cycy233-l3-bdpo-v5-c1

developer_uid: shiroe40
submission_id: cycy233-l3-bdpo-v5-c1_v4
model_name: auto
model_group: cycy233/L3-bdpo-v5-c1
status: torndown
timestamp: 2024-07-15T03:28:36+00:00
num_battles: 62147
num_wins: 26821
celo_rating: 1145.35
family_friendly_score: 0.0
submission_type: basic
model_repo: cycy233/L3-bdpo-v5-c1
model_architecture: LlamaForCausalLM
reward_repo: Jellywibble/gpt2_xl_pairwise_89m_step_347634
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: auto
is_internal_developer: False
language_model: cycy233/L3-bdpo-v5-c1
model_size: 8B
ranking_group: single
us_pacific_date: 2024-07-14
win_ratio: 0.43157352728208925
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, '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': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-l3-bdpo-v5-c1-v4-mkmlizer
Waiting for job on cycy233-l3-bdpo-v5-c1-v4-mkmlizer to finish
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: ║     _____            __           __                                ║
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: ║       /___/                                                         ║
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: ║                                                                     ║
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: ║  Version: 0.9.5.post2                                               ║
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: ║                                                                     ║
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: ║  belonging to:                                                      ║
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: ║                                                                     ║
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: ║                                                                     ║
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: Downloaded to shared memory in 31.287s
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.10.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.10.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.10.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.10.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.10.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.10.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.11.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.11.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.11.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.11.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.11.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.11.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.12.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.12.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.12.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.12.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.12.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.12.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.13.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.13.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.13.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.13.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.13.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.13.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.14.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.14.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.14.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.14.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.14.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.14.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.15.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.15.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.15.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.15.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.15.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.15.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.16.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.16.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.16.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.16.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.16.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.16.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.17.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.17.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.17.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.17.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.17.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.17.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.18.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.18.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.18.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.18.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.18.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.18.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.19.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.19.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.19.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.19.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.19.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.19.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.20.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.20.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.9.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.9.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.9.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.9.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.9.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.9.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.20.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.20.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.20.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.20.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.21.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.21.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.21.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.21.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.21.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.21.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.22.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.22.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.22.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.22.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.22.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.22.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.23.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.23.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.23.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.23.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.23.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.23.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.24.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.24.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.24.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
                                                  

Loading 0:   0%|          | 1/291 [00:00<00:00, 1424.70it/s]
                                                            

Loading 0:   1%|          | 2/291 [00:00<00:03, 86.55it/s]
                                                          

Loading 0:   1%|▏         | 4/291 [00:00<00:04, 62.57it/s]
                                                          

Loading 0:   2%|▏         | 5/291 [00:00<00:03, 77.82it/s]
                                                          

Loading 0:   2%|▏         | 7/291 [00:00<00:02, 98.31it/s]
                                                          

Loading 0:   3%|▎         | 9/291 [00:00<00:02, 115.10it/s]
                                                           

Loading 0:   3%|▎         | 10/291 [00:00<00:02, 127.49it/s]
                                                            

Loading 0:   4%|▍         | 11/291 [00:00<00:02, 114.15it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:02, 113.15it/s]
                                                            

Loading 0:   4%|▍         | 13/291 [00:00<00:02, 113.15it/s]
                                                            

Loading 0:   5%|▍         | 14/291 [00:00<00:02, 113.15it/s]
                                                            

Loading 0:   5%|▌         | 16/291 [00:00<00:02, 113.15it/s]
                                                            

Loading 0:   6%|▌         | 18/291 [00:00<00:02, 113.15it/s]
                                                            

Loading 0:   7%|▋         | 19/291 [00:00<00:02, 113.15it/s]
                                                            

Loading 0:   7%|▋         | 20/291 [00:00<00:02, 113.15it/s]
                                                            

Loading 0:   8%|▊         | 22/291 [00:00<00:02, 113.15it/s]
                                                            

Loading 0:   8%|▊         | 23/291 [00:00<00:02, 113.15it/s]
                                                            

Loading 0:   9%|▊         | 25/291 [00:00<00:02, 113.15it/s]
Loading 0:   9%|▉         | 27/291 [00:00<00:02, 127.64it/s]
                                                            

Loading 0:   9%|▉         | 27/291 [00:00<00:02, 127.64it/s]
                                                            

Loading 0:  10%|▉         | 28/291 [00:00<00:02, 127.64it/s]
                                                            

Loading 0:  10%|▉         | 29/291 [00:00<00:02, 127.64it/s]
                                                            

Loading 0:  11%|█         | 31/291 [00:00<00:02, 127.64it/s]
                                                            

Loading 0:  11%|█         | 32/291 [00:00<00:02, 127.64it/s]
                                                            

Loading 0:  12%|█▏        | 34/291 [00:00<00:02, 127.64it/s]
                                                            

Loading 0:  12%|█▏        | 36/291 [00:00<00:01, 127.64it/s]
                                                            

Loading 0:  13%|█▎        | 37/291 [00:00<00:01, 127.64it/s]
                                                            

Loading 0:  13%|█▎        | 38/291 [00:00<00:01, 127.64it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:02, 124.92it/s]
                                                            

Loading 0:  14%|█▎        | 40/291 [00:00<00:02, 124.92it/s]
                                                            

Loading 0:  14%|█▍        | 41/291 [00:00<00:02, 124.92it/s]
                                                            

Loading 0:  15%|█▍        | 43/291 [00:00<00:01, 124.92it/s]
                                                            

Loading 0:  15%|█▌        | 45/291 [00:00<00:01, 124.92it/s]
                                                            

Loading 0:  16%|█▌        | 46/291 [00:00<00:01, 124.92it/s]
                                                            

Loading 0:  16%|█▌        | 47/291 [00:00<00:01, 124.92it/s]
                                                            

Loading 0:  17%|█▋        | 49/291 [00:00<00:01, 124.92it/s]
                                                            

Loading 0:  17%|█▋        | 50/291 [00:00<00:01, 124.92it/s]
                                                            

Loading 0:  18%|█▊        | 52/291 [00:00<00:01, 124.92it/s]
                                                            

Loading 0:  19%|█▊        | 54/291 [00:00<00:01, 124.92it/s]
Loading 0:  19%|█▉        | 55/291 [00:00<00:01, 133.85it/s]
                                                            

Loading 0:  19%|█▉        | 55/291 [00:00<00:01, 133.85it/s]
                                                            

Loading 0:  19%|█▉        | 56/291 [00:00<00:01, 133.85it/s]
                                                            

Loading 0:  20%|█▉        | 58/291 [00:00<00:01, 133.85it/s]
                                                            

Loading 0:  20%|██        | 59/291 [00:00<00:01, 133.85it/s]
                                                            

Loading 0:  21%|██        | 61/291 [00:00<00:01, 133.85it/s]
                                                            

Loading 0:  22%|██▏       | 63/291 [00:00<00:01, 133.85it/s]
                                                            

Loading 0:  22%|██▏       | 64/291 [00:00<00:01, 133.85it/s]
                                                            

Loading 0:  22%|██▏       | 65/291 [00:00<00:01, 133.85it/s]
                                                            

Loading 0:  23%|██▎       | 67/291 [00:00<00:01, 133.85it/s]
                                                            

Loading 0:  23%|██▎       | 68/291 [00:00<00:01, 133.85it/s]
Loading 0:  24%|██▎       | 69/291 [00:00<00:01, 125.73it/s]
                                                            

Loading 0:  24%|██▍       | 70/291 [00:00<00:01, 125.73it/s]
                                                            

Loading 0:  25%|██▍       | 72/291 [00:00<00:01, 125.73it/s]
                                                            

Loading 0:  25%|██▌       | 73/291 [00:00<00:01, 125.73it/s]
                                                            

Loading 0:  25%|██▌       | 74/291 [00:00<00:01, 125.73it/s]
                                                            

Loading 0:  26%|██▌       | 76/291 [00:00<00:01, 125.73it/s]
                                                            

Loading 0:  26%|██▋       | 77/291 [00:00<00:01, 125.73it/s]
                                                            

Loading 0:  27%|██▋       | 79/291 [00:00<00:01, 125.73it/s]
                                                            

Loading 0:  28%|██▊       | 81/291 [00:00<00:01, 125.73it/s]
                                                            

Loading 0:  28%|██▊       | 82/291 [00:00<00:01, 125.73it/s]
Loading 0:  29%|██▊       | 83/291 [00:00<00:03, 68.86it/s] 
                                                           

Loading 0:  29%|██▊       | 83/291 [00:00<00:03, 68.86it/s]
                                                           

Loading 0:  29%|██▉       | 85/291 [00:00<00:02, 68.86it/s]
                                                           

Loading 0:  30%|██▉       | 86/291 [00:00<00:02, 68.86it/s]
                                                           

Loading 0:  30%|███       | 88/291 [00:00<00:02, 68.86it/s]
                                                           

Loading 0:  31%|███       | 90/291 [00:00<00:02, 68.86it/s]
                                                           

Loading 0:  31%|███▏      | 91/291 [00:00<00:02, 68.86it/s]
                                                           

Loading 0:  32%|███▏      | 92/291 [00:01<00:02, 68.86it/s]
Loading 0:  32%|███▏      | 94/291 [00:01<00:02, 76.02it/s]
                                                           

Loading 0:  32%|███▏      | 94/291 [00:01<00:02, 76.02it/s]
                                                           

Loading 0:  33%|███▎      | 95/291 [00:01<00:02, 76.02it/s]
                                                           

Loading 0:  33%|███▎      | 97/291 [00:01<00:02, 76.02it/s]
                                                           

Loading 0:  34%|███▍      | 99/291 [00:01<00:02, 76.02it/s]
                                                           

Loading 0:  34%|███▍      | 100/291 [00:01<00:02, 76.02it/s]
                                                            

Loading 0:  35%|███▍      | 101/291 [00:01<00:02, 76.02it/s]
                                                            

Loading 0:  35%|███▌      | 103/291 [00:01<00:02, 76.02it/s]
                                                            

Loading 0:  36%|███▌      | 104/291 [00:01<00:02, 76.02it/s]
                                                            

Loading 0:  36%|███▋      | 106/291 [00:01<00:02, 76.02it/s]
                                                            

Loading 0:  37%|███▋      | 108/291 [00:01<00:02, 76.02it/s]
Loading 0:  37%|███▋      | 109/291 [00:01<00:01, 91.58it/s]
                                                            

Loading 0:  37%|███▋      | 109/291 [00:01<00:01, 91.58it/s]
                                                            

Loading 0:  38%|███▊      | 110/291 [00:01<00:01, 91.58it/s]
                                                            

Loading 0:  38%|███▊      | 112/291 [00:01<00:01, 91.58it/s]
                                                            

Loading 0:  39%|███▉      | 113/291 [00:01<00:01, 91.58it/s]
                                                            

Loading 0:  40%|███▉      | 115/291 [00:01<00:01, 91.58it/s]
                                                            

Loading 0:  40%|████      | 117/291 [00:01<00:01, 91.58it/s]
                                                            

Loading 0:  41%|████      | 118/291 [00:01<00:01, 91.58it/s]
                                                            

Loading 0:  41%|████      | 119/291 [00:01<00:01, 91.58it/s]
Loading 0:  42%|████▏     | 121/291 [00:01<00:01, 97.67it/s]
                                                            

Loading 0:  42%|████▏     | 121/291 [00:01<00:01, 97.67it/s]
                                                            

Loading 0:  42%|████▏     | 122/291 [00:01<00:01, 97.67it/s]
                                                            

Loading 0:  43%|████▎     | 124/291 [00:01<00:01, 97.67it/s]
                                                            

Loading 0:  43%|████▎     | 126/291 [00:01<00:01, 97.67it/s]
                                                            

Loading 0:  44%|████▎     | 127/291 [00:01<00:01, 97.67it/s]
                                                            

Loading 0:  44%|████▍     | 128/291 [00:01<00:01, 97.67it/s]
                                                            

Loading 0:  45%|████▍     | 130/291 [00:01<00:01, 97.67it/s]
                                                            

Loading 0:  45%|████▌     | 131/291 [00:01<00:01, 97.67it/s]
                                                            

Loading 0:  46%|████▌     | 133/291 [00:01<00:01, 97.67it/s]
                                                            

Loading 0:  46%|████▋     | 135/291 [00:01<00:01, 97.67it/s]
Loading 0:  47%|████▋     | 136/291 [00:01<00:01, 110.67it/s]
                                                             

Loading 0:  47%|████▋     | 136/291 [00:01<00:01, 110.67it/s]
                                                             

Loading 0:  47%|████▋     | 137/291 [00:01<00:01, 110.67it/s]
                                                             

Loading 0:  48%|████▊     | 139/291 [00:01<00:01, 110.67it/s]
                                                             

Loading 0:  48%|████▊     | 140/291 [00:01<00:01, 110.67it/s]
                                                             

Loading 0:  49%|████▉     | 142/291 [00:01<00:01, 110.67it/s]
                                                             

Loading 0:  49%|████▉     | 144/291 [00:01<00:01, 110.67it/s]
                                                             

Loading 0:  50%|████▉     | 145/291 [00:01<00:01, 110.67it/s]
                                                             

Loading 0:  50%|█████     | 146/291 [00:01<00:01, 110.67it/s]
                                                             

Loading 0:  51%|█████     | 148/291 [00:01<00:01, 110.67it/s]
Loading 0:  51%|█████     | 149/291 [00:01<00:01, 110.05it/s]
                                                             

Loading 0:  51%|█████     | 149/291 [00:01<00:01, 110.05it/s]
                                                             

Loading 0:  52%|█████▏    | 151/291 [00:01<00:01, 110.05it/s]
                                                             

Loading 0:  53%|█████▎    | 153/291 [00:01<00:01, 110.05it/s]
                                                             

Loading 0:  53%|█████▎    | 154/291 [00:01<00:01, 110.05it/s]
                                                             

Loading 0:  53%|█████▎    | 155/291 [00:01<00:01, 110.05it/s]
                                                             

Loading 0:  54%|█████▍    | 157/291 [00:01<00:01, 110.05it/s]
                                                             

Loading 0:  54%|█████▍    | 158/291 [00:01<00:01, 110.05it/s]
                                                             

Loading 0:  55%|█████▍    | 160/291 [00:01<00:01, 110.05it/s]
                                                             

Loading 0:  56%|█████▌    | 162/291 [00:01<00:01, 110.05it/s]
                                                             

Loading 0:  56%|█████▌    | 163/291 [00:01<00:01, 110.05it/s]
                                                             

Loading 0:  56%|█████▋    | 164/291 [00:01<00:01, 110.05it/s]
Loading 0:  57%|█████▋    | 166/291 [00:01<00:01, 120.69it/s]
                                                             

Loading 0:  57%|█████▋    | 166/291 [00:01<00:01, 120.69it/s]
                                                             

Loading 0:  57%|█████▋    | 167/291 [00:01<00:01, 120.69it/s]
                                                             

Loading 0:  58%|█████▊    | 169/291 [00:01<00:01, 120.69it/s]
                                                             

Loading 0:  59%|█████▉    | 171/291 [00:01<00:00, 120.69it/s]
                                                             

Loading 0:  60%|█████▉    | 174/291 [00:01<00:00, 120.69it/s]
                                                             

Loading 0:  60%|██████    | 176/291 [00:01<00:00, 120.69it/s]
                                                             

Loading 0:  61%|██████    | 177/291 [00:01<00:00, 120.69it/s]
                                                             

Loading 0:  61%|██████    | 178/291 [00:01<00:00, 120.69it/s]
                                                             

Loading 0:  62%|██████▏   | 180/291 [00:01<00:00, 120.69it/s]
Loading 0:  62%|██████▏   | 181/291 [0model.layers.24.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.24.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.24.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.25.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.25.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.25.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.25.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.25.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.25.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.26.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.26.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.26.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.26.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.26.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.26.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.27.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.27.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.27.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.27.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.27.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.27.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.28.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.28.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.28.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.28.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.28.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.28.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.29.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.29.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.29.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.29.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.29.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.29.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.30.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.30.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.30.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.30.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.30.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.30.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.31.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.31.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.31.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: lm_head.weight torch.Size([139542528])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.31.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.31.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.31.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.norm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: 0:01<00:00, 123.12it/s]
                                                             

Loading 0:  62%|██████▏   | 181/291 [00:01<00:00, 123.12it/s]
                                                             

Loading 0:  63%|██████▎   | 183/291 [00:01<00:00, 123.12it/s]
                                                             

Loading 0:  64%|██████▎   | 185/291 [00:01<00:00, 123.12it/s]
                                                             

Loading 0:  64%|██████▍   | 186/291 [00:01<00:00, 123.12it/s]
                                                             

Loading 0:  64%|██████▍   | 187/291 [00:01<00:00, 123.12it/s]
                                                             

Loading 0:  65%|██████▍   | 188/291 [00:02<00:00, 123.12it/s]
                                                             

Loading 0:  65%|██████▍   | 189/291 [00:02<00:00, 123.12it/s]
                                                             

Loading 0:  65%|██████▌   | 190/291 [00:02<00:00, 123.12it/s]
                                                             

Loading 0:  66%|██████▌   | 191/291 [00:02<00:00, 123.12it/s]
                                                             

Loading 0:  66%|██████▋   | 193/291 [00:02<00:00, 123.12it/s]
Loading 0:  67%|██████▋   | 194/291 [00:02<00:01, 71.99it/s] 
                                                            

Loading 0:  67%|██████▋   | 194/291 [00:02<00:01, 71.99it/s]
                                                            

Loading 0:  67%|██████▋   | 196/291 [00:02<00:01, 71.99it/s]
                                                            

Loading 0:  68%|██████▊   | 198/291 [00:02<00:01, 71.99it/s]
                                                            

Loading 0:  68%|██████▊   | 199/291 [00:02<00:01, 71.99it/s]
                                                            

Loading 0:  69%|██████▊   | 200/291 [00:02<00:01, 71.99it/s]
                                                            

Loading 0:  69%|██████▉   | 202/291 [00:02<00:01, 71.99it/s]
                                                            

Loading 0:  70%|██████▉   | 203/291 [00:02<00:01, 71.99it/s]
                                                            

Loading 0:  70%|███████   | 205/291 [00:02<00:01, 71.99it/s]
                                                            

Loading 0:  71%|███████   | 207/291 [00:02<00:01, 71.99it/s]
                                                            

Loading 0:  71%|███████▏  | 208/291 [00:02<00:01, 71.99it/s]
                                                            

Loading 0:  72%|███████▏  | 209/291 [00:02<00:01, 71.99it/s]
Loading 0:  73%|███████▎  | 211/291 [00:02<00:00, 87.51it/s]
                                                            

Loading 0:  73%|███████▎  | 211/291 [00:02<00:00, 87.51it/s]
                                                            

Loading 0:  73%|███████▎  | 212/291 [00:02<00:00, 87.51it/s]
                                                            

Loading 0:  74%|███████▎  | 214/291 [00:02<00:00, 87.51it/s]
                                                            

Loading 0:  74%|███████▍  | 216/291 [00:02<00:00, 87.51it/s]
                                                            

Loading 0:  75%|███████▍  | 217/291 [00:02<00:00, 87.51it/s]
                                                            

Loading 0:  75%|███████▍  | 218/291 [00:02<00:00, 87.51it/s]
                                                            

Loading 0:  76%|███████▌  | 220/291 [00:02<00:00, 87.51it/s]
                                                            

Loading 0:  76%|███████▌  | 221/291 [00:02<00:00, 87.51it/s]
                                                            

Loading 0:  77%|███████▋  | 223/291 [00:02<00:00, 87.51it/s]
                                                            

Loading 0:  77%|███████▋  | 225/291 [00:02<00:00, 87.51it/s]
                                                            

Loading 0:  78%|███████▊  | 226/291 [00:02<00:00, 87.51it/s]
                                                            

Loading 0:  78%|███████▊  | 227/291 [00:02<00:00, 87.51it/s]
Loading 0:  78%|███████▊  | 228/291 [00:02<00:00, 101.14it/s]
                                                             

Loading 0:  79%|███████▊  | 229/291 [00:02<00:00, 101.14it/s]
                                                             

Loading 0:  79%|███████▉  | 230/291 [00:02<00:00, 101.14it/s]
                                                             

Loading 0:  80%|███████▉  | 232/291 [00:02<00:00, 101.14it/s]
                                                             

Loading 0:  80%|████████  | 234/291 [00:02<00:00, 101.14it/s]
                                                             

Loading 0:  81%|████████  | 235/291 [00:02<00:00, 101.14it/s]
                                                             

Loading 0:  81%|████████  | 236/291 [00:02<00:00, 101.14it/s]
                                                             

Loading 0:  82%|████████▏ | 238/291 [00:02<00:00, 101.14it/s]
                                                             

Loading 0:  82%|████████▏ | 239/291 [00:02<00:00, 101.14it/s]
Loading 0:  83%|████████▎ | 241/291 [00:02<00:00, 106.69it/s]
                                                             

Loading 0:  83%|████████▎ | 241/291 [00:02<00:00, 106.69it/s]
                                                             

Loading 0:  84%|████████▎ | 243/291 [00:02<00:00, 106.69it/s]
                                                             

Loading 0:  84%|████████▍ | 244/291 [00:02<00:00, 106.69it/s]
                                                             

Loading 0:  84%|████████▍ | 245/291 [00:02<00:00, 106.69it/s]
                                                             

Loading 0:  85%|████████▍ | 247/291 [00:02<00:00, 106.69it/s]
                                                             

Loading 0:  85%|████████▌ | 248/291 [00:02<00:00, 106.69it/s]
                                                             

Loading 0:  86%|████████▌ | 250/291 [00:02<00:00, 106.69it/s]
                                                             

Loading 0:  87%|████████▋ | 252/291 [00:02<00:00, 106.69it/s]
                                                             

Loading 0:  87%|████████▋ | 253/291 [00:02<00:00, 106.69it/s]
                                                             

Loading 0:  87%|████████▋ | 254/291 [00:02<00:00, 106.69it/s]
Loading 0:  88%|████████▊ | 256/291 [00:02<00:00, 114.40it/s]
                                                             

Loading 0:  88%|████████▊ | 256/291 [00:02<00:00, 114.40it/s]
                                                             

Loading 0:  88%|████████▊ | 257/291 [00:02<00:00, 114.40it/s]
                                                             

Loading 0:  89%|████████▉ | 259/291 [00:02<00:00, 114.40it/s]
                                                             

Loading 0:  90%|████████▉ | 261/291 [00:02<00:00, 114.40it/s]
                                                             

Loading 0:  90%|█████████ | 262/291 [00:02<00:00, 114.40it/s]
                                                             

Loading 0:  90%|█████████ | 263/291 [00:02<00:00, 114.40it/s]
                                                             

Loading 0:  91%|█████████ | 265/291 [00:02<00:00, 114.40it/s]
                                                             

Loading 0:  91%|█████████▏| 266/291 [00:02<00:00, 114.40it/s]
                                                             

Loading 0:  92%|█████████▏| 268/291 [00:02<00:00, 114.40it/s]
                                                             

Loading 0:  93%|█████████▎| 270/291 [00:02<00:00, 114.40it/s]
                                                             

Loading 0:  93%|█████████▎| 271/291 [00:02<00:00, 114.40it/s]
                                                             

Loading 0:  93%|█████████▎| 272/291 [00:02<00:00, 114.40it/s]
Loading 0:  94%|█████████▍| 273/291 [00:02<00:00, 124.52it/s]
                                                             

Loading 0:  94%|█████████▍| 274/291 [00:02<00:00, 124.52it/s]
                                                             

Loading 0:  95%|█████████▍| 275/291 [00:02<00:00, 124.52it/s]
                                                             

Loading 0:  95%|█████████▌| 277/291 [00:02<00:00, 124.52it/s]
                                                             

Loading 0:  96%|█████████▌| 279/291 [00:02<00:00, 124.52it/s]
                                                             

Loading 0:  97%|█████████▋| 281/291 [00:02<00:00, 124.52it/s]
                                                             

Loading 0:  97%|█████████▋| 283/291 [00:02<00:00, 124.52it/s]
                                                             

Loading 0:  98%|█████████▊| 285/291 [00:02<00:00, 124.52it/s]
                                                             

Loading 0:  98%|█████████▊| 286/291 [00:08<00:00, 124.52it/s]
Loading 0:  99%|█████████▊| 287/291 [00:08<00:00,  8.37it/s] 
                                                            

Loading 0:  99%|█████████▊| 287/291 [00:08<00:00,  8.37it/s]
                                                            

Loading 0:  99%|█████████▉| 288/291 [00:08<00:00,  8.37it/s]
                                                            

Loading 0:  99%|█████████▉| 289/291 [00:08<00:00,  8.37it/s]
                                                            

Loading 0: 100%|█████████▉| 290/291 [00:08<00:00,  8.37it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: quantized model in 24.583s
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: Processed model cycy233/L3-bdpo-v5-c1 in 55.870s
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-bdpo-v5-c1-v4
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-bdpo-v5-c1-v4/config.json
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-bdpo-v5-c1-v4/special_tokens_map.json
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-bdpo-v5-c1-v4/tokenizer_config.json
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-bdpo-v5-c1-v4/tokenizer.json
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-bdpo-v5-c1-v4/flywheel_model.0.safetensors
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:950: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:   warnings.warn(
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:778: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:   warnings.warn(
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: Traceback (most recent call last):
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/urllib3/connectionpool.py", line 536, in _make_request
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:     response = conn.getresponse()
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/urllib3/connection.py", line 461, in getresponse
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:     httplib_response = super().getresponse()
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:   File "/opt/conda/lib/python3.10/http/client.py", line 1375, in getresponse
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:     response.begin()
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:   File "/opt/conda/lib/python3.10/http/client.py", line 318, in begin
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:     version, status, reason = self._read_status()
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:   File "/opt/conda/lib/python3.10/http/client.py", line 279, in _read_status
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:     line = str(self.fp.readline(_MAXLINE + 1), "iso-8859-1")
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:   File "/opt/conda/lib/python3.10/socket.py", line 705, in readinto
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:     return self._sock.recv_into(b)
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:   File "/opt/conda/lib/python3.10/ssl.py", line 1307, in recv_into
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:     return self.read(nbytes, buffer)
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:   File "/opt/conda/lib/python3.10/ssl.py", line 1163, in read
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:     return self._sslobj.read(len, buffer)
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: TimeoutError: The read operation timed out
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: The above exception was the direct cause of the following exception:
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: Traceback (most recent call last):
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/requests/adapters.py", line 667, in send
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:     resp = conn.urlopen(
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/urllib3/connectionpool.py", line 844, in urlopen
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:     retries = retries.increment(
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/urllib3/util/retry.py", line 470, in increment
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:     raise reraise(type(error), error, _stacktrace)
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/urllib3/util/util.py", line 39, in reraise
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:     raise value
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/urllib3/connectionpool.py", line 790, in urlopen
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:     response = self._make_request(
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/urllib3/connectionpool.py", line 538, in _make_request
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:     self._raise_timeout(err=e, url=url, timeout_value=read_timeout)
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/urllib3/connectionpool.py", line 370, in _raise_timeout
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:     raise ReadTimeoutError(
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: urllib3.exceptions.ReadTimeoutError: HTTPSConnectionPool(host='huggingface.co', port=443): Read timed out. (read timeout=10)
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: During handling of the above exception, another exception occurred:
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: Traceback (most recent call last):
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:   File "/code/uploading/reward.py", line 66, in <module>
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:     cli()
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1157, in __call__
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:     return self.main(*args, **kwargs)
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1078, in main
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:     rv = self.invoke(ctx)
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1688, in invoke
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:     return _process_result(sub_ctx.command.invoke(sub_ctx))
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1434, in invoke
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:     return ctx.invoke(self.callback, **ctx.params)
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 783, in invoke
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:     return __callback(*args, **kwargs)
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:   File "/code/uploading/reward.py", line 29, in tensorize_reward_model
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:     model, config, tokenizer = download_from_huggingface(repo_id, revision, hf_auth_token)
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:   File "/code/uploading/reward.py", line 38, in download_from_huggingface
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:     tokenizer = AutoTokenizer.from_pretrained(
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py", line 889, in from_pretrained
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:     return tokenizer_class.from_pretrained(pretrained_model_name_or_path, *inputs, **kwargs)
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 2119, in from_pretrained
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:     resolved_vocab_files[file_id] = cached_file(
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/transformers/utils/hub.py", line 402, in cached_file
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:     resolved_file = hf_hub_download(
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:     return fn(*args, **kwargs)
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1221, in hf_hub_download
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:     return _hf_hub_download_to_cache_dir(
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1367, in _hf_hub_download_to_cache_dir
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:     _download_to_tmp_and_move(
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1884, in _download_to_tmp_and_move
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:     http_get(
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 459, in http_get
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:     r = _request_wrapper(
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 395, in _request_wrapper
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:     response = get_session().request(method=method, url=url, **params)
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/requests/sessions.py", line 589, in request
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:     resp = self.send(prep, **send_kwargs)
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/requests/sessions.py", line 703, in send
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:     r = adapter.send(request, **kwargs)
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 66, in send
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:     return super().send(request, *args, **kwargs)
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/requests/adapters.py", line 713, in send
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:     raise ReadTimeout(e, request=request)
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: requests.exceptions.ReadTimeout: (ReadTimeoutError("HTTPSConnectionPool(host='huggingface.co', port=443): Read timed out. (read timeout=10)"), '(Request ID: 0457cdb9-5997-4f2a-b4b9-593b7acfaa9a)')
Job cycy233-l3-bdpo-v5-c1-v4-mkmlizer completed after 95.37s with status: failed
Stopping job with name cycy233-l3-bdpo-v5-c1-v4-mkmlizer
%s, retrying in %s seconds...
Starting job with name cycy233-l3-bdpo-v5-c1-v4-mkmlizer
Waiting for job on cycy233-l3-bdpo-v5-c1-v4-mkmlizer to finish
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: ║     _____            __           __                                ║
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: ║       /___/                                                         ║
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: ║                                                                     ║
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: ║  Version: 0.9.5.post2                                               ║
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: ║                                                                     ║
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: ║  belonging to:                                                      ║
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: ║                                                                     ║
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: ║                                                                     ║
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: Downloaded to shared memory in 28.502s
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.embed_tokens.weight torch.Size([139542528])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.0.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.0.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.0.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.0.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.0.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.0.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.1.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.1.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.1.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.1.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.1.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.1.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.2.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.2.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.2.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.2.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.2.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.2.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.3.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.3.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.3.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.3.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.3.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.3.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.4.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.4.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.4.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.4.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.4.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.4.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.5.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.5.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.5.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.5.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.5.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.5.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.6.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.6.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.6.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.6.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.6.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.6.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.7.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.7.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.7.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.7.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.7.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.7.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.8.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.8.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.8.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.8.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.8.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.8.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.10.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.10.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.10.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.10.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.10.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.10.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.11.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.11.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.11.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.11.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.11.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.11.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.12.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.12.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.12.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.12.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.12.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.12.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.13.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.13.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.13.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.13.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.13.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.13.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.14.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.14.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.14.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.14.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.14.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.14.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.15.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.15.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.15.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.15.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.15.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.15.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.16.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.16.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.16.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.16.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.16.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.16.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.17.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.17.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.17.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.17.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.17.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.17.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.18.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.18.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.18.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.18.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.18.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.18.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.19.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.19.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.19.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.19.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.19.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.19.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.20.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.20.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.9.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.9.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.9.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.9.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.9.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.9.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.20.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.20.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.20.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.20.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.21.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.21.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.21.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.21.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.21.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.21.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.22.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.22.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.22.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.22.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.22.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.22.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.23.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.23.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.23.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.23.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.23.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.23.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.24.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.24.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.24.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.24.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
                                                  

Loading 0:   0%|          | 1/291 [00:00<00:00, 1240.18it/s]
                                                            

Loading 0:   1%|          | 2/291 [00:00<00:03, 87.74it/s]
                                                          

Loading 0:   1%|▏         | 4/291 [00:00<00:04, 64.35it/s]
                                                          

Loading 0:   2%|▏         | 5/291 [00:00<00:03, 79.99it/s]
                                                          

Loading 0:   2%|▏         | 7/291 [00:00<00:02, 101.28it/s]
                                                           

Loading 0:   3%|▎         | 9/291 [00:00<00:02, 118.87it/s]
                                                           

Loading 0:   3%|▎         | 10/291 [00:00<00:02, 131.65it/s]
                                                            

Loading 0:   4%|▍         | 11/291 [00:00<00:02, 118.40it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:02, 117.44it/s]
                                                            

Loading 0:   4%|▍         | 13/291 [00:00<00:02, 117.44it/s]
                                                            

Loading 0:   5%|▍         | 14/291 [00:00<00:02, 117.44it/s]
                                                            

Loading 0:   5%|▌         | 16/291 [00:00<00:02, 117.44it/s]
                                                            

Loading 0:   6%|▌         | 18/291 [00:00<00:02, 117.44it/s]
                                                            

Loading 0:   7%|▋         | 19/291 [00:00<00:02, 117.44it/s]
                                                            

Loading 0:   7%|▋         | 20/291 [00:00<00:02, 117.44it/s]
                                                            

Loading 0:   8%|▊         | 22/291 [00:00<00:02, 117.44it/s]
                                                            

Loading 0:   8%|▊         | 23/291 [00:00<00:02, 117.44it/s]
                                                            

Loading 0:   9%|▊         | 25/291 [00:00<00:02, 117.44it/s]
                                                            

Loading 0:   9%|▉         | 27/291 [00:00<00:02, 117.44it/s]
Loading 0:  10%|▉         | 28/291 [00:00<00:01, 135.47it/s]
                                                            

Loading 0:  10%|▉         | 28/291 [00:00<00:01, 135.47it/s]
                                                            

Loading 0:  10%|▉         | 29/291 [00:00<00:01, 135.47it/s]
                                                            

Loading 0:  11%|█         | 31/291 [00:00<00:01, 135.47it/s]
                                                            

Loading 0:  11%|█         | 32/291 [00:00<00:01, 135.47it/s]
                                                            

Loading 0:  12%|█▏        | 34/291 [00:00<00:01, 135.47it/s]
                                                            

Loading 0:  12%|█▏        | 36/291 [00:00<00:01, 135.47it/s]
                                                            

Loading 0:  13%|█▎        | 37/291 [00:00<00:01, 135.47it/s]
                                                            

Loading 0:  13%|█▎        | 38/291 [00:00<00:01, 135.47it/s]
                                                            

Loading 0:  14%|█▎        | 40/291 [00:00<00:01, 135.47it/s]
                                                            

Loading 0:  14%|█▍        | 41/291 [00:00<00:01, 135.47it/s]
Loading 0:  14%|█▍        | 42/291 [00:00<00:01, 124.86it/s]
                                                            

Loading 0:  15%|█▍        | 43/291 [00:00<00:01, 124.86it/s]
                                                            

Loading 0:  15%|█▌        | 45/291 [00:00<00:01, 124.86it/s]
                                                            

Loading 0:  16%|█▌        | 46/291 [00:00<00:01, 124.86it/s]
                                                            

Loading 0:  16%|█▌        | 47/291 [00:00<00:01, 124.86it/s]
                                                            

Loading 0:  17%|█▋        | 49/291 [00:00<00:01, 124.86it/s]
                                                            

Loading 0:  17%|█▋        | 50/291 [00:00<00:01, 124.86it/s]
                                                            

Loading 0:  18%|█▊        | 52/291 [00:00<00:01, 124.86it/s]
                                                            

Loading 0:  19%|█▊        | 54/291 [00:00<00:01, 124.86it/s]
                                                            

Loading 0:  19%|█▉        | 55/291 [00:00<00:01, 124.86it/s]
                                                            

Loading 0:  19%|█▉        | 56/291 [00:00<00:01, 124.86it/s]
Loading 0:  20%|█▉        | 58/291 [00:00<00:01, 129.79it/s]
                                                            

Loading 0:  20%|█▉        | 58/291 [00:00<00:01, 129.79it/s]
                                                            

Loading 0:  20%|██        | 59/291 [00:00<00:01, 129.79it/s]
                                                            

Loading 0:  21%|██        | 61/291 [00:00<00:01, 129.79it/s]
                                                            

Loading 0:  22%|██▏       | 63/291 [00:00<00:01, 129.79it/s]
                                                            

Loading 0:  22%|██▏       | 64/291 [00:00<00:01, 129.79it/s]
                                                            

Loading 0:  22%|██▏       | 65/291 [00:00<00:01, 129.79it/s]
                                                            

Loading 0:  23%|██▎       | 67/291 [00:00<00:01, 129.79it/s]
                                                            

Loading 0:  23%|██▎       | 68/291 [00:00<00:01, 129.79it/s]
                                                            

Loading 0:  24%|██▍       | 70/291 [00:00<00:01, 129.79it/s]
                                                            

Loading 0:  25%|██▍       | 72/291 [00:00<00:01, 129.79it/s]
                                                            

Loading 0:  25%|██▌       | 73/291 [00:00<00:01, 129.79it/s]
Loading 0:  25%|██▌       | 74/291 [00:00<00:01, 139.76it/s]
                                                            

Loading 0:  25%|██▌       | 74/291 [00:00<00:01, 139.76it/s]
                                                            

Loading 0:  26%|██▌       | 76/291 [00:00<00:01, 139.76it/s]
                                                            

Loading 0:  26%|██▋       | 77/291 [00:00<00:01, 139.76it/s]
                                                            

Loading 0:  27%|██▋       | 79/291 [00:00<00:01, 139.76it/s]
                                                            

Loading 0:  28%|██▊       | 81/291 [00:00<00:01, 139.76it/s]
                                                            

Loading 0:  28%|██▊       | 82/291 [00:00<00:01, 139.76it/s]
                                                            

Loading 0:  29%|██▊       | 83/291 [00:00<00:01, 139.76it/s]
                                                            

Loading 0:  29%|██▉       | 85/291 [00:00<00:01, 139.76it/s]
                                                            

Loading 0:  30%|██▉       | 86/291 [00:00<00:01, 139.76it/s]
                                                            

Loading 0:  30%|███       | 88/291 [00:00<00:01, 139.76it/s]
Loading 0:  31%|███       | 89/291 [00:00<00:02, 73.64it/s] 
                                                           

Loading 0:  31%|███       | 90/291 [00:00<00:02, 73.64it/s]
                                                           

Loading 0:  31%|███▏      | 91/291 [00:00<00:02, 73.64it/s]
                                                           

Loading 0:  32%|███▏      | 92/291 [00:00<00:02, 73.64it/s]
                                                           

Loading 0:  32%|███▏      | 94/291 [00:01<00:02, 73.64it/s]
                                                           

Loading 0:  33%|███▎      | 95/291 [00:01<00:02, 73.64it/s]
                                                           

Loading 0:  33%|███▎      | 97/291 [00:01<00:02, 73.64it/s]
                                                           

Loading 0:  34%|███▍      | 99/291 [00:01<00:02, 73.64it/s]
                                                           

Loading 0:  34%|███▍      | 100/291 [00:01<00:02, 73.64it/s]
                                                            

Loading 0:  35%|███▍      | 101/291 [00:01<00:02, 73.64it/s]
Loading 0:  35%|███▌      | 103/291 [00:01<00:02, 85.01it/s]
                                                            

Loading 0:  35%|███▌      | 103/291 [00:01<00:02, 85.01it/s]
                                                            

Loading 0:  36%|███▌      | 104/291 [00:01<00:02, 85.01it/s]
                                                            

Loading 0:  36%|███▋      | 106/291 [00:01<00:02, 85.01it/s]
                                                            

Loading 0:  37%|███▋      | 108/291 [00:01<00:02, 85.01it/s]
                                                            

Loading 0:  37%|███▋      | 109/291 [00:01<00:02, 85.01it/s]
                                                            

Loading 0:  38%|███▊      | 110/291 [00:01<00:02, 85.01it/s]
                                                            

Loading 0:  38%|███▊      | 112/291 [00:01<00:02, 85.01it/s]
                                                            

Loading 0:  39%|███▉      | 113/291 [00:01<00:02, 85.01it/s]
                                                            

Loading 0:  40%|███▉      | 115/291 [00:01<00:02, 85.01it/s]
                                                            

Loading 0:  40%|████      | 117/291 [00:01<00:02, 85.01it/s]
                                                            

Loading 0:  41%|████      | 118/291 [00:01<00:02, 85.01it/s]
Loading 0:  41%|████      | 119/291 [00:01<00:01, 100.85it/s]
                                                             

Loading 0:  41%|████      | 119/291 [00:01<00:01, 100.85it/s]
                                                             

Loading 0:  42%|████▏     | 121/291 [00:01<00:01, 100.85it/s]
                                                             

Loading 0:  42%|████▏     | 122/291 [00:01<00:01, 100.85it/s]
                                                             

Loading 0:  43%|████▎     | 124/291 [00:01<00:01, 100.85it/s]
                                                             

Loading 0:  43%|████▎     | 126/291 [00:01<00:01, 100.85it/s]
                                                             

Loading 0:  44%|████▎     | 127/291 [00:01<00:01, 100.85it/s]
                                                             

Loading 0:  44%|████▍     | 128/291 [00:01<00:01, 100.85it/s]
                                                             

Loading 0:  45%|████▍     | 130/291 [00:01<00:01, 100.85it/s]
                                                             

Loading 0:  45%|████▌     | 131/291 [00:01<00:01, 100.85it/s]
Loading 0:  45%|████▌     | 132/291 [00:01<00:01, 102.65it/s]
                                                             

Loading 0:  46%|████▌     | 133/291 [00:01<00:01, 102.65it/s]
                                                             

Loading 0:  46%|████▋     | 135/291 [00:01<00:01, 102.65it/s]
                                                             

Loading 0:  47%|████▋     | 136/291 [00:01<00:01, 102.65it/s]
                                                             

Loading 0:  47%|████▋     | 137/291 [00:01<00:01, 102.65it/s]
                                                             

Loading 0:  48%|████▊     | 139/291 [00:01<00:01, 102.65it/s]
                                                             

Loading 0:  48%|████▊     | 140/291 [00:01<00:01, 102.65it/s]
                                                             

Loading 0:  49%|████▉     | 142/291 [00:01<00:01, 102.65it/s]
                                                             

Loading 0:  49%|████▉     | 144/291 [00:01<00:01, 102.65it/s]
                                                             

Loading 0:  50%|████▉     | 145/291 [00:01<00:01, 102.65it/s]
                                                             

Loading 0:  50%|█████     | 146/291 [00:01<00:01, 102.65it/s]
Loading 0:  51%|█████     | 148/291 [00:01<00:01, 112.61it/s]
                                                             

Loading 0:  51%|█████     | 148/291 [00:01<00:01, 112.61it/s]
                                                             

Loading 0:  51%|█████     | 149/291 [00:01<00:01, 112.61it/s]
                                                             

Loading 0:  52%|█████▏    | 151/291 [00:01<00:01, 112.61it/s]
                                                             

Loading 0:  53%|█████▎    | 153/291 [00:01<00:01, 112.61it/s]
                                                             

Loading 0:  53%|█████▎    | 154/291 [00:01<00:01, 112.61it/s]
                                                             

Loading 0:  53%|█████▎    | 155/291 [00:01<00:01, 112.61it/s]
                                                             

Loading 0:  54%|█████▍    | 157/291 [00:01<00:01, 112.61it/s]
                                                             

Loading 0:  54%|█████▍    | 158/291 [00:01<00:01, 112.61it/s]
                                                             

Loading 0:  55%|█████▍    | 160/291 [00:01<00:01, 112.61it/s]
                                                             

Loading 0:  56%|█████▌    | 162/291 [00:01<00:01, 112.61it/s]
                                                             

Loading 0:  56%|█████▌    | 163/291 [00:01<00:01, 112.61it/s]
Loading 0:  56%|█████▋    | 164/291 [00:01<00:01, 124.37it/s]
                                                             

Loading 0:  56%|█████▋    | 164/291 [00:01<00:01, 124.37it/s]
                                                             

Loading 0:  57%|█████▋    | 166/291 [00:01<00:01, 124.37it/s]
                                                             

Loading 0:  57%|█████▋    | 167/291 [00:01<00:00, 124.37it/s]
                                                             

Loading 0:  58%|█████▊    | 169/291 [00:01<00:00, 124.37it/s]
                                                             

Loading 0:  59%|█████▉    | 171/291 [00:01<00:00, 124.37it/s]
                                                             

Loading 0:  60%|█████▉    | 174/291 [00:01<00:00, 124.37it/s]
                                                             

Loading 0:  60%|██████    | 176/291 [00:01<00:00, 124.37it/s]
                                                             

Loading 0:  61%|██████    | 177/291 [00:01<00:00, 124.37it/s]
                                                             

Loading 0:  61%|██████    | 178/291 [00:01<00:00, 124.37it/s]
Loading 0:  62%|██████▏   | 179/291 [00:01<00:00, 125.80it/s]
                                                             

Loading 0:  62%|██████▏   | 180/291 [00:01<00:00, 125.80it/s]
             model.layers.24.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.24.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.25.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.25.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.25.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.25.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.25.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.25.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.26.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.26.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.26.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.26.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.26.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.26.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.27.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.27.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.27.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.27.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.27.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.27.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.28.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.28.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.28.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.28.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.28.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.28.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.29.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.29.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.29.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.29.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.29.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.29.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.30.input_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.30.mlp.down_proj.weight torch.Size([11927552])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.30.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.30.post_attention_layernorm.weight torch.Size([4096])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.30.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.30.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.31.mlp.up_gate_proj.weight torch.Size([23855104])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.31.self_attn.o_proj.weight torch.Size([3407872])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: model.layers.31.self_attn.qkv_proj.weight torch.Size([5111808])
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:                                                 

Loading 0:  62%|██████▏   | 181/291 [00:01<00:00, 125.80it/s]
                                                             

Loading 0:  63%|██████▎   | 183/291 [00:01<00:00, 125.80it/s]
                                                             

Loading 0:  64%|██████▎   | 185/291 [00:01<00:00, 125.80it/s]
                                                             

Loading 0:  64%|██████▍   | 186/291 [00:01<00:00, 125.80it/s]
                                                             

Loading 0:  64%|██████▍   | 187/291 [00:01<00:00, 125.80it/s]
                                                             

Loading 0:  65%|██████▍   | 188/291 [00:01<00:00, 125.80it/s]
                                                             

Loading 0:  65%|██████▍   | 189/291 [00:01<00:00, 125.80it/s]
                                                             

Loading 0:  65%|██████▌   | 190/291 [00:01<00:00, 125.80it/s]
                                                             

Loading 0:  66%|██████▌   | 191/291 [00:01<00:00, 125.80it/s]
Loading 0:  66%|██████▋   | 193/291 [00:01<00:01, 74.97it/s] 
                                                            

Loading 0:  66%|██████▋   | 193/291 [00:01<00:01, 74.97it/s]
                                                            

Loading 0:  67%|██████▋   | 194/291 [00:01<00:01, 74.97it/s]
                                                            

Loading 0:  67%|██████▋   | 196/291 [00:02<00:01, 74.97it/s]
                                                            

Loading 0:  68%|██████▊   | 198/291 [00:02<00:01, 74.97it/s]
                                                            

Loading 0:  68%|██████▊   | 199/291 [00:02<00:01, 74.97it/s]
                                                            

Loading 0:  69%|██████▊   | 200/291 [00:02<00:01, 74.97it/s]
                                                            

Loading 0:  69%|██████▉   | 202/291 [00:02<00:01, 74.97it/s]
                                                            

Loading 0:  70%|██████▉   | 203/291 [00:02<00:01, 74.97it/s]
                                                            

Loading 0:  70%|███████   | 205/291 [00:02<00:01, 74.97it/s]
                                                            

Loading 0:  71%|███████   | 207/291 [00:02<00:01, 74.97it/s]
                                                            

Loading 0:  71%|███████▏  | 208/291 [00:02<00:01, 74.97it/s]
                                                            

Loading 0:  72%|███████▏  | 209/291 [00:02<00:01, 74.97it/s]
Loading 0:  72%|███████▏  | 210/291 [00:02<00:00, 89.66it/s]
                                                            

Loading 0:  73%|███████▎  | 211/291 [00:02<00:00, 89.66it/s]
                                                            

Loading 0:  73%|███████▎  | 212/291 [00:02<00:00, 89.66it/s]
                                                            

Loading 0:  74%|███████▎  | 214/291 [00:02<00:00, 89.66it/s]
                                                            

Loading 0:  74%|███████▍  | 216/291 [00:02<00:00, 89.66it/s]
                                                            

Loading 0:  75%|███████▍  | 217/291 [00:02<00:00, 89.66it/s]
                                                            

Loading 0:  75%|███████▍  | 218/291 [00:02<00:00, 89.66it/s]
                                                            

Loading 0:  76%|███████▌  | 220/291 [00:02<00:00, 89.66it/s]
                                                            

Loading 0:  76%|███████▌  | 221/291 [00:02<00:00, 89.66it/s]
Loading 0:  76%|███████▋  | 222/291 [00:02<00:00, 95.38it/s]
                                                            

Loading 0:  77%|███████▋  | 223/291 [00:02<00:00, 95.38it/s]
                                                            

Loading 0:  77%|███████▋  | 225/291 [00:02<00:00, 95.38it/s]
                                                            

Loading 0:  78%|███████▊  | 226/291 [00:02<00:00, 95.38it/s]
                                                            

Loading 0:  78%|███████▊  | 227/291 [00:02<00:00, 95.38it/s]
                                                            

Loading 0:  79%|███████▊  | 229/291 [00:02<00:00, 95.38it/s]
                                                            

Loading 0:  79%|███████▉  | 230/291 [00:02<00:00, 95.38it/s]
                                                            

Loading 0:  80%|███████▉  | 232/291 [00:02<00:00, 95.38it/s]
                                                            

Loading 0:  80%|████████  | 234/291 [00:02<00:00, 95.38it/s]
                                                            

Loading 0:  81%|████████  | 235/291 [00:02<00:00, 95.38it/s]
                                                            

Loading 0:  81%|████████  | 236/291 [00:02<00:00, 95.38it/s]
Loading 0:  82%|████████▏ | 238/291 [00:02<00:00, 106.70it/s]
                                                             

Loading 0:  82%|████████▏ | 238/291 [00:02<00:00, 106.70it/s]
                                                             

Loading 0:  82%|████████▏ | 239/291 [00:02<00:00, 106.70it/s]
                                                             

Loading 0:  83%|████████▎ | 241/291 [00:02<00:00, 106.70it/s]
                                                             

Loading 0:  84%|████████▎ | 243/291 [00:02<00:00, 106.70it/s]
                                                             

Loading 0:  84%|████████▍ | 244/291 [00:02<00:00, 106.70it/s]
                                                             

Loading 0:  84%|████████▍ | 245/291 [00:02<00:00, 106.70it/s]
                                                             

Loading 0:  85%|████████▍ | 247/291 [00:02<00:00, 106.70it/s]
                                                             

Loading 0:  85%|████████▌ | 248/291 [00:02<00:00, 106.70it/s]
                                                             

Loading 0:  86%|████████▌ | 250/291 [00:02<00:00, 106.70it/s]
                                                             

Loading 0:  87%|████████▋ | 252/291 [00:02<00:00, 106.70it/s]
                                                             

Loading 0:  87%|████████▋ | 253/291 [00:02<00:00, 106.70it/s]
                                                             

Loading 0:  87%|████████▋ | 254/291 [00:02<00:00, 106.70it/s]
Loading 0:  88%|████████▊ | 255/291 [00:02<00:00, 117.60it/s]
                                                             

Loading 0:  88%|████████▊ | 256/291 [00:02<00:00, 117.60it/s]
                                                             

Loading 0:  88%|████████▊ | 257/291 [00:02<00:00, 117.60it/s]
                                                             

Loading 0:  89%|████████▉ | 259/291 [00:02<00:00, 117.60it/s]
                                                             

Loading 0:  90%|████████▉ | 261/291 [00:02<00:00, 117.60it/s]
                                                             

Loading 0:  90%|█████████ | 262/291 [00:02<00:00, 117.60it/s]
                                                             

Loading 0:  90%|█████████ | 263/291 [00:02<00:00, 117.60it/s]
                                                             

Loading 0:  91%|█████████ | 265/291 [00:02<00:00, 117.60it/s]
                                                             

Loading 0:  91%|█████████▏| 266/291 [00:02<00:00, 117.60it/s]
                                                             

Loading 0:  92%|█████████▏| 268/291 [00:02<00:00, 117.60it/s]
Loading 0:  92%|█████████▏| 269/291 [00:02<00:00, 120.65it/s]
                                                             

Loading 0:  93%|█████████▎| 270/291 [00:02<00:00, 120.65it/s]
                                                             

Loading 0:  93%|█████████▎| 271/291 [00:02<00:00, 120.65it/s]
                                                             

Loading 0:  93%|█████████▎| 272/291 [00:02<00:00, 120.65it/s]
                                                             

Loading 0:  94%|█████████▍| 274/291 [00:02<00:00, 120.65it/s]
                                                             

Loading 0:  95%|█████████▍| 275/291 [00:02<00:00, 120.65it/s]
                                                             

Loading 0:  95%|█████████▌| 277/291 [00:02<00:00, 120.65it/s]
                                                             

Loading 0:  96%|█████████▌| 279/291 [00:02<00:00, 120.65it/s]
                                                             

Loading 0:  97%|█████████▋| 281/291 [00:02<00:00, 120.65it/s]
Loading 0:  97%|█████████▋| 283/291 [00:02<00:00, 122.80it/s]
                                                             

Loading 0:  97%|█████████▋| 283/291 [00:02<00:00, 122.80it/s]
                                                             

Loading 0:  98%|█████████▊| 285/291 [00:02<00:00, 122.80it/s]
                                                             

Loading 0:  98%|█████████▊| 286/291 [00:08<00:00, 122.80it/s]
                                                             

Loading 0:  99%|█████████▊| 287/291 [00:08<00:00, 122.80it/s]
                                                             

Loading 0:  99%|█████████▉| 288/291 [00:08<00:00, 122.80it/s]
                                                             

Loading 0:  99%|█████████▉| 289/291 [00:08<00:00, 122.80it/s]
                                                             

Loading 0: 100%|█████████▉| 290/291 [00:08<00:00, 122.80it/s]
                                                             
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: quantized model in 24.762s
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: Processed model cycy233/L3-bdpo-v5-c1 in 53.265s
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-bdpo-v5-c1-v4
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-bdpo-v5-c1-v4/config.json
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-bdpo-v5-c1-v4/special_tokens_map.json
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-bdpo-v5-c1-v4/tokenizer_config.json
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-bdpo-v5-c1-v4/tokenizer.json
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-bdpo-v5-c1-v4/flywheel_model.0.safetensors
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:950: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:   warnings.warn(
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:778: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:   warnings.warn(
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:469: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
cycy233-l3-bdpo-v5-c1-v4-mkmlizer:   warnings.warn(
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: Saving duration: 1.929s
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 14.184s
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-bdpo-v5-c1-v4_reward
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-bdpo-v5-c1-v4_reward/config.json
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-bdpo-v5-c1-v4_reward/special_tokens_map.json
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-bdpo-v5-c1-v4_reward/tokenizer_config.json
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-bdpo-v5-c1-v4_reward/merges.txt
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-bdpo-v5-c1-v4_reward/vocab.json
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-bdpo-v5-c1-v4_reward/tokenizer.json
cycy233-l3-bdpo-v5-c1-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-bdpo-v5-c1-v4_reward/reward.tensors
Job cycy233-l3-bdpo-v5-c1-v4-mkmlizer completed after 100.01s with status: succeeded
Stopping job with name cycy233-l3-bdpo-v5-c1-v4-mkmlizer
Pipeline stage MKMLizer completed in 196.76s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.16s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-bdpo-v5-c1-v4
Waiting for inference service cycy233-l3-bdpo-v5-c1-v4 to be ready
Inference service cycy233-l3-bdpo-v5-c1-v4 ready after 50.214245319366455s
Pipeline stage ISVCDeployer completed in 57.25s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3620376586914062s
Received healthy response to inference request in 1.4381976127624512s
Received healthy response to inference request in 1.4233174324035645s
Received healthy response to inference request in 1.3911471366882324s
Received healthy response to inference request in 1.4428489208221436s
5 requests
0 failed requests
5th percentile: 1.397581195831299
10th percentile: 1.4040152549743652
20th percentile: 1.416883373260498
30th percentile: 1.4262934684753419
40th percentile: 1.4322455406188965
50th percentile: 1.4381976127624512
60th percentile: 1.440058135986328
70th percentile: 1.4419186592102051
80th percentile: 1.6266866683959962
90th percentile: 1.9943621635437012
95th percentile: 2.1781999111175536
99th percentile: 2.325270109176636
mean time: 1.6115097522735595
Pipeline stage StressChecker completed in 10.20s
cycy233-l3-bdpo-v5-c1_v4 status is now deployed due to DeploymentManager action
cycy233-l3-bdpo-v5-c1_v4 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-l3-bdpo-v5-c1_v4
Running pipeline stage ISVCDeleter
Checking if service cycy233-l3-bdpo-v5-c1-v4 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 6.10s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-l3-bdpo-v5-c1-v4/config.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-bdpo-v5-c1-v4/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-l3-bdpo-v5-c1-v4/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-bdpo-v5-c1-v4/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-bdpo-v5-c1-v4/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-l3-bdpo-v5-c1-v4_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-bdpo-v5-c1-v4_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-l3-bdpo-v5-c1-v4_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-l3-bdpo-v5-c1-v4_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-l3-bdpo-v5-c1-v4_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-l3-bdpo-v5-c1-v4_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-bdpo-v5-c1-v4_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 8.52s
cycy233-l3-bdpo-v5-c1_v4 status is now torndown due to DeploymentManager action