Training Step 67500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be980c155e01ffcaf64c836045f9ff53ee0fdd86afba65707321436f11249ec1
+oid sha256:61eaea1ffab2112a77d00db91c7888b1474937eb02235ccb523c1592b5954f71
 size 26066332

trainer_state.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:141194112fffc701d45af92c45275b66596308eaa92b592d31d183ad3ab5b765
+oid sha256:a0477ecbc28b7d6636958bea3c37edd8cbed74cd73297e457c8b688341277aaa
 size 52140166

training_config.json

@@ -47,7 +47,7 @@
   "hf_api": "<huggingface_hub.hf_api.HfApi object at 0x14f5796b5150>",
   "wandb_writer": "<wandb.sdk.wandb_run.Run object at 0x14f5796fd7f0>",
   "wandb_table": "<wandb.sdk.data_types.table.Table object at 0x14f5796fe7b0>",
-  "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: 0.0003\n    lr: 5.876484878892085e-05\n    maximize: False\n    weight_decay: 0.05\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: 0.0003\n    lr: 3.394963419217409e-05\n    maximize: False\n    weight_decay: 0.05\n)",
   "scheduler": "<torch.optim.lr_scheduler.SequentialLR object at 0x14f5798c2660>",
   "optimizer_class": "adamw",
   "scheduler_class": "cosine",