Delete configs/.ipynb_checkpoints

configs/.ipynb_checkpoints/pretrain_5090_stage1-checkpoint.json

@@ -1,27 +0,0 @@
-{
-  "seed": 42,
-  "train_dir": "data/pretokenized/train",
-  "val_dir": "data/pretokenized/val",
-  "output_dir": "outputs/pretrain_stage1",
-  "checkpoint_dir": "checkpoints/pretrain_stage1",
-  "init_from": null,
-  "resume_from": null,
-  "seq_len": 2048,
-  "micro_batch_size": 8,
-  "grad_accum_steps": 32,
-  "max_steps": 20000,
-  "warmup_steps": 2000,
-  "learning_rate": 0.003,
-  "min_lr": 0.0003,
-  "weight_decay": 0.1,
-  "beta1": 0.9,
-  "beta2": 0.95,
-  "grad_clip": 1.0,
-  "precision": "bf16",
-  "num_workers": 0,
-  "log_interval": 10,
-  "eval_interval": 250,
-  "eval_batches": 50,
-  "save_interval": 100,
-  "compile_model": false
-}

configs/.ipynb_checkpoints/pretrain_5090_stage2_anneal-checkpoint.json

@@ -1,27 +0,0 @@
-{
-  "seed": 42,
-  "train_dir": "data/pretokenized/train",
-  "val_dir": "data/pretokenized/val",
-  "output_dir": "outputs/pretrain_stage2",
-  "checkpoint_dir": "checkpoints/pretrain_stage2",
-  "init_from": "checkpoints/pretrain_stage1/last.pt",
-  "resume_from": null,
-  "seq_len": 8192,
-  "micro_batch_size": 2,
-  "grad_accum_steps": 16,
-  "max_steps": 1000,
-  "warmup_steps": 100,
-  "learning_rate": 0.001,
-  "min_lr": 0.0001,
-  "weight_decay": 0.1,
-  "beta1": 0.9,
-  "beta2": 0.95,
-  "grad_clip": 1.0,
-  "precision": "bf16",
-  "num_workers": 0,
-  "log_interval": 5,
-  "eval_interval": 100,
-  "eval_batches": 20,
-  "save_interval": 50,
-  "compile_model": false
-}