chaiml-mistral-24b-dpo-_43220

developer_uid: rirv938

submission_id: chaiml-mistral-24b-dpo-_43220_v5

model_name: chaiml-mistral-24b-dpo-_43220_v5

model_group: ChaiML/mistral_24b_dpo_4

status: torndown

timestamp: 2025-04-16T18:45:26+00:00

num_battles: 5787

num_wins: 2895

celo_rating: 1288.27

family_friendly_score: 0.46120000000000005

family_friendly_standard_error: 0.007049745527322245

submission_type: basic

model_repo: ChaiML/mistral_24b_dpo_40k_95w_pref_1250_instruct_dpo_2_merged

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 8

max_input_tokens: 768

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.3864879509003883, 'latency_mean': 2.587307492494583, 'latency_p50': 2.575433611869812, 'latency_p90': 2.866808867454529}, {'batch_size': 3, 'throughput': 0.7998334819331742, 'latency_mean': 3.74163822889328, 'latency_p50': 3.718487024307251, 'latency_p90': 4.132718801498413}, {'batch_size': 5, 'throughput': 1.0377151217697216, 'latency_mean': 4.783027431964874, 'latency_p50': 4.7850446701049805, 'latency_p90': 5.357693815231324}, {'batch_size': 6, 'throughput': 1.119856691160377, 'latency_mean': 5.3133665263652805, 'latency_p50': 5.3342039585113525, 'latency_p90': 5.8475738048553465}, {'batch_size': 10, 'throughput': 1.2652892364029125, 'latency_mean': 7.830508300065994, 'latency_p50': 7.860274314880371, 'latency_p90': 8.662798643112183}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-mistral-24b-dpo-_43220_v5

is_internal_developer: True

language_model: ChaiML/mistral_24b_dpo_40k_95w_pref_1250_instruct_dpo_2_merged

model_size: 24B

ranking_group: single

throughput_3p7s: 0.79

us_pacific_date: 2025-04-16

win_ratio: 0.5002592016588906

generation_params: {'temperature': 0.9, 'top_p': 0.9, 'min_p': 0.6, 'top_k': 80, 'presence_penalty': 0.5, 'frequency_penalty': 0.5, 'stopping_words': ['\n', '</s>', 'You:', '###'], 'max_input_tokens': 768, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '[INST]', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '[/INST]{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-mistral-24b-dpo-43220-v5-mkmlizer
Waiting for job on chaiml-mistral-24b-dpo-43220-v5-mkmlizer to finish
chaiml-mistral-24b-dpo-43220-v5-mkmlizer: Downloaded to shared memory in 193.104s
chaiml-mistral-24b-dpo-43220-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmptpxd2kf8, device:0
chaiml-mistral-24b-dpo-43220-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral-24b-dpo-43220-v5-mkmlizer: quantized model in 63.968s
chaiml-mistral-24b-dpo-43220-v5-mkmlizer: Processed model ChaiML/mistral_24b_dpo_40k_95w_pref_1250_instruct_dpo_2_merged in 257.073s
chaiml-mistral-24b-dpo-43220-v5-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral-24b-dpo-43220-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral-24b-dpo-43220-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral-24b-dpo-43220-v5
chaiml-mistral-24b-dpo-43220-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral-24b-dpo-43220-v5/config.json
chaiml-mistral-24b-dpo-43220-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral-24b-dpo-43220-v5/special_tokens_map.json
chaiml-mistral-24b-dpo-43220-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral-24b-dpo-43220-v5/tokenizer_config.json
chaiml-mistral-24b-dpo-43220-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral-24b-dpo-43220-v5/tokenizer.json
chaiml-mistral-24b-dpo-43220-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral-24b-dpo-43220-v5/flywheel_model.0.safetensors
chaiml-mistral-24b-dpo-43220-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-mistral-24b-dpo-43220-v5/flywheel_model.1.safetensors
chaiml-mistral-24b-dpo-43220-v5-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:00<00:12, 29.39it/s]
Loading 0:   2%|▏         | 6/363 [00:00<00:25, 13.91it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:17, 20.65it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:25, 13.96it/s]
Loading 0:   4%|▍         | 15/363 [00:01<00:30, 11.57it/s]
Loading 0:   6%|▌         | 21/363 [00:01<00:20, 16.75it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:25, 13.41it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:17, 18.71it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:15, 21.54it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:21, 14.95it/s]
Loading 0:  10%|█         | 38/363 [00:02<00:20, 15.54it/s]
Loading 0:  11%|█         | 40/363 [00:02<00:23, 13.90it/s]
Loading 0:  12%|█▏        | 42/363 [00:02<00:24, 13.25it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:18, 17.20it/s]
Loading 0:  14%|█▍        | 50/363 [00:03<00:15, 20.65it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:21, 14.43it/s]
Loading 0:  15%|█▌        | 55/363 [00:03<00:22, 13.77it/s]
Loading 0:  16%|█▌        | 57/363 [00:03<00:20, 14.67it/s]
Loading 0:  16%|█▋        | 59/363 [00:03<00:25, 11.93it/s]
Loading 0:  18%|█▊        | 64/363 [00:04<00:16, 17.76it/s]
Loading 0:  19%|█▊        | 68/363 [00:04<00:13, 21.24it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:19, 14.99it/s]
Loading 0:  20%|██        | 74/363 [00:04<00:18, 15.78it/s]
Loading 0:  21%|██        | 76/363 [00:04<00:20, 14.09it/s]
Loading 0:  21%|██▏       | 78/363 [00:05<00:20, 13.80it/s]
Loading 0:  23%|██▎       | 82/363 [00:05<00:15, 17.94it/s]
Loading 0:  24%|██▎       | 86/363 [00:05<00:12, 21.57it/s]
Loading 0:  25%|██▍       | 89/363 [00:05<00:18, 15.07it/s]
Loading 0:  25%|██▌       | 91/363 [00:05<00:19, 14.27it/s]
Loading 0:  26%|██▌       | 95/363 [00:05<00:14, 18.36it/s]
Loading 0:  27%|██▋       | 99/363 [00:06<00:12, 21.77it/s]
Loading 0:  28%|██▊       | 102/363 [00:06<00:13, 19.98it/s]
Loading 0:  29%|██▉       | 105/363 [00:06<00:17, 14.86it/s]
Loading 0:  29%|██▉       | 107/363 [00:06<00:18, 13.72it/s]
Loading 0:  30%|███       | 109/363 [00:06<00:19, 13.24it/s]
Loading 0:  31%|███       | 111/363 [00:07<00:17, 14.25it/s]
Loading 0:  31%|███       | 113/363 [00:07<00:21, 11.60it/s]
Loading 0:  33%|███▎      | 118/363 [00:07<00:13, 17.95it/s]
Loading 0:  34%|███▎      | 122/363 [00:07<00:11, 21.75it/s]
Loading 0:  34%|███▍      | 125/363 [00:07<00:15, 15.42it/s]
Loading 0:  35%|███▌      | 128/363 [00:08<00:14, 16.04it/s]
Loading 0:  36%|███▌      | 131/363 [00:08<00:18, 12.59it/s]
Loading 0:  37%|███▋      | 136/363 [00:08<00:12, 17.60it/s]
Loading 0:  39%|███▊      | 140/363 [00:08<00:10, 20.86it/s]
Loading 0:  39%|███▉      | 143/363 [00:08<00:14, 15.60it/s]
Loading 0:  40%|████      | 146/363 [00:09<00:13, 16.16it/s]
Loading 0:  41%|████      | 149/363 [00:09<00:16, 12.74it/s]
Loading 0:  42%|████▏     | 154/363 [00:09<00:11, 17.47it/s]
Loading 0:  44%|████▎     | 158/363 [00:09<00:09, 20.55it/s]
Loading 0:  44%|████▍     | 161/363 [00:10<00:13, 15.16it/s]
Loading 0:  45%|████▌     | 164/363 [00:10<00:12, 15.77it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:15, 12.55it/s]
Loading 0:  47%|████▋     | 172/363 [00:10<00:11, 17.19it/s]
Loading 0:  48%|████▊     | 176/363 [00:10<00:09, 20.11it/s]
Loading 0:  49%|████▉     | 179/363 [00:11<00:12, 14.96it/s]
Loading 0:  50%|█████     | 182/363 [00:11<00:11, 15.58it/s]
Loading 0:  51%|█████     | 184/363 [00:11<00:12, 14.07it/s]
Loading 0:  51%|█████     | 186/363 [00:11<00:13, 13.46it/s]
Loading 0:  52%|█████▏    | 190/363 [00:11<00:10, 16.95it/s]
Loading 0:  53%|█████▎    | 194/363 [00:12<00:08, 20.35it/s]
Loading 0:  54%|█████▍    | 197/363 [00:12<00:11, 14.62it/s]
Loading 0:  55%|█████▍    | 199/363 [00:12<00:11, 13.83it/s]
Loading 0:  55%|█████▌    | 201/363 [00:27<04:41,  1.74s/it]
Loading 0:  56%|█████▌    | 203/363 [00:27<03:34,  1.34s/it]
Loading 0:  57%|█████▋    | 207/363 [00:27<02:04,  1.25it/s]
Loading 0:  58%|█████▊    | 210/363 [00:27<01:26,  1.76it/s]
Loading 0:  59%|█████▊    | 213/363 [00:28<01:03,  2.36it/s]
Loading 0:  59%|█████▉    | 215/363 [00:28<00:51,  2.87it/s]
Loading 0:  60%|█████▉    | 217/363 [00:28<00:41,  3.55it/s]
Loading 0:  61%|██████    | 220/363 [00:28<00:29,  4.84it/s]
Loading 0:  61%|██████    | 222/363 [00:28<00:24,  5.67it/s]
Loading 0:  62%|██████▏   | 226/363 [00:28<00:15,  8.70it/s]
Loading 0:  63%|██████▎   | 230/363 [00:28<00:11, 12.02it/s]
Loading 0:  64%|██████▍   | 233/363 [00:29<00:11, 11.14it/s]
Loading 0:  65%|██████▌   | 236/363 [00:29<00:10, 12.63it/s]
Loading 0:  66%|██████▌   | 238/363 [00:29<00:10, 12.17it/s]
Loading 0:  66%|██████▌   | 240/363 [00:29<00:10, 12.14it/s]
Loading 0:  67%|██████▋   | 244/363 [00:29<00:07, 16.34it/s]
Loading 0:  68%|██████▊   | 248/363 [00:29<00:05, 20.09it/s]
Loading 0:  69%|██████▉   | 251/363 [00:30<00:07, 14.99it/s]
Loading 0:  70%|██████▉   | 254/363 [00:30<00:06, 15.89it/s]
Loading 0:  71%|███████   | 256/363 [00:30<00:07, 14.16it/s]
Loading 0:  71%|███████   | 258/363 [00:30<00:07, 13.68it/s]
Loading 0:  72%|███████▏  | 262/363 [00:30<00:05, 17.97it/s]
Loading 0:  73%|███████▎  | 266/363 [00:31<00:04, 21.67it/s]
Loading 0:  74%|███████▍  | 269/363 [00:31<00:06, 15.18it/s]
Loading 0:  75%|███████▍  | 271/363 [00:31<00:06, 14.44it/s]
Loading 0:  75%|███████▌  | 273/363 [00:31<00:05, 15.31it/s]
Loading 0:  76%|███████▌  | 275/363 [00:31<00:07, 12.10it/s]
Loading 0:  77%|███████▋  | 280/363 [00:32<00:04, 18.16it/s]
Loading 0:  78%|███████▊  | 284/363 [00:32<00:03, 21.52it/s]
Loading 0:  79%|███████▉  | 287/363 [00:32<00:05, 15.20it/s]
Loading 0:  80%|███████▉  | 290/363 [00:32<00:04, 15.92it/s]
Loading 0:  80%|████████  | 292/363 [00:32<00:04, 14.22it/s]
Loading 0:  81%|████████  | 294/363 [00:33<00:05, 13.53it/s]
Loading 0:  82%|████████▏ | 298/363 [00:33<00:03, 17.45it/s]
Loading 0:  83%|████████▎ | 302/363 [00:33<00:02, 20.99it/s]
Loading 0:  84%|████████▍ | 305/363 [00:33<00:03, 14.71it/s]
Loading 0:  85%|████████▍ | 307/363 [00:33<00:03, 14.04it/s]
Loading 0:  85%|████████▌ | 309/363 [00:33<00:03, 14.99it/s]
Loading 0:  86%|████████▌ | 311/363 [00:34<00:04, 12.26it/s]
Loading 0:  87%|████████▋ | 316/363 [00:34<00:02, 18.37it/s]
Loading 0:  88%|████████▊ | 320/363 [00:34<00:01, 21.72it/s]
Loading 0:  89%|████████▉ | 323/363 [00:34<00:02, 15.33it/s]
Loading 0:  90%|████████▉ | 326/363 [00:35<00:02, 15.70it/s]
Loading 0:  90%|█████████ | 328/363 [00:35<00:02, 14.23it/s]
Loading 0:  91%|█████████ | 330/363 [00:35<00:02, 13.82it/s]
Loading 0:  92%|█████████▏| 334/363 [00:35<00:01, 18.10it/s]
Loading 0:  93%|█████████▎| 338/363 [00:35<00:01, 21.74it/s]
Loading 0:  94%|█████████▍| 341/363 [00:35<00:01, 15.30it/s]
Loading 0:  95%|█████████▍| 344/363 [00:36<00:01, 16.09it/s]
Loading 0:  95%|█████████▌| 346/363 [00:36<00:01, 14.41it/s]
Loading 0:  96%|█████████▌| 348/363 [00:36<00:01, 13.98it/s]
Loading 0:  97%|█████████▋| 352/363 [00:36<00:00, 18.16it/s]
Loading 0:  98%|█████████▊| 356/363 [00:36<00:00, 21.52it/s]
Loading 0:  99%|█████████▉| 359/363 [00:43<00:02,  1.44it/s]
Loading 0:  99%|█████████▉| 361/363 [00:44<00:01,  1.74it/s]
                                                            
Job chaiml-mistral-24b-dpo-43220-v5-mkmlizer completed after 288.69s with status: succeeded
Stopping job with name chaiml-mistral-24b-dpo-43220-v5-mkmlizer
Pipeline stage MKMLizer completed in 289.25s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.20s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-mistral-24b-dpo-43220-v5
Waiting for inference service chaiml-mistral-24b-dpo-43220-v5 to be ready
Inference service chaiml-mistral-24b-dpo-43220-v5 ready after 130.6015305519104s
Pipeline stage MKMLDeployer completed in 131.15s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.470691442489624s
Received healthy response to inference request in 2.574948787689209s
Received healthy response to inference request in 2.8164143562316895s
Received healthy response to inference request in 2.7145941257476807s
Received healthy response to inference request in 2.9274332523345947s
5 requests
0 failed requests
5th percentile: 2.6028778553009033
10th percentile: 2.6308069229125977
20th percentile: 2.6866650581359863
30th percentile: 2.7349581718444824
40th percentile: 2.775686264038086
50th percentile: 2.8164143562316895
60th percentile: 2.8608219146728517
70th percentile: 2.9052294731140136
80th percentile: 3.0360848903656006
90th percentile: 3.2533881664276123
95th percentile: 3.362039804458618
99th percentile: 3.448961114883423
mean time: 2.9008163928985597
Pipeline stage StressChecker completed in 15.92s
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 0.72s
Shutdown handler de-registered
chaiml-mistral-24b-dpo-_43220_v5 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 0.10s
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-mistral-24b-dpo-43220-v5-profiler
Waiting for inference service chaiml-mistral-24b-dpo-43220-v5-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 3123.01s
Shutdown handler de-registered
chaiml-mistral-24b-dpo-_43220_v5 status is now inactive due to auto deactivation removed underperforming models
chaiml-mistral-24b-dpo-_43220_v5 status is now torndown due to DeploymentManager action