Upload llama_1b_seq8k_bs2M_100B_gqa_64skyladder/0000030000/train_state_00032.json with huggingface_hub

llama_1b_seq8k_bs2M_100B_gqa_64skyladder/0000030000/train_state_00032.json

@@ -0,0 +1 @@
+{"step": 30000, "acc_step": 0, "data_loader_state": {"it_state": {"start_token": 1370, "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.00032.jsonl", "position": 3992310274, "block_size": 1, "offset": 0, "current_iter": 0}}, "rng_state": {"bit_generator": "PCG64", "state": {"state": 173726657538172990376386953257222287262, "inc": 69139510000717023814464056382053857141}, "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": 304, "rng_state": {"bit_generator": "PCG64", "state": {"state": 174696010309912305408395773457150901292, "inc": 202019553427190354279925986185519973319}, "has_uint32": 0, "uinteger": 2938286253}, "batch_size": 4, "prefetch_size": 1024}, "scheduler": {"base_lrs": [0.0004], "last_epoch": 30000, "verbose": false, "_step_count": 30001, "_get_lr_called_within_step": false, "_last_lr": [0.0004], "lr_lambdas": [{}]}}