developer_uid: rica40325
submission_id: rica40325-my-first-dpo_v4
model_name: rica40325-my-first-dpo_v1
model_group: rica40325/my-first-dpo
status: torndown
timestamp: 2024-08-29T03:45:26+00:00
num_battles: 11482
num_wins: 5668
celo_rating: 1229.21
family_friendly_score: 0.0
submission_type: basic
model_repo: rica40325/my-first-dpo
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: rica40325-my-first-dpo_v1
is_internal_developer: False
language_model: rica40325/my-first-dpo
model_size: 8B
ranking_group: single
us_pacific_date: 2024-08-28
win_ratio: 0.4936422226093015
generation_params: {'temperature': 0.95, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "<|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\nYou: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}:', 'truncate_by_message': False}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name rica40325-my-first-dpo-v4-mkmlizer
Waiting for job on rica40325-my-first-dpo-v4-mkmlizer to finish
Stopping job with name rica40325-my-first-dpo-v4-mkmlizer
%s, retrying in %s seconds...
Starting job with name rica40325-my-first-dpo-v4-mkmlizer
Waiting for job on rica40325-my-first-dpo-v4-mkmlizer to finish
Retrying (%r) after connection broken by '%r': %s
rica40325-my-first-dpo-v4-mkmlizer: Downloaded to shared memory in 27.229s
rica40325-my-first-dpo-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp353_pra8, device:0
rica40325-my-first-dpo-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Retrying (%r) after connection broken by '%r': %s
rica40325-my-first-dpo-v4-mkmlizer: quantized model in 25.188s
rica40325-my-first-dpo-v4-mkmlizer: Processed model rica40325/my-first-dpo in 52.417s
rica40325-my-first-dpo-v4-mkmlizer: creating bucket guanaco-mkml-models
rica40325-my-first-dpo-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rica40325-my-first-dpo-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rica40325-my-first-dpo-v4
rica40325-my-first-dpo-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rica40325-my-first-dpo-v4/config.json
rica40325-my-first-dpo-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rica40325-my-first-dpo-v4/special_tokens_map.json
rica40325-my-first-dpo-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rica40325-my-first-dpo-v4/tokenizer_config.json
rica40325-my-first-dpo-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rica40325-my-first-dpo-v4/tokenizer.json
rica40325-my-first-dpo-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rica40325-my-first-dpo-v4/flywheel_model.0.safetensors
rica40325-my-first-dpo-v4-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:05, 51.28it/s]
Loading 0:   8%|▊         | 22/291 [00:00<00:03, 87.37it/s]
Loading 0:  11%|█▏        | 33/291 [00:00<00:02, 95.85it/s]
Loading 0:  15%|█▍        | 43/291 [00:00<00:03, 82.23it/s]
Loading 0:  18%|█▊        | 52/291 [00:00<00:02, 81.33it/s]
Loading 0:  23%|██▎       | 67/291 [00:00<00:02, 93.09it/s]
Loading 0:  27%|██▋       | 79/291 [00:00<00:02, 90.29it/s]
Loading 0:  31%|███       | 89/291 [00:02<00:07, 25.55it/s]
Loading 0:  33%|███▎      | 97/291 [00:02<00:06, 30.37it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:04, 42.37it/s]
Loading 0:  42%|████▏     | 121/291 [00:02<00:03, 47.44it/s]
Loading 0:  45%|████▍     | 130/291 [00:02<00:03, 52.83it/s]
Loading 0:  49%|████▉     | 142/291 [00:02<00:02, 61.09it/s]
Loading 0:  52%|█████▏    | 152/291 [00:02<00:02, 68.49it/s]
Loading 0:  57%|█████▋    | 166/291 [00:02<00:01, 79.27it/s]
Loading 0:  61%|██████    | 178/291 [00:02<00:01, 82.11it/s]
Loading 0:  65%|██████▍   | 188/291 [00:04<00:03, 26.03it/s]
Loading 0:  67%|██████▋   | 196/291 [00:04<00:03, 30.87it/s]
Loading 0:  71%|███████   | 206/291 [00:04<00:02, 38.74it/s]
Loading 0:  76%|███████▌  | 220/291 [00:04<00:01, 49.99it/s]
Loading 0:  79%|███████▊  | 229/291 [00:04<00:01, 55.54it/s]
Loading 0:  82%|████████▏ | 238/291 [00:04<00:00, 60.09it/s]
Loading 0:  86%|████████▌ | 250/291 [00:04<00:00, 68.22it/s]
Loading 0:  91%|█████████ | 265/291 [00:04<00:00, 78.78it/s]
Loading 0:  95%|█████████▌| 277/291 [00:05<00:00, 81.24it/s]
Loading 0:  99%|█████████▊| 287/291 [00:05<00:00, 49.99it/s]
                                                            

Job rica40325-my-first-dpo-v4-mkmlizer completed after 84.35s with status: succeeded
Stopping job with name rica40325-my-first-dpo-v4-mkmlizer
Pipeline stage MKMLizer completed in 86.76s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.16s
Running pipeline stage ISVCDeployer
Creating inference service rica40325-my-first-dpo-v4
Waiting for inference service rica40325-my-first-dpo-v4 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service rica40325-my-first-dpo-v4 ready after 191.2137188911438s
Pipeline stage ISVCDeployer completed in 191.78s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0684456825256348s
Received healthy response to inference request in 1.7423887252807617s
Received healthy response to inference request in 1.9277853965759277s
Received healthy response to inference request in 1.5102870464324951s
Received healthy response to inference request in 1.8673958778381348s
5 requests
0 failed requests
5th percentile: 1.5567073822021484
10th percentile: 1.6031277179718018
20th percentile: 1.6959683895111084
30th percentile: 1.7673901557922362
40th percentile: 1.8173930168151855
50th percentile: 1.8673958778381348
60th percentile: 1.891551685333252
70th percentile: 1.915707492828369
80th percentile: 1.9559174537658692
90th percentile: 2.0121815681457518
95th percentile: 2.0403136253356933
99th percentile: 2.0628192710876463
mean time: 1.8232605457305908
Pipeline stage StressChecker completed in 10.00s
rica40325-my-first-dpo_v4 status is now deployed due to DeploymentManager action
rica40325-my-first-dpo_v4 status is now inactive due to auto deactivation removed underperforming models
rica40325-my-first-dpo_v4 status is now torndown due to DeploymentManager action
rica40325-my-first-dpo_v4 status is now torndown due to DeploymentManager action