Upload llama_7b_seq8k_bs2M_decay/0000040000/train_state_00063.json with huggingface_hub

llama_7b_seq8k_bs2M_decay/0000040000/train_state_00063.json

@@ -0,0 +1 @@
+{"step": 40000, "acc_step": 0, "data_loader_state": {"it_state": {"start_token": 14159, "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.00063.jsonl", "position": 5356869018, "block_size": 1, "offset": 0, "current_iter": 0}}, "rng_state": {"bit_generator": "PCG64", "state": {"state": 99278746417814426470249017238091221112, "inc": 212233488579996093995791538832249536073}, "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": 124603959267437779356481358906939117136, "inc": 116309495240665725662210951802735177975}, "has_uint32": 1, "uinteger": 813604231}, "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": [{}]}}