Best model at Step 76565

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e806afbd891675287dc2df64d2cd88629b819f73510c1f1bdfae023a58acfd21
+oid sha256:2cba6184f3c6f694d863bb64a97597df969e38b06ed0afa179c44e3ec460dbf6
 size 445494204

trainer_state.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9031bcd1ff9814eb5f9f73edc427cda44c03f67a18cdc42918c0f8157ff1780c
+oid sha256:48e7c400db30151ba8f3d582cd512c172ad8808e7d54df163fc411d252d797fb
 size 890995910

training_config.json

@@ -47,7 +47,7 @@
   "hf_api": "<huggingface_hub.hf_api.HfApi object at 0x1483a37b1150>",
   "wandb_writer": "<wandb.sdk.wandb_run.Run object at 0x1483a26ed940>",
   "wandb_table": "<wandb.sdk.data_types.table.Table object at 0x1484249297f0>",
-  "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 0x1483a46ae7b0>",
   "optimizer_class": "adamw",
   "scheduler_class": "cosine",