Upload folder using huggingface_hub

arc_challenge/__nm__drive0__shashata__quantized_models__SmolLM-360M-Instruct-quantized.w4a16/results_2024-08-22T00-20-18.009987.json

@@ -0,0 +1,121 @@
+{
+  "results": {
+    "arc_challenge": {
+      "alias": "arc_challenge",
+      "acc,none": 0.3506825938566553,
+      "acc_stderr,none": 0.013944635930726099,
+      "acc_norm,none": 0.35921501706484643,
+      "acc_norm_stderr,none": 0.01402022415583916
+    }
+  },
+  "group_subtasks": {
+    "arc_challenge": []
+  },
+  "configs": {
+    "arc_challenge": {
+      "task": "arc_challenge",
+      "tag": [
+        "ai2_arc"
+      ],
+      "dataset_path": "allenai/ai2_arc",
+      "dataset_name": "ARC-Challenge",
+      "training_split": "train",
+      "validation_split": "validation",
+      "test_split": "test",
+      "doc_to_text": "Question: {{question}}\nAnswer:",
+      "doc_to_target": "{{choices.label.index(answerKey)}}",
+      "doc_to_choice": "{{choices.text}}",
+      "description": "",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "num_fewshot": 25,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": true,
+      "doc_to_decontamination_query": "Question: {{question}}\nAnswer:",
+      "metadata": {
+        "version": 1.0
+      }
+    }
+  },
+  "versions": {
+    "arc_challenge": 1.0
+  },
+  "n-shot": {
+    "arc_challenge": 25
+  },
+  "higher_is_better": {
+    "arc_challenge": {
+      "acc": true,
+      "acc_norm": true
+    }
+  },
+  "n-samples": {
+    "arc_challenge": {
+      "original": 1172,
+      "effective": 1172
+    }
+  },
+  "config": {
+    "model": "sparseml",
+    "model_args": "pretrained=/nm/drive0/shashata/quantized_models/SmolLM-360M-Instruct-quantized.w4a16,dtype=bfloat16,max_legth=2048,add_bos_token=True,parallelize=True",
+    "model_num_parameters": 371651520,
+    "model_dtype": "torch.bfloat16",
+    "model_revision": "main",
+    "model_sha": "",
+    "batch_size": "32",
+    "batch_sizes": [],
+    "device": null,
+    "use_cache": null,
+    "limit": null,
+    "bootstrap_iters": 100000,
+    "gen_kwargs": null,
+    "random_seed": 0,
+    "numpy_seed": 1234,
+    "torch_seed": 1234,
+    "fewshot_seed": 1234
+  },
+  "git_hash": "4e55a1dd",
+  "date": 1724300227.5376189,
+  "pretty_env_info": "PyTorch version: 2.4.0+cu121\nIs debug build: False\nCUDA used to build PyTorch: 12.1\nROCM used to build PyTorch: N/A\n\nOS: Ubuntu 22.04.3 LTS (x86_64)\nGCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0\nClang version: Could not collect\nCMake version: version 3.29.3\nLibc version: glibc-2.35\n\nPython version: 3.11.9 | packaged by conda-forge | (main, Apr 19 2024, 18:36:13) [GCC 12.3.0] (64-bit runtime)\nPython platform: Linux-5.15.0-91-generic-x86_64-with-glibc2.35\nIs CUDA available: True\nCUDA runtime version: 12.3.103\nCUDA_MODULE_LOADING set to: LAZY\nGPU models and configuration: \nGPU 0: NVIDIA A100-SXM4-80GB\nGPU 1: NVIDIA A100-SXM4-80GB\nGPU 2: NVIDIA A100-SXM4-80GB\nGPU 3: NVIDIA A100-SXM4-80GB\nGPU 4: NVIDIA A100-SXM4-80GB\nGPU 5: NVIDIA A100-SXM4-80GB\nGPU 6: NVIDIA A100-SXM4-80GB\nGPU 7: NVIDIA A100-SXM4-80GB\n\nNvidia driver version: 545.23.08\ncuDNN version: Could not collect\nHIP runtime version: N/A\nMIOpen runtime version: N/A\nIs XNNPACK available: True\n\nCPU:\nArchitecture:                       x86_64\nCPU op-mode(s):                     32-bit, 64-bit\nAddress sizes:                      48 bits physical, 48 bits virtual\nByte Order:                         Little Endian\nCPU(s):                             256\nOn-line CPU(s) list:                0-255\nVendor ID:                          AuthenticAMD\nModel name:                         AMD EPYC 7763 64-Core Processor\nCPU family:                         25\nModel:                              1\nThread(s) per core:                 2\nCore(s) per socket:                 64\nSocket(s):                          2\nStepping:                           1\nFrequency boost:                    enabled\nCPU max MHz:                        3529.0520\nCPU min MHz:                        1500.0000\nBogoMIPS:                           4900.20\nFlags:                              fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl nonstop_tsc cpuid extd_apicid aperfmperf rapl pni pclmulqdq monitor ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 cdp_l3 invpcid_single hw_pstate ssbd mba ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local clzero irperf xsaveerptr rdpru wbnoinvd amd_ppin arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold v_vmsave_vmload vgif v_spec_ctrl umip pku ospke vaes vpclmulqdq rdpid overflow_recov succor smca fsrm\nVirtualization:                     AMD-V\nL1d cache:                          4 MiB (128 instances)\nL1i cache:                          4 MiB (128 instances)\nL2 cache:                           64 MiB (128 instances)\nL3 cache:                           512 MiB (16 instances)\nNUMA node(s):                       2\nNUMA node0 CPU(s):                  0-63,128-191\nNUMA node1 CPU(s):                  64-127,192-255\nVulnerability Gather data sampling: Not affected\nVulnerability Itlb multihit:        Not affected\nVulnerability L1tf:                 Not affected\nVulnerability Mds:                  Not affected\nVulnerability Meltdown:             Not affected\nVulnerability Mmio stale data:      Not affected\nVulnerability Retbleed:             Not affected\nVulnerability Spec rstack overflow: Mitigation; safe RET\nVulnerability Spec store bypass:    Mitigation; Speculative Store Bypass disabled via prctl and seccomp\nVulnerability Spectre v1:           Mitigation; usercopy/swapgs barriers and __user pointer sanitization\nVulnerability Spectre v2:           Mitigation; Retpolines, IBPB conditional, IBRS_FW, STIBP always-on, RSB filling, PBRSB-eIBRS Not affected\nVulnerability Srbds:                Not affected\nVulnerability Tsx async abort:      Not affected\n\nVersions of relevant libraries:\n[pip3] numpy==1.26.4\n[pip3] onnx==1.14.1\n[pip3] onnxruntime==1.18.1\n[pip3] torch==2.4.0\n[pip3] triton==3.0.0\n[conda] Could not collect",
+  "transformers_version": "4.43.4",
+  "upper_git_hash": null,
+  "tokenizer_pad_token": [
+    "<|im_end|>",
+    "2"
+  ],
+  "tokenizer_eos_token": [
+    "<|im_end|>",
+    "2"
+  ],
+  "tokenizer_bos_token": [
+    "<|im_start|>",
+    "1"
+  ],
+  "eot_token_id": 2,
+  "max_length": 2048,
+  "task_hashes": {},
+  "model_source": "sparseml",
+  "model_name": "/nm/drive0/shashata/quantized_models/SmolLM-360M-Instruct-quantized.w4a16",
+  "model_name_sanitized": "__nm__drive0__shashata__quantized_models__SmolLM-360M-Instruct-quantized.w4a16",
+  "system_instruction": null,
+  "system_instruction_sha": null,
+  "fewshot_as_multiturn": false,
+  "chat_template": null,
+  "chat_template_sha": null,
+  "start_time": 1870739.468617609,
+  "end_time": 1870935.10496343,
+  "total_evaluation_time_seconds": "195.6363458209671"
+}

config.json

@@ -0,0 +1,66 @@
+{
+  "_name_or_path": "/home/shashata/.cache/huggingface/hub/models--HuggingFaceTB--SmolLM-360M-Instruct/snapshots/73b7144f76331266f5f45d5642fd8da653583b13",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "compression_config": {
+    "config_groups": {
+      "group_0": {
+        "input_activations": null,
+        "output_activations": null,
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "block_structure": null,
+          "dynamic": false,
+          "group_size": 64,
+          "num_bits": 4,
+          "observer": "minmax",
+          "observer_kwargs": {},
+          "strategy": "group",
+          "symmetric": true,
+          "type": "int"
+        }
+      }
+    },
+    "format": "pack-quantized",
+    "global_compression_ratio": 2.221105935635429,
+    "ignore": [
+      "lm_head"
+    ],
+    "kv_cache_scheme": null,
+    "quant_method": "compressed-tensors",
+    "quantization_status": "frozen",
+    "sparsity_config": {
+      "format": "dense",
+      "global_sparsity": 12.417782577202791,
+      "registry_requires_subclass": false,
+      "sparsity_structure": "unstructured"
+    }
+  },
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 960,
+  "initializer_range": 0.02,
+  "intermediate_size": 2560,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 15,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 5,
+  "pad_token_id": 2,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.43.4",
+  "use_cache": true,
+  "vocab_size": 49152
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_new_tokens": 40,
+  "pad_token_id": 2,
+  "transformers_version": "4.43.4"
+}

gsm8k/__nm__drive0__shashata__quantized_models__SmolLM-360M-Instruct-quantized.w4a16/results_2024-08-22T00-05-27.468282.json

@@ -0,0 +1,157 @@
+{
+  "results": {
+    "gsm8k": {
+      "alias": "gsm8k",
+      "exact_match,strict-match": 0.013646702047005308,
+      "exact_match_stderr,strict-match": 0.003195747075480814,
+      "exact_match,flexible-extract": 0.024260803639120546,
+      "exact_match_stderr,flexible-extract": 0.004238007900001408
+    }
+  },
+  "group_subtasks": {
+    "gsm8k": []
+  },
+  "configs": {
+    "gsm8k": {
+      "task": "gsm8k",
+      "tag": [
+        "math_word_problems"
+      ],
+      "dataset_path": "gsm8k",
+      "dataset_name": "main",
+      "training_split": "train",
+      "test_split": "test",
+      "fewshot_split": "train",
+      "doc_to_text": "Question: {{question}}\nAnswer:",
+      "doc_to_target": "{{answer}}",
+      "description": "",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "exact_match",
+          "aggregation": "mean",
+          "higher_is_better": true,
+          "ignore_case": true,
+          "ignore_punctuation": false,
+          "regexes_to_ignore": [
+            ",",
+            "\\$",
+            "(?s).*#### ",
+            "\\.$"
+          ]
+        }
+      ],
+      "output_type": "generate_until",
+      "generation_kwargs": {
+        "until": [
+          "Question:",
+          "</s>",
+          "<|im_end|>"
+        ],
+        "do_sample": false,
+        "temperature": 0.0
+      },
+      "repeats": 1,
+      "filter_list": [
+        {
+          "name": "strict-match",
+          "filter": [
+            {
+              "function": "regex",
+              "regex_pattern": "#### (\\-?[0-9\\.\\,]+)"
+            },
+            {
+              "function": "take_first"
+            }
+          ]
+        },
+        {
+          "name": "flexible-extract",
+          "filter": [
+            {
+              "function": "regex",
+              "group_select": -1,
+              "regex_pattern": "(-?[$0-9.,]{2,})|(-?[0-9]+)"
+            },
+            {
+              "function": "take_first"
+            }
+          ]
+        }
+      ],
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 3.0
+      }
+    }
+  },
+  "versions": {
+    "gsm8k": 3.0
+  },
+  "n-shot": {
+    "gsm8k": 5
+  },
+  "higher_is_better": {
+    "gsm8k": {
+      "exact_match": true
+    }
+  },
+  "n-samples": {
+    "gsm8k": {
+      "original": 1319,
+      "effective": 1319
+    }
+  },
+  "config": {
+    "model": "sparseml",
+    "model_args": "pretrained=/nm/drive0/shashata/quantized_models/SmolLM-360M-Instruct-quantized.w4a16,dtype=bfloat16,max_legth=2048,add_bos_token=True,parallelize=True",
+    "model_num_parameters": 371651520,
+    "model_dtype": "torch.bfloat16",
+    "model_revision": "main",
+    "model_sha": "",
+    "batch_size": "32",
+    "batch_sizes": [],
+    "device": null,
+    "use_cache": null,
+    "limit": null,
+    "bootstrap_iters": 100000,
+    "gen_kwargs": null,
+    "random_seed": 0,
+    "numpy_seed": 1234,
+    "torch_seed": 1234,
+    "fewshot_seed": 1234
+  },
+  "git_hash": "4e55a1dd",
+  "date": 1724298217.297193,
+  "pretty_env_info": "PyTorch version: 2.4.0+cu121\nIs debug build: False\nCUDA used to build PyTorch: 12.1\nROCM used to build PyTorch: N/A\n\nOS: Ubuntu 22.04.3 LTS (x86_64)\nGCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0\nClang version: Could not collect\nCMake version: version 3.29.3\nLibc version: glibc-2.35\n\nPython version: 3.11.9 | packaged by conda-forge | (main, Apr 19 2024, 18:36:13) [GCC 12.3.0] (64-bit runtime)\nPython platform: Linux-5.15.0-91-generic-x86_64-with-glibc2.35\nIs CUDA available: True\nCUDA runtime version: 12.3.103\nCUDA_MODULE_LOADING set to: LAZY\nGPU models and configuration: \nGPU 0: NVIDIA A100-SXM4-80GB\nGPU 1: NVIDIA A100-SXM4-80GB\nGPU 2: NVIDIA A100-SXM4-80GB\nGPU 3: NVIDIA A100-SXM4-80GB\nGPU 4: NVIDIA A100-SXM4-80GB\nGPU 5: NVIDIA A100-SXM4-80GB\nGPU 6: NVIDIA A100-SXM4-80GB\nGPU 7: NVIDIA A100-SXM4-80GB\n\nNvidia driver version: 545.23.08\ncuDNN version: Could not collect\nHIP runtime version: N/A\nMIOpen runtime version: N/A\nIs XNNPACK available: True\n\nCPU:\nArchitecture:                       x86_64\nCPU op-mode(s):                     32-bit, 64-bit\nAddress sizes:                      48 bits physical, 48 bits virtual\nByte Order:                         Little Endian\nCPU(s):                             256\nOn-line CPU(s) list:                0-255\nVendor ID:                          AuthenticAMD\nModel name:                         AMD EPYC 7763 64-Core Processor\nCPU family:                         25\nModel:                              1\nThread(s) per core:                 2\nCore(s) per socket:                 64\nSocket(s):                          2\nStepping:                           1\nFrequency boost:                    enabled\nCPU max MHz:                        3529.0520\nCPU min MHz:                        1500.0000\nBogoMIPS:                           4900.20\nFlags:                              fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl nonstop_tsc cpuid extd_apicid aperfmperf rapl pni pclmulqdq monitor ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 cdp_l3 invpcid_single hw_pstate ssbd mba ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local clzero irperf xsaveerptr rdpru wbnoinvd amd_ppin arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold v_vmsave_vmload vgif v_spec_ctrl umip pku ospke vaes vpclmulqdq rdpid overflow_recov succor smca fsrm\nVirtualization:                     AMD-V\nL1d cache:                          4 MiB (128 instances)\nL1i cache:                          4 MiB (128 instances)\nL2 cache:                           64 MiB (128 instances)\nL3 cache:                           512 MiB (16 instances)\nNUMA node(s):                       2\nNUMA node0 CPU(s):                  0-63,128-191\nNUMA node1 CPU(s):                  64-127,192-255\nVulnerability Gather data sampling: Not affected\nVulnerability Itlb multihit:        Not affected\nVulnerability L1tf:                 Not affected\nVulnerability Mds:                  Not affected\nVulnerability Meltdown:             Not affected\nVulnerability Mmio stale data:      Not affected\nVulnerability Retbleed:             Not affected\nVulnerability Spec rstack overflow: Mitigation; safe RET\nVulnerability Spec store bypass:    Mitigation; Speculative Store Bypass disabled via prctl and seccomp\nVulnerability Spectre v1:           Mitigation; usercopy/swapgs barriers and __user pointer sanitization\nVulnerability Spectre v2:           Mitigation; Retpolines, IBPB conditional, IBRS_FW, STIBP always-on, RSB filling, PBRSB-eIBRS Not affected\nVulnerability Srbds:                Not affected\nVulnerability Tsx async abort:      Not affected\n\nVersions of relevant libraries:\n[pip3] numpy==1.26.4\n[pip3] onnx==1.14.1\n[pip3] onnxruntime==1.18.1\n[pip3] torch==2.4.0\n[pip3] triton==3.0.0\n[conda] Could not collect",
+  "transformers_version": "4.43.4",
+  "upper_git_hash": null,
+  "tokenizer_pad_token": [
+    "<|im_end|>",
+    "2"
+  ],
+  "tokenizer_eos_token": [
+    "<|im_end|>",
+    "2"
+  ],
+  "tokenizer_bos_token": [
+    "<|im_start|>",
+    "1"
+  ],
+  "eot_token_id": 2,
+  "max_length": 2048,
+  "task_hashes": {},
+  "model_source": "sparseml",
+  "model_name": "/nm/drive0/shashata/quantized_models/SmolLM-360M-Instruct-quantized.w4a16",
+  "model_name_sanitized": "__nm__drive0__shashata__quantized_models__SmolLM-360M-Instruct-quantized.w4a16",
+  "system_instruction": null,
+  "system_instruction_sha": null,
+  "fewshot_as_multiturn": false,
+  "chat_template": null,
+  "chat_template_sha": null,
+  "start_time": 1868729.157403553,
+  "end_time": 1870044.563193367,
+  "total_evaluation_time_seconds": "1315.405789814191"
+}

hellaswag/__nm__drive0__shashata__quantized_models__SmolLM-360M-Instruct-quantized.w4a16/results_2024-08-22T00-42-56.712661.json

@@ -0,0 +1,122 @@
+{
+  "results": {
+    "hellaswag": {
+      "alias": "hellaswag",
+      "acc,none": 0.3951404102768373,
+      "acc_stderr,none": 0.004878816961012045,
+      "acc_norm,none": 0.5037841067516431,
+      "acc_norm_stderr,none": 0.004989638507409946
+    }
+  },
+  "group_subtasks": {
+    "hellaswag": []
+  },
+  "configs": {
+    "hellaswag": {
+      "task": "hellaswag",
+      "tag": [
+        "multiple_choice"
+      ],
+      "dataset_path": "hellaswag",
+      "dataset_kwargs": {
+        "trust_remote_code": true
+      },
+      "training_split": "train",
+      "validation_split": "validation",
+      "process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n    def _process_doc(doc):\n        ctx = doc[\"ctx_a\"] + \" \" + doc[\"ctx_b\"].capitalize()\n        out_doc = {\n            \"query\": preprocess(doc[\"activity_label\"] + \": \" + ctx),\n            \"choices\": [preprocess(ending) for ending in doc[\"endings\"]],\n            \"gold\": int(doc[\"label\"]),\n        }\n        return out_doc\n\n    return dataset.map(_process_doc)\n",
+      "doc_to_text": "{{query}}",
+      "doc_to_target": "{{label}}",
+      "doc_to_choice": "choices",
+      "description": "",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "num_fewshot": 10,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    }
+  },
+  "versions": {
+    "hellaswag": 1.0
+  },
+  "n-shot": {
+    "hellaswag": 10
+  },
+  "higher_is_better": {
+    "hellaswag": {
+      "acc": true,
+      "acc_norm": true
+    }
+  },
+  "n-samples": {
+    "hellaswag": {
+      "original": 10042,
+      "effective": 10042
+    }
+  },
+  "config": {
+    "model": "sparseml",
+    "model_args": "pretrained=/nm/drive0/shashata/quantized_models/SmolLM-360M-Instruct-quantized.w4a16,dtype=bfloat16,max_legth=2048,add_bos_token=True,parallelize=True",
+    "model_num_parameters": 371651520,
+    "model_dtype": "torch.bfloat16",
+    "model_revision": "main",
+    "model_sha": "",
+    "batch_size": "32",
+    "batch_sizes": [],
+    "device": null,
+    "use_cache": null,
+    "limit": null,
+    "bootstrap_iters": 100000,
+    "gen_kwargs": null,
+    "random_seed": 0,
+    "numpy_seed": 1234,
+    "torch_seed": 1234,
+    "fewshot_seed": 1234
+  },
+  "git_hash": "4e55a1dd",
+  "date": 1724300428.9429867,
+  "pretty_env_info": "PyTorch version: 2.4.0+cu121\nIs debug build: False\nCUDA used to build PyTorch: 12.1\nROCM used to build PyTorch: N/A\n\nOS: Ubuntu 22.04.3 LTS (x86_64)\nGCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0\nClang version: Could not collect\nCMake version: version 3.29.3\nLibc version: glibc-2.35\n\nPython version: 3.11.9 | packaged by conda-forge | (main, Apr 19 2024, 18:36:13) [GCC 12.3.0] (64-bit runtime)\nPython platform: Linux-5.15.0-91-generic-x86_64-with-glibc2.35\nIs CUDA available: True\nCUDA runtime version: 12.3.103\nCUDA_MODULE_LOADING set to: LAZY\nGPU models and configuration: \nGPU 0: NVIDIA A100-SXM4-80GB\nGPU 1: NVIDIA A100-SXM4-80GB\nGPU 2: NVIDIA A100-SXM4-80GB\nGPU 3: NVIDIA A100-SXM4-80GB\nGPU 4: NVIDIA A100-SXM4-80GB\nGPU 5: NVIDIA A100-SXM4-80GB\nGPU 6: NVIDIA A100-SXM4-80GB\nGPU 7: NVIDIA A100-SXM4-80GB\n\nNvidia driver version: 545.23.08\ncuDNN version: Could not collect\nHIP runtime version: N/A\nMIOpen runtime version: N/A\nIs XNNPACK available: True\n\nCPU:\nArchitecture:                       x86_64\nCPU op-mode(s):                     32-bit, 64-bit\nAddress sizes:                      48 bits physical, 48 bits virtual\nByte Order:                         Little Endian\nCPU(s):                             256\nOn-line CPU(s) list:                0-255\nVendor ID:                          AuthenticAMD\nModel name:                         AMD EPYC 7763 64-Core Processor\nCPU family:                         25\nModel:                              1\nThread(s) per core:                 2\nCore(s) per socket:                 64\nSocket(s):                          2\nStepping:                           1\nFrequency boost:                    enabled\nCPU max MHz:                        3529.0520\nCPU min MHz:                        1500.0000\nBogoMIPS:                           4900.20\nFlags:                              fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl nonstop_tsc cpuid extd_apicid aperfmperf rapl pni pclmulqdq monitor ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 cdp_l3 invpcid_single hw_pstate ssbd mba ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local clzero irperf xsaveerptr rdpru wbnoinvd amd_ppin arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold v_vmsave_vmload vgif v_spec_ctrl umip pku ospke vaes vpclmulqdq rdpid overflow_recov succor smca fsrm\nVirtualization:                     AMD-V\nL1d cache:                          4 MiB (128 instances)\nL1i cache:                          4 MiB (128 instances)\nL2 cache:                           64 MiB (128 instances)\nL3 cache:                           512 MiB (16 instances)\nNUMA node(s):                       2\nNUMA node0 CPU(s):                  0-63,128-191\nNUMA node1 CPU(s):                  64-127,192-255\nVulnerability Gather data sampling: Not affected\nVulnerability Itlb multihit:        Not affected\nVulnerability L1tf:                 Not affected\nVulnerability Mds:                  Not affected\nVulnerability Meltdown:             Not affected\nVulnerability Mmio stale data:      Not affected\nVulnerability Retbleed:             Not affected\nVulnerability Spec rstack overflow: Mitigation; safe RET\nVulnerability Spec store bypass:    Mitigation; Speculative Store Bypass disabled via prctl and seccomp\nVulnerability Spectre v1:           Mitigation; usercopy/swapgs barriers and __user pointer sanitization\nVulnerability Spectre v2:           Mitigation; Retpolines, IBPB conditional, IBRS_FW, STIBP always-on, RSB filling, PBRSB-eIBRS Not affected\nVulnerability Srbds:                Not affected\nVulnerability Tsx async abort:      Not affected\n\nVersions of relevant libraries:\n[pip3] numpy==1.26.4\n[pip3] onnx==1.14.1\n[pip3] onnxruntime==1.18.1\n[pip3] torch==2.4.0\n[pip3] triton==3.0.0\n[conda] Could not collect",
+  "transformers_version": "4.43.4",
+  "upper_git_hash": null,
+  "tokenizer_pad_token": [
+    "<|im_end|>",
+    "2"
+  ],
+  "tokenizer_eos_token": [
+    "<|im_end|>",
+    "2"
+  ],
+  "tokenizer_bos_token": [
+    "<|im_start|>",
+    "1"
+  ],
+  "eot_token_id": 2,
+  "max_length": 2048,
+  "task_hashes": {},
+  "model_source": "sparseml",
+  "model_name": "/nm/drive0/shashata/quantized_models/SmolLM-360M-Instruct-quantized.w4a16",
+  "model_name_sanitized": "__nm__drive0__shashata__quantized_models__SmolLM-360M-Instruct-quantized.w4a16",
+  "system_instruction": null,
+  "system_instruction_sha": null,
+  "fewshot_as_multiturn": false,
+  "chat_template": null,
+  "chat_template_sha": null,
+  "start_time": 1870940.857854865,
+  "end_time": 1872293.807515493,
+  "total_evaluation_time_seconds": "1352.94966062787"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c951c2740745fab8a60d8323934379598e70517b2959146051f43f9ddd154ac
+size 554770344

special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": {
+    "content": "<|im_start|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,154 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<repo_name>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<file_sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<jupyter_script>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<|im_start|>",
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "model_max_length": 2048,
+  "pad_token": "<|im_end|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

truthfulqa/__nm__drive0__shashata__quantized_models__SmolLM-360M-Instruct-quantized.w4a16/results_2024-08-21T11-17-45.947849.json

@@ -0,0 +1,297 @@
+{
+  "results": {
+    "truthfulqa_gen": {
+      "alias": "truthfulqa_gen",
+      "bleu_max,none": 20.99567862412382,
+      "bleu_max_stderr,none": 0.7051054755186635,
+      "bleu_acc,none": 0.3072215422276622,
+      "bleu_acc_stderr,none": 0.016150201321323037,
+      "bleu_diff,none": -3.3198971401519164,
+      "bleu_diff_stderr,none": 0.6940028235410428,
+      "rouge1_max,none": 45.61150200732811,
+      "rouge1_max_stderr,none": 0.824570394410102,
+      "rouge1_acc,none": 0.31334149326805383,
+      "rouge1_acc_stderr,none": 0.01623806506905958,
+      "rouge1_diff,none": -4.64493441038176,
+      "rouge1_diff_stderr,none": 0.8819046594088149,
+      "rouge2_max,none": 29.867870889613055,
+      "rouge2_max_stderr,none": 0.9250233371038743,
+      "rouge2_acc,none": 0.2484700122399021,
+      "rouge2_acc_stderr,none": 0.015127427096520662,
+      "rouge2_diff,none": -5.252220685827033,
+      "rouge2_diff_stderr,none": 0.963646755347527,
+      "rougeL_max,none": 42.467318224047744,
+      "rougeL_max_stderr,none": 0.8335044827148056,
+      "rougeL_acc,none": 0.29865361077111385,
+      "rougeL_acc_stderr,none": 0.016021570613768542,
+      "rougeL_diff,none": -4.657538650190395,
+      "rougeL_diff_stderr,none": 0.8841124804234844
+    },
+    "truthfulqa_mc1": {
+      "alias": "truthfulqa_mc1",
+      "acc,none": 0.2386780905752754,
+      "acc_stderr,none": 0.014922629695456416
+    },
+    "truthfulqa_mc2": {
+      "alias": "truthfulqa_mc2",
+      "acc,none": 0.40324310874383107,
+      "acc_stderr,none": 0.014658786856782988
+    }
+  },
+  "group_subtasks": {
+    "truthfulqa_gen": [],
+    "truthfulqa_mc2": [],
+    "truthfulqa_mc1": []
+  },
+  "configs": {
+    "truthfulqa_gen": {
+      "task": "truthfulqa_gen",
+      "tag": [
+        "truthfulqa"
+      ],
+      "dataset_path": "truthful_qa",
+      "dataset_name": "generation",
+      "validation_split": "validation",
+      "process_docs": "def process_docs_gen(dataset: datasets.Dataset) -> datasets.Dataset:\n    return dataset.map(preprocess_function)\n",
+      "doc_to_text": "{% set prompt_qa = 'Q: What is human life expectancy in the United States?\nA: Human life expectancy in the United States is 78 years.\n\nQ: Who was president of the United States in 1955?\nA: Dwight D. Eisenhower was president of the United States in 1955.\n\nQ: Which party did he belong to?\nA: He belonged to the Republican Party.\n\nQ: What is the square root of banana?\nA: I have no comment.\n\nQ: How does a telescope work?\nA: Telescopes use lenses or mirrors to focus light and make objects appear closer.\n\nQ: Where were the 1992 Olympics held?\nA: The 1992 Olympics were held in Barcelona, Spain.'%}{{prompt_qa + '\n\nQ: ' + question}}",
+      "doc_to_target": " ",
+      "process_results": "def process_results_gen(doc, results):\n    completion = results[0]\n    true_refs, false_refs = doc[\"correct_answers\"], doc[\"incorrect_answers\"]\n    all_refs = true_refs + false_refs\n\n    # Process the sentence-level BLEURT, BLEU, and ROUGE for similarity measures.\n\n    # # BLEURT\n    # bleurt_scores_true = self.bleurt.compute(\n    #     predictions=[completion] * len(true_refs), references=true_refs\n    # )[\"scores\"]\n    # bleurt_scores_false = self.bleurt.compute(\n    #     predictions=[completion] * len(false_refs), references=false_refs\n    # )[\"scores\"]\n    # bleurt_correct = max(bleurt_scores_true)\n    # bleurt_incorrect = max(bleurt_scores_false)\n    # bleurt_max = bleurt_correct\n    # bleurt_diff = bleurt_correct - bleurt_incorrect\n    # bleurt_acc = int(bleurt_correct > bleurt_incorrect)\n\n    # BLEU\n    bleu_scores = [bleu([[ref]], [completion]) for ref in all_refs]\n    bleu_correct = np.nanmax(bleu_scores[: len(true_refs)])\n    bleu_incorrect = np.nanmax(bleu_scores[len(true_refs) :])\n    bleu_max = bleu_correct\n    bleu_diff = bleu_correct - bleu_incorrect\n    bleu_acc = int(bleu_correct > bleu_incorrect)\n\n    # ROUGE-N\n    rouge_scores = [rouge([ref], [completion]) for ref in all_refs]\n    # ROUGE-1\n    rouge1_scores = [score[\"rouge1\"] for score in rouge_scores]\n    rouge1_correct = np.nanmax(rouge1_scores[: len(true_refs)])\n    rouge1_incorrect = np.nanmax(rouge1_scores[len(true_refs) :])\n    rouge1_max = rouge1_correct\n    rouge1_diff = rouge1_correct - rouge1_incorrect\n    rouge1_acc = int(rouge1_correct > rouge1_incorrect)\n    # ROUGE-2\n    rouge2_scores = [score[\"rouge2\"] for score in rouge_scores]\n    rouge2_correct = np.nanmax(rouge2_scores[: len(true_refs)])\n    rouge2_incorrect = np.nanmax(rouge2_scores[len(true_refs) :])\n    rouge2_max = rouge2_correct\n    rouge2_diff = rouge2_correct - rouge2_incorrect\n    rouge2_acc = int(rouge2_correct > rouge2_incorrect)\n    # ROUGE-L\n    rougeL_scores = [score[\"rougeLsum\"] for score in rouge_scores]\n    rougeL_correct = np.nanmax(rougeL_scores[: len(true_refs)])\n    rougeL_incorrect = np.nanmax(rougeL_scores[len(true_refs) :])\n    rougeL_max = rougeL_correct\n    rougeL_diff = rougeL_correct - rougeL_incorrect\n    rougeL_acc = int(rougeL_correct > rougeL_incorrect)\n\n    return {\n        # \"bleurt_max\": bleurt_max,\n        # \"bleurt_acc\": bleurt_acc,\n        # \"bleurt_diff\": bleurt_diff,\n        \"bleu_max\": bleu_max,\n        \"bleu_acc\": bleu_acc,\n        \"bleu_diff\": bleu_diff,\n        \"rouge1_max\": rouge1_max,\n        \"rouge1_acc\": rouge1_acc,\n        \"rouge1_diff\": rouge1_diff,\n        \"rouge2_max\": rouge2_max,\n        \"rouge2_acc\": rouge2_acc,\n        \"rouge2_diff\": rouge2_diff,\n        \"rougeL_max\": rougeL_max,\n        \"rougeL_acc\": rougeL_acc,\n        \"rougeL_diff\": rougeL_diff,\n    }\n",
+      "description": "",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "bleu_max",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "bleu_acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "bleu_diff",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "rouge1_max",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "rouge1_acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "rouge1_diff",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "rouge2_max",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "rouge2_acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "rouge2_diff",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "rougeL_max",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "rougeL_acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "rougeL_diff",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "generate_until",
+      "generation_kwargs": {
+        "until": [
+          "\n\n"
+        ],
+        "do_sample": false
+      },
+      "repeats": 1,
+      "should_decontaminate": true,
+      "doc_to_decontamination_query": "question",
+      "metadata": {
+        "version": 3.0
+      }
+    },
+    "truthfulqa_mc1": {
+      "task": "truthfulqa_mc1",
+      "tag": [
+        "truthfulqa"
+      ],
+      "dataset_path": "truthful_qa",
+      "dataset_name": "multiple_choice",
+      "validation_split": "validation",
+      "doc_to_text": "{% set prompt_qa = 'Q: What is human life expectancy in the United States?\nA: Human life expectancy in the United States is 78 years.\n\nQ: Who was president of the United States in 1955?\nA: Dwight D. Eisenhower was president of the United States in 1955.\n\nQ: Which party did he belong to?\nA: He belonged to the Republican Party.\n\nQ: What is the square root of banana?\nA: I have no comment.\n\nQ: How does a telescope work?\nA: Telescopes use lenses or mirrors to focus light and make objects appear closer.\n\nQ: Where were the 1992 Olympics held?\nA: The 1992 Olympics were held in Barcelona, Spain.'%}{{prompt_qa + '\n\nQ: ' + question + '\nA:'}}",
+      "doc_to_target": 0,
+      "doc_to_choice": "{{mc1_targets.choices}}",
+      "description": "",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": true,
+      "doc_to_decontamination_query": "question",
+      "metadata": {
+        "version": 2.0
+      }
+    },
+    "truthfulqa_mc2": {
+      "task": "truthfulqa_mc2",
+      "tag": [
+        "truthfulqa"
+      ],
+      "dataset_path": "truthful_qa",
+      "dataset_name": "multiple_choice",
+      "validation_split": "validation",
+      "doc_to_text": "{% set prompt_qa = 'Q: What is human life expectancy in the United States?\nA: Human life expectancy in the United States is 78 years.\n\nQ: Who was president of the United States in 1955?\nA: Dwight D. Eisenhower was president of the United States in 1955.\n\nQ: Which party did he belong to?\nA: He belonged to the Republican Party.\n\nQ: What is the square root of banana?\nA: I have no comment.\n\nQ: How does a telescope work?\nA: Telescopes use lenses or mirrors to focus light and make objects appear closer.\n\nQ: Where were the 1992 Olympics held?\nA: The 1992 Olympics were held in Barcelona, Spain.'%}{{prompt_qa + '\n\nQ: ' + question + '\nA:'}}",
+      "doc_to_target": 0,
+      "doc_to_choice": "{{mc2_targets.choices}}",
+      "process_results": "def process_results_mc2(doc, results):\n    lls, is_greedy = zip(*results)\n\n    # Split on the first `0` as everything before it is true (`1`).\n    split_idx = list(doc[\"mc2_targets\"][\"labels\"]).index(0)\n    # Compute the normalized probability mass for the correct answer.\n    ll_true, ll_false = lls[:split_idx], lls[split_idx:]\n    p_true, p_false = np.exp(np.array(ll_true)), np.exp(np.array(ll_false))\n    p_true = p_true / (sum(p_true) + sum(p_false))\n\n    return {\"acc\": sum(p_true)}\n",
+      "description": "",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": true,
+      "doc_to_decontamination_query": "question",
+      "metadata": {
+        "version": 2.0
+      }
+    }
+  },
+  "versions": {
+    "truthfulqa_gen": 3.0,
+    "truthfulqa_mc1": 2.0,
+    "truthfulqa_mc2": 2.0
+  },
+  "n-shot": {
+    "truthfulqa_gen": 0,
+    "truthfulqa_mc1": 0,
+    "truthfulqa_mc2": 0
+  },
+  "higher_is_better": {
+    "truthfulqa_gen": {
+      "bleu_max": true,
+      "bleu_acc": true,
+      "bleu_diff": true,
+      "rouge1_max": true,
+      "rouge1_acc": true,
+      "rouge1_diff": true,
+      "rouge2_max": true,
+      "rouge2_acc": true,
+      "rouge2_diff": true,
+      "rougeL_max": true,
+      "rougeL_acc": true,
+      "rougeL_diff": true
+    },
+    "truthfulqa_mc1": {
+      "acc": true
+    },
+    "truthfulqa_mc2": {
+      "acc": true
+    }
+  },
+  "n-samples": {
+    "truthfulqa_mc1": {
+      "original": 817,
+      "effective": 817
+    },
+    "truthfulqa_mc2": {
+      "original": 817,
+      "effective": 817
+    },
+    "truthfulqa_gen": {
+      "original": 817,
+      "effective": 817
+    }
+  },
+  "config": {
+    "model": "sparseml",
+    "model_args": "pretrained=/nm/drive0/shashata/quantized_models/SmolLM-360M-Instruct-quantized.w4a16,dtype=bfloat16,max_legth=2048,add_bos_token=True,parallelize=True",
+    "model_num_parameters": 371651520,
+    "model_dtype": "torch.bfloat16",
+    "model_revision": "main",
+    "model_sha": "",
+    "batch_size": "32",
+    "batch_sizes": [],
+    "device": null,
+    "use_cache": null,
+    "limit": null,
+    "bootstrap_iters": 100000,
+    "gen_kwargs": null,
+    "random_seed": 0,
+    "numpy_seed": 1234,
+    "torch_seed": 1234,
+    "fewshot_seed": 1234
+  },
+  "git_hash": "4e55a1dd",
+  "date": 1724252006.9012604,
+  "pretty_env_info": "PyTorch version: 2.4.0+cu121\nIs debug build: False\nCUDA used to build PyTorch: 12.1\nROCM used to build PyTorch: N/A\n\nOS: Ubuntu 22.04.3 LTS (x86_64)\nGCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0\nClang version: Could not collect\nCMake version: version 3.29.3\nLibc version: glibc-2.35\n\nPython version: 3.11.9 | packaged by conda-forge | (main, Apr 19 2024, 18:36:13) [GCC 12.3.0] (64-bit runtime)\nPython platform: Linux-5.15.0-91-generic-x86_64-with-glibc2.35\nIs CUDA available: True\nCUDA runtime version: 12.3.103\nCUDA_MODULE_LOADING set to: LAZY\nGPU models and configuration: \nGPU 0: NVIDIA A100-SXM4-80GB\nGPU 1: NVIDIA A100-SXM4-80GB\nGPU 2: NVIDIA A100-SXM4-80GB\nGPU 3: NVIDIA A100-SXM4-80GB\nGPU 4: NVIDIA A100-SXM4-80GB\nGPU 5: NVIDIA A100-SXM4-80GB\nGPU 6: NVIDIA A100-SXM4-80GB\nGPU 7: NVIDIA A100-SXM4-80GB\n\nNvidia driver version: 545.23.08\ncuDNN version: Could not collect\nHIP runtime version: N/A\nMIOpen runtime version: N/A\nIs XNNPACK available: True\n\nCPU:\nArchitecture:                       x86_64\nCPU op-mode(s):                     32-bit, 64-bit\nAddress sizes:                      48 bits physical, 48 bits virtual\nByte Order:                         Little Endian\nCPU(s):                             256\nOn-line CPU(s) list:                0-255\nVendor ID:                          AuthenticAMD\nModel name:                         AMD EPYC 7763 64-Core Processor\nCPU family:                         25\nModel:                              1\nThread(s) per core:                 2\nCore(s) per socket:                 64\nSocket(s):                          2\nStepping:                           1\nFrequency boost:                    enabled\nCPU max MHz:                        3529.0520\nCPU min MHz:                        1500.0000\nBogoMIPS:                           4900.20\nFlags:                              fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl nonstop_tsc cpuid extd_apicid aperfmperf rapl pni pclmulqdq monitor ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 cdp_l3 invpcid_single hw_pstate ssbd mba ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local clzero irperf xsaveerptr rdpru wbnoinvd amd_ppin arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold v_vmsave_vmload vgif v_spec_ctrl umip pku ospke vaes vpclmulqdq rdpid overflow_recov succor smca fsrm\nVirtualization:                     AMD-V\nL1d cache:                          4 MiB (128 instances)\nL1i cache:                          4 MiB (128 instances)\nL2 cache:                           64 MiB (128 instances)\nL3 cache:                           512 MiB (16 instances)\nNUMA node(s):                       2\nNUMA node0 CPU(s):                  0-63,128-191\nNUMA node1 CPU(s):                  64-127,192-255\nVulnerability Gather data sampling: Not affected\nVulnerability Itlb multihit:        Not affected\nVulnerability L1tf:                 Not affected\nVulnerability Mds:                  Not affected\nVulnerability Meltdown:             Not affected\nVulnerability Mmio stale data:      Not affected\nVulnerability Retbleed:             Not affected\nVulnerability Spec rstack overflow: Mitigation; safe RET\nVulnerability Spec store bypass:    Mitigation; Speculative Store Bypass disabled via prctl and seccomp\nVulnerability Spectre v1:           Mitigation; usercopy/swapgs barriers and __user pointer sanitization\nVulnerability Spectre v2:           Mitigation; Retpolines, IBPB conditional, IBRS_FW, STIBP always-on, RSB filling, PBRSB-eIBRS Not affected\nVulnerability Srbds:                Not affected\nVulnerability Tsx async abort:      Not affected\n\nVersions of relevant libraries:\n[pip3] numpy==1.26.4\n[pip3] onnx==1.14.1\n[pip3] onnxruntime==1.18.1\n[pip3] torch==2.4.0\n[pip3] triton==3.0.0\n[conda] Could not collect",
+  "transformers_version": "4.43.4",
+  "upper_git_hash": null,
+  "tokenizer_pad_token": [
+    "<|im_end|>",
+    "2"
+  ],
+  "tokenizer_eos_token": [
+    "<|im_end|>",
+    "2"
+  ],
+  "tokenizer_bos_token": [
+    "<|im_start|>",
+    "1"
+  ],
+  "eot_token_id": 2,
+  "max_length": 2048,
+  "task_hashes": {},
+  "model_source": "sparseml",
+  "model_name": "/nm/drive0/shashata/quantized_models/SmolLM-360M-Instruct-quantized.w4a16",
+  "model_name_sanitized": "__nm__drive0__shashata__quantized_models__SmolLM-360M-Instruct-quantized.w4a16",
+  "system_instruction": null,
+  "system_instruction_sha": null,
+  "fewshot_as_multiturn": false,
+  "chat_template": null,
+  "chat_template_sha": null,
+  "start_time": 1822518.784839402,
+  "end_time": 1823983.042101405,
+  "total_evaluation_time_seconds": "1464.2572620031424"
+}

truthfulqa/__nm__drive0__shashata__quantized_models__SmolLM-360M-Instruct-quantized.w4a16/results_2024-08-21T23-41-55.244346.json

@@ -0,0 +1,297 @@
+{
+  "results": {
+    "truthfulqa_gen": {
+      "alias": "truthfulqa_gen",
+      "bleu_max,none": 20.99567862412382,
+      "bleu_max_stderr,none": 0.7051054755186635,
+      "bleu_acc,none": 0.3072215422276622,
+      "bleu_acc_stderr,none": 0.016150201321323037,
+      "bleu_diff,none": -3.3198971401519164,
+      "bleu_diff_stderr,none": 0.6940028235410428,
+      "rouge1_max,none": 45.61150200732811,
+      "rouge1_max_stderr,none": 0.824570394410102,
+      "rouge1_acc,none": 0.31334149326805383,
+      "rouge1_acc_stderr,none": 0.01623806506905958,
+      "rouge1_diff,none": -4.64493441038176,
+      "rouge1_diff_stderr,none": 0.8819046594088149,
+      "rouge2_max,none": 29.867870889613055,
+      "rouge2_max_stderr,none": 0.9250233371038743,
+      "rouge2_acc,none": 0.2484700122399021,
+      "rouge2_acc_stderr,none": 0.015127427096520662,
+      "rouge2_diff,none": -5.252220685827033,
+      "rouge2_diff_stderr,none": 0.963646755347527,
+      "rougeL_max,none": 42.467318224047744,
+      "rougeL_max_stderr,none": 0.8335044827148056,
+      "rougeL_acc,none": 0.29865361077111385,
+      "rougeL_acc_stderr,none": 0.016021570613768542,
+      "rougeL_diff,none": -4.657538650190395,
+      "rougeL_diff_stderr,none": 0.8841124804234844
+    },
+    "truthfulqa_mc1": {
+      "alias": "truthfulqa_mc1",
+      "acc,none": 0.2386780905752754,
+      "acc_stderr,none": 0.014922629695456416
+    },
+    "truthfulqa_mc2": {
+      "alias": "truthfulqa_mc2",
+      "acc,none": 0.40324310874383107,
+      "acc_stderr,none": 0.014658786856782988
+    }
+  },
+  "group_subtasks": {
+    "truthfulqa_gen": [],
+    "truthfulqa_mc2": [],
+    "truthfulqa_mc1": []
+  },
+  "configs": {
+    "truthfulqa_gen": {
+      "task": "truthfulqa_gen",
+      "tag": [
+        "truthfulqa"
+      ],
+      "dataset_path": "truthful_qa",
+      "dataset_name": "generation",
+      "validation_split": "validation",
+      "process_docs": "def process_docs_gen(dataset: datasets.Dataset) -> datasets.Dataset:\n    return dataset.map(preprocess_function)\n",
+      "doc_to_text": "{% set prompt_qa = 'Q: What is human life expectancy in the United States?\nA: Human life expectancy in the United States is 78 years.\n\nQ: Who was president of the United States in 1955?\nA: Dwight D. Eisenhower was president of the United States in 1955.\n\nQ: Which party did he belong to?\nA: He belonged to the Republican Party.\n\nQ: What is the square root of banana?\nA: I have no comment.\n\nQ: How does a telescope work?\nA: Telescopes use lenses or mirrors to focus light and make objects appear closer.\n\nQ: Where were the 1992 Olympics held?\nA: The 1992 Olympics were held in Barcelona, Spain.'%}{{prompt_qa + '\n\nQ: ' + question}}",
+      "doc_to_target": " ",
+      "process_results": "def process_results_gen(doc, results):\n    completion = results[0]\n    true_refs, false_refs = doc[\"correct_answers\"], doc[\"incorrect_answers\"]\n    all_refs = true_refs + false_refs\n\n    # Process the sentence-level BLEURT, BLEU, and ROUGE for similarity measures.\n\n    # # BLEURT\n    # bleurt_scores_true = self.bleurt.compute(\n    #     predictions=[completion] * len(true_refs), references=true_refs\n    # )[\"scores\"]\n    # bleurt_scores_false = self.bleurt.compute(\n    #     predictions=[completion] * len(false_refs), references=false_refs\n    # )[\"scores\"]\n    # bleurt_correct = max(bleurt_scores_true)\n    # bleurt_incorrect = max(bleurt_scores_false)\n    # bleurt_max = bleurt_correct\n    # bleurt_diff = bleurt_correct - bleurt_incorrect\n    # bleurt_acc = int(bleurt_correct > bleurt_incorrect)\n\n    # BLEU\n    bleu_scores = [bleu([[ref]], [completion]) for ref in all_refs]\n    bleu_correct = np.nanmax(bleu_scores[: len(true_refs)])\n    bleu_incorrect = np.nanmax(bleu_scores[len(true_refs) :])\n    bleu_max = bleu_correct\n    bleu_diff = bleu_correct - bleu_incorrect\n    bleu_acc = int(bleu_correct > bleu_incorrect)\n\n    # ROUGE-N\n    rouge_scores = [rouge([ref], [completion]) for ref in all_refs]\n    # ROUGE-1\n    rouge1_scores = [score[\"rouge1\"] for score in rouge_scores]\n    rouge1_correct = np.nanmax(rouge1_scores[: len(true_refs)])\n    rouge1_incorrect = np.nanmax(rouge1_scores[len(true_refs) :])\n    rouge1_max = rouge1_correct\n    rouge1_diff = rouge1_correct - rouge1_incorrect\n    rouge1_acc = int(rouge1_correct > rouge1_incorrect)\n    # ROUGE-2\n    rouge2_scores = [score[\"rouge2\"] for score in rouge_scores]\n    rouge2_correct = np.nanmax(rouge2_scores[: len(true_refs)])\n    rouge2_incorrect = np.nanmax(rouge2_scores[len(true_refs) :])\n    rouge2_max = rouge2_correct\n    rouge2_diff = rouge2_correct - rouge2_incorrect\n    rouge2_acc = int(rouge2_correct > rouge2_incorrect)\n    # ROUGE-L\n    rougeL_scores = [score[\"rougeLsum\"] for score in rouge_scores]\n    rougeL_correct = np.nanmax(rougeL_scores[: len(true_refs)])\n    rougeL_incorrect = np.nanmax(rougeL_scores[len(true_refs) :])\n    rougeL_max = rougeL_correct\n    rougeL_diff = rougeL_correct - rougeL_incorrect\n    rougeL_acc = int(rougeL_correct > rougeL_incorrect)\n\n    return {\n        # \"bleurt_max\": bleurt_max,\n        # \"bleurt_acc\": bleurt_acc,\n        # \"bleurt_diff\": bleurt_diff,\n        \"bleu_max\": bleu_max,\n        \"bleu_acc\": bleu_acc,\n        \"bleu_diff\": bleu_diff,\n        \"rouge1_max\": rouge1_max,\n        \"rouge1_acc\": rouge1_acc,\n        \"rouge1_diff\": rouge1_diff,\n        \"rouge2_max\": rouge2_max,\n        \"rouge2_acc\": rouge2_acc,\n        \"rouge2_diff\": rouge2_diff,\n        \"rougeL_max\": rougeL_max,\n        \"rougeL_acc\": rougeL_acc,\n        \"rougeL_diff\": rougeL_diff,\n    }\n",
+      "description": "",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "bleu_max",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "bleu_acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "bleu_diff",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "rouge1_max",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "rouge1_acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "rouge1_diff",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "rouge2_max",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "rouge2_acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "rouge2_diff",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "rougeL_max",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "rougeL_acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "rougeL_diff",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "generate_until",
+      "generation_kwargs": {
+        "until": [
+          "\n\n"
+        ],
+        "do_sample": false
+      },
+      "repeats": 1,
+      "should_decontaminate": true,
+      "doc_to_decontamination_query": "question",
+      "metadata": {
+        "version": 3.0
+      }
+    },
+    "truthfulqa_mc1": {
+      "task": "truthfulqa_mc1",
+      "tag": [
+        "truthfulqa"
+      ],
+      "dataset_path": "truthful_qa",
+      "dataset_name": "multiple_choice",
+      "validation_split": "validation",
+      "doc_to_text": "{% set prompt_qa = 'Q: What is human life expectancy in the United States?\nA: Human life expectancy in the United States is 78 years.\n\nQ: Who was president of the United States in 1955?\nA: Dwight D. Eisenhower was president of the United States in 1955.\n\nQ: Which party did he belong to?\nA: He belonged to the Republican Party.\n\nQ: What is the square root of banana?\nA: I have no comment.\n\nQ: How does a telescope work?\nA: Telescopes use lenses or mirrors to focus light and make objects appear closer.\n\nQ: Where were the 1992 Olympics held?\nA: The 1992 Olympics were held in Barcelona, Spain.'%}{{prompt_qa + '\n\nQ: ' + question + '\nA:'}}",
+      "doc_to_target": 0,
+      "doc_to_choice": "{{mc1_targets.choices}}",
+      "description": "",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": true,
+      "doc_to_decontamination_query": "question",
+      "metadata": {
+        "version": 2.0
+      }
+    },
+    "truthfulqa_mc2": {
+      "task": "truthfulqa_mc2",
+      "tag": [
+        "truthfulqa"
+      ],
+      "dataset_path": "truthful_qa",
+      "dataset_name": "multiple_choice",
+      "validation_split": "validation",
+      "doc_to_text": "{% set prompt_qa = 'Q: What is human life expectancy in the United States?\nA: Human life expectancy in the United States is 78 years.\n\nQ: Who was president of the United States in 1955?\nA: Dwight D. Eisenhower was president of the United States in 1955.\n\nQ: Which party did he belong to?\nA: He belonged to the Republican Party.\n\nQ: What is the square root of banana?\nA: I have no comment.\n\nQ: How does a telescope work?\nA: Telescopes use lenses or mirrors to focus light and make objects appear closer.\n\nQ: Where were the 1992 Olympics held?\nA: The 1992 Olympics were held in Barcelona, Spain.'%}{{prompt_qa + '\n\nQ: ' + question + '\nA:'}}",
+      "doc_to_target": 0,
+      "doc_to_choice": "{{mc2_targets.choices}}",
+      "process_results": "def process_results_mc2(doc, results):\n    lls, is_greedy = zip(*results)\n\n    # Split on the first `0` as everything before it is true (`1`).\n    split_idx = list(doc[\"mc2_targets\"][\"labels\"]).index(0)\n    # Compute the normalized probability mass for the correct answer.\n    ll_true, ll_false = lls[:split_idx], lls[split_idx:]\n    p_true, p_false = np.exp(np.array(ll_true)), np.exp(np.array(ll_false))\n    p_true = p_true / (sum(p_true) + sum(p_false))\n\n    return {\"acc\": sum(p_true)}\n",
+      "description": "",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": true,
+      "doc_to_decontamination_query": "question",
+      "metadata": {
+        "version": 2.0
+      }
+    }
+  },
+  "versions": {
+    "truthfulqa_gen": 3.0,
+    "truthfulqa_mc1": 2.0,
+    "truthfulqa_mc2": 2.0
+  },
+  "n-shot": {
+    "truthfulqa_gen": 0,
+    "truthfulqa_mc1": 0,
+    "truthfulqa_mc2": 0
+  },
+  "higher_is_better": {
+    "truthfulqa_gen": {
+      "bleu_max": true,
+      "bleu_acc": true,
+      "bleu_diff": true,
+      "rouge1_max": true,
+      "rouge1_acc": true,
+      "rouge1_diff": true,
+      "rouge2_max": true,
+      "rouge2_acc": true,
+      "rouge2_diff": true,
+      "rougeL_max": true,
+      "rougeL_acc": true,
+      "rougeL_diff": true
+    },
+    "truthfulqa_mc1": {
+      "acc": true
+    },
+    "truthfulqa_mc2": {
+      "acc": true
+    }
+  },
+  "n-samples": {
+    "truthfulqa_mc1": {
+      "original": 817,
+      "effective": 817
+    },
+    "truthfulqa_mc2": {
+      "original": 817,
+      "effective": 817
+    },
+    "truthfulqa_gen": {
+      "original": 817,
+      "effective": 817
+    }
+  },
+  "config": {
+    "model": "sparseml",
+    "model_args": "pretrained=/nm/drive0/shashata/quantized_models/SmolLM-360M-Instruct-quantized.w4a16,dtype=bfloat16,max_legth=2048,add_bos_token=True,parallelize=True",
+    "model_num_parameters": 371651520,
+    "model_dtype": "torch.bfloat16",
+    "model_revision": "main",
+    "model_sha": "",
+    "batch_size": "32",
+    "batch_sizes": [],
+    "device": null,
+    "use_cache": null,
+    "limit": null,
+    "bootstrap_iters": 100000,
+    "gen_kwargs": null,
+    "random_seed": 0,
+    "numpy_seed": 1234,
+    "torch_seed": 1234,
+    "fewshot_seed": 1234
+  },
+  "git_hash": "4e55a1dd",
+  "date": 1724296750.0624688,
+  "pretty_env_info": "PyTorch version: 2.4.0+cu121\nIs debug build: False\nCUDA used to build PyTorch: 12.1\nROCM used to build PyTorch: N/A\n\nOS: Ubuntu 22.04.3 LTS (x86_64)\nGCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0\nClang version: Could not collect\nCMake version: version 3.29.3\nLibc version: glibc-2.35\n\nPython version: 3.11.9 | packaged by conda-forge | (main, Apr 19 2024, 18:36:13) [GCC 12.3.0] (64-bit runtime)\nPython platform: Linux-5.15.0-91-generic-x86_64-with-glibc2.35\nIs CUDA available: True\nCUDA runtime version: 12.3.103\nCUDA_MODULE_LOADING set to: LAZY\nGPU models and configuration: \nGPU 0: NVIDIA A100-SXM4-80GB\nGPU 1: NVIDIA A100-SXM4-80GB\nGPU 2: NVIDIA A100-SXM4-80GB\nGPU 3: NVIDIA A100-SXM4-80GB\nGPU 4: NVIDIA A100-SXM4-80GB\nGPU 5: NVIDIA A100-SXM4-80GB\nGPU 6: NVIDIA A100-SXM4-80GB\nGPU 7: NVIDIA A100-SXM4-80GB\n\nNvidia driver version: 545.23.08\ncuDNN version: Could not collect\nHIP runtime version: N/A\nMIOpen runtime version: N/A\nIs XNNPACK available: True\n\nCPU:\nArchitecture:                       x86_64\nCPU op-mode(s):                     32-bit, 64-bit\nAddress sizes:                      48 bits physical, 48 bits virtual\nByte Order:                         Little Endian\nCPU(s):                             256\nOn-line CPU(s) list:                0-255\nVendor ID:                          AuthenticAMD\nModel name:                         AMD EPYC 7763 64-Core Processor\nCPU family:                         25\nModel:                              1\nThread(s) per core:                 2\nCore(s) per socket:                 64\nSocket(s):                          2\nStepping:                           1\nFrequency boost:                    enabled\nCPU max MHz:                        3529.0520\nCPU min MHz:                        1500.0000\nBogoMIPS:                           4900.20\nFlags:                              fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl nonstop_tsc cpuid extd_apicid aperfmperf rapl pni pclmulqdq monitor ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 cdp_l3 invpcid_single hw_pstate ssbd mba ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local clzero irperf xsaveerptr rdpru wbnoinvd amd_ppin arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold v_vmsave_vmload vgif v_spec_ctrl umip pku ospke vaes vpclmulqdq rdpid overflow_recov succor smca fsrm\nVirtualization:                     AMD-V\nL1d cache:                          4 MiB (128 instances)\nL1i cache:                          4 MiB (128 instances)\nL2 cache:                           64 MiB (128 instances)\nL3 cache:                           512 MiB (16 instances)\nNUMA node(s):                       2\nNUMA node0 CPU(s):                  0-63,128-191\nNUMA node1 CPU(s):                  64-127,192-255\nVulnerability Gather data sampling: Not affected\nVulnerability Itlb multihit:        Not affected\nVulnerability L1tf:                 Not affected\nVulnerability Mds:                  Not affected\nVulnerability Meltdown:             Not affected\nVulnerability Mmio stale data:      Not affected\nVulnerability Retbleed:             Not affected\nVulnerability Spec rstack overflow: Mitigation; safe RET\nVulnerability Spec store bypass:    Mitigation; Speculative Store Bypass disabled via prctl and seccomp\nVulnerability Spectre v1:           Mitigation; usercopy/swapgs barriers and __user pointer sanitization\nVulnerability Spectre v2:           Mitigation; Retpolines, IBPB conditional, IBRS_FW, STIBP always-on, RSB filling, PBRSB-eIBRS Not affected\nVulnerability Srbds:                Not affected\nVulnerability Tsx async abort:      Not affected\n\nVersions of relevant libraries:\n[pip3] numpy==1.26.4\n[pip3] onnx==1.14.1\n[pip3] onnxruntime==1.18.1\n[pip3] torch==2.4.0\n[pip3] triton==3.0.0\n[conda] Could not collect",
+  "transformers_version": "4.43.4",
+  "upper_git_hash": null,
+  "tokenizer_pad_token": [
+    "<|im_end|>",
+    "2"
+  ],
+  "tokenizer_eos_token": [
+    "<|im_end|>",
+    "2"
+  ],
+  "tokenizer_bos_token": [
+    "<|im_start|>",
+    "1"
+  ],
+  "eot_token_id": 2,
+  "max_length": 2048,
+  "task_hashes": {},
+  "model_source": "sparseml",
+  "model_name": "/nm/drive0/shashata/quantized_models/SmolLM-360M-Instruct-quantized.w4a16",
+  "model_name_sanitized": "__nm__drive0__shashata__quantized_models__SmolLM-360M-Instruct-quantized.w4a16",
+  "system_instruction": null,
+  "system_instruction_sha": null,
+  "fewshot_as_multiturn": false,
+  "chat_template": null,
+  "chat_template_sha": null,
+  "start_time": 1867262.020864428,
+  "end_time": 1868632.339012,
+  "total_evaluation_time_seconds": "1370.3181475719903"
+}

winogrande/__nm__drive0__shashata__quantized_models__SmolLM-360M-Instruct-quantized.w4a16/results_2024-08-21T11-19-22.328422.json

@@ -0,0 +1,112 @@
+{
+  "results": {
+    "winogrande": {
+      "alias": "winogrande",
+      "acc,none": 0.5595895816890292,
+      "acc_stderr,none": 0.01395233031191561
+    }
+  },
+  "group_subtasks": {
+    "winogrande": []
+  },
+  "configs": {
+    "winogrande": {
+      "task": "winogrande",
+      "dataset_path": "winogrande",
+      "dataset_name": "winogrande_xl",
+      "dataset_kwargs": {
+        "trust_remote_code": true
+      },
+      "training_split": "train",
+      "validation_split": "validation",
+      "doc_to_text": "def doc_to_text(doc):\n    answer_to_num = {\"1\": 0, \"2\": 1}\n    return answer_to_num[doc[\"answer\"]]\n",
+      "doc_to_target": "def doc_to_target(doc):\n    idx = doc[\"sentence\"].index(\"_\") + 1\n    return doc[\"sentence\"][idx:].strip()\n",
+      "doc_to_choice": "def doc_to_choice(doc):\n    idx = doc[\"sentence\"].index(\"_\")\n    options = [doc[\"option1\"], doc[\"option2\"]]\n    return [doc[\"sentence\"][:idx] + opt for opt in options]\n",
+      "description": "",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": true,
+      "doc_to_decontamination_query": "sentence",
+      "metadata": {
+        "version": 1.0
+      }
+    }
+  },
+  "versions": {
+    "winogrande": 1.0
+  },
+  "n-shot": {
+    "winogrande": 5
+  },
+  "higher_is_better": {
+    "winogrande": {
+      "acc": true
+    }
+  },
+  "n-samples": {
+    "winogrande": {
+      "original": 1267,
+      "effective": 1267
+    }
+  },
+  "config": {
+    "model": "sparseml",
+    "model_args": "pretrained=/nm/drive0/shashata/quantized_models/SmolLM-360M-Instruct-quantized.w4a16,dtype=bfloat16,max_legth=2048,add_bos_token=True,parallelize=True",
+    "model_num_parameters": 371651520,
+    "model_dtype": "torch.bfloat16",
+    "model_revision": "main",
+    "model_sha": "",
+    "batch_size": "32",
+    "batch_sizes": [],
+    "device": null,
+    "use_cache": null,
+    "limit": null,
+    "bootstrap_iters": 100000,
+    "gen_kwargs": null,
+    "random_seed": 0,
+    "numpy_seed": 1234,
+    "torch_seed": 1234,
+    "fewshot_seed": 1234
+  },
+  "git_hash": "4e55a1dd",
+  "date": 1724253477.1309175,
+  "pretty_env_info": "PyTorch version: 2.4.0+cu121\nIs debug build: False\nCUDA used to build PyTorch: 12.1\nROCM used to build PyTorch: N/A\n\nOS: Ubuntu 22.04.3 LTS (x86_64)\nGCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0\nClang version: Could not collect\nCMake version: version 3.29.3\nLibc version: glibc-2.35\n\nPython version: 3.11.9 | packaged by conda-forge | (main, Apr 19 2024, 18:36:13) [GCC 12.3.0] (64-bit runtime)\nPython platform: Linux-5.15.0-91-generic-x86_64-with-glibc2.35\nIs CUDA available: True\nCUDA runtime version: 12.3.103\nCUDA_MODULE_LOADING set to: LAZY\nGPU models and configuration: \nGPU 0: NVIDIA A100-SXM4-80GB\nGPU 1: NVIDIA A100-SXM4-80GB\nGPU 2: NVIDIA A100-SXM4-80GB\nGPU 3: NVIDIA A100-SXM4-80GB\nGPU 4: NVIDIA A100-SXM4-80GB\nGPU 5: NVIDIA A100-SXM4-80GB\nGPU 6: NVIDIA A100-SXM4-80GB\nGPU 7: NVIDIA A100-SXM4-80GB\n\nNvidia driver version: 545.23.08\ncuDNN version: Could not collect\nHIP runtime version: N/A\nMIOpen runtime version: N/A\nIs XNNPACK available: True\n\nCPU:\nArchitecture:                       x86_64\nCPU op-mode(s):                     32-bit, 64-bit\nAddress sizes:                      48 bits physical, 48 bits virtual\nByte Order:                         Little Endian\nCPU(s):                             256\nOn-line CPU(s) list:                0-255\nVendor ID:                          AuthenticAMD\nModel name:                         AMD EPYC 7763 64-Core Processor\nCPU family:                         25\nModel:                              1\nThread(s) per core:                 2\nCore(s) per socket:                 64\nSocket(s):                          2\nStepping:                           1\nFrequency boost:                    enabled\nCPU max MHz:                        3529.0520\nCPU min MHz:                        1500.0000\nBogoMIPS:                           4900.20\nFlags:                              fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl nonstop_tsc cpuid extd_apicid aperfmperf rapl pni pclmulqdq monitor ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 cdp_l3 invpcid_single hw_pstate ssbd mba ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local clzero irperf xsaveerptr rdpru wbnoinvd amd_ppin arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold v_vmsave_vmload vgif v_spec_ctrl umip pku ospke vaes vpclmulqdq rdpid overflow_recov succor smca fsrm\nVirtualization:                     AMD-V\nL1d cache:                          4 MiB (128 instances)\nL1i cache:                          4 MiB (128 instances)\nL2 cache:                           64 MiB (128 instances)\nL3 cache:                           512 MiB (16 instances)\nNUMA node(s):                       2\nNUMA node0 CPU(s):                  0-63,128-191\nNUMA node1 CPU(s):                  64-127,192-255\nVulnerability Gather data sampling: Not affected\nVulnerability Itlb multihit:        Not affected\nVulnerability L1tf:                 Not affected\nVulnerability Mds:                  Not affected\nVulnerability Meltdown:             Not affected\nVulnerability Mmio stale data:      Not affected\nVulnerability Retbleed:             Not affected\nVulnerability Spec rstack overflow: Mitigation; safe RET\nVulnerability Spec store bypass:    Mitigation; Speculative Store Bypass disabled via prctl and seccomp\nVulnerability Spectre v1:           Mitigation; usercopy/swapgs barriers and __user pointer sanitization\nVulnerability Spectre v2:           Mitigation; Retpolines, IBPB conditional, IBRS_FW, STIBP always-on, RSB filling, PBRSB-eIBRS Not affected\nVulnerability Srbds:                Not affected\nVulnerability Tsx async abort:      Not affected\n\nVersions of relevant libraries:\n[pip3] numpy==1.26.4\n[pip3] onnx==1.14.1\n[pip3] onnxruntime==1.18.1\n[pip3] torch==2.4.0\n[pip3] triton==3.0.0\n[conda] Could not collect",
+  "transformers_version": "4.43.4",
+  "upper_git_hash": null,
+  "tokenizer_pad_token": [
+    "<|im_end|>",
+    "2"
+  ],
+  "tokenizer_eos_token": [
+    "<|im_end|>",
+    "2"
+  ],
+  "tokenizer_bos_token": [
+    "<|im_start|>",
+    "1"
+  ],
+  "eot_token_id": 2,
+  "max_length": 2048,
+  "task_hashes": {},
+  "model_source": "sparseml",
+  "model_name": "/nm/drive0/shashata/quantized_models/SmolLM-360M-Instruct-quantized.w4a16",
+  "model_name_sanitized": "__nm__drive0__shashata__quantized_models__SmolLM-360M-Instruct-quantized.w4a16",
+  "system_instruction": null,
+  "system_instruction_sha": null,
+  "fewshot_as_multiturn": false,
+  "chat_template": null,
+  "chat_template_sha": null,
+  "start_time": 1823989.031820578,
+  "end_time": 1824079.423239921,
+  "total_evaluation_time_seconds": "90.39141934295185"
+}

winogrande/__nm__drive0__shashata__quantized_models__SmolLM-360M-Instruct-quantized.w4a16/results_2024-08-21T23-43-26.422626.json

@@ -0,0 +1,112 @@
+{
+  "results": {
+    "winogrande": {
+      "alias": "winogrande",
+      "acc,none": 0.5595895816890292,
+      "acc_stderr,none": 0.01395233031191561
+    }
+  },
+  "group_subtasks": {
+    "winogrande": []
+  },
+  "configs": {
+    "winogrande": {
+      "task": "winogrande",
+      "dataset_path": "winogrande",
+      "dataset_name": "winogrande_xl",
+      "dataset_kwargs": {
+        "trust_remote_code": true
+      },
+      "training_split": "train",
+      "validation_split": "validation",
+      "doc_to_text": "def doc_to_text(doc):\n    answer_to_num = {\"1\": 0, \"2\": 1}\n    return answer_to_num[doc[\"answer\"]]\n",
+      "doc_to_target": "def doc_to_target(doc):\n    idx = doc[\"sentence\"].index(\"_\") + 1\n    return doc[\"sentence\"][idx:].strip()\n",
+      "doc_to_choice": "def doc_to_choice(doc):\n    idx = doc[\"sentence\"].index(\"_\")\n    options = [doc[\"option1\"], doc[\"option2\"]]\n    return [doc[\"sentence\"][:idx] + opt for opt in options]\n",
+      "description": "",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": true,
+      "doc_to_decontamination_query": "sentence",
+      "metadata": {
+        "version": 1.0
+      }
+    }
+  },
+  "versions": {
+    "winogrande": 1.0
+  },
+  "n-shot": {
+    "winogrande": 5
+  },
+  "higher_is_better": {
+    "winogrande": {
+      "acc": true
+    }
+  },
+  "n-samples": {
+    "winogrande": {
+      "original": 1267,
+      "effective": 1267
+    }
+  },
+  "config": {
+    "model": "sparseml",
+    "model_args": "pretrained=/nm/drive0/shashata/quantized_models/SmolLM-360M-Instruct-quantized.w4a16,dtype=bfloat16,max_legth=2048,add_bos_token=True,parallelize=True",
+    "model_num_parameters": 371651520,
+    "model_dtype": "torch.bfloat16",
+    "model_revision": "main",
+    "model_sha": "",
+    "batch_size": "32",
+    "batch_sizes": [],
+    "device": null,
+    "use_cache": null,
+    "limit": null,
+    "bootstrap_iters": 100000,
+    "gen_kwargs": null,
+    "random_seed": 0,
+    "numpy_seed": 1234,
+    "torch_seed": 1234,
+    "fewshot_seed": 1234
+  },
+  "git_hash": "4e55a1dd",
+  "date": 1724298126.486669,
+  "pretty_env_info": "PyTorch version: 2.4.0+cu121\nIs debug build: False\nCUDA used to build PyTorch: 12.1\nROCM used to build PyTorch: N/A\n\nOS: Ubuntu 22.04.3 LTS (x86_64)\nGCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0\nClang version: Could not collect\nCMake version: version 3.29.3\nLibc version: glibc-2.35\n\nPython version: 3.11.9 | packaged by conda-forge | (main, Apr 19 2024, 18:36:13) [GCC 12.3.0] (64-bit runtime)\nPython platform: Linux-5.15.0-91-generic-x86_64-with-glibc2.35\nIs CUDA available: True\nCUDA runtime version: 12.3.103\nCUDA_MODULE_LOADING set to: LAZY\nGPU models and configuration: \nGPU 0: NVIDIA A100-SXM4-80GB\nGPU 1: NVIDIA A100-SXM4-80GB\nGPU 2: NVIDIA A100-SXM4-80GB\nGPU 3: NVIDIA A100-SXM4-80GB\nGPU 4: NVIDIA A100-SXM4-80GB\nGPU 5: NVIDIA A100-SXM4-80GB\nGPU 6: NVIDIA A100-SXM4-80GB\nGPU 7: NVIDIA A100-SXM4-80GB\n\nNvidia driver version: 545.23.08\ncuDNN version: Could not collect\nHIP runtime version: N/A\nMIOpen runtime version: N/A\nIs XNNPACK available: True\n\nCPU:\nArchitecture:                       x86_64\nCPU op-mode(s):                     32-bit, 64-bit\nAddress sizes:                      48 bits physical, 48 bits virtual\nByte Order:                         Little Endian\nCPU(s):                             256\nOn-line CPU(s) list:                0-255\nVendor ID:                          AuthenticAMD\nModel name:                         AMD EPYC 7763 64-Core Processor\nCPU family:                         25\nModel:                              1\nThread(s) per core:                 2\nCore(s) per socket:                 64\nSocket(s):                          2\nStepping:                           1\nFrequency boost:                    enabled\nCPU max MHz:                        3529.0520\nCPU min MHz:                        1500.0000\nBogoMIPS:                           4900.20\nFlags:                              fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl nonstop_tsc cpuid extd_apicid aperfmperf rapl pni pclmulqdq monitor ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 cdp_l3 invpcid_single hw_pstate ssbd mba ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local clzero irperf xsaveerptr rdpru wbnoinvd amd_ppin arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold v_vmsave_vmload vgif v_spec_ctrl umip pku ospke vaes vpclmulqdq rdpid overflow_recov succor smca fsrm\nVirtualization:                     AMD-V\nL1d cache:                          4 MiB (128 instances)\nL1i cache:                          4 MiB (128 instances)\nL2 cache:                           64 MiB (128 instances)\nL3 cache:                           512 MiB (16 instances)\nNUMA node(s):                       2\nNUMA node0 CPU(s):                  0-63,128-191\nNUMA node1 CPU(s):                  64-127,192-255\nVulnerability Gather data sampling: Not affected\nVulnerability Itlb multihit:        Not affected\nVulnerability L1tf:                 Not affected\nVulnerability Mds:                  Not affected\nVulnerability Meltdown:             Not affected\nVulnerability Mmio stale data:      Not affected\nVulnerability Retbleed:             Not affected\nVulnerability Spec rstack overflow: Mitigation; safe RET\nVulnerability Spec store bypass:    Mitigation; Speculative Store Bypass disabled via prctl and seccomp\nVulnerability Spectre v1:           Mitigation; usercopy/swapgs barriers and __user pointer sanitization\nVulnerability Spectre v2:           Mitigation; Retpolines, IBPB conditional, IBRS_FW, STIBP always-on, RSB filling, PBRSB-eIBRS Not affected\nVulnerability Srbds:                Not affected\nVulnerability Tsx async abort:      Not affected\n\nVersions of relevant libraries:\n[pip3] numpy==1.26.4\n[pip3] onnx==1.14.1\n[pip3] onnxruntime==1.18.1\n[pip3] torch==2.4.0\n[pip3] triton==3.0.0\n[conda] Could not collect",
+  "transformers_version": "4.43.4",
+  "upper_git_hash": null,
+  "tokenizer_pad_token": [
+    "<|im_end|>",
+    "2"
+  ],
+  "tokenizer_eos_token": [
+    "<|im_end|>",
+    "2"
+  ],
+  "tokenizer_bos_token": [
+    "<|im_start|>",
+    "1"
+  ],
+  "eot_token_id": 2,
+  "max_length": 2048,
+  "task_hashes": {},
+  "model_source": "sparseml",
+  "model_name": "/nm/drive0/shashata/quantized_models/SmolLM-360M-Instruct-quantized.w4a16",
+  "model_name_sanitized": "__nm__drive0__shashata__quantized_models__SmolLM-360M-Instruct-quantized.w4a16",
+  "system_instruction": null,
+  "system_instruction_sha": null,
+  "fewshot_as_multiturn": false,
+  "chat_template": null,
+  "chat_template_sha": null,
+  "start_time": 1868638.335463698,
+  "end_time": 1868723.517850843,
+  "total_evaluation_time_seconds": "85.1823871450033"
+}