Best model at Step 76565

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7883c9489e7d0f16fad0a02c5fa3b476f1cb15c061cc68a5f49c1f8f4d776b4
+oid sha256:0fe340a3651cc9b5c6441a64322e3d402d54b4bf9c687c63f6097020936ba09f
 size 105233332

trainer_state.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbc93eefeded0944e15cb3f516d4a67bcf76dee5e27e562c03cdc01067cba1a0
+oid sha256:84fb2d19e8e339b09e3246a7a72c0ed83e31369bbae751d2aa85d7ff4ab9ba94
 size 210474182

training_config.json

@@ -47,7 +47,7 @@
   "hf_api": "<huggingface_hub.hf_api.HfApi object at 0x15220b251150>",
   "wandb_writer": "<wandb.sdk.wandb_run.Run object at 0x15220b299940>",
   "wandb_table": "<wandb.sdk.data_types.table.Table object at 0x15220b29a900>",
-  "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: 1.5289315058583208e-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: 7.350326937918619e-06\n    maximize: False\n    weight_decay: 0.05\n)",
   "scheduler": "<torch.optim.lr_scheduler.SequentialLR object at 0x15220b40e7b0>",
   "optimizer_class": "adamw",
   "scheduler_class": "cosine",