Best model at Step 76565

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f249a61ed5b857d9f6f4f5bf8aba7934ee7248fb99fd801c3781447be9fd36f
+oid sha256:b0406f041522d528d310d070da5af56b77f14cdc681ed1c82ead6e15007967fe
 size 649331200

trainer_state.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6e808e8800d189f9efae7b76dcc39efa0cf37ebdd84bf43a39a543d64d76dd9
+oid sha256:50226c3e949ba129bfab3553428efaf206880175685968a2beb069389cc9f76b
 size 989959707

training_config.json

@@ -47,7 +47,7 @@
   "hf_api": "<huggingface_hub.hf_api.HfApi object at 0x14eae2909d00>",
   "wandb_writer": "<wandb.sdk.wandb_run.Run object at 0x14e8f2bc2270>",
   "wandb_table": "<wandb.sdk.data_types.table.Table object at 0x14eb411ba120>",
-  "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 0x14eae28baf90>",
   "optimizer_class": "adamw",
   "scheduler_class": "cosine",