rirv938-mistral-24b-dpo-_3658

developer_uid: rirv938

submission_id: rirv938-mistral-24b-dpo-_3658_v1

model_name: rirv938-mistral-24b-dpo-_3658_v1

model_group: rirv938/mistral_24b_dpo_

status: torndown

timestamp: 2025-02-23T18:12:29+00:00

num_battles: 6566

num_wins: 3314

celo_rating: 1281.05

family_friendly_score: 0.6158

family_friendly_standard_error: 0.006878813269743554

submission_type: basic

model_repo: rirv938/mistral_24b_dpo_40k_95w_pref_2500_instruct_l128_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': 0.3885192739079583, 'latency_mean': 2.573809472322464, 'latency_p50': 2.55924129486084, 'latency_p90': 2.86470742225647}, {'batch_size': 3, 'throughput': 0.8056241899654382, 'latency_mean': 3.7160777366161346, 'latency_p50': 3.7166343927383423, 'latency_p90': 4.106613421440125}, {'batch_size': 5, 'throughput': 1.058013151976587, 'latency_mean': 4.705806645154953, 'latency_p50': 4.706043243408203, 'latency_p90': 5.2135869503021235}, {'batch_size': 6, 'throughput': 1.1439187431351867, 'latency_mean': 5.214606226682663, 'latency_p50': 5.217777967453003, 'latency_p90': 5.730869626998901}, {'batch_size': 10, 'throughput': 1.3201723993119945, 'latency_mean': 7.507862460613251, 'latency_p50': 7.522092223167419, 'latency_p90': 8.489790153503417}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: rirv938-mistral-24b-dpo-_3658_v1

is_internal_developer: True

language_model: rirv938/mistral_24b_dpo_40k_95w_pref_2500_instruct_l128_v2

model_size: 24B

ranking_group: single

throughput_3p7s: 0.8

us_pacific_date: 2025-02-23

win_ratio: 0.5047212915016753

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-3658-v1-mkmlizer
Waiting for job on rirv938-mistral-24b-dpo-3658-v1-mkmlizer to finish
rirv938-mistral-24b-dpo-3658-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-mistral-24b-dpo-3658-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-mistral-24b-dpo-3658-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-mistral-24b-dpo-3658-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-mistral-24b-dpo-3658-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-mistral-24b-dpo-3658-v1-mkmlizer: ║       /___/                                                         ║
rirv938-mistral-24b-dpo-3658-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-dpo-3658-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-mistral-24b-dpo-3658-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-mistral-24b-dpo-3658-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-mistral-24b-dpo-3658-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-dpo-3658-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-mistral-24b-dpo-3658-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-mistral-24b-dpo-3658-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-dpo-3658-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-mistral-24b-dpo-3658-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-mistral-24b-dpo-3658-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
rirv938-mistral-24b-dpo-3658-v1-mkmlizer: ║                                                                     ║
rirv938-mistral-24b-dpo-3658-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission rirv938-mistral-24b-dpo_77960_v1: ('http://rirv938-mistral-24b-dpo-77960-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-dpo_77960_v1: ('http://rirv938-mistral-24b-dpo-77960-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-dpo_35049_v1: HTTPConnectionPool(host='rirv938-mistral-24b-dpo-35049-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission rirv938-mistral-24b-dpo_77960_v1: ('http://rirv938-mistral-24b-dpo-77960-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-dpo_77960_v2: ('http://rirv938-mistral-24b-dpo-77960-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
rirv938-mistral-24b-dpo-3658-v1-mkmlizer: Downloaded to shared memory in 189.465s
rirv938-mistral-24b-dpo-3658-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpx418suk2, device:0
rirv938-mistral-24b-dpo-3658-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-mistral-24b-dpo-3658-v1-mkmlizer: quantized model in 61.709s
rirv938-mistral-24b-dpo-3658-v1-mkmlizer: Processed model rirv938/mistral_24b_dpo_40k_95w_pref_2500_instruct_l128_v2 in 251.174s
rirv938-mistral-24b-dpo-3658-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-mistral-24b-dpo-3658-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-mistral-24b-dpo-3658-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-3658-v1
rirv938-mistral-24b-dpo-3658-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-3658-v1/config.json
rirv938-mistral-24b-dpo-3658-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-3658-v1/special_tokens_map.json
rirv938-mistral-24b-dpo-3658-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-3658-v1/tokenizer_config.json
rirv938-mistral-24b-dpo-3658-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-3658-v1/tokenizer.json
rirv938-mistral-24b-dpo-3658-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-3658-v1/flywheel_model.1.safetensors
rirv938-mistral-24b-dpo-3658-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-3658-v1/flywheel_model.0.safetensors
rirv938-mistral-24b-dpo-3658-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:17, 20.76it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:20, 17.31it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:16, 21.22it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:26, 13.40it/s]
Loading 0:   4%|▍         | 16/363 [00:01<00:26, 13.22it/s]
Loading 0:   6%|▌         | 21/363 [00:01<00:20, 16.99it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:24, 13.76it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:16, 19.96it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:14, 23.48it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:20, 16.31it/s]
Loading 0:  10%|█         | 38/363 [00:02<00:18, 17.14it/s]
Loading 0:  11%|█▏        | 41/363 [00:02<00:23, 13.58it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:16, 19.03it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:13, 22.39it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:18, 16.46it/s]
Loading 0:  15%|█▌        | 56/363 [00:03<00:17, 17.21it/s]
Loading 0:  16%|█▋        | 59/363 [00:03<00:22, 13.32it/s]
Loading 0:  18%|█▊        | 64/363 [00:03<00:16, 18.54it/s]
Loading 0:  19%|█▊        | 68/363 [00:03<00:13, 21.96it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:18, 15.82it/s]
Loading 0:  20%|██        | 74/363 [00:04<00:17, 16.55it/s]
Loading 0:  21%|██        | 77/363 [00:04<00:21, 13.38it/s]
Loading 0:  23%|██▎       | 82/363 [00:04<00:15, 18.56it/s]
Loading 0:  24%|██▎       | 86/363 [00:04<00:12, 22.14it/s]
Loading 0:  25%|██▍       | 90/363 [00:05<00:18, 14.57it/s]
Loading 0:  26%|██▌       | 95/363 [00:05<00:13, 19.19it/s]
Loading 0:  27%|██▋       | 99/363 [00:05<00:11, 22.37it/s]
Loading 0:  28%|██▊       | 103/363 [00:05<00:14, 18.14it/s]
Loading 0:  29%|██▉       | 106/363 [00:06<00:15, 16.42it/s]
Loading 0:  30%|███       | 109/363 [00:06<00:16, 15.23it/s]
Loading 0:  31%|███       | 111/363 [00:06<00:15, 15.85it/s]
Loading 0:  31%|███       | 113/363 [00:06<00:18, 13.21it/s]
Loading 0:  33%|███▎      | 118/363 [00:06<00:12, 19.45it/s]
Loading 0:  34%|███▎      | 122/363 [00:06<00:10, 23.42it/s]
Loading 0:  35%|███▍      | 126/363 [00:07<00:16, 14.58it/s]
Loading 0:  36%|███▌      | 130/363 [00:07<00:14, 16.20it/s]
Loading 0:  37%|███▋      | 133/363 [00:07<00:13, 16.58it/s]
Loading 0:  38%|███▊      | 137/363 [00:07<00:11, 20.39it/s]
Loading 0:  39%|███▉      | 141/363 [00:08<00:11, 19.41it/s]
Loading 0:  40%|███▉      | 144/363 [00:08<00:14, 14.94it/s]
Loading 0:  40%|████      | 147/363 [00:08<00:12, 17.21it/s]
Loading 0:  41%|████▏     | 150/363 [00:08<00:13, 15.49it/s]
Loading 0:  42%|████▏     | 154/363 [00:08<00:10, 19.52it/s]
Loading 0:  44%|████▎     | 158/363 [00:09<00:08, 23.35it/s]
Loading 0:  44%|████▍     | 161/363 [00:09<00:12, 16.52it/s]
Loading 0:  45%|████▌     | 164/363 [00:09<00:11, 17.38it/s]
Loading 0:  46%|████▌     | 167/363 [00:09<00:14, 13.79it/s]
Loading 0:  47%|████▋     | 172/363 [00:09<00:09, 19.33it/s]
Loading 0:  48%|████▊     | 176/363 [00:10<00:08, 22.68it/s]
Loading 0:  50%|████▉     | 180/363 [00:10<00:12, 14.59it/s]
Loading 0:  50%|█████     | 183/363 [00:10<00:10, 16.44it/s]
Loading 0:  51%|█████     | 186/363 [00:10<00:11, 15.06it/s]
Loading 0:  52%|█████▏    | 190/363 [00:10<00:09, 18.90it/s]
Loading 0:  53%|█████▎    | 194/363 [00:11<00:07, 22.58it/s]
Loading 0:  54%|█████▍    | 197/363 [00:11<00:10, 16.28it/s]
Loading 0:  55%|█████▌    | 200/363 [00:11<00:09, 17.15it/s]
Loading 0:  55%|█████▌    | 200/363 [00:21<00:09, 17.15it/s]
Loading 0:  55%|█████▌    | 201/363 [00:25<04:25,  1.64s/it]
Loading 0:  56%|█████▌    | 203/363 [00:25<03:23,  1.27s/it]
Loading 0:  57%|█████▋    | 207/363 [00:25<01:58,  1.32it/s]
Loading 0:  58%|█████▊    | 210/363 [00:26<01:22,  1.85it/s]
Loading 0:  59%|█████▊    | 213/363 [00:26<01:00,  2.48it/s]
Loading 0:  60%|█████▉    | 216/363 [00:26<00:46,  3.18it/s]
Loading 0:  60%|██████    | 219/363 [00:26<00:33,  4.35it/s]
Loading 0:  61%|██████    | 222/363 [00:27<00:26,  5.40it/s]
Loading 0:  62%|██████▏   | 226/363 [00:27<00:17,  7.85it/s]
Loading 0:  63%|██████▎   | 230/363 [00:27<00:12, 10.71it/s]
Loading 0:  64%|██████▍   | 233/363 [00:27<00:12, 10.38it/s]
Loading 0:  65%|██████▌   | 236/363 [00:27<00:10, 11.76it/s]
Loading 0:  66%|██████▌   | 239/363 [00:28<00:11, 10.59it/s]
Loading 0:  67%|██████▋   | 244/363 [00:28<00:07, 15.38it/s]
Loading 0:  68%|██████▊   | 248/363 [00:28<00:06, 19.01it/s]
Loading 0:  69%|██████▉   | 251/363 [00:28<00:07, 14.84it/s]
Loading 0:  70%|██████▉   | 254/363 [00:28<00:06, 15.71it/s]
Loading 0:  71%|███████   | 257/363 [00:29<00:08, 12.92it/s]
Loading 0:  72%|███████▏  | 263/363 [00:29<00:05, 19.41it/s]
Loading 0:  74%|███████▎  | 267/363 [00:29<00:05, 18.71it/s]
Loading 0:  74%|███████▍  | 270/363 [00:29<00:06, 14.97it/s]
Loading 0:  75%|███████▌  | 274/363 [00:30<00:05, 16.58it/s]
Loading 0:  76%|███████▋  | 277/363 [00:30<00:05, 17.02it/s]
Loading 0:  77%|███████▋  | 281/363 [00:30<00:03, 20.84it/s]
Loading 0:  79%|███████▊  | 285/363 [00:30<00:03, 19.90it/s]
Loading 0:  79%|███████▉  | 288/363 [00:30<00:04, 15.30it/s]
Loading 0:  80%|████████  | 292/363 [00:31<00:04, 16.60it/s]
Loading 0:  81%|████████  | 294/363 [00:31<00:04, 15.61it/s]
Loading 0:  82%|████████▏ | 298/363 [00:31<00:03, 19.69it/s]
Loading 0:  83%|████████▎ | 302/363 [00:31<00:02, 23.47it/s]
Loading 0:  84%|████████▍ | 305/363 [00:31<00:03, 16.30it/s]
Loading 0:  85%|████████▍ | 308/363 [00:31<00:03, 17.03it/s]
Loading 0:  86%|████████▌ | 311/363 [00:32<00:03, 13.40it/s]
Loading 0:  87%|████████▋ | 316/363 [00:32<00:02, 18.82it/s]
Loading 0:  88%|████████▊ | 320/363 [00:32<00:01, 21.79it/s]
Loading 0:  89%|████████▉ | 323/363 [00:32<00:02, 16.21it/s]
Loading 0:  90%|████████▉ | 326/363 [00:32<00:02, 16.97it/s]
Loading 0:  91%|█████████ | 329/363 [00:33<00:02, 13.37it/s]
Loading 0:  92%|█████████▏| 334/363 [00:33<00:01, 18.59it/s]
Loading 0:  93%|█████████▎| 338/363 [00:33<00:01, 22.16it/s]
Loading 0:  94%|█████████▍| 342/363 [00:33<00:01, 14.70it/s]
Loading 0:  95%|█████████▌| 345/363 [00:34<00:01, 16.80it/s]
Loading 0:  96%|█████████▌| 348/363 [00:34<00:00, 15.44it/s]
Loading 0:  97%|█████████▋| 352/363 [00:34<00:00, 19.00it/s]
Loading 0:  98%|█████████▊| 356/363 [00:34<00:00, 22.49it/s]
Loading 0:  99%|█████████▉| 359/363 [00:41<00:02,  1.53it/s]
Loading 0: 100%|█████████▉| 362/363 [00:42<00:00,  2.00it/s]
                                                            
Job rirv938-mistral-24b-dpo-3658-v1-mkmlizer completed after 288.36s with status: succeeded
Stopping job with name rirv938-mistral-24b-dpo-3658-v1-mkmlizer
Pipeline stage MKMLizer completed in 288.93s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-mistral-24b-dpo-3658-v1
Waiting for inference service rirv938-mistral-24b-dpo-3658-v1 to be ready
Failed to get response for submission rirv938-mistral-24b-dpo_35049_v1: HTTPConnectionPool(host='rirv938-mistral-24b-dpo-35049-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission rirv938-mistral-24b-dpo_35049_v1: HTTPConnectionPool(host='rirv938-mistral-24b-dpo-35049-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Failed to get response for submission rirv938-mistral-24b-dpo_77960_v2: ('http://rirv938-mistral-24b-dpo-77960-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Failed to get response for submission rirv938-mistral-24b-dpo_77960_v1: ('http://rirv938-mistral-24b-dpo-77960-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Inference service rirv938-mistral-24b-dpo-3658-v1 ready after 230.85538363456726s
Pipeline stage MKMLDeployer completed in 231.35s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.9176433086395264s
Received healthy response to inference request in 1.9040319919586182s
Received healthy response to inference request in 2.1286466121673584s
Received healthy response to inference request in 1.7294440269470215s
Received healthy response to inference request in 2.3872551918029785s
5 requests
0 failed requests
5th percentile: 1.7643616199493408
10th percentile: 1.7992792129516602
20th percentile: 1.8691143989562988
30th percentile: 1.9489549160003663
40th percentile: 2.038800764083862
50th percentile: 2.1286466121673584
60th percentile: 2.2320900440216063
70th percentile: 2.3355334758758546
80th percentile: 2.4933328151702883
90th percentile: 2.7054880619049073
95th percentile: 2.8115656852722166
99th percentile: 2.8964277839660646
mean time: 2.2134042263031004
Pipeline stage StressChecker completed in 12.51s
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 0.65s
Shutdown handler de-registered
rirv938-mistral-24b-dpo-_3658_v1 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 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-mistral-24b-dpo-3658-v1-profiler
Waiting for inference service rirv938-mistral-24b-dpo-3658-v1-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4806.34s
Shutdown handler de-registered
rirv938-mistral-24b-dpo-_3658_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-mistral-24b-dpo-_3658_v1 status is now torndown due to DeploymentManager action

ChatRequest

Bot Name

Generation Params

Prompt Formatter

ChatMessage 1

Sender

Message

User Message