-dpo-ftmeg_78741_v4
model_group: ChaiML/exp118-DPO-ftmega
status: torndown
timestamp: 2025-03-25T19:25:34+00:00
num_battles: 5642
num_wins: 1306
celo_rating: 1062.25
family_friendly_score: 0.012599999999999945
family_friendly_standard_error: 0.0015774181436765552
submission_type: basic
model_repo: ChaiML/exp118-DPO-ftmegasft-20ksspref-s01-e3
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.37382490477411656, 'latency_mean': 2.6749588441848755, 'latency_p50': 2.660792112350464, 'latency_p90': 2.9813311100006104}, {'batch_size': 2, 'throughput': 0.578125427463408, 'latency_mean': 3.4559375429153443, 'latency_p50': 3.4619016647338867, 'latency_p90': 3.7976712226867675}, {'batch_size': 3, 'throughput': 0.7277080169851744, 'latency_mean': 4.106423672437668, 'latency_p50': 4.088833570480347, 'latency_p90': 4.532722091674804}, {'batch_size': 4, 'throughput': 0.8563903499896575, 'latency_mean': 4.664404175281525, 'latency_p50': 4.6417646408081055, 'latency_p90': 5.283989214897156}, {'batch_size': 5, 'throughput': 0.9465474097806061, 'latency_mean': 5.267806894779206, 'latency_p50': 5.287561297416687, 'latency_p90': 5.912284398078919}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: chaiml-exp118-dpo-ftmeg_78741_v4
is_internal_developer: False
language_model: ChaiML/exp118-DPO-ftmegasft-20ksspref-s01-e3
model_size: 24B
ranking_group: single
throughput_3p7s: 0.64
us_pacific_date: 2025-03-25
win_ratio: 0.2314781992201347
generation_params: {'temperature': 0.45, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.45, 'frequency_penalty': 0.45, 'stopping_words': ['\n', '</s>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': "''", 'prompt_template': "''", 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '### Response:\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 chaiml-exp118-dpo-ftmeg-78741-v4-mkmlizer
Waiting for job on chaiml-exp118-dpo-ftmeg-78741-v4-mkmlizer to finish
chaiml-exp118-dpo-ftmeg-78741-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-exp118-dpo-ftmeg-78741-v4-mkmlizer: ║ _____ __ __ ║
chaiml-exp118-dpo-ftmeg-78741-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-exp118-dpo-ftmeg-78741-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-exp118-dpo-ftmeg-78741-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-exp118-dpo-ftmeg-78741-v4-mkmlizer: ║ /___/ ║
chaiml-exp118-dpo-ftmeg-78741-v4-mkmlizer: ║ ║
chaiml-exp118-dpo-ftmeg-78741-v4-mkmlizer: ║ Version: 0.12.8 ║
chaiml-exp118-dpo-ftmeg-78741-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-exp118-dpo-ftmeg-78741-v4-mkmlizer: ║ https://mk1.ai ║
chaiml-exp118-dpo-ftmeg-78741-v4-mkmlizer: ║ ║
chaiml-exp118-dpo-ftmeg-78741-v4-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-exp118-dpo-ftmeg-78741-v4-mkmlizer: ║ belonging to: ║
chaiml-exp118-dpo-ftmeg-78741-v4-mkmlizer: ║ ║
chaiml-exp118-dpo-ftmeg-78741-v4-mkmlizer: ║ Chai Research Corp. ║
chaiml-exp118-dpo-ftmeg-78741-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-exp118-dpo-ftmeg-78741-v4-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
chaiml-exp118-dpo-ftmeg-78741-v4-mkmlizer: ║ ║
chaiml-exp118-dpo-ftmeg-78741-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-exp118-dpo-ftmeg-78741-v4-mkmlizer: Downloaded to shared memory in 71.606s
chaiml-exp118-dpo-ftmeg-78741-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpccno9kuy, device:0
chaiml-exp118-dpo-ftmeg-78741-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-exp118-dpo-ftmeg-78741-v4-mkmlizer: quantized model in 53.329s
chaiml-exp118-dpo-ftmeg-78741-v4-mkmlizer: Processed model ChaiML/exp118-DPO-ftmegasft-20ksspref-s01-e3 in 124.936s
chaiml-exp118-dpo-ftmeg-78741-v4-mkmlizer: creating bucket guanaco-mkml-models
chaiml-exp118-dpo-ftmeg-78741-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-exp118-dpo-ftmeg-78741-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-exp118-dpo-ftmeg-78741-v4
chaiml-exp118-dpo-ftmeg-78741-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-exp118-dpo-ftmeg-78741-v4/config.json
chaiml-exp118-dpo-ftmeg-78741-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-exp118-dpo-ftmeg-78741-v4/special_tokens_map.json
chaiml-exp118-dpo-ftmeg-78741-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-exp118-dpo-ftmeg-78741-v4/tokenizer_config.json
chaiml-exp118-dpo-ftmeg-78741-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-exp118-dpo-ftmeg-78741-v4/tokenizer.json
chaiml-exp118-dpo-ftmeg-78741-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-exp118-dpo-ftmeg-78741-v4/flywheel_model.0.safetensors
chaiml-exp118-dpo-ftmeg-78741-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-exp118-dpo-ftmeg-78741-v4/flywheel_model.1.safetensors
chaiml-exp118-dpo-ftmeg-78741-v4-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 4/363 [00:00<00:09, 38.24it/s] Loading 0: 2%|▏ | 8/363 [00:00<00:12, 29.05it/s] Loading 0: 3%|▎ | 12/363 [00:00<00:11, 30.25it/s] Loading 0: 4%|▍ | 16/363 [00:00<00:13, 26.33it/s] Loading 0: 6%|▌ | 21/363 [00:00<00:11, 29.62it/s] Loading 0: 7%|▋ | 25/363 [00:00<00:12, 27.30it/s] Loading 0: 9%|▉ | 32/363 [00:01<00:09, 33.89it/s] Loading 0: 10%|▉ | 36/363 [00:01<00:15, 20.73it/s] Loading 0: 11%|█ | 40/363 [00:01<00:13, 23.20it/s] Loading 0: 12%|█▏ | 43/363 [00:01<00:13, 23.69it/s] Loading 0: 13%|█▎ | 48/363 [00:01<00:11, 27.72it/s] Loading 0: 14%|█▍ | 52/363 [00:01<00:11, 27.35it/s] Loading 0: 16%|█▌ | 57/363 [00:02<00:10, 30.32it/s] Loading 0: 17%|█▋ | 61/363 [00:02<00:10, 28.27it/s] Loading 0: 18%|█▊ | 65/363 [00:02<00:10, 28.94it/s] Loading 0: 19%|█▉ | 70/363 [00:02<00:12, 23.88it/s] Loading 0: 20%|██ | 73/363 [00:02<00:14, 20.66it/s] Loading 0: 22%|██▏ | 79/363 [00:03<00:11, 25.77it/s] Loading 0: 23%|██▎ | 82/363 [00:03<00:11, 25.51it/s] Loading 0: 24%|██▎ | 86/363 [00:03<00:10, 27.62it/s] Loading 0: 25%|██▍ | 89/363 [00:03<00:09, 27.63it/s] Loading 0: 25%|██▌ | 92/363 [00:03<00:12, 21.91it/s] Loading 0: 27%|██▋ | 99/363 [00:03<00:08, 29.52it/s] Loading 0: 28%|██▊ | 103/363 [00:03<00:09, 27.93it/s] Loading 0: 29%|██▉ | 107/363 [00:04<00:10, 23.37it/s] Loading 0: 31%|███ | 112/363 [00:04<00:09, 26.02it/s] Loading 0: 32%|███▏ | 115/363 [00:04<00:09, 25.73it/s] Loading 0: 33%|███▎ | 120/363 [00:04<00:08, 28.30it/s] Loading 0: 34%|███▍ | 123/363 [00:04<00:09, 25.26it/s] Loading 0: 36%|███▌ | 129/363 [00:04<00:07, 30.34it/s] Loading 0: 37%|███▋ | 133/363 [00:04<00:08, 27.98it/s] Loading 0: 38%|███▊ | 138/363 [00:05<00:07, 30.50it/s] Loading 0: 39%|███▉ | 142/363 [00:05<00:07, 29.18it/s] Loading 0: 41%|████ | 149/363 [00:05<00:06, 34.96it/s] Loading 0: 42%|████▏ | 153/363 [00:05<00:09, 22.24it/s] Loading 0: 43%|████▎ | 157/363 [00:05<00:08, 24.69it/s] Loading 0: 44%|████▍ | 161/363 [00:06<00:07, 26.07it/s] Loading 0: 45%|████▌ | 165/363 [00:06<00:07, 27.75it/s] Loading 0: 47%|████▋ | 169/363 [00:06<00:07, 27.14it/s] Loading 0: 48%|████▊ | 174/363 [00:06<00:06, 29.19it/s] Loading 0: 49%|████▉ | 178/363 [00:06<00:06, 27.75it/s] Loading 0: 50%|█████ | 182/363 [00:06<00:06, 28.12it/s] Loading 0: 52%|█████▏ | 187/363 [00:06<00:06, 25.54it/s] Loading 0: 52%|█████▏ | 190/363 [00:07<00:07, 23.33it/s] Loading 0: 53%|█████▎ | 193/363 [00:07<00:07, 24.13it/s] Loading 0: 54%|█████▍ | 196/363 [00:07<00:06, 24.54it/s] Loading 0: 55%|█████▌ | 200/363 [00:21<00:06, 24.54it/s] Loading 0: 55%|█████▌ | 201/363 [00:21<03:00, 1.11s/it] Loading 0: 56%|█████▌ | 203/363 [00:21<02:29, 1.07it/s] Loading 0: 57%|█████▋ | 208/363 [00:22<01:29, 1.73it/s] Loading 0: 58%|█████▊ | 211/363 [00:22<01:08, 2.21it/s] Loading 0: 59%|█████▉ | 214/363 [00:22<00:51, 2.92it/s] Loading 0: 60%|██████ | 218/363 [00:22<00:34, 4.18it/s] Loading 0: 61%|██████ | 221/363 [00:22<00:26, 5.36it/s] Loading 0: 62%|██████▏ | 224/363 [00:22<00:21, 6.37it/s] Loading 0: 63%|██████▎ | 228/363 [00:22<00:15, 8.91it/s] Loading 0: 64%|██████▎ | 231/363 [00:23<00:12, 10.35it/s] Loading 0: 65%|██████▌ | 237/363 [00:23<00:08, 15.53it/s] Loading 0: 66%|██████▋ | 241/363 [00:23<00:06, 17.61it/s] Loading 0: 68%|██████▊ | 246/363 [00:23<00:05, 21.69it/s] Loading 0: 69%|██████▉ | 250/363 [00:23<00:04, 22.82it/s] Loading 0: 70%|███████ | 255/363 [00:23<00:04, 26.32it/s] Loading 0: 71%|███████▏ | 259/363 [00:23<00:03, 26.37it/s] Loading 0: 73%|███████▎ | 266/363 [00:24<00:02, 32.57it/s] Loading 0: 74%|███████▍ | 270/363 [00:24<00:04, 21.45it/s] Loading 0: 75%|███████▌ | 274/363 [00:24<00:03, 24.04it/s] Loading 0: 77%|███████▋ | 278/363 [00:24<00:03, 25.85it/s] Loading 0: 78%|███████▊ | 282/363 [00:24<00:02, 27.31it/s] Loading 0: 79%|███████▉ | 286/363 [00:25<00:02, 25.67it/s] Loading 0: 80%|████████ | 291/363 [00:25<00:02, 28.48it/s] Loading 0: 81%|████████▏ | 295/363 [00:25<00:02, 26.70it/s] Loading 0: 82%|████████▏ | 299/363 [00:25<00:02, 27.76it/s] Loading 0: 84%|████████▎ | 304/363 [00:25<00:02, 25.24it/s] Loading 0: 85%|████████▍ | 307/363 [00:25<00:02, 23.20it/s] Loading 0: 85%|████████▌ | 310/363 [00:25<00:02, 23.99it/s] Loading 0: 86%|████████▌ | 313/363 [00:26<00:02, 23.68it/s] Loading 0: 88%|████████▊ | 318/363 [00:26<00:01, 26.75it/s] Loading 0: 88%|████████▊ | 321/363 [00:26<00:01, 24.48it/s] Loading 0: 90%|█████████ | 327/363 [00:26<00:01, 30.05it/s] Loading 0: 91%|█████████ | 331/363 [00:26<00:01, 28.85it/s] Loading 0: 92%|█████████▏| 335/363 [00:26<00:00, 28.98it/s] Loading 0: 93%|█████████▎| 338/363 [00:26<00:00, 27.66it/s] Loading 0: 94%|█████████▍| 341/363 [00:33<00:13, 1.67it/s] Loading 0: 96%|█████████▌| 347/363 [00:33<00:05, 2.78it/s] Loading 0: 96%|█████████▋| 350/363 [00:34<00:03, 3.50it/s] Loading 0: 98%|█████████▊| 355/363 [00:34<00:01, 5.19it/s] Loading 0: 99%|█████████▉| 359/363 [00:34<00:00, 6.65it/s]
Job chaiml-exp118-dpo-ftmeg-78741-v4-mkmlizer completed after 165.57s with status: succeeded
Stopping job with name chaiml-exp118-dpo-ftmeg-78741-v4-mkmlizer
Pipeline stage MKMLizer completed in 166.07s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.35s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-exp118-dpo-ftmeg-78741-v4
Waiting for inference service chaiml-exp118-dpo-ftmeg-78741-v4 to be ready
Inference service chaiml-exp118-dpo-ftmeg-78741-v4 ready after 100.53312683105469s
Pipeline stage MKMLDeployer completed in 101.22s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.8039143085479736s
Received healthy response to inference request in 2.851489305496216s
Received healthy response to inference request in 2.2878880500793457s
Received healthy response to inference request in 2.3589890003204346s
Received healthy response to inference request in 2.472639322280884s
5 requests
0 failed requests
5th percentile: 2.3021082401275637
10th percentile: 2.316328430175781
20th percentile: 2.3447688102722166
30th percentile: 2.3817190647125246
40th percentile: 2.427179193496704
50th percentile: 2.472639322280884
60th percentile: 2.6051493167877195
70th percentile: 2.7376593112945558
80th percentile: 2.8134293079376222
90th percentile: 2.832459306716919
95th percentile: 2.841974306106567
99th percentile: 2.849586305618286
mean time: 2.5549839973449706
Pipeline stage StressChecker completed in 14.08s
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 0.62s
Shutdown handler de-registered
chaiml-exp118-dpo-ftmeg_78741_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
Pipeline stage OfflineFamilyFriendlyScorer completed in 2872.47s
Shutdown handler de-registered
chaiml-exp118-dpo-ftmeg_78741_v4 status is now inactive due to auto deactivation removed underperforming models
chaiml-exp118-dpo-ftmeg_78741_v4 status is now torndown due to DeploymentManager action