Training Step 630

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:747fdf3d9722e92ae28ef9fefa0815803d5e46e54cce55739f5e0b6c2a392488
+oid sha256:c4c47af170a8e817d39a01692a703c8b141ad58a682506e322bbeb18598c40bc
 size 68876952

trainer_state.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa6d76274ac195823f4be6592e1318cd565b93bcf7f457b511d1608dbe3412fc
+oid sha256:045355f224e6bbe500f259a66dc5a518537f943ff7171a0bef316d9704e62f02
 size 129403747

training_config.json

@@ -66,7 +66,7 @@
   "hf_api": "<huggingface_hub.hf_api.HfApi object at 0x14e5868dd3a0>",
   "wandb_writer": "<wandb.sdk.wandb_run.Run object at 0x14e57f3612e0>",
   "wandb_table": null,
-  "optimizer": "AdamW (\nParameter Group 0\n    amsgrad: False\n    betas: (0.9, 0.999)\n    capturable: False\n    decoupled_weight_decay: True\n    differentiable: False\n    eps: 1e-08\n    foreach: None\n    fused: None\n    initial_lr: 0.000125\n    lr: 1.7489919354838728e-06\n    maximize: False\n    weight_decay: 0.04000014350830139\n)",
+  "optimizer": "AdamW (\nParameter Group 0\n    amsgrad: False\n    betas: (0.9, 0.999)\n    capturable: False\n    decoupled_weight_decay: True\n    differentiable: False\n    eps: 1e-08\n    foreach: None\n    fused: None\n    initial_lr: 0.000125\n    lr: 2.2479838709677466e-06\n    maximize: False\n    weight_decay: 0.04000057586256178\n)",
   "lr_scheduler": "<torch.optim.lr_scheduler.SequentialLR object at 0x14e586a1dca0>",
   "wd_scheduler": "<trainers.schedulers.weight_decay.WeightDecayScheduler object at 0x14e57e241820>",
   "momentum_scheduler": "<trainers.schedulers.momentum.MomentumScheduler object at 0x14e57e241850>",