Training Step 1575

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab03e3867772e7b8258f1161523dc5fbf8f5abf0d225a132a97fc7ccedd72828
+oid sha256:473cfc428df4f2a0421e08827c92d4cc7449a8160c59da4819cc4fcb2903f3cf
 size 124660456

trainer_state.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd7536abc57c0925c906be6d3143fc90669fa5a1459f6d1e795850f228155a3a
+oid sha256:1f720a15452755ce26249ed94b176af8e05c74d47eee60af0323e7390b650dd3
 size 215673699

training_config.json

@@ -61,7 +61,7 @@
   "hf_api": "<huggingface_hub.hf_api.HfApi object at 0x14e641e1e600>",
   "wandb_writer": "<wandb.sdk.wandb_run.Run object at 0x14e642ade690>",
   "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: 0.0002\n    lr: 1.4774193548387002e-05\n    maximize: False\n    weight_decay: 0.04003691257857578\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: 0.0002\n    lr: 1.796774193548379e-05\n    maximize: False\n    weight_decay: 0.040057693119629145\n)",
   "lr_scheduler": "<torch.optim.lr_scheduler.SequentialLR object at 0x14e642129e50>",
   "wd_scheduler": "<trainers.schedulers.weight_decay.WeightDecayScheduler object at 0x14e642129f40>",
   "momentum_scheduler": "<trainers.schedulers.momentum.MomentumScheduler object at 0x14e642129e80>",