Upload llama_1b_seq8k_bs2M_100B_gqa_64skyladder/0000020000/train_state_00050.json with huggingface_hub

llama_1b_seq8k_bs2M_100B_gqa_64skyladder/0000020000/train_state_00050.json

@@ -0,0 +1 @@
+{"step": 20000, "acc_step": 0, "data_loader_state": {"it_state": {"start_token": 70, "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.00050.jsonl", "position": 2611356284, "block_size": 1, "offset": 0, "current_iter": 0}}, "rng_state": {"bit_generator": "PCG64", "state": {"state": 154208337936549272683208474753199359299, "inc": 10340472873057795476239454964766072259}, "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": 544, "rng_state": {"bit_generator": "PCG64", "state": {"state": 225476040017312635573888410638807031016, "inc": 116985742229375194186627932947822288687}, "has_uint32": 1, "uinteger": 3807714750}, "batch_size": 4, "prefetch_size": 1024}, "scheduler": {"base_lrs": [0.0004], "last_epoch": 20000, "verbose": false, "_step_count": 20001, "_get_lr_called_within_step": false, "_last_lr": [0.0004], "lr_lambdas": [{}]}}