Training Step 1260

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ae60708378fb8c0aac28a98aa9a483b6b52cc9a1fae88be1e8ba9dd2be77248
+oid sha256:a7a8d2cd2111c68f0d3015eaa0ee10f23aab39a1ef3b6fb39129b90a993ad6d6
 size 68876952

trainer_state.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38b6a24480759e2dc0c5204bdb0565079a141a499c54587c34c33d2b50e0efe9
+oid sha256:f44bfe39ab439a3176dbc1f7d28d90c2fb9c91f3fa7512683977be2246064664
 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: 2.7469758064516153e-06\n    maximize: False\n    weight_decay: 0.040001297063542884\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: 3.245967741935487e-06\n    maximize: False\n    weight_decay: 0.0400023071100874\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>",