Upload llama_7b_seq8k_bs2M_skyladder_decay/0000045000/train_state_00041.json with huggingface_hub

llama_7b_seq8k_bs2M_skyladder_decay/0000045000/train_state_00041.json

@@ -0,0 +1 @@
+{"step": 45000, "acc_step": 0, "data_loader_state": {"it_state": {"start_token": 1817, "it_state": {"it_state": {"root_dir": "/mnt/hdfs/tiktok_aiic/user/liuqian", "sources": {"dclm_pro": 1.0}, "source_to_state": {"dclm_pro": {"file_path": "/mnt/hdfs/tiktok_aiic/user/liuqian/dclm_pro/dclm_pro.chunk.00041.jsonl", "position": 6015706918, "block_size": 1, "offset": 0, "current_iter": 0}}, "rng_state": {"bit_generator": "PCG64", "state": {"state": 180255924750324250844851372813249646193, "inc": 253108913021927798422538288190084620567}, "has_uint32": 0, "uinteger": 0}}, "add_bos": true, "add_eos": true, "name": "sp", "path": "/opt/tiger/Github-Repo/lingua/tokenizers/llama2/tokenizer.model"}, "output_seq_len": 8192, "n_views": 2}, "seq_idx": 800, "rng_state": {"bit_generator": "PCG64", "state": {"state": 164291735105728734136822301233204055131, "inc": 133211955349370476574874325691595993941}, "has_uint32": 1, "uinteger": 2160649054}, "batch_size": 1, "prefetch_size": 1024}, "scheduler": {"base_lrs": [4e-05], "last_epoch": 45000, "verbose": false, "_step_count": 45001, "_get_lr_called_within_step": false, "_last_lr": [4e-05], "lr_lambdas": [{}]}}