Upload imatrix.log with huggingface_hub

imatrix.log

@@ -1,4 +1,4 @@
-llama_model_loader: loaded meta data with 26 key-value pairs and 464 tensors from gemma-2-9b-it-IMat-GGUF/gemma-2-9b-it.Q8_0.gguf.hardlink.gguf (version GGUF V3 (latest))
+llama_model_loader: loaded meta data with 28 key-value pairs and 464 tensors from gemma-2-9b-it-IMat-GGUF/gemma-2-9b-it.Q8_0.gguf.hardlink.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              = gemma2
 llama_model_loader: - kv   1:                               general.name str              = gemma-2-9b-it
@@ -12,20 +12,22 @@ llama_model_loader: - kv   8:    gemma2.attention.layer_norm_rms_epsilon f32
 llama_model_loader: - kv   9:                gemma2.attention.key_length u32              = 256
 llama_model_loader: - kv  10:              gemma2.attention.value_length u32              = 256
 llama_model_loader: - kv  11:                          general.file_type u32              = 7
-llama_model_loader: - kv  12:                       tokenizer.ggml.model str              = llama
-llama_model_loader: - kv  13:                         tokenizer.ggml.pre str              = default
-llama_model_loader: - kv  14:                      tokenizer.ggml.tokens arr[str,256000]  = ["<pad>", "<eos>", "<bos>", "<unk>", ...
-llama_model_loader: - kv  15:                      tokenizer.ggml.scores arr[f32,256000]  = [-1000.000000, -1000.000000, -1000.00...
-llama_model_loader: - kv  16:                  tokenizer.ggml.token_type arr[i32,256000]  = [3, 3, 3, 3, 1, 1, 1, 1, 1, 1, 1, 1, ...
-llama_model_loader: - kv  17:                tokenizer.ggml.bos_token_id u32              = 2
-llama_model_loader: - kv  18:                tokenizer.ggml.eos_token_id u32              = 1
-llama_model_loader: - kv  19:            tokenizer.ggml.unknown_token_id u32              = 3
-llama_model_loader: - kv  20:            tokenizer.ggml.padding_token_id u32              = 0
-llama_model_loader: - kv  21:               tokenizer.ggml.add_bos_token bool             = true
-llama_model_loader: - kv  22:               tokenizer.ggml.add_eos_token bool             = false
-llama_model_loader: - kv  23:                    tokenizer.chat_template str              = {{ bos_token }}{% if messages[0]['rol...
-llama_model_loader: - kv  24:            tokenizer.ggml.add_space_prefix bool             = false
-llama_model_loader: - kv  25:               general.quantization_version u32              = 2
+llama_model_loader: - kv  12:              gemma2.attn_logit_softcapping f32              = 50.000000
+llama_model_loader: - kv  13:             gemma2.final_logit_softcapping f32              = 30.000000
+llama_model_loader: - kv  14:                       tokenizer.ggml.model str              = llama
+llama_model_loader: - kv  15:                         tokenizer.ggml.pre str              = default
+llama_model_loader: - kv  16:                      tokenizer.ggml.tokens arr[str,256000]  = ["<pad>", "<eos>", "<bos>", "<unk>", ...
+llama_model_loader: - kv  17:                      tokenizer.ggml.scores arr[f32,256000]  = [-1000.000000, -1000.000000, -1000.00...
+llama_model_loader: - kv  18:                  tokenizer.ggml.token_type arr[i32,256000]  = [3, 3, 3, 3, 1, 1, 1, 1, 1, 1, 1, 1, ...
+llama_model_loader: - kv  19:                tokenizer.ggml.bos_token_id u32              = 2
+llama_model_loader: - kv  20:                tokenizer.ggml.eos_token_id u32              = 1
+llama_model_loader: - kv  21:            tokenizer.ggml.unknown_token_id u32              = 3
+llama_model_loader: - kv  22:            tokenizer.ggml.padding_token_id u32              = 0
+llama_model_loader: - kv  23:               tokenizer.ggml.add_bos_token bool             = true
+llama_model_loader: - kv  24:               tokenizer.ggml.add_eos_token bool             = false
+llama_model_loader: - kv  25:                    tokenizer.chat_template str              = {{ bos_token }}{% if messages[0]['rol...
+llama_model_loader: - kv  26:            tokenizer.ggml.add_space_prefix bool             = false
+llama_model_loader: - kv  27:               general.quantization_version u32              = 2
 llama_model_loader: - type  f32:  169 tensors
 llama_model_loader: - type q8_0:  295 tensors
 llm_load_vocab: special tokens cache size = 261
@@ -83,11 +85,10 @@ ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
 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 =    0.41 MiB
-llm_load_tensors: offloading 42 repeating layers to GPU
-llm_load_tensors: offloading non-repeating layers to GPU
-llm_load_tensors: offloaded 43/43 layers to GPU
-llm_load_tensors:        CPU buffer size =   929.69 MiB
-llm_load_tensors:      CUDA0 buffer size =  9366.12 MiB
+llm_load_tensors: offloading 11 repeating layers to GPU
+llm_load_tensors: offloaded 11/43 layers to GPU
+llm_load_tensors:        CPU buffer size =  9366.12 MiB
+llm_load_tensors:      CUDA0 buffer size =  2209.54 MiB
 ....................................................................................
 llama_new_context_with_model: n_ctx      = 512
 llama_new_context_with_model: n_batch    = 512
@@ -95,50 +96,51 @@ llama_new_context_with_model: n_ubatch   = 512
 llama_new_context_with_model: flash_attn = 0
 llama_new_context_with_model: freq_base  = 10000.0
 llama_new_context_with_model: freq_scale = 1
-llama_kv_cache_init:      CUDA0 KV buffer size =   168.00 MiB
+llama_kv_cache_init:  CUDA_Host KV buffer size =   124.00 MiB
+llama_kv_cache_init:      CUDA0 KV buffer size =    44.00 MiB
 llama_new_context_with_model: KV self size  =  168.00 MiB, K (f16):   84.00 MiB, V (f16):   84.00 MiB
 llama_new_context_with_model:  CUDA_Host  output buffer size =     0.98 MiB
-llama_new_context_with_model:      CUDA0 compute buffer size =   507.00 MiB
-llama_new_context_with_model:  CUDA_Host compute buffer size =     8.01 MiB
-llama_new_context_with_model: graph nodes  = 1561
-llama_new_context_with_model: graph splits = 2
+llama_new_context_with_model:      CUDA0 compute buffer size =  1436.69 MiB
+llama_new_context_with_model:  CUDA_Host compute buffer size =     9.01 MiB
+llama_new_context_with_model: graph nodes  = 1690
+llama_new_context_with_model: graph splits = 407
 
 system_info: n_threads = 25 / 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 97.236 ms
+compute_imatrix: tokenization took 91.303 ms
 compute_imatrix: computing over 128 chunks with batch_size 512
-compute_imatrix: 0.79 seconds per pass - ETA 1.67 minutes
-[1]25.5555,[2]11.3371,[3]9.6572,[4]12.0692,[5]13.4088,[6]14.1829,[7]15.8326,[8]17.3340,[9]17.9398,
+compute_imatrix: 1.34 seconds per pass - ETA 2.85 minutes
+[1]14.7486,[2]7.3963,[3]6.5677,[4]7.8490,[5]8.6193,[6]9.1006,[7]10.0154,[8]10.8556,[9]11.1957,
 save_imatrix: stored collected data after 10 chunks in gemma-2-9b-it-IMat-GGUF/imatrix.dat
-[10]15.2815,[11]14.8649,[12]16.5897,[13]17.6261,[14]17.7479,[15]19.0873,[16]19.1682,[17]19.2087,[18]19.9391,[19]19.7468,
+[10]9.8358,[11]9.5880,[12]10.6132,[13]11.2166,[14]11.3352,[15]12.0575,[16]12.1605,[17]12.2130,[18]12.6384,[19]12.5495,
 save_imatrix: stored collected data after 20 chunks in gemma-2-9b-it-IMat-GGUF/imatrix.dat
-[20]20.1653,[21]22.1505,[22]22.3124,[23]21.8212,[24]22.2676,[25]22.0063,[26]21.5170,[27]21.9266,[28]22.2449,[29]22.2217,
+[20]12.7233,[21]13.7801,[22]13.8033,[23]13.5919,[24]13.8287,[25]13.6927,[26]13.4495,[27]13.6978,[28]13.9355,[29]13.9524,
 save_imatrix: stored collected data after 30 chunks in gemma-2-9b-it-IMat-GGUF/imatrix.dat
-[30]22.6759,[31]20.7289,[32]19.6957,[33]18.9266,[34]18.2634,[35]17.8145,[36]17.9976,[37]18.5187,[38]18.8666,[39]19.1825,
+[30]14.1488,[31]13.1149,[32]12.5387,[33]12.1100,[34]11.7329,[35]11.4517,[36]11.6110,[37]11.9132,[38]12.0730,[39]12.2426,
 save_imatrix: stored collected data after 40 chunks in gemma-2-9b-it-IMat-GGUF/imatrix.dat
-[40]19.3533,[41]19.4193,[42]20.3610,[43]20.9211,[44]21.5207,[45]21.8640,[46]21.3869,[47]21.0216,[48]21.4183,[49]21.8035,
+[40]12.3500,[41]12.3930,[42]12.9499,[43]13.3055,[44]13.6998,[45]13.9306,[46]13.6677,[47]13.4581,[48]13.6644,[49]13.8789,
 save_imatrix: stored collected data after 50 chunks in gemma-2-9b-it-IMat-GGUF/imatrix.dat
-[50]21.4532,[51]21.2299,[52]21.3418,[53]21.7373,[54]22.2971,[55]22.7546,[56]22.9648,[57]22.9028,[58]22.8850,[59]22.5015,
+[50]13.6841,[51]13.5410,[52]13.6019,[53]13.8284,[54]14.1067,[55]14.3488,[56]14.4667,[57]14.4566,[58]14.4479,[59]14.2384,
 save_imatrix: stored collected data after 60 chunks in gemma-2-9b-it-IMat-GGUF/imatrix.dat
-[60]22.1941,[61]21.8891,[62]21.6051,[63]21.7991,[64]22.0817,[65]21.8311,[66]21.8910,[67]21.8394,[68]21.7671,[69]21.6403,
+[60]14.0794,[61]13.9048,[62]13.7419,[63]13.8516,[64]13.9902,[65]13.8558,[66]13.8803,[67]13.8491,[68]13.7963,[69]13.7287,
 save_imatrix: stored collected data after 70 chunks in gemma-2-9b-it-IMat-GGUF/imatrix.dat
-[70]21.5486,[71]21.5095,[72]21.4334,[73]21.5543,[74]21.4526,[75]21.2407,[76]21.2201,[77]21.2480,[78]21.1739,[79]21.0144,
+[70]13.6754,[71]13.6579,[72]13.6290,[73]13.6891,[74]13.6254,[75]13.5058,[76]13.4907,[77]13.5002,[78]13.4537,[79]13.3696,
 save_imatrix: stored collected data after 80 chunks in gemma-2-9b-it-IMat-GGUF/imatrix.dat
-[80]21.1184,[81]21.2594,[82]21.3021,[83]21.4948,[84]21.5654,[85]21.2021,[86]21.0964,[87]20.8221,[88]20.8641,[89]20.8093,
+[80]13.4245,[81]13.4999,[82]13.5207,[83]13.6156,[84]13.6529,[85]13.4393,[86]13.3795,[87]13.2302,[88]13.2605,[89]13.2322,
 save_imatrix: stored collected data after 90 chunks in gemma-2-9b-it-IMat-GGUF/imatrix.dat
-[90]20.9594,[91]20.8774,[92]20.7254,[93]20.5958,[94]20.4042,[95]20.3073,[96]20.1582,[97]20.0437,[98]19.8836,[99]19.9673,
+[90]13.2980,[91]13.2455,[92]13.1607,[93]13.0864,[94]12.9782,[95]12.9127,[96]12.8267,[97]12.7595,[98]12.6714,[99]12.7111,
 save_imatrix: stored collected data after 100 chunks in gemma-2-9b-it-IMat-GGUF/imatrix.dat
-[100]19.9773,[101]20.2196,[102]20.3460,[103]20.4376,[104]20.7373,[105]20.9656,[106]20.9967,[107]21.0194,[108]20.9206,[109]20.9610,
+[100]12.7194,[101]12.8597,[102]12.9495,[103]13.0106,[104]13.1816,[105]13.3131,[106]13.3254,[107]13.3336,[108]13.2762,[109]13.3038,
 save_imatrix: stored collected data after 110 chunks in gemma-2-9b-it-IMat-GGUF/imatrix.dat
-[110]20.7368,[111]20.5050,[112]20.2327,[113]20.3919,[114]20.4664,[115]20.4441,[116]20.4104,[117]20.5285,[118]20.5751,[119]20.6017,
+[110]13.1821,[111]13.0499,[112]12.8931,[113]12.9668,[114]13.0116,[115]12.9995,[116]12.9720,[117]13.0261,[118]13.0587,[119]13.0765,
 save_imatrix: stored collected data after 120 chunks in gemma-2-9b-it-IMat-GGUF/imatrix.dat
-[120]20.5870,[121]20.6010,[122]20.5378,[123]20.5777,[124]20.7099,[125]20.8429,[126]21.0201,[127]21.0849,[128]21.1542,
+[120]13.0687,[121]13.0658,[122]13.0268,[123]13.0554,[124]13.1495,[125]13.2406,[126]13.3502,[127]13.3960,[128]13.4523,
 save_imatrix: stored collected data after 128 chunks in gemma-2-9b-it-IMat-GGUF/imatrix.dat
 
-llama_print_timings:        load time =    2307.06 ms
+llama_print_timings:        load time =    1979.52 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 =   87159.32 ms / 65536 tokens (    1.33 ms per token,   751.91 tokens per second)
+llama_print_timings: prompt eval time =  150211.73 ms / 65536 tokens (    2.29 ms per token,   436.29 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 =   90163.64 ms / 65537 tokens
+llama_print_timings:       total time =  152551.51 ms / 65537 tokens
 
-Final estimate: PPL = 21.1542 +/- 0.50274
+Final estimate: PPL = 13.4523 +/- 0.26031