Best model at Step 1953

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:122d00eaf24ff70417426bb0511ba131fca6ec7347a2d0acdfca9ba2279a5a78
+oid sha256:4941b77d9529eb1630354819a0f3a97d64f964c4d2506e63cc67ba2687280aa2
 size 124660456

trainer_state.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecfd3e8045f9392f4cc785105af3e84e0c2ae3b7a0e95cc8d783e54ff51d0e89
+oid sha256:8adc1a21cd4089ad917dfc03ffc572a74b2520f810f174ec3cf1c6038cf1b747
 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: 2.116129032258056e-05\n    maximize: False\n    weight_decay: 0.04008309373244129\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: 2.179999999999991e-05\n    maximize: False\n    weight_decay: 0.0400887282083115\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>",