Upload 11 files

logs/logs_cpu_2025.05.22 round3 parallelise1.txt

@@ -0,0 +1,197 @@
+https://www.kaggle.com/code/kaiquanmah/01a-kaggle-ollama-llama3-2?scriptVersionId=241139873
+
+time=2025-05-22T03:18:37.534Z level=INFO source=server.go:135 msg="system memory" total="31.4 GiB" free="30.1 GiB" free_swap="0 B"
+time=2025-05-22T03:18:37.534Z level=INFO source=server.go:168 msg=offload library=cpu layers.requested=-1 layers.model=29 layers.offload=0 layers.split="" memory.available="[30.1 GiB]" memory.gpu_overhead="0 B" memory.required.full="3.5 GiB" memory.required.partial="0 B" memory.required.kv="896.0 MiB" memory.required.allocations="[3.5 GiB]" memory.weights.total="1.9 GiB" memory.weights.repeating="1.6 GiB" memory.weights.nonrepeating="308.2 MiB" memory.graph.full="424.0 MiB" memory.graph.partial="570.7 MiB"
+llama_model_loader: loaded meta data with 30 key-value pairs and 255 tensors from /root/.ollama/models/blobs/sha256-dde5aa3fc5ffc17176b5e8bdc82f587b24b2678c6c66101bf7da77af9f7ccdff (version GGUF V3 (latest))
+llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
+llama_model_loader: - kv   0:                       general.architecture str              = llama
+llama_model_loader: - kv   1:                               general.type str              = model
+llama_model_loader: - kv   2:                               general.name str              = Llama 3.2 3B Instruct
+llama_model_loader: - kv   3:                           general.finetune str              = Instruct
+llama_model_loader: - kv   4:                           general.basename str              = Llama-3.2
+llama_model_loader: - kv   5:                         general.size_label str              = 3B
+llama_model_loader: - kv   6:                               general.tags arr[str,6]       = ["facebook", "meta", "pytorch", "llam...
+llama_model_loader: - kv   7:                          general.languages arr[str,8]       = ["en", "de", "fr", "it", "pt", "hi", ...
+llama_model_loader: - kv   8:                          llama.block_count u32              = 28
+llama_model_loader: - kv   9:                       llama.context_length u32              = 131072
+llama_model_loader: - kv  10:                     llama.embedding_length u32              = 3072
+llama_model_loader: - kv  11:                  llama.feed_forward_length u32              = 8192
+llama_model_loader: - kv  12:                 llama.attention.head_count u32              = 24
+llama_model_loader: - kv  13:              llama.attention.head_count_kv u32              = 8
+llama_model_loader: - kv  14:                       llama.rope.freq_base f32              = 500000.000000
+llama_model_loader: - kv  15:     llama.attention.layer_norm_rms_epsilon f32              = 0.000010
+llama_model_loader: - kv  16:                 llama.attention.key_length u32              = 128
+llama_model_loader: - kv  17:               llama.attention.value_length u32              = 128
+llama_model_loader: - kv  18:                          general.file_type u32              = 15
+llama_model_loader: - kv  19:                           llama.vocab_size u32              = 128256
+llama_model_loader: - kv  20:                 llama.rope.dimension_count u32              = 128
+llama_model_loader: - kv  21:                       tokenizer.ggml.model str              = gpt2
+llama_model_loader: - kv  22:                         tokenizer.ggml.pre str              = llama-bpe
+llama_model_loader: - kv  23:                      tokenizer.ggml.tokens arr[str,128256]  = ["!", "\"", "#", "$", "%", "&", "'", ...
+llama_model_loader: - kv  24:                  tokenizer.ggml.token_type arr[i32,128256]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
+llama_model_loader: - kv  25:                      tokenizer.ggml.merges arr[str,280147]  = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "...
+llama_model_loader: - kv  26:                tokenizer.ggml.bos_token_id u32              = 128000
+llama_model_loader: - kv  27:                tokenizer.ggml.eos_token_id u32              = 128009
+llama_model_loader: - kv  28:                    tokenizer.chat_template str              = {{- bos_token }}\n{%- if custom_tools ...
+llama_model_loader: - kv  29:               general.quantization_version u32              = 2
+llama_model_loader: - type  f32:   58 tensors
+llama_model_loader: - type q4_K:  168 tensors
+llama_model_loader: - type q6_K:   29 tensors
+print_info: file format = GGUF V3 (latest)
+print_info: file type   = Q4_K - Medium
+print_info: file size   = 1.87 GiB (5.01 BPW) 
+load: special tokens cache size = 256
+load: token to piece cache size = 0.7999 MB
+print_info: arch             = llama
+print_info: vocab_only       = 1
+print_info: model type       = ?B
+print_info: model params     = 3.21 B
+print_info: general.name     = Llama 3.2 3B Instruct
+print_info: vocab type       = BPE
+print_info: n_vocab          = 128256
+print_info: n_merges         = 280147
+print_info: BOS token        = 128000 '<|begin_of_text|>'
+print_info: EOS token        = 128009 '<|eot_id|>'
+print_info: EOT token        = 128009 '<|eot_id|>'
+print_info: EOM token        = 128008 '<|eom_id|>'
+print_info: LF token         = 198 'Ċ'
+print_info: EOG token        = 128008 '<|eom_id|>'
+print_info: EOG token        = 128009 '<|eot_id|>'
+print_info: max token length = 256
+llama_model_load: vocab only - skipping tensors
+time=2025-05-22T03:18:38.186Z level=INFO source=server.go:431 msg="starting llama server" cmd="/usr/local/bin/ollama runner --model /root/.ollama/models/blobs/sha256-dde5aa3fc5ffc17176b5e8bdc82f587b24b2678c6c66101bf7da77af9f7ccdff --ctx-size 8192 --batch-size 512 --threads 2 --no-mmap --parallel 2 --port 38637"
+time=2025-05-22T03:18:38.187Z level=INFO source=sched.go:472 msg="loaded runners" count=1
+time=2025-05-22T03:18:38.187Z level=INFO source=server.go:591 msg="waiting for llama runner to start responding"
+time=2025-05-22T03:18:38.188Z level=INFO source=server.go:625 msg="waiting for server to become available" status="llm server not responding"
+time=2025-05-22T03:18:38.217Z level=INFO source=runner.go:815 msg="starting go runner"
+load_backend: loaded CPU backend from /usr/local/lib/ollama/libggml-cpu-haswell.so
+time=2025-05-22T03:18:38.228Z level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(gcc)
+time=2025-05-22T03:18:38.234Z level=INFO source=runner.go:874 msg="Server listening on 127.0.0.1:38637"
+llama_model_loader: loaded meta data with 30 key-value pairs and 255 tensors from /root/.ollama/models/blobs/sha256-dde5aa3fc5ffc17176b5e8bdc82f587b24b2678c6c66101bf7da77af9f7ccdff (version GGUF V3 (latest))
+llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
+llama_model_loader: - kv   0:                       general.architecture str              = llama
+llama_model_loader: - kv   1:                               general.type str              = model
+llama_model_loader: - kv   2:                               general.name str              = Llama 3.2 3B Instruct
+llama_model_loader: - kv   3:                           general.finetune str              = Instruct
+llama_model_loader: - kv   4:                           general.basename str              = Llama-3.2
+llama_model_loader: - kv   5:                         general.size_label str              = 3B
+llama_model_loader: - kv   6:                               general.tags arr[str,6]       = ["facebook", "meta", "pytorch", "llam...
+llama_model_loader: - kv   7:                          general.languages arr[str,8]       = ["en", "de", "fr", "it", "pt", "hi", ...
+llama_model_loader: - kv   8:                          llama.block_count u32              = 28
+llama_model_loader: - kv   9:                       llama.context_length u32              = 131072
+llama_model_loader: - kv  10:                     llama.embedding_length u32              = 3072
+llama_model_loader: - kv  11:                  llama.feed_forward_length u32              = 8192
+llama_model_loader: - kv  12:                 llama.attention.head_count u32              = 24
+llama_model_loader: - kv  13:              llama.attention.head_count_kv u32              = 8
+llama_model_loader: - kv  14:                       llama.rope.freq_base f32              = 500000.000000
+llama_model_loader: - kv  15:     llama.attention.layer_norm_rms_epsilon f32              = 0.000010
+llama_model_loader: - kv  16:                 llama.attention.key_length u32              = 128
+llama_model_loader: - kv  17:               llama.attention.value_length u32              = 128
+llama_model_loader: - kv  18:                          general.file_type u32              = 15
+llama_model_loader: - kv  19:                           llama.vocab_size u32              = 128256
+llama_model_loader: - kv  20:                 llama.rope.dimension_count u32              = 128
+llama_model_loader: - kv  21:                       tokenizer.ggml.model str              = gpt2
+llama_model_loader: - kv  22:                         tokenizer.ggml.pre str              = llama-bpe
+llama_model_loader: - kv  23:                      tokenizer.ggml.tokens arr[str,128256]  = ["!", "\"", "#", "$", "%", "&", "'", ...
+llama_model_loader: - kv  24:                  tokenizer.ggml.token_type arr[i32,128256]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
+llama_model_loader: - kv  25:                      tokenizer.ggml.merges arr[str,280147]  = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "...
+llama_model_loader: - kv  26:                tokenizer.ggml.bos_token_id u32              = 128000
+llama_model_loader: - kv  27:                tokenizer.ggml.eos_token_id u32              = 128009
+llama_model_loader: - kv  28:                    tokenizer.chat_template str              = {{- bos_token }}\n{%- if custom_tools ...
+llama_model_loader: - kv  29:               general.quantization_version u32              = 2
+llama_model_loader: - type  f32:   58 tensors
+llama_model_loader: - type q4_K:  168 tensors
+llama_model_loader: - type q6_K:   29 tensors
+print_info: file format = GGUF V3 (latest)
+print_info: file type   = Q4_K - Medium
+print_info: file size   = 1.87 GiB (5.01 BPW) 
+time=2025-05-22T03:18:38.440Z level=INFO source=server.go:625 msg="waiting for server to become available" status="llm server loading model"
+load: special tokens cache size = 256
+load: token to piece cache size = 0.7999 MB
+print_info: arch             = llama
+print_info: vocab_only       = 0
+print_info: n_ctx_train      = 131072
+print_info: n_embd           = 3072
+print_info: n_layer          = 28
+print_info: n_head           = 24
+print_info: n_head_kv        = 8
+print_info: n_rot            = 128
+print_info: n_swa            = 0
+print_info: n_swa_pattern    = 1
+print_info: n_embd_head_k    = 128
+print_info: n_embd_head_v    = 128
+print_info: n_gqa            = 3
+print_info: n_embd_k_gqa     = 1024
+print_info: n_embd_v_gqa     = 1024
+print_info: f_norm_eps       = 0.0e+00
+print_info: f_norm_rms_eps   = 1.0e-05
+print_info: f_clamp_kqv      = 0.0e+00
+print_info: f_max_alibi_bias = 0.0e+00
+print_info: f_logit_scale    = 0.0e+00
+print_info: f_attn_scale     = 0.0e+00
+print_info: n_ff             = 8192
+print_info: n_expert         = 0
+print_info: n_expert_used    = 0
+print_info: causal attn      = 1
+print_info: pooling type     = 0
+print_info: rope type        = 0
+print_info: rope scaling     = linear
+print_info: freq_base_train  = 500000.0
+print_info: freq_scale_train = 1
+print_info: n_ctx_orig_yarn  = 131072
+print_info: rope_finetuned   = unknown
+print_info: ssm_d_conv       = 0
+print_info: ssm_d_inner      = 0
+print_info: ssm_d_state      = 0
+print_info: ssm_dt_rank      = 0
+print_info: ssm_dt_b_c_rms   = 0
+print_info: model type       = 3B
+print_info: model params     = 3.21 B
+print_info: general.name     = Llama 3.2 3B Instruct
+print_info: vocab type       = BPE
+print_info: n_vocab          = 128256
+print_info: n_merges         = 280147
+print_info: BOS token        = 128000 '<|begin_of_text|>'
+print_info: EOS token        = 128009 '<|eot_id|>'
+print_info: EOT token        = 128009 '<|eot_id|>'
+print_info: EOM token        = 128008 '<|eom_id|>'
+print_info: LF token         = 198 'Ċ'
+print_info: EOG token        = 128008 '<|eom_id|>'
+print_info: EOG token        = 128009 '<|eot_id|>'
+print_info: max token length = 256
+load_tensors: loading model tensors, this can take a while... (mmap = false)
+load_tensors:          CPU model buffer size =  1918.35 MiB
+llama_context: constructing llama_context
+llama_context: n_seq_max     = 2
+llama_context: n_ctx         = 8192
+llama_context: n_ctx_per_seq = 4096
+llama_context: n_batch       = 1024
+llama_context: n_ubatch      = 512
+llama_context: causal_attn   = 1
+llama_context: flash_attn    = 0
+llama_context: freq_base     = 500000.0
+llama_context: freq_scale    = 1
+llama_context: n_ctx_per_seq (4096) < n_ctx_train (131072) -- the full capacity of the model will not be utilized
+llama_context:        CPU  output buffer size =     1.00 MiB
+llama_kv_cache_unified: kv_size = 8192, type_k = 'f16', type_v = 'f16', n_layer = 28, can_shift = 1, padding = 32
+llama_kv_cache_unified:        CPU KV buffer size =   896.00 MiB
+llama_kv_cache_unified: KV self size  =  896.00 MiB, K (f16):  448.00 MiB, V (f16):  448.00 MiB
+llama_context:        CPU compute buffer size =   424.01 MiB
+llama_context: graph nodes  = 958
+llama_context: graph splits = 1
+time=2025-05-22T03:18:44.220Z level=INFO source=server.go:630 msg="llama runner started in 6.03 seconds"
+[GIN] 2025/05/22 - 03:21:18 | 200 |         2m41s |       127.0.0.1 | POST     "/api/chat"
+Processed 0 rows | Elapsed: 161.03s | ETA: 2106716.46s
+[GIN] 2025/05/22 - 03:21:39 | 200 |          3m2s |       127.0.0.1 | POST     "/api/chat"
+[GIN] 2025/05/22 - 03:22:15 | 200 |         3m38s |       127.0.0.1 | POST     "/api/chat"
+[GIN] 2025/05/22 - 03:22:15 | 200 |         3m38s |       127.0.0.1 | POST     "/api/chat"
+[GIN] 2025/05/22 - 03:23:02 | 200 |         4m24s |       127.0.0.1 | POST     "/api/chat"
+[GIN] 2025/05/22 - 03:23:02 | 200 |         4m25s |       127.0.0.1 | POST     "/api/chat"
+[GIN] 2025/05/22 - 03:23:45 | 200 |          5m7s |       127.0.0.1 | POST     "/api/chat"
+[GIN] 2025/05/22 - 03:24:05 | 200 |         5m27s |       127.0.0.1 | POST     "/api/chat"
+[GIN] 2025/05/22 - 03:24:32 | 200 |         3m14s |       127.0.0.1 | POST     "/api/chat"
+[GIN] 2025/05/22 - 03:24:55 | 200 |         3m15s |       127.0.0.1 | POST     "/api/chat"
+[GIN] 2025/05/22 - 03:25:22 | 200 |          3m7s |       127.0.0.1 | POST     "/api/chat"
+[GIN] 2025/05/22 - 03:25:45 | 200 |         3m29s |       127.0.0.1 | POST     "/api/chat"
+[GIN] 2025/05/22 - 03:26:08 | 200 |          3m6s |       127.0.0.1 | POST     "/api/chat"
+[GIN] 2025/05/22 - 03:26:30 | 200 |         3m27s |       127.0.0.1 | POST     "/api/chat"