rirv938-mistral-24b-dpo_77960

developer_uid: rirv938

submission_id: rirv938-mistral-24b-dpo_77960_v1

model_name: rirv938-mistral-24b-dpo_77960_v1

model_group: rirv938/mistral_24b_dpo_

status: torndown

timestamp: 2025-02-23T16:02:07+00:00

num_battles: 57

num_wins: 29

family_friendly_score: 0.0

family_friendly_standard_error: 0.0

submission_type: basic

model_repo: rirv938/mistral_24b_dpo_96k_6000_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': 0.38695431816228293, 'latency_mean': 2.584200040102005, 'latency_p50': 2.608766794204712, 'latency_p90': 2.88020544052124}, {'batch_size': 3, 'throughput': 0.794186180972352, 'latency_mean': 3.7640536987781523, 'latency_p50': 3.7579351663589478, 'latency_p90': 4.111753821372986}, {'batch_size': 5, 'throughput': 1.058777792540299, 'latency_mean': 4.699408493041992, 'latency_p50': 4.691870450973511, 'latency_p90': 5.191868448257446}, {'batch_size': 6, 'throughput': 1.1234304623971545, 'latency_mean': 5.305357538461685, 'latency_p50': 5.302021026611328, 'latency_p90': 5.9132682323455805}, {'batch_size': 10, 'throughput': 1.3137686226693024, 'latency_mean': 7.539451429843902, 'latency_p50': 7.489315509796143, 'latency_p90': 8.499076509475708}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: rirv938-mistral-24b-dpo_77960_v1

ineligible_reason: num_battles<5000

is_internal_developer: True

language_model: rirv938/mistral_24b_dpo_96k_6000_v2

model_size: 24B

ranking_group: single

throughput_3p7s: 0.78

us_pacific_date: 2025-02-23

win_ratio: 0.5087719298245614

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-77960-v1-mkmlizer
Waiting for job on rirv938-mistral-24b-dpo-77960-v1-mkmlizer to finish
rirv938-mistral-24b-dpo-77960-v1-mkmlizer: Downloaded to shared memory in 165.731s
rirv938-mistral-24b-dpo-77960-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp1ibq04vr, device:0
rirv938-mistral-24b-dpo-77960-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-mistral-24b-dpo-77960-v1-mkmlizer: quantized model in 62.979s
rirv938-mistral-24b-dpo-77960-v1-mkmlizer: Processed model rirv938/mistral_24b_dpo_96k_6000_v2 in 228.711s
rirv938-mistral-24b-dpo-77960-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-mistral-24b-dpo-77960-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-mistral-24b-dpo-77960-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-77960-v1
rirv938-mistral-24b-dpo-77960-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-77960-v1/config.json
rirv938-mistral-24b-dpo-77960-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-77960-v1/special_tokens_map.json
rirv938-mistral-24b-dpo-77960-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-77960-v1/tokenizer_config.json
rirv938-mistral-24b-dpo-77960-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-77960-v1/tokenizer.json
rirv938-mistral-24b-dpo-77960-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-77960-v1/flywheel_model.1.safetensors
rirv938-mistral-24b-dpo-77960-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-mistral-24b-dpo-77960-v1/flywheel_model.0.safetensors
rirv938-mistral-24b-dpo-77960-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:17, 20.82it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:20, 17.30it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:16, 21.07it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:25, 13.47it/s]
Loading 0:   4%|▍         | 15/363 [00:01<00:31, 11.20it/s]
Loading 0:   5%|▌         | 19/363 [00:01<00:21, 16.23it/s]
Loading 0:   6%|▌         | 22/363 [00:01<00:21, 15.62it/s]
Loading 0:   7%|▋         | 25/363 [00:01<00:21, 15.83it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:19, 17.49it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:15, 21.04it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:22, 14.39it/s]
Loading 0:  10%|█         | 37/363 [00:02<00:23, 13.82it/s]
Loading 0:  11%|█         | 40/363 [00:02<00:22, 14.29it/s]
Loading 0:  12%|█▏        | 42/363 [00:02<00:23, 13.70it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:17, 17.89it/s]
Loading 0:  14%|█▍        | 50/363 [00:03<00:14, 21.07it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:21, 14.38it/s]
Loading 0:  15%|█▌        | 55/363 [00:03<00:22, 13.71it/s]
Loading 0:  16%|█▌        | 57/363 [00:03<00:20, 14.76it/s]
Loading 0:  16%|█▋        | 59/363 [00:03<00:25, 11.75it/s]
Loading 0:  18%|█▊        | 64/363 [00:04<00:17, 17.51it/s]
Loading 0:  19%|█▊        | 68/363 [00:04<00:14, 21.01it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:19, 14.98it/s]
Loading 0:  20%|██        | 74/363 [00:04<00:18, 15.60it/s]
Loading 0:  21%|██        | 76/363 [00:04<00:20, 14.08it/s]
Loading 0:  21%|██▏       | 78/363 [00:05<00:21, 13.39it/s]
Loading 0:  23%|██▎       | 82/363 [00:05<00:16, 17.27it/s]
Loading 0:  24%|██▎       | 86/363 [00:05<00:13, 20.64it/s]
Loading 0:  25%|██▍       | 89/363 [00:05<00:18, 14.54it/s]
Loading 0:  25%|██▌       | 91/363 [00:05<00:19, 13.82it/s]
Loading 0:  26%|██▌       | 95/363 [00:05<00:15, 17.74it/s]
Loading 0:  27%|██▋       | 99/363 [00:06<00:12, 21.00it/s]
Loading 0:  28%|██▊       | 102/363 [00:06<00:13, 19.10it/s]
Loading 0:  29%|██▉       | 105/363 [00:06<00:18, 14.12it/s]
Loading 0:  29%|██▉       | 107/363 [00:06<00:19, 13.16it/s]
Loading 0:  30%|███       | 109/363 [00:07<00:20, 12.70it/s]
Loading 0:  31%|███       | 111/363 [00:07<00:18, 13.72it/s]
Loading 0:  31%|███       | 113/363 [00:07<00:22, 11.02it/s]
Loading 0:  33%|███▎      | 118/363 [00:07<00:14, 16.80it/s]
Loading 0:  34%|███▎      | 122/363 [00:07<00:11, 20.42it/s]
Loading 0:  34%|███▍      | 125/363 [00:08<00:16, 14.56it/s]
Loading 0:  35%|███▍      | 127/363 [00:08<00:17, 13.81it/s]
Loading 0:  36%|███▌      | 130/363 [00:08<00:16, 14.50it/s]
Loading 0:  36%|███▋      | 132/363 [00:08<00:16, 13.59it/s]
Loading 0:  37%|███▋      | 136/363 [00:08<00:12, 17.61it/s]
Loading 0:  39%|███▊      | 140/363 [00:08<00:10, 21.15it/s]
Loading 0:  39%|███▉      | 143/363 [00:09<00:14, 14.97it/s]
Loading 0:  40%|███▉      | 145/363 [00:09<00:15, 14.19it/s]
Loading 0:  40%|████      | 147/363 [00:09<00:14, 15.16it/s]
Loading 0:  41%|████      | 149/363 [00:09<00:17, 12.22it/s]
Loading 0:  42%|████▏     | 154/363 [00:09<00:11, 17.96it/s]
Loading 0:  44%|████▎     | 158/363 [00:09<00:09, 21.17it/s]
Loading 0:  44%|████▍     | 161/363 [00:10<00:13, 14.92it/s]
Loading 0:  45%|████▍     | 163/363 [00:10<00:14, 14.10it/s]
Loading 0:  45%|████▌     | 165/363 [00:10<00:13, 14.99it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:16, 12.11it/s]
Loading 0:  47%|████▋     | 172/363 [00:10<00:10, 18.00it/s]
Loading 0:  48%|████▊     | 176/363 [00:11<00:08, 21.31it/s]
Loading 0:  49%|████▉     | 179/363 [00:11<00:12, 15.22it/s]
Loading 0:  50%|█████     | 182/363 [00:11<00:11, 15.67it/s]
Loading 0:  51%|█████     | 184/363 [00:11<00:12, 14.09it/s]
Loading 0:  51%|█████     | 186/363 [00:11<00:13, 13.59it/s]
Loading 0:  52%|█████▏    | 190/363 [00:12<00:09, 17.72it/s]
Loading 0:  53%|█████▎    | 194/363 [00:12<00:07, 21.40it/s]
Loading 0:  54%|█████▍    | 197/363 [00:12<00:10, 15.27it/s]
Loading 0:  55%|█████▍    | 199/363 [00:12<00:11, 14.45it/s]
Loading 0:  55%|█████▌    | 201/363 [00:26<04:32,  1.68s/it]
Loading 0:  56%|█████▌    | 203/363 [00:27<03:28,  1.30s/it]
Loading 0:  57%|█████▋    | 207/363 [00:27<02:00,  1.29it/s]
Loading 0:  58%|█████▊    | 210/363 [00:27<01:24,  1.82it/s]
Loading 0:  59%|█████▊    | 213/363 [00:27<01:01,  2.42it/s]
Loading 0:  59%|█████▉    | 215/363 [00:27<00:50,  2.94it/s]
Loading 0:  60%|█████▉    | 217/363 [00:28<00:40,  3.60it/s]
Loading 0:  60%|██████    | 219/363 [00:28<00:31,  4.54it/s]
Loading 0:  61%|██████    | 221/363 [00:28<00:27,  5.10it/s]
Loading 0:  62%|██████▏   | 226/363 [00:28<00:15,  8.92it/s]
Loading 0:  63%|██████▎   | 230/363 [00:28<00:11, 12.03it/s]
Loading 0:  64%|██████▍   | 233/363 [00:29<00:11, 10.85it/s]
Loading 0:  65%|██████▍   | 235/363 [00:29<00:11, 11.02it/s]
Loading 0:  65%|██████▌   | 237/363 [00:29<00:10, 12.16it/s]
Loading 0:  66%|██████▌   | 239/363 [00:29<00:11, 10.49it/s]
Loading 0:  67%|██████▋   | 244/363 [00:29<00:07, 16.18it/s]
Loading 0:  68%|██████▊   | 248/363 [00:29<00:05, 19.72it/s]
Loading 0:  69%|██████▉   | 251/363 [00:30<00:07, 14.39it/s]
Loading 0:  70%|██████▉   | 254/363 [00:30<00:07, 14.95it/s]
Loading 0:  71%|███████   | 256/363 [00:30<00:07, 13.43it/s]
Loading 0:  71%|███████   | 258/363 [00:30<00:08, 13.00it/s]
Loading 0:  72%|███████▏  | 262/363 [00:30<00:05, 17.12it/s]
Loading 0:  73%|███████▎  | 266/363 [00:30<00:04, 20.67it/s]
Loading 0:  74%|███████▍  | 269/363 [00:31<00:06, 14.86it/s]
Loading 0:  75%|███████▍  | 271/363 [00:31<00:06, 13.99it/s]
Loading 0:  75%|███████▌  | 273/363 [00:31<00:06, 14.77it/s]
Loading 0:  76%|███████▌  | 275/363 [00:31<00:07, 11.73it/s]
Loading 0:  77%|███████▋  | 280/363 [00:31<00:04, 17.63it/s]
Loading 0:  78%|███████▊  | 284/363 [00:32<00:03, 20.93it/s]
Loading 0:  79%|███████▉  | 287/363 [00:32<00:05, 14.89it/s]
Loading 0:  80%|███████▉  | 290/363 [00:32<00:04, 15.45it/s]
Loading 0:  80%|████████  | 292/363 [00:32<00:05, 13.74it/s]
Loading 0:  81%|████████  | 294/363 [00:33<00:05, 13.23it/s]
Loading 0:  82%|████████▏ | 298/363 [00:33<00:03, 17.08it/s]
Loading 0:  83%|████████▎ | 302/363 [00:33<00:02, 20.74it/s]
Loading 0:  84%|████████▍ | 305/363 [00:33<00:03, 14.62it/s]
Loading 0:  85%|████████▍ | 307/363 [00:33<00:04, 13.68it/s]
Loading 0:  85%|████████▌ | 309/363 [00:33<00:03, 14.51it/s]
Loading 0:  86%|████████▌ | 311/363 [00:34<00:04, 11.67it/s]
Loading 0:  87%|████████▋ | 316/363 [00:34<00:02, 17.46it/s]
Loading 0:  88%|████████▊ | 320/363 [00:34<00:02, 20.82it/s]
Loading 0:  89%|████████▉ | 323/363 [00:34<00:02, 14.81it/s]
Loading 0:  90%|████████▉ | 326/363 [00:34<00:02, 15.50it/s]
Loading 0:  90%|█████████ | 328/363 [00:35<00:02, 13.85it/s]
Loading 0:  91%|█████████ | 330/363 [00:35<00:02, 13.28it/s]
Loading 0:  92%|█████████▏| 334/363 [00:35<00:01, 17.22it/s]
Loading 0:  93%|█████████▎| 338/363 [00:35<00:01, 20.89it/s]
Loading 0:  94%|█████████▍| 341/363 [00:35<00:01, 14.88it/s]
Loading 0:  94%|█████████▍| 343/363 [00:36<00:01, 14.10it/s]
Loading 0:  95%|█████████▌| 345/363 [00:36<00:01, 14.77it/s]
Loading 0:  96%|█████████▌| 347/363 [00:36<00:01, 12.06it/s]
Loading 0:  97%|█████████▋| 352/363 [00:36<00:00, 18.08it/s]
Loading 0:  98%|█████████▊| 356/363 [00:36<00:00, 21.60it/s]
Loading 0:  99%|█████████▉| 359/363 [00:43<00:02,  1.51it/s]
Loading 0:  99%|█████████▉| 361/363 [00:43<00:01,  1.81it/s]
                                                            
Job rirv938-mistral-24b-dpo-77960-v1-mkmlizer completed after 266.58s with status: succeeded
Stopping job with name rirv938-mistral-24b-dpo-77960-v1-mkmlizer
Pipeline stage MKMLizer completed in 267.06s
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-77960-v1
Waiting for inference service rirv938-mistral-24b-dpo-77960-v1 to be ready
Inference service rirv938-mistral-24b-dpo-77960-v1 ready after 231.3748641014099s
Pipeline stage MKMLDeployer completed in 231.78s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 2.7619287967681885s
Received healthy response to inference request in 2.212604522705078s
Received healthy response to inference request in 2.158853054046631s
Received healthy response to inference request in 2.3734183311462402s
5 requests
1 failed requests
5th percentile: 2.1696033477783203
10th percentile: 2.1803536415100098
20th percentile: 2.2018542289733887
30th percentile: 2.2447672843933106
40th percentile: 2.309092807769775
50th percentile: 2.3734183311462402
60th percentile: 2.5288225173950196
70th percentile: 2.6842267036437986
80th percentile: 6.232848215103152
90th percentile: 13.174687051773073
95th percentile: 16.645606470108028
99th percentile: 19.422342004776
mean time: 5.924666118621826
%s, retrying in %s seconds...
Received healthy response to inference request in 2.474032402038574s
Received healthy response to inference request in 2.4507179260253906s
Received healthy response to inference request in 2.489539623260498s
Received healthy response to inference request in 2.5110201835632324s
Received healthy response to inference request in 2.4580507278442383s
5 requests
0 failed requests
5th percentile: 2.45218448638916
10th percentile: 2.4536510467529298
20th percentile: 2.456584167480469
30th percentile: 2.4612470626831056
40th percentile: 2.4676397323608397
50th percentile: 2.474032402038574
60th percentile: 2.480235290527344
70th percentile: 2.486438179016113
80th percentile: 2.4938357353210447
90th percentile: 2.5024279594421386
95th percentile: 2.5067240715026857
99th percentile: 2.510160961151123
mean time: 2.4766721725463867
Pipeline stage StressChecker completed in 44.53s
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 0.72s
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 0.69s
Shutdown handler de-registered
rirv938-mistral-24b-dpo_77960_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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
clean up pipeline due to error=DeploymentChecksError('None: None')
Shutdown handler de-registered
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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
clean up pipeline due to error=DeploymentChecksError('None: None')
Shutdown handler de-registered
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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
clean up pipeline due to error=DeploymentChecksError("('http://rirv938-mistral-24b-dpo-77960-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')")
Shutdown handler de-registered
rirv938-mistral-24b-dpo_77960_v1 status is now torndown due to DeploymentManager action

ChatRequest

Bot Name

Generation Params

Prompt Formatter

ChatMessage 1

Sender

Message

User Message