Upload imatrix.log with huggingface_hub

imatrix.log

@@ -0,0 +1,142 @@
+main: build = 3086 (554c247c)
+main: built with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu
+main: seed  = 1717675894
+llama_model_loader: loaded meta data with 23 key-value pairs and 723 tensors from Higgs-Llama-3-70B-IMat-GGUF/Higgs-Llama-3-70B.Q8_0.gguf (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.name str              = Higgs-Llama-3-70B
+llama_model_loader: - kv   2:                          llama.block_count u32              = 80
+llama_model_loader: - kv   3:                       llama.context_length u32              = 8192
+llama_model_loader: - kv   4:                     llama.embedding_length u32              = 8192
+llama_model_loader: - kv   5:                  llama.feed_forward_length u32              = 28672
+llama_model_loader: - kv   6:                 llama.attention.head_count u32              = 64
+llama_model_loader: - kv   7:              llama.attention.head_count_kv u32              = 8
+llama_model_loader: - kv   8:                       llama.rope.freq_base f32              = 500000.000000
+llama_model_loader: - kv   9:     llama.attention.layer_norm_rms_epsilon f32              = 0.000010
+llama_model_loader: - kv  10:                          general.file_type u32              = 7
+llama_model_loader: - kv  11:                           llama.vocab_size u32              = 128256
+llama_model_loader: - kv  12:                 llama.rope.dimension_count u32              = 128
+llama_model_loader: - kv  13:                       tokenizer.ggml.model str              = gpt2
+llama_model_loader: - kv  14:                         tokenizer.ggml.pre str              = smaug-bpe
+llama_model_loader: - kv  15:                      tokenizer.ggml.tokens arr[str,128256]  = ["!", "\"", "#", "$", "%", "&", "'", ...
+llama_model_loader: - kv  16:                  tokenizer.ggml.token_type arr[i32,128256]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
+llama_model_loader: - kv  17:                      tokenizer.ggml.merges arr[str,280147]  = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "...
+llama_model_loader: - kv  18:                tokenizer.ggml.bos_token_id u32              = 128000
+llama_model_loader: - kv  19:                tokenizer.ggml.eos_token_id u32              = 128001
+llama_model_loader: - kv  20:            tokenizer.ggml.padding_token_id u32              = 128001
+llama_model_loader: - kv  21:                    tokenizer.chat_template str              = {% set loop_messages = messages %}{% ...
+llama_model_loader: - kv  22:               general.quantization_version u32              = 2
+llama_model_loader: - type  f32:  161 tensors
+llama_model_loader: - type q8_0:  562 tensors
+llm_load_vocab: special tokens cache size = 256
+llm_load_vocab: token to piece cache size = 0.8000 MB
+llm_load_print_meta: format           = GGUF V3 (latest)
+llm_load_print_meta: arch             = llama
+llm_load_print_meta: vocab type       = BPE
+llm_load_print_meta: n_vocab          = 128256
+llm_load_print_meta: n_merges         = 280147
+llm_load_print_meta: n_ctx_train      = 8192
+llm_load_print_meta: n_embd           = 8192
+llm_load_print_meta: n_head           = 64
+llm_load_print_meta: n_head_kv        = 8
+llm_load_print_meta: n_layer          = 80
+llm_load_print_meta: n_rot            = 128
+llm_load_print_meta: n_embd_head_k    = 128
+llm_load_print_meta: n_embd_head_v    = 128
+llm_load_print_meta: n_gqa            = 8
+llm_load_print_meta: n_embd_k_gqa     = 1024
+llm_load_print_meta: n_embd_v_gqa     = 1024
+llm_load_print_meta: f_norm_eps       = 0.0e+00
+llm_load_print_meta: f_norm_rms_eps   = 1.0e-05
+llm_load_print_meta: f_clamp_kqv      = 0.0e+00
+llm_load_print_meta: f_max_alibi_bias = 0.0e+00
+llm_load_print_meta: f_logit_scale    = 0.0e+00
+llm_load_print_meta: n_ff             = 28672
+llm_load_print_meta: n_expert         = 0
+llm_load_print_meta: n_expert_used    = 0
+llm_load_print_meta: causal attn      = 1
+llm_load_print_meta: pooling type     = 0
+llm_load_print_meta: rope type        = 0
+llm_load_print_meta: rope scaling     = linear
+llm_load_print_meta: freq_base_train  = 500000.0
+llm_load_print_meta: freq_scale_train = 1
+llm_load_print_meta: n_yarn_orig_ctx  = 8192
+llm_load_print_meta: rope_finetuned   = unknown
+llm_load_print_meta: ssm_d_conv       = 0
+llm_load_print_meta: ssm_d_inner      = 0
+llm_load_print_meta: ssm_d_state      = 0
+llm_load_print_meta: ssm_dt_rank      = 0
+llm_load_print_meta: model type       = 70B
+llm_load_print_meta: model ftype      = Q8_0
+llm_load_print_meta: model params     = 70.55 B
+llm_load_print_meta: model size       = 69.82 GiB (8.50 BPW) 
+llm_load_print_meta: general.name     = Higgs-Llama-3-70B
+llm_load_print_meta: BOS token        = 128000 '<|begin_of_text|>'
+llm_load_print_meta: EOS token        = 128001 '<|end_of_text|>'
+llm_load_print_meta: PAD token        = 128001 '<|end_of_text|>'
+llm_load_print_meta: LF token         = 128 'Ä'
+llm_load_print_meta: EOT token        = 128009 '<|eot_id|>'
+ggml_cuda_init: GGML_CUDA_FORCE_MMQ:   no
+ggml_cuda_init: CUDA_USE_TENSOR_CORES: yes
+ggml_cuda_init: found 1 CUDA devices:
+  Device 0: NVIDIA GeForce RTX 4090, compute capability 8.9, VMM: yes
+llm_load_tensors: ggml ctx size =    0.74 MiB
+llm_load_tensors: offloading 23 repeating layers to GPU
+llm_load_tensors: offloaded 23/81 layers to GPU
+llm_load_tensors:        CPU buffer size = 71494.28 MiB
+llm_load_tensors:      CUDA0 buffer size = 19942.44 MiB
+....................................................................................................
+llama_new_context_with_model: n_ctx      = 512
+llama_new_context_with_model: n_batch    = 512
+llama_new_context_with_model: n_ubatch   = 512
+llama_new_context_with_model: flash_attn = 0
+llama_new_context_with_model: freq_base  = 500000.0
+llama_new_context_with_model: freq_scale = 1
+llama_kv_cache_init:  CUDA_Host KV buffer size =   114.00 MiB
+llama_kv_cache_init:      CUDA0 KV buffer size =    46.00 MiB
+llama_new_context_with_model: KV self size  =  160.00 MiB, K (f16):   80.00 MiB, V (f16):   80.00 MiB
+llama_new_context_with_model:  CUDA_Host  output buffer size =     0.49 MiB
+llama_new_context_with_model:      CUDA0 compute buffer size =  1331.12 MiB
+llama_new_context_with_model:  CUDA_Host compute buffer size =    17.01 MiB
+llama_new_context_with_model: graph nodes  = 2566
+llama_new_context_with_model: graph splits = 631
+
+system_info: n_threads = 32 / 32 | AVX = 1 | AVX_VNNI = 0 | AVX2 = 1 | AVX512 = 1 | AVX512_VBMI = 1 | AVX512_VNNI = 1 | AVX512_BF16 = 1 | FMA = 1 | NEON = 0 | SVE = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 1 | 
+compute_imatrix: tokenizing the input ..
+compute_imatrix: tokenization took 181.501 ms
+compute_imatrix: computing over 125 chunks with batch_size 512
+compute_imatrix: 15.83 seconds per pass - ETA 32.97 minutes
+[1]4.6746,[2]3.7264,[3]3.3172,[4]4.0074,[5]4.0752,[6]3.4988,[7]3.4849,[8]3.8297,[9]4.0246,
+save_imatrix: stored collected data after 10 chunks in Higgs-Llama-3-70B-IMat-GGUF/imatrix.dat
+[10]3.7410,[11]4.1182,[12]4.4985,[13]4.8429,[14]5.1377,[15]5.3348,[16]5.5907,[17]5.7580,[18]5.5967,[19]5.3528,
+save_imatrix: stored collected data after 20 chunks in Higgs-Llama-3-70B-IMat-GGUF/imatrix.dat
+[20]5.3698,[21]5.4181,[22]5.4081,[23]5.5465,[24]5.5286,[25]5.8102,[26]5.8008,[27]5.4435,[28]5.1707,[29]5.1692,
+save_imatrix: stored collected data after 30 chunks in Higgs-Llama-3-70B-IMat-GGUF/imatrix.dat
+[30]5.1437,[31]4.9295,[32]4.7268,[33]4.6368,[34]4.5639,[35]4.6244,[36]4.6603,[37]4.6356,[38]4.7010,[39]4.8262,
+save_imatrix: stored collected data after 40 chunks in Higgs-Llama-3-70B-IMat-GGUF/imatrix.dat
+[40]4.8947,[41]4.7263,[42]4.5693,[43]4.4226,[44]4.2843,[45]4.2261,[46]4.1950,[47]4.2907,[48]4.3776,[49]4.4714,
+save_imatrix: stored collected data after 50 chunks in Higgs-Llama-3-70B-IMat-GGUF/imatrix.dat
+[50]4.4302,[51]4.5180,[52]4.5959,[53]4.6672,[54]4.7153,[55]4.7853,[56]4.8274,[57]4.8785,[58]4.9240,[59]4.9343,
+save_imatrix: stored collected data after 60 chunks in Higgs-Llama-3-70B-IMat-GGUF/imatrix.dat
+[60]4.9289,[61]4.9437,[62]4.9834,[63]5.0309,[64]4.9949,[65]4.9789,[66]4.9964,[67]4.9923,[68]4.9953,[69]4.9955,
+save_imatrix: stored collected data after 70 chunks in Higgs-Llama-3-70B-IMat-GGUF/imatrix.dat
+[70]5.0128,[71]5.0165,[72]5.0321,[73]5.0233,[74]5.0112,[75]5.0205,[76]5.0366,[77]5.0282,[78]5.0190,[79]5.0533,
+save_imatrix: stored collected data after 80 chunks in Higgs-Llama-3-70B-IMat-GGUF/imatrix.dat
+[80]5.0795,[81]5.0735,[82]5.0908,[83]5.1158,[84]5.0649,[85]5.0625,[86]5.0650,[87]5.0743,[88]5.1019,[89]5.1233,
+save_imatrix: stored collected data after 90 chunks in Higgs-Llama-3-70B-IMat-GGUF/imatrix.dat
+[90]5.0981,[91]5.0728,[92]5.0463,[93]5.0234,[94]4.9954,[95]4.9709,[96]4.9480,[97]4.9650,[98]4.9980,[99]5.0550,
+save_imatrix: stored collected data after 100 chunks in Higgs-Llama-3-70B-IMat-GGUF/imatrix.dat
+[100]5.1048,[101]5.1433,[102]5.2264,[103]5.2540,[104]5.2822,[105]5.2387,[106]5.2514,[107]5.2253,[108]5.1687,[109]5.1074,
+save_imatrix: stored collected data after 110 chunks in Higgs-Llama-3-70B-IMat-GGUF/imatrix.dat
+[110]5.1347,[111]5.1748,[112]5.1846,[113]5.1979,[114]5.2238,[115]5.2558,[116]5.2696,[117]5.2861,[118]5.3158,[119]5.2941,
+save_imatrix: stored collected data after 120 chunks in Higgs-Llama-3-70B-IMat-GGUF/imatrix.dat
+[120]5.2402,[121]5.1726,[122]5.1055,[123]5.0469,[124]4.9872,[125]4.9270,
+save_imatrix: stored collected data after 125 chunks in Higgs-Llama-3-70B-IMat-GGUF/imatrix.dat
+
+llama_print_timings:        load time =   19623.38 ms
+llama_print_timings:      sample time =       0.00 ms /     1 runs   (    0.00 ms per token,      inf tokens per second)
+llama_print_timings: prompt eval time = 1807072.34 ms / 64000 tokens (   28.24 ms per token,    35.42 tokens per second)
+llama_print_timings:        eval time =       0.00 ms /     1 runs   (    0.00 ms per token,      inf tokens per second)
+llama_print_timings:       total time = 1812278.76 ms / 64001 tokens
+
+Final estimate: PPL = 4.9270 +/- 0.06224