Upload llama_7b_seq8k_bs2M_decay/0000005000/train_state_00060.json with huggingface_hub

llama_7b_seq8k_bs2M_decay/0000005000/train_state_00060.json

@@ -0,0 +1 @@
+{"step": 5000, "acc_step": 0, "data_loader_state": {"it_state": {"start_token": 812, "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.00060.jsonl", "position": 649484303, "block_size": 1, "offset": 0, "current_iter": 0}}, "rng_state": {"bit_generator": "PCG64", "state": {"state": 240259021855967893593744674848599512891, "inc": 180135128688417733083210763744005026881}, "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": 168563712934892809705331724839144252838, "inc": 295830431176996740215996940866944595183}, "has_uint32": 1, "uinteger": 4158749127}, "batch_size": 1, "prefetch_size": 1024}, "scheduler": {"base_lrs": [4e-05], "last_epoch": 5000, "verbose": false, "_step_count": 5001, "_get_lr_called_within_step": false, "_last_lr": [4e-05], "lr_lambdas": [{}]}}