Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,22 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+llmtf_eval_k0/daru_treewayextractive.jsonl filter=lfs diff=lfs merge=lfs -text
+llmtf_eval_k0/darumeru_ruMMLU.jsonl filter=lfs diff=lfs merge=lfs -text
+llmtf_eval_k0/darumeru_ruTiE.jsonl filter=lfs diff=lfs merge=lfs -text
+llmtf_eval_k0/nlpcoreteam_enMMLU.jsonl filter=lfs diff=lfs merge=lfs -text
+llmtf_eval_k0/nlpcoreteam_ruMMLU.jsonl filter=lfs diff=lfs merge=lfs -text
+llmtf_eval_k1/daru_treewayextractive.jsonl filter=lfs diff=lfs merge=lfs -text
+llmtf_eval_k1/darumeru_ruMMLU.jsonl filter=lfs diff=lfs merge=lfs -text
+llmtf_eval_k1/darumeru_ruTiE.jsonl filter=lfs diff=lfs merge=lfs -text
+llmtf_eval_k1/nlpcoreteam_enMMLU.jsonl filter=lfs diff=lfs merge=lfs -text
+llmtf_eval_k1/nlpcoreteam_ruMMLU.jsonl filter=lfs diff=lfs merge=lfs -text
+llmtf_eval_k5/daru_treewayabstractive.jsonl filter=lfs diff=lfs merge=lfs -text
+llmtf_eval_k5/daru_treewayextractive.jsonl filter=lfs diff=lfs merge=lfs -text
+llmtf_eval_k5/darumeru_MultiQ.jsonl filter=lfs diff=lfs merge=lfs -text
+llmtf_eval_k5/darumeru_USE.jsonl filter=lfs diff=lfs merge=lfs -text
+llmtf_eval_k5/darumeru_ruMMLU.jsonl filter=lfs diff=lfs merge=lfs -text
+llmtf_eval_k5/darumeru_ruTiE.jsonl filter=lfs diff=lfs merge=lfs -text
+llmtf_eval_k5/nlpcoreteam_enMMLU.jsonl filter=lfs diff=lfs merge=lfs -text
+llmtf_eval_k5/nlpcoreteam_ruMMLU.jsonl filter=lfs diff=lfs merge=lfs -text
+llmtf_eval_k5/russiannlp_rucola_custom.jsonl filter=lfs diff=lfs merge=lfs -text

llmtf_eval_k0/daru_treewayabstractive_params.jsonl

@@ -0,0 +1,60 @@
+{
+    "custom_generation_config": null,
+    "model_params": {
+        "model_name_or_path": "Qwen/Qwen2-7B-Instruct",
+        "generation_config": {
+            "do_sample": true,
+            "eos_token_id": [
+                151645,
+                198,
+                271
+            ],
+            "max_length": 32768,
+            "max_new_tokens": 512,
+            "pad_token_id": 151643,
+            "stop_strings": [
+                "\n",
+                "\n\n"
+            ],
+            "temperature": 0.1,
+            "top_k": 40,
+            "top_p": 0.9,
+            "transformers_version": "4.38.2",
+            "trust_remote_code": [
+                false
+            ]
+        },
+        "conversation_template": {
+            "system_prompt": "",
+            "system_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
+            "user_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
+            "bot_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
+            "bot_message_template_incomplete": "<|im_start|>{role}\n{content}",
+            "user_role": "user",
+            "bot_role": "assistant",
+            "system_role": "system",
+            "global_prefix": "",
+            "suffix": "<|im_start|>assistant\n",
+            "add_special_tokens": false,
+            "eos_token": "<|im_end|>"
+        },
+        "load_in_8bit": false,
+        "torch_dtype": "auto",
+        "use_flash_attention_2": true,
+        "device_map": "cuda:0",
+        "use_fast_tokenizer": true,
+        "leading_space": false,
+        "space_token": null,
+        "trust_remote_code": [
+            false
+        ],
+        "max_model_len": 32768
+    },
+    "task_params": {
+        "max_len": 4000,
+        "few_shot_count": 0,
+        "batch_size": 1,
+        "max_sample_per_dataset": 500,
+        "method": "generate"
+    }
+}

llmtf_eval_k0/daru_treewayabstractive_total.jsonl

@@ -0,0 +1,8 @@
+{
+    "task_name": "daru/treewayabstractive",
+    "results": {
+        "rouge1": 0.2813082731366044,
+        "rouge2": 0.10129515826302848
+    },
+    "leaderboard_result": 0.19130171569981644
+}

llmtf_eval_k0/daru_treewayextractive.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ca290a5c85ddb32a4da9e675786e739d29e8edcb2723e9650859f391b53ca42
+size 2139832235

llmtf_eval_k0/daru_treewayextractive_params.jsonl

@@ -0,0 +1,55 @@
+{
+    "custom_generation_config": null,
+    "model_params": {
+        "model_name_or_path": "Qwen/Qwen2-7B-Instruct",
+        "generation_config": {
+            "do_sample": true,
+            "eos_token_id": [
+                151645
+            ],
+            "max_length": 32768,
+            "max_new_tokens": 1,
+            "pad_token_id": 151643,
+            "stop_strings": [],
+            "temperature": 0.1,
+            "top_k": 40,
+            "top_p": 0.9,
+            "transformers_version": "4.38.2",
+            "trust_remote_code": [
+                false
+            ]
+        },
+        "conversation_template": {
+            "system_prompt": "",
+            "system_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
+            "user_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
+            "bot_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
+            "bot_message_template_incomplete": "<|im_start|>{role}\n{content}",
+            "user_role": "user",
+            "bot_role": "assistant",
+            "system_role": "system",
+            "global_prefix": "",
+            "suffix": "<|im_start|>assistant\n",
+            "add_special_tokens": false,
+            "eos_token": "<|im_end|>"
+        },
+        "load_in_8bit": false,
+        "torch_dtype": "auto",
+        "use_flash_attention_2": true,
+        "device_map": "cuda:0",
+        "use_fast_tokenizer": true,
+        "leading_space": false,
+        "space_token": null,
+        "trust_remote_code": [
+            false
+        ],
+        "max_model_len": 32768
+    },
+    "task_params": {
+        "max_len": 4000,
+        "few_shot_count": 0,
+        "batch_size": 1,
+        "max_sample_per_dataset": 500,
+        "method": "calculate_logsoftmax"
+    }
+}

llmtf_eval_k0/daru_treewayextractive_total.jsonl

@@ -0,0 +1,7 @@
+{
+    "task_name": "daru/treewayextractive",
+    "results": {
+        "r-prec": 0.3917012265512266
+    },
+    "leaderboard_result": 0.3917012265512266
+}

llmtf_eval_k0/darumeru_MultiQ_params.jsonl

@@ -0,0 +1,60 @@
+{
+    "custom_generation_config": null,
+    "model_params": {
+        "model_name_or_path": "Qwen/Qwen2-7B-Instruct",
+        "generation_config": {
+            "do_sample": true,
+            "eos_token_id": [
+                151645,
+                198,
+                271
+            ],
+            "max_length": 32768,
+            "max_new_tokens": 64,
+            "pad_token_id": 151643,
+            "stop_strings": [
+                "\n",
+                "\n\n"
+            ],
+            "temperature": 0.1,
+            "top_k": 40,
+            "top_p": 0.9,
+            "transformers_version": "4.38.2",
+            "trust_remote_code": [
+                false
+            ]
+        },
+        "conversation_template": {
+            "system_prompt": "",
+            "system_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
+            "user_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
+            "bot_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
+            "bot_message_template_incomplete": "<|im_start|>{role}\n{content}",
+            "user_role": "user",
+            "bot_role": "assistant",
+            "system_role": "system",
+            "global_prefix": "",
+            "suffix": "<|im_start|>assistant\n",
+            "add_special_tokens": false,
+            "eos_token": "<|im_end|>"
+        },
+        "load_in_8bit": false,
+        "torch_dtype": "auto",
+        "use_flash_attention_2": true,
+        "device_map": "cuda:0",
+        "use_fast_tokenizer": true,
+        "leading_space": false,
+        "space_token": null,
+        "trust_remote_code": [
+            false
+        ],
+        "max_model_len": 32768
+    },
+    "task_params": {
+        "max_len": 4000,
+        "few_shot_count": 0,
+        "batch_size": 1,
+        "max_sample_per_dataset": 10000000000000,
+        "method": "generate"
+    }
+}

llmtf_eval_k0/darumeru_MultiQ_total.jsonl

@@ -0,0 +1,8 @@
+{
+    "task_name": "darumeru/MultiQ",
+    "results": {
+        "f1": 0.23082049162131107,
+        "em": 0.13288718929254303
+    },
+    "leaderboard_result": 0.18185384045692704
+}

llmtf_eval_k0/darumeru_PARus_params.jsonl

@@ -0,0 +1,60 @@
+{
+    "custom_generation_config": null,
+    "model_params": {
+        "model_name_or_path": "Qwen/Qwen2-7B-Instruct",
+        "generation_config": {
+            "do_sample": true,
+            "eos_token_id": [
+                151645,
+                198,
+                271
+            ],
+            "max_length": 32768,
+            "max_new_tokens": 64,
+            "pad_token_id": 151643,
+            "stop_strings": [
+                "\n",
+                "\n\n"
+            ],
+            "temperature": 0.1,
+            "top_k": 40,
+            "top_p": 0.9,
+            "transformers_version": "4.38.2",
+            "trust_remote_code": [
+                false
+            ]
+        },
+        "conversation_template": {
+            "system_prompt": "",
+            "system_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
+            "user_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
+            "bot_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
+            "bot_message_template_incomplete": "<|im_start|>{role}\n{content}",
+            "user_role": "user",
+            "bot_role": "assistant",
+            "system_role": "system",
+            "global_prefix": "",
+            "suffix": "<|im_start|>assistant\n",
+            "add_special_tokens": false,
+            "eos_token": "<|im_end|>"
+        },
+        "load_in_8bit": false,
+        "torch_dtype": "auto",
+        "use_flash_attention_2": true,
+        "device_map": "cuda:0",
+        "use_fast_tokenizer": true,
+        "leading_space": false,
+        "space_token": null,
+        "trust_remote_code": [
+            false
+        ],
+        "max_model_len": 32768
+    },
+    "task_params": {
+        "max_len": 4000,
+        "few_shot_count": 0,
+        "batch_size": 1,
+        "max_sample_per_dataset": 10000000000000,
+        "method": "calculate_tokens_proba"
+    }
+}

llmtf_eval_k0/darumeru_PARus_total.jsonl

@@ -0,0 +1,7 @@
+{
+    "task_name": "darumeru/PARus",
+    "results": {
+        "acc": 0.79
+    },
+    "leaderboard_result": 0.79
+}

llmtf_eval_k0/darumeru_RCB_params.jsonl

@@ -0,0 +1,60 @@
+{
+    "custom_generation_config": null,
+    "model_params": {
+        "model_name_or_path": "Qwen/Qwen2-7B-Instruct",
+        "generation_config": {
+            "do_sample": true,
+            "eos_token_id": [
+                151645,
+                198,
+                271
+            ],
+            "max_length": 32768,
+            "max_new_tokens": 64,
+            "pad_token_id": 151643,
+            "stop_strings": [
+                "\n",
+                "\n\n"
+            ],
+            "temperature": 0.1,
+            "top_k": 40,
+            "top_p": 0.9,
+            "transformers_version": "4.38.2",
+            "trust_remote_code": [
+                false
+            ]
+        },
+        "conversation_template": {
+            "system_prompt": "",
+            "system_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
+            "user_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
+            "bot_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
+            "bot_message_template_incomplete": "<|im_start|>{role}\n{content}",
+            "user_role": "user",
+            "bot_role": "assistant",
+            "system_role": "system",
+            "global_prefix": "",
+            "suffix": "<|im_start|>assistant\n",
+            "add_special_tokens": false,
+            "eos_token": "<|im_end|>"
+        },
+        "load_in_8bit": false,
+        "torch_dtype": "auto",
+        "use_flash_attention_2": true,
+        "device_map": "cuda:0",
+        "use_fast_tokenizer": true,
+        "leading_space": false,
+        "space_token": null,
+        "trust_remote_code": [
+            false
+        ],
+        "max_model_len": 32768
+    },
+    "task_params": {
+        "max_len": 4000,
+        "few_shot_count": 0,
+        "batch_size": 1,
+        "max_sample_per_dataset": 10000000000000,
+        "method": "calculate_tokens_proba"
+    }
+}

llmtf_eval_k0/darumeru_RCB_total.jsonl

@@ -0,0 +1,8 @@
+{
+    "task_name": "darumeru/RCB",
+    "results": {
+        "acc": 0.5181818181818182,
+        "f1_macro": 0.4329109928238468
+    },
+    "leaderboard_result": 0.4755464055028325
+}

llmtf_eval_k0/darumeru_RWSD_params.jsonl

@@ -0,0 +1,60 @@
+{
+    "custom_generation_config": null,
+    "model_params": {
+        "model_name_or_path": "Qwen/Qwen2-7B-Instruct",
+        "generation_config": {
+            "do_sample": true,
+            "eos_token_id": [
+                151645,
+                198,
+                271
+            ],
+            "max_length": 32768,
+            "max_new_tokens": 64,
+            "pad_token_id": 151643,
+            "stop_strings": [
+                "\n",
+                "\n\n"
+            ],
+            "temperature": 0.1,
+            "top_k": 40,
+            "top_p": 0.9,
+            "transformers_version": "4.38.2",
+            "trust_remote_code": [
+                false
+            ]
+        },
+        "conversation_template": {
+            "system_prompt": "",
+            "system_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
+            "user_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
+            "bot_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
+            "bot_message_template_incomplete": "<|im_start|>{role}\n{content}",
+            "user_role": "user",
+            "bot_role": "assistant",
+            "system_role": "system",
+            "global_prefix": "",
+            "suffix": "<|im_start|>assistant\n",
+            "add_special_tokens": false,
+            "eos_token": "<|im_end|>"
+        },
+        "load_in_8bit": false,
+        "torch_dtype": "auto",
+        "use_flash_attention_2": true,
+        "device_map": "cuda:0",
+        "use_fast_tokenizer": true,
+        "leading_space": false,
+        "space_token": null,
+        "trust_remote_code": [
+            false
+        ],
+        "max_model_len": 32768
+    },
+    "task_params": {
+        "max_len": 4000,
+        "few_shot_count": 0,
+        "batch_size": 1,
+        "max_sample_per_dataset": 10000000000000,
+        "method": "calculate_tokens_proba"
+    }
+}

llmtf_eval_k0/darumeru_RWSD_total.jsonl

@@ -0,0 +1,7 @@
+{
+    "task_name": "darumeru/RWSD",
+    "results": {
+        "acc": 0.6029411764705882
+    },
+    "leaderboard_result": 0.6029411764705882
+}

llmtf_eval_k0/darumeru_USE_params.jsonl

@@ -0,0 +1,60 @@
+{
+    "custom_generation_config": null,
+    "model_params": {
+        "model_name_or_path": "Qwen/Qwen2-7B-Instruct",
+        "generation_config": {
+            "do_sample": true,
+            "eos_token_id": [
+                151645,
+                198,
+                271
+            ],
+            "max_length": 32768,
+            "max_new_tokens": 64,
+            "pad_token_id": 151643,
+            "stop_strings": [
+                "\n",
+                "\n\n"
+            ],
+            "temperature": 0.1,
+            "top_k": 40,
+            "top_p": 0.9,
+            "transformers_version": "4.38.2",
+            "trust_remote_code": [
+                false
+            ]
+        },
+        "conversation_template": {
+            "system_prompt": "",
+            "system_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
+            "user_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
+            "bot_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
+            "bot_message_template_incomplete": "<|im_start|>{role}\n{content}",
+            "user_role": "user",
+            "bot_role": "assistant",
+            "system_role": "system",
+            "global_prefix": "",
+            "suffix": "<|im_start|>assistant\n",
+            "add_special_tokens": false,
+            "eos_token": "<|im_end|>"
+        },
+        "load_in_8bit": false,
+        "torch_dtype": "auto",
+        "use_flash_attention_2": true,
+        "device_map": "cuda:0",
+        "use_fast_tokenizer": true,
+        "leading_space": false,
+        "space_token": null,
+        "trust_remote_code": [
+            false
+        ],
+        "max_model_len": 32768
+    },
+    "task_params": {
+        "max_len": 4000,
+        "few_shot_count": 0,
+        "batch_size": 1,
+        "max_sample_per_dataset": 10000000000000,
+        "method": "generate"
+    }
+}

llmtf_eval_k0/darumeru_USE_total.jsonl

@@ -0,0 +1,7 @@
+{
+    "task_name": "darumeru/USE",
+    "results": {
+        "grade_norm": 0.153921568627451
+    },
+    "leaderboard_result": 0.153921568627451
+}

llmtf_eval_k0/darumeru_cp_para_en_params.jsonl

@@ -0,0 +1,60 @@
+{
+    "custom_generation_config": null,
+    "model_params": {
+        "model_name_or_path": "Qwen/Qwen2-7B-Instruct",
+        "generation_config": {
+            "do_sample": true,
+            "eos_token_id": [
+                151645,
+                198,
+                271
+            ],
+            "max_length": 32768,
+            "max_new_tokens": 1024,
+            "pad_token_id": 151643,
+            "stop_strings": [
+                "\n",
+                "\n\n"
+            ],
+            "temperature": 0.1,
+            "top_k": 40,
+            "top_p": 0.9,
+            "transformers_version": "4.38.2",
+            "trust_remote_code": [
+                false
+            ]
+        },
+        "conversation_template": {
+            "system_prompt": "",
+            "system_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
+            "user_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
+            "bot_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
+            "bot_message_template_incomplete": "<|im_start|>{role}\n{content}",
+            "user_role": "user",
+            "bot_role": "assistant",
+            "system_role": "system",
+            "global_prefix": "",
+            "suffix": "<|im_start|>assistant\n",
+            "add_special_tokens": false,
+            "eos_token": "<|im_end|>"
+        },
+        "load_in_8bit": false,
+        "torch_dtype": "auto",
+        "use_flash_attention_2": true,
+        "device_map": "cuda:0",
+        "use_fast_tokenizer": true,
+        "leading_space": false,
+        "space_token": null,
+        "trust_remote_code": [
+            false
+        ],
+        "max_model_len": 32768
+    },
+    "task_params": {
+        "max_len": 4000,
+        "few_shot_count": 0,
+        "batch_size": 1,
+        "max_sample_per_dataset": 10000000000000,
+        "method": "generate"
+    }
+}

llmtf_eval_k0/darumeru_cp_para_en_total.jsonl

@@ -0,0 +1,9 @@
+{
+    "task_name": "darumeru/cp_para_en",
+    "results": {
+        "symbol_per_token": 4.353034074577473,
+        "len": 0.9802575114789726,
+        "lcs": 0.9058441645642358
+    },
+    "leaderboard_result": 0.9058441645642358
+}

llmtf_eval_k0/darumeru_cp_para_ru_params.jsonl

@@ -0,0 +1,60 @@
+{
+    "custom_generation_config": null,
+    "model_params": {
+        "model_name_or_path": "Qwen/Qwen2-7B-Instruct",
+        "generation_config": {
+            "do_sample": true,
+            "eos_token_id": [
+                151645,
+                198,
+                271
+            ],
+            "max_length": 32768,
+            "max_new_tokens": 1024,
+            "pad_token_id": 151643,
+            "stop_strings": [
+                "\n",
+                "\n\n"
+            ],
+            "temperature": 0.1,
+            "top_k": 40,
+            "top_p": 0.9,
+            "transformers_version": "4.38.2",
+            "trust_remote_code": [
+                false
+            ]
+        },
+        "conversation_template": {
+            "system_prompt": "",
+            "system_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
+            "user_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
+            "bot_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
+            "bot_message_template_incomplete": "<|im_start|>{role}\n{content}",
+            "user_role": "user",
+            "bot_role": "assistant",
+            "system_role": "system",
+            "global_prefix": "",
+            "suffix": "<|im_start|>assistant\n",
+            "add_special_tokens": false,
+            "eos_token": "<|im_end|>"
+        },
+        "load_in_8bit": false,
+        "torch_dtype": "auto",
+        "use_flash_attention_2": true,
+        "device_map": "cuda:0",
+        "use_fast_tokenizer": true,
+        "leading_space": false,
+        "space_token": null,
+        "trust_remote_code": [
+            false
+        ],
+        "max_model_len": 32768
+    },
+    "task_params": {
+        "max_len": 4000,
+        "few_shot_count": 0,
+        "batch_size": 1,
+        "max_sample_per_dataset": 10000000000000,
+        "method": "generate"
+    }
+}

llmtf_eval_k0/darumeru_cp_para_ru_total.jsonl

@@ -0,0 +1,9 @@
+{
+    "task_name": "darumeru/cp_para_ru",
+    "results": {
+        "symbol_per_token": 2.654953066881009,
+        "len": 0.9876165527469303,
+        "lcs": 0.8268038045788856
+    },
+    "leaderboard_result": 0.8268038045788856
+}

llmtf_eval_k0/darumeru_cp_sent_en_params.jsonl

@@ -0,0 +1,60 @@
+{
+    "custom_generation_config": null,
+    "model_params": {
+        "model_name_or_path": "Qwen/Qwen2-7B-Instruct",
+        "generation_config": {
+            "do_sample": true,
+            "eos_token_id": [
+                151645,
+                198,
+                271
+            ],
+            "max_length": 32768,
+            "max_new_tokens": 128,
+            "pad_token_id": 151643,
+            "stop_strings": [
+                "\n",
+                "\n\n"
+            ],
+            "temperature": 0.1,
+            "top_k": 40,
+            "top_p": 0.9,
+            "transformers_version": "4.38.2",
+            "trust_remote_code": [
+                false
+            ]
+        },
+        "conversation_template": {
+            "system_prompt": "",
+            "system_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
+            "user_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
+            "bot_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
+            "bot_message_template_incomplete": "<|im_start|>{role}\n{content}",
+            "user_role": "user",
+            "bot_role": "assistant",
+            "system_role": "system",
+            "global_prefix": "",
+            "suffix": "<|im_start|>assistant\n",
+            "add_special_tokens": false,
+            "eos_token": "<|im_end|>"
+        },
+        "load_in_8bit": false,
+        "torch_dtype": "auto",
+        "use_flash_attention_2": true,
+        "device_map": "cuda:0",
+        "use_fast_tokenizer": true,
+        "leading_space": false,
+        "space_token": null,
+        "trust_remote_code": [
+            false
+        ],
+        "max_model_len": 32768
+    },
+    "task_params": {
+        "max_len": 4000,
+        "few_shot_count": 0,
+        "batch_size": 1,
+        "max_sample_per_dataset": 10000000000000,
+        "method": "generate"
+    }
+}

llmtf_eval_k0/darumeru_cp_sent_en_total.jsonl

@@ -0,0 +1,9 @@
+{
+    "task_name": "darumeru/cp_sent_en",
+    "results": {
+        "symbol_per_token": 4.31579408268585,
+        "len": 0.8895181009295375,
+        "lcs": 0.8825764242763656
+    },
+    "leaderboard_result": 0.8895181009295375
+}

llmtf_eval_k0/darumeru_cp_sent_ru_params.jsonl

@@ -0,0 +1,60 @@
+{
+    "custom_generation_config": null,
+    "model_params": {
+        "model_name_or_path": "Qwen/Qwen2-7B-Instruct",
+        "generation_config": {
+            "do_sample": true,
+            "eos_token_id": [
+                151645,
+                198,
+                271
+            ],
+            "max_length": 32768,
+            "max_new_tokens": 128,
+            "pad_token_id": 151643,
+            "stop_strings": [
+                "\n",
+                "\n\n"
+            ],
+            "temperature": 0.1,
+            "top_k": 40,
+            "top_p": 0.9,
+            "transformers_version": "4.38.2",
+            "trust_remote_code": [
+                false
+            ]
+        },
+        "conversation_template": {
+            "system_prompt": "",
+            "system_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
+            "user_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
+            "bot_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
+            "bot_message_template_incomplete": "<|im_start|>{role}\n{content}",
+            "user_role": "user",
+            "bot_role": "assistant",
+            "system_role": "system",
+            "global_prefix": "",
+            "suffix": "<|im_start|>assistant\n",
+            "add_special_tokens": false,
+            "eos_token": "<|im_end|>"
+        },
+        "load_in_8bit": false,
+        "torch_dtype": "auto",
+        "use_flash_attention_2": true,
+        "device_map": "cuda:0",
+        "use_fast_tokenizer": true,
+        "leading_space": false,
+        "space_token": null,
+        "trust_remote_code": [
+            false
+        ],
+        "max_model_len": 32768
+    },
+    "task_params": {
+        "max_len": 4000,
+        "few_shot_count": 0,
+        "batch_size": 1,
+        "max_sample_per_dataset": 10000000000000,
+        "method": "generate"
+    }
+}

llmtf_eval_k0/darumeru_cp_sent_ru_total.jsonl

@@ -0,0 +1,9 @@
+{
+    "task_name": "darumeru/cp_sent_ru",
+    "results": {
+        "symbol_per_token": 2.531882961858218,
+        "len": 0.9931991516400629,
+        "lcs": 0.9651252623970072
+    },
+    "leaderboard_result": 0.9931991516400629
+}

llmtf_eval_k0/darumeru_ruMMLU.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0efc9923721404aa22a0d7f16a5462d753529496db4794671bf3122a6e665f1e
+size 32250795

llmtf_eval_k0/darumeru_ruMMLU_params.jsonl

@@ -0,0 +1,60 @@
+{
+    "custom_generation_config": null,
+    "model_params": {
+        "model_name_or_path": "Qwen/Qwen2-7B-Instruct",
+        "generation_config": {
+            "do_sample": true,
+            "eos_token_id": [
+                151645,
+                198,
+                271
+            ],
+            "max_length": 32768,
+            "max_new_tokens": 64,
+            "pad_token_id": 151643,
+            "stop_strings": [
+                "\n",
+                "\n\n"
+            ],
+            "temperature": 0.1,
+            "top_k": 40,
+            "top_p": 0.9,
+            "transformers_version": "4.38.2",
+            "trust_remote_code": [
+                false
+            ]
+        },
+        "conversation_template": {
+            "system_prompt": "",
+            "system_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
+            "user_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
+            "bot_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
+            "bot_message_template_incomplete": "<|im_start|>{role}\n{content}",
+            "user_role": "user",
+            "bot_role": "assistant",
+            "system_role": "system",
+            "global_prefix": "",
+            "suffix": "<|im_start|>assistant\n",
+            "add_special_tokens": false,
+            "eos_token": "<|im_end|>"
+        },
+        "load_in_8bit": false,
+        "torch_dtype": "auto",
+        "use_flash_attention_2": true,
+        "device_map": "cuda:0",
+        "use_fast_tokenizer": true,
+        "leading_space": false,
+        "space_token": null,
+        "trust_remote_code": [
+            false
+        ],
+        "max_model_len": 32768
+    },
+    "task_params": {
+        "max_len": 4000,
+        "few_shot_count": 0,
+        "batch_size": 1,
+        "max_sample_per_dataset": 10000000000000,
+        "method": "calculate_tokens_proba"
+    }
+}

llmtf_eval_k0/darumeru_ruMMLU_total.jsonl

@@ -0,0 +1,7 @@
+{
+    "task_name": "darumeru/ruMMLU",
+    "results": {
+        "acc": 0.5755761747979646
+    },
+    "leaderboard_result": 0.5755761747979646
+}

llmtf_eval_k0/darumeru_ruOpenBookQA_params.jsonl

@@ -0,0 +1,60 @@
+{
+    "custom_generation_config": null,
+    "model_params": {
+        "model_name_or_path": "Qwen/Qwen2-7B-Instruct",
+        "generation_config": {
+            "do_sample": true,
+            "eos_token_id": [
+                151645,
+                198,
+                271
+            ],
+            "max_length": 32768,
+            "max_new_tokens": 64,
+            "pad_token_id": 151643,
+            "stop_strings": [
+                "\n",
+                "\n\n"
+            ],
+            "temperature": 0.1,
+            "top_k": 40,
+            "top_p": 0.9,
+            "transformers_version": "4.38.2",
+            "trust_remote_code": [
+                false
+            ]
+        },
+        "conversation_template": {
+            "system_prompt": "",
+            "system_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
+            "user_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
+            "bot_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
+            "bot_message_template_incomplete": "<|im_start|>{role}\n{content}",
+            "user_role": "user",
+            "bot_role": "assistant",
+            "system_role": "system",
+            "global_prefix": "",
+            "suffix": "<|im_start|>assistant\n",
+            "add_special_tokens": false,
+            "eos_token": "<|im_end|>"
+        },
+        "load_in_8bit": false,
+        "torch_dtype": "auto",
+        "use_flash_attention_2": true,
+        "device_map": "cuda:0",
+        "use_fast_tokenizer": true,
+        "leading_space": false,
+        "space_token": null,
+        "trust_remote_code": [
+            false
+        ],
+        "max_model_len": 32768
+    },
+    "task_params": {
+        "max_len": 4000,
+        "few_shot_count": 0,
+        "batch_size": 1,
+        "max_sample_per_dataset": 10000000000000,
+        "method": "calculate_tokens_proba"
+    }
+}

llmtf_eval_k0/darumeru_ruOpenBookQA_total.jsonl

@@ -0,0 +1,8 @@
+{
+    "task_name": "darumeru/ruOpenBookQA",
+    "results": {
+        "acc": 0.8178694158075601,
+        "f1_macro": 0.8177749093697874
+    },
+    "leaderboard_result": 0.8178221625886737
+}

llmtf_eval_k0/darumeru_ruTiE.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:218542d4729b8fc7384fae25ede4aade4276134a7c3af8d643ad7fb242f2dfc6
+size 12205558

llmtf_eval_k0/darumeru_ruTiE_params.jsonl

@@ -0,0 +1,60 @@
+{
+    "custom_generation_config": null,
+    "model_params": {
+        "model_name_or_path": "Qwen/Qwen2-7B-Instruct",
+        "generation_config": {
+            "do_sample": true,
+            "eos_token_id": [
+                151645,
+                198,
+                271
+            ],
+            "max_length": 32768,
+            "max_new_tokens": 64,
+            "pad_token_id": 151643,
+            "stop_strings": [
+                "\n",
+                "\n\n"
+            ],
+            "temperature": 0.1,
+            "top_k": 40,
+            "top_p": 0.9,
+            "transformers_version": "4.38.2",
+            "trust_remote_code": [
+                false
+            ]
+        },
+        "conversation_template": {
+            "system_prompt": "",
+            "system_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
+            "user_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
+            "bot_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
+            "bot_message_template_incomplete": "<|im_start|>{role}\n{content}",
+            "user_role": "user",
+            "bot_role": "assistant",
+            "system_role": "system",
+            "global_prefix": "",
+            "suffix": "<|im_start|>assistant\n",
+            "add_special_tokens": false,
+            "eos_token": "<|im_end|>"
+        },
+        "load_in_8bit": false,
+        "torch_dtype": "auto",
+        "use_flash_attention_2": true,
+        "device_map": "cuda:0",
+        "use_fast_tokenizer": true,
+        "leading_space": false,
+        "space_token": null,
+        "trust_remote_code": [
+            false
+        ],
+        "max_model_len": 32768
+    },
+    "task_params": {
+        "max_len": 4000,
+        "few_shot_count": 0,
+        "batch_size": 1,
+        "max_sample_per_dataset": 10000000000000,
+        "method": "calculate_tokens_proba"
+    }
+}

llmtf_eval_k0/darumeru_ruTiE_total.jsonl

@@ -0,0 +1,7 @@
+{
+    "task_name": "darumeru/ruTiE",
+    "results": {
+        "acc": 0.6348837209302326
+    },
+    "leaderboard_result": 0.6348837209302326
+}

llmtf_eval_k0/darumeru_ruWorldTree_params.jsonl

@@ -0,0 +1,60 @@
+{
+    "custom_generation_config": null,
+    "model_params": {
+        "model_name_or_path": "Qwen/Qwen2-7B-Instruct",
+        "generation_config": {
+            "do_sample": true,
+            "eos_token_id": [
+                151645,
+                198,
+                271
+            ],
+            "max_length": 32768,
+            "max_new_tokens": 64,
+            "pad_token_id": 151643,
+            "stop_strings": [
+                "\n",
+                "\n\n"
+            ],
+            "temperature": 0.1,
+            "top_k": 40,
+            "top_p": 0.9,
+            "transformers_version": "4.38.2",
+            "trust_remote_code": [
+                false
+            ]
+        },
+        "conversation_template": {
+            "system_prompt": "",
+            "system_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
+            "user_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
+            "bot_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
+            "bot_message_template_incomplete": "<|im_start|>{role}\n{content}",
+            "user_role": "user",
+            "bot_role": "assistant",
+            "system_role": "system",
+            "global_prefix": "",
+            "suffix": "<|im_start|>assistant\n",
+            "add_special_tokens": false,
+            "eos_token": "<|im_end|>"
+        },
+        "load_in_8bit": false,
+        "torch_dtype": "auto",
+        "use_flash_attention_2": true,
+        "device_map": "cuda:0",
+        "use_fast_tokenizer": true,
+        "leading_space": false,
+        "space_token": null,
+        "trust_remote_code": [
+            false
+        ],
+        "max_model_len": 32768
+    },
+    "task_params": {
+        "max_len": 4000,
+        "few_shot_count": 0,
+        "batch_size": 1,
+        "max_sample_per_dataset": 10000000000000,
+        "method": "calculate_tokens_proba"
+    }
+}

llmtf_eval_k0/darumeru_ruWorldTree_total.jsonl

@@ -0,0 +1,8 @@
+{
+    "task_name": "darumeru/ruWorldTree",
+    "results": {
+        "acc": 0.9047619047619048,
+        "f1_macro": 0.9043845651108326
+    },
+    "leaderboard_result": 0.9045732349363687
+}

llmtf_eval_k0/evaluation_log.txt

@@ -0,0 +1,273 @@
+INFO: 2024-07-12 13:32:20,716: llmtf.base.evaluator: Starting eval on ['darumeru/multiq', 'darumeru/parus', 'darumeru/rcb', 'darumeru/ruopenbookqa', 'darumeru/rutie', 'darumeru/ruworldtree', 'darumeru/rwsd', 'darumeru/use', 'russiannlp/rucola_custom']
+INFO: 2024-07-12 13:32:20,717: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [151645, 198, 271]
+INFO: 2024-07-12 13:32:20,717: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['\n', '\n\n']
+INFO: 2024-07-12 13:32:21,381: llmtf.base.evaluator: Starting eval on ['darumeru/rummlu']
+INFO: 2024-07-12 13:32:21,381: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [151645, 198, 271]
+INFO: 2024-07-12 13:32:21,381: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['\n', '\n\n']
+INFO: 2024-07-12 13:32:23,188: llmtf.base.evaluator: Starting eval on ['nlpcoreteam/rummlu']
+INFO: 2024-07-12 13:32:23,189: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [151645]
+INFO: 2024-07-12 13:32:23,189: llmtf.base.hfmodel: Updated generation_config.stop_strings: []
+INFO: 2024-07-12 13:32:24,860: llmtf.base.darumeru/MultiQ: Loading Dataset: 4.14s
+INFO: 2024-07-12 13:32:24,879: llmtf.base.evaluator: Starting eval on ['nlpcoreteam/enmmlu']
+INFO: 2024-07-12 13:32:24,879: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [151645]
+INFO: 2024-07-12 13:32:24,879: llmtf.base.hfmodel: Updated generation_config.stop_strings: []
+INFO: 2024-07-12 13:32:26,606: llmtf.base.evaluator: Starting eval on ['daru/treewayabstractive']
+INFO: 2024-07-12 13:32:26,607: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [151645, 198, 271]
+INFO: 2024-07-12 13:32:26,607: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['\n', '\n\n']
+INFO: 2024-07-12 13:32:28,649: llmtf.base.evaluator: Starting eval on ['daru/treewayextractive']
+INFO: 2024-07-12 13:32:28,649: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [151645]
+INFO: 2024-07-12 13:32:28,649: llmtf.base.hfmodel: Updated generation_config.stop_strings: []
+INFO: 2024-07-12 13:32:30,170: llmtf.base.darumeru/ruMMLU: Loading Dataset: 8.79s
+INFO: 2024-07-12 13:32:31,039: llmtf.base.evaluator: Starting eval on ['darumeru/cp_sent_ru', 'darumeru/cp_sent_en', 'darumeru/cp_para_ru', 'darumeru/cp_para_en']
+INFO: 2024-07-12 13:32:31,040: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [151645, 198, 271]
+INFO: 2024-07-12 13:32:31,040: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['\n', '\n\n']
+INFO: 2024-07-12 13:32:31,528: llmtf.base.daru/treewayabstractive: Loading Dataset: 4.92s
+INFO: 2024-07-12 13:32:33,602: llmtf.base.darumeru/cp_sent_ru: Loading Dataset: 2.56s
+INFO: 2024-07-12 13:32:41,690: llmtf.base.daru/treewayextractive: Loading Dataset: 13.04s
+INFO: 2024-07-12 13:34:36,781: llmtf.base.nlpcoreteam/enMMLU: Loading Dataset: 131.90s
+INFO: 2024-07-12 13:34:38,322: llmtf.base.nlpcoreteam/ruMMLU: Loading Dataset: 135.13s
+INFO: 2024-07-12 13:39:29,078: llmtf.base.darumeru/ruMMLU: Processing Dataset: 418.89s
+INFO: 2024-07-12 13:39:29,081: llmtf.base.darumeru/ruMMLU: Results for darumeru/ruMMLU:
+INFO: 2024-07-12 13:39:29,091: llmtf.base.darumeru/ruMMLU: {'acc': 0.5755761747979646}
+INFO: 2024-07-12 13:39:29,136: llmtf.base.evaluator: Ended eval
+INFO: 2024-07-12 13:39:29,141: llmtf.base.evaluator: 
+mean	darumeru/ruMMLU
+0.576	0.576
+INFO: 2024-07-12 13:42:34,523: llmtf.base.nlpcoreteam/enMMLU: Processing Dataset: 477.74s
+INFO: 2024-07-12 13:42:34,527: llmtf.base.nlpcoreteam/enMMLU: Results for nlpcoreteam/enMMLU:
+INFO: 2024-07-12 13:42:34,569: llmtf.base.nlpcoreteam/enMMLU:                                        metric
+subject                                      
+abstract_algebra                     0.490000
+anatomy                              0.585185
+astronomy                            0.743421
+business_ethics                      0.750000
+clinical_knowledge                   0.762264
+college_biology                      0.784722
+college_chemistry                    0.460000
+college_computer_science             0.630000
+college_mathematics                  0.420000
+college_medicine                     0.664740
+college_physics                      0.392157
+computer_security                    0.690000
+conceptual_physics                   0.697872
+econometrics                         0.570175
+electrical_engineering               0.689655
+elementary_mathematics               0.611111
+formal_logic                         0.507937
+global_facts                         0.440000
+high_school_biology                  0.809677
+high_school_chemistry                0.615764
+high_school_computer_science         0.780000
+high_school_european_history         0.812121
+high_school_geography                0.848485
+high_school_government_and_politics  0.911917
+high_school_macroeconomics           0.715385
+high_school_mathematics              0.488889
+high_school_microeconomics           0.802521
+high_school_physics                  0.456954
+high_school_psychology               0.858716
+high_school_statistics               0.675926
+high_school_us_history               0.828431
+high_school_world_history            0.848101
+human_aging                          0.686099
+human_sexuality                      0.755725
+international_law                    0.801653
+jurisprudence                        0.833333
+logical_fallacies                    0.815951
+machine_learning                     0.455357
+management                           0.776699
+marketing                            0.893162
+medical_genetics                     0.790000
+miscellaneous                        0.845466
+moral_disputes                       0.739884
+moral_scenarios                      0.422346
+nutrition                            0.774510
+philosophy                           0.742765
+prehistory                           0.746914
+professional_accounting              0.570922
+professional_law                     0.505215
+professional_medicine                0.687500
+professional_psychology              0.722222
+public_relations                     0.727273
+security_studies                     0.722449
+sociology                            0.870647
+us_foreign_policy                    0.870000
+virology                             0.542169
+world_religions                      0.801170
+INFO: 2024-07-12 13:42:34,577: llmtf.base.nlpcoreteam/enMMLU:                                    metric
+subject                                  
+STEM                             0.605084
+humanities                       0.723525
+other (business, health, misc.)  0.697765
+social sciences                  0.781293
+INFO: 2024-07-12 13:42:34,584: llmtf.base.nlpcoreteam/enMMLU: {'acc': 0.7019166707055704}
+INFO: 2024-07-12 13:42:34,616: llmtf.base.evaluator: Ended eval
+INFO: 2024-07-12 13:42:34,636: llmtf.base.evaluator: 
+mean	darumeru/ruMMLU	nlpcoreteam/enMMLU
+0.639	0.576	0.702
+INFO: 2024-07-12 13:42:36,791: llmtf.base.darumeru/cp_sent_ru: Processing Dataset: 603.17s
+INFO: 2024-07-12 13:42:36,793: llmtf.base.darumeru/cp_sent_ru: Results for darumeru/cp_sent_ru:
+INFO: 2024-07-12 13:42:36,798: llmtf.base.darumeru/cp_sent_ru: {'symbol_per_token': 2.531882961858218, 'len': 0.9931991516400629, 'lcs': 0.9651252623970072}
+INFO: 2024-07-12 13:42:36,799: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [151645, 198, 271]
+INFO: 2024-07-12 13:42:36,799: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['\n', '\n\n']
+INFO: 2024-07-12 13:42:38,975: llmtf.base.darumeru/cp_sent_en: Loading Dataset: 2.17s
+INFO: 2024-07-12 13:43:48,104: llmtf.base.nlpcoreteam/ruMMLU: Processing Dataset: 549.78s
+INFO: 2024-07-12 13:43:48,105: llmtf.base.nlpcoreteam/ruMMLU: Results for nlpcoreteam/ruMMLU:
+INFO: 2024-07-12 13:43:48,145: llmtf.base.nlpcoreteam/ruMMLU:                                        metric
+subject                                      
+abstract_algebra                     0.430000
+anatomy                              0.562963
+astronomy                            0.677632
+business_ethics                      0.660000
+clinical_knowledge                   0.600000
+college_biology                      0.597222
+college_chemistry                    0.390000
+college_computer_science             0.540000
+college_mathematics                  0.470000
+college_medicine                     0.554913
+college_physics                      0.372549
+computer_security                    0.660000
+conceptual_physics                   0.574468
+econometrics                         0.464912
+electrical_engineering               0.558621
+elementary_mathematics               0.576720
+formal_logic                         0.476190
+global_facts                         0.420000
+high_school_biology                  0.729032
+high_school_chemistry                0.512315
+high_school_computer_science         0.750000
+high_school_european_history         0.745455
+high_school_geography                0.717172
+high_school_government_and_politics  0.663212
+high_school_macroeconomics           0.615385
+high_school_mathematics              0.455556
+high_school_microeconomics           0.642857
+high_school_physics                  0.410596
+high_school_psychology               0.759633
+high_school_statistics               0.560185
+high_school_us_history               0.715686
+high_school_world_history            0.767932
+human_aging                          0.609865
+human_sexuality                      0.633588
+international_law                    0.710744
+jurisprudence                        0.611111
+logical_fallacies                    0.527607
+machine_learning                     0.348214
+management                           0.718447
+marketing                            0.769231
+medical_genetics                     0.610000
+miscellaneous                        0.688378
+moral_disputes                       0.638728
+moral_scenarios                      0.244693
+nutrition                            0.669935
+philosophy                           0.639871
+prehistory                           0.608025
+professional_accounting              0.390071
+professional_law                     0.410039
+professional_medicine                0.610294
+professional_psychology              0.542484
+public_relations                     0.618182
+security_studies                     0.653061
+sociology                            0.741294
+us_foreign_policy                    0.740000
+virology                             0.506024
+world_religions                      0.719298
+INFO: 2024-07-12 13:43:48,152: llmtf.base.nlpcoreteam/ruMMLU:                                    metric
+subject                                  
+STEM                             0.534062
+humanities                       0.601183
+other (business, health, misc.)  0.597866
+social sciences                  0.649315
+INFO: 2024-07-12 13:43:48,160: llmtf.base.nlpcoreteam/ruMMLU: {'acc': 0.5956063721324766}
+INFO: 2024-07-12 13:43:48,192: llmtf.base.evaluator: Ended eval
+INFO: 2024-07-12 13:43:48,197: llmtf.base.evaluator: 
+mean	darumeru/cp_sent_ru	darumeru/ruMMLU	nlpcoreteam/enMMLU	nlpcoreteam/ruMMLU
+0.717	0.993	0.576	0.702	0.596
+INFO: 2024-07-12 13:44:07,504: llmtf.base.darumeru/MultiQ: Processing Dataset: 702.63s
+INFO: 2024-07-12 13:44:07,507: llmtf.base.darumeru/MultiQ: Results for darumeru/MultiQ:
+INFO: 2024-07-12 13:44:07,511: llmtf.base.darumeru/MultiQ: {'f1': 0.23082049162131107, 'em': 0.13288718929254303}
+INFO: 2024-07-12 13:44:07,516: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [151645, 198, 271]
+INFO: 2024-07-12 13:44:07,516: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['\n', '\n\n']
+INFO: 2024-07-12 13:44:09,506: llmtf.base.darumeru/PARus: Loading Dataset: 1.99s
+INFO: 2024-07-12 13:44:15,843: llmtf.base.darumeru/PARus: Processing Dataset: 6.34s
+INFO: 2024-07-12 13:44:15,844: llmtf.base.darumeru/PARus: Results for darumeru/PARus:
+INFO: 2024-07-12 13:44:15,857: llmtf.base.darumeru/PARus: {'acc': 0.79}
+INFO: 2024-07-12 13:44:15,858: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [151645, 198, 271]
+INFO: 2024-07-12 13:44:15,858: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['\n', '\n\n']
+INFO: 2024-07-12 13:44:17,890: llmtf.base.darumeru/RCB: Loading Dataset: 2.03s
+INFO: 2024-07-12 13:44:26,535: llmtf.base.darumeru/RCB: Processing Dataset: 8.64s
+INFO: 2024-07-12 13:44:26,550: llmtf.base.darumeru/RCB: Results for darumeru/RCB:
+INFO: 2024-07-12 13:44:26,556: llmtf.base.darumeru/RCB: {'acc': 0.5181818181818182, 'f1_macro': 0.4329109928238468}
+INFO: 2024-07-12 13:44:26,557: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [151645, 198, 271]
+INFO: 2024-07-12 13:44:26,557: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['\n', '\n\n']
+INFO: 2024-07-12 13:44:29,227: llmtf.base.darumeru/ruOpenBookQA: Loading Dataset: 2.67s
+INFO: 2024-07-12 13:45:43,981: llmtf.base.darumeru/ruOpenBookQA: Processing Dataset: 74.75s
+INFO: 2024-07-12 13:45:43,996: llmtf.base.darumeru/ruOpenBookQA: Results for darumeru/ruOpenBookQA:
+INFO: 2024-07-12 13:45:44,008: llmtf.base.darumeru/ruOpenBookQA: {'acc': 0.8178694158075601, 'f1_macro': 0.8177749093697874}
+INFO: 2024-07-12 13:45:44,015: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [151645, 198, 271]
+INFO: 2024-07-12 13:45:44,015: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['\n', '\n\n']
+INFO: 2024-07-12 13:45:51,418: llmtf.base.darumeru/ruTiE: Loading Dataset: 7.40s
+INFO: 2024-07-12 13:50:12,621: llmtf.base.darumeru/ruTiE: Processing Dataset: 261.20s
+INFO: 2024-07-12 13:50:12,624: llmtf.base.darumeru/ruTiE: Results for darumeru/ruTiE:
+INFO: 2024-07-12 13:50:12,657: llmtf.base.darumeru/ruTiE: {'acc': 0.6348837209302326}
+INFO: 2024-07-12 13:50:12,660: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [151645, 198, 271]
+INFO: 2024-07-12 13:50:12,661: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['\n', '\n\n']
+INFO: 2024-07-12 13:50:15,001: llmtf.base.darumeru/ruWorldTree: Loading Dataset: 2.34s
+INFO: 2024-07-12 13:50:18,607: llmtf.base.darumeru/ruWorldTree: Processing Dataset: 3.60s
+INFO: 2024-07-12 13:50:18,609: llmtf.base.darumeru/ruWorldTree: Results for darumeru/ruWorldTree:
+INFO: 2024-07-12 13:50:18,614: llmtf.base.darumeru/ruWorldTree: {'acc': 0.9047619047619048, 'f1_macro': 0.9043845651108326}
+INFO: 2024-07-12 13:50:18,615: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [151645, 198, 271]
+INFO: 2024-07-12 13:50:18,615: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['\n', '\n\n']
+INFO: 2024-07-12 13:50:20,678: llmtf.base.darumeru/RWSD: Loading Dataset: 2.06s
+INFO: 2024-07-12 13:50:28,821: llmtf.base.darumeru/RWSD: Processing Dataset: 8.14s
+INFO: 2024-07-12 13:50:28,823: llmtf.base.darumeru/RWSD: Results for darumeru/RWSD:
+INFO: 2024-07-12 13:50:28,827: llmtf.base.darumeru/RWSD: {'acc': 0.6029411764705882}
+INFO: 2024-07-12 13:50:28,828: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [151645, 198, 271]
+INFO: 2024-07-12 13:50:28,828: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['\n', '\n\n']
+INFO: 2024-07-12 13:50:31,849: llmtf.base.darumeru/USE: Loading Dataset: 3.02s
+INFO: 2024-07-12 13:51:35,478: llmtf.base.darumeru/cp_sent_en: Processing Dataset: 536.50s
+INFO: 2024-07-12 13:51:35,480: llmtf.base.darumeru/cp_sent_en: Results for darumeru/cp_sent_en:
+INFO: 2024-07-12 13:51:35,484: llmtf.base.darumeru/cp_sent_en: {'symbol_per_token': 4.31579408268585, 'len': 0.8895181009295375, 'lcs': 0.8825764242763656}
+INFO: 2024-07-12 13:51:35,486: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [151645, 198, 271]
+INFO: 2024-07-12 13:51:35,486: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['\n', '\n\n']
+INFO: 2024-07-12 13:51:37,358: llmtf.base.darumeru/cp_para_ru: Loading Dataset: 1.87s
+INFO: 2024-07-12 13:55:22,257: llmtf.base.darumeru/USE: Processing Dataset: 290.41s
+INFO: 2024-07-12 13:55:22,261: llmtf.base.darumeru/USE: Results for darumeru/USE:
+INFO: 2024-07-12 13:55:22,266: llmtf.base.darumeru/USE: {'grade_norm': 0.153921568627451}
+INFO: 2024-07-12 13:55:22,269: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [151645]
+INFO: 2024-07-12 13:55:22,269: llmtf.base.hfmodel: Updated generation_config.stop_strings: []
+INFO: 2024-07-12 13:55:26,569: llmtf.base.russiannlp/rucola_custom: Loading Dataset: 4.30s
+INFO: 2024-07-12 13:56:58,317: llmtf.base.russiannlp/rucola_custom: Processing Dataset: 91.75s
+INFO: 2024-07-12 13:56:58,322: llmtf.base.russiannlp/rucola_custom: Results for russiannlp/rucola_custom:
+INFO: 2024-07-12 13:56:58,334: llmtf.base.russiannlp/rucola_custom: {'acc': 0.7072120559741658, 'mcc': 0.23883340451741628}
+INFO: 2024-07-12 13:56:58,338: llmtf.base.evaluator: Ended eval
+INFO: 2024-07-12 13:56:58,365: llmtf.base.evaluator: 
+mean	darumeru/MultiQ	darumeru/PARus	darumeru/RCB	darumeru/RWSD	darumeru/USE	darumeru/cp_sent_en	darumeru/cp_sent_ru	darumeru/ruMMLU	darumeru/ruOpenBookQA	darumeru/ruTiE	darumeru/ruWorldTree	nlpcoreteam/enMMLU	nlpcoreteam/ruMMLU	russiannlp/rucola_custom
+0.628	0.182	0.790	0.476	0.603	0.154	0.890	0.993	0.576	0.818	0.635	0.905	0.702	0.596	0.473
+INFO: 2024-07-12 13:58:57,546: llmtf.base.daru/treewayextractive: Processing Dataset: 1575.85s
+INFO: 2024-07-12 13:58:57,550: llmtf.base.daru/treewayextractive: Results for daru/treewayextractive:
+INFO: 2024-07-12 13:58:57,798: llmtf.base.daru/treewayextractive: {'r-prec': 0.3917012265512266}
+INFO: 2024-07-12 13:58:58,347: llmtf.base.evaluator: Ended eval
+INFO: 2024-07-12 13:58:58,375: llmtf.base.evaluator: 
+mean	daru/treewayextractive	darumeru/MultiQ	darumeru/PARus	darumeru/RCB	darumeru/RWSD	darumeru/USE	darumeru/cp_sent_en	darumeru/cp_sent_ru	darumeru/ruMMLU	darumeru/ruOpenBookQA	darumeru/ruTiE	darumeru/ruWorldTree	nlpcoreteam/enMMLU	nlpcoreteam/ruMMLU	russiannlp/rucola_custom
+0.612	0.392	0.182	0.790	0.476	0.603	0.154	0.890	0.993	0.576	0.818	0.635	0.905	0.702	0.596	0.473
+INFO: 2024-07-12 14:04:59,106: llmtf.base.darumeru/cp_para_ru: Processing Dataset: 801.75s
+INFO: 2024-07-12 14:04:59,122: llmtf.base.darumeru/cp_para_ru: Results for darumeru/cp_para_ru:
+INFO: 2024-07-12 14:04:59,126: llmtf.base.darumeru/cp_para_ru: {'symbol_per_token': 2.654953066881009, 'len': 0.9876165527469303, 'lcs': 0.8268038045788856}
+INFO: 2024-07-12 14:04:59,127: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [151645, 198, 271]
+INFO: 2024-07-12 14:04:59,127: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['\n', '\n\n']
+INFO: 2024-07-12 14:05:01,461: llmtf.base.darumeru/cp_para_en: Loading Dataset: 2.33s
+INFO: 2024-07-12 14:14:59,808: llmtf.base.darumeru/cp_para_en: Processing Dataset: 598.35s
+INFO: 2024-07-12 14:14:59,811: llmtf.base.darumeru/cp_para_en: Results for darumeru/cp_para_en:
+INFO: 2024-07-12 14:14:59,832: llmtf.base.darumeru/cp_para_en: {'symbol_per_token': 4.353034074577473, 'len': 0.9802575114789726, 'lcs': 0.9058441645642358}
+INFO: 2024-07-12 14:14:59,833: llmtf.base.evaluator: Ended eval
+INFO: 2024-07-12 14:14:59,844: llmtf.base.evaluator: 
+mean	daru/treewayextractive	darumeru/MultiQ	darumeru/PARus	darumeru/RCB	darumeru/RWSD	darumeru/USE	darumeru/cp_para_en	darumeru/cp_para_ru	darumeru/cp_sent_en	darumeru/cp_sent_ru	darumeru/ruMMLU	darumeru/ruOpenBookQA	darumeru/ruTiE	darumeru/ruWorldTree	nlpcoreteam/enMMLU	nlpcoreteam/ruMMLU	russiannlp/rucola_custom
+0.642	0.392	0.182	0.790	0.476	0.603	0.154	0.906	0.827	0.890	0.993	0.576	0.818	0.635	0.905	0.702	0.596	0.473
+INFO: 2024-07-12 14:37:23,690: llmtf.base.daru/treewayabstractive: Processing Dataset: 3892.16s
+INFO: 2024-07-12 14:37:23,708: llmtf.base.daru/treewayabstractive: Results for daru/treewayabstractive:
+INFO: 2024-07-12 14:37:23,718: llmtf.base.daru/treewayabstractive: {'rouge1': 0.2813082731366044, 'rouge2': 0.10129515826302848}
+INFO: 2024-07-12 14:37:23,720: llmtf.base.evaluator: Ended eval
+INFO: 2024-07-12 14:37:23,733: llmtf.base.evaluator: 
+mean	daru/treewayabstractive	daru/treewayextractive	darumeru/MultiQ	darumeru/PARus	darumeru/RCB	darumeru/RWSD	darumeru/USE	darumeru/cp_para_en	darumeru/cp_para_ru	darumeru/cp_sent_en	darumeru/cp_sent_ru	darumeru/ruMMLU	darumeru/ruOpenBookQA	darumeru/ruTiE	darumeru/ruWorldTree	nlpcoreteam/enMMLU	nlpcoreteam/ruMMLU	russiannlp/rucola_custom
+0.617	0.191	0.392	0.182	0.790	0.476	0.603	0.154	0.906	0.827	0.890	0.993	0.576	0.818	0.635	0.905	0.702	0.596	0.473

llmtf_eval_k0/evaluation_results.txt

@@ -0,0 +1,2 @@
+mean	daru/treewayabstractive	daru/treewayextractive	darumeru/MultiQ	darumeru/PARus	darumeru/RCB	darumeru/RWSD	darumeru/USE	darumeru/cp_para_en	darumeru/cp_para_ru	darumeru/cp_sent_en	darumeru/cp_sent_ru	darumeru/ruMMLU	darumeru/ruOpenBookQA	darumeru/ruTiE	darumeru/ruWorldTree	nlpcoreteam/enMMLU	nlpcoreteam/ruMMLU	russiannlp/rucola_custom
+0.617	0.191	0.392	0.182	0.790	0.476	0.603	0.154	0.906	0.827	0.890	0.993	0.576	0.818	0.635	0.905	0.702	0.596	0.473

llmtf_eval_k0/nlpcoreteam_enMMLU.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71000a11ac35e74385e8cbeb590e2ffe89f4803f551c6067edb7fceb2acaa051
+size 37162610

llmtf_eval_k0/nlpcoreteam_enMMLU_params.jsonl

@@ -0,0 +1,55 @@
+{
+    "custom_generation_config": null,
+    "model_params": {
+        "model_name_or_path": "Qwen/Qwen2-7B-Instruct",
+        "generation_config": {
+            "do_sample": true,
+            "eos_token_id": [
+                151645
+            ],
+            "max_length": 32768,
+            "max_new_tokens": 64,
+            "pad_token_id": 151643,
+            "stop_strings": [],
+            "temperature": 0.1,
+            "top_k": 40,
+            "top_p": 0.9,
+            "transformers_version": "4.38.2",
+            "trust_remote_code": [
+                false
+            ]
+        },
+        "conversation_template": {
+            "system_prompt": "",
+            "system_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
+            "user_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
+            "bot_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n",
+            "bot_message_template_incomplete": "<|im_start|>{role}\n{content}",
+            "user_role": "user",
+            "bot_role": "assistant",
+            "system_role": "system",
+            "global_prefix": "",
+            "suffix": "<|im_start|>assistant\n",
+            "add_special_tokens": false,
+            "eos_token": "<|im_end|>"
+        },
+        "load_in_8bit": false,
+        "torch_dtype": "auto",
+        "use_flash_attention_2": true,
+        "device_map": "cuda:0",
+        "use_fast_tokenizer": true,
+        "leading_space": false,
+        "space_token": null,
+        "trust_remote_code": [
+            false
+        ],
+        "max_model_len": 32768
+    },
+    "task_params": {
+        "max_len": 4000,
+        "few_shot_count": 0,
+        "batch_size": 1,
+        "max_sample_per_dataset": 10000000000000,
+        "method": "calculate_tokens_proba"
+    }
+}