初始化项目，由ModelHub XC社区提供模型

Model: fava-uw/fava-model
Source: Original Platform

open_instruct/1694454900.079274/events.out.tfevents.1694454900.g3073.19792.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a52b51160518605bb4a367c6663100c28cb9ea35173d3848304eea8e6c581565
+size 1831

open_instruct/1694454900.0843773/hparams.yml

@@ -0,0 +1,32 @@
+checkpointing_steps: '50'
+config_name: null
+dataset_config_name: null
+dataset_name: null
+gradient_accumulation_steps: 16
+learning_rate: 2.0e-05
+logging_steps: 1
+lora_alpha: 16
+lora_dropout: 0.1
+lora_rank: 64
+low_cpu_mem_usage: false
+lr_scheduler_type: cosine
+max_seq_length: 2048
+max_train_steps: 550
+model_name_or_path: meta-llama/Llama-2-7b-chat-hf
+num_train_epochs: 2
+output_dir: multi_passage_w_qa
+overwrite_cache: false
+per_device_train_batch_size: 1
+preprocessing_num_workers: 16
+report_to: tensorboard
+resume_from_checkpoint: null
+save_merged_lora_model: false
+seed: null
+tokenizer_name: meta-llama/Llama-2-7b-chat-hf
+train_file: /gscratch/h2lab/abhikam/llm-factuality/data/training/open-instruct-multi-qa.json
+use_flash_attn: true
+use_lora: false
+use_slow_tokenizer: true
+warmup_ratio: 0.03
+weight_decay: 0.0
+with_tracking: true

open_instruct/1694473353.448148/events.out.tfevents.1694473353.g3057.74725.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a416f1323b83ccf64cef4a6e5115f7fb5422fe96c7430351aad5d473f796c45
+size 1916

open_instruct/1694473353.4580002/hparams.yml

@@ -0,0 +1,32 @@
+checkpointing_steps: '50'
+config_name: null
+dataset_config_name: null
+dataset_name: null
+gradient_accumulation_steps: 16
+learning_rate: 2.0e-05
+logging_steps: 1
+lora_alpha: 16
+lora_dropout: 0.1
+lora_rank: 64
+low_cpu_mem_usage: false
+lr_scheduler_type: cosine
+max_seq_length: 2048
+max_train_steps: 550
+model_name_or_path: meta-llama/Llama-2-7b-chat-hf
+num_train_epochs: 2
+output_dir: multi_passage_w_qa
+overwrite_cache: false
+per_device_train_batch_size: 1
+preprocessing_num_workers: 16
+report_to: tensorboard
+resume_from_checkpoint: multi_passage_w_qa/step_100
+save_merged_lora_model: false
+seed: null
+tokenizer_name: meta-llama/Llama-2-7b-chat-hf
+train_file: /gscratch/h2lab/abhikam/llm-factuality/data/training/open-instruct-multi-qa.json
+use_flash_attn: true
+use_lora: false
+use_slow_tokenizer: true
+warmup_ratio: 0.03
+weight_decay: 0.0
+with_tracking: true

open_instruct/1694473649.2233653/events.out.tfevents.1694473649.g3057.77254.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10b74c6f774d729b6af680f4e8ea767cfabf2df025cd74f71df9640b862dba10
+size 1916

open_instruct/1694473649.2345717/hparams.yml

@@ -0,0 +1,32 @@
+checkpointing_steps: '50'
+config_name: null
+dataset_config_name: null
+dataset_name: null
+gradient_accumulation_steps: 16
+learning_rate: 2.0e-05
+logging_steps: 1
+lora_alpha: 16
+lora_dropout: 0.1
+lora_rank: 64
+low_cpu_mem_usage: false
+lr_scheduler_type: cosine
+max_seq_length: 2048
+max_train_steps: 550
+model_name_or_path: meta-llama/Llama-2-7b-chat-hf
+num_train_epochs: 2
+output_dir: multi_passage_w_qa
+overwrite_cache: false
+per_device_train_batch_size: 1
+preprocessing_num_workers: 16
+report_to: tensorboard
+resume_from_checkpoint: multi_passage_w_qa/step_100
+save_merged_lora_model: false
+seed: null
+tokenizer_name: meta-llama/Llama-2-7b-chat-hf
+train_file: /gscratch/h2lab/abhikam/llm-factuality/data/training/open-instruct-multi-qa.json
+use_flash_attn: true
+use_lora: false
+use_slow_tokenizer: true
+warmup_ratio: 0.03
+weight_decay: 0.0
+with_tracking: true

open_instruct/1694499102.1265042/events.out.tfevents.1694499102.g3041.70110.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6035e9cf6d2060a3a51c046446e92541d4b25a490c3bda38eb864b7ee1efbc9
+size 1916

open_instruct/1694499102.1359086/hparams.yml

@@ -0,0 +1,32 @@
+checkpointing_steps: '50'
+config_name: null
+dataset_config_name: null
+dataset_name: null
+gradient_accumulation_steps: 16
+learning_rate: 2.0e-05
+logging_steps: 1
+lora_alpha: 16
+lora_dropout: 0.1
+lora_rank: 64
+low_cpu_mem_usage: false
+lr_scheduler_type: cosine
+max_seq_length: 2048
+max_train_steps: 550
+model_name_or_path: meta-llama/Llama-2-7b-chat-hf
+num_train_epochs: 2
+output_dir: multi_passage_w_qa
+overwrite_cache: false
+per_device_train_batch_size: 1
+preprocessing_num_workers: 16
+report_to: tensorboard
+resume_from_checkpoint: multi_passage_w_qa/step_250
+save_merged_lora_model: false
+seed: null
+tokenizer_name: meta-llama/Llama-2-7b-chat-hf
+train_file: /gscratch/h2lab/abhikam/llm-factuality/data/training/open-instruct-multi-qa.json
+use_flash_attn: true
+use_lora: false
+use_slow_tokenizer: true
+warmup_ratio: 0.03
+weight_decay: 0.0
+with_tracking: true

open_instruct/1694517340.2777019/events.out.tfevents.1694517340.g3043.20410.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52287e454a884daa449c4f4315dc8768890c0b0c5fdcfdd36f21a6d0026f475d
+size 1916

open_instruct/1694517340.3150113/hparams.yml

@@ -0,0 +1,32 @@
+checkpointing_steps: '50'
+config_name: null
+dataset_config_name: null
+dataset_name: null
+gradient_accumulation_steps: 16
+learning_rate: 2.0e-05
+logging_steps: 1
+lora_alpha: 16
+lora_dropout: 0.1
+lora_rank: 64
+low_cpu_mem_usage: false
+lr_scheduler_type: cosine
+max_seq_length: 2048
+max_train_steps: 550
+model_name_or_path: meta-llama/Llama-2-7b-chat-hf
+num_train_epochs: 2
+output_dir: multi_passage_w_qa
+overwrite_cache: false
+per_device_train_batch_size: 1
+preprocessing_num_workers: 16
+report_to: tensorboard
+resume_from_checkpoint: multi_passage_w_qa/step_400
+save_merged_lora_model: false
+seed: null
+tokenizer_name: meta-llama/Llama-2-7b-chat-hf
+train_file: /gscratch/h2lab/abhikam/llm-factuality/data/training/open-instruct-multi-qa.json
+use_flash_attn: true
+use_lora: false
+use_slow_tokenizer: true
+warmup_ratio: 0.03
+weight_decay: 0.0
+with_tracking: true

open_instruct/1694518076.1833658/events.out.tfevents.1694518076.g3043.23771.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0f450f6e7e4caa1407a2ad7d4d1a601ae6946ebe59c4fe8b924b0ed56a0ecbd
+size 1916

open_instruct/1694518076.2119565/hparams.yml

@@ -0,0 +1,32 @@
+checkpointing_steps: '50'
+config_name: null
+dataset_config_name: null
+dataset_name: null
+gradient_accumulation_steps: 16
+learning_rate: 2.0e-05
+logging_steps: 1
+lora_alpha: 16
+lora_dropout: 0.1
+lora_rank: 64
+low_cpu_mem_usage: false
+lr_scheduler_type: cosine
+max_seq_length: 2048
+max_train_steps: 550
+model_name_or_path: meta-llama/Llama-2-7b-chat-hf
+num_train_epochs: 2
+output_dir: multi_passage_w_qa
+overwrite_cache: false
+per_device_train_batch_size: 1
+preprocessing_num_workers: 16
+report_to: tensorboard
+resume_from_checkpoint: multi_passage_w_qa/step_400
+save_merged_lora_model: false
+seed: null
+tokenizer_name: meta-llama/Llama-2-7b-chat-hf
+train_file: /gscratch/h2lab/abhikam/llm-factuality/data/training/open-instruct-multi-qa.json
+use_flash_attn: true
+use_lora: false
+use_slow_tokenizer: true
+warmup_ratio: 0.03
+weight_decay: 0.0
+with_tracking: true

open_instruct/1694518380.1387873/events.out.tfevents.1694518380.g3043.25749.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5338826a2287655b7c7a2d302534670ad3cad3742b52f3e4fee44f4fb3373397
+size 1916

open_instruct/1694518380.279593/hparams.yml

@@ -0,0 +1,32 @@
+checkpointing_steps: '50'
+config_name: null
+dataset_config_name: null
+dataset_name: null
+gradient_accumulation_steps: 16
+learning_rate: 2.0e-05
+logging_steps: 1
+lora_alpha: 16
+lora_dropout: 0.1
+lora_rank: 64
+low_cpu_mem_usage: false
+lr_scheduler_type: cosine
+max_seq_length: 2048
+max_train_steps: 550
+model_name_or_path: meta-llama/Llama-2-7b-chat-hf
+num_train_epochs: 2
+output_dir: multi_passage_w_qa
+overwrite_cache: false
+per_device_train_batch_size: 1
+preprocessing_num_workers: 16
+report_to: tensorboard
+resume_from_checkpoint: multi_passage_w_qa/step_400
+save_merged_lora_model: false
+seed: null
+tokenizer_name: meta-llama/Llama-2-7b-chat-hf
+train_file: /gscratch/h2lab/abhikam/llm-factuality/data/training/open-instruct-multi-qa.json
+use_flash_attn: true
+use_lora: false
+use_slow_tokenizer: true
+warmup_ratio: 0.03
+weight_decay: 0.0
+with_tracking: true

open_instruct/events.out.tfevents.1694454899.g3073.19792.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f78aadb6ad02755c808b0772534583a6ead1b5c08241a0cefca5b33f5b53b1f1
+size 14681

open_instruct/events.out.tfevents.1694473353.g3057.74725.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf6c9632b71373703f0f87bdbdbe03c8c2112cc8e973a317cddffdfe014aa899
+size 290

open_instruct/events.out.tfevents.1694473649.g3057.77254.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b89d08fd51bc5b219476775fc54aaf11dba1f43fe62b6e7c375dbef275780b7
+size 19325

open_instruct/events.out.tfevents.1694499102.g3041.70110.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4677f0734a8c0a6b9fc733e6e820c7a92da2674e0d495347bc7833151c0fbb83
+size 20187

open_instruct/events.out.tfevents.1694517340.g3043.20410.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84c44ce55fde51eb2a2652665577f7cda24d784503bbb1d92e17ffea0031bc85
+size 189

open_instruct/events.out.tfevents.1694518076.g3043.23771.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e424e6dffbff8270f4a58b9664c65383e3af16612cbee5332b7c6fa0dea63a6
+size 88

open_instruct/events.out.tfevents.1694518380.g3043.25749.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94a1b7333712f79560c5d9cca5ccee9ca81c97fe377e6e7b8a20cc5c42a876ef
+size 15137