rirv938-mistral-24b-dpo_92582

developer_uid: rirv938

submission_id: rirv938-mistral-24b-dpo_92582_v1

model_name: rirv938-mistral-24b-dpo_92582_v1

model_group: rirv938/mistral_24b_dpo_

status: torndown

timestamp: 2025-02-23T00:33:36+00:00

num_battles: 6583

num_wins: 3368

celo_rating: 1277.53

family_friendly_score: 0.6366

family_friendly_standard_error: 0.006802064980577589

submission_type: basic

model_repo: rirv938/mistral_24b_dpo_20k_1875_without_instruct_format_v2

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 8

max_input_tokens: 768

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.3869335886993566, 'latency_mean': 2.584359738826752, 'latency_p50': 2.581681489944458, 'latency_p90': 2.8537187099456784}, {'batch_size': 3, 'throughput': 0.7954042657573722, 'latency_mean': 3.7640153408050536, 'latency_p50': 3.7553011178970337, 'latency_p90': 4.144362235069275}, {'batch_size': 5, 'throughput': 1.0524919872025598, 'latency_mean': 4.7187128984928135, 'latency_p50': 4.6669453382492065, 'latency_p90': 5.2684062957763675}, {'batch_size': 6, 'throughput': 1.1297101642763816, 'latency_mean': 5.272884795665741, 'latency_p50': 5.285893559455872, 'latency_p90': 5.920025396347046}, {'batch_size': 10, 'throughput': 1.3003165331324325, 'latency_mean': 7.641319974660873, 'latency_p50': 7.672014355659485, 'latency_p90': 8.649037718772888}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: rirv938-mistral-24b-dpo_92582_v1

is_internal_developer: True

language_model: rirv938/mistral_24b_dpo_20k_1875_without_instruct_format_v2

model_size: 24B

ranking_group: single

throughput_3p7s: 0.78

us_pacific_date: 2025-02-22

win_ratio: 0.511620841561598

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 rirv938-mistral-24b-dpo-92582-v1-mkmlizer
Waiting for job on rirv938-mistral-24b-dpo-92582-v1-mkmlizer to finish
Failed to get response for submission rirv938-mistral-24b-bon_67508_v2: ('http://rirv938-mistral-24b-bon-67508-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
rirv938-mistral-24b-dpo-92582-v1-mkmlizer: Downloaded to shared memory in 201.990s
rirv938-mistral-24b-dpo-92582-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpxt9c38mb, device:0
rirv938-mistral-24b-dpo-92582-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission rirv938-mistral-24b-bon_67508_v1: ('http://rirv938-mistral-24b-bon-67508-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Failed to get response for submission rirv938-mistral-24b-bon_67508_v2: ('http://rirv938-mistral-24b-bon-67508-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
rirv938-mistral-24b-dpo-92582-v1-mkmlizer: quantized model in 66.547s
rirv938-mistral-24b-dpo-92582-v1-mkmlizer: Processed model rirv938/mistral_24b_dpo_20k_1875_without_instruct_format_v2 in 268.538s
rirv938-mistral-24b-dpo-92582-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-mistral-24b-dpo-92582-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-mistral-24b-dpo-92582-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-92582-v1
rirv938-mistral-24b-dpo-92582-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-92582-v1/config.json
rirv938-mistral-24b-dpo-92582-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-92582-v1/special_tokens_map.json
rirv938-mistral-24b-dpo-92582-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-92582-v1/tokenizer_config.json
rirv938-mistral-24b-dpo-92582-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-92582-v1/tokenizer.json
rirv938-mistral-24b-dpo-92582-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-92582-v1/flywheel_model.1.safetensors
rirv938-mistral-24b-dpo-92582-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-92582-v1/flywheel_model.0.safetensors
rirv938-mistral-24b-dpo-92582-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:00<00:12, 28.37it/s]
Loading 0:   2%|▏         | 6/363 [00:00<00:26, 13.26it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:17, 20.00it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:25, 13.58it/s]
Loading 0:   4%|▍         | 15/363 [00:01<00:32, 10.86it/s]
Loading 0:   5%|▌         | 19/363 [00:01<00:22, 15.41it/s]
Loading 0:   6%|▌         | 22/363 [00:01<00:23, 14.77it/s]
Loading 0:   7%|▋         | 24/363 [00:01<00:24, 13.63it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:18, 17.95it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:15, 21.28it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:23, 14.14it/s]
Loading 0:  10%|█         | 37/363 [00:02<00:24, 13.14it/s]
Loading 0:  11%|█         | 39/363 [00:02<00:23, 13.91it/s]
Loading 0:  11%|█▏        | 41/363 [00:02<00:29, 10.95it/s]
Loading 0:  13%|█▎        | 46/363 [00:03<00:19, 16.41it/s]
Loading 0:  14%|█▍        | 50/363 [00:03<00:15, 19.61it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:22, 13.73it/s]
Loading 0:  15%|█▌        | 55/363 [00:03<00:23, 12.99it/s]
Loading 0:  16%|█▌        | 57/363 [00:03<00:22, 13.87it/s]
Loading 0:  16%|█▋        | 59/363 [00:04<00:27, 10.89it/s]
Loading 0:  18%|█▊        | 64/363 [00:04<00:18, 16.37it/s]
Loading 0:  19%|█▊        | 68/363 [00:04<00:15, 19.58it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:21, 13.81it/s]
Loading 0:  20%|██        | 73/363 [00:05<00:22, 13.11it/s]
Loading 0:  21%|██        | 75/363 [00:05<00:20, 13.97it/s]
Loading 0:  21%|██        | 77/363 [00:05<00:25, 11.02it/s]
Loading 0:  23%|██▎       | 82/363 [00:05<00:17, 16.53it/s]
Loading 0:  24%|██▎       | 86/363 [00:05<00:13, 19.87it/s]
Loading 0:  25%|██▍       | 89/363 [00:06<00:19, 14.17it/s]
Loading 0:  25%|██▌       | 91/363 [00:06<00:20, 13.52it/s]
Loading 0:  26%|██▌       | 95/363 [00:06<00:15, 17.36it/s]
Loading 0:  27%|██▋       | 99/363 [00:06<00:12, 20.84it/s]
Loading 0:  28%|██▊       | 102/363 [00:06<00:14, 18.58it/s]
Loading 0:  29%|██▉       | 105/363 [00:07<00:18, 14.07it/s]
Loading 0:  29%|██▉       | 107/363 [00:07<00:20, 12.80it/s]
Loading 0:  30%|███       | 109/363 [00:07<00:20, 12.36it/s]
Loading 0:  31%|███       | 111/363 [00:07<00:19, 13.13it/s]
Loading 0:  31%|███       | 113/363 [00:07<00:23, 10.61it/s]
Loading 0:  33%|███▎      | 118/363 [00:07<00:14, 16.51it/s]
Loading 0:  34%|███▎      | 122/363 [00:08<00:11, 20.45it/s]
Loading 0:  34%|███▍      | 125/363 [00:08<00:16, 14.66it/s]
Loading 0:  35%|███▌      | 128/363 [00:08<00:15, 15.44it/s]
Loading 0:  36%|███▌      | 130/363 [00:08<00:17, 13.09it/s]
Loading 0:  36%|███▋      | 132/363 [00:09<00:18, 12.64it/s]
Loading 0:  37%|███▋      | 136/363 [00:09<00:13, 16.89it/s]
Loading 0:  39%|███▊      | 140/363 [00:09<00:10, 20.90it/s]
Loading 0:  39%|███▉      | 143/363 [00:09<00:14, 14.80it/s]
Loading 0:  40%|████      | 146/363 [00:09<00:14, 15.45it/s]
Loading 0:  41%|████      | 148/363 [00:09<00:16, 13.41it/s]
Loading 0:  41%|████▏     | 150/363 [00:10<00:16, 13.00it/s]
Loading 0:  42%|████▏     | 154/363 [00:10<00:11, 17.52it/s]
Loading 0:  44%|████▎     | 158/363 [00:10<00:09, 20.86it/s]
Loading 0:  44%|████▍     | 161/363 [00:10<00:13, 14.58it/s]
Loading 0:  45%|████▍     | 163/363 [00:10<00:14, 13.85it/s]
Loading 0:  45%|████▌     | 165/363 [00:11<00:13, 14.55it/s]
Loading 0:  46%|████▌     | 167/363 [00:11<00:16, 11.73it/s]
Loading 0:  47%|████▋     | 172/363 [00:11<00:10, 17.90it/s]
Loading 0:  48%|████▊     | 176/363 [00:11<00:08, 21.88it/s]
Loading 0:  49%|████▉     | 179/363 [00:11<00:11, 15.44it/s]
Loading 0:  50%|█████     | 182/363 [00:12<00:11, 15.79it/s]
Loading 0:  51%|█████     | 185/363 [00:12<00:14, 12.21it/s]
Loading 0:  52%|█████▏    | 190/363 [00:12<00:10, 17.30it/s]
Loading 0:  53%|█████▎    | 194/363 [00:12<00:08, 20.73it/s]
Loading 0:  54%|█████▍    | 197/363 [00:13<00:10, 15.21it/s]
Loading 0:  55%|█████▌    | 200/363 [00:13<00:10, 15.70it/s]
Loading 0:  56%|█████▌    | 203/363 [00:28<03:57,  1.48s/it]
Loading 0:  57%|█████▋    | 207/363 [00:28<02:33,  1.02it/s]
Loading 0:  58%|█████▊    | 210/363 [00:29<01:51,  1.37it/s]
Loading 0:  59%|█████▊    | 213/363 [00:29<01:23,  1.80it/s]
Loading 0:  60%|█████▉    | 216/363 [00:29<01:04,  2.29it/s]
Loading 0:  60%|██████    | 219/363 [00:29<00:46,  3.10it/s]
Loading 0:  61%|██████    | 221/363 [00:30<00:40,  3.54it/s]
Loading 0:  62%|██████▏   | 226/363 [00:30<00:23,  5.89it/s]
Loading 0:  63%|██████▎   | 230/363 [00:30<00:16,  8.12it/s]
Loading 0:  64%|██████▍   | 233/363 [00:30<00:16,  8.11it/s]
Loading 0:  65%|██████▌   | 236/363 [00:31<00:13,  9.43it/s]
Loading 0:  66%|██████▌   | 238/363 [00:31<00:13,  9.42it/s]
Loading 0:  66%|██████▌   | 240/363 [00:31<00:12,  9.79it/s]
Loading 0:  67%|██████▋   | 244/363 [00:31<00:08, 13.56it/s]
Loading 0:  68%|██████▊   | 248/363 [00:31<00:06, 17.27it/s]
Loading 0:  69%|██████▉   | 251/363 [00:32<00:08, 12.98it/s]
Loading 0:  70%|██████▉   | 253/363 [00:32<00:08, 12.38it/s]
Loading 0:  70%|███████   | 255/363 [00:32<00:08, 13.20it/s]
Loading 0:  71%|███████   | 257/363 [00:32<00:09, 10.84it/s]
Loading 0:  72%|███████▏  | 262/363 [00:32<00:06, 16.54it/s]
Loading 0:  73%|███████▎  | 266/363 [00:32<00:04, 20.22it/s]
Loading 0:  74%|███████▍  | 269/363 [00:33<00:06, 14.41it/s]
Loading 0:  75%|███████▍  | 272/363 [00:33<00:06, 15.10it/s]
Loading 0:  75%|███████▌  | 274/363 [00:33<00:06, 13.01it/s]
Loading 0:  76%|███████▌  | 276/363 [00:33<00:07, 12.04it/s]
Loading 0:  77%|███████▋  | 280/363 [00:33<00:05, 16.23it/s]
Loading 0:  78%|███████▊  | 284/363 [00:34<00:03, 20.29it/s]
Loading 0:  79%|███████▉  | 287/363 [00:34<00:05, 14.21it/s]
Loading 0:  80%|███████▉  | 289/363 [00:34<00:05, 13.40it/s]
Loading 0:  80%|████████  | 291/363 [00:34<00:05, 14.17it/s]
Loading 0:  81%|████████  | 293/363 [00:35<00:06, 11.07it/s]
Loading 0:  82%|████████▏ | 298/363 [00:35<00:03, 16.76it/s]
Loading 0:  83%|████████▎ | 302/363 [00:35<00:02, 20.34it/s]
Loading 0:  84%|████████▍ | 305/363 [00:35<00:04, 14.20it/s]
Loading 0:  85%|████████▍ | 308/363 [00:35<00:03, 14.73it/s]
Loading 0:  85%|████████▌ | 310/363 [00:36<00:04, 13.14it/s]
Loading 0:  86%|████████▌ | 312/363 [00:36<00:04, 12.69it/s]
Loading 0:  87%|████████▋ | 316/363 [00:36<00:02, 16.80it/s]
Loading 0:  88%|████████▊ | 320/363 [00:36<00:02, 20.12it/s]
Loading 0:  89%|████████▉ | 323/363 [00:36<00:02, 14.18it/s]
Loading 0:  90%|████████▉ | 325/363 [00:37<00:02, 13.47it/s]
Loading 0:  90%|█████████ | 327/363 [00:37<00:02, 14.29it/s]
Loading 0:  91%|█████████ | 329/363 [00:37<00:02, 11.41it/s]
Loading 0:  92%|█████████▏| 334/363 [00:37<00:01, 17.52it/s]
Loading 0:  93%|█████████▎| 338/363 [00:37<00:01, 20.75it/s]
Loading 0:  94%|█████████▍| 341/363 [00:38<00:01, 14.25it/s]
Loading 0:  95%|█████████▍| 344/363 [00:38<00:01, 14.87it/s]
Loading 0:  95%|█████████▌| 346/363 [00:38<00:01, 12.90it/s]
Loading 0:  96%|█████████▌| 348/363 [00:38<00:01, 12.35it/s]
Loading 0:  97%|█████████▋| 352/363 [00:38<00:00, 16.51it/s]
Loading 0:  98%|█████████▊| 356/363 [00:38<00:00, 20.28it/s]
Loading 0:  99%|█████████▉| 359/363 [00:46<00:02,  1.40it/s]
Loading 0:  99%|█████████▉| 361/363 [00:46<00:01,  1.69it/s]
                                                            
Job rirv938-mistral-24b-dpo-92582-v1-mkmlizer completed after 296.5s with status: succeeded
Stopping job with name rirv938-mistral-24b-dpo-92582-v1-mkmlizer
Pipeline stage MKMLizer completed in 296.96s
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 rirv938-mistral-24b-dpo-92582-v1
Waiting for inference service rirv938-mistral-24b-dpo-92582-v1 to be ready
Failed to get response for submission rirv938-mistral-24b-bon_67508_v1: ('http://rirv938-mistral-24b-bon-67508-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Inference service rirv938-mistral-24b-dpo-92582-v1 ready after 220.74136567115784s
Pipeline stage MKMLDeployer completed in 221.25s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3513872623443604s
Received healthy response to inference request in 1.816704511642456s
Received healthy response to inference request in 2.494417905807495s
Received healthy response to inference request in 2.0106124877929688s
Received healthy response to inference request in 2.459031820297241s
5 requests
0 failed requests
5th percentile: 1.8554861068725585
10th percentile: 1.894267702102661
20th percentile: 1.9718308925628663
30th percentile: 2.078767442703247
40th percentile: 2.215077352523804
50th percentile: 2.3513872623443604
60th percentile: 2.3944450855255126
70th percentile: 2.437502908706665
80th percentile: 2.466109037399292
90th percentile: 2.4802634716033936
95th percentile: 2.4873406887054443
99th percentile: 2.493002462387085
mean time: 2.226430797576904
Pipeline stage StressChecker completed in 12.34s
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 0.69s
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 0.65s
Shutdown handler de-registered
rirv938-mistral-24b-dpo_92582_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 3013.24s
Shutdown handler de-registered
rirv938-mistral-24b-dpo_92582_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-mistral-24b-dpo_92582_v1 status is now torndown due to DeploymentManager action

ChatRequest

Bot Name

Generation Params

Prompt Formatter

ChatMessage 1

Sender

Message

User Message