Upload llama_7b_seq8k_bs2M_skyladder_decay/0000040000/train_state_00046.json with huggingface_hub

llama_7b_seq8k_bs2M_skyladder_decay/0000040000/train_state_00046.json

@@ -0,0 +1 @@
+{"step": 40000, "acc_step": 0, "data_loader_state": {"it_state": {"start_token": 1143, "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.00046.jsonl", "position": 5362283988, "block_size": 1, "offset": 0, "current_iter": 0}}, "rng_state": {"bit_generator": "PCG64", "state": {"state": 226811706610996610201835804354412990580, "inc": 216328329527095408858480720965542029775}, "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": 256, "rng_state": {"bit_generator": "PCG64", "state": {"state": 67148248140502787725522941409734596396, "inc": 332739318554936550888936484011639663327}, "has_uint32": 0, "uinteger": 2965018791}, "batch_size": 1, "prefetch_size": 1024}, "scheduler": {"base_lrs": [4e-05], "last_epoch": 40000, "verbose": false, "_step_count": 40001, "_get_lr_called_within_step": false, "_last_lr": [4e-05], "lr_lambdas": [{}]}}